netdata_patch_1_4_1: Add patch to run on Debian 10

In commit 4794f18bf4 ("sync: Sync .mailmap entries"), we updated the
sync-up script to automatically update libbpf's .mailmap; however, the
script would not take care of committing the changes. Let's address
this.

The code is copied and adapted from the part where we commit changes to
src/bpf_helper_defs.h.

Signed-off-by: Quentin Monnet <qmo@kernel.org>

.gitattributes

@@ -0,0 +1 @@
+assets/** export-ignore

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,3 @@
+Thank you for considering a contribution!
+
+Please note that the `libbpf` authoritative source code is developed as part of bpf-next Linux source tree under tools/lib/bpf subdirectory and is periodically synced to Github. As such, all the libbpf changes should be sent to BPF mailing list, please don't open PRs here unless you are changing Github-specific parts of libbpf (e.g., Github-specific Makefile).

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

@@ -0,0 +1,31 @@
+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: |
+        source $GITHUB_ACTION_PATH/../../../ci/vmtest/helpers.sh
+        foldable start "Setup Env"
+        sudo apt-get install -y qemu-kvm zstd binutils-dev elfutils libcap-dev libelf-dev libdw-dev python3-docutils
+        foldable end
+    - shell: bash
+      run: |
+        export KERNEL=${{ 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 +1,60 @@
+#!/bin/bash
+
+set -euo pipefail
+
+THISDIR="$(cd $(dirname $0) && pwd)"
+
+source ${THISDIR}/helpers.sh
+
+foldable start prepare_selftests "Building selftests"
+
+LIBBPF_PATH="${REPO_ROOT}"
+
+llvm_default_version() {
+	echo "16"
+}
+
+llvm_latest_version() {
+	echo "17"
+}
+
+LLVM_VERSION=$(llvm_default_version)
+if [[ "${LLVM_VERSION}" == $(llvm_latest_version) ]]; then
+	REPO_DISTRO_SUFFIX=""
+else
+	REPO_DISTRO_SUFFIX="-${LLVM_VERSION}"
+fi
+
+echo "deb https://apt.llvm.org/focal/ llvm-toolchain-focal${REPO_DISTRO_SUFFIX} main" \
+	| sudo tee /etc/apt/sources.list.d/llvm.list
+
+PREPARE_SELFTESTS_SCRIPT=${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 headers
+make \
+	CLANG=clang-${LLVM_VERSION} \
+	LLC=llc-${LLVM_VERSION} \
+	LLVM_STRIP=llvm-strip-${LLVM_VERSION} \
+	VMLINUX_BTF="${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
+
+foldable end prepare_selftests

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

@@ -0,0 +1,38 @@
+# shellcheck shell=bash
+
+# $1 - start or end
+# $2 - fold identifier, no spaces
+# $3 - fold section description
+foldable() {
+  local YELLOW='\033[1;33m'
+  local NOCOLOR='\033[0m'
+  if [ $1 = "start" ]; then
+    line="::group::$2"
+    if [ ! -z "${3:-}" ]; then
+      line="$line - ${YELLOW}$3${NOCOLOR}"
+    fi
+  else
+    line="::endgroup::"
+  fi
+  echo -e "$line"
+}
+
+__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

@@ -1,3 +1,5 @@
 #!/bin/bash
 
 printf "all:\n\ttouch bpf_testmod.ko\n\nclean:\n" > bpf_testmod/Makefile
+printf "all:\n\ttouch bpf_test_no_cfi.ko\n\nclean:\n" > bpf_test_no_cfi/Makefile
+

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

@@ -1,3 +1,5 @@
 #!/bin/bash
 
 printf "all:\n\ttouch bpf_testmod.ko\n\nclean:\n" > bpf_testmod/Makefile
+printf "all:\n\ttouch bpf_test_no_cfi.ko\n\nclean:\n" > bpf_test_no_cfi/Makefile
+

.github/actions/setup/action.yml

@@ -6,17 +6,17 @@ runs:
     - id: variables
       run: |
         export REPO_ROOT=$GITHUB_WORKSPACE
-        export CI_ROOT=$REPO_ROOT/travis-ci
+        export CI_ROOT=$REPO_ROOT/ci
         # this is somewhat ugly, but that is the easiest way to share this code with
         # arch specific docker
         echo 'echo ::group::Env setup' > /tmp/ci_setup
         echo export DEBIAN_FRONTEND=noninteractive >> /tmp/ci_setup
         echo sudo apt-get update >> /tmp/ci_setup
-        echo sudo apt-get install -y aptitude qemu-kvm zstd binutils-dev elfutils libcap-dev libelf-dev libdw-dev >> /tmp/ci_setup
+        echo sudo apt-get install -y aptitude qemu-kvm zstd binutils-dev elfutils libcap-dev libelf-dev libdw-dev libguestfs-tools >> /tmp/ci_setup
         echo export PROJECT_NAME='libbpf' >> /tmp/ci_setup
         echo export AUTHOR_EMAIL="$(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 CI_ROOT=$REPO_ROOT/ci >> /tmp/ci_setup
         echo export VMTEST_ROOT=$CI_ROOT/vmtest >> /tmp/ci_setup
         echo 'echo ::endgroup::' >> /tmp/ci_setup
       shell: bash

.github/actions/vmtest/action.yml

@@ -5,31 +5,114 @@ inputs:
     description: 'kernel version or LATEST'
     required: true
     default: 'LATEST'
-  kernel-rev:
-    description: 'CHECKPOINT or rev/tag/branch'
+  arch:
+    description: 'what arch to test'
     required: true
-    default: 'CHECKPOINT'
-  kernel-origin:
-    description: 'kernel repo'
-    required: true
-    default: 'https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git'
+    default: 'x86_64'
   pahole:
-    description: 'pahole rev/tag/branch'
+    description: 'pahole rev or master'
     required: true
     default: 'master'
-  pahole-origin:
-    description: 'pahole repo'
-    required: true
-    default: 'https://git.kernel.org/pub/scm/devel/pahole/pahole.git'
 runs:
   using: "composite"
   steps:
-    - run: |
-        source /tmp/ci_setup
-        export KERNEL=${{ inputs.kernel }}
-        export KERNEL_BRANCH=${{ inputs.kernel-rev }}
-        export KERNEL_ORIGIN=${{ inputs.kernel-origin }}
-        export PAHOLE_BRANCH=${{ inputs.pahole }}
-        export PAHOLE_ORIGIN=${{ inputs.pahole-origin }}
-        $CI_ROOT/vmtest/run_vmtest.sh
+    # Allow CI user to access /dev/kvm (via qemu) w/o group change/relogin
+    # by changing permissions set by udev.
+    - name: Set /dev/kvm permissions
       shell: bash
+      run: |
+        if [ -e /dev/kvm ]; then
+          echo "/dev/kvm exists"
+          if [ $(id -u) != 0 ]; then
+            echo 'KERNEL=="kvm", GROUP="kvm", MODE="0666", OPTIONS+="static_node=kvm"' \
+              | sudo tee /etc/udev/rules.d/99-kvm4all.rules > /dev/null
+            sudo udevadm control --reload-rules
+            sudo udevadm trigger --name-match=kvm
+          fi
+        else
+          echo "/dev/kvm does not exist"
+        fi
+    # setup environment
+    - name: Setup environment
+      uses: libbpf/ci/setup-build-env@main
+      with:
+        pahole: ${{ inputs.pahole }}
+        arch: ${{ inputs.arch }}
+    # 1. download CHECKPOINT kernel source
+    - name: Get checkpoint commit
+      shell: bash
+      run: |
+        cat CHECKPOINT-COMMIT
+        echo "CHECKPOINT=$(cat CHECKPOINT-COMMIT)" >> $GITHUB_ENV
+    - name: Get kernel source at checkpoint
+      uses: libbpf/ci/get-linux-source@main
+      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@main
+      with:
+        patches-root: '${{ github.workspace }}/ci/diffs'
+        repo-root: '.kernel'
+    - name: Prepare to build BPF selftests
+      shell: bash
+      run: |
+        source $GITHUB_ACTION_PATH/../../../ci/vmtest/helpers.sh
+        foldable start "Prepare building selftest"
+        cd .kernel
+        cat tools/testing/selftests/bpf/config \
+            tools/testing/selftests/bpf/config.${{ inputs.arch }} > .config
+        # this file might or mihgt not exist depending on kernel version
+        cat tools/testing/selftests/bpf/config.vm >> .config || :
+        make olddefconfig && make prepare
+        cd -
+        foldable end
+    # 2. if kernel == LATEST, build kernel image from tree
+    - name: Build kernel image
+      if: ${{ inputs.kernel == 'LATEST' }}
+      shell: bash
+      run: |
+        source $GITHUB_ACTION_PATH/../../../ci/vmtest/helpers.sh
+        foldable start "Build Kernel Image"
+        cd .kernel
+        make -j $((4*$(nproc))) all > /dev/null
+        cp vmlinux ${{ github.workspace }}
+        cd -
+        foldable end
+    # else, just download prebuilt kernel image
+    - name: Download prebuilt kernel
+      if: ${{ inputs.kernel != 'LATEST' }}
+      uses: libbpf/ci/download-vmlinux@main
+      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@main
+      env:
+        KBUILD_OUTPUT: '.kernel'
+      with:
+        project-name: 'libbpf'
+        arch: ${{ inputs.arch }}
+        kernel: ${{ inputs.kernel }}
+        kernel-root: '.kernel'
+        kbuild-output: ${{ env.KBUILD_OUTPUT }}
+        image-output: '/tmp/root.img'
+    # 5. run selftest in QEMU
+    - name: Run selftests
+      env:
+        KERNEL: ${{ inputs.kernel }}
+        REPO_ROOT: ${{ github.workspace }}
+      uses: libbpf/ci/run-qemu@main
+      with:
+        arch: ${{ inputs.arch }}
+        img: '/tmp/root.img'
+        vmlinuz: 'vmlinuz'
+        kernel-root: '.kernel'

.github/workflows/build.yml

@@ -0,0 +1,91 @@
+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 ASan+UBSan
+            target: RUN_CLANG_ASAN
+          - name: gcc-10 ASan+UBSan
+            target: RUN_GCC10_ASAN
+          - name: clang
+            target: RUN_CLANG
+          - name: clang-14
+            target: RUN_CLANG14
+          - name: clang-15
+            target: RUN_CLANG15
+          - name: clang-16
+            target: RUN_CLANG16
+          - name: gcc-10
+            target: RUN_GCC10
+          - name: gcc-11
+            target: RUN_GCC11
+          - name: gcc-12
+            target: RUN_GCC12
+    steps:
+      - uses: actions/checkout@v4
+        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@v4
+        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@v2.7.1
+        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/codeql.yml

@@ -0,0 +1,52 @@
+---
+# vi: ts=2 sw=2 et:
+
+name: "CodeQL"
+
+on:
+  push:
+    branches:
+      - master
+  pull_request:
+    branches:
+      - master
+
+permissions:
+  contents: read
+
+jobs:
+  analyze:
+    name: Analyze
+    runs-on: ubuntu-22.04
+    concurrency:
+      group: ${{ github.workflow }}-${{ matrix.language }}-${{ github.ref }}
+      cancel-in-progress: true
+    permissions:
+      actions: read
+      security-events: write
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language: ['cpp', 'python']
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Initialize CodeQL
+        uses: github/codeql-action/init@v2
+        with:
+          languages: ${{ matrix.language }}
+          queries: +security-extended,security-and-quality
+
+      - name: Setup
+        uses: ./.github/actions/setup
+
+      - name: Build
+        run: |
+          source /tmp/ci_setup
+          make -C ./src
+
+      - name: Perform CodeQL Analysis
+        uses: github/codeql-action/analyze@v2

.github/workflows/coverity.yml

@@ -11,16 +11,17 @@ jobs:
     if: github.repository == 'libbpf/libbpf'
     name: Coverity
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - uses: ./.github/actions/setup
       - name: Run coverity
         run: |
-          echo ::group::Setup CI env
+          source "${GITHUB_WORKSPACE}"/ci/vmtest/helpers.sh
+          foldable start "Setup CI env"
           source /tmp/ci_setup
           export COVERITY_SCAN_NOTIFICATION_EMAIL="${AUTHOR_EMAIL}"
           export COVERITY_SCAN_BRANCH_PATTERN=${GITHUB_REF##refs/*/}
           export TRAVIS_BRANCH=${COVERITY_SCAN_BRANCH_PATTERN}
-          echo ::endgroup::
+          foldable end
           scripts/coverity.sh
         env:
           COVERITY_SCAN_TOKEN: ${{ secrets.COVERITY_SCAN_TOKEN }}

.github/workflows/lint.yml

@@ -0,0 +1,19 @@
+name: "lint"
+
+on:
+  pull_request:
+  push:
+    branches:
+      - master
+
+jobs:
+  shellcheck:
+    name: ShellCheck
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+      - name: Run ShellCheck
+        uses: ludeeus/action-shellcheck@master
+        env:
+          SHELLCHECK_OPTS: --severity=error

.github/workflows/ondemand.yml

@@ -25,7 +25,7 @@ jobs:
     runs-on: ubuntu-latest
     name: vmtest with customized pahole/Kernel
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - uses: ./.github/actions/setup
       - uses: ./.github/actions/vmtest
         with:

.github/workflows/pahole.yml

@@ -7,12 +7,12 @@ on:
 
 jobs:
   vmtest:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-20.04
     name: Kernel LATEST + staging pahole
     env:
       STAGING: tmp.master
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - uses: ./.github/actions/setup
       - uses: ./.github/actions/vmtest
         with:

.github/workflows/test.yml

@@ -12,17 +12,26 @@ concurrency:
 
 jobs:
   vmtest:
-    runs-on: ubuntu-latest
-    name: Kernel ${{ matrix.kernel }} + selftests
+    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-20.04
+            arch: 'x86_64'
           - kernel: '5.5.0'
+            runs_on: ubuntu-20.04
+            arch: 'x86_64'
           - kernel: '4.9.0'
+            runs_on: ubuntu-20.04
+            arch: 'x86_64'
+          - kernel: 'LATEST'
+            runs_on: s390x
+            arch: 's390x'
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
         name: Checkout
       - uses: ./.github/actions/setup
         name: Setup
@@ -30,71 +39,4 @@ jobs:
         name: vmtest
         with:
           kernel: ${{ matrix.kernel }}
-
-  debian:
-    runs-on: ubuntu-latest
-    name: Debian Build (${{ 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
+          arch: ${{ matrix.arch }}

.lgtm.yml

@@ -1,14 +0,0 @@
-# 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

.mailmap

@@ -0,0 +1,17 @@
+Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com>
+Antoine Tenart <atenart@kernel.org> <antoine.tenart@bootlin.com>
+Benjamin Tissoires <bentiss@kernel.org> <benjamin.tissoires@redhat.com>
+Björn Töpel <bjorn@kernel.org> <bjorn.topel@intel.com>
+Changbin Du <changbin.du@intel.com> <changbin.du@gmail.com>
+Colin Ian King <colin.i.king@gmail.com> <colin.king@canonical.com>
+Dan Carpenter <error27@gmail.com> <dan.carpenter@oracle.com>
+Geliang Tang <geliang@kernel.org> <geliang.tang@suse.com>
+Herbert Xu <herbert@gondor.apana.org.au>
+Jakub Kicinski <kuba@kernel.org> <jakub.kicinski@netronome.com>
+Leo Yan <leo.yan@linux.dev> <leo.yan@linaro.org>
+Mark Starovoytov <mstarovo@pm.me> <mstarovoitov@marvell.com>
+Maxim Mikityanskiy <maxtram95@gmail.com> <maximmi@mellanox.com>
+Maxim Mikityanskiy <maxtram95@gmail.com> <maximmi@nvidia.com>
+Quentin Monnet <qmo@kernel.org> <quentin@isovalent.com>
+Quentin Monnet <qmo@kernel.org> <quentin.monnet@netronome.com>
+Vadim Fedorenko <vadim.fedorenko@linux.dev> <vfedorenko@novek.ru>

.readthedocs.yaml

@@ -5,13 +5,22 @@
 # Required
 version: 2
 
+build:
+  os: "ubuntu-22.04"
+  tools:
+    python: "3.11"
+
 # Build documentation in the docs/ directory with Sphinx
 sphinx:
   builder: html
   configuration: docs/conf.py
 
+formats:
+  - htmlzip
+  - pdf
+  - epub
+
 # Optionally set the version of Python and requirements required to build your docs
 python:
-   version: 3.7
    install:
-   - requirements: docs/sphinx/requirements.txt
+   - requirements: docs/sphinx/requirements.txt

.travis.yml

@@ -1,130 +0,0 @@
-sudo: required
-language: bash
-dist: focal
-services:
-    - docker
-
-env:
-    global:
-        - 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: 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 $CI_ROOT/managers/ubuntu.sh || travis_terminate 1
-
-        - stage: Coverity
-          language: bash
-          env:
-              # Coverity configuration
-              # COVERITY_SCAN_TOKEN=xxx
-              # Encrypted using `travis encrypt --repo libbpf/libbpf COVERITY_SCAN_TOKEN=xxx`
-              - secure: "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"
-              - COVERITY_SCAN_PROJECT_NAME="libbpf"
-              - COVERITY_SCAN_NOTIFICATION_EMAIL="${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:
-              - 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:
-              - scripts/coverity.sh || travis_terminate 1
-    allow_failures:
-        - env: KERNEL=x.x.x

BPF-CHECKPOINT-COMMIT

@@ -1 +1 @@
-47b3708c6088a60e7dc3b809dbb0d4c46590b32f
+3e9bc0472b910d4115e16e9c2d684c7757cb6c60

CHECKPOINT-COMMIT

@@ -1 +1 @@
-b8b5cb55f5d3f03cc1479a3768d68173a10359ad
+0737df6de94661ae55fd3343ce9abec32c687e62

LICENSE.BSD-2-Clause

@@ -7,7 +7,7 @@ Usage-Guide:
     SPDX-License-Identifier: BSD-2-Clause
 License-Text:
 
-Copyright (c) <year> <owner> . All rights reserved.
+Copyright (c) 2015 The Libbpf Authors. All rights reserved.
 
 Redistribution and use in source and binary forms, with or without
 modification, are permitted provided that the following conditions are met:

README.md

@@ -1,17 +1,33 @@
-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.
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="assets/libbpf-logo-sideways-darkbg.png" width="40%">
+  <img src="assets/libbpf-logo-sideways.png" width="40%">
+</picture>
 
-All the gory details of syncing can be found in `scripts/sync-kernel.sh`
-script.
+libbpf
+[![Github Actions Builds & Tests](https://github.com/libbpf/libbpf/actions/workflows/test.yml/badge.svg)](https://github.com/libbpf/libbpf/actions/workflows/test.yml)
+[![Coverity](https://img.shields.io/coverity/scan/18195.svg)](https://scan.coverity.com/projects/libbpf)
+[![CodeQL](https://github.com/libbpf/libbpf/workflows/CodeQL/badge.svg?branch=master)](https://github.com/libbpf/libbpf/actions?query=workflow%3ACodeQL+branch%3Amaster)
+[![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)
+[![Read the Docs](https://readthedocs.org/projects/libbpf/badge/?version=latest)](https://libbpf.readthedocs.io/en/latest/)
+======
 
-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.
+**This is the official home of the libbpf library.**
 
-BPF/libbpf usage and questions
-==============================
+*Please use this Github repository for building and packaging libbpf
+and when using it in your projects through Git submodule.*
+
+Libbpf *authoritative source code* is developed as part of [bpf-next Linux source
+tree](https://kernel.googlesource.com/pub/scm/linux/kernel/git/bpf/bpf-next) under
+`tools/lib/bpf` subdirectory and is periodically synced to Github. As such, all the
+libbpf changes should be sent to [BPF mailing list](http://vger.kernel.org/vger-lists.html#bpf),
+please don't open PRs here unless you are changing Github-specific parts of libbpf
+(e.g., Github-specific Makefile).
+
+Libbpf and general BPF usage questions
+======================================
+
+Libbpf documentation can be found [here](https://libbpf.readthedocs.io/en/latest/api.html).
+It's an ongoing effort and has ways to go, but please take a look and consider contributing as well.
 
 Please check out [libbpf-bootstrap](https://github.com/libbpf/libbpf-bootstrap)
 and [the companion blog post](https://nakryiko.com/posts/libbpf-bootstrap/) for
@@ -36,12 +52,8 @@ 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)
-=====
+Building 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
@@ -73,34 +85,6 @@ $ cd src
 $ PKG_CONFIG_PATH=/build/root/lib64/pkgconfig DESTDIR=/build/root make install
 ```
 
-Distributions
-=============
-
-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/groovy/libbpf)
-  - [Alpine](https://pkgs.alpinelinux.org/packages?name=libbpf)
-
-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)
 =========================================
 
@@ -154,6 +138,48 @@ use it:
   converting some more to both contribute to the BPF community and gain some
   more experience with it.
 
+Distributions
+=============
+
+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://archlinux.org/packages/core/x86_64/libbpf/)
+  - [Ubuntu](https://packages.ubuntu.com/source/jammy/libbpf)
+  - [Alpine](https://pkgs.alpinelinux.org/packages?name=libbpf)
+
+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
+    [GitHub Actions](https://github.com/libbpf/libbpf/actions).
+  - 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
+
+[![libbpf distro packaging status](https://repology.org/badge/vertical-allrepos/libbpf.svg)](https://repology.org/project/libbpf/versions)
+
+
+bpf-next to Github sync
+=======================
+
+All the gory details of syncing can be found in `scripts/sync-kernel.sh`
+script. See [SYNC.md](SYNC.md) for instruction.
+
+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.
+
 License
 =======
 

SYNC.md

@@ -0,0 +1,281 @@
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="assets/libbpf-logo-sideways-darkbg.png" width="40%">
+  <img src="assets/libbpf-logo-sideways.png" width="40%">
+</picture>
+
+Libbpf sync
+===========
+
+Libbpf *authoritative source code* is developed as part of [bpf-next Linux source
+tree](https://kernel.googlesource.com/pub/scm/linux/kernel/git/bpf/bpf-next) under
+`tools/lib/bpf` subdirectory and is periodically synced to Github.
+
+Most of the mundane mechanical things like bpf and bpf-next tree merge, Git
+history transformation, cherry-picking relevant commits, re-generating
+auto-generated headers, etc. are taken care by
+[sync-kernel.sh script](https://github.com/libbpf/libbpf/blob/master/scripts/sync-kernel.sh).
+But occasionally human needs to do few extra things to make everything work
+nicely.
+
+This document goes over the process of syncing libbpf sources from Linux repo
+to this Github repository. Feel free to contribute fixes and additions if you
+run into new problems not outlined here.
+
+Setup expectations
+------------------
+
+Sync script has particular expectation of upstream Linux repo setup. It
+expects that current HEAD of that repo points to bpf-next's master branch and
+that there is a separate local branch pointing to bpf tree's master branch.
+This is important, as the script will automatically merge their histories for
+the purpose of libbpf sync.
+
+Below, we assume that Linux repo is located at `~/linux`, it's current head is
+at latest `bpf-next/master`, and libbpf's Github repo is located at
+`~/libbpf`, checked out to latest commit on `master` branch. It doesn't matter
+from where to run `sync-kernel.sh` script, but we'll be running it from inside
+`~/libbpf`.
+
+```
+$ cd ~/linux && git remote -v | grep -E '^(bpf|bpf-next)'
+bpf     https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git (fetch)
+bpf     ssh://git@gitolite.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git
+(push)
+bpf-next
+https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git (fetch)
+bpf-next
+ssh://git@gitolite.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git (push)
+$ git branch -vv | grep -E '^? (master|bpf-master)'
+* bpf-master                               2d311f480b52 [bpf/master] riscv, bpf: Fix patch_text implicit declaration
+  master                                   c8ee37bde402 [bpf-next/master] libbpf: Fix bpf_xdp_query() in old kernels
+$ git checkout bpf-master && git pull && git checkout master && git pull
+...
+$ git log --oneline -n1
+c8ee37bde402 (HEAD -> master, bpf-next/master) libbpf: Fix bpf_xdp_query() in old kernels
+$ cd ~/libbpf && git checkout master && git pull
+Your branch is up to date with 'libbpf/master'.
+Already up to date.
+```
+
+Running setup script
+--------------------
+
+First step is to always run `sync-kernel.sh` script. It expects three arguments:
+
+```
+$ scripts/sync-kernel.sh <libbpf-repo> <kernel-repo> <bpf-branch>
+```
+
+Note, that we'll store script's entire output in `/tmp/libbpf-sync.txt` and
+put it into PR summary later on. **Please store scripts output and include it
+in PR summary for others to check for anything unexpected and suspicious.**
+
+```
+$ scripts/sync-kernel.sh ~/libbpf ~/linux bpf-master | tee /tmp/libbpf-sync.txt
+Dumping existing libbpf commit signatures...
+WORKDIR:          /home/andriin/libbpf
+LINUX REPO:       /home/andriin/linux
+LIBBPF REPO:      /home/andriin/libbpf
+...
+```
+
+Most of the time this will go very uneventful. One expected case when sync
+script might require user intervention is if `bpf` tree has some libbpf fixes,
+which is nowadays not a very frequent occurence. But if that happens, script
+will show you a diff between expected state as of latest bpf-next and synced
+Github repo state. And will ask if these changes look good. Please use your
+best judgement to verify that differences are indeed from expected `bpf` tree
+fixes. E.g., it might look like below:
+
+```
+Comparing list of files...
+Comparing file contents...
+--- /home/andriin/linux/include/uapi/linux/netdev.h     2023-02-27 16:54:42.270583372 -0800
++++ /home/andriin/libbpf/include/uapi/linux/netdev.h    2023-02-27 16:54:34.615530796 -0800
+@@ -19,7 +19,7 @@
+  * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP
+  *   in zero copy mode.
+  * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw
+- *   oflloading.
++ *   offloading.
+  * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear
+  *   XDP buffer support in the driver napi callback.
+  * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements
+/home/andriin/linux/include/uapi/linux/netdev.h and /home/andriin/libbpf/include/uapi/linux/netdev.h are different!
+Unfortunately, there are some inconsistencies, please double check.
+Does everything look good? [y/N]:
+```
+
+If it looks sensible and expected, type `y` and script will proceed.
+
+If sync is successful, your `~/linux` repo will be left in original state on
+the original HEAD commit. `~/libbpf` repo will now be on a new branch, named
+`libbpf-sync-<timestamp>` (e.g., `libbpf-sync-2023-02-28T00-53-40.072Z`).
+
+Push this branch into your fork of `libbpf/libbpf` Github repo and create a PR:
+
+```
+$ git push --set-upstream origin libbpf-sync-2023-02-28T00-53-40.072Z
+Enumerating objects: 130, done.
+Counting objects: 100% (115/115), done.
+Delta compression using up to 80 threads
+Compressing objects: 100% (28/28), done.
+Writing objects: 100% (32/32), 5.57 KiB | 1.86 MiB/s, done.
+Total 32 (delta 21), reused 0 (delta 0), pack-reused 0
+remote: Resolving deltas: 100% (21/21), completed with 9 local objects.
+remote:
+remote: Create a pull request for 'libbpf-sync-2023-02-28T00-53-40.072Z' on GitHub by visiting:
+remote:      https://github.com/anakryiko/libbpf/pull/new/libbpf-sync-2023-02-28T00-53-40.072Z
+remote:
+To github.com:anakryiko/libbpf.git
+ * [new branch]                libbpf-sync-2023-02-28T00-53-40.072Z -> libbpf-sync-2023-02-28T00-53-40.072Z
+Branch 'libbpf-sync-2023-02-28T00-53-40.072Z' set up to track remote branch 'libbpf-sync-2023-02-28T00-53-40.072Z' from 'origin'.
+```
+
+**Please, adjust PR name to have a properly looking timestamp. Libbpf
+maintainers will be very thankful for that!**
+
+By default Github will turn above branch name into PR with subject "Libbpf sync
+2023 02 28 t00 53 40.072 z". Please fix this into a proper timestamp, e.g.:
+"Libbpf sync 2023-02-28T00:53:40.072Z". Thank you!
+
+**Please don't forget to paste contents of /tmp/libbpf-sync.txt into PR
+summary!**
+
+Once PR is created, libbpf CI will run a bunch of tests to check that
+everything is good. In simple cases that would be all you'd need to do. In more
+complicated cases some extra adjustments might be necessary.
+
+**Please, keep naming and style consistent.** Prefix CI-related fixes with `ci: `
+prefix. If you had to modify sync script, prefix it with `sync: `. Also make
+sure that each such commit has `Signed-off-by: Your Full Name <your@email.com>`,
+just like you'd do that for Linux upstream patch. Libbpf closely follows kernel
+conventions and styling, so please help maintaining that.
+
+Including new sources
+---------------------
+
+If entirely new source files (typically `*.c`) were added to the library in the
+kernel repository, it may be necessary to add these to the build system
+manually (you may notice linker errors otherwise), because the script cannot
+handle such changes automatically. To that end, edit `src/Makefile` as
+necessary. Commit
+[c2495832ced4](https://github.com/libbpf/libbpf/commit/c2495832ced4239bcd376b9954db38a6addd89ca)
+is an example of how to go about doing that.
+
+Similarly, if new public API header files were added, the `Makefile` will need
+to be adjusted as well.
+
+Updating allow/deny lists
+-------------------------
+
+Libbpf CI intentionally runs a subset of latest BPF selftests on old kernel
+(4.9 and 5.5, currently). It happens from time to time that some tests that
+previously were successfully running on old kernels now don't, typically due to
+reliance on some freshly added kernel feature. It might look something like this in [CI logs](https://github.com/libbpf/libbpf/actions/runs/4206303272/jobs/7299609578#step:4:2733):
+
+```
+  All error logs:
+  serial_test_xdp_info:FAIL:get_xdp_none errno=2
+  #283     xdp_info:FAIL
+  Summary: 49/166 PASSED, 5 SKIPPED, 1 FAILED
+```
+
+In such case we can either work with upstream to fix test to be compatible with
+old kernels, or we'll have to add a test into a denylist (or remove it from
+allowlist, like was [done](https://github.com/libbpf/libbpf/commit/ea284299025bf85b85b4923191de6463cd43ccd6)
+for the case above).
+
+```
+$ find . -name '*LIST*'
+./ci/vmtest/configs/ALLOWLIST-4.9.0
+./ci/vmtest/configs/DENYLIST-5.5.0
+./ci/vmtest/configs/DENYLIST-latest.s390x
+./ci/vmtest/configs/DENYLIST-latest
+./ci/vmtest/configs/ALLOWLIST-5.5.0
+```
+
+Please determine which tests need to be added/removed from which list. And then
+add that as a separate commit. **Please keep using the same branch name, so
+that the same PR can be updated.** There is no need to open new PRs for each
+such fix.
+
+Regenerating vmlinux.h header
+-----------------------------
+
+To compile latest BPF selftests against old kernels, we check in pre-generated
+[vmlinux.h](https://github.com/libbpf/libbpf/blob/master/.github/actions/build-selftests/vmlinux.h)
+header file, located at `.github/actions/build-selftests/vmlinux.h`, which
+contains type definitions from latest upstream kernel. When after libbpf sync
+upstream BPF selftests require new kernel types, we'd need to regenerate
+`vmlinux.h` and check it in as well.
+
+This will looks something like this in [CI logs](https://github.com/libbpf/libbpf/actions/runs/4198939244/jobs/7283214243#step:4:1903):
+
+```
+  In file included from progs/test_spin_lock_fail.c:5:
+  /home/runner/work/libbpf/libbpf/.kernel/tools/testing/selftests/bpf/bpf_experimental.h:73:53: error: declaration of 'struct bpf_rb_root' will not be visible outside of this function [-Werror,-Wvisibility]
+  extern struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root,
+                                                      ^
+  /home/runner/work/libbpf/libbpf/.kernel/tools/testing/selftests/bpf/bpf_experimental.h:81:35: error: declaration of 'struct bpf_rb_root' will not be visible outside of this function [-Werror,-Wvisibility]
+  extern void bpf_rbtree_add(struct bpf_rb_root *root, struct bpf_rb_node *node,
+                                    ^
+  /home/runner/work/libbpf/libbpf/.kernel/tools/testing/selftests/bpf/bpf_experimental.h:90:52: error: declaration of 'struct bpf_rb_root' will not be visible outside of this function [-Werror,-Wvisibility]
+  extern struct bpf_rb_node *bpf_rbtree_first(struct bpf_rb_root *root) __ksym;
+                                                     ^
+  3 errors generated.
+  make: *** [Makefile:572: /home/runner/work/libbpf/libbpf/.kernel/tools/testing/selftests/bpf/test_spin_lock_fail.bpf.o] Error 1
+  make: *** Waiting for unfinished jobs....
+  Error: Process completed with exit code 2.
+```
+
+You'll need to build latest upstream kernel from `bpf-next` tree, using BPF
+selftest configs. Concat arch-agnostic and arch-specific configs, build kernel,
+then use bpftool to dump `vmlinux.h`:
+
+```
+$ cd ~/linux
+$ cat tools/testing/selftests/bpf/config \
+   tools/testing/selftests/bpf/config.x86_64 > .config
+$ make -j$(nproc) olddefconfig all
+...
+$ bpftool btf dump file ~/linux/vmlinux format c > ~/libbpf/.github/actions/build-selftests/vmlinux.h
+$ cd ~/libbpf && git add . && git commit -s
+```
+
+Check in generated `vmlinux.h`, don't forget to use `ci: ` commit prefix, add
+it on top of sync commits. Push to Github and let libbpf CI do the checking for
+you. See [this commit](https://github.com/libbpf/libbpf/commit/34212c94a64df8eeb1dd5d064630a65e1dfd4c20)
+for reference.
+
+Troubleshooting
+---------------
+
+If something goes wrong and sync script exits early or is terminated early by
+user, you might end up with `~/linux` repo on temporary sync-related branch.
+Don't worry, though, sync script never destroys repo state, it follows
+"copy-on-write" philosophy and creates new branches where necessary. So it's
+very easy to restore previous state. So if anything goes wrong, it's easy to
+start fresh:
+
+```
+$ git branch | grep -E 'libbpf-.*Z'
+  libbpf-baseline-2023-02-28T00-43-35.146Z
+  libbpf-bpf-baseline-2023-02-28T00-43-35.146Z
+  libbpf-bpf-tip-2023-02-28T00-43-35.146Z
+  libbpf-squash-base-2023-02-28T00-43-35.146Z
+* libbpf-squash-tip-2023-02-28T00-43-35.146Z
+$ git cherry-pick --abort
+$ git checkout master && git branch | grep -E 'libbpf-.*Z' | xargs git br -D
+Switched to branch 'master'
+Your branch is up to date with 'bpf-next/master'.
+Deleted branch libbpf-baseline-2023-02-28T00-43-35.146Z (was 951bce29c898).
+Deleted branch libbpf-bpf-baseline-2023-02-28T00-43-35.146Z (was 3a70e0d4c9d7).
+Deleted branch libbpf-bpf-tip-2023-02-28T00-43-35.146Z (was 2d311f480b52).
+Deleted branch libbpf-squash-base-2023-02-28T00-43-35.146Z (was 957f109ef883).
+Deleted branch libbpf-squash-tip-2023-02-28T00-43-35.146Z (was be66130d2339).
+Deleted branch libbpf-tip-2023-02-28T00-43-35.146Z (was 2d311f480b52).
+```
+
+You might need to do the same for your `~/libbpf` repo sometimes, depending at
+which stage sync script was terminated.

ci/diffs/0001-arch-Kconfig-Move-SPECULATION_MITIGATIONS-to-arch-Kc.patch

@@ -0,0 +1,69 @@
+From c71766e8ff7a7f950522d25896fba758585500df Mon Sep 17 00:00:00 2001
+From: Song Liu <song@kernel.org>
+Date: Mon, 22 Apr 2024 21:14:40 -0700
+Subject: [PATCH] arch/Kconfig: Move SPECULATION_MITIGATIONS to arch/Kconfig
+
+SPECULATION_MITIGATIONS is currently defined only for x86. As a result,
+IS_ENABLED(CONFIG_SPECULATION_MITIGATIONS) is always false for other
+archs. f337a6a21e2f effectively set "mitigations=off" by default on
+non-x86 archs, which is not desired behavior. Jakub observed this
+change when running bpf selftests on s390 and arm64.
+
+Fix this by moving SPECULATION_MITIGATIONS to arch/Kconfig so that it is
+available in all archs and thus can be used safely in kernel/cpu.c
+
+Fixes: f337a6a21e2f ("x86/cpu: Actually turn off mitigations by default for SPECULATION_MITIGATIONS=n")
+Cc: stable@vger.kernel.org
+Cc: Sean Christopherson <seanjc@google.com>
+Cc: Ingo Molnar <mingo@kernel.org>
+Cc: Daniel Sneddon <daniel.sneddon@linux.intel.com>
+Cc: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Song Liu <song@kernel.org>
+---
+ arch/Kconfig     | 10 ++++++++++
+ arch/x86/Kconfig | 10 ----------
+ 2 files changed, 10 insertions(+), 10 deletions(-)
+
+diff --git a/arch/Kconfig b/arch/Kconfig
+index 9f066785bb71..8f4af75005f8 100644
+--- a/arch/Kconfig
++++ b/arch/Kconfig
+@@ -1609,4 +1609,14 @@ config CC_HAS_SANE_FUNCTION_ALIGNMENT
+ 	# strict alignment always, even with -falign-functions.
+ 	def_bool CC_HAS_MIN_FUNCTION_ALIGNMENT || CC_IS_CLANG
+ 
++menuconfig SPECULATION_MITIGATIONS
++	bool "Mitigations for speculative execution vulnerabilities"
++	default y
++	help
++	  Say Y here to enable options which enable mitigations for
++	  speculative execution hardware vulnerabilities.
++
++	  If you say N, all mitigations will be disabled. You really
++	  should know what you are doing to say so.
++
+ endmenu
+diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
+index 39886bab943a..50c890fce5e0 100644
+--- a/arch/x86/Kconfig
++++ b/arch/x86/Kconfig
+@@ -2486,16 +2486,6 @@ config PREFIX_SYMBOLS
+ 	def_bool y
+ 	depends on CALL_PADDING && !CFI_CLANG
+ 
+-menuconfig SPECULATION_MITIGATIONS
+-	bool "Mitigations for speculative execution vulnerabilities"
+-	default y
+-	help
+-	  Say Y here to enable options which enable mitigations for
+-	  speculative execution hardware vulnerabilities.
+-
+-	  If you say N, all mitigations will be disabled. You really
+-	  should know what you are doing to say so.
+-
+ if SPECULATION_MITIGATIONS
+ 
+ config MITIGATION_PAGE_TABLE_ISOLATION
+-- 
+2.43.0
+

ci/diffs/0002-xdp-bonding-Fix-feature-flags-when-there-are-no-slav.patch

@@ -0,0 +1,56 @@
+From f267f262815033452195f46c43b572159262f533 Mon Sep 17 00:00:00 2001
+From: Daniel Borkmann <daniel@iogearbox.net>
+Date: Tue, 5 Mar 2024 10:08:28 +0100
+Subject: [PATCH 2/2] xdp, bonding: Fix feature flags when there are no slave
+ devs anymore
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+Commit 9b0ed890ac2a ("bonding: do not report NETDEV_XDP_ACT_XSK_ZEROCOPY")
+changed the driver from reporting everything as supported before a device
+was bonded into having the driver report that no XDP feature is supported
+until a real device is bonded as it seems to be more truthful given
+eventually real underlying devices decide what XDP features are supported.
+
+The change however did not take into account when all slave devices get
+removed from the bond device. In this case after 9b0ed890ac2a, the driver
+keeps reporting a feature mask of 0x77, that is, NETDEV_XDP_ACT_MASK &
+~NETDEV_XDP_ACT_XSK_ZEROCOPY whereas it should have reported a feature
+mask of 0.
+
+Fix it by resetting XDP feature flags in the same way as if no XDP program
+is attached to the bond device. This was uncovered by the XDP bond selftest
+which let BPF CI fail. After adjusting the starting masks on the latter
+to 0 instead of NETDEV_XDP_ACT_MASK the test passes again together with
+this fix.
+
+Fixes: 9b0ed890ac2a ("bonding: do not report NETDEV_XDP_ACT_XSK_ZEROCOPY")
+Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
+Cc: Magnus Karlsson <magnus.karlsson@intel.com>
+Cc: Prashant Batra <prbatra.mail@gmail.com>
+Cc: Toke Høiland-Jørgensen <toke@redhat.com>
+Cc: Jakub Kicinski <kuba@kernel.org>
+Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
+Message-ID: <20240305090829.17131-1-daniel@iogearbox.net>
+Signed-off-by: Alexei Starovoitov <ast@kernel.org>
+---
+ drivers/net/bonding/bond_main.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
+index a11748b8d69b..cd0683bcca03 100644
+--- a/drivers/net/bonding/bond_main.c
++++ b/drivers/net/bonding/bond_main.c
+@@ -1811,7 +1811,7 @@ void bond_xdp_set_features(struct net_device *bond_dev)
+ 
+ 	ASSERT_RTNL();
+ 
+-	if (!bond_xdp_check(bond)) {
++	if (!bond_xdp_check(bond) || !bond_has_slaves(bond)) {
+ 		xdp_clear_features_flag(bond_dev);
+ 		return;
+ 	}
+-- 
+2.43.0
+

ci/managers/debian.sh

@@ -6,8 +6,9 @@ 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-10)
-CFLAGS="-g -O2 -Werror -Wall"
+ADDITIONAL_DEPS=(pkgconf)
+EXTRA_CFLAGS=""
+EXTRA_LDFLAGS=""
 
 function info() {
     echo -e "\033[33;1m$1\033[0m"
@@ -42,30 +43,35 @@ for phase in "${PHASES[@]}"; do
             docker_exec bash -c "echo deb-src http://deb.debian.org/debian $DEBIAN_RELEASE main >>/etc/apt/sources.list"
             docker_exec apt-get -y update
             docker_exec apt-get -y install aptitude
-            docker_exec aptitude -y build-dep libelf-dev
-            docker_exec aptitude -y install libelf-dev
+            docker_exec aptitude -y install make libz-dev libelf-dev
             docker_exec aptitude -y install "${ADDITIONAL_DEPS[@]}"
             echo -e "::endgroup::"
             ;;
-        RUN|RUN_CLANG|RUN_GCC10|RUN_ASAN|RUN_CLANG_ASAN|RUN_GCC10_ASAN)
+        RUN|RUN_CLANG|RUN_CLANG14|RUN_CLANG15|RUN_CLANG16|RUN_GCC10|RUN_GCC11|RUN_GCC12|RUN_ASAN|RUN_CLANG_ASAN|RUN_GCC10_ASAN)
             CC="cc"
-            if [[ "$phase" = *"CLANG"* ]]; then
+            if [[ "$phase" =~ "RUN_CLANG(\d+)(_ASAN)?" ]]; then
+                ENV_VARS="-e CC=clang-${BASH_REMATCH[1]} -e CXX=clang++-${BASH_REMATCH[1]}"
+                CC="clang-${BASH_REMATCH[1]}"
+            elif [[ "$phase" = *"CLANG"* ]]; then
                 ENV_VARS="-e CC=clang -e CXX=clang++"
                 CC="clang"
-            elif [[ "$phase" = *"GCC10"* ]]; then
-                ENV_VARS="-e CC=gcc-10 -e CXX=g++-10"
-                CC="gcc-10"
-                CFLAGS="${CFLAGS} -Wno-stringop-truncation"
-            else
-                CFLAGS="${CFLAGS} -Wno-stringop-truncation"
+            elif [[ "$phase" =~ "RUN_GCC(\d+)(_ASAN)?" ]]; then
+                ENV_VARS="-e CC=gcc-${BASH_REMATCH[1]} -e CXX=g++-${BASH_REMATCH[1]}"
+                CC="gcc-${BASH_REMATCH[1]}"
             fi
             if [[ "$phase" = *"ASAN"* ]]; then
-                CFLAGS="${CFLAGS} -fsanitize=address,undefined"
+                EXTRA_CFLAGS="${EXTRA_CFLAGS} -fsanitize=address,undefined"
+                EXTRA_LDFLAGS="${EXTRA_LDFLAGS} -fsanitize=address,undefined"
+            fi
+            if [[ "$CC" != "cc" ]]; then
+                docker_exec aptitude -y install "$CC"
+            else
+                docker_exec aptitude -y install gcc
             fi
             docker_exec mkdir build install
             docker_exec ${CC} --version
             info "build"
-            docker_exec make -j$((4*$(nproc))) CFLAGS="${CFLAGS}" -C ./src -B OBJDIR=../build
+            docker_exec make -j$((4*$(nproc))) EXTRA_CFLAGS="${EXTRA_CFLAGS}" EXTRA_LDFLAGS="${EXTRA_LDFLAGS}" -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
@@ -75,7 +81,7 @@ for phase in "${PHASES[@]}"; do
             info "install"
             docker_exec make -j$((4*$(nproc))) -C src OBJDIR=../build DESTDIR=../install install
             info "link binary"
-            docker_exec bash -c "CFLAGS=\"${CFLAGS}\" ./travis-ci/managers/test_compile.sh"
+            docker_exec bash -c "EXTRA_CFLAGS=\"${EXTRA_CFLAGS}\" EXTRA_LDFLAGS=\"${EXTRA_LDFLAGS}\" ./ci/managers/test_compile.sh"
             ;;
         CLEANUP)
             info "Cleanup phase"

ci/managers/test_compile.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+set -euox pipefail
+
+EXTRA_CFLAGS=${EXTRA_CFLAGS:-}
+EXTRA_LDFLAGS=${EXTRA_LDFLAGS:-}
+
+cat << EOF > main.c
+#include <bpf/libbpf.h>
+int main() {
+  return bpf_object__open(0) < 0;
+}
+EOF
+
+# static linking
+${CC:-cc} ${EXTRA_CFLAGS} ${EXTRA_LDFLAGS} -o main -I./include/uapi -I./install/usr/include main.c ./build/libbpf.a -lelf -lz

ci/managers/ubuntu.sh

@@ -10,14 +10,15 @@ source "$(dirname $0)/travis_wait.bash"
 
 cd $REPO_ROOT
 
-CFLAGS="-g -O2 -Werror -Wall -fsanitize=address,undefined -Wno-stringop-truncation"
+EXTRA_CFLAGS="-Werror -Wall -fsanitize=address,undefined"
+EXTRA_LDFLAGS="-Werror -Wall -fsanitize=address,undefined"
 mkdir build install
 cc --version
-make -j$((4*$(nproc))) CFLAGS="${CFLAGS}" -C ./src -B OBJDIR=../build
+make -j$((4*$(nproc))) EXTRA_CFLAGS="${EXTRA_CFLAGS}" EXTRA_LDFLAGS="${EXTRA_LDFLAGS}" -C ./src -B OBJDIR=../build
 ldd build/libbpf.so
 if ! ldd build/libbpf.so | grep -q libelf; then
     echo "FAIL: No reference to libelf.so in libbpf.so!"
     exit 1
 fi
 make -j$((4*$(nproc))) -C src OBJDIR=../build DESTDIR=../install install
-CFLAGS=${CFLAGS} $(dirname $0)/test_compile.sh
+EXTRA_CFLAGS=${EXTRA_CFLAGS} EXTRA_LDFLAGS=${EXTRA_LDFLAGS} $(dirname $0)/test_compile.sh

ci/vmtest/configs/ALLOWLIST-4.9.0

@@ -2,6 +2,7 @@
 core_retro
 cpu_mask
 hashmap
+legacy_printk
 perf_buffer
 section_names
 

ci/vmtest/configs/ALLOWLIST-5.5.0

@@ -1,4 +1,4 @@
-attach_probe
+# attach_probe
 autoload
 bpf_verif_scale
 cgroup_attach_autodetach
@@ -10,14 +10,13 @@ core_reloc
 core_retro
 cpu_mask
 endian
-fexit_stress
 get_branch_snapshot
 get_stackid_cannot_attach
 global_data
 global_data_init
 global_func_args
 hashmap
-l4lb_all
+legacy_printk
 linked_funcs
 linked_maps
 map_lock
@@ -33,23 +32,18 @@ raw_tp_writable_test_run
 rdonly_maps
 section_names
 signal_pending
-skeleton
 sockmap_ktls
-sockopt
-sockopt_inherit
-sockopt_multi
 spinlock
 stacktrace_map
 stacktrace_map_raw_tp
 static_linked
-subprogs
 task_fd_query_rawtp
 task_fd_query_tp
 tc_bpf
 tcp_estats
-tcp_rtt
+test_global_funcs/arg_tag_ctx*
 tp_attach_query
+usdt/urand_pid_attach
 xdp
-xdp_info
 xdp_noinline
 xdp_perf

ci/vmtest/configs/DENYLIST

@@ -0,0 +1,14 @@
+# TEMPORARY
+btf_dump/btf_dump: syntax
+kprobe_multi_bench_attach
+core_reloc/enum64val
+core_reloc/size___diff_sz
+core_reloc/type_based___diff_sz
+test_ima	# All of CI is broken on it following 6.3-rc1 merge
+
+lwt_reroute      # crashes kernel after netnext merge from 2ab1efad60ad "net/sched: cls_api: complement tcf_tfilter_dump_policy"
+tc_links_ingress # started failing after net-next merge from 2ab1efad60ad "net/sched: cls_api: complement tcf_tfilter_dump_policy"
+xdp_bonding/xdp_bonding_features     # started failing after net merge from 359e54a93ab4 "l2tp: pass correct message length to ip6_append_data"
+tc_redirect/tc_redirect_dtime # uapi breakage after net-next commit 885c36e59f46 ("net: Re-use and set mono_delivery_time bit for userspace tstamp packets")
+migrate_reuseport/IPv4 TCP_NEW_SYN_RECV reqsk_timer_handler # flaky, under investigation
+migrate_reuseport/IPv6 TCP_NEW_SYN_RECV reqsk_timer_handler # flaky, under investigation

ci/vmtest/configs/DENYLIST-5.5.0

@@ -0,0 +1,5 @@
+# This complements ALLOWLIST-5.5.0 but excludes subtest that can't work on 5.5
+
+btf			# "size check test", "func (Non zero vlen)"
+tailcalls		# tailcall_bpf2bpf_1, tailcall_bpf2bpf_2, tailcall_bpf2bpf_3
+tc_bpf/tc_bpf_non_root

ci/vmtest/configs/DENYLIST-latest

@@ -0,0 +1,13 @@
+decap_sanity  # weird failure with decap_sanity_ns netns already existing, TBD
+empty_skb # waiting the fix in bpf tree to make it to bpf-next
+bpf_nf/tc-bpf-ct # test consistently failing on x86: https://github.com/libbpf/libbpf/pull/698#issuecomment-1590341200
+bpf_nf/xdp-ct   # test consistently failing on x86: https://github.com/libbpf/libbpf/pull/698#issuecomment-1590341200
+kprobe_multi_bench_attach # suspected to cause crashes in CI
+find_vma # test consistently fails on latest kernel, see https://github.com/libbpf/libbpf/issues/754 for details
+bpf_cookie/perf_event
+send_signal/send_signal_nmi
+send_signal/send_signal_nmi_thread
+
+lwt_reroute # crashes kernel, fix pending upstream
+tc_links_ingress # fails, same fix is pending upstream
+tc_redirect		  # enough is enough, banned for life for flakiness

ci/vmtest/configs/DENYLIST-latest.s390x

@@ -0,0 +1,17 @@
+# TEMPORARY
+sockmap_listen/sockhash VSOCK test_vsock_redir
+usdt/basic                               # failing verifier due to bounds check after LLVM update
+usdt/multispec                           # same as above
+
+deny_namespace                           # not yet in bpf denylist
+tc_redirect/tc_redirect_dtime            # very flaky
+lru_bug                                  # not yet in bpf-next denylist
+
+# Disabled temporarily for a crash.
+# https://lore.kernel.org/bpf/c9923c1d-971d-4022-8dc8-1364e929d34c@gmail.com/
+dummy_st_ops/dummy_init_ptr_arg
+fexit_bpf2bpf
+tailcalls
+trace_ext
+xdp_bpf2bpf
+xdp_metadata

ci/vmtest/helpers.sh

@@ -0,0 +1,38 @@
+# shellcheck shell=bash
+
+# $1 - start or end
+# $2 - fold identifier, no spaces
+# $3 - fold section description
+foldable() {
+  local YELLOW='\033[1;33m'
+  local NOCOLOR='\033[0m'
+  if [ $1 = "start" ]; then
+    line="::group::$2"
+    if [ ! -z "${3:-}" ]; then
+      line="$line - ${YELLOW}$3${NOCOLOR}"
+    fi
+  else
+    line="::endgroup::"
+  fi
+  echo -e "$line"
+}
+
+__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
+}

ci/vmtest/run_selftests.sh

@@ -0,0 +1,94 @@
+#!/bin/bash
+
+set -euo pipefail
+
+source $(cd $(dirname $0) && pwd)/helpers.sh
+
+ARCH=$(uname -m)
+
+STATUS_FILE=/exitstatus
+
+read_lists() {
+	(for path in "$@"; do
+		if [[ -s "$path" ]]; then
+			cat "$path"
+		fi;
+	done) | cut -d'#' -f1 | sed -e 's/^[[:space:]]*//' -e 's/[[:space:]]*$//' | tr -s '\n' ','
+}
+
+test_progs() {
+	if [[ "${KERNEL}" != '4.9.0' ]]; then
+		foldable start test_progs "Testing test_progs"
+		# "&& true" does not change the return code (it is not executed
+		# if the Python script fails), but it prevents exiting on a
+		# failure due to the "set -e".
+		./test_progs ${DENYLIST:+-d"$DENYLIST"} ${ALLOWLIST:+-a"$ALLOWLIST"} && true
+		echo "test_progs:$?" >> "${STATUS_FILE}"
+		foldable end test_progs
+	fi
+}
+
+test_progs_no_alu32() {
+	foldable start test_progs-no_alu32 "Testing test_progs-no_alu32"
+	./test_progs-no_alu32 ${DENYLIST:+-d"$DENYLIST"} ${ALLOWLIST:+-a"$ALLOWLIST"} && true
+	echo "test_progs-no_alu32:$?" >> "${STATUS_FILE}"
+	foldable end test_progs-no_alu32
+}
+
+test_maps() {
+	if [[ "${KERNEL}" == 'latest' ]]; then
+		foldable start test_maps "Testing test_maps"
+		./test_maps && true
+		echo "test_maps:$?" >> "${STATUS_FILE}"
+		foldable end test_maps
+	fi
+}
+
+test_verifier() {
+	if [[ "${KERNEL}" == 'latest' ]]; then
+		foldable start test_verifier "Testing test_verifier"
+		./test_verifier && true
+		echo "test_verifier:$?" >> "${STATUS_FILE}"
+		foldable end test_verifier
+	fi
+}
+
+foldable end vm_init
+
+foldable start kernel_config "Kconfig"
+
+zcat /proc/config.gz
+
+foldable end kernel_config
+
+
+configs_path=/${PROJECT_NAME}/selftests/bpf
+local_configs_path=${PROJECT_NAME}/vmtest/configs
+DENYLIST=$(read_lists \
+	"$configs_path/DENYLIST" \
+	"$configs_path/DENYLIST.${ARCH}" \
+	"$local_configs_path/DENYLIST-${KERNEL}" \
+	"$local_configs_path/DENYLIST-${KERNEL}.${ARCH}" \
+)
+ALLOWLIST=$(read_lists \
+	"$configs_path/ALLOWLIST" \
+	"$configs_path/ALLOWLIST.${ARCH}" \
+	"$local_configs_path/ALLOWLIST-${KERNEL}" \
+	"$local_configs_path/ALLOWLIST-${KERNEL}.${ARCH}" \
+)
+
+echo "DENYLIST: ${DENYLIST}"
+echo "ALLOWLIST: ${ALLOWLIST}"
+
+cd ${PROJECT_NAME}/selftests/bpf
+
+if [ $# -eq 0 ]; then
+	test_progs
+	test_progs_no_alu32
+	# test_maps
+	test_verifier
+else
+	for test_name in "$@"; do
+		"${test_name}"
+	done
+fi

docs/api.rst

@@ -6,7 +6,49 @@
 
 
 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
 --------

docs/conf.py

@@ -18,6 +18,7 @@ extensions = [
     'sphinx.ext.viewcode',
     'sphinx.ext.imgmath',
     'sphinx.ext.todo',
+    'sphinx_rtd_theme',
     'breathe',
 ]
 

docs/index.rst

@@ -1,22 +1,33 @@
 .. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 
+.. _libbpf:
+
+======
 libbpf
 ======
 
-For API documentation see the `versioned API documentation site <https://libbpf.readthedocs.io/en/latest/api.html>`_.
+If you are looking to develop BPF applications using the libbpf library, this
+directory contains important documentation that you should read.
+
+To get started, it is recommended to begin with the :doc:`libbpf Overview
+<libbpf_overview>` document, which provides a high-level understanding of the
+libbpf APIs and their usage. This will give you a solid foundation to start
+exploring and utilizing the various features of libbpf to develop your BPF
+applications.
 
 .. toctree::
    :maxdepth: 1
 
+   libbpf_overview
+   API Documentation <https://libbpf.readthedocs.io/en/latest/api.html>
+   program_types
    libbpf_naming_convention
    libbpf_build
 
-This is documentation for libbpf, a userspace library for loading and
-interacting with bpf programs.
 
-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.
+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 may be that this was already addressed or
+answered before.

docs/libbpf_naming_convention.rst

@@ -9,8 +9,8 @@ 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_``,
-``btf_dump_``, ``ring_buffer_``, ``perf_buffer_``.
+following prefixes: ``bpf_``, ``btf_``, ``libbpf_``, ``btf_dump_``,
+``ring_buffer_``, ``perf_buffer_``.
 
 System call wrappers
 --------------------
@@ -59,15 +59,6 @@ Auxiliary functions and types that don't fit well in any of categories
 described above should have ``libbpf_`` prefix, e.g.
 ``libbpf_get_error`` or ``libbpf_prog_type_by_name``.
 
-AF_XDP functions
--------------------
-
-AF_XDP functions should have an ``xsk_`` prefix, e.g.
-``xsk_umem__get_data`` or ``xsk_umem__create``. The interface consists
-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.
-
 ABI
 ---
 
@@ -92,8 +83,8 @@ This prevents from accidentally exporting a symbol, that is not supposed
 to be a part of ABI what, in turn, improves both libbpf developer- and
 user-experiences.
 
-ABI versionning
----------------
+ABI versioning
+--------------
 
 To make future ABI extensions possible libbpf ABI is versioned.
 Versioning is implemented by ``libbpf.map`` version script that is
@@ -157,7 +148,7 @@ 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.
+convention in which these comments should be formatted.
 
 Here is an example from btf.h:
 

docs/libbpf_overview.rst

@@ -0,0 +1,228 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===============
+libbpf Overview
+===============
+
+libbpf is a C-based library containing a BPF loader that takes compiled BPF
+object files and prepares and loads them into the Linux kernel. libbpf takes the
+heavy lifting of loading, verifying, and attaching BPF programs to various
+kernel hooks, allowing BPF application developers to focus only on BPF program
+correctness and performance.
+
+The following are the high-level features supported by libbpf:
+
+* Provides high-level and low-level APIs for user space programs to interact
+  with BPF programs. The low-level APIs wrap all the bpf system call
+  functionality, which is useful when users need more fine-grained control
+  over the interactions between user space and BPF programs.
+* Provides overall support for the BPF object skeleton generated by bpftool.
+  The skeleton file simplifies the process for the user space programs to access
+  global variables and work with BPF programs.
+* Provides BPF-side APIS, including BPF helper definitions, BPF maps support,
+  and tracing helpers, allowing developers to simplify BPF code writing.
+* Supports BPF CO-RE mechanism, enabling BPF developers to write portable
+  BPF programs that can be compiled once and run across different kernel
+  versions.
+
+This document will delve into the above concepts in detail, providing a deeper
+understanding of the capabilities and advantages of libbpf and how it can help
+you develop BPF applications efficiently.
+
+BPF App Lifecycle and libbpf APIs
+==================================
+
+A BPF application consists of one or more BPF programs (either cooperating or
+completely independent), BPF maps, and global variables. The global
+variables are shared between all BPF programs, which allows them to cooperate on
+a common set of data. libbpf provides APIs that user space programs can use to
+manipulate the BPF programs by triggering different phases of a BPF application
+lifecycle.
+
+The following section provides a brief overview of each phase in the BPF life
+cycle:
+
+* **Open phase**: In this phase, libbpf parses the BPF
+  object file and discovers BPF maps, BPF programs, and global variables. After
+  a BPF app is opened, user space apps can make additional adjustments
+  (setting BPF program types, if necessary; pre-setting initial values for
+  global variables, etc.) before all the entities are created and loaded.
+
+* **Load phase**: In the load phase, libbpf creates BPF
+  maps, resolves various relocations, and verifies and loads BPF programs into
+  the kernel. At this point, libbpf validates all the parts of a BPF application
+  and loads the BPF program into the kernel, but no BPF program has yet been
+  executed. After the load phase, it’s possible to set up the initial BPF map
+  state without racing with the BPF program code execution.
+
+* **Attachment phase**: In this phase, libbpf
+  attaches BPF programs to various BPF hook points (e.g., tracepoints, kprobes,
+  cgroup hooks, network packet processing pipeline, etc.). During this
+  phase, BPF programs perform useful work such as processing
+  packets, or updating BPF maps and global variables that can be read from user
+  space.
+
+* **Tear down phase**: In the tear down phase,
+  libbpf detaches BPF programs and unloads them from the kernel. BPF maps are
+  destroyed, and all the resources used by the BPF app are freed.
+
+BPF Object Skeleton File
+========================
+
+BPF skeleton is an alternative interface to libbpf APIs for working with BPF
+objects. Skeleton code abstract away generic libbpf APIs to significantly
+simplify code for manipulating BPF programs from user space. Skeleton code
+includes a bytecode representation of the BPF object file, simplifying the
+process of distributing your BPF code. With BPF bytecode embedded, there are no
+extra files to deploy along with your application binary.
+
+You can generate the skeleton header file ``(.skel.h)`` for a specific object
+file by passing the BPF object to the bpftool. The generated BPF skeleton
+provides the following custom functions that correspond to the BPF lifecycle,
+each of them prefixed with the specific object name:
+
+* ``<name>__open()`` – creates and opens BPF application (``<name>`` stands for
+  the specific bpf object name)
+* ``<name>__load()`` – instantiates, loads,and verifies BPF application parts
+* ``<name>__attach()`` – attaches all auto-attachable BPF programs (it’s
+  optional, you can have more control by using libbpf APIs directly)
+* ``<name>__destroy()`` – detaches all BPF programs and
+  frees up all used resources
+
+Using the skeleton code is the recommended way to work with bpf programs. Keep
+in mind, BPF skeleton provides access to the underlying BPF object, so whatever
+was possible to do with generic libbpf APIs is still possible even when the BPF
+skeleton is used. It's an additive convenience feature, with no syscalls, and no
+cumbersome code.
+
+Other Advantages of Using Skeleton File
+---------------------------------------
+
+* BPF skeleton provides an interface for user space programs to work with BPF
+  global variables. The skeleton code memory maps global variables as a struct
+  into user space. The struct interface allows user space programs to initialize
+  BPF programs before the BPF load phase and fetch and update data from user
+  space afterward.
+
+* The ``skel.h`` file reflects the object file structure by listing out the
+  available maps, programs, etc. BPF skeleton provides direct access to all the
+  BPF maps and BPF programs as struct fields. This eliminates the need for
+  string-based lookups with ``bpf_object_find_map_by_name()`` and
+  ``bpf_object_find_program_by_name()`` APIs, reducing errors due to BPF source
+  code and user-space code getting out of sync.
+
+* The embedded bytecode representation of the object file ensures that the
+  skeleton and the BPF object file are always in sync.
+
+BPF Helpers
+===========
+
+libbpf provides BPF-side APIs that BPF programs can use to interact with the
+system. The BPF helpers definition allows developers to use them in BPF code as
+any other plain C function. For example, there are helper functions to print
+debugging messages, get the time since the system was booted, interact with BPF
+maps, manipulate network packets, etc.
+
+For a complete description of what the helpers do, the arguments they take, and
+the return value, see the `bpf-helpers
+<https://man7.org/linux/man-pages/man7/bpf-helpers.7.html>`_ man page.
+
+BPF CO-RE (Compile Once – Run Everywhere)
+=========================================
+
+BPF programs work in the kernel space and have access to kernel memory and data
+structures. One limitation that BPF applications come across is the lack of
+portability across different kernel versions and configurations. `BCC
+<https://github.com/iovisor/bcc/>`_ is one of the solutions for BPF
+portability. However, it comes with runtime overhead and a large binary size
+from embedding the compiler with the application.
+
+libbpf steps up the BPF program portability by supporting the BPF CO-RE concept.
+BPF CO-RE brings together BTF type information, libbpf, and the compiler to
+produce a single executable binary that you can run on multiple kernel versions
+and configurations.
+
+To make BPF programs portable libbpf relies on the BTF type information of the
+running kernel. Kernel also exposes this self-describing authoritative BTF
+information through ``sysfs`` at ``/sys/kernel/btf/vmlinux``.
+
+You can generate the BTF information for the running kernel with the following
+command:
+
+::
+
+  $ bpftool btf dump file /sys/kernel/btf/vmlinux format c > vmlinux.h
+
+The command generates a ``vmlinux.h`` header file with all kernel types
+(:doc:`BTF types <../btf>`) that the running kernel uses. Including
+``vmlinux.h`` in your BPF program eliminates dependency on system-wide kernel
+headers.
+
+libbpf enables portability of BPF programs by looking at the BPF program’s
+recorded BTF type and relocation information and matching them to BTF
+information (vmlinux) provided by the running kernel. libbpf then resolves and
+matches all the types and fields, and updates necessary offsets and other
+relocatable data to ensure that BPF program’s logic functions correctly for a
+specific kernel on the host. BPF CO-RE concept thus eliminates overhead
+associated with BPF development and allows developers to write portable BPF
+applications without modifications and runtime source code compilation on the
+target machine.
+
+The following code snippet shows how to read the parent field of a kernel
+``task_struct`` using BPF CO-RE and libbf. The basic helper to read a field in a
+CO-RE relocatable manner is ``bpf_core_read(dst, sz, src)``, which will read
+``sz`` bytes from the field referenced by ``src`` into the memory pointed to by
+``dst``.
+
+.. code-block:: C
+   :emphasize-lines: 6
+
+    //...
+    struct task_struct *task = (void *)bpf_get_current_task();
+    struct task_struct *parent_task;
+    int err;
+
+    err = bpf_core_read(&parent_task, sizeof(void *), &task->parent);
+    if (err) {
+      /* handle error */
+    }
+
+    /* parent_task contains the value of task->parent pointer */
+
+In the code snippet, we first get a pointer to the current ``task_struct`` using
+``bpf_get_current_task()``.  We then use ``bpf_core_read()`` to read the parent
+field of task struct into the ``parent_task`` variable. ``bpf_core_read()`` is
+just like ``bpf_probe_read_kernel()`` BPF helper, except it records information
+about the field that should be relocated on the target kernel. i.e, if the
+``parent`` field gets shifted to a different offset within
+``struct task_struct`` due to some new field added in front of it, libbpf will
+automatically adjust the actual offset to the proper value.
+
+Getting Started with libbpf
+===========================
+
+Check out the `libbpf-bootstrap <https://github.com/libbpf/libbpf-bootstrap>`_
+repository with simple examples of using libbpf to build various BPF
+applications.
+
+See also `libbpf API documentation
+<https://libbpf.readthedocs.io/en/latest/api.html>`_.
+
+libbpf and Rust
+===============
+
+If you are building BPF applications in Rust, it is recommended to use the
+`Libbpf-rs <https://github.com/libbpf/libbpf-rs>`_ library instead of bindgen
+bindings directly to libbpf. Libbpf-rs wraps libbpf functionality in
+Rust-idiomatic interfaces and provides libbpf-cargo plugin to handle BPF code
+compilation and skeleton generation. Using Libbpf-rs will make building user
+space part of the BPF application easier. Note that the BPF program themselves
+must still be written in plain C.
+
+Additional Documentation
+========================
+
+* `Program types and ELF Sections <https://libbpf.readthedocs.io/en/latest/program_types.html>`_
+* `API naming convention <https://libbpf.readthedocs.io/en/latest/libbpf_naming_convention.html>`_
+* `Building libbpf <https://libbpf.readthedocs.io/en/latest/libbpf_build.html>`_
+* `API documentation Convention <https://libbpf.readthedocs.io/en/latest/libbpf_naming_convention.html#api-documentation-convention>`_

docs/program_types.rst

@@ -0,0 +1,213 @@
+.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+.. _program_types_and_elf:
+
+Program Types and ELF Sections
+==============================
+
+The table below lists the program types, their attach types where relevant and the ELF section
+names supported by libbpf for them. The ELF section names follow these rules:
+
+- ``type`` is an exact match, e.g. ``SEC("socket")``
+- ``type+`` means it can be either exact ``SEC("type")`` or well-formed ``SEC("type/extras")``
+  with a '``/``' separator between ``type`` and ``extras``.
+
+When ``extras`` are specified, they provide details of how to auto-attach the BPF program.  The
+format of ``extras`` depends on the program type, e.g. ``SEC("tracepoint/<category>/<name>")``
+for tracepoints or ``SEC("usdt/<path>:<provider>:<name>")`` for USDT probes. The extras are
+described in more detail in the footnotes.
+
+
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| Program Type                              | Attach Type                            | ELF Section Name                 | Sleepable |
++===========================================+========================================+==================================+===========+
+| ``BPF_PROG_TYPE_CGROUP_DEVICE``           | ``BPF_CGROUP_DEVICE``                  | ``cgroup/dev``                   |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_CGROUP_SKB``              |                                        | ``cgroup/skb``                   |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET_EGRESS``             | ``cgroup_skb/egress``            |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET_INGRESS``            | ``cgroup_skb/ingress``           |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_CGROUP_SOCKOPT``          | ``BPF_CGROUP_GETSOCKOPT``              | ``cgroup/getsockopt``            |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_SETSOCKOPT``              | ``cgroup/setsockopt``            |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_CGROUP_SOCK_ADDR``        | ``BPF_CGROUP_INET4_BIND``              | ``cgroup/bind4``                 |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET4_CONNECT``           | ``cgroup/connect4``              |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET4_GETPEERNAME``       | ``cgroup/getpeername4``          |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET4_GETSOCKNAME``       | ``cgroup/getsockname4``          |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET6_BIND``              | ``cgroup/bind6``                 |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET6_CONNECT``           | ``cgroup/connect6``              |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET6_GETPEERNAME``       | ``cgroup/getpeername6``          |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET6_GETSOCKNAME``       | ``cgroup/getsockname6``          |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_UDP4_RECVMSG``            | ``cgroup/recvmsg4``              |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_UDP4_SENDMSG``            | ``cgroup/sendmsg4``              |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_UDP6_RECVMSG``            | ``cgroup/recvmsg6``              |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_UDP6_SENDMSG``            | ``cgroup/sendmsg6``              |           |
+|                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_UNIX_CONNECT``            | ``cgroup/connect_unix``          |           |
+|                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_UNIX_SENDMSG``            | ``cgroup/sendmsg_unix``          |           |
+|                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_UNIX_RECVMSG``            | ``cgroup/recvmsg_unix``          |           |
+|                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_UNIX_GETPEERNAME``        | ``cgroup/getpeername_unix``      |           |
+|                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_UNIX_GETSOCKNAME``        | ``cgroup/getsockname_unix``      |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_CGROUP_SOCK``             | ``BPF_CGROUP_INET4_POST_BIND``         | ``cgroup/post_bind4``            |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET6_POST_BIND``         | ``cgroup/post_bind6``            |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET_SOCK_CREATE``        | ``cgroup/sock_create``           |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``cgroup/sock``                  |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET_SOCK_RELEASE``       | ``cgroup/sock_release``          |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_CGROUP_SYSCTL``           | ``BPF_CGROUP_SYSCTL``                  | ``cgroup/sysctl``                |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_EXT``                     |                                        | ``freplace+`` [#fentry]_         |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_FLOW_DISSECTOR``          | ``BPF_FLOW_DISSECTOR``                 | ``flow_dissector``               |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_KPROBE``                  |                                        | ``kprobe+`` [#kprobe]_           |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``kretprobe+`` [#kprobe]_        |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``ksyscall+`` [#ksyscall]_       |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        |  ``kretsyscall+`` [#ksyscall]_   |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``uprobe+`` [#uprobe]_           |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``uprobe.s+`` [#uprobe]_         | Yes       |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``uretprobe+`` [#uprobe]_        |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``uretprobe.s+`` [#uprobe]_      | Yes       |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``usdt+`` [#usdt]_               |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_TRACE_KPROBE_MULTI``             | ``kprobe.multi+`` [#kpmulti]_    |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``kretprobe.multi+`` [#kpmulti]_ |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_LIRC_MODE2``              | ``BPF_LIRC_MODE2``                     | ``lirc_mode2``                   |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_LSM``                     | ``BPF_LSM_CGROUP``                     | ``lsm_cgroup+``                  |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_LSM_MAC``                        | ``lsm+`` [#lsm]_                 |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``lsm.s+`` [#lsm]_               | Yes       |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_LWT_IN``                  |                                        | ``lwt_in``                       |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_LWT_OUT``                 |                                        | ``lwt_out``                      |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_LWT_SEG6LOCAL``           |                                        | ``lwt_seg6local``                |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_LWT_XMIT``                |                                        | ``lwt_xmit``                     |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_PERF_EVENT``              |                                        | ``perf_event``                   |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE`` |                                        | ``raw_tp.w+`` [#rawtp]_          |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``raw_tracepoint.w+``            |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_RAW_TRACEPOINT``          |                                        | ``raw_tp+`` [#rawtp]_            |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``raw_tracepoint+``              |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_SCHED_ACT``               |                                        | ``action``                       |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_SCHED_CLS``               |                                        | ``classifier``                   |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``tc``                           |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_SK_LOOKUP``               | ``BPF_SK_LOOKUP``                      | ``sk_lookup``                    |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_SK_MSG``                  | ``BPF_SK_MSG_VERDICT``                 | ``sk_msg``                       |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_SK_REUSEPORT``            | ``BPF_SK_REUSEPORT_SELECT_OR_MIGRATE`` | ``sk_reuseport/migrate``         |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_SK_REUSEPORT_SELECT``            | ``sk_reuseport``                 |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_SK_SKB``                  |                                        | ``sk_skb``                       |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_SK_SKB_STREAM_PARSER``           | ``sk_skb/stream_parser``         |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_SK_SKB_STREAM_VERDICT``          | ``sk_skb/stream_verdict``        |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_SOCKET_FILTER``           |                                        | ``socket``                       |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_SOCK_OPS``                | ``BPF_CGROUP_SOCK_OPS``                | ``sockops``                      |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_STRUCT_OPS``              |                                        | ``struct_ops+``                  |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_SYSCALL``                 |                                        | ``syscall``                      | Yes       |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_TRACEPOINT``              |                                        | ``tp+`` [#tp]_                   |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``tracepoint+`` [#tp]_           |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_TRACING``                 | ``BPF_MODIFY_RETURN``                  | ``fmod_ret+`` [#fentry]_         |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``fmod_ret.s+`` [#fentry]_       | Yes       |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_TRACE_FENTRY``                   | ``fentry+`` [#fentry]_           |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``fentry.s+`` [#fentry]_         | Yes       |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_TRACE_FEXIT``                    | ``fexit+`` [#fentry]_            |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``fexit.s+`` [#fentry]_          | Yes       |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_TRACE_ITER``                     | ``iter+`` [#iter]_               |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``iter.s+`` [#iter]_             | Yes       |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_TRACE_RAW_TP``                   | ``tp_btf+`` [#fentry]_           |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_XDP``                     | ``BPF_XDP_CPUMAP``                     | ``xdp.frags/cpumap``             |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``xdp/cpumap``                   |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_XDP_DEVMAP``                     | ``xdp.frags/devmap``             |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``xdp/devmap``                   |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_XDP``                            | ``xdp.frags``                    |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``xdp``                          |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+
+
+.. rubric:: Footnotes
+
+.. [#fentry] The ``fentry`` attach format is ``fentry[.s]/<function>``.
+.. [#kprobe] The ``kprobe`` attach format is ``kprobe/<function>[+<offset>]``. Valid
+             characters for ``function`` are ``a-zA-Z0-9_.`` and ``offset`` must be a valid
+             non-negative integer.
+.. [#ksyscall] The ``ksyscall`` attach format is ``ksyscall/<syscall>``.
+.. [#uprobe] The ``uprobe`` attach format is ``uprobe[.s]/<path>:<function>[+<offset>]``.
+.. [#usdt] The ``usdt`` attach format is ``usdt/<path>:<provider>:<name>``.
+.. [#kpmulti] The ``kprobe.multi`` attach format is ``kprobe.multi/<pattern>`` where ``pattern``
+              supports ``*`` and ``?`` wildcards. Valid characters for pattern are
+              ``a-zA-Z0-9_.*?``.
+.. [#lsm] The ``lsm`` attachment format is ``lsm[.s]/<hook>``.
+.. [#rawtp] The ``raw_tp`` attach format is ``raw_tracepoint[.w]/<tracepoint>``.
+.. [#tp] The ``tracepoint`` attach format is ``tracepoint/<category>/<name>``.
+.. [#iter] The ``iter`` attach format is ``iter[.s]/<struct-name>``.

docs/sphinx/requirements.txt

@@ -1 +1,2 @@
-breathe
+breathe
+sphinx_rtd_theme

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/filter.h

@@ -37,6 +37,14 @@
 		.off   = 0,					\
 		.imm   = IMM })
 
+#define BPF_CALL_REL(DST)					\
+	((struct bpf_insn) {					\
+		.code = BPF_JMP | BPF_CALL,			\
+		.dst_reg = 0,					\
+		.src_reg = BPF_PSEUDO_CALL,			\
+		.off = 0,					\
+		.imm = DST })
+
 #define BPF_EXIT_INSN()						\
 	((struct bpf_insn) {					\
 		.code  = BPF_JMP | BPF_EXIT,			\

include/linux/kernel.h

@@ -3,6 +3,8 @@
 #ifndef __LINUX_KERNEL_H
 #define __LINUX_KERNEL_H
 
+#include <linux/compiler.h>
+
 #ifndef offsetof
 #define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->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/uapi/linux/btf.h

@@ -33,17 +33,17 @@ struct btf_type {
 	/* "info" bits arrangement
 	 * bits  0-15: vlen (e.g. # of struct's members)
 	 * bits 16-23: unused
-	 * bits 24-27: kind (e.g. int, ptr, array...etc)
-	 * bits 28-30: unused
+	 * bits 24-28: kind (e.g. int, ptr, array...etc)
+	 * bits 29-30: unused
 	 * bit     31: kind_flag, currently used by
-	 *             struct, union and fwd
+	 *             struct, union, enum, fwd and enum64
 	 */
 	__u32 info;
-	/* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC.
+	/* "size" is used by INT, ENUM, STRUCT, UNION, DATASEC and ENUM64.
 	 * "size" tells the size of the type it is describing.
 	 *
 	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
-	 * FUNC, FUNC_PROTO, VAR and DECL_TAG.
+	 * FUNC, FUNC_PROTO, VAR, DECL_TAG and TYPE_TAG.
 	 * "type" is a type_id referring to another type.
 	 */
 	union {
@@ -63,7 +63,7 @@ enum {
 	BTF_KIND_ARRAY		= 3,	/* Array	*/
 	BTF_KIND_STRUCT		= 4,	/* Struct	*/
 	BTF_KIND_UNION		= 5,	/* Union	*/
-	BTF_KIND_ENUM		= 6,	/* Enumeration	*/
+	BTF_KIND_ENUM		= 6,	/* Enumeration up to 32-bit values */
 	BTF_KIND_FWD		= 7,	/* Forward	*/
 	BTF_KIND_TYPEDEF	= 8,	/* Typedef	*/
 	BTF_KIND_VOLATILE	= 9,	/* Volatile	*/
@@ -75,6 +75,8 @@ enum {
 	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 */
+	BTF_KIND_ENUM64		= 19,	/* Enumeration up to 64-bit values */
 
 	NR_BTF_KINDS,
 	BTF_KIND_MAX		= NR_BTF_KINDS - 1,
@@ -185,4 +187,14 @@ struct btf_decl_tag {
        __s32   component_idx;
 };
 
+/* BTF_KIND_ENUM64 is followed by multiple "struct btf_enum64".
+ * The exact number of btf_enum64 is stored in the vlen (of the
+ * info in "struct btf_type").
+ */
+struct btf_enum64 {
+	__u32	name_off;
+	__u32	val_lo32;
+	__u32	val_hi32;
+};
+
 #endif /* _UAPI__LINUX_BTF_H__ */

include/uapi/linux/fcntl.h

@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_FCNTL_H
+#define _UAPI_LINUX_FCNTL_H
+
+#include <asm/fcntl.h>
+#include <linux/openat2.h>
+
+#define F_SETLEASE	(F_LINUX_SPECIFIC_BASE + 0)
+#define F_GETLEASE	(F_LINUX_SPECIFIC_BASE + 1)
+
+/*
+ * Cancel a blocking posix lock; internal use only until we expose an
+ * asynchronous lock api to userspace:
+ */
+#define F_CANCELLK	(F_LINUX_SPECIFIC_BASE + 5)
+
+/* Create a file descriptor with FD_CLOEXEC set. */
+#define F_DUPFD_CLOEXEC	(F_LINUX_SPECIFIC_BASE + 6)
+
+/*
+ * Request nofications on a directory.
+ * See below for events that may be notified.
+ */
+#define F_NOTIFY	(F_LINUX_SPECIFIC_BASE+2)
+
+/*
+ * Set and get of pipe page size array
+ */
+#define F_SETPIPE_SZ	(F_LINUX_SPECIFIC_BASE + 7)
+#define F_GETPIPE_SZ	(F_LINUX_SPECIFIC_BASE + 8)
+
+/*
+ * Set/Get seals
+ */
+#define F_ADD_SEALS	(F_LINUX_SPECIFIC_BASE + 9)
+#define F_GET_SEALS	(F_LINUX_SPECIFIC_BASE + 10)
+
+/*
+ * Types of seals
+ */
+#define F_SEAL_SEAL	0x0001	/* prevent further seals from being set */
+#define F_SEAL_SHRINK	0x0002	/* prevent file from shrinking */
+#define F_SEAL_GROW	0x0004	/* prevent file from growing */
+#define F_SEAL_WRITE	0x0008	/* prevent writes */
+#define F_SEAL_FUTURE_WRITE	0x0010  /* prevent future writes while mapped */
+#define F_SEAL_EXEC	0x0020  /* prevent chmod modifying exec bits */
+/* (1U << 31) is reserved for signed error codes */
+
+/*
+ * Set/Get write life time hints. {GET,SET}_RW_HINT operate on the
+ * underlying inode, while {GET,SET}_FILE_RW_HINT operate only on
+ * the specific file.
+ */
+#define F_GET_RW_HINT		(F_LINUX_SPECIFIC_BASE + 11)
+#define F_SET_RW_HINT		(F_LINUX_SPECIFIC_BASE + 12)
+#define F_GET_FILE_RW_HINT	(F_LINUX_SPECIFIC_BASE + 13)
+#define F_SET_FILE_RW_HINT	(F_LINUX_SPECIFIC_BASE + 14)
+
+/*
+ * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be
+ * used to clear any hints previously set.
+ */
+#define RWH_WRITE_LIFE_NOT_SET	0
+#define RWH_WRITE_LIFE_NONE	1
+#define RWH_WRITE_LIFE_SHORT	2
+#define RWH_WRITE_LIFE_MEDIUM	3
+#define RWH_WRITE_LIFE_LONG	4
+#define RWH_WRITE_LIFE_EXTREME	5
+
+/*
+ * The originally introduced spelling is remained from the first
+ * versions of the patch set that introduced the feature, see commit
+ * v4.13-rc1~212^2~51.
+ */
+#define RWF_WRITE_LIFE_NOT_SET	RWH_WRITE_LIFE_NOT_SET
+
+/*
+ * Types of directory notifications that may be requested.
+ */
+#define DN_ACCESS	0x00000001	/* File accessed */
+#define DN_MODIFY	0x00000002	/* File modified */
+#define DN_CREATE	0x00000004	/* File created */
+#define DN_DELETE	0x00000008	/* File removed */
+#define DN_RENAME	0x00000010	/* File renamed */
+#define DN_ATTRIB	0x00000020	/* File changed attibutes */
+#define DN_MULTISHOT	0x80000000	/* Don't remove notifier */
+
+/*
+ * The constants AT_REMOVEDIR and AT_EACCESS have the same value.  AT_EACCESS is
+ * meaningful only to faccessat, while AT_REMOVEDIR is meaningful only to
+ * unlinkat.  The two functions do completely different things and therefore,
+ * the flags can be allowed to overlap.  For example, passing AT_REMOVEDIR to
+ * faccessat would be undefined behavior and thus treating it equivalent to
+ * AT_EACCESS is valid undefined behavior.
+ */
+#define AT_FDCWD		-100    /* Special value used to indicate
+                                           openat should use the current
+                                           working directory. */
+#define AT_SYMLINK_NOFOLLOW	0x100   /* Do not follow symbolic links.  */
+#define AT_EACCESS		0x200	/* Test access permitted for
+                                           effective IDs, not real IDs.  */
+#define AT_REMOVEDIR		0x200   /* Remove directory instead of
+                                           unlinking file.  */
+#define AT_SYMLINK_FOLLOW	0x400   /* Follow symbolic links.  */
+#define AT_NO_AUTOMOUNT		0x800	/* Suppress terminal automount traversal */
+#define AT_EMPTY_PATH		0x1000	/* Allow empty relative pathname */
+
+#define AT_STATX_SYNC_TYPE	0x6000	/* Type of synchronisation required from statx() */
+#define AT_STATX_SYNC_AS_STAT	0x0000	/* - Do whatever stat() does */
+#define AT_STATX_FORCE_SYNC	0x2000	/* - Force the attributes to be sync'd with the server */
+#define AT_STATX_DONT_SYNC	0x4000	/* - Don't sync attributes with the server */
+
+#define AT_RECURSIVE		0x8000	/* Apply to the entire subtree */
+
+/* Flags for name_to_handle_at(2). We reuse AT_ flag space to save bits... */
+#define AT_HANDLE_FID		AT_REMOVEDIR	/* file handle is needed to
+					compare object identity and may not
+					be usable to open_by_handle_at(2) */
+#if defined(__KERNEL__)
+#define AT_GETATTR_NOSEC	0x80000000
+#endif
+
+#endif /* _UAPI_LINUX_FCNTL_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 +36,204 @@ 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).
+ *
+ * @rx_otherhost_dropped: Number of packets dropped due to mismatch
+ *   in destination MAC address.
+ */
 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 +245,24 @@ struct rtnl_link_stats64 {
 	/* for cslip etc */
 	__u64	rx_compressed;
 	__u64	tx_compressed;
+	__u64	rx_nohandler;
 
-	__u64	rx_nohandler;		/* dropped, no handler found	*/
+	__u64	rx_otherhost_dropped;
+};
+
+/* Subset of link stats useful for in-HW collection. Meaning of the fields is as
+ * for struct rtnl_link_stats64.
+ */
+struct rtnl_hw_stats64 {
+	__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;
 };
 
 /* The struct should be in sync with struct ifmap */
@@ -170,12 +360,38 @@ enum {
 	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_TSO_MAX_SIZE,
+	IFLA_TSO_MAX_SEGS,
+	IFLA_ALLMULTI,		/* Allmulti count: > 0 means acts ALLMULTI */
+
+	IFLA_DEVLINK_PORT,
+
+	IFLA_GSO_IPV4_MAX_SIZE,
+	IFLA_GRO_IPV4_MAX_SIZE,
+	IFLA_DPLL_PIN,
 	__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))))
@@ -293,6 +509,7 @@ enum {
 	IFLA_BR_MCAST_MLD_VERSION,
 	IFLA_BR_VLAN_STATS_PER_PORT,
 	IFLA_BR_MULTI_BOOLOPT,
+	IFLA_BR_MCAST_QUERIER_STATE,
 	__IFLA_BR_MAX,
 };
 
@@ -346,6 +563,14 @@ enum {
 	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_LOCKED,
+	IFLA_BRPORT_MAB,
+	IFLA_BRPORT_MCAST_N_GROUPS,
+	IFLA_BRPORT_MCAST_MAX_GROUPS,
+	IFLA_BRPORT_NEIGH_VLAN_SUPPRESS,
+	IFLA_BRPORT_BACKUP_NHID,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -412,6 +637,7 @@ enum {
 	IFLA_MACVLAN_MACADDR_COUNT,
 	IFLA_MACVLAN_BC_QUEUE_LEN,
 	IFLA_MACVLAN_BC_QUEUE_LEN_USED,
+	IFLA_MACVLAN_BC_CUTOFF,
 	__IFLA_MACVLAN_MAX,
 };
 
@@ -433,6 +659,7 @@ enum macvlan_macaddr_mode {
 };
 
 #define MACVLAN_FLAG_NOPROMISC	1
+#define MACVLAN_FLAG_NODST	2 /* skip dst macvlan if matching src macvlan */
 
 /* VRF section */
 enum {
@@ -479,6 +706,7 @@ enum {
 	IFLA_XFRM_UNSPEC,
 	IFLA_XFRM_LINK,
 	IFLA_XFRM_IF_ID,
+	IFLA_XFRM_COLLECT_METADATA,
 	__IFLA_XFRM_MAX
 };
 
@@ -520,7 +748,79 @@ enum ipvlan_mode {
 #define IPVLAN_F_PRIVATE	0x01
 #define IPVLAN_F_VEPA		0x02
 
+/* Tunnel RTM header */
+struct tunnel_msg {
+	__u8 family;
+	__u8 flags;
+	__u16 reserved2;
+	__u32 ifindex;
+};
+
+/* netkit section */
+enum netkit_action {
+	NETKIT_NEXT	= -1,
+	NETKIT_PASS	= 0,
+	NETKIT_DROP	= 2,
+	NETKIT_REDIRECT	= 7,
+};
+
+enum netkit_mode {
+	NETKIT_L2,
+	NETKIT_L3,
+};
+
+enum {
+	IFLA_NETKIT_UNSPEC,
+	IFLA_NETKIT_PEER_INFO,
+	IFLA_NETKIT_PRIMARY,
+	IFLA_NETKIT_POLICY,
+	IFLA_NETKIT_PEER_POLICY,
+	IFLA_NETKIT_MODE,
+	__IFLA_NETKIT_MAX,
+};
+#define IFLA_NETKIT_MAX	(__IFLA_NETKIT_MAX - 1)
+
 /* VXLAN section */
+
+/* include statistics in the dump */
+#define TUNNEL_MSG_FLAG_STATS	0x01
+
+#define TUNNEL_MSG_VALID_USER_FLAGS TUNNEL_MSG_FLAG_STATS
+
+/* Embedded inside VXLAN_VNIFILTER_ENTRY_STATS */
+enum {
+	VNIFILTER_ENTRY_STATS_UNSPEC,
+	VNIFILTER_ENTRY_STATS_RX_BYTES,
+	VNIFILTER_ENTRY_STATS_RX_PKTS,
+	VNIFILTER_ENTRY_STATS_RX_DROPS,
+	VNIFILTER_ENTRY_STATS_RX_ERRORS,
+	VNIFILTER_ENTRY_STATS_TX_BYTES,
+	VNIFILTER_ENTRY_STATS_TX_PKTS,
+	VNIFILTER_ENTRY_STATS_TX_DROPS,
+	VNIFILTER_ENTRY_STATS_TX_ERRORS,
+	VNIFILTER_ENTRY_STATS_PAD,
+	__VNIFILTER_ENTRY_STATS_MAX
+};
+#define VNIFILTER_ENTRY_STATS_MAX (__VNIFILTER_ENTRY_STATS_MAX - 1)
+
+enum {
+	VXLAN_VNIFILTER_ENTRY_UNSPEC,
+	VXLAN_VNIFILTER_ENTRY_START,
+	VXLAN_VNIFILTER_ENTRY_END,
+	VXLAN_VNIFILTER_ENTRY_GROUP,
+	VXLAN_VNIFILTER_ENTRY_GROUP6,
+	VXLAN_VNIFILTER_ENTRY_STATS,
+	__VXLAN_VNIFILTER_ENTRY_MAX
+};
+#define VXLAN_VNIFILTER_ENTRY_MAX	(__VXLAN_VNIFILTER_ENTRY_MAX - 1)
+
+enum {
+	VXLAN_VNIFILTER_UNSPEC,
+	VXLAN_VNIFILTER_ENTRY,
+	__VXLAN_VNIFILTER_MAX
+};
+#define VXLAN_VNIFILTER_MAX	(__VXLAN_VNIFILTER_MAX - 1)
+
 enum {
 	IFLA_VXLAN_UNSPEC,
 	IFLA_VXLAN_ID,
@@ -552,6 +852,8 @@ enum {
 	IFLA_VXLAN_GPE,
 	IFLA_VXLAN_TTL_INHERIT,
 	IFLA_VXLAN_DF,
+	IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */
+	IFLA_VXLAN_LOCALBYPASS,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
@@ -585,6 +887,7 @@ enum {
 	IFLA_GENEVE_LABEL,
 	IFLA_GENEVE_TTL_INHERIT,
 	IFLA_GENEVE_DF,
+	IFLA_GENEVE_INNER_PROTO_INHERIT,
 	__IFLA_GENEVE_MAX
 };
 #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
@@ -597,6 +900,18 @@ 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,
@@ -618,6 +933,8 @@ enum {
 	IFLA_GTP_FD1,
 	IFLA_GTP_PDP_HASHSIZE,
 	IFLA_GTP_ROLE,
+	IFLA_GTP_CREATE_SOCKETS,
+	IFLA_GTP_RESTART_COUNT,
 	__IFLA_GTP_MAX,
 };
 #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1)
@@ -655,6 +972,9 @@ enum {
 	IFLA_BOND_TLB_DYNAMIC_LB,
 	IFLA_BOND_PEER_NOTIF_DELAY,
 	IFLA_BOND_AD_LACP_ACTIVE,
+	IFLA_BOND_MISSED_MAX,
+	IFLA_BOND_NS_IP6_TARGET,
+	IFLA_BOND_COUPLED_CONTROL,
 	__IFLA_BOND_MAX,
 };
 
@@ -682,6 +1002,7 @@ enum {
 	IFLA_BOND_SLAVE_AD_AGGREGATOR_ID,
 	IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE,
 	IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE,
+	IFLA_BOND_SLAVE_PRIO,
 	__IFLA_BOND_SLAVE_MAX,
 };
 
@@ -899,7 +1220,14 @@ 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,
@@ -909,6 +1237,9 @@ 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,
 };
 
@@ -941,6 +1272,17 @@ enum {
 
 #define IFLA_STATS_FILTER_BIT(ATTR)	(1 << (ATTR - 1))
 
+enum {
+	IFLA_STATS_GETSET_UNSPEC,
+	IFLA_STATS_GET_FILTERS, /* Nest of IFLA_STATS_LINK_xxx, each a u32 with
+				 * a filter mask for the corresponding group.
+				 */
+	IFLA_STATS_SET_OFFLOAD_XSTATS_L3_STATS, /* 0 or 1 as u8 */
+	__IFLA_STATS_GETSET_MAX,
+};
+
+#define IFLA_STATS_GETSET_MAX (__IFLA_STATS_GETSET_MAX - 1)
+
 /* These are embedded into IFLA_STATS_LINK_XSTATS:
  * [IFLA_STATS_LINK_XSTATS]
  * -> [LINK_XSTATS_TYPE_xxx]
@@ -958,10 +1300,21 @@ enum {
 enum {
 	IFLA_OFFLOAD_XSTATS_UNSPEC,
 	IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */
+	IFLA_OFFLOAD_XSTATS_HW_S_INFO,	/* HW stats info. A nest */
+	IFLA_OFFLOAD_XSTATS_L3_STATS,	/* struct rtnl_hw_stats64 */
 	__IFLA_OFFLOAD_XSTATS_MAX
 };
 #define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1)
 
+enum {
+	IFLA_OFFLOAD_XSTATS_HW_S_INFO_UNSPEC,
+	IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST,		/* u8 */
+	IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED,		/* u8 */
+	__IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX,
+};
+#define IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX \
+	(__IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX - 1)
+
 /* XDP section */
 
 #define XDP_FLAGS_UPDATE_IF_NOEXIST	(1U << 0)
@@ -1033,6 +1386,8 @@ 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,
@@ -1048,4 +1403,24 @@ 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)
+
+/* DSA section */
+
+enum {
+	IFLA_DSA_UNSPEC,
+	IFLA_DSA_MASTER,
+	__IFLA_DSA_MAX,
+};
+
+#define IFLA_DSA_MAX	(__IFLA_DSA_MAX - 1)
+
 #endif /* _UAPI_LINUX_IF_LINK_H */

include/uapi/linux/if_xdp.h

@@ -25,9 +25,21 @@
  * application.
  */
 #define XDP_USE_NEED_WAKEUP (1 << 3)
+/* By setting this option, userspace application indicates that it can
+ * handle multiple descriptors per packet thus enabling AF_XDP to split
+ * multi-buffer XDP frames into multiple Rx descriptors. Without this set
+ * such frames will be dropped.
+ */
+#define XDP_USE_SG	(1 << 4)
 
 /* Flags for xsk_umem_config flags */
-#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
+#define XDP_UMEM_UNALIGNED_CHUNK_FLAG	(1 << 0)
+
+/* Force checksum calculation in software. Can be used for testing or
+ * working around potential HW issues. This option causes performance
+ * degradation and only works in XDP_COPY mode.
+ */
+#define XDP_UMEM_TX_SW_CSUM		(1 << 1)
 
 struct sockaddr_xdp {
 	__u16 sxdp_family;
@@ -70,6 +82,7 @@ struct xdp_umem_reg {
 	__u32 chunk_size;
 	__u32 headroom;
 	__u32 flags;
+	__u32 tx_metadata_len;
 };
 
 struct xdp_statistics {
@@ -99,6 +112,41 @@ struct xdp_options {
 #define XSK_UNALIGNED_BUF_ADDR_MASK \
 	((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1)
 
+/* Request transmit timestamp. Upon completion, put it into tx_timestamp
+ * field of union xsk_tx_metadata.
+ */
+#define XDP_TXMD_FLAGS_TIMESTAMP		(1 << 0)
+
+/* Request transmit checksum offload. Checksum start position and offset
+ * are communicated via csum_start and csum_offset fields of union
+ * xsk_tx_metadata.
+ */
+#define XDP_TXMD_FLAGS_CHECKSUM			(1 << 1)
+
+/* AF_XDP offloads request. 'request' union member is consumed by the driver
+ * when the packet is being transmitted. 'completion' union member is
+ * filled by the driver when the transmit completion arrives.
+ */
+struct xsk_tx_metadata {
+	__u64 flags;
+
+	union {
+		struct {
+			/* XDP_TXMD_FLAGS_CHECKSUM */
+
+			/* Offset from desc->addr where checksumming should start. */
+			__u16 csum_start;
+			/* Offset from csum_start where checksum should be stored. */
+			__u16 csum_offset;
+		} request;
+
+		struct {
+			/* XDP_TXMD_FLAGS_TIMESTAMP */
+			__u64 tx_timestamp;
+		} completion;
+	};
+};
+
 /* Rx/Tx descriptor */
 struct xdp_desc {
 	__u64 addr;
@@ -108,4 +156,14 @@ struct xdp_desc {
 
 /* UMEM descriptor is __u64 */
 
+/* Flag indicating that the packet continues with the buffer pointed out by the
+ * next frame in the ring. The end of the packet is signalled by setting this
+ * bit to zero. For single buffer packets, every descriptor has 'options' set
+ * to 0 and this maintains backward compatibility.
+ */
+#define XDP_PKT_CONTD (1 << 0)
+
+/* TX packet carries valid metadata. */
+#define XDP_TX_METADATA (1 << 1)
+
 #endif /* _LINUX_IF_XDP_H */

include/uapi/linux/netdev.h

@@ -0,0 +1,175 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/netdev.yaml */
+/* YNL-GEN uapi header */
+
+#ifndef _UAPI_LINUX_NETDEV_H
+#define _UAPI_LINUX_NETDEV_H
+
+#define NETDEV_FAMILY_NAME	"netdev"
+#define NETDEV_FAMILY_VERSION	1
+
+/**
+ * enum netdev_xdp_act
+ * @NETDEV_XDP_ACT_BASIC: XDP features set supported by all drivers
+ *   (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX)
+ * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT
+ * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements
+ *   ndo_xdp_xmit callback.
+ * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP
+ *   in zero copy mode.
+ * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw
+ *   offloading.
+ * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear
+ *   XDP buffer support in the driver napi callback.
+ * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements
+ *   non-linear XDP buffer support in ndo_xdp_xmit callback.
+ */
+enum netdev_xdp_act {
+	NETDEV_XDP_ACT_BASIC = 1,
+	NETDEV_XDP_ACT_REDIRECT = 2,
+	NETDEV_XDP_ACT_NDO_XMIT = 4,
+	NETDEV_XDP_ACT_XSK_ZEROCOPY = 8,
+	NETDEV_XDP_ACT_HW_OFFLOAD = 16,
+	NETDEV_XDP_ACT_RX_SG = 32,
+	NETDEV_XDP_ACT_NDO_XMIT_SG = 64,
+
+	/* private: */
+	NETDEV_XDP_ACT_MASK = 127,
+};
+
+/**
+ * enum netdev_xdp_rx_metadata
+ * @NETDEV_XDP_RX_METADATA_TIMESTAMP: Device is capable of exposing receive HW
+ *   timestamp via bpf_xdp_metadata_rx_timestamp().
+ * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet
+ *   hash via bpf_xdp_metadata_rx_hash().
+ * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive
+ *   packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag().
+ */
+enum netdev_xdp_rx_metadata {
+	NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
+	NETDEV_XDP_RX_METADATA_HASH = 2,
+	NETDEV_XDP_RX_METADATA_VLAN_TAG = 4,
+};
+
+/**
+ * enum netdev_xsk_flags
+ * @NETDEV_XSK_FLAGS_TX_TIMESTAMP: HW timestamping egress packets is supported
+ *   by the driver.
+ * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the
+ *   driver.
+ */
+enum netdev_xsk_flags {
+	NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1,
+	NETDEV_XSK_FLAGS_TX_CHECKSUM = 2,
+};
+
+enum netdev_queue_type {
+	NETDEV_QUEUE_TYPE_RX,
+	NETDEV_QUEUE_TYPE_TX,
+};
+
+enum netdev_qstats_scope {
+	NETDEV_QSTATS_SCOPE_QUEUE = 1,
+};
+
+enum {
+	NETDEV_A_DEV_IFINDEX = 1,
+	NETDEV_A_DEV_PAD,
+	NETDEV_A_DEV_XDP_FEATURES,
+	NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
+	NETDEV_A_DEV_XDP_RX_METADATA_FEATURES,
+	NETDEV_A_DEV_XSK_FEATURES,
+
+	__NETDEV_A_DEV_MAX,
+	NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
+};
+
+enum {
+	NETDEV_A_PAGE_POOL_ID = 1,
+	NETDEV_A_PAGE_POOL_IFINDEX,
+	NETDEV_A_PAGE_POOL_NAPI_ID,
+	NETDEV_A_PAGE_POOL_INFLIGHT,
+	NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
+	NETDEV_A_PAGE_POOL_DETACH_TIME,
+
+	__NETDEV_A_PAGE_POOL_MAX,
+	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
+};
+
+enum {
+	NETDEV_A_PAGE_POOL_STATS_INFO = 1,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST = 8,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT,
+
+	__NETDEV_A_PAGE_POOL_STATS_MAX,
+	NETDEV_A_PAGE_POOL_STATS_MAX = (__NETDEV_A_PAGE_POOL_STATS_MAX - 1)
+};
+
+enum {
+	NETDEV_A_NAPI_IFINDEX = 1,
+	NETDEV_A_NAPI_ID,
+	NETDEV_A_NAPI_IRQ,
+	NETDEV_A_NAPI_PID,
+
+	__NETDEV_A_NAPI_MAX,
+	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
+};
+
+enum {
+	NETDEV_A_QUEUE_ID = 1,
+	NETDEV_A_QUEUE_IFINDEX,
+	NETDEV_A_QUEUE_TYPE,
+	NETDEV_A_QUEUE_NAPI_ID,
+
+	__NETDEV_A_QUEUE_MAX,
+	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
+};
+
+enum {
+	NETDEV_A_QSTATS_IFINDEX = 1,
+	NETDEV_A_QSTATS_QUEUE_TYPE,
+	NETDEV_A_QSTATS_QUEUE_ID,
+	NETDEV_A_QSTATS_SCOPE,
+	NETDEV_A_QSTATS_RX_PACKETS = 8,
+	NETDEV_A_QSTATS_RX_BYTES,
+	NETDEV_A_QSTATS_TX_PACKETS,
+	NETDEV_A_QSTATS_TX_BYTES,
+	NETDEV_A_QSTATS_RX_ALLOC_FAIL,
+
+	__NETDEV_A_QSTATS_MAX,
+	NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1)
+};
+
+enum {
+	NETDEV_CMD_DEV_GET = 1,
+	NETDEV_CMD_DEV_ADD_NTF,
+	NETDEV_CMD_DEV_DEL_NTF,
+	NETDEV_CMD_DEV_CHANGE_NTF,
+	NETDEV_CMD_PAGE_POOL_GET,
+	NETDEV_CMD_PAGE_POOL_ADD_NTF,
+	NETDEV_CMD_PAGE_POOL_DEL_NTF,
+	NETDEV_CMD_PAGE_POOL_CHANGE_NTF,
+	NETDEV_CMD_PAGE_POOL_STATS_GET,
+	NETDEV_CMD_QUEUE_GET,
+	NETDEV_CMD_NAPI_GET,
+	NETDEV_CMD_QSTATS_GET,
+
+	__NETDEV_CMD_MAX,
+	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
+};
+
+#define NETDEV_MCGRP_MGMT	"mgmt"
+#define NETDEV_MCGRP_PAGE_POOL	"page-pool"
+
+#endif /* _UAPI_LINUX_NETDEV_H */

include/uapi/linux/openat2.h

@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_OPENAT2_H
+#define _UAPI_LINUX_OPENAT2_H
+
+#include <linux/types.h>
+
+/*
+ * Arguments for how openat2(2) should open the target path. If only @flags and
+ * @mode are non-zero, then openat2(2) operates very similarly to openat(2).
+ *
+ * However, unlike openat(2), unknown or invalid bits in @flags result in
+ * -EINVAL rather than being silently ignored. @mode must be zero unless one of
+ * {O_CREAT, O_TMPFILE} are set.
+ *
+ * @flags: O_* flags.
+ * @mode: O_CREAT/O_TMPFILE file mode.
+ * @resolve: RESOLVE_* flags.
+ */
+struct open_how {
+	__u64 flags;
+	__u64 mode;
+	__u64 resolve;
+};
+
+/* how->resolve flags for openat2(2). */
+#define RESOLVE_NO_XDEV		0x01 /* Block mount-point crossings
+					(includes bind-mounts). */
+#define RESOLVE_NO_MAGICLINKS	0x02 /* Block traversal through procfs-style
+					"magic-links". */
+#define RESOLVE_NO_SYMLINKS	0x04 /* Block traversal through all symlinks
+					(implies OEXT_NO_MAGICLINKS) */
+#define RESOLVE_BENEATH		0x08 /* Block "lexical" trickery like
+					"..", symlinks, and absolute
+					paths which escape the dirfd. */
+#define RESOLVE_IN_ROOT		0x10 /* Make all jumps to "/" and ".."
+					be scoped inside the dirfd
+					(similar to chroot(2)). */
+#define RESOLVE_CACHED		0x20 /* Only complete if resolution can be
+					completed through cached lookup. May
+					return -EAGAIN if that's not
+					possible. */
+
+#endif /* _UAPI_LINUX_OPENAT2_H */

include/uapi/linux/pkt_cls.h

@@ -180,7 +180,7 @@ struct tc_u32_sel {
 
 	short			hoff;
 	__be32			hmask;
-	struct tc_u32_key	keys[0];
+	struct tc_u32_key	keys[];
 };
 
 struct tc_u32_mark {
@@ -192,7 +192,7 @@ struct tc_u32_mark {
 struct tc_u32_pcnt {
 	__u64 rcnt;
 	__u64 rhit;
-	__u64 kcnts[0];
+	__u64 kcnts[];
 };
 
 /* Flags */
@@ -204,37 +204,6 @@ struct tc_u32_pcnt {
 
 #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 {
@@ -265,22 +234,6 @@ enum {
 
 #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 {

include/uapi/linux/pkt_sched.h

@@ -457,115 +457,6 @@ enum {
 
 #define TCA_HFSC_MAX (__TCA_HFSC_MAX - 1)
 
-
-/* CBQ section */
-
-#define TC_CBQ_MAXPRIO		8
-#define TC_CBQ_MAXLEVEL		8
-#define TC_CBQ_DEF_EWMA		5
-
-struct tc_cbq_lssopt {
-	unsigned char	change;
-	unsigned char	flags;
-#define TCF_CBQ_LSS_BOUNDED	1
-#define TCF_CBQ_LSS_ISOLATED	2
-	unsigned char  	ewma_log;
-	unsigned char  	level;
-#define TCF_CBQ_LSS_FLAGS	1
-#define TCF_CBQ_LSS_EWMA	2
-#define TCF_CBQ_LSS_MAXIDLE	4
-#define TCF_CBQ_LSS_MINIDLE	8
-#define TCF_CBQ_LSS_OFFTIME	0x10
-#define TCF_CBQ_LSS_AVPKT	0x20
-	__u32		maxidle;
-	__u32		minidle;
-	__u32		offtime;
-	__u32		avpkt;
-};
-
-struct tc_cbq_wrropt {
-	unsigned char	flags;
-	unsigned char	priority;
-	unsigned char	cpriority;
-	unsigned char	__reserved;
-	__u32		allot;
-	__u32		weight;
-};
-
-struct tc_cbq_ovl {
-	unsigned char	strategy;
-#define	TC_CBQ_OVL_CLASSIC	0
-#define	TC_CBQ_OVL_DELAY	1
-#define	TC_CBQ_OVL_LOWPRIO	2
-#define	TC_CBQ_OVL_DROP		3
-#define	TC_CBQ_OVL_RCLASSIC	4
-	unsigned char	priority2;
-	__u16		pad;
-	__u32		penalty;
-};
-
-struct tc_cbq_police {
-	unsigned char	police;
-	unsigned char	__res1;
-	unsigned short	__res2;
-};
-
-struct tc_cbq_fopt {
-	__u32		split;
-	__u32		defmap;
-	__u32		defchange;
-};
-
-struct tc_cbq_xstats {
-	__u32		borrows;
-	__u32		overactions;
-	__s32		avgidle;
-	__s32		undertime;
-};
-
-enum {
-	TCA_CBQ_UNSPEC,
-	TCA_CBQ_LSSOPT,
-	TCA_CBQ_WRROPT,
-	TCA_CBQ_FOPT,
-	TCA_CBQ_OVL_STRATEGY,
-	TCA_CBQ_RATE,
-	TCA_CBQ_RTAB,
-	TCA_CBQ_POLICE,
-	__TCA_CBQ_MAX,
-};
-
-#define TCA_CBQ_MAX	(__TCA_CBQ_MAX - 1)
-
-/* dsmark section */
-
-enum {
-	TCA_DSMARK_UNSPEC,
-	TCA_DSMARK_INDICES,
-	TCA_DSMARK_DEFAULT_INDEX,
-	TCA_DSMARK_SET_TC_INDEX,
-	TCA_DSMARK_MASK,
-	TCA_DSMARK_VALUE,
-	__TCA_DSMARK_MAX,
-};
-
-#define TCA_DSMARK_MAX (__TCA_DSMARK_MAX - 1)
-
-/* ATM  section */
-
-enum {
-	TCA_ATM_UNSPEC,
-	TCA_ATM_FD,		/* file/socket descriptor */
-	TCA_ATM_PTR,		/* pointer to descriptor - later */
-	TCA_ATM_HDR,		/* LL header */
-	TCA_ATM_EXCESS,		/* excess traffic class (0 for CLP)  */
-	TCA_ATM_ADDR,		/* PVC address (for output only) */
-	TCA_ATM_STATE,		/* VC state (ATM_VS_*; for output only) */
-	__TCA_ATM_MAX,
-};
-
-#define TCA_ATM_MAX	(__TCA_ATM_MAX - 1)
-
 /* Network emulator */
 
 enum {

scripts/build-fuzzers.sh

@@ -0,0 +1,82 @@
+#!/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=${LIB_FUZZING_ENGINE:--fsanitize=fuzzer}
+
+# libelf is compiled with _FORTIFY_SOURCE by default and it
+# isn't compatible with MSan. It was borrowed
+# from https://github.com/google/oss-fuzz/pull/7422
+if [[ "$SANITIZER" == memory ]]; then
+    CFLAGS+=" -U_FORTIFY_SOURCE"
+    CXXFLAGS+=" -U_FORTIFY_SOURCE"
+fi
+
+# The alignment check is turned off by default on OSS-Fuzz/CFLite so it should be
+# turned on explicitly there. It was borrowed from
+# https://github.com/google/oss-fuzz/pull/7092
+if [[ "$SANITIZER" == undefined ]]; then
+    additional_ubsan_checks=alignment
+    UBSAN_FLAGS="-fsanitize=$additional_ubsan_checks -fno-sanitize-recover=$additional_ubsan_checks"
+    CFLAGS+=" $UBSAN_FLAGS"
+    CXXFLAGS+=" $UBSAN_FLAGS"
+fi
+
+# 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 https://sourceware.org/git/elfutils.git
+(
+cd elfutils
+git checkout 67a187d4c1790058fc7fd218317851cb68bb087c
+git log --oneline -1
+
+# ASan isn't compatible with -Wl,--no-undefined: https://github.com/google/sanitizers/issues/380
+sed -i 's/^\(NO_UNDEFINED=\).*/\1/' configure.ac
+
+# 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
+
+if [[ "$SANITIZER" == undefined ]]; then
+    # That's basicaly what --enable-sanitize-undefined does to turn off unaligned access
+    # elfutils heavily relies on on i386/x86_64 but without changing compiler flags along the way
+    sed -i 's/\(check_undefined_val\)=[0-9]/\1=1/' configure.ac
+fi
+
+autoreconf -i -f
+if ! ./configure --enable-maintainer-mode --disable-debuginfod --disable-libdebuginfod \
+            --disable-demangler --without-bzlib --without-lzma --without-zstd \
+	    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/mailmap-update.sh

@@ -0,0 +1,37 @@
+#!/usr/bin/env bash
+
+set -eu
+
+usage () {
+    echo "USAGE: ./mailmap-update.sh <libbpf-repo> <linux-repo>"
+    exit 1
+}
+
+LIBBPF_REPO="${1-""}"
+LINUX_REPO="${2-""}"
+
+if [ -z "${LIBBPF_REPO}" ] || [ -z "${LINUX_REPO}" ]; then
+    echo "Error: libbpf or linux repos are not specified"
+    usage
+fi
+
+LIBBPF_MAILMAP="${LIBBPF_REPO}/.mailmap"
+LINUX_MAILMAP="${LINUX_REPO}/.mailmap"
+
+tmpfile="$(mktemp)"
+cleanup() {
+    rm -f "${tmpfile}"
+}
+trap cleanup EXIT
+
+grep_lines() {
+    local pattern="$1"
+    local file="$2"
+    grep "${pattern}" "${file}" || true
+}
+
+while read -r email; do
+    grep_lines "${email}$" "${LINUX_MAILMAP}" >> "${tmpfile}"
+done < <(git log --format='<%ae>' | sort -u)
+
+sort -u "${tmpfile}" > "${LIBBPF_MAILMAP}"

scripts/sync-kernel.sh

@@ -42,16 +42,20 @@ PATH_MAP=(									\
 	[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/fcntl.h]=include/uapi/linux/fcntl.h		\
+	[tools/include/uapi/linux/openat2.h]=include/uapi/linux/openat2.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/netdev.h]=include/uapi/linux/netdev.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_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$'
 
@@ -84,7 +88,9 @@ commit_desc()
 # $2 - paths filter
 commit_signature()
 {
-	git show --pretty='("%s")|%aI|%b' --shortstat $1 -- ${2-.} | tr '\n' '|'
+	local ref=$1
+	shift
+	git show --pretty='("%s")|%aI|%b' --shortstat $ref -- "${@-.}" | tr '\n' '|'
 }
 
 # Cherry-pick commits touching libbpf-related files
@@ -103,7 +109,7 @@ cherry_pick_commits()
 	local libbpf_conflict_cnt
 	local desc
 
-	new_commits=$(git rev-list --no-merges --topo-order --reverse ${baseline_tag}..${tip_tag} ${LIBBPF_PATHS[@]})
+	new_commits=$(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[@]}")"
@@ -137,7 +143,7 @@ cherry_pick_commits()
 		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 -- ${LIBBPF_PATHS[@]} | wc -l)
+			libbpf_conflict_cnt=$(git diff --name-only --diff-filter=U -- "${LIBBPF_PATHS[@]}" | wc -l)
 			conflict_cnt=$(git diff --name-only | wc -l)
 			prompt_resolution=1
 
@@ -256,15 +262,18 @@ if ((${COMMIT_CNT} <= 0)); then
 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
+git format-patch --no-signature ${SQUASH_BASE_TAG}..${SQUASH_TIP_TAG} --cover-letter -o ${TMP_DIR}/patches
 
 # Now is time to re-apply libbpf-related linux patches to libbpf repo
 cd_to ${LIBBPF_REPO}
 git checkout -b ${LIBBPF_SYNC_TAG}
 
 for patch in $(ls -1 ${TMP_DIR}/patches | tail -n +2); do
-	if ! git am --3way --committer-date-is-author-date "${TMP_DIR}/patches/${patch}"; then
-		read -p "Applying ${TMP_DIR}/patches/${patch} failed, please resolve manually and press <return> to proceed..."
+	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
 
@@ -280,12 +289,28 @@ cd_to ${LIBBPF_REPO}
 helpers_changes=$(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
+	git commit -s -m "sync: auto-generate latest BPF helpers
 
 Latest changes to BPF helper definitions.
 " -- src/bpf_helper_defs.h
 fi
 
+echo "Regenerating .mailmap..."
+cd_to "${LINUX_REPO}"
+git checkout "${TIP_SYM_REF}"
+cd_to "${LIBBPF_REPO}"
+"${LIBBPF_REPO}"/scripts/mailmap-update.sh "${LIBBPF_REPO}" "${LINUX_REPO}"
+# if anything changed, commit it
+mailmap_changes=$(git status --porcelain .mailmap | wc -l)
+if ((${mailmap_changes} == 1)); then
+	git add .mailmap
+	git commit -s -m "sync: update .mailmap
+
+Update .mailmap based on libbpf's list of contributors and on the latest
+.mailmap version in the upstream repository.
+" -- .mailmap
+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)
@@ -302,7 +327,7 @@ 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=-
+git commit -s --file=-
 
 echo "SUCCESS! ${COMMIT_CNT} commits synced."
 
@@ -312,10 +337,10 @@ cd_to ${LINUX_REPO}
 git checkout -b ${VIEW_TAG} ${TIP_COMMIT}
 FILTER_BRANCH_SQUELCH_WARNING=1 git filter-branch -f --tree-filter "${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}" > ${TMP_DIR}/linux-view.ls
+git ls-files -- "${LIBBPF_VIEW_PATHS[@]}" | grep -v -E "${LINUX_VIEW_EXCLUDE_REGEX}" > ${TMP_DIR}/linux-view.ls
 
 cd_to ${LIBBPF_REPO}
-git ls-files -- ${LIBBPF_VIEW_PATHS[@]} | grep -v -E "${LIBBPF_VIEW_EXCLUDE_REGEX}" > ${TMP_DIR}/github-view.ls
+git ls-files -- "${LIBBPF_VIEW_PATHS[@]}" | grep -v -E "${LIBBPF_VIEW_EXCLUDE_REGEX}" > ${TMP_DIR}/github-view.ls
 
 echo "Comparing list of files..."
 diff -u ${TMP_DIR}/linux-view.ls ${TMP_DIR}/github-view.ls

src/Makefile

@@ -5,13 +5,27 @@ ifeq ($(V),1)
 	msg =
 else
 	Q = @
-	msg = @printf '  %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))";
+	msg = @printf '  %-8s %s%s\n' "$(1)" "$(2)" "$(if $(3), $(3))";
 endif
 
-LIBBPF_VERSION := $(shell \
-	grep -oE '^LIBBPF_([0-9.]+)' libbpf.map | \
-	sort -rV | head -n1 | cut -d'_' -f2)
-LIBBPF_MAJOR_VERSION := $(firstword $(subst ., ,$(LIBBPF_VERSION)))
+LIBBPF_MAJOR_VERSION := 1
+LIBBPF_MINOR_VERSION := 5
+LIBBPF_PATCH_VERSION := 0
+LIBBPF_VERSION := $(LIBBPF_MAJOR_VERSION).$(LIBBPF_MINOR_VERSION).$(LIBBPF_PATCH_VERSION)
+LIBBPF_MAJMIN_VERSION := $(LIBBPF_MAJOR_VERSION).$(LIBBPF_MINOR_VERSION).0
+LIBBPF_MAP_VERSION := $(shell grep -oE '^LIBBPF_([0-9.]+)' libbpf.map | sort -rV | head -n1 | cut -d'_' -f2)
+ifneq ($(LIBBPF_MAJMIN_VERSION), $(LIBBPF_MAP_VERSION))
+$(error Libbpf release ($(LIBBPF_VERSION)) and map ($(LIBBPF_MAP_VERSION)) versions are out of sync!)
+endif
+
+define allow-override
+  $(if $(or $(findstring environment,$(origin $(1))),\
+            $(findstring command line,$(origin $(1)))),,\
+    $(eval $(1) = $(2)))
+endef
+
+$(call allow-override,CC,$(CROSS_COMPILE)cc)
+$(call allow-override,LD,$(CROSS_COMPILE)ld)
 
 TOPDIR = ..
 
@@ -20,9 +34,13 @@ ALL_CFLAGS := $(INCLUDES)
 
 SHARED_CFLAGS += -fPIC -fvisibility=hidden -DSHARED
 
-CFLAGS ?= -g -O2 -Werror -Wall
-ALL_CFLAGS += $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
-ALL_LDFLAGS += $(LDFLAGS)
+CFLAGS ?= -g -O2 -Werror -Wall -std=gnu89
+ALL_CFLAGS += $(CFLAGS) 						\
+	      -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64		\
+	      -Wno-unknown-warning-option -Wno-format-overflow		\
+	      $(EXTRA_CFLAGS)
+ALL_LDFLAGS += $(LDFLAGS) $(EXTRA_LDFLAGS)
+
 ifdef NO_PKG_CONFIG
 	ALL_LDFLAGS += -lelf -lz
 else
@@ -35,9 +53,9 @@ 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 \
+	nlattr.o str_error.o libbpf_probes.o bpf_prog_linfo.o \
 	btf_dump.o hashmap.o ringbuf.o strset.o linker.o gen_loader.o \
-	relo_core.o
+	relo_core.o usdt.o zip.o elf.o features.o
 SHARED_OBJS := $(addprefix $(SHARED_OBJDIR)/,$(OBJS))
 STATIC_OBJS := $(addprefix $(STATIC_OBJDIR)/,$(OBJS))
 
@@ -49,9 +67,10 @@ ifndef BUILD_STATIC_ONLY
 	VERSION_SCRIPT := libbpf.map
 endif
 
-HEADERS := bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h xsk.h \
+HEADERS := bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h \
 	   bpf_helpers.h bpf_helper_defs.h bpf_tracing.h \
-	   bpf_endian.h bpf_core_read.h skel_internal.h libbpf_version.h
+	   bpf_endian.h bpf_core_read.h skel_internal.h libbpf_version.h \
+	   usdt.bpf.h
 UAPI_HEADERS := $(addprefix $(TOPDIR)/include/uapi/linux/,\
 			    bpf.h bpf_common.h btf.h)
 
@@ -61,7 +80,8 @@ INSTALL = install
 
 DESTDIR ?=
 
-ifeq ($(filter-out %64 %64be %64eb %64le %64el s390x, $(shell uname -m)),)
+HOSTARCH = $(firstword $(subst -, ,$(shell $(CC) -dumpmachine)))
+ifeq ($(filter-out %64 %64be %64eb %64le %64el s390x, $(HOSTARCH)),)
 	LIBSUBDIR := lib64
 else
 	LIBSUBDIR := lib
@@ -99,7 +119,7 @@ $(OBJDIR)/libbpf.so.$(LIBBPF_VERSION): $(SHARED_OBJS)
 		  -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \
 		  $^ $(ALL_LDFLAGS) -o $@
 
-$(OBJDIR)/libbpf.pc:
+$(OBJDIR)/libbpf.pc: force
 	$(Q)sed -e "s|@PREFIX@|$(PREFIX)|" \
 		-e "s|@LIBDIR@|$(LIBDIR_PC)|" \
 		-e "s|@VERSION@|$(LIBBPF_VERSION)|" \
@@ -152,7 +172,7 @@ clean:
 	$(call msg,CLEAN)
 	$(Q)rm -rf *.o *.a *.so *.so.* *.pc $(SHARED_OBJDIR) $(STATIC_OBJDIR)
 
-.PHONY: cscope tags
+.PHONY: cscope tags force
 cscope:
 	$(call msg,CSCOPE)
 	$(Q)ls *.c *.h > cscope.files
@@ -162,3 +182,5 @@ tags:
 	$(call msg,CTAGS)
 	$(Q)rm -f TAGS tags
 	$(Q)ls *.c *.h | xargs $(TAGS_PROG) -a
+
+force:

src/bpf.h

@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 
 /*
- * common eBPF ELF operations.
+ * Common BPF ELF operations.
  *
  * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
  * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
@@ -29,92 +29,121 @@
 #include <stdint.h>
 
 #include "libbpf_common.h"
+#include "libbpf_legacy.h"
 
 #ifdef __cplusplus
 extern "C" {
 #endif
 
-struct bpf_create_map_attr {
-	const char *name;
-	enum bpf_map_type map_type;
-	__u32 map_flags;
-	__u32 key_size;
-	__u32 value_size;
-	__u32 max_entries;
-	__u32 numa_node;
+LIBBPF_API 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;
-	union {
-		__u32 inner_map_fd;
-		__u32 btf_vmlinux_value_type_id;
-	};
+	__s32 value_type_btf_obj_fd;
+
+	__u32 token_fd;
+	size_t :0;
 };
+#define bpf_map_create_opts__last_field token_fd
 
-LIBBPF_API int
-bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr);
-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_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_API int bpf_create_map(enum bpf_map_type map_type, int key_size,
-			      int value_size, int max_entries, __u32 map_flags);
-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_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);
+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_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;
 
-struct bpf_load_program_attr {
-	enum bpf_prog_type prog_type;
 	enum bpf_attach_type expected_attach_type;
-	const char *name;
-	const struct bpf_insn *insns;
-	size_t insns_cnt;
-	const char *license;
-	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;
+	__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 line_info_rec_size;
+	__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 prog_flags;
+	__u32 log_size;
+	char *log_buf;
+	/* output: actual total log contents size (including termintaing zero).
+	 * It could be both larger than original log_size (if log was
+	 * truncated), or smaller (if log buffer wasn't filled completely).
+	 * If kernel doesn't support this feature, log_size is left unchanged.
+	 */
+	__u32 log_true_size;
+	__u32 token_fd;
+	size_t :0;
 };
+#define bpf_prog_load_opts__last_field token_fd
+
+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,
+			     struct bpf_prog_load_opts *opts);
 
 /* 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_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_API int bpf_verify_program(enum bpf_prog_type type,
-				  const struct bpf_insn *insns,
-				  size_t insns_cnt, __u32 prog_flags,
-				  const char *license, __u32 kern_version,
-				  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;
+	/* output: actual total log contents size (including termintaing zero).
+	 * It could be both larger than original log_size (if log was
+	 * truncated), or smaller (if log buffer wasn't filled completely).
+	 * If kernel doesn't support this feature, log_size is left unchanged.
+	 */
+	__u32 log_true_size;
+
+	__u32 btf_flags;
+	__u32 token_fd;
+	size_t :0;
+};
+#define bpf_btf_load_opts__last_field token_fd
+
+LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size,
+			    struct bpf_btf_load_opts *opts);
 
 LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value,
 				   __u64 flags);
@@ -127,6 +156,7 @@ LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key,
 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_delete_elem_flags(int fd, const void *key, __u64 flags);
 LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key);
 LIBBPF_API int bpf_map_freeze(int fd);
 
@@ -137,39 +167,228 @@ struct bpf_map_batch_opts {
 };
 #define bpf_map_batch_opts__last_field flags
 
-LIBBPF_API int bpf_map_delete_batch(int fd, void *keys,
+
+/**
+ * @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. Both *in_batch* and *out_batch* must point to memory large enough to
+ * hold a single key, except for maps of type **BPF_MAP_TYPE_{HASH, PERCPU_HASH,
+ * LRU_HASH, LRU_PERCPU_HASH}**, for which the memory size must be at
+ * least 4 bytes wide regardless of key size.
+ *
+ * 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*. If not NULL, must be large
+ * enough to hold a key. For **BPF_MAP_TYPE_{HASH, PERCPU_HASH, LRU_HASH,
+ * LRU_PERCPU_HASH}**, the memory size must be at least 4 bytes wide regardless
+ * of key size.
+ * @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);
-LIBBPF_API int bpf_map_update_batch(int fd, void *keys, void *values,
+
+/**
+ * @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 {
+struct bpf_obj_pin_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */
-	unsigned int flags;
-	int replace_prog_fd;
+
+	__u32 file_flags;
+	int path_fd;
+
+	size_t :0;
 };
-#define bpf_prog_attach_opts__last_field replace_prog_fd
+#define bpf_obj_pin_opts__last_field path_fd
+
+LIBBPF_API int bpf_obj_pin(int fd, const char *pathname);
+LIBBPF_API int bpf_obj_pin_opts(int fd, const char *pathname,
+				const struct bpf_obj_pin_opts *opts);
+
+struct bpf_obj_get_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+
+	__u32 file_flags;
+	int path_fd;
+
+	size_t :0;
+};
+#define bpf_obj_get_opts__last_field path_fd
+
+LIBBPF_API int bpf_obj_get(const char *pathname);
+LIBBPF_API int bpf_obj_get_opts(const char *pathname,
+				const struct bpf_obj_get_opts *opts);
 
 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_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);
 
+struct bpf_prog_attach_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u32 flags;
+	union {
+		int replace_prog_fd;
+		int replace_fd;
+	};
+	int relative_fd;
+	__u32 relative_id;
+	__u64 expected_revision;
+	size_t :0;
+};
+#define bpf_prog_attach_opts__last_field expected_revision
+
+struct bpf_prog_detach_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u32 flags;
+	int relative_fd;
+	__u32 relative_id;
+	__u64 expected_revision;
+	size_t :0;
+};
+#define bpf_prog_detach_opts__last_field expected_revision
+
+/**
+ * @brief **bpf_prog_attach_opts()** attaches the BPF program corresponding to
+ * *prog_fd* to a *target* which can represent a file descriptor or netdevice
+ * ifindex.
+ *
+ * @param prog_fd BPF program file descriptor
+ * @param target attach location file descriptor or ifindex
+ * @param type attach type for the BPF program
+ * @param opts options for configuring the attachment
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
+LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int target,
+				    enum bpf_attach_type type,
+				    const struct bpf_prog_attach_opts *opts);
+
+/**
+ * @brief **bpf_prog_detach_opts()** detaches the BPF program corresponding to
+ * *prog_fd* from a *target* which can represent a file descriptor or netdevice
+ * ifindex.
+ *
+ * @param prog_fd BPF program file descriptor
+ * @param target detach location file descriptor or ifindex
+ * @param type detach type for the BPF program
+ * @param opts options for configuring the detachment
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
+LIBBPF_API int bpf_prog_detach_opts(int prog_fd, int target,
+				    enum bpf_attach_type type,
+				    const struct bpf_prog_detach_opts *opts);
+
 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 */
@@ -181,10 +400,45 @@ struct bpf_link_create_opts {
 		struct {
 			__u64 bpf_cookie;
 		} perf_event;
+		struct {
+			__u32 flags;
+			__u32 cnt;
+			const char **syms;
+			const unsigned long *addrs;
+			const __u64 *cookies;
+		} kprobe_multi;
+		struct {
+			__u32 flags;
+			__u32 cnt;
+			const char *path;
+			const unsigned long *offsets;
+			const unsigned long *ref_ctr_offsets;
+			const __u64 *cookies;
+			__u32 pid;
+		} uprobe_multi;
+		struct {
+			__u64 cookie;
+		} tracing;
+		struct {
+			__u32 pf;
+			__u32 hooknum;
+			__s32 priority;
+			__u32 flags;
+		} netfilter;
+		struct {
+			__u32 relative_fd;
+			__u32 relative_id;
+			__u64 expected_revision;
+		} tcx;
+		struct {
+			__u32 relative_fd;
+			__u32 relative_id;
+			__u64 expected_revision;
+		} netkit;
 	};
 	size_t :0;
 };
-#define bpf_link_create_opts__last_field perf_event
+#define bpf_link_create_opts__last_field uprobe_multi.pid
 
 LIBBPF_API int bpf_link_create(int prog_fd, int target_fd,
 			       enum bpf_attach_type attach_type,
@@ -196,8 +450,9 @@ 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 */
+	__u32 old_map_fd;  /* expected old map FD */
 };
-#define bpf_link_update_opts__last_field old_prog_fd
+#define bpf_link_update_opts__last_field old_map_fd
 
 LIBBPF_API int bpf_link_update(int link_fd, int new_prog_fd,
 			       const struct bpf_link_update_opts *opts);
@@ -221,36 +476,170 @@ struct bpf_prog_test_run_attr {
 			     * out: length of cxt_out */
 };
 
-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.
- */
-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);
+
+struct bpf_get_fd_by_id_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u32 open_flags; /* permissions requested for the operation on fd */
+	size_t :0;
+};
+#define bpf_get_fd_by_id_opts__last_field open_flags
+
 LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_prog_get_fd_by_id_opts(__u32 id,
+				const struct bpf_get_fd_by_id_opts *opts);
 LIBBPF_API int bpf_map_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_map_get_fd_by_id_opts(__u32 id,
+				const struct bpf_get_fd_by_id_opts *opts);
 LIBBPF_API int bpf_btf_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_btf_get_fd_by_id_opts(__u32 id,
+				const struct bpf_get_fd_by_id_opts *opts);
 LIBBPF_API int bpf_link_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_link_get_fd_by_id_opts(__u32 id,
+				const struct bpf_get_fd_by_id_opts *opts);
 LIBBPF_API int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len);
+
+/**
+ * @brief **bpf_prog_get_info_by_fd()** obtains information about the BPF
+ * program corresponding to *prog_fd*.
+ *
+ * Populates up to *info_len* bytes of *info* and updates *info_len* with the
+ * actual number of bytes written to *info*. Note that *info* should be
+ * zero-initialized or initialized as expected by the requested *info*
+ * type. Failing to (zero-)initialize *info* under certain circumstances can
+ * result in this helper returning an error.
+ *
+ * @param prog_fd BPF program file descriptor
+ * @param info pointer to **struct bpf_prog_info** that will be populated with
+ * BPF program information
+ * @param info_len pointer to the size of *info*; on success updated with the
+ * number of bytes written to *info*
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
+LIBBPF_API int bpf_prog_get_info_by_fd(int prog_fd, struct bpf_prog_info *info, __u32 *info_len);
+
+/**
+ * @brief **bpf_map_get_info_by_fd()** obtains information about the BPF
+ * map corresponding to *map_fd*.
+ *
+ * Populates up to *info_len* bytes of *info* and updates *info_len* with the
+ * actual number of bytes written to *info*. Note that *info* should be
+ * zero-initialized or initialized as expected by the requested *info*
+ * type. Failing to (zero-)initialize *info* under certain circumstances can
+ * result in this helper returning an error.
+ *
+ * @param map_fd BPF map file descriptor
+ * @param info pointer to **struct bpf_map_info** that will be populated with
+ * BPF map information
+ * @param info_len pointer to the size of *info*; on success updated with the
+ * number of bytes written to *info*
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
+LIBBPF_API int bpf_map_get_info_by_fd(int map_fd, struct bpf_map_info *info, __u32 *info_len);
+
+/**
+ * @brief **bpf_btf_get_info_by_fd()** obtains information about the
+ * BTF object corresponding to *btf_fd*.
+ *
+ * Populates up to *info_len* bytes of *info* and updates *info_len* with the
+ * actual number of bytes written to *info*. Note that *info* should be
+ * zero-initialized or initialized as expected by the requested *info*
+ * type. Failing to (zero-)initialize *info* under certain circumstances can
+ * result in this helper returning an error.
+ *
+ * @param btf_fd BTF object file descriptor
+ * @param info pointer to **struct bpf_btf_info** that will be populated with
+ * BTF object information
+ * @param info_len pointer to the size of *info*; on success updated with the
+ * number of bytes written to *info*
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
+LIBBPF_API int bpf_btf_get_info_by_fd(int btf_fd, struct bpf_btf_info *info, __u32 *info_len);
+
+/**
+ * @brief **bpf_btf_get_info_by_fd()** obtains information about the BPF
+ * link corresponding to *link_fd*.
+ *
+ * Populates up to *info_len* bytes of *info* and updates *info_len* with the
+ * actual number of bytes written to *info*. Note that *info* should be
+ * zero-initialized or initialized as expected by the requested *info*
+ * type. Failing to (zero-)initialize *info* under certain circumstances can
+ * result in this helper returning an error.
+ *
+ * @param link_fd BPF link file descriptor
+ * @param info pointer to **struct bpf_link_info** that will be populated with
+ * BPF link information
+ * @param info_len pointer to the size of *info*; on success updated with the
+ * number of bytes written to *info*
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
+LIBBPF_API int bpf_link_get_info_by_fd(int link_fd, struct bpf_link_info *info, __u32 *info_len);
+
+struct bpf_prog_query_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u32 query_flags;
+	__u32 attach_flags; /* output argument */
+	__u32 *prog_ids;
+	union {
+		/* input+output argument */
+		__u32 prog_cnt;
+		__u32 count;
+	};
+	__u32 *prog_attach_flags;
+	__u32 *link_ids;
+	__u32 *link_attach_flags;
+	__u64 revision;
+	size_t :0;
+};
+#define bpf_prog_query_opts__last_field revision
+
+/**
+ * @brief **bpf_prog_query_opts()** queries the BPF programs and BPF links
+ * which are attached to *target* which can represent a file descriptor or
+ * netdevice ifindex.
+ *
+ * @param target query location file descriptor or ifindex
+ * @param type attach type for the BPF program
+ * @param opts options for configuring the query
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
+LIBBPF_API int bpf_prog_query_opts(int target, enum bpf_attach_type type,
+				   struct bpf_prog_query_opts *opts);
 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);
+
+struct bpf_raw_tp_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	const char *tp_name;
+	__u64 cookie;
+	size_t :0;
+};
+#define bpf_raw_tp_opts__last_field cookie
+
+LIBBPF_API int bpf_raw_tracepoint_open_opts(int prog_fd, struct bpf_raw_tp_opts *opts);
 LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd);
-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_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);
 
+#ifdef __cplusplus
+/* forward-declaring enums in C++ isn't compatible with pure C enums, so
+ * instead define bpf_enable_stats() as accepting int as an input
+ */
+LIBBPF_API int bpf_enable_stats(int type);
+#else
 enum bpf_stats_type; /* defined in up-to-date linux/bpf.h */
 LIBBPF_API int bpf_enable_stats(enum bpf_stats_type type);
+#endif
 
 struct bpf_prog_bind_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */
@@ -280,12 +669,37 @@ struct bpf_test_run_opts {
 	__u32 duration;      /* out: average per repetition in ns */
 	__u32 flags;
 	__u32 cpu;
+	__u32 batch_size;
 };
-#define bpf_test_run_opts__last_field cpu
+#define bpf_test_run_opts__last_field batch_size
 
 LIBBPF_API int bpf_prog_test_run_opts(int prog_fd,
 				      struct bpf_test_run_opts *opts);
 
+struct bpf_token_create_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u32 flags;
+	size_t :0;
+};
+#define bpf_token_create_opts__last_field flags
+
+/**
+ * @brief **bpf_token_create()** creates a new instance of BPF token derived
+ * from specified BPF FS mount point.
+ *
+ * BPF token created with this API can be passed to bpf() syscall for
+ * commands like BPF_PROG_LOAD, BPF_MAP_CREATE, etc.
+ *
+ * @param bpffs_fd FD for BPF FS instance from which to derive a BPF token
+ * instance.
+ * @param opts optional BPF token creation options, can be NULL
+ *
+ * @return BPF token FD > 0, on success; negative error code, otherwise (errno
+ * is also set to the error code)
+ */
+LIBBPF_API int bpf_token_create(int bpffs_fd,
+				struct bpf_token_create_opts *opts);
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif

src/bpf_core_read.h

@@ -2,6 +2,8 @@
 #ifndef __BPF_CORE_READ_H__
 #define __BPF_CORE_READ_H__
 
+#include "bpf_helpers.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
@@ -29,6 +31,7 @@ enum bpf_type_id_kind {
 enum bpf_type_info_kind {
 	BPF_TYPE_EXISTS = 0,		/* type existence in target kernel */
 	BPF_TYPE_SIZE = 1,		/* type size in target kernel */
+	BPF_TYPE_MATCHES = 2,		/* type match in target kernel */
 };
 
 /* second argument to __builtin_preserve_enum_value() built-in */
@@ -43,7 +46,7 @@ enum bpf_enum_value_kind {
 #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 #define __CORE_BITFIELD_PROBE_READ(dst, src, fld)			      \
 	bpf_probe_read_kernel(						      \
-			(void *)dst,				      \
+			(void *)dst,					      \
 			__CORE_RELO(src, fld, BYTE_SIZE),		      \
 			(const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET))
 #else
@@ -110,21 +113,103 @@ enum bpf_enum_value_kind {
 	val;								      \
 })
 
+/*
+ * Write to a bitfield, identified by s->field.
+ * This is the inverse of BPF_CORE_WRITE_BITFIELD().
+ */
+#define BPF_CORE_WRITE_BITFIELD(s, field, new_val) ({			\
+	void *p = (void *)s + __CORE_RELO(s, field, BYTE_OFFSET);	\
+	unsigned int byte_size = __CORE_RELO(s, field, BYTE_SIZE);	\
+	unsigned int lshift = __CORE_RELO(s, field, LSHIFT_U64);	\
+	unsigned int rshift = __CORE_RELO(s, field, RSHIFT_U64);	\
+	unsigned long long mask, val, nval = new_val;			\
+	unsigned int rpad = rshift - lshift;				\
+									\
+	asm volatile("" : "+r"(p));					\
+									\
+	switch (byte_size) {						\
+	case 1: val = *(unsigned char *)p; break;			\
+	case 2: val = *(unsigned short *)p; break;			\
+	case 4: val = *(unsigned int *)p; break;			\
+	case 8: val = *(unsigned long long *)p; break;			\
+	}								\
+									\
+	mask = (~0ULL << rshift) >> lshift;				\
+	val = (val & ~mask) | ((nval << rpad) & mask);			\
+									\
+	switch (byte_size) {						\
+	case 1: *(unsigned char *)p      = val; break;			\
+	case 2: *(unsigned short *)p     = val; break;			\
+	case 4: *(unsigned int *)p       = val; break;			\
+	case 8: *(unsigned long long *)p = val; break;			\
+	}								\
+})
+
+/* Differentiator between compilers builtin implementations. This is a
+ * requirement due to the compiler parsing differences where GCC optimizes
+ * early in parsing those constructs of type pointers to the builtin specific
+ * type, resulting in not being possible to collect the required type
+ * information in the builtin expansion.
+ */
+#ifdef __clang__
+#define ___bpf_typeof(type) ((typeof(type) *) 0)
+#else
+#define ___bpf_typeof1(type, NR) ({					    \
+	extern typeof(type) *___concat(bpf_type_tmp_, NR);		    \
+	___concat(bpf_type_tmp_, NR);					    \
+})
+#define ___bpf_typeof(type) ___bpf_typeof1(type, __COUNTER__)
+#endif
+
+#ifdef __clang__
+#define ___bpf_field_ref1(field)	(field)
+#define ___bpf_field_ref2(type, field)	(___bpf_typeof(type)->field)
+#else
+#define ___bpf_field_ref1(field)	(&(field))
+#define ___bpf_field_ref2(type, field)	(&(___bpf_typeof(type)->field))
+#endif
+#define ___bpf_field_ref(args...)					    \
+	___bpf_apply(___bpf_field_ref, ___bpf_narg(args))(args)
+
 /*
  * 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.
+ *
+ * Supports two forms:
+ *   - field reference through variable access:
+ *     bpf_core_field_exists(p->my_field);
+ *   - field reference through type and field names:
+ *     bpf_core_field_exists(struct my_type, my_field).
  */
-#define bpf_core_field_exists(field)					    \
-	__builtin_preserve_field_info(field, BPF_FIELD_EXISTS)
+#define bpf_core_field_exists(field...)					    \
+	__builtin_preserve_field_info(___bpf_field_ref(field), BPF_FIELD_EXISTS)
 
 /*
  * Convenience macro to get the byte size of a field. Works for integers,
  * struct/unions, pointers, arrays, and enums.
+ *
+ * Supports two forms:
+ *   - field reference through variable access:
+ *     bpf_core_field_size(p->my_field);
+ *   - field reference through type and field names:
+ *     bpf_core_field_size(struct my_type, my_field).
  */
-#define bpf_core_field_size(field)					    \
-	__builtin_preserve_field_info(field, BPF_FIELD_BYTE_SIZE)
+#define bpf_core_field_size(field...)					    \
+	__builtin_preserve_field_info(___bpf_field_ref(field), BPF_FIELD_BYTE_SIZE)
+
+/*
+ * Convenience macro to get field's byte offset.
+ *
+ * Supports two forms:
+ *   - field reference through variable access:
+ *     bpf_core_field_offset(p->my_field);
+ *   - field reference through type and field names:
+ *     bpf_core_field_offset(struct my_type, my_field).
+ */
+#define bpf_core_field_offset(field...)					    \
+	__builtin_preserve_field_info(___bpf_field_ref(field), BPF_FIELD_BYTE_OFFSET)
 
 /*
  * Convenience macro to get BTF type ID of a specified type, using a local BTF
@@ -132,7 +217,7 @@ enum bpf_enum_value_kind {
  * BTF. Always succeeds.
  */
 #define bpf_core_type_id_local(type)					    \
-	__builtin_btf_type_id(*(typeof(type) *)0, BPF_TYPE_ID_LOCAL)
+	__builtin_btf_type_id(*___bpf_typeof(type), BPF_TYPE_ID_LOCAL)
 
 /*
  * Convenience macro to get BTF type ID of a target kernel's type that matches
@@ -142,7 +227,7 @@ enum bpf_enum_value_kind {
  *    - 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)
+	__builtin_btf_type_id(*___bpf_typeof(type), BPF_TYPE_ID_TARGET)
 
 /*
  * Convenience macro to check that provided named type
@@ -152,7 +237,17 @@ enum bpf_enum_value_kind {
  *    0, if no matching type is found.
  */
 #define bpf_core_type_exists(type)					    \
-	__builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_EXISTS)
+	__builtin_preserve_type_info(*___bpf_typeof(type), BPF_TYPE_EXISTS)
+
+/*
+ * Convenience macro to check that provided named type
+ * (struct/union/enum/typedef) "matches" that in a target kernel.
+ * Returns:
+ *    1, if the type matches in the target kernel's BTF;
+ *    0, if the type does not match any in the target kernel
+ */
+#define bpf_core_type_matches(type)					    \
+	__builtin_preserve_type_info(*___bpf_typeof(type), BPF_TYPE_MATCHES)
 
 /*
  * Convenience macro to get the byte size of a provided named type
@@ -162,7 +257,7 @@ enum bpf_enum_value_kind {
  *    0, if no matching type is found.
  */
 #define bpf_core_type_size(type)					    \
-	__builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_SIZE)
+	__builtin_preserve_type_info(*___bpf_typeof(type), BPF_TYPE_SIZE)
 
 /*
  * Convenience macro to check that provided enumerator value is defined in
@@ -172,8 +267,13 @@ enum bpf_enum_value_kind {
  *    kernel's BTF;
  *    0, if no matching enum and/or enum value within that enum is found.
  */
+#ifdef __clang__
 #define bpf_core_enum_value_exists(enum_type, enum_value)		    \
 	__builtin_preserve_enum_value(*(typeof(enum_type) *)enum_value, BPF_ENUMVAL_EXISTS)
+#else
+#define bpf_core_enum_value_exists(enum_type, enum_value)		    \
+	__builtin_preserve_enum_value(___bpf_typeof(enum_type), enum_value, BPF_ENUMVAL_EXISTS)
+#endif
 
 /*
  * Convenience macro to get the integer value of an enumerator value in
@@ -183,8 +283,13 @@ enum bpf_enum_value_kind {
  *    present in target kernel's BTF;
  *    0, if no matching enum and/or enum value within that enum is found.
  */
+#ifdef __clang__
 #define bpf_core_enum_value(enum_type, enum_value)			    \
 	__builtin_preserve_enum_value(*(typeof(enum_type) *)enum_value, BPF_ENUMVAL_VALUE)
+#else
+#define bpf_core_enum_value(enum_type, enum_value)			    \
+	__builtin_preserve_enum_value(___bpf_typeof(enum_type), enum_value, BPF_ENUMVAL_VALUE)
+#endif
 
 /*
  * bpf_core_read() abstracts away bpf_probe_read_kernel() call and captures
@@ -196,7 +301,7 @@ enum bpf_enum_value_kind {
  * 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.
+ * semantics in comments to struct bpf_core_relo in include/uapi/linux/bpf.h.
  *
  * This relocation allows libbpf to adjust BPF instruction to use correct
  * actual field offset, based on target kernel BTF type that matches original
@@ -220,6 +325,17 @@ enum bpf_enum_value_kind {
 #define bpf_core_read_user_str(dst, sz, src)				    \
 	bpf_probe_read_user_str(dst, sz, (const void *)__builtin_preserve_access_index(src))
 
+extern void *bpf_rdonly_cast(const void *obj, __u32 btf_id) __ksym __weak;
+
+/*
+ * Cast provided pointer *ptr* into a pointer to a specified *type* in such
+ * a way that BPF verifier will become aware of associated kernel-side BTF
+ * type. This allows to access members of kernel types directly without the
+ * need to use BPF_CORE_READ() macros.
+ */
+#define bpf_core_cast(ptr, type)					    \
+	((typeof(type) *)bpf_rdonly_cast((ptr), bpf_core_type_id_kernel(type)))
+
 #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
@@ -324,7 +440,7 @@ enum bpf_enum_value_kind {
 
 /* 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,			    \
+	___core_read(bpf_probe_read_kernel, bpf_probe_read_kernel,	    \
 		     dst, (src), a, ##__VA_ARGS__)			    \
 })
 
@@ -360,7 +476,7 @@ enum bpf_enum_value_kind {
 
 /* 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,		    \
+	___core_read(bpf_probe_read_kernel_str, bpf_probe_read_kernel,	    \
 		     dst, (src), a, ##__VA_ARGS__)			    \
 })
 

src/bpf_gen_internal.h

@@ -3,12 +3,15 @@
 #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;
+	bool is_ld64;
 };
 
 struct ksym_desc {
@@ -22,6 +25,7 @@ struct ksym_desc {
 		bool typeless;
 	};
 	int insn;
+	bool is_ld64;
 };
 
 struct bpf_gen {
@@ -37,6 +41,8 @@ struct bpf_gen {
 	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;
@@ -45,17 +51,24 @@ struct bpf_gen {
 	int nr_fd_array;
 };
 
-void bpf_gen__init(struct bpf_gen *gen, int log_level);
-int bpf_gen__finish(struct bpf_gen *gen);
+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, struct bpf_create_map_params *map_attr, int map_idx);
-struct bpf_prog_load_params;
-void bpf_gen__prog_load(struct bpf_gen *gen, struct bpf_prog_load_params *load_attr, int prog_idx);
+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);
+			    bool is_typeless, bool is_ld64, 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

@@ -13,6 +13,7 @@
 #define __uint(name, val) int (*name)[val]
 #define __type(name, val) typeof(val) *name
 #define __array(name, val) typeof(val) *name[]
+#define __ulong(name, val) enum { ___bpf_concat(__unique_value, __COUNTER__) = val } name
 
 /*
  * Helper macro to place programs, maps, license in
@@ -22,12 +23,25 @@
  * To allow use of SEC() with externs (e.g., for extern .maps declarations),
  * make sure __attribute__((unused)) doesn't trigger compilation warning.
  */
+#if __GNUC__ && !__clang__
+
+/*
+ * Pragma macros are broken on GCC
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=55578
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90400
+ */
+#define SEC(name) __attribute__((section(name), used))
+
+#else
+
 #define SEC(name) \
 	_Pragma("GCC diagnostic push")					    \
 	_Pragma("GCC diagnostic ignored \"-Wignored-attributes\"")	    \
 	__attribute__((section(name), used))				    \
 	_Pragma("GCC diagnostic pop")					    \
 
+#endif
+
 /* Avoid 'linux/stddef.h' definition of '__always_inline'. */
 #undef __always_inline
 #define __always_inline inline __attribute__((always_inline))
@@ -64,15 +78,44 @@
 /*
  * Helper macros to manipulate data structures
  */
-#ifndef offsetof
-#define offsetof(TYPE, MEMBER)	((unsigned long)&((TYPE *)0)->MEMBER)
-#endif
-#ifndef container_of
+
+/* offsetof() definition that uses __builtin_offset() might not preserve field
+ * offset CO-RE relocation properly, so force-redefine offsetof() using
+ * old-school approach which works with CO-RE correctly
+ */
+#undef offsetof
+#define offsetof(type, member)	((unsigned long)&((type *)0)->member)
+
+/* redefined container_of() to ensure we use the above offsetof() macro */
+#undef container_of
 #define container_of(ptr, type, member)				\
 	({							\
 		void *__mptr = (void *)(ptr);			\
 		((type *)(__mptr - offsetof(type, member)));	\
 	})
+
+/*
+ * Compiler (optimization) barrier.
+ */
+#ifndef barrier
+#define barrier() asm volatile("" ::: "memory")
+#endif
+
+/* Variable-specific compiler (optimization) barrier. It's a no-op which makes
+ * compiler believe that there is some black box modification of a given
+ * variable and thus prevents compiler from making extra assumption about its
+ * value and potential simplifications and optimizations on this variable.
+ *
+ * E.g., compiler might often delay or even omit 32-bit to 64-bit casting of
+ * a variable, making some code patterns unverifiable. Putting barrier_var()
+ * in place will ensure that cast is performed before the barrier_var()
+ * invocation, because compiler has to pessimistically assume that embedded
+ * asm section might perform some extra operations on that variable.
+ *
+ * This is a variable-specific variant of more global barrier().
+ */
+#ifndef barrier_var
+#define barrier_var(var) asm volatile("" : "+r"(var))
 #endif
 
 /*
@@ -94,7 +137,8 @@
 /*
  * Helper function to perform a tail call with a constant/immediate map slot.
  */
-#if __clang_major__ >= 8 && defined(__bpf__)
+#if (defined(__clang__) && __clang_major__ >= 8) || (!defined(__clang__) && __GNUC__ > 12)
+#if defined(__bpf__)
 static __always_inline void
 bpf_tail_call_static(void *ctx, const void *map, const __u32 slot)
 {
@@ -122,18 +166,7 @@ bpf_tail_call_static(void *ctx, const void *map, const __u32 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;
-};
+#endif
 
 enum libbpf_pin_type {
 	LIBBPF_PIN_NONE,
@@ -149,6 +182,20 @@ enum libbpf_tristate {
 
 #define __kconfig __attribute__((section(".kconfig")))
 #define __ksym __attribute__((section(".ksyms")))
+#define __kptr_untrusted __attribute__((btf_type_tag("kptr_untrusted")))
+#define __kptr __attribute__((btf_type_tag("kptr")))
+#define __percpu_kptr __attribute__((btf_type_tag("percpu_kptr")))
+
+#define bpf_ksym_exists(sym) ({									\
+	_Static_assert(!__builtin_constant_p(!!sym), #sym " should be marked as __weak");	\
+	!!sym;											\
+})
+
+#define __arg_ctx __attribute__((btf_decl_tag("arg:ctx")))
+#define __arg_nonnull __attribute((btf_decl_tag("arg:nonnull")))
+#define __arg_nullable __attribute((btf_decl_tag("arg:nullable")))
+#define __arg_trusted __attribute((btf_decl_tag("arg:trusted")))
+#define __arg_arena __attribute((btf_decl_tag("arg:arena")))
 
 #ifndef ___bpf_concat
 #define ___bpf_concat(a, b) a ## b
@@ -259,4 +306,107 @@ enum libbpf_tristate {
 /* Helper macro to print out debug messages */
 #define bpf_printk(fmt, args...) ___bpf_pick_printk(args)(fmt, ##args)
 
+struct bpf_iter_num;
+
+extern int bpf_iter_num_new(struct bpf_iter_num *it, int start, int end) __weak __ksym;
+extern int *bpf_iter_num_next(struct bpf_iter_num *it) __weak __ksym;
+extern void bpf_iter_num_destroy(struct bpf_iter_num *it) __weak __ksym;
+
+#ifndef bpf_for_each
+/* bpf_for_each(iter_type, cur_elem, args...) provides generic construct for
+ * using BPF open-coded iterators without having to write mundane explicit
+ * low-level loop logic. Instead, it provides for()-like generic construct
+ * that can be used pretty naturally. E.g., for some hypothetical cgroup
+ * iterator, you'd write:
+ *
+ * struct cgroup *cg, *parent_cg = <...>;
+ *
+ * bpf_for_each(cgroup, cg, parent_cg, CG_ITER_CHILDREN) {
+ *     bpf_printk("Child cgroup id = %d", cg->cgroup_id);
+ *     if (cg->cgroup_id == 123)
+ *         break;
+ * }
+ *
+ * I.e., it looks almost like high-level for each loop in other languages,
+ * supports continue/break, and is verifiable by BPF verifier.
+ *
+ * For iterating integers, the difference betwen bpf_for_each(num, i, N, M)
+ * and bpf_for(i, N, M) is in that bpf_for() provides additional proof to
+ * verifier that i is in [N, M) range, and in bpf_for_each() case i is `int
+ * *`, not just `int`. So for integers bpf_for() is more convenient.
+ *
+ * Note: this macro relies on C99 feature of allowing to declare variables
+ * inside for() loop, bound to for() loop lifetime. It also utilizes GCC
+ * extension: __attribute__((cleanup(<func>))), supported by both GCC and
+ * Clang.
+ */
+#define bpf_for_each(type, cur, args...) for (							\
+	/* initialize and define destructor */							\
+	struct bpf_iter_##type ___it __attribute__((aligned(8), /* enforce, just in case */,	\
+						    cleanup(bpf_iter_##type##_destroy))),	\
+	/* ___p pointer is just to call bpf_iter_##type##_new() *once* to init ___it */		\
+			       *___p __attribute__((unused)) = (				\
+					bpf_iter_##type##_new(&___it, ##args),			\
+	/* this is a workaround for Clang bug: it currently doesn't emit BTF */			\
+	/* for bpf_iter_##type##_destroy() when used from cleanup() attribute */		\
+					(void)bpf_iter_##type##_destroy, (void *)0);		\
+	/* iteration and termination check */							\
+	(((cur) = bpf_iter_##type##_next(&___it)));						\
+)
+#endif /* bpf_for_each */
+
+#ifndef bpf_for
+/* bpf_for(i, start, end) implements a for()-like looping construct that sets
+ * provided integer variable *i* to values starting from *start* through,
+ * but not including, *end*. It also proves to BPF verifier that *i* belongs
+ * to range [start, end), so this can be used for accessing arrays without
+ * extra checks.
+ *
+ * Note: *start* and *end* are assumed to be expressions with no side effects
+ * and whose values do not change throughout bpf_for() loop execution. They do
+ * not have to be statically known or constant, though.
+ *
+ * Note: similarly to bpf_for_each(), it relies on C99 feature of declaring for()
+ * loop bound variables and cleanup attribute, supported by GCC and Clang.
+ */
+#define bpf_for(i, start, end) for (								\
+	/* initialize and define destructor */							\
+	struct bpf_iter_num ___it __attribute__((aligned(8), /* enforce, just in case */	\
+						 cleanup(bpf_iter_num_destroy))),		\
+	/* ___p pointer is necessary to call bpf_iter_num_new() *once* to init ___it */		\
+			    *___p __attribute__((unused)) = (					\
+				bpf_iter_num_new(&___it, (start), (end)),			\
+	/* this is a workaround for Clang bug: it currently doesn't emit BTF */			\
+	/* for bpf_iter_num_destroy() when used from cleanup() attribute */			\
+				(void)bpf_iter_num_destroy, (void *)0);				\
+	({											\
+		/* iteration step */								\
+		int *___t = bpf_iter_num_next(&___it);						\
+		/* termination and bounds check */						\
+		(___t && ((i) = *___t, (i) >= (start) && (i) < (end)));				\
+	});											\
+)
+#endif /* bpf_for */
+
+#ifndef bpf_repeat
+/* bpf_repeat(N) performs N iterations without exposing iteration number
+ *
+ * Note: similarly to bpf_for_each(), it relies on C99 feature of declaring for()
+ * loop bound variables and cleanup attribute, supported by GCC and Clang.
+ */
+#define bpf_repeat(N) for (									\
+	/* initialize and define destructor */							\
+	struct bpf_iter_num ___it __attribute__((aligned(8), /* enforce, just in case */	\
+						 cleanup(bpf_iter_num_destroy))),		\
+	/* ___p pointer is necessary to call bpf_iter_num_new() *once* to init ___it */		\
+			    *___p __attribute__((unused)) = (					\
+				bpf_iter_num_new(&___it, 0, (N)),				\
+	/* this is a workaround for Clang bug: it currently doesn't emit BTF */			\
+	/* for bpf_iter_num_destroy() when used from cleanup() attribute */			\
+				(void)bpf_iter_num_destroy, (void *)0);				\
+	bpf_iter_num_next(&___it);								\
+	/* nothing here  */									\
+)
+#endif /* bpf_repeat */
+
 #endif

src/btf.h

@@ -116,24 +116,15 @@ LIBBPF_API struct btf *btf__parse_raw_split(const char *path, struct btf *base_b
 
 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,
@@ -147,32 +138,13 @@ 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 void btf__set_fd(struct btf *btf, int fd);
-LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__raw_data() instead")
-LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size);
 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 const char *btf__str_by_offset(const struct btf *btf, __u32 offset);
-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 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 __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 int btf__find_str(struct btf *btf, const char *s);
 LIBBPF_API int btf__add_str(struct btf *btf, const char *s);
@@ -215,6 +187,8 @@ LIBBPF_API int btf__add_field(struct btf *btf, const char *name, int field_type_
 /* 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);
+LIBBPF_API int btf__add_enum64(struct btf *btf, const char *name, __u32 bytes_sz, bool is_signed);
+LIBBPF_API int btf__add_enum64_value(struct btf *btf, const char *name, __u64 value);
 
 enum btf_fwd_kind {
 	BTF_FWD_STRUCT = 0,
@@ -227,6 +201,7 @@ LIBBPF_API int btf__add_typedef(struct btf *btf, const char *name, int ref_type_
 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,
@@ -245,25 +220,31 @@ LIBBPF_API int btf__add_decl_tag(struct btf *btf, const char *value, int ref_typ
 			    int component_idx);
 
 struct btf_dedup_opts {
-	unsigned int dedup_table_size;
-	bool dont_resolve_fwds;
+	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, struct btf_ext *btf_ext,
-			  const struct btf_dedup_opts *opts);
+LIBBPF_API int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts);
 
 struct btf_dump;
 
 struct btf_dump_opts {
-	void *ctx;
+	size_t sz;
 };
+#define btf_dump_opts__last_field sz
 
 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,
-					  const struct btf_ext *btf_ext,
-					  const struct btf_dump_opts *opts,
-					  btf_dump_printf_fn_t printf_fn);
+					  btf_dump_printf_fn_t printf_fn,
+					  void *ctx,
+					  const struct btf_dump_opts *opts);
+
 LIBBPF_API void btf_dump__free(struct btf_dump *d);
 
 LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id);
@@ -313,8 +294,29 @@ btf_dump__dump_type_data(struct btf_dump *d, __u32 id,
 			 const struct btf_dump_type_data_opts *opts);
 
 /*
- * A set of helpers for easier BTF types handling
+ * 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 the following were never #defined */
+#define BTF_KIND_DECL_TAG	17	/* Decl Tag */
+#define BTF_KIND_TYPE_TAG	18	/* Type Tag */
+#define BTF_KIND_ENUM64		19	/* Enum for up-to 64bit values */
+
 static inline __u16 btf_kind(const struct btf_type *t)
 {
 	return BTF_INFO_KIND(t->info);
@@ -372,6 +374,11 @@ static inline bool btf_is_enum(const struct btf_type *t)
 	return btf_kind(t) == BTF_KIND_ENUM;
 }
 
+static inline bool btf_is_enum64(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_ENUM64;
+}
+
 static inline bool btf_is_fwd(const struct btf_type *t)
 {
 	return btf_kind(t) == BTF_KIND_FWD;
@@ -403,7 +410,8 @@ static inline bool btf_is_mod(const struct btf_type *t)
 
 	return kind == BTF_KIND_VOLATILE ||
 	       kind == BTF_KIND_CONST ||
-	       kind == BTF_KIND_RESTRICT;
+	       kind == BTF_KIND_RESTRICT ||
+	       kind == BTF_KIND_TYPE_TAG;
 }
 
 static inline bool btf_is_func(const struct btf_type *t)
@@ -436,6 +444,23 @@ 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 bool btf_is_any_enum(const struct btf_type *t)
+{
+	return btf_is_enum(t) || btf_is_enum64(t);
+}
+
+static inline bool btf_kind_core_compat(const struct btf_type *t1,
+					const struct btf_type *t2)
+{
+	return btf_kind(t1) == btf_kind(t2) ||
+	       (btf_is_any_enum(t1) && btf_is_any_enum(t2));
+}
+
 static inline __u8 btf_int_encoding(const struct btf_type *t)
 {
 	return BTF_INT_ENCODING(*(__u32 *)(t + 1));
@@ -461,6 +486,39 @@ static inline struct btf_enum *btf_enum(const struct btf_type *t)
 	return (struct btf_enum *)(t + 1);
 }
 
+struct btf_enum64;
+
+static inline struct btf_enum64 *btf_enum64(const struct btf_type *t)
+{
+	return (struct btf_enum64 *)(t + 1);
+}
+
+static inline __u64 btf_enum64_value(const struct btf_enum64 *e)
+{
+	/* struct btf_enum64 is introduced in Linux 6.0, which is very
+	 * bleeding-edge. Here we are avoiding relying on struct btf_enum64
+	 * definition coming from kernel UAPI headers to support wider range
+	 * of system-wide kernel headers.
+	 *
+	 * Given this header can be also included from C++ applications, that
+	 * further restricts C tricks we can use (like using compatible
+	 * anonymous struct). So just treat struct btf_enum64 as
+	 * a three-element array of u32 and access second (lo32) and third
+	 * (hi32) elements directly.
+	 *
+	 * For reference, here is a struct btf_enum64 definition:
+	 *
+	 * const struct btf_enum64 {
+	 *	__u32	name_off;
+	 *	__u32	val_lo32;
+	 *	__u32	val_hi32;
+	 * };
+	 */
+	const __u32 *e64 = (const __u32 *)e;
+
+	return ((__u64)e64[2] << 32) | e64[1];
+}
+
 static inline struct btf_member *btf_members(const struct btf_type *t)
 {
 	return (struct btf_member *)(t + 1);

src/btf_dump.c

@@ -13,6 +13,7 @@
 #include <ctype.h>
 #include <endian.h>
 #include <errno.h>
+#include <limits.h>
 #include <linux/err.h>
 #include <linux/btf.h>
 #include <linux/kernel.h>
@@ -77,9 +78,8 @@ struct btf_dump_data {
 
 struct btf_dump {
 	const struct btf *btf;
-	const struct btf_ext *btf_ext;
 	btf_dump_printf_fn_t printf_fn;
-	struct btf_dump_opts opts;
+	void *cb_ctx;
 	int ptr_sz;
 	bool strip_mods;
 	bool skip_anon_defs;
@@ -118,14 +118,14 @@ struct btf_dump {
 	struct btf_dump_data *typed_dump;
 };
 
-static size_t str_hash_fn(const void *key, void *ctx)
+static size_t str_hash_fn(long key, void *ctx)
 {
-	return str_hash(key);
+	return str_hash((void *)key);
 }
 
-static bool str_equal_fn(const void *a, const void *b, void *ctx)
+static bool str_equal_fn(long a, long b, void *ctx)
 {
-	return strcmp(a, b) == 0;
+	return strcmp((void *)a, (void *)b) == 0;
 }
 
 static const char *btf_name_of(const struct btf_dump *d, __u32 name_off)
@@ -138,7 +138,7 @@ static void btf_dump_printf(const struct btf_dump *d, const char *fmt, ...)
 	va_list args;
 
 	va_start(args, fmt);
-	d->printf_fn(d->opts.ctx, fmt, args);
+	d->printf_fn(d->cb_ctx, fmt, args);
 	va_end(args);
 }
 
@@ -146,21 +146,26 @@ static int btf_dump_mark_referenced(struct btf_dump *d);
 static int btf_dump_resize(struct btf_dump *d);
 
 struct btf_dump *btf_dump__new(const struct btf *btf,
-			       const struct btf_ext *btf_ext,
-			       const struct btf_dump_opts *opts,
-			       btf_dump_printf_fn_t printf_fn)
+			       btf_dump_printf_fn_t printf_fn,
+			       void *ctx,
+			       const struct btf_dump_opts *opts)
 {
 	struct btf_dump *d;
 	int err;
 
+	if (!OPTS_VALID(opts, btf_dump_opts))
+		return libbpf_err_ptr(-EINVAL);
+
+	if (!printf_fn)
+		return libbpf_err_ptr(-EINVAL);
+
 	d = calloc(1, sizeof(struct btf_dump));
 	if (!d)
 		return libbpf_err_ptr(-ENOMEM);
 
 	d->btf = btf;
-	d->btf_ext = btf_ext;
 	d->printf_fn = printf_fn;
-	d->opts.ctx = opts ? opts->ctx : NULL;
+	d->cb_ctx = ctx;
 	d->ptr_sz = btf__pointer_size(btf) ? : sizeof(void *);
 
 	d->type_names = hashmap__new(str_hash_fn, str_equal_fn, NULL);
@@ -215,6 +220,17 @@ static int btf_dump_resize(struct btf_dump *d)
 	return 0;
 }
 
+static void btf_dump_free_names(struct hashmap *map)
+{
+	size_t bkt;
+	struct hashmap_entry *cur;
+
+	hashmap__for_each_entry(map, cur, bkt)
+		free((void *)cur->pkey);
+
+	hashmap__free(map);
+}
+
 void btf_dump__free(struct btf_dump *d)
 {
 	int i;
@@ -233,8 +249,8 @@ void btf_dump__free(struct btf_dump *d)
 	free(d->cached_names);
 	free(d->emit_queue);
 	free(d->decl_stack);
-	hashmap__free(d->type_names);
-	hashmap__free(d->ident_names);
+	btf_dump_free_names(d->type_names);
+	btf_dump_free_names(d->ident_names);
 
 	free(d);
 }
@@ -305,6 +321,7 @@ static int btf_dump_mark_referenced(struct btf_dump *d)
 		switch (btf_kind(t)) {
 		case BTF_KIND_INT:
 		case BTF_KIND_ENUM:
+		case BTF_KIND_ENUM64:
 		case BTF_KIND_FWD:
 		case BTF_KIND_FLOAT:
 			break;
@@ -317,6 +334,7 @@ static int btf_dump_mark_referenced(struct btf_dump *d)
 		case BTF_KIND_FUNC:
 		case BTF_KIND_VAR:
 		case BTF_KIND_DECL_TAG:
+		case BTF_KIND_TYPE_TAG:
 			d->type_states[t->type].referenced = 1;
 			break;
 
@@ -524,6 +542,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 		return 1;
 	}
 	case BTF_KIND_ENUM:
+	case BTF_KIND_ENUM64:
 	case BTF_KIND_FWD:
 		/*
 		 * non-anonymous or non-referenced enums are top-level
@@ -560,6 +579,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 	case BTF_KIND_VOLATILE:
 	case BTF_KIND_CONST:
 	case BTF_KIND_RESTRICT:
+	case BTF_KIND_TYPE_TAG:
 		return btf_dump_order_type(d, t->type, through_ptr);
 
 	case BTF_KIND_FUNC_PROTO: {
@@ -724,6 +744,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
 		tstate->emit_state = EMITTED;
 		break;
 	case BTF_KIND_ENUM:
+	case BTF_KIND_ENUM64:
 		if (top_level_def) {
 			btf_dump_emit_enum_def(d, id, t, 0);
 			btf_dump_printf(d, ";\n\n");
@@ -734,6 +755,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
 	case BTF_KIND_VOLATILE:
 	case BTF_KIND_CONST:
 	case BTF_KIND_RESTRICT:
+	case BTF_KIND_TYPE_TAG:
 		btf_dump_emit_type(d, t->type, cont_id);
 		break;
 	case BTF_KIND_ARRAY:
@@ -812,14 +834,9 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id,
 				 const struct btf_type *t)
 {
 	const struct btf_member *m;
-	int align, i, bit_sz;
+	int max_align = 1, align, i, bit_sz;
 	__u16 vlen;
 
-	align = btf__align_of(btf, id);
-	/* size of a non-packed struct has to be a multiple of its alignment*/
-	if (align && t->size % align)
-		return true;
-
 	m = btf_members(t);
 	vlen = btf_vlen(t);
 	/* all non-bitfield fields have to be naturally aligned */
@@ -828,8 +845,11 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id,
 		bit_sz = btf_member_bitfield_size(t, i);
 		if (align && bit_sz == 0 && m->offset % (8 * align) != 0)
 			return true;
+		max_align = max(align, max_align);
 	}
-
+	/* size of a non-packed struct has to be a multiple of its alignment */
+	if (t->size % max_align != 0)
+		return true;
 	/*
 	 * if original struct was marked as packed, but its layout is
 	 * naturally aligned, we'll detect that it's not packed
@@ -837,44 +857,97 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id,
 	return false;
 }
 
-static int chip_away_bits(int total, int at_most)
-{
-	return total % at_most ? : at_most;
-}
-
 static void btf_dump_emit_bit_padding(const struct btf_dump *d,
-				      int cur_off, int m_off, int m_bit_sz,
-				      int align, int lvl)
+				      int cur_off, int next_off, int next_align,
+				      bool in_bitfield, int lvl)
 {
-	int off_diff = m_off - cur_off;
-	int ptr_bits = d->ptr_sz * 8;
+	const struct {
+		const char *name;
+		int bits;
+	} pads[] = {
+		{"long", d->ptr_sz * 8}, {"int", 32}, {"short", 16}, {"char", 8}
+	};
+	int new_off, pad_bits, bits, i;
+	const char *pad_type;
 
-	if (off_diff <= 0)
-		/* no gap */
-		return;
-	if (m_bit_sz == 0 && off_diff < align * 8)
-		/* natural padding will take care of a gap */
-		return;
+	if (cur_off >= next_off)
+		return; /* no gap */
 
-	while (off_diff > 0) {
-		const char *pad_type;
-		int pad_bits;
+	/* For filling out padding we want to take advantage of
+	 * natural alignment rules to minimize unnecessary explicit
+	 * padding. First, we find the largest type (among long, int,
+	 * short, or char) that can be used to force naturally aligned
+	 * boundary. Once determined, we'll use such type to fill in
+	 * the remaining padding gap. In some cases we can rely on
+	 * compiler filling some gaps, but sometimes we need to force
+	 * alignment to close natural alignment with markers like
+	 * `long: 0` (this is always the case for bitfields).  Note
+	 * that even if struct itself has, let's say 4-byte alignment
+	 * (i.e., it only uses up to int-aligned types), using `long:
+	 * X;` explicit padding doesn't actually change struct's
+	 * overall alignment requirements, but compiler does take into
+	 * account that type's (long, in this example) natural
+	 * alignment requirements when adding implicit padding. We use
+	 * this fact heavily and don't worry about ruining correct
+	 * struct alignment requirement.
+	 */
+	for (i = 0; i < ARRAY_SIZE(pads); i++) {
+		pad_bits = pads[i].bits;
+		pad_type = pads[i].name;
 
-		if (ptr_bits > 32 && off_diff > 32) {
-			pad_type = "long";
-			pad_bits = chip_away_bits(off_diff, ptr_bits);
-		} else if (off_diff > 16) {
-			pad_type = "int";
-			pad_bits = chip_away_bits(off_diff, 32);
-		} else if (off_diff > 8) {
-			pad_type = "short";
-			pad_bits = chip_away_bits(off_diff, 16);
-		} else {
-			pad_type = "char";
-			pad_bits = chip_away_bits(off_diff, 8);
+		new_off = roundup(cur_off, pad_bits);
+		if (new_off <= next_off)
+			break;
+	}
+
+	if (new_off > cur_off && new_off <= next_off) {
+		/* We need explicit `<type>: 0` aligning mark if next
+		 * field is right on alignment offset and its
+		 * alignment requirement is less strict than <type>'s
+		 * alignment (so compiler won't naturally align to the
+		 * offset we expect), or if subsequent `<type>: X`,
+		 * will actually completely fit in the remaining hole,
+		 * making compiler basically ignore `<type>: X`
+		 * completely.
+		 */
+		if (in_bitfield ||
+		    (new_off == next_off && roundup(cur_off, next_align * 8) != new_off) ||
+		    (new_off != next_off && next_off - new_off <= new_off - cur_off))
+			/* but for bitfields we'll emit explicit bit count */
+			btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type,
+					in_bitfield ? new_off - cur_off : 0);
+		cur_off = new_off;
+	}
+
+	/* Now we know we start at naturally aligned offset for a chosen
+	 * padding type (long, int, short, or char), and so the rest is just
+	 * a straightforward filling of remaining padding gap with full
+	 * `<type>: sizeof(<type>);` markers, except for the last one, which
+	 * might need smaller than sizeof(<type>) padding.
+	 */
+	while (cur_off != next_off) {
+		bits = min(next_off - cur_off, pad_bits);
+		if (bits == pad_bits) {
+			btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, pad_bits);
+			cur_off += bits;
+			continue;
+		}
+		/* For the remainder padding that doesn't cover entire
+		 * pad_type bit length, we pick the smallest necessary type.
+		 * This is pure aesthetics, we could have just used `long`,
+		 * but having smallest necessary one communicates better the
+		 * scale of the padding gap.
+		 */
+		for (i = ARRAY_SIZE(pads) - 1; i >= 0; i--) {
+			pad_type = pads[i].name;
+			pad_bits = pads[i].bits;
+			if (pad_bits < bits)
+				continue;
+
+			btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, bits);
+			cur_off += bits;
+			break;
 		}
-		btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, pad_bits);
-		off_diff -= pad_bits;
 	}
 }
 
@@ -894,9 +967,11 @@ static void btf_dump_emit_struct_def(struct btf_dump *d,
 {
 	const struct btf_member *m = btf_members(t);
 	bool is_struct = btf_is_struct(t);
-	int align, i, packed, off = 0;
+	bool packed, prev_bitfield = false;
+	int align, i, off = 0;
 	__u16 vlen = btf_vlen(t);
 
+	align = btf__align_of(d->btf, id);
 	packed = is_struct ? btf_is_struct_packed(d->btf, id, t) : 0;
 
 	btf_dump_printf(d, "%s%s%s {",
@@ -906,37 +981,47 @@ static void btf_dump_emit_struct_def(struct btf_dump *d,
 
 	for (i = 0; i < vlen; i++, m++) {
 		const char *fname;
-		int m_off, m_sz;
+		int m_off, m_sz, m_align;
+		bool in_bitfield;
 
 		fname = btf_name_of(d, m->name_off);
 		m_sz = btf_member_bitfield_size(t, i);
 		m_off = btf_member_bit_offset(t, i);
-		align = packed ? 1 : btf__align_of(d->btf, m->type);
+		m_align = packed ? 1 : btf__align_of(d->btf, m->type);
 
-		btf_dump_emit_bit_padding(d, off, m_off, m_sz, align, lvl + 1);
+		in_bitfield = prev_bitfield && m_sz != 0;
+
+		btf_dump_emit_bit_padding(d, off, m_off, m_align, in_bitfield, lvl + 1);
 		btf_dump_printf(d, "\n%s", pfx(lvl + 1));
 		btf_dump_emit_type_decl(d, m->type, fname, lvl + 1);
 
 		if (m_sz) {
 			btf_dump_printf(d, ": %d", m_sz);
 			off = m_off + m_sz;
+			prev_bitfield = true;
 		} else {
 			m_sz = max((__s64)0, btf__resolve_size(d->btf, m->type));
 			off = m_off + m_sz * 8;
+			prev_bitfield = false;
 		}
+
 		btf_dump_printf(d, ";");
 	}
 
 	/* pad at the end, if necessary */
-	if (is_struct) {
-		align = packed ? 1 : btf__align_of(d->btf, id);
-		btf_dump_emit_bit_padding(d, off, t->size * 8, 0, align,
-					  lvl + 1);
-	}
+	if (is_struct)
+		btf_dump_emit_bit_padding(d, off, t->size * 8, align, false, lvl + 1);
 
-	if (vlen)
+	/*
+	 * Keep `struct empty {}` on a single line,
+	 * only print newline when there are regular or padding fields.
+	 */
+	if (vlen || t->size) {
 		btf_dump_printf(d, "\n");
-	btf_dump_printf(d, "%s}", pfx(lvl));
+		btf_dump_printf(d, "%s}", pfx(lvl));
+	} else {
+		btf_dump_printf(d, "}");
+	}
 	if (packed)
 		btf_dump_printf(d, " __attribute__((packed))");
 }
@@ -973,38 +1058,118 @@ static void btf_dump_emit_enum_fwd(struct btf_dump *d, __u32 id,
 	btf_dump_printf(d, "enum %s", btf_dump_type_name(d, id));
 }
 
+static void btf_dump_emit_enum32_val(struct btf_dump *d,
+				     const struct btf_type *t,
+				     int lvl, __u16 vlen)
+{
+	const struct btf_enum *v = btf_enum(t);
+	bool is_signed = btf_kflag(t);
+	const char *fmt_str;
+	const char *name;
+	size_t dup_cnt;
+	int i;
+
+	for (i = 0; i < vlen; i++, v++) {
+		name = btf_name_of(d, v->name_off);
+		/* enumerators share namespace with typedef idents */
+		dup_cnt = btf_dump_name_dups(d, d->ident_names, name);
+		if (dup_cnt > 1) {
+			fmt_str = is_signed ? "\n%s%s___%zd = %d," : "\n%s%s___%zd = %u,";
+			btf_dump_printf(d, fmt_str, pfx(lvl + 1), name, dup_cnt, v->val);
+		} else {
+			fmt_str = is_signed ? "\n%s%s = %d," : "\n%s%s = %u,";
+			btf_dump_printf(d, fmt_str, pfx(lvl + 1), name, v->val);
+		}
+	}
+}
+
+static void btf_dump_emit_enum64_val(struct btf_dump *d,
+				     const struct btf_type *t,
+				     int lvl, __u16 vlen)
+{
+	const struct btf_enum64 *v = btf_enum64(t);
+	bool is_signed = btf_kflag(t);
+	const char *fmt_str;
+	const char *name;
+	size_t dup_cnt;
+	__u64 val;
+	int i;
+
+	for (i = 0; i < vlen; i++, v++) {
+		name = btf_name_of(d, v->name_off);
+		dup_cnt = btf_dump_name_dups(d, d->ident_names, name);
+		val = btf_enum64_value(v);
+		if (dup_cnt > 1) {
+			fmt_str = is_signed ? "\n%s%s___%zd = %lldLL,"
+					    : "\n%s%s___%zd = %lluULL,";
+			btf_dump_printf(d, fmt_str,
+					pfx(lvl + 1), name, dup_cnt,
+					(unsigned long long)val);
+		} else {
+			fmt_str = is_signed ? "\n%s%s = %lldLL,"
+					    : "\n%s%s = %lluULL,";
+			btf_dump_printf(d, fmt_str,
+					pfx(lvl + 1), name,
+					(unsigned long long)val);
+		}
+	}
+}
 static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id,
 				   const struct btf_type *t,
 				   int lvl)
 {
-	const struct btf_enum *v = btf_enum(t);
 	__u16 vlen = btf_vlen(t);
-	const char *name;
-	size_t dup_cnt;
-	int i;
 
 	btf_dump_printf(d, "enum%s%s",
 			t->name_off ? " " : "",
 			btf_dump_type_name(d, id));
 
-	if (vlen) {
-		btf_dump_printf(d, " {");
-		for (i = 0; i < vlen; i++, v++) {
-			name = btf_name_of(d, v->name_off);
-			/* enumerators share namespace with typedef idents */
-			dup_cnt = btf_dump_name_dups(d, d->ident_names, name);
-			if (dup_cnt > 1) {
-				btf_dump_printf(d, "\n%s%s___%zu = %u,",
-						pfx(lvl + 1), name, dup_cnt,
-						(__u32)v->val);
-			} else {
-				btf_dump_printf(d, "\n%s%s = %u,",
-						pfx(lvl + 1), name,
-						(__u32)v->val);
+	if (!vlen)
+		return;
+
+	btf_dump_printf(d, " {");
+	if (btf_is_enum(t))
+		btf_dump_emit_enum32_val(d, t, lvl, vlen);
+	else
+		btf_dump_emit_enum64_val(d, t, lvl, vlen);
+	btf_dump_printf(d, "\n%s}", pfx(lvl));
+
+	/* special case enums with special sizes */
+	if (t->size == 1) {
+		/* one-byte enums can be forced with mode(byte) attribute */
+		btf_dump_printf(d, " __attribute__((mode(byte)))");
+	} else if (t->size == 8 && d->ptr_sz == 8) {
+		/* enum can be 8-byte sized if one of the enumerator values
+		 * doesn't fit in 32-bit integer, or by adding mode(word)
+		 * attribute (but probably only on 64-bit architectures); do
+		 * our best here to try to satisfy the contract without adding
+		 * unnecessary attributes
+		 */
+		bool needs_word_mode;
+
+		if (btf_is_enum(t)) {
+			/* enum can't represent 64-bit values, so we need word mode */
+			needs_word_mode = true;
+		} else {
+			/* enum64 needs mode(word) if none of its values has
+			 * non-zero upper 32-bits (which means that all values
+			 * fit in 32-bit integers and won't cause compiler to
+			 * bump enum to be 64-bit naturally
+			 */
+			int i;
+
+			needs_word_mode = true;
+			for (i = 0; i < vlen; i++) {
+				if (btf_enum64(t)[i].val_hi32 != 0) {
+					needs_word_mode = false;
+					break;
+				}
 			}
 		}
-		btf_dump_printf(d, "\n%s}", pfx(lvl));
+		if (needs_word_mode)
+			btf_dump_printf(d, " __attribute__((mode(word)))");
 	}
+
 }
 
 static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id,
@@ -1154,6 +1319,7 @@ skip_mod:
 		case BTF_KIND_CONST:
 		case BTF_KIND_RESTRICT:
 		case BTF_KIND_FUNC_PROTO:
+		case BTF_KIND_TYPE_TAG:
 			id = t->type;
 			break;
 		case BTF_KIND_ARRAY:
@@ -1161,6 +1327,7 @@ skip_mod:
 			break;
 		case BTF_KIND_INT:
 		case BTF_KIND_ENUM:
+		case BTF_KIND_ENUM64:
 		case BTF_KIND_FWD:
 		case BTF_KIND_STRUCT:
 		case BTF_KIND_UNION:
@@ -1295,6 +1462,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 				btf_dump_emit_struct_fwd(d, id, t);
 			break;
 		case BTF_KIND_ENUM:
+		case BTF_KIND_ENUM64:
 			btf_dump_emit_mods(d, decls);
 			/* inline anonymous enum */
 			if (t->name_off == 0 && !d->skip_anon_defs)
@@ -1322,6 +1490,11 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 		case BTF_KIND_RESTRICT:
 			btf_dump_printf(d, " restrict");
 			break;
+		case BTF_KIND_TYPE_TAG:
+			btf_dump_emit_mods(d, decls);
+			name = btf_name_of(d, t->name_off);
+			btf_dump_printf(d, " __attribute__((btf_type_tag(\"%s\")))", name);
+			break;
 		case BTF_KIND_ARRAY: {
 			const struct btf_array *a = btf_array(t);
 			const struct btf_type *next_t;
@@ -1459,11 +1632,22 @@ static void btf_dump_emit_type_cast(struct btf_dump *d, __u32 id,
 static size_t btf_dump_name_dups(struct btf_dump *d, struct hashmap *name_map,
 				 const char *orig_name)
 {
+	char *old_name, *new_name;
 	size_t dup_cnt = 0;
+	int err;
 
-	hashmap__find(name_map, orig_name, (void **)&dup_cnt);
+	new_name = strdup(orig_name);
+	if (!new_name)
+		return 1;
+
+	(void)hashmap__find(name_map, orig_name, &dup_cnt);
 	dup_cnt++;
-	hashmap__set(name_map, orig_name, (void *)dup_cnt, NULL, NULL);
+
+	err = hashmap__set(name_map, new_name, dup_cnt, &old_name, NULL);
+	if (err)
+		free(new_name);
+
+	free(old_name);
 
 	return dup_cnt;
 }
@@ -1483,6 +1667,11 @@ static const char *btf_dump_resolve_name(struct btf_dump *d, __u32 id,
 	if (s->name_resolved)
 		return *cached_name ? *cached_name : orig_name;
 
+	if (btf_is_fwd(t) || (btf_is_enum(t) && btf_vlen(t) == 0)) {
+		s->name_resolved = 1;
+		return orig_name;
+	}
+
 	dup_cnt = btf_dump_name_dups(d, name_map, orig_name);
 	if (dup_cnt > 1) {
 		const size_t max_len = 256;
@@ -1740,6 +1929,7 @@ static int btf_dump_int_data(struct btf_dump *d,
 			if (d->typed_dump->is_array_terminated)
 				break;
 			if (*(char *)data == '\0') {
+				btf_dump_type_values(d, "'\\0'");
 				d->typed_dump->is_array_terminated = true;
 				break;
 			}
@@ -1839,14 +2029,17 @@ static int btf_dump_array_data(struct btf_dump *d,
 {
 	const struct btf_array *array = btf_array(t);
 	const struct btf_type *elem_type;
-	__u32 i, elem_size = 0, elem_type_id;
+	__u32 i, elem_type_id;
+	__s64 elem_size;
 	bool is_array_member;
+	bool is_array_terminated;
 
 	elem_type_id = array->type;
 	elem_type = skip_mods_and_typedefs(d->btf, elem_type_id, NULL);
 	elem_size = btf__resolve_size(d->btf, elem_type_id);
 	if (elem_size <= 0) {
-		pr_warn("unexpected elem size %d for array type [%u]\n", elem_size, id);
+		pr_warn("unexpected elem size %zd for array type [%u]\n",
+			(ssize_t)elem_size, id);
 		return -EINVAL;
 	}
 
@@ -1875,12 +2068,15 @@ static int btf_dump_array_data(struct btf_dump *d,
 	 */
 	is_array_member = d->typed_dump->is_array_member;
 	d->typed_dump->is_array_member = true;
+	is_array_terminated = d->typed_dump->is_array_terminated;
+	d->typed_dump->is_array_terminated = false;
 	for (i = 0; i < array->nelems; i++, data += elem_size) {
 		if (d->typed_dump->is_array_terminated)
 			break;
 		btf_dump_dump_type_data(d, NULL, elem_type, elem_type_id, data, 0, 0);
 	}
 	d->typed_dump->is_array_member = is_array_member;
+	d->typed_dump->is_array_terminated = is_array_terminated;
 	d->typed_dump->depth--;
 	btf_dump_data_pfx(d);
 	btf_dump_type_values(d, "]");
@@ -1895,7 +2091,7 @@ static int btf_dump_struct_data(struct btf_dump *d,
 {
 	const struct btf_member *m = btf_members(t);
 	__u16 n = btf_vlen(t);
-	int i, err;
+	int i, err = 0;
 
 	/* note that we increment depth before calling btf_dump_print() below;
 	 * this is intentional.  btf_dump_data_newline() will not print a
@@ -1959,7 +2155,8 @@ static int btf_dump_get_enum_value(struct btf_dump *d,
 				   __u32 id,
 				   __s64 *value)
 {
-	/* handle unaligned enum value */
+	bool is_signed = btf_kflag(t);
+
 	if (!ptr_is_aligned(d->btf, id, data)) {
 		__u64 val;
 		int err;
@@ -1976,13 +2173,13 @@ static int btf_dump_get_enum_value(struct btf_dump *d,
 		*value = *(__s64 *)data;
 		return 0;
 	case 4:
-		*value = *(__s32 *)data;
+		*value = is_signed ? (__s64)*(__s32 *)data : *(__u32 *)data;
 		return 0;
 	case 2:
-		*value = *(__s16 *)data;
+		*value = is_signed ? *(__s16 *)data : *(__u16 *)data;
 		return 0;
 	case 1:
-		*value = *(__s8 *)data;
+		*value = is_signed ? *(__s8 *)data : *(__u8 *)data;
 		return 0;
 	default:
 		pr_warn("unexpected size %d for enum, id:[%u]\n", t->size, id);
@@ -1995,7 +2192,7 @@ static int btf_dump_enum_data(struct btf_dump *d,
 			      __u32 id,
 			      const void *data)
 {
-	const struct btf_enum *e;
+	bool is_signed;
 	__s64 value;
 	int i, err;
 
@@ -2003,14 +2200,31 @@ static int btf_dump_enum_data(struct btf_dump *d,
 	if (err)
 		return err;
 
-	for (i = 0, e = btf_enum(t); i < btf_vlen(t); i++, e++) {
-		if (value != e->val)
-			continue;
-		btf_dump_type_values(d, "%s", btf_name_of(d, e->name_off));
-		return 0;
-	}
+	is_signed = btf_kflag(t);
+	if (btf_is_enum(t)) {
+		const struct btf_enum *e;
 
-	btf_dump_type_values(d, "%d", value);
+		for (i = 0, e = btf_enum(t); i < btf_vlen(t); i++, e++) {
+			if (value != e->val)
+				continue;
+			btf_dump_type_values(d, "%s", btf_name_of(d, e->name_off));
+			return 0;
+		}
+
+		btf_dump_type_values(d, is_signed ? "%d" : "%u", value);
+	} else {
+		const struct btf_enum64 *e;
+
+		for (i = 0, e = btf_enum64(t); i < btf_vlen(t); i++, e++) {
+			if (value != btf_enum64_value(e))
+				continue;
+			btf_dump_type_values(d, "%s", btf_name_of(d, e->name_off));
+			return 0;
+		}
+
+		btf_dump_type_values(d, is_signed ? "%lldLL" : "%lluULL",
+				     (unsigned long long)value);
+	}
 	return 0;
 }
 
@@ -2041,9 +2255,25 @@ static int btf_dump_type_data_check_overflow(struct btf_dump *d,
 					     const struct btf_type *t,
 					     __u32 id,
 					     const void *data,
-					     __u8 bits_offset)
+					     __u8 bits_offset,
+					     __u8 bit_sz)
 {
-	__s64 size = btf__resolve_size(d->btf, id);
+	__s64 size;
+
+	if (bit_sz) {
+		/* bits_offset is at most 7. bit_sz is at most 128. */
+		__u8 nr_bytes = (bits_offset + bit_sz + 7) / 8;
+
+		/* When bit_sz is non zero, it is called from
+		 * btf_dump_struct_data() where it only cares about
+		 * negative error value.
+		 * Return nr_bytes in success case to make it
+		 * consistent as the regular integer case below.
+		 */
+		return data + nr_bytes > d->typed_dump->data_end ? -E2BIG : nr_bytes;
+	}
+
+	size = btf__resolve_size(d->btf, id);
 
 	if (size < 0 || size >= INT_MAX) {
 		pr_warn("unexpected size [%zu] for id [%u]\n",
@@ -2070,6 +2300,7 @@ static int btf_dump_type_data_check_overflow(struct btf_dump *d,
 	case BTF_KIND_FLOAT:
 	case BTF_KIND_PTR:
 	case BTF_KIND_ENUM:
+	case BTF_KIND_ENUM64:
 		if (data + bits_offset / 8 + size > d->typed_dump->data_end)
 			return -E2BIG;
 		break;
@@ -2174,6 +2405,7 @@ static int btf_dump_type_data_check_zero(struct btf_dump *d,
 		return -ENODATA;
 	}
 	case BTF_KIND_ENUM:
+	case BTF_KIND_ENUM64:
 		err = btf_dump_get_enum_value(d, t, data, id, &value);
 		if (err)
 			return err;
@@ -2194,9 +2426,9 @@ static int btf_dump_dump_type_data(struct btf_dump *d,
 				   __u8 bits_offset,
 				   __u8 bit_sz)
 {
-	int size, err;
+	int size, err = 0;
 
-	size = btf_dump_type_data_check_overflow(d, t, id, data, bits_offset);
+	size = btf_dump_type_data_check_overflow(d, t, id, data, bits_offset, bit_sz);
 	if (size < 0)
 		return size;
 	err = btf_dump_type_data_check_zero(d, t, id, data, bits_offset, bit_sz);
@@ -2246,6 +2478,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d,
 		err = btf_dump_struct_data(d, t, id, data);
 		break;
 	case BTF_KIND_ENUM:
+	case BTF_KIND_ENUM64:
 		/* handle bitfield and int enum values */
 		if (bit_sz) {
 			__u64 print_num;
@@ -2296,11 +2529,11 @@ int btf_dump__dump_type_data(struct btf_dump *d, __u32 id,
 	d->typed_dump->indent_lvl = OPTS_GET(opts, indent_level, 0);
 
 	/* default indent string is a tab */
-	if (!opts->indent_str)
+	if (!OPTS_GET(opts, indent_str, NULL))
 		d->typed_dump->indent_str[0] = '\t';
 	else
-		strncat(d->typed_dump->indent_str, opts->indent_str,
-			sizeof(d->typed_dump->indent_str) - 1);
+		libbpf_strlcpy(d->typed_dump->indent_str, opts->indent_str,
+			       sizeof(d->typed_dump->indent_str));
 
 	d->typed_dump->compact = OPTS_GET(opts, compact, false);
 	d->typed_dump->skip_names = OPTS_GET(opts, skip_names, false);

src/elf.c

@@ -0,0 +1,558 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE
+#endif
+#include <libelf.h>
+#include <gelf.h>
+#include <fcntl.h>
+#include <linux/kernel.h>
+
+#include "libbpf_internal.h"
+#include "str_error.h"
+
+/* A SHT_GNU_versym section holds 16-bit words. This bit is set if
+ * the symbol is hidden and can only be seen when referenced using an
+ * explicit version number. This is a GNU extension.
+ */
+#define VERSYM_HIDDEN	0x8000
+
+/* This is the mask for the rest of the data in a word read from a
+ * SHT_GNU_versym section.
+ */
+#define VERSYM_VERSION	0x7fff
+
+int elf_open(const char *binary_path, struct elf_fd *elf_fd)
+{
+	char errmsg[STRERR_BUFSIZE];
+	int fd, ret;
+	Elf *elf;
+
+	if (elf_version(EV_CURRENT) == EV_NONE) {
+		pr_warn("elf: failed to init libelf for %s\n", binary_path);
+		return -LIBBPF_ERRNO__LIBELF;
+	}
+	fd = open(binary_path, O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		ret = -errno;
+		pr_warn("elf: failed to open %s: %s\n", binary_path,
+			libbpf_strerror_r(ret, errmsg, sizeof(errmsg)));
+		return ret;
+	}
+	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
+	if (!elf) {
+		pr_warn("elf: could not read elf from %s: %s\n", binary_path, elf_errmsg(-1));
+		close(fd);
+		return -LIBBPF_ERRNO__FORMAT;
+	}
+	elf_fd->fd = fd;
+	elf_fd->elf = elf;
+	return 0;
+}
+
+void elf_close(struct elf_fd *elf_fd)
+{
+	if (!elf_fd)
+		return;
+	elf_end(elf_fd->elf);
+	close(elf_fd->fd);
+}
+
+/* Return next ELF section of sh_type after scn, or first of that type if scn is NULL. */
+static Elf_Scn *elf_find_next_scn_by_type(Elf *elf, int sh_type, Elf_Scn *scn)
+{
+	while ((scn = elf_nextscn(elf, scn)) != NULL) {
+		GElf_Shdr sh;
+
+		if (!gelf_getshdr(scn, &sh))
+			continue;
+		if (sh.sh_type == sh_type)
+			return scn;
+	}
+	return NULL;
+}
+
+struct elf_sym {
+	const char *name;
+	GElf_Sym sym;
+	GElf_Shdr sh;
+	int ver;
+	bool hidden;
+};
+
+struct elf_sym_iter {
+	Elf *elf;
+	Elf_Data *syms;
+	Elf_Data *versyms;
+	Elf_Data *verdefs;
+	size_t nr_syms;
+	size_t strtabidx;
+	size_t verdef_strtabidx;
+	size_t next_sym_idx;
+	struct elf_sym sym;
+	int st_type;
+};
+
+static int elf_sym_iter_new(struct elf_sym_iter *iter,
+			    Elf *elf, const char *binary_path,
+			    int sh_type, int st_type)
+{
+	Elf_Scn *scn = NULL;
+	GElf_Ehdr ehdr;
+	GElf_Shdr sh;
+
+	memset(iter, 0, sizeof(*iter));
+
+	if (!gelf_getehdr(elf, &ehdr)) {
+		pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1));
+		return -EINVAL;
+	}
+
+	scn = elf_find_next_scn_by_type(elf, sh_type, NULL);
+	if (!scn) {
+		pr_debug("elf: failed to find symbol table ELF sections in '%s'\n",
+			 binary_path);
+		return -ENOENT;
+	}
+
+	if (!gelf_getshdr(scn, &sh))
+		return -EINVAL;
+
+	iter->strtabidx = sh.sh_link;
+	iter->syms = elf_getdata(scn, 0);
+	if (!iter->syms) {
+		pr_warn("elf: failed to get symbols for symtab section in '%s': %s\n",
+			binary_path, elf_errmsg(-1));
+		return -EINVAL;
+	}
+	iter->nr_syms = iter->syms->d_size / sh.sh_entsize;
+	iter->elf = elf;
+	iter->st_type = st_type;
+
+	/* Version symbol table is meaningful to dynsym only */
+	if (sh_type != SHT_DYNSYM)
+		return 0;
+
+	scn = elf_find_next_scn_by_type(elf, SHT_GNU_versym, NULL);
+	if (!scn)
+		return 0;
+	iter->versyms = elf_getdata(scn, 0);
+
+	scn = elf_find_next_scn_by_type(elf, SHT_GNU_verdef, NULL);
+	if (!scn)
+		return 0;
+
+	iter->verdefs = elf_getdata(scn, 0);
+	if (!iter->verdefs || !gelf_getshdr(scn, &sh)) {
+		pr_warn("elf: failed to get verdef ELF section in '%s'\n", binary_path);
+		return -EINVAL;
+	}
+	iter->verdef_strtabidx = sh.sh_link;
+
+	return 0;
+}
+
+static struct elf_sym *elf_sym_iter_next(struct elf_sym_iter *iter)
+{
+	struct elf_sym *ret = &iter->sym;
+	GElf_Sym *sym = &ret->sym;
+	const char *name = NULL;
+	GElf_Versym versym;
+	Elf_Scn *sym_scn;
+	size_t idx;
+
+	for (idx = iter->next_sym_idx; idx < iter->nr_syms; idx++) {
+		if (!gelf_getsym(iter->syms, idx, sym))
+			continue;
+		if (GELF_ST_TYPE(sym->st_info) != iter->st_type)
+			continue;
+		name = elf_strptr(iter->elf, iter->strtabidx, sym->st_name);
+		if (!name)
+			continue;
+		sym_scn = elf_getscn(iter->elf, sym->st_shndx);
+		if (!sym_scn)
+			continue;
+		if (!gelf_getshdr(sym_scn, &ret->sh))
+			continue;
+
+		iter->next_sym_idx = idx + 1;
+		ret->name = name;
+		ret->ver = 0;
+		ret->hidden = false;
+
+		if (iter->versyms) {
+			if (!gelf_getversym(iter->versyms, idx, &versym))
+				continue;
+			ret->ver = versym & VERSYM_VERSION;
+			ret->hidden = versym & VERSYM_HIDDEN;
+		}
+		return ret;
+	}
+
+	return NULL;
+}
+
+static const char *elf_get_vername(struct elf_sym_iter *iter, int ver)
+{
+	GElf_Verdaux verdaux;
+	GElf_Verdef verdef;
+	int offset;
+
+	if (!iter->verdefs)
+		return NULL;
+
+	offset = 0;
+	while (gelf_getverdef(iter->verdefs, offset, &verdef)) {
+		if (verdef.vd_ndx != ver) {
+			if (!verdef.vd_next)
+				break;
+
+			offset += verdef.vd_next;
+			continue;
+		}
+
+		if (!gelf_getverdaux(iter->verdefs, offset + verdef.vd_aux, &verdaux))
+			break;
+
+		return elf_strptr(iter->elf, iter->verdef_strtabidx, verdaux.vda_name);
+
+	}
+	return NULL;
+}
+
+static bool symbol_match(struct elf_sym_iter *iter, int sh_type, struct elf_sym *sym,
+			 const char *name, size_t name_len, const char *lib_ver)
+{
+	const char *ver_name;
+
+	/* Symbols are in forms of func, func@LIB_VER or func@@LIB_VER
+	 * make sure the func part matches the user specified name
+	 */
+	if (strncmp(sym->name, name, name_len) != 0)
+		return false;
+
+	/* ...but we don't want a search for "foo" to match 'foo2" also, so any
+	 * additional characters in sname should be of the form "@@LIB".
+	 */
+	if (sym->name[name_len] != '\0' && sym->name[name_len] != '@')
+		return false;
+
+	/* If user does not specify symbol version, then we got a match */
+	if (!lib_ver)
+		return true;
+
+	/* If user specifies symbol version, for dynamic symbols,
+	 * get version name from ELF verdef section for comparison.
+	 */
+	if (sh_type == SHT_DYNSYM) {
+		ver_name = elf_get_vername(iter, sym->ver);
+		if (!ver_name)
+			return false;
+		return strcmp(ver_name, lib_ver) == 0;
+	}
+
+	/* For normal symbols, it is already in form of func@LIB_VER */
+	return strcmp(sym->name, name) == 0;
+}
+
+/* Transform symbol's virtual address (absolute for binaries and relative
+ * for shared libs) into file offset, which is what kernel is expecting
+ * for uprobe/uretprobe attachment.
+ * See Documentation/trace/uprobetracer.rst for more details. This is done
+ * by looking up symbol's containing section's header and using iter's virtual
+ * address (sh_addr) and corresponding file offset (sh_offset) to transform
+ * sym.st_value (virtual address) into desired final file offset.
+ */
+static unsigned long elf_sym_offset(struct elf_sym *sym)
+{
+	return sym->sym.st_value - sym->sh.sh_addr + sym->sh.sh_offset;
+}
+
+/* Find offset of function name in the provided ELF object. "binary_path" is
+ * the path to the ELF binary represented by "elf", and only used for error
+ * reporting matters. "name" matches symbol name or name@@LIB for library
+ * functions.
+ */
+long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name)
+{
+	int i, sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB };
+	const char *at_symbol, *lib_ver;
+	bool is_shared_lib;
+	long ret = -ENOENT;
+	size_t name_len;
+	GElf_Ehdr ehdr;
+
+	if (!gelf_getehdr(elf, &ehdr)) {
+		pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1));
+		ret = -LIBBPF_ERRNO__FORMAT;
+		goto out;
+	}
+	/* for shared lib case, we do not need to calculate relative offset */
+	is_shared_lib = ehdr.e_type == ET_DYN;
+
+	/* Does name specify "@@LIB_VER" or "@LIB_VER" ? */
+	at_symbol = strchr(name, '@');
+	if (at_symbol) {
+		name_len = at_symbol - name;
+		/* skip second @ if it's @@LIB_VER case */
+		if (at_symbol[1] == '@')
+			at_symbol++;
+		lib_ver = at_symbol + 1;
+	} else {
+		name_len = strlen(name);
+		lib_ver = NULL;
+	}
+
+	/* Search SHT_DYNSYM, SHT_SYMTAB for symbol. This search order is used because if
+	 * a binary is stripped, it may only have SHT_DYNSYM, and a fully-statically
+	 * linked binary may not have SHT_DYMSYM, so absence of a section should not be
+	 * reported as a warning/error.
+	 */
+	for (i = 0; i < ARRAY_SIZE(sh_types); i++) {
+		struct elf_sym_iter iter;
+		struct elf_sym *sym;
+		int last_bind = -1;
+		int cur_bind;
+
+		ret = elf_sym_iter_new(&iter, elf, binary_path, sh_types[i], STT_FUNC);
+		if (ret == -ENOENT)
+			continue;
+		if (ret)
+			goto out;
+
+		while ((sym = elf_sym_iter_next(&iter))) {
+			if (!symbol_match(&iter, sh_types[i], sym, name, name_len, lib_ver))
+				continue;
+
+			cur_bind = GELF_ST_BIND(sym->sym.st_info);
+
+			if (ret > 0) {
+				/* handle multiple matches */
+				if (elf_sym_offset(sym) == ret) {
+					/* same offset, no problem */
+					continue;
+				} else if (last_bind != STB_WEAK && cur_bind != STB_WEAK) {
+					/* Only accept one non-weak bind. */
+					pr_warn("elf: ambiguous match for '%s', '%s' in '%s'\n",
+						sym->name, name, binary_path);
+					ret = -LIBBPF_ERRNO__FORMAT;
+					goto out;
+				} else if (cur_bind == STB_WEAK) {
+					/* already have a non-weak bind, and
+					 * this is a weak bind, so ignore.
+					 */
+					continue;
+				}
+			}
+
+			ret = elf_sym_offset(sym);
+			last_bind = cur_bind;
+		}
+		if (ret > 0)
+			break;
+	}
+
+	if (ret > 0) {
+		pr_debug("elf: symbol address match for '%s' in '%s': 0x%lx\n", name, binary_path,
+			 ret);
+	} else {
+		if (ret == 0) {
+			pr_warn("elf: '%s' is 0 in symtab for '%s': %s\n", name, binary_path,
+				is_shared_lib ? "should not be 0 in a shared library" :
+						"try using shared library path instead");
+			ret = -ENOENT;
+		} else {
+			pr_warn("elf: failed to find symbol '%s' in '%s'\n", name, binary_path);
+		}
+	}
+out:
+	return ret;
+}
+
+/* Find offset of function name in ELF object specified by path. "name" matches
+ * symbol name or name@@LIB for library functions.
+ */
+long elf_find_func_offset_from_file(const char *binary_path, const char *name)
+{
+	struct elf_fd elf_fd;
+	long ret = -ENOENT;
+
+	ret = elf_open(binary_path, &elf_fd);
+	if (ret)
+		return ret;
+	ret = elf_find_func_offset(elf_fd.elf, binary_path, name);
+	elf_close(&elf_fd);
+	return ret;
+}
+
+struct symbol {
+	const char *name;
+	int bind;
+	int idx;
+};
+
+static int symbol_cmp(const void *a, const void *b)
+{
+	const struct symbol *sym_a = a;
+	const struct symbol *sym_b = b;
+
+	return strcmp(sym_a->name, sym_b->name);
+}
+
+/*
+ * Return offsets in @poffsets for symbols specified in @syms array argument.
+ * On success returns 0 and offsets are returned in allocated array with @cnt
+ * size, that needs to be released by the caller.
+ */
+int elf_resolve_syms_offsets(const char *binary_path, int cnt,
+			     const char **syms, unsigned long **poffsets,
+			     int st_type)
+{
+	int sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB };
+	int err = 0, i, cnt_done = 0;
+	unsigned long *offsets;
+	struct symbol *symbols;
+	struct elf_fd elf_fd;
+
+	err = elf_open(binary_path, &elf_fd);
+	if (err)
+		return err;
+
+	offsets = calloc(cnt, sizeof(*offsets));
+	symbols = calloc(cnt, sizeof(*symbols));
+
+	if (!offsets || !symbols) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0; i < cnt; i++) {
+		symbols[i].name = syms[i];
+		symbols[i].idx = i;
+	}
+
+	qsort(symbols, cnt, sizeof(*symbols), symbol_cmp);
+
+	for (i = 0; i < ARRAY_SIZE(sh_types); i++) {
+		struct elf_sym_iter iter;
+		struct elf_sym *sym;
+
+		err = elf_sym_iter_new(&iter, elf_fd.elf, binary_path, sh_types[i], st_type);
+		if (err == -ENOENT)
+			continue;
+		if (err)
+			goto out;
+
+		while ((sym = elf_sym_iter_next(&iter))) {
+			unsigned long sym_offset = elf_sym_offset(sym);
+			int bind = GELF_ST_BIND(sym->sym.st_info);
+			struct symbol *found, tmp = {
+				.name = sym->name,
+			};
+			unsigned long *offset;
+
+			found = bsearch(&tmp, symbols, cnt, sizeof(*symbols), symbol_cmp);
+			if (!found)
+				continue;
+
+			offset = &offsets[found->idx];
+			if (*offset > 0) {
+				/* same offset, no problem */
+				if (*offset == sym_offset)
+					continue;
+				/* handle multiple matches */
+				if (found->bind != STB_WEAK && bind != STB_WEAK) {
+					/* Only accept one non-weak bind. */
+					pr_warn("elf: ambiguous match found '%s@%lu' in '%s' previous offset %lu\n",
+						sym->name, sym_offset, binary_path, *offset);
+					err = -ESRCH;
+					goto out;
+				} else if (bind == STB_WEAK) {
+					/* already have a non-weak bind, and
+					 * this is a weak bind, so ignore.
+					 */
+					continue;
+				}
+			} else {
+				cnt_done++;
+			}
+			*offset = sym_offset;
+			found->bind = bind;
+		}
+	}
+
+	if (cnt != cnt_done) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	*poffsets = offsets;
+
+out:
+	free(symbols);
+	if (err)
+		free(offsets);
+	elf_close(&elf_fd);
+	return err;
+}
+
+/*
+ * Return offsets in @poffsets for symbols specified by @pattern argument.
+ * On success returns 0 and offsets are returned in allocated @poffsets
+ * array with the @pctn size, that needs to be released by the caller.
+ */
+int elf_resolve_pattern_offsets(const char *binary_path, const char *pattern,
+				unsigned long **poffsets, size_t *pcnt)
+{
+	int sh_types[2] = { SHT_SYMTAB, SHT_DYNSYM };
+	unsigned long *offsets = NULL;
+	size_t cap = 0, cnt = 0;
+	struct elf_fd elf_fd;
+	int err = 0, i;
+
+	err = elf_open(binary_path, &elf_fd);
+	if (err)
+		return err;
+
+	for (i = 0; i < ARRAY_SIZE(sh_types); i++) {
+		struct elf_sym_iter iter;
+		struct elf_sym *sym;
+
+		err = elf_sym_iter_new(&iter, elf_fd.elf, binary_path, sh_types[i], STT_FUNC);
+		if (err == -ENOENT)
+			continue;
+		if (err)
+			goto out;
+
+		while ((sym = elf_sym_iter_next(&iter))) {
+			if (!glob_match(sym->name, pattern))
+				continue;
+
+			err = libbpf_ensure_mem((void **) &offsets, &cap, sizeof(*offsets),
+						cnt + 1);
+			if (err)
+				goto out;
+
+			offsets[cnt++] = elf_sym_offset(sym);
+		}
+
+		/* If we found anything in the first symbol section,
+		 * do not search others to avoid duplicates.
+		 */
+		if (cnt)
+			break;
+	}
+
+	if (cnt) {
+		*poffsets = offsets;
+		*pcnt = cnt;
+	} else {
+		err = -ENOENT;
+	}
+
+out:
+	if (err)
+		free(offsets);
+	elf_close(&elf_fd);
+	return err;
+}

src/features.c

@@ -0,0 +1,583 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+#include <linux/kernel.h>
+#include <linux/filter.h>
+#include "bpf.h"
+#include "libbpf.h"
+#include "libbpf_common.h"
+#include "libbpf_internal.h"
+#include "str_error.h"
+
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+	return (__u64)(unsigned long)ptr;
+}
+
+int probe_fd(int fd)
+{
+	if (fd >= 0)
+		close(fd);
+	return fd >= 0;
+}
+
+static int probe_kern_prog_name(int token_fd)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, prog_name);
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	union bpf_attr attr;
+	int ret;
+
+	memset(&attr, 0, attr_sz);
+	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+	attr.license = ptr_to_u64("GPL");
+	attr.insns = ptr_to_u64(insns);
+	attr.insn_cnt = (__u32)ARRAY_SIZE(insns);
+	attr.prog_token_fd = token_fd;
+	if (token_fd)
+		attr.prog_flags |= BPF_F_TOKEN_FD;
+	libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name));
+
+	/* make sure loading with name works */
+	ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS);
+	return probe_fd(ret);
+}
+
+static int probe_kern_global_data(int token_fd)
+{
+	char *cp, errmsg[STRERR_BUFSIZE];
+	struct bpf_insn insns[] = {
+		BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16),
+		BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts,
+		.token_fd = token_fd,
+		.map_flags = token_fd ? BPF_F_TOKEN_FD : 0,
+	);
+	LIBBPF_OPTS(bpf_prog_load_opts, prog_opts,
+		.token_fd = token_fd,
+		.prog_flags = token_fd ? BPF_F_TOKEN_FD : 0,
+	);
+	int ret, map, insn_cnt = ARRAY_SIZE(insns);
+
+	map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, &map_opts);
+	if (map < 0) {
+		ret = -errno;
+		cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
+		pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n",
+			__func__, cp, -ret);
+		return ret;
+	}
+
+	insns[0].imm = map;
+
+	ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts);
+	close(map);
+	return probe_fd(ret);
+}
+
+static int probe_kern_btf(int token_fd)
+{
+	static const char strs[] = "\0int";
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs), token_fd));
+}
+
+static int probe_kern_btf_func(int token_fd)
+{
+	static const char strs[] = "\0int\0x\0a";
+	/* void x(int a) {} */
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* FUNC_PROTO */                                /* [2] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0),
+		BTF_PARAM_ENC(7, 1),
+		/* FUNC x */                                    /* [3] */
+		BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs), token_fd));
+}
+
+static int probe_kern_btf_func_global(int token_fd)
+{
+	static const char strs[] = "\0int\0x\0a";
+	/* static void x(int a) {} */
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* FUNC_PROTO */                                /* [2] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0),
+		BTF_PARAM_ENC(7, 1),
+		/* FUNC x BTF_FUNC_GLOBAL */                    /* [3] */
+		BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs), token_fd));
+}
+
+static int probe_kern_btf_datasec(int token_fd)
+{
+	static const char strs[] = "\0x\0.data";
+	/* static int a; */
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* VAR x */                                     /* [2] */
+		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
+		BTF_VAR_STATIC,
+		/* DATASEC val */                               /* [3] */
+		BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+		BTF_VAR_SECINFO_ENC(2, 0, 4),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs), token_fd));
+}
+
+static int probe_kern_btf_qmark_datasec(int token_fd)
+{
+	static const char strs[] = "\0x\0?.data";
+	/* static int a; */
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* VAR x */                                     /* [2] */
+		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
+		BTF_VAR_STATIC,
+		/* DATASEC ?.data */                            /* [3] */
+		BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+		BTF_VAR_SECINFO_ENC(2, 0, 4),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs), token_fd));
+}
+
+static int probe_kern_btf_float(int token_fd)
+{
+	static const char strs[] = "\0float";
+	__u32 types[] = {
+		/* float */
+		BTF_TYPE_FLOAT_ENC(1, 4),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs), token_fd));
+}
+
+static int probe_kern_btf_decl_tag(int token_fd)
+{
+	static const char strs[] = "\0tag";
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* VAR x */                                     /* [2] */
+		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
+		BTF_VAR_STATIC,
+		/* attr */
+		BTF_TYPE_DECL_TAG_ENC(1, 2, -1),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs), token_fd));
+}
+
+static int probe_kern_btf_type_tag(int token_fd)
+{
+	static const char strs[] = "\0tag";
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		/* attr */
+		BTF_TYPE_TYPE_TAG_ENC(1, 1),				/* [2] */
+		/* ptr */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2),	/* [3] */
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs), token_fd));
+}
+
+static int probe_kern_array_mmap(int token_fd)
+{
+	LIBBPF_OPTS(bpf_map_create_opts, opts,
+		.map_flags = BPF_F_MMAPABLE | (token_fd ? BPF_F_TOKEN_FD : 0),
+		.token_fd = token_fd,
+	);
+	int fd;
+
+	fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts);
+	return probe_fd(fd);
+}
+
+static int probe_kern_exp_attach_type(int token_fd)
+{
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE,
+		.token_fd = token_fd,
+		.prog_flags = token_fd ? BPF_F_TOKEN_FD : 0,
+	);
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int fd, insn_cnt = ARRAY_SIZE(insns);
+
+	/* use any valid combination of program type and (optional)
+	 * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS)
+	 * to see if kernel supports expected_attach_type field for
+	 * BPF_PROG_LOAD command
+	 */
+	fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, insn_cnt, &opts);
+	return probe_fd(fd);
+}
+
+static int probe_kern_probe_read_kernel(int token_fd)
+{
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		.token_fd = token_fd,
+		.prog_flags = token_fd ? BPF_F_TOKEN_FD : 0,
+	);
+	struct bpf_insn insns[] = {
+		BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),	/* r1 = r10 (fp) */
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),	/* r1 += -8 */
+		BPF_MOV64_IMM(BPF_REG_2, 8),		/* r2 = 8 */
+		BPF_MOV64_IMM(BPF_REG_3, 0),		/* r3 = 0 */
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel),
+		BPF_EXIT_INSN(),
+	};
+	int fd, insn_cnt = ARRAY_SIZE(insns);
+
+	fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts);
+	return probe_fd(fd);
+}
+
+static int probe_prog_bind_map(int token_fd)
+{
+	char *cp, errmsg[STRERR_BUFSIZE];
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts,
+		.token_fd = token_fd,
+		.map_flags = token_fd ? BPF_F_TOKEN_FD : 0,
+	);
+	LIBBPF_OPTS(bpf_prog_load_opts, prog_opts,
+		.token_fd = token_fd,
+		.prog_flags = token_fd ? BPF_F_TOKEN_FD : 0,
+	);
+	int ret, map, prog, insn_cnt = ARRAY_SIZE(insns);
+
+	map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, &map_opts);
+	if (map < 0) {
+		ret = -errno;
+		cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
+		pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n",
+			__func__, cp, -ret);
+		return ret;
+	}
+
+	prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts);
+	if (prog < 0) {
+		close(map);
+		return 0;
+	}
+
+	ret = bpf_prog_bind_map(prog, map, NULL);
+
+	close(map);
+	close(prog);
+
+	return ret >= 0;
+}
+
+static int probe_module_btf(int token_fd)
+{
+	static const char strs[] = "\0int";
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),
+	};
+	struct bpf_btf_info info;
+	__u32 len = sizeof(info);
+	char name[16];
+	int fd, err;
+
+	fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs), token_fd);
+	if (fd < 0)
+		return 0; /* BTF not supported at all */
+
+	memset(&info, 0, sizeof(info));
+	info.name = ptr_to_u64(name);
+	info.name_len = sizeof(name);
+
+	/* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer;
+	 * kernel's module BTF support coincides with support for
+	 * name/name_len fields in struct bpf_btf_info.
+	 */
+	err = bpf_btf_get_info_by_fd(fd, &info, &len);
+	close(fd);
+	return !err;
+}
+
+static int probe_perf_link(int token_fd)
+{
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		.token_fd = token_fd,
+		.prog_flags = token_fd ? BPF_F_TOKEN_FD : 0,
+	);
+	int prog_fd, link_fd, err;
+
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL",
+				insns, ARRAY_SIZE(insns), &opts);
+	if (prog_fd < 0)
+		return -errno;
+
+	/* use invalid perf_event FD to get EBADF, if link is supported;
+	 * otherwise EINVAL should be returned
+	 */
+	link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL);
+	err = -errno; /* close() can clobber errno */
+
+	if (link_fd >= 0)
+		close(link_fd);
+	close(prog_fd);
+
+	return link_fd < 0 && err == -EBADF;
+}
+
+static int probe_uprobe_multi_link(int token_fd)
+{
+	LIBBPF_OPTS(bpf_prog_load_opts, load_opts,
+		.expected_attach_type = BPF_TRACE_UPROBE_MULTI,
+		.token_fd = token_fd,
+		.prog_flags = token_fd ? BPF_F_TOKEN_FD : 0,
+	);
+	LIBBPF_OPTS(bpf_link_create_opts, link_opts);
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int prog_fd, link_fd, err;
+	unsigned long offset = 0;
+
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL",
+				insns, ARRAY_SIZE(insns), &load_opts);
+	if (prog_fd < 0)
+		return -errno;
+
+	/* Creating uprobe in '/' binary should fail with -EBADF. */
+	link_opts.uprobe_multi.path = "/";
+	link_opts.uprobe_multi.offsets = &offset;
+	link_opts.uprobe_multi.cnt = 1;
+
+	link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts);
+	err = -errno; /* close() can clobber errno */
+
+	if (link_fd >= 0)
+		close(link_fd);
+	close(prog_fd);
+
+	return link_fd < 0 && err == -EBADF;
+}
+
+static int probe_kern_bpf_cookie(int token_fd)
+{
+	struct bpf_insn insns[] = {
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie),
+		BPF_EXIT_INSN(),
+	};
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		.token_fd = token_fd,
+		.prog_flags = token_fd ? BPF_F_TOKEN_FD : 0,
+	);
+	int ret, insn_cnt = ARRAY_SIZE(insns);
+
+	ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts);
+	return probe_fd(ret);
+}
+
+static int probe_kern_btf_enum64(int token_fd)
+{
+	static const char strs[] = "\0enum64";
+	__u32 types[] = {
+		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs), token_fd));
+}
+
+static int probe_kern_arg_ctx_tag(int token_fd)
+{
+	static const char strs[] = "\0a\0b\0arg:ctx\0";
+	const __u32 types[] = {
+		/* [1] INT */
+		BTF_TYPE_INT_ENC(1 /* "a" */, BTF_INT_SIGNED, 0, 32, 4),
+		/* [2] PTR -> VOID */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 0),
+		/* [3] FUNC_PROTO `int(void *a)` */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 1),
+		BTF_PARAM_ENC(1 /* "a" */, 2),
+		/* [4] FUNC 'a' -> FUNC_PROTO (main prog) */
+		BTF_TYPE_ENC(1 /* "a" */, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 3),
+		/* [5] FUNC_PROTO `int(void *b __arg_ctx)` */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 1),
+		BTF_PARAM_ENC(3 /* "b" */, 2),
+		/* [6] FUNC 'b' -> FUNC_PROTO (subprog) */
+		BTF_TYPE_ENC(3 /* "b" */, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 5),
+		/* [7] DECL_TAG 'arg:ctx' -> func 'b' arg 'b' */
+		BTF_TYPE_DECL_TAG_ENC(5 /* "arg:ctx" */, 6, 0),
+	};
+	const struct bpf_insn insns[] = {
+		/* main prog */
+		BPF_CALL_REL(+1),
+		BPF_EXIT_INSN(),
+		/* global subprog */
+		BPF_EMIT_CALL(BPF_FUNC_get_func_ip), /* needs PTR_TO_CTX */
+		BPF_EXIT_INSN(),
+	};
+	const struct bpf_func_info_min func_infos[] = {
+		{ 0, 4 }, /* main prog -> FUNC 'a' */
+		{ 2, 6 }, /* subprog -> FUNC 'b' */
+	};
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		.token_fd = token_fd,
+		.prog_flags = token_fd ? BPF_F_TOKEN_FD : 0,
+	);
+	int prog_fd, btf_fd, insn_cnt = ARRAY_SIZE(insns);
+
+	btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs), token_fd);
+	if (btf_fd < 0)
+		return 0;
+
+	opts.prog_btf_fd = btf_fd;
+	opts.func_info = &func_infos;
+	opts.func_info_cnt = ARRAY_SIZE(func_infos);
+	opts.func_info_rec_size = sizeof(func_infos[0]);
+
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, "det_arg_ctx",
+				"GPL", insns, insn_cnt, &opts);
+	close(btf_fd);
+
+	return probe_fd(prog_fd);
+}
+
+typedef int (*feature_probe_fn)(int /* token_fd */);
+
+static struct kern_feature_cache feature_cache;
+
+static struct kern_feature_desc {
+	const char *desc;
+	feature_probe_fn probe;
+} feature_probes[__FEAT_CNT] = {
+	[FEAT_PROG_NAME] = {
+		"BPF program name", probe_kern_prog_name,
+	},
+	[FEAT_GLOBAL_DATA] = {
+		"global variables", probe_kern_global_data,
+	},
+	[FEAT_BTF] = {
+		"minimal BTF", probe_kern_btf,
+	},
+	[FEAT_BTF_FUNC] = {
+		"BTF functions", probe_kern_btf_func,
+	},
+	[FEAT_BTF_GLOBAL_FUNC] = {
+		"BTF global function", probe_kern_btf_func_global,
+	},
+	[FEAT_BTF_DATASEC] = {
+		"BTF data section and variable", probe_kern_btf_datasec,
+	},
+	[FEAT_ARRAY_MMAP] = {
+		"ARRAY map mmap()", probe_kern_array_mmap,
+	},
+	[FEAT_EXP_ATTACH_TYPE] = {
+		"BPF_PROG_LOAD expected_attach_type attribute",
+		probe_kern_exp_attach_type,
+	},
+	[FEAT_PROBE_READ_KERN] = {
+		"bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel,
+	},
+	[FEAT_PROG_BIND_MAP] = {
+		"BPF_PROG_BIND_MAP support", probe_prog_bind_map,
+	},
+	[FEAT_MODULE_BTF] = {
+		"module BTF support", probe_module_btf,
+	},
+	[FEAT_BTF_FLOAT] = {
+		"BTF_KIND_FLOAT support", probe_kern_btf_float,
+	},
+	[FEAT_PERF_LINK] = {
+		"BPF perf link support", probe_perf_link,
+	},
+	[FEAT_BTF_DECL_TAG] = {
+		"BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag,
+	},
+	[FEAT_BTF_TYPE_TAG] = {
+		"BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag,
+	},
+	[FEAT_MEMCG_ACCOUNT] = {
+		"memcg-based memory accounting", probe_memcg_account,
+	},
+	[FEAT_BPF_COOKIE] = {
+		"BPF cookie support", probe_kern_bpf_cookie,
+	},
+	[FEAT_BTF_ENUM64] = {
+		"BTF_KIND_ENUM64 support", probe_kern_btf_enum64,
+	},
+	[FEAT_SYSCALL_WRAPPER] = {
+		"Kernel using syscall wrapper", probe_kern_syscall_wrapper,
+	},
+	[FEAT_UPROBE_MULTI_LINK] = {
+		"BPF multi-uprobe link support", probe_uprobe_multi_link,
+	},
+	[FEAT_ARG_CTX_TAG] = {
+		"kernel-side __arg_ctx tag", probe_kern_arg_ctx_tag,
+	},
+	[FEAT_BTF_QMARK_DATASEC] = {
+		"BTF DATASEC names starting from '?'", probe_kern_btf_qmark_datasec,
+	},
+};
+
+bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id)
+{
+	struct kern_feature_desc *feat = &feature_probes[feat_id];
+	int ret;
+
+	/* assume global feature cache, unless custom one is provided */
+	if (!cache)
+		cache = &feature_cache;
+
+	if (READ_ONCE(cache->res[feat_id]) == FEAT_UNKNOWN) {
+		ret = feat->probe(cache->token_fd);
+		if (ret > 0) {
+			WRITE_ONCE(cache->res[feat_id], FEAT_SUPPORTED);
+		} else if (ret == 0) {
+			WRITE_ONCE(cache->res[feat_id], FEAT_MISSING);
+		} else {
+			pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret);
+			WRITE_ONCE(cache->res[feat_id], FEAT_MISSING);
+		}
+	}
+
+	return READ_ONCE(cache->res[feat_id]) == FEAT_SUPPORTED;
+}

src/gen_loader.c

@@ -18,7 +18,7 @@
 #define MAX_USED_MAPS	64
 #define MAX_USED_PROGS	32
 #define MAX_KFUNC_DESCS 256
-#define MAX_FD_ARRAY_SZ (MAX_USED_PROGS + MAX_KFUNC_DESCS)
+#define MAX_FD_ARRAY_SZ (MAX_USED_MAPS + MAX_KFUNC_DESCS)
 
 /* The following structure describes the stack layout of the loader program.
  * In addition R6 contains the pointer to context.
@@ -33,8 +33,8 @@
  */
 struct loader_stack {
 	__u32 btf_fd;
-	__u32 prog_fd[MAX_USED_PROGS];
 	__u32 inner_map_fd;
+	__u32 prog_fd[MAX_USED_PROGS];
 };
 
 #define stack_off(field) \
@@ -42,6 +42,11 @@ struct loader_stack {
 
 #define attr_field(attr, field) (attr + offsetof(union bpf_attr, field))
 
+static int blob_fd_array_off(struct bpf_gen *gen, int index)
+{
+	return gen->fd_array + index * sizeof(int);
+}
+
 static int realloc_insn_buf(struct bpf_gen *gen, __u32 size)
 {
 	size_t off = gen->insn_cur - gen->insn_start;
@@ -102,11 +107,15 @@ static void emit2(struct bpf_gen *gen, struct bpf_insn insn1, struct bpf_insn in
 	emit(gen, insn2);
 }
 
-void bpf_gen__init(struct bpf_gen *gen, int log_level)
+static int add_data(struct bpf_gen *gen, const void *data, __u32 size);
+static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off);
+
+void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps)
 {
-	size_t stack_sz = sizeof(struct loader_stack);
+	size_t stack_sz = sizeof(struct loader_stack), nr_progs_sz;
 	int i;
 
+	gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int));
 	gen->log_level = log_level;
 	/* save ctx pointer into R6 */
 	emit(gen, BPF_MOV64_REG(BPF_REG_6, BPF_REG_1));
@@ -118,19 +127,27 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level)
 	emit(gen, BPF_MOV64_IMM(BPF_REG_3, 0));
 	emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel));
 
+	/* amount of stack actually used, only used to calculate iterations, not stack offset */
+	nr_progs_sz = offsetof(struct loader_stack, prog_fd[nr_progs]);
 	/* jump over cleanup code */
 	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0,
-			      /* size of cleanup code below */
-			      (stack_sz / 4) * 3 + 2));
+			      /* size of cleanup code below (including map fd cleanup) */
+			      (nr_progs_sz / 4) * 3 + 2 +
+			      /* 6 insns for emit_sys_close_blob,
+			       * 6 insns for debug_regs in emit_sys_close_blob
+			       */
+			      nr_maps * (6 + (gen->log_level ? 6 : 0))));
 
 	/* remember the label where all error branches will jump to */
 	gen->cleanup_label = gen->insn_cur - gen->insn_start;
 	/* emit cleanup code: close all temp FDs */
-	for (i = 0; i < stack_sz; i += 4) {
+	for (i = 0; i < nr_progs_sz; i += 4) {
 		emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, -stack_sz + i));
 		emit(gen, BPF_JMP_IMM(BPF_JSLE, BPF_REG_1, 0, 1));
 		emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_close));
 	}
+	for (i = 0; i < nr_maps; i++)
+		emit_sys_close_blob(gen, blob_fd_array_off(gen, i));
 	/* R7 contains the error code from sys_bpf. Copy it into R0 and exit. */
 	emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_7));
 	emit(gen, BPF_EXIT_INSN());
@@ -160,8 +177,6 @@ static int add_data(struct bpf_gen *gen, const void *data, __u32 size)
  */
 static int add_map_fd(struct bpf_gen *gen)
 {
-	if (!gen->fd_array)
-		gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int));
 	if (gen->nr_maps == MAX_USED_MAPS) {
 		pr_warn("Total maps exceeds %d\n", MAX_USED_MAPS);
 		gen->error = -E2BIG;
@@ -174,8 +189,6 @@ static int add_kfunc_btf_fd(struct bpf_gen *gen)
 {
 	int cur;
 
-	if (!gen->fd_array)
-		gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int));
 	if (gen->nr_fd_array == MAX_KFUNC_DESCS) {
 		cur = add_data(gen, NULL, sizeof(int));
 		return (cur - gen->fd_array) / sizeof(int);
@@ -183,11 +196,6 @@ static int add_kfunc_btf_fd(struct bpf_gen *gen)
 	return MAX_USED_MAPS + gen->nr_fd_array++;
 }
 
-static int blob_fd_array_off(struct bpf_gen *gen, int index)
-{
-	return gen->fd_array + index * sizeof(int);
-}
-
 static int insn_bytes_to_bpf_size(__u32 sz)
 {
 	switch (sz) {
@@ -359,10 +367,16 @@ static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off)
 	__emit_sys_close(gen);
 }
 
-int bpf_gen__finish(struct bpf_gen *gen)
+int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps)
 {
 	int i;
 
+	if (nr_progs < gen->nr_progs || nr_maps != gen->nr_maps) {
+		pr_warn("nr_progs %d/%d nr_maps %d/%d mismatch\n",
+			nr_progs, gen->nr_progs, nr_maps, gen->nr_maps);
+		gen->error = -EFAULT;
+		return gen->error;
+	}
 	emit_sys_close_stack(gen, stack_off(btf_fd));
 	for (i = 0; i < gen->nr_progs; i++)
 		move_stack2ctx(gen,
@@ -432,47 +446,32 @@ void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data,
 }
 
 void bpf_gen__map_create(struct bpf_gen *gen,
-			 struct bpf_create_map_params *map_attr, int map_idx)
+			 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)
 {
-	int attr_size = offsetofend(union bpf_attr, btf_vmlinux_value_type_id);
+	int attr_size = offsetofend(union bpf_attr, map_extra);
 	bool close_inner_map_fd = false;
 	int map_create_attr, idx;
 	union bpf_attr attr;
 
 	memset(&attr, 0, attr_size);
-	attr.map_type = map_attr->map_type;
-	attr.key_size = map_attr->key_size;
-	attr.value_size = map_attr->value_size;
+	attr.map_type = map_type;
+	attr.key_size = key_size;
+	attr.value_size = value_size;
 	attr.map_flags = map_attr->map_flags;
 	attr.map_extra = map_attr->map_extra;
-	memcpy(attr.map_name, map_attr->name,
-	       min((unsigned)strlen(map_attr->name), BPF_OBJ_NAME_LEN - 1));
+	if (map_name)
+		libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name));
 	attr.numa_node = map_attr->numa_node;
 	attr.map_ifindex = map_attr->map_ifindex;
-	attr.max_entries = map_attr->max_entries;
-	switch (attr.map_type) {
-	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
-	case BPF_MAP_TYPE_CGROUP_ARRAY:
-	case BPF_MAP_TYPE_STACK_TRACE:
-	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_CPUMAP:
-	case BPF_MAP_TYPE_XSKMAP:
-	case BPF_MAP_TYPE_SOCKMAP:
-	case BPF_MAP_TYPE_SOCKHASH:
-	case BPF_MAP_TYPE_QUEUE:
-	case BPF_MAP_TYPE_STACK:
-	case BPF_MAP_TYPE_RINGBUF:
-		break;
-	default:
-		attr.btf_key_type_id = map_attr->btf_key_type_id;
-		attr.btf_value_type_id = map_attr->btf_value_type_id;
-	}
+	attr.max_entries = max_entries;
+	attr.btf_key_type_id = map_attr->btf_key_type_id;
+	attr.btf_value_type_id = map_attr->btf_value_type_id;
 
 	pr_debug("gen: map_create: %s idx %d type %d value_type_id %d\n",
-		 attr.map_name, map_idx, map_attr->map_type, attr.btf_value_type_id);
+		 attr.map_name, map_idx, map_type, attr.btf_value_type_id);
 
 	map_create_attr = add_data(gen, &attr, attr_size);
 	if (attr.btf_value_type_id)
@@ -499,7 +498,7 @@ void bpf_gen__map_create(struct bpf_gen *gen,
 	/* emit MAP_CREATE command */
 	emit_sys_bpf(gen, BPF_MAP_CREATE, map_create_attr, attr_size);
 	debug_ret(gen, "map_create %s idx %d type %d value_size %d value_btf_id %d",
-		  attr.map_name, map_idx, map_attr->map_type, attr.value_size,
+		  attr.map_name, map_idx, map_type, value_size,
 		  attr.btf_value_type_id);
 	emit_check_err(gen);
 	/* remember map_fd in the stack, if successful */
@@ -534,7 +533,7 @@ void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *attach_name,
 	gen->attach_kind = kind;
 	ret = snprintf(gen->attach_target, sizeof(gen->attach_target), "%s%s",
 		       prefix, attach_name);
-	if (ret == sizeof(gen->attach_target))
+	if (ret >= sizeof(gen->attach_target))
 		gen->error = -ENOSPC;
 }
 
@@ -561,7 +560,7 @@ static void emit_find_attach_target(struct bpf_gen *gen)
 }
 
 void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak,
-			    bool is_typeless, int kind, int insn_idx)
+			    bool is_typeless, bool is_ld64, int kind, int insn_idx)
 {
 	struct ksym_relo_desc *relo;
 
@@ -575,6 +574,7 @@ void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak,
 	relo->name = name;
 	relo->is_weak = is_weak;
 	relo->is_typeless = is_typeless;
+	relo->is_ld64 = is_ld64;
 	relo->kind = kind;
 	relo->insn_idx = insn_idx;
 	gen->relo_cnt++;
@@ -587,9 +587,11 @@ static struct ksym_desc *get_ksym_desc(struct bpf_gen *gen, struct ksym_relo_des
 	int i;
 
 	for (i = 0; i < gen->nr_ksyms; i++) {
-		if (!strcmp(gen->ksyms[i].name, relo->name)) {
-			gen->ksyms[i].ref++;
-			return &gen->ksyms[i];
+		kdesc = &gen->ksyms[i];
+		if (kdesc->kind == relo->kind && kdesc->is_ld64 == relo->is_ld64 &&
+		    !strcmp(kdesc->name, relo->name)) {
+			kdesc->ref++;
+			return kdesc;
 		}
 	}
 	kdesc = libbpf_reallocarray(gen->ksyms, gen->nr_ksyms + 1, sizeof(*kdesc));
@@ -604,6 +606,7 @@ static struct ksym_desc *get_ksym_desc(struct bpf_gen *gen, struct ksym_relo_des
 	kdesc->ref = 1;
 	kdesc->off = 0;
 	kdesc->insn = 0;
+	kdesc->is_ld64 = relo->is_ld64;
 	return kdesc;
 }
 
@@ -688,27 +691,29 @@ static void emit_relo_kfunc_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo
 		return;
 	}
 	kdesc->off = btf_fd_idx;
-	/* set a default value for imm */
+	/* jump to success case */
+	emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3));
+	/* set value for imm, off as 0 */
 	emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, offsetof(struct bpf_insn, imm), 0));
-	/* skip success case store if ret < 0 */
-	emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 1));
+	emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0));
+	/* skip success case for ret < 0 */
+	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 10));
 	/* store btf_id into insn[insn_idx].imm */
 	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, offsetof(struct bpf_insn, imm)));
+	/* obtain fd in BPF_REG_9 */
+	emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_7));
+	emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32));
 	/* load fd_array slot pointer */
 	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE,
 					 0, 0, 0, blob_fd_array_off(gen, btf_fd_idx)));
-	/* skip store of BTF fd if ret < 0 */
-	emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 3));
-	/* store BTF fd in slot */
-	emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_7));
-	emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32));
+	/* store BTF fd in slot, 0 for vmlinux */
 	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_9, 0));
-	/* set a default value for off */
+	/* jump to insn[insn_idx].off store if fd denotes module BTF */
+	emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 2));
+	/* set the default value for off */
 	emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0));
-	/* skip insn->off store if ret < 0 */
-	emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 2));
-	/* skip if vmlinux BTF */
-	emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_9, 0, 1));
+	/* skip BTF fd store for vmlinux BTF */
+	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 1));
 	/* store index into insn[insn_idx].off */
 	emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), btf_fd_idx));
 log:
@@ -803,13 +808,14 @@ static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo,
 		return;
 	/* try to copy from existing ldimm64 insn */
 	if (kdesc->ref > 1) {
-		move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4,
-			       kdesc->insn + offsetof(struct bpf_insn, imm));
 		move_blob2blob(gen, insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 4,
 			       kdesc->insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm));
-		emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_8, offsetof(struct bpf_insn, imm)));
-		/* jump over src_reg adjustment if imm is not 0 */
-		emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 3));
+		move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4,
+			       kdesc->insn + offsetof(struct bpf_insn, imm));
+		/* jump over src_reg adjustment if imm (btf_id) is not 0, reuse BPF_REG_0 from move_blob2blob
+		 * If btf_id is zero, clear BPF_PSEUDO_BTF_ID flag in src_reg of ld_imm64 insn
+		 */
+		emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3));
 		goto clear_src_reg;
 	}
 	/* remember insn offset, so we can copy BTF ID and FD later */
@@ -817,18 +823,21 @@ static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo,
 	emit_bpf_find_by_name_kind(gen, relo);
 	if (!relo->is_weak)
 		emit_check_err(gen);
-	/* set default values as 0 */
+	/* jump to success case */
+	emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3));
+	/* set values for insn[insn_idx].imm, insn[insn_idx + 1].imm as 0 */
 	emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, offsetof(struct bpf_insn, imm), 0));
 	emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 0));
-	/* skip success case stores if ret < 0 */
-	emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 4));
+	/* skip success case for ret < 0 */
+	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 4));
 	/* store btf_id into insn[insn_idx].imm */
 	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, offsetof(struct bpf_insn, imm)));
 	/* store btf_obj_fd into insn[insn_idx + 1].imm */
 	emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32));
 	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7,
 			      sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm)));
-	emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3));
+	/* skip src_reg adjustment */
+	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 3));
 clear_src_reg:
 	/* clear bpf_object__relocate_data's src_reg assignment, otherwise we get a verifier failure */
 	reg_mask = src_reg_mask();
@@ -839,27 +848,37 @@ clear_src_reg:
 	emit_ksym_relo_log(gen, relo, kdesc->ref);
 }
 
+void bpf_gen__record_relo_core(struct bpf_gen *gen,
+			       const struct bpf_core_relo *core_relo)
+{
+	struct bpf_core_relo *relos;
+
+	relos = libbpf_reallocarray(gen->core_relos, gen->core_relo_cnt + 1, sizeof(*relos));
+	if (!relos) {
+		gen->error = -ENOMEM;
+		return;
+	}
+	gen->core_relos = relos;
+	relos += gen->core_relo_cnt;
+	memcpy(relos, core_relo, sizeof(*relos));
+	gen->core_relo_cnt++;
+}
+
 static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insns)
 {
 	int insn;
 
-	pr_debug("gen: emit_relo (%d): %s at %d\n", relo->kind, relo->name, relo->insn_idx);
+	pr_debug("gen: emit_relo (%d): %s at %d %s\n",
+		 relo->kind, relo->name, relo->insn_idx, relo->is_ld64 ? "ld64" : "call");
 	insn = insns + sizeof(struct bpf_insn) * relo->insn_idx;
 	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_8, BPF_PSEUDO_MAP_IDX_VALUE, 0, 0, 0, insn));
-	switch (relo->kind) {
-	case BTF_KIND_VAR:
+	if (relo->is_ld64) {
 		if (relo->is_typeless)
 			emit_relo_ksym_typeless(gen, relo, insn);
 		else
 			emit_relo_ksym_btf(gen, relo, insn);
-		break;
-	case BTF_KIND_FUNC:
+	} else {
 		emit_relo_kfunc_btf(gen, relo, insn);
-		break;
-	default:
-		pr_warn("Unknown relocation kind '%d'\n", relo->kind);
-		gen->error = -EDOM;
-		return;
 	}
 }
 
@@ -871,20 +890,31 @@ static void emit_relos(struct bpf_gen *gen, int insns)
 		emit_relo(gen, gen->relos + i, insns);
 }
 
+static void cleanup_core_relo(struct bpf_gen *gen)
+{
+	if (!gen->core_relo_cnt)
+		return;
+	free(gen->core_relos);
+	gen->core_relo_cnt = 0;
+	gen->core_relos = NULL;
+}
+
 static void cleanup_relos(struct bpf_gen *gen, int insns)
 {
+	struct ksym_desc *kdesc;
 	int i, insn;
 
 	for (i = 0; i < gen->nr_ksyms; i++) {
+		kdesc = &gen->ksyms[i];
 		/* only close fds for typed ksyms and kfuncs */
-		if (gen->ksyms[i].kind == BTF_KIND_VAR && !gen->ksyms[i].typeless) {
+		if (kdesc->is_ld64 && !kdesc->typeless) {
 			/* close fd recorded in insn[insn_idx + 1].imm */
-			insn = gen->ksyms[i].insn;
+			insn = kdesc->insn;
 			insn += sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm);
 			emit_sys_close_blob(gen, insn);
-		} else if (gen->ksyms[i].kind == BTF_KIND_FUNC) {
-			emit_sys_close_blob(gen, blob_fd_array_off(gen, gen->ksyms[i].off));
-			if (gen->ksyms[i].off < MAX_FD_ARRAY_SZ)
+		} else if (!kdesc->is_ld64) {
+			emit_sys_close_blob(gen, blob_fd_array_off(gen, kdesc->off));
+			if (kdesc->off < MAX_FD_ARRAY_SZ)
 				gen->nr_fd_array--;
 		}
 	}
@@ -898,30 +928,32 @@ static void cleanup_relos(struct bpf_gen *gen, int insns)
 		gen->relo_cnt = 0;
 		gen->relos = NULL;
 	}
+	cleanup_core_relo(gen);
 }
 
 void bpf_gen__prog_load(struct bpf_gen *gen,
-			struct bpf_prog_load_params *load_attr, int prog_idx)
+			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)
 {
-	int attr_size = offsetofend(union bpf_attr, fd_array);
-	int prog_load_attr, license, insns, func_info, line_info;
+	int prog_load_attr, license_off, insns_off, func_info, line_info, core_relos;
+	int attr_size = offsetofend(union bpf_attr, core_relo_rec_size);
 	union bpf_attr attr;
 
 	memset(&attr, 0, attr_size);
-	pr_debug("gen: prog_load: type %d insns_cnt %zd\n",
-		 load_attr->prog_type, load_attr->insn_cnt);
+	pr_debug("gen: prog_load: type %d insns_cnt %zd progi_idx %d\n",
+		 prog_type, insn_cnt, prog_idx);
 	/* add license string to blob of bytes */
-	license = add_data(gen, load_attr->license, strlen(load_attr->license) + 1);
+	license_off = add_data(gen, license, strlen(license) + 1);
 	/* add insns to blob of bytes */
-	insns = add_data(gen, load_attr->insns,
-			 load_attr->insn_cnt * sizeof(struct bpf_insn));
+	insns_off = add_data(gen, insns, insn_cnt * sizeof(struct bpf_insn));
 
-	attr.prog_type = load_attr->prog_type;
+	attr.prog_type = prog_type;
 	attr.expected_attach_type = load_attr->expected_attach_type;
 	attr.attach_btf_id = load_attr->attach_btf_id;
 	attr.prog_ifindex = load_attr->prog_ifindex;
 	attr.kern_version = 0;
-	attr.insn_cnt = (__u32)load_attr->insn_cnt;
+	attr.insn_cnt = (__u32)insn_cnt;
 	attr.prog_flags = load_attr->prog_flags;
 
 	attr.func_info_rec_size = load_attr->func_info_rec_size;
@@ -934,15 +966,19 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
 	line_info = add_data(gen, load_attr->line_info,
 			     attr.line_info_cnt * attr.line_info_rec_size);
 
-	memcpy(attr.prog_name, load_attr->name,
-	       min((unsigned)strlen(load_attr->name), BPF_OBJ_NAME_LEN - 1));
+	attr.core_relo_rec_size = sizeof(struct bpf_core_relo);
+	attr.core_relo_cnt = gen->core_relo_cnt;
+	core_relos = add_data(gen, gen->core_relos,
+			     attr.core_relo_cnt * attr.core_relo_rec_size);
+
+	libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
 	prog_load_attr = add_data(gen, &attr, attr_size);
 
 	/* populate union bpf_attr with a pointer to license */
-	emit_rel_store(gen, attr_field(prog_load_attr, license), license);
+	emit_rel_store(gen, attr_field(prog_load_attr, license), license_off);
 
 	/* populate union bpf_attr with a pointer to instructions */
-	emit_rel_store(gen, attr_field(prog_load_attr, insns), insns);
+	emit_rel_store(gen, attr_field(prog_load_attr, insns), insns_off);
 
 	/* populate union bpf_attr with a pointer to func_info */
 	emit_rel_store(gen, attr_field(prog_load_attr, func_info), func_info);
@@ -950,6 +986,9 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
 	/* populate union bpf_attr with a pointer to line_info */
 	emit_rel_store(gen, attr_field(prog_load_attr, line_info), line_info);
 
+	/* populate union bpf_attr with a pointer to core_relos */
+	emit_rel_store(gen, attr_field(prog_load_attr, core_relos), core_relos);
+
 	/* populate union bpf_attr fd_array with a pointer to data where map_fds are saved */
 	emit_rel_store(gen, attr_field(prog_load_attr, fd_array), gen->fd_array);
 
@@ -974,15 +1013,17 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
 		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7,
 				      offsetof(union bpf_attr, attach_btf_obj_fd)));
 	}
-	emit_relos(gen, insns);
+	emit_relos(gen, insns_off);
 	/* emit PROG_LOAD command */
 	emit_sys_bpf(gen, BPF_PROG_LOAD, prog_load_attr, attr_size);
 	debug_ret(gen, "prog_load %s insn_cnt %d", attr.prog_name, attr.insn_cnt);
 	/* successful or not, close btf module FDs used in extern ksyms and attach_btf_obj_fd */
-	cleanup_relos(gen, insns);
-	if (gen->attach_kind)
+	cleanup_relos(gen, insns_off);
+	if (gen->attach_kind) {
 		emit_sys_close_blob(gen,
 				    attr_field(prog_load_attr, attach_btf_obj_fd));
+		gen->attach_kind = 0;
+	}
 	emit_check_err(gen);
 	/* remember prog_fd in the stack, if successful */
 	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7,
@@ -1004,18 +1045,27 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue,
 	value = add_data(gen, pvalue, value_size);
 	key = add_data(gen, &zero, sizeof(zero));
 
-	/* if (map_desc[map_idx].initial_value)
-	 *    copy_from_user(value, initial_value, value_size);
+	/* if (map_desc[map_idx].initial_value) {
+	 *    if (ctx->flags & BPF_SKEL_KERNEL)
+	 *        bpf_probe_read_kernel(value, value_size, initial_value);
+	 *    else
+	 *        bpf_copy_from_user(value, value_size, initial_value);
+	 * }
 	 */
 	emit(gen, BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_6,
 			      sizeof(struct bpf_loader_ctx) +
 			      sizeof(struct bpf_map_desc) * map_idx +
 			      offsetof(struct bpf_map_desc, initial_value)));
-	emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0, 4));
+	emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0, 8));
 	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
 					 0, 0, 0, value));
 	emit(gen, BPF_MOV64_IMM(BPF_REG_2, value_size));
+	emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6,
+			      offsetof(struct bpf_loader_ctx, flags)));
+	emit(gen, BPF_JMP_IMM(BPF_JSET, BPF_REG_0, BPF_SKEL_KERNEL, 2));
 	emit(gen, BPF_EMIT_CALL(BPF_FUNC_copy_from_user));
+	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 1));
+	emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel));
 
 	map_update_attr = add_data(gen, &attr, attr_size);
 	move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4,
@@ -1028,6 +1078,33 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue,
 	emit_check_err(gen);
 }
 
+void bpf_gen__populate_outer_map(struct bpf_gen *gen, int outer_map_idx, int slot,
+				 int inner_map_idx)
+{
+	int attr_size = offsetofend(union bpf_attr, flags);
+	int map_update_attr, key;
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_size);
+	pr_debug("gen: populate_outer_map: outer %d key %d inner %d\n",
+		 outer_map_idx, slot, inner_map_idx);
+
+	key = add_data(gen, &slot, sizeof(slot));
+
+	map_update_attr = add_data(gen, &attr, attr_size);
+	move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4,
+		       blob_fd_array_off(gen, outer_map_idx));
+	emit_rel_store(gen, attr_field(map_update_attr, key), key);
+	emit_rel_store(gen, attr_field(map_update_attr, value),
+		       blob_fd_array_off(gen, inner_map_idx));
+
+	/* emit MAP_UPDATE_ELEM command */
+	emit_sys_bpf(gen, BPF_MAP_UPDATE_ELEM, map_update_attr, attr_size);
+	debug_ret(gen, "populate_outer_map outer %d key %d inner %d",
+		  outer_map_idx, slot, inner_map_idx);
+	emit_check_err(gen);
+}
+
 void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx)
 {
 	int attr_size = offsetofend(union bpf_attr, map_fd);

src/hashmap.c

@@ -75,7 +75,7 @@ void hashmap__clear(struct hashmap *map)
 
 void hashmap__free(struct hashmap *map)
 {
-	if (!map)
+	if (IS_ERR_OR_NULL(map))
 		return;
 
 	hashmap__clear(map);
@@ -128,7 +128,7 @@ static int hashmap_grow(struct hashmap *map)
 }
 
 static bool hashmap_find_entry(const struct hashmap *map,
-			       const void *key, size_t hash,
+			       const long key, size_t hash,
 			       struct hashmap_entry ***pprev,
 			       struct hashmap_entry **entry)
 {
@@ -151,18 +151,18 @@ static bool hashmap_find_entry(const struct hashmap *map,
 	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)
+int hashmap_insert(struct hashmap *map, long key, long value,
+		   enum hashmap_insert_strategy strategy,
+		   long *old_key, long *old_value)
 {
 	struct hashmap_entry *entry;
 	size_t h;
 	int err;
 
 	if (old_key)
-		*old_key = NULL;
+		*old_key = 0;
 	if (old_value)
-		*old_value = NULL;
+		*old_value = 0;
 
 	h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits);
 	if (strategy != HASHMAP_APPEND &&
@@ -203,7 +203,7 @@ int hashmap__insert(struct hashmap *map, const void *key, void *value,
 	return 0;
 }
 
-bool hashmap__find(const struct hashmap *map, const void *key, void **value)
+bool hashmap_find(const struct hashmap *map, long key, long *value)
 {
 	struct hashmap_entry *entry;
 	size_t h;
@@ -217,8 +217,8 @@ bool hashmap__find(const struct hashmap *map, const void *key, void **value)
 	return true;
 }
 
-bool hashmap__delete(struct hashmap *map, const void *key,
-		     const void **old_key, void **old_value)
+bool hashmap_delete(struct hashmap *map, long key,
+		    long *old_key, long *old_value)
 {
 	struct hashmap_entry **pprev, *entry;
 	size_t h;
@@ -238,4 +238,3 @@ bool hashmap__delete(struct hashmap *map, const void *key,
 
 	return true;
 }
-

src/hashmap.h

@@ -40,12 +40,32 @@ static inline size_t str_hash(const char *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);
+typedef size_t (*hashmap_hash_fn)(long key, void *ctx);
+typedef bool (*hashmap_equal_fn)(long key1, long key2, void *ctx);
 
+/*
+ * Hashmap interface is polymorphic, keys and values could be either
+ * long-sized integers or pointers, this is achieved as follows:
+ * - interface functions that operate on keys and values are hidden
+ *   behind auxiliary macros, e.g. hashmap_insert <-> hashmap__insert;
+ * - these auxiliary macros cast the key and value parameters as
+ *   long or long *, so the user does not have to specify the casts explicitly;
+ * - for pointer parameters (e.g. old_key) the size of the pointed
+ *   type is verified by hashmap_cast_ptr using _Static_assert;
+ * - when iterating using hashmap__for_each_* forms
+ *   hasmap_entry->key should be used for integer keys and
+ *   hasmap_entry->pkey should be used for pointer keys,
+ *   same goes for values.
+ */
 struct hashmap_entry {
-	const void *key;
-	void *value;
+	union {
+		long key;
+		const void *pkey;
+	};
+	union {
+		long value;
+		void *pvalue;
+	};
 	struct hashmap_entry *next;
 };
 
@@ -60,16 +80,6 @@ struct hashmap {
 	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,
@@ -102,6 +112,13 @@ enum hashmap_insert_strategy {
 	HASHMAP_APPEND,
 };
 
+#define hashmap_cast_ptr(p) ({								\
+	_Static_assert((__builtin_constant_p((p)) ? (p) == NULL : 0) ||			\
+				sizeof(*(p)) == sizeof(long),				\
+		       #p " pointee should be a long-sized integer or a pointer");	\
+	(long *)(p);									\
+})
+
 /*
  * hashmap__insert() adds key/value entry w/ various semantics, depending on
  * provided strategy value. If a given key/value pair replaced already
@@ -109,42 +126,38 @@ enum hashmap_insert_strategy {
  * 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);
+int hashmap_insert(struct hashmap *map, long key, long value,
+		   enum hashmap_insert_strategy strategy,
+		   long *old_key, long *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);
-}
+#define hashmap__insert(map, key, value, strategy, old_key, old_value) \
+	hashmap_insert((map), (long)(key), (long)(value), (strategy),  \
+		       hashmap_cast_ptr(old_key),		       \
+		       hashmap_cast_ptr(old_value))
 
-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);
-}
+#define hashmap__add(map, key, value) \
+	hashmap__insert((map), (key), (value), HASHMAP_ADD, NULL, NULL)
 
-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);
-}
+#define hashmap__set(map, key, value, old_key, old_value) \
+	hashmap__insert((map), (key), (value), HASHMAP_SET, (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);
-}
+#define hashmap__update(map, key, value, old_key, old_value) \
+	hashmap__insert((map), (key), (value), HASHMAP_UPDATE, (old_key), (old_value))
 
-bool hashmap__delete(struct hashmap *map, const void *key,
-		     const void **old_key, void **old_value);
+#define hashmap__append(map, key, value) \
+	hashmap__insert((map), (key), (value), HASHMAP_APPEND, NULL, NULL)
 
-bool hashmap__find(const struct hashmap *map, const void *key, void **value);
+bool hashmap_delete(struct hashmap *map, long key, long *old_key, long *old_value);
+
+#define hashmap__delete(map, key, old_key, old_value)		       \
+	hashmap_delete((map), (long)(key),			       \
+		       hashmap_cast_ptr(old_key),		       \
+		       hashmap_cast_ptr(old_value))
+
+bool hashmap_find(const struct hashmap *map, long key, long *value);
+
+#define hashmap__find(map, key, value) \
+	hashmap_find((map), (long)(key), hashmap_cast_ptr(value))
 
 /*
  * hashmap__for_each_entry - iterate over all entries in hashmap

src/libbpf.map

@@ -1,29 +1,14 @@
 LIBBPF_0.0.1 {
 	global:
 		bpf_btf_get_fd_by_id;
-		bpf_create_map;
-		bpf_create_map_in_map;
-		bpf_create_map_in_map_node;
-		bpf_create_map_name;
-		bpf_create_map_node;
-		bpf_create_map_xattr;
-		bpf_load_btf;
-		bpf_load_program;
-		bpf_load_program_xattr;
 		bpf_map__btf_key_type_id;
 		bpf_map__btf_value_type_id;
-		bpf_map__def;
 		bpf_map__fd;
-		bpf_map__is_offload_neutral;
 		bpf_map__name;
-		bpf_map__next;
 		bpf_map__pin;
-		bpf_map__prev;
-		bpf_map__priv;
 		bpf_map__reuse_fd;
 		bpf_map__set_ifindex;
 		bpf_map__set_inner_map_fd;
-		bpf_map__set_priv;
 		bpf_map__unpin;
 		bpf_map_delete_elem;
 		bpf_map_get_fd_by_id;
@@ -38,79 +23,37 @@ LIBBPF_0.0.1 {
 		bpf_object__btf_fd;
 		bpf_object__close;
 		bpf_object__find_map_by_name;
-		bpf_object__find_map_by_offset;
-		bpf_object__find_program_by_title;
 		bpf_object__kversion;
 		bpf_object__load;
 		bpf_object__name;
-		bpf_object__next;
 		bpf_object__open;
-		bpf_object__open_buffer;
-		bpf_object__open_xattr;
 		bpf_object__pin;
 		bpf_object__pin_maps;
 		bpf_object__pin_programs;
-		bpf_object__priv;
-		bpf_object__set_priv;
-		bpf_object__unload;
 		bpf_object__unpin_maps;
 		bpf_object__unpin_programs;
-		bpf_perf_event_read_simple;
 		bpf_prog_attach;
 		bpf_prog_detach;
 		bpf_prog_detach2;
 		bpf_prog_get_fd_by_id;
 		bpf_prog_get_next_id;
-		bpf_prog_load;
-		bpf_prog_load_xattr;
 		bpf_prog_query;
-		bpf_prog_test_run;
-		bpf_prog_test_run_xattr;
 		bpf_program__fd;
-		bpf_program__is_kprobe;
-		bpf_program__is_perf_event;
-		bpf_program__is_raw_tracepoint;
-		bpf_program__is_sched_act;
-		bpf_program__is_sched_cls;
-		bpf_program__is_socket_filter;
-		bpf_program__is_tracepoint;
-		bpf_program__is_xdp;
-		bpf_program__load;
-		bpf_program__next;
-		bpf_program__nth_fd;
 		bpf_program__pin;
-		bpf_program__pin_instance;
-		bpf_program__prev;
-		bpf_program__priv;
 		bpf_program__set_expected_attach_type;
 		bpf_program__set_ifindex;
-		bpf_program__set_kprobe;
-		bpf_program__set_perf_event;
-		bpf_program__set_prep;
-		bpf_program__set_priv;
-		bpf_program__set_raw_tracepoint;
-		bpf_program__set_sched_act;
-		bpf_program__set_sched_cls;
-		bpf_program__set_socket_filter;
-		bpf_program__set_tracepoint;
 		bpf_program__set_type;
-		bpf_program__set_xdp;
-		bpf_program__title;
 		bpf_program__unload;
 		bpf_program__unpin;
-		bpf_program__unpin_instance;
 		bpf_prog_linfo__free;
 		bpf_prog_linfo__new;
 		bpf_prog_linfo__lfind_addr_func;
 		bpf_prog_linfo__lfind;
 		bpf_raw_tracepoint_open;
-		bpf_set_link_xdp_fd;
 		bpf_task_fd_query;
-		bpf_verify_program;
 		btf__fd;
 		btf__find_by_name;
 		btf__free;
-		btf__get_from_id;
 		btf__name_by_offset;
 		btf__new;
 		btf__resolve_size;
@@ -127,48 +70,24 @@ LIBBPF_0.0.1 {
 
 LIBBPF_0.0.2 {
 	global:
-		bpf_probe_helper;
-		bpf_probe_map_type;
-		bpf_probe_prog_type;
-		bpf_map__resize;
 		bpf_map_lookup_elem_flags;
 		bpf_object__btf;
 		bpf_object__find_map_fd_by_name;
-		bpf_get_link_xdp_id;
-		btf__dedup;
-		btf__get_map_kv_tids;
-		btf__get_nr_types;
 		btf__get_raw_data;
-		btf__load;
 		btf_ext__free;
-		btf_ext__func_info_rec_size;
 		btf_ext__get_raw_data;
-		btf_ext__line_info_rec_size;
 		btf_ext__new;
-		btf_ext__reloc_func_info;
-		btf_ext__reloc_line_info;
-		xsk_umem__create;
-		xsk_socket__create;
-		xsk_umem__delete;
-		xsk_socket__delete;
-		xsk_umem__fd;
-		xsk_socket__fd;
-		bpf_program__get_prog_info_linear;
-		bpf_program__bpil_addr_to_offs;
-		bpf_program__bpil_offs_to_addr;
 } LIBBPF_0.0.1;
 
 LIBBPF_0.0.3 {
 	global:
 		bpf_map__is_internal;
 		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;
@@ -176,14 +95,10 @@ LIBBPF_0.0.4 {
 		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 {
@@ -193,7 +108,6 @@ LIBBPF_0.0.5 {
 
 LIBBPF_0.0.6 {
 	global:
-		bpf_get_link_xdp_info;
 		bpf_map__get_pin_path;
 		bpf_map__is_pinned;
 		bpf_map__set_pin_path;
@@ -202,9 +116,6 @@ LIBBPF_0.0.6 {
 		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;
@@ -224,14 +135,8 @@ LIBBPF_0.0.7 {
 		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;
@@ -247,12 +152,10 @@ LIBBPF_0.0.8 {
 		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 {
@@ -290,9 +193,7 @@ LIBBPF_0.1.0 {
 		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;
@@ -335,7 +236,6 @@ LIBBPF_0.2.0 {
 		perf_buffer__buffer_fd;
 		perf_buffer__epoll_fd;
 		perf_buffer__consume_buffer;
-		xsk_socket__create_shared;
 } LIBBPF_0.1.0;
 
 LIBBPF_0.3.0 {
@@ -345,10 +245,7 @@ LIBBPF_0.3.0 {
 		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 {
@@ -391,14 +288,138 @@ 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;
+		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__raw_data;
 		btf__type_cnt;
+		btf_dump__new;
+		libbpf_major_version;
+		libbpf_minor_version;
+		libbpf_version_string;
+		perf_buffer__new;
+		perf_buffer__new_raw;
 } 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;
+} LIBBPF_0.6.0;
+
+LIBBPF_0.8.0 {
+	global:
+		bpf_map__autocreate;
+		bpf_map__get_next_key;
+		bpf_map__delete_elem;
+		bpf_map__lookup_and_delete_elem;
+		bpf_map__lookup_elem;
+		bpf_map__set_autocreate;
+		bpf_map__update_elem;
+		bpf_map_delete_elem_flags;
+		bpf_object__destroy_subskeleton;
+		bpf_object__open_subskeleton;
+		bpf_program__attach_kprobe_multi_opts;
+		bpf_program__attach_trace_opts;
+		bpf_program__attach_usdt;
+		bpf_program__set_insns;
+		libbpf_register_prog_handler;
+		libbpf_unregister_prog_handler;
+} LIBBPF_0.7.0;
+
+LIBBPF_1.0.0 {
+	global:
+		bpf_obj_get_opts;
+		bpf_prog_query_opts;
+		bpf_program__attach_ksyscall;
+		bpf_program__autoattach;
+		bpf_program__set_autoattach;
+		btf__add_enum64;
+		btf__add_enum64_value;
+		libbpf_bpf_attach_type_str;
+		libbpf_bpf_link_type_str;
+		libbpf_bpf_map_type_str;
+		libbpf_bpf_prog_type_str;
+		perf_buffer__buffer;
+} LIBBPF_0.8.0;
+
+LIBBPF_1.1.0 {
+	global:
+		bpf_btf_get_fd_by_id_opts;
+		bpf_link_get_fd_by_id_opts;
+		bpf_map_get_fd_by_id_opts;
+		bpf_prog_get_fd_by_id_opts;
+		user_ring_buffer__discard;
+		user_ring_buffer__free;
+		user_ring_buffer__new;
+		user_ring_buffer__reserve;
+		user_ring_buffer__reserve_blocking;
+		user_ring_buffer__submit;
+} LIBBPF_1.0.0;
+
+LIBBPF_1.2.0 {
+	global:
+		bpf_btf_get_info_by_fd;
+		bpf_link__update_map;
+		bpf_link_get_info_by_fd;
+		bpf_map_get_info_by_fd;
+		bpf_prog_get_info_by_fd;
+} LIBBPF_1.1.0;
+
+LIBBPF_1.3.0 {
+	global:
+		bpf_obj_pin_opts;
+		bpf_object__unpin;
+		bpf_prog_detach_opts;
+		bpf_program__attach_netfilter;
+		bpf_program__attach_netkit;
+		bpf_program__attach_tcx;
+		bpf_program__attach_uprobe_multi;
+		ring__avail_data_size;
+		ring__consume;
+		ring__consumer_pos;
+		ring__map_fd;
+		ring__producer_pos;
+		ring__size;
+		ring_buffer__ring;
+} LIBBPF_1.2.0;
+
+LIBBPF_1.4.0 {
+	global:
+		bpf_program__attach_raw_tracepoint_opts;
+		bpf_raw_tracepoint_open_opts;
+		bpf_token_create;
+		btf__new_split;
+		btf_ext__raw_data;
+} LIBBPF_1.3.0;
+
+LIBBPF_1.5.0 {
+	global:
+		bpf_program__attach_sockmap;
+		ring__consume_n;
+		ring_buffer__consume_n;
+} LIBBPF_1.4.0;

src/libbpf_common.h

@@ -30,17 +30,24 @@
 /* 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
+#if __LIBBPF_CURRENT_VERSION_GEQ(1, 0)
+#define __LIBBPF_MARK_DEPRECATED_1_0(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)
+#define __LIBBPF_MARK_DEPRECATED_1_0(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,
@@ -54,7 +61,7 @@
  * including any extra padding, it with memset() and then assigns initial
  * values provided by users in struct initializer-syntax as varargs.
  */
-#define DECLARE_LIBBPF_OPTS(TYPE, NAME, ...)				    \
+#define LIBBPF_OPTS(TYPE, NAME, ...)					    \
 	struct TYPE NAME = ({ 						    \
 		memset(&NAME, 0, sizeof(struct TYPE));			    \
 		(struct TYPE) {						    \
@@ -63,4 +70,23 @@
 		};							    \
 	})
 
+/* Helper macro to clear and optionally reinitialize libbpf options struct
+ *
+ * Small helper macro to reset all fields and to reinitialize the common
+ * structure size member. Values provided by users in struct initializer-
+ * syntax as varargs can be provided as well to reinitialize options struct
+ * specific members.
+ */
+#define LIBBPF_OPTS_RESET(NAME, ...)					    \
+	do {								    \
+		typeof(NAME) ___##NAME = ({ 				    \
+			memset(&___##NAME, 0, sizeof(NAME));		    \
+			(typeof(NAME)) {				    \
+				.sz = sizeof(NAME),			    \
+				__VA_ARGS__				    \
+			};						    \
+		});							    \
+		memcpy(&NAME, &___##NAME, sizeof(NAME));		    \
+	} while (0)
+
 #endif /* __LIBBPF_LIBBPF_COMMON_H */

src/libbpf_errno.c

@@ -39,14 +39,14 @@ static const char *libbpf_strerror_table[NR_ERRNO] = {
 
 int libbpf_strerror(int err, char *buf, size_t size)
 {
+	int ret;
+
 	if (!buf || !size)
 		return libbpf_err(-EINVAL);
 
 	err = err > 0 ? err : -err;
 
 	if (err < __LIBBPF_ERRNO__START) {
-		int ret;
-
 		ret = strerror_r(err, buf, size);
 		buf[size - 1] = '\0';
 		return libbpf_err_errno(ret);
@@ -56,12 +56,20 @@ int libbpf_strerror(int err, char *buf, size_t size)
 		const char *msg;
 
 		msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
-		snprintf(buf, size, "%s", msg);
+		ret = snprintf(buf, size, "%s", msg);
 		buf[size - 1] = '\0';
+		/* The length of the buf and msg is positive.
+		 * A negative number may be returned only when the
+		 * size exceeds INT_MAX. Not likely to appear.
+		 */
+		if (ret >= size)
+			return libbpf_err(-ERANGE);
 		return 0;
 	}
 
-	snprintf(buf, size, "Unknown libbpf error %d", err);
+	ret = snprintf(buf, size, "Unknown libbpf error %d", err);
 	buf[size - 1] = '\0';
+	if (ret >= size)
+		return libbpf_err(-ERANGE);
 	return libbpf_err(-ENOENT);
 }

src/libbpf_internal.h

@@ -15,9 +15,24 @@
 #include <linux/err.h>
 #include <fcntl.h>
 #include <unistd.h>
-#include "libbpf_legacy.h"
+#include <sys/syscall.h>
+#include <libelf.h>
 #include "relo_core.h"
 
+/* Android's libc doesn't support AT_EACCESS in faccessat() implementation
+ * ([0]), and just returns -EINVAL even if file exists and is accessible.
+ * See [1] for issues caused by this.
+ *
+ * So just redefine it to 0 on Android.
+ *
+ * [0] https://android.googlesource.com/platform/bionic/+/refs/heads/android13-release/libc/bionic/faccessat.cpp#50
+ * [1] https://github.com/libbpf/libbpf-bootstrap/issues/250#issuecomment-1911324250
+ */
+#ifdef __ANDROID__
+#undef AT_EACCESS
+#define AT_EACCESS 0
+#endif
+
 /* make sure libbpf doesn't use kernel-only integer typedefs */
 #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
 
@@ -73,6 +88,8 @@
 	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)
@@ -90,6 +107,9 @@
 # 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
@@ -98,6 +118,17 @@
 #define str_has_pfx(str, pfx) \
 	(strncmp(str, pfx, __builtin_constant_p(pfx) ? sizeof(pfx) - 1 : strlen(pfx)) == 0)
 
+/* suffix check */
+static inline bool str_has_sfx(const char *str, const char *sfx)
+{
+	size_t str_len = strlen(str);
+	size_t sfx_len = strlen(sfx);
+
+	if (sfx_len > str_len)
+		return false;
+	return strcmp(str + str_len - sfx_len, sfx) == 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.
@@ -143,6 +174,15 @@ do {				\
 #ifndef __has_builtin
 #define __has_builtin(x) 0
 #endif
+
+struct bpf_link {
+	int (*detach)(struct bpf_link *link);
+	void (*dealloc)(struct bpf_link *link);
+	char *pin_path;		/* NULL, if not pinned */
+	int fd;			/* hook FD, -1 if not applicable */
+	bool disconnected;
+};
+
 /*
  * Re-implement glibc's reallocarray() for libbpf internal-only use.
  * reallocarray(), unfortunately, is not available in all versions of glibc,
@@ -167,10 +207,31 @@ static inline void *libbpf_reallocarray(void *ptr, size_t nmemb, size_t size)
 	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(struct btf *btf, __u32 type_id);
+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);
 
@@ -270,63 +331,80 @@ static inline bool libbpf_validate_opts(const char *opts,
 					(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,
+	/* BPF cookie (bpf_get_attach_cookie() BPF helper) support */
+	FEAT_BPF_COOKIE,
+	/* BTF_KIND_ENUM64 support and BTF_KIND_ENUM kflag support */
+	FEAT_BTF_ENUM64,
+	/* Kernel uses syscall wrapper (CONFIG_ARCH_HAS_SYSCALL_WRAPPER) */
+	FEAT_SYSCALL_WRAPPER,
+	/* BPF multi-uprobe link support */
+	FEAT_UPROBE_MULTI_LINK,
+	/* Kernel supports arg:ctx tag (__arg_ctx) for global subprogs natively */
+	FEAT_ARG_CTX_TAG,
+	/* Kernel supports '?' at the front of datasec names */
+	FEAT_BTF_QMARK_DATASEC,
+	__FEAT_CNT,
+};
+
+enum kern_feature_result {
+	FEAT_UNKNOWN = 0,
+	FEAT_SUPPORTED = 1,
+	FEAT_MISSING = 2,
+};
+
+struct kern_feature_cache {
+	enum kern_feature_result res[__FEAT_CNT];
+	int token_fd;
+};
+
+bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id);
+bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id);
+
+int probe_kern_syscall_wrapper(int token_fd);
+int probe_memcg_account(int token_fd);
+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);
-
-struct bpf_prog_load_params {
-	enum bpf_prog_type prog_type;
-	enum bpf_attach_type expected_attach_type;
-	const char *name;
-	const struct bpf_insn *insns;
-	size_t insn_cnt;
-	const char *license;
-	__u32 kern_version;
-	__u32 attach_prog_fd;
-	__u32 attach_btf_obj_fd;
-	__u32 attach_btf_id;
-	__u32 prog_ifindex;
-	__u32 prog_btf_fd;
-	__u32 prog_flags;
-
-	__u32 func_info_rec_size;
-	const void *func_info;
-	__u32 func_info_cnt;
-
-	__u32 line_info_rec_size;
-	const void *line_info;
-	__u32 line_info_cnt;
-
-	__u32 log_level;
-	char *log_buf;
-	size_t log_buf_sz;
-	int *fd_array;
-};
-
-int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr);
-
-struct bpf_create_map_params {
-	const char *name;
-	enum bpf_map_type map_type;
-	__u32 map_flags;
-	__u32 key_size;
-	__u32 value_size;
-	__u32 max_entries;
-	__u32 numa_node;
-	__u32 btf_fd;
-	__u32 btf_key_type_id;
-	__u32 btf_value_type_id;
-	__u32 map_ifindex;
-	union {
-		__u32 inner_map_fd;
-		__u32 btf_vmlinux_value_type_id;
-	};
-	__u64 map_extra;
-};
-
-int libbpf__bpf_create_map_xattr(const struct bpf_create_map_params *create_attr);
+			 const char *str_sec, size_t str_len,
+			 int token_fd);
+int btf_load_into_kernel(struct btf *btf,
+			 char *log_buf, size_t log_sz, __u32 log_level,
+			 int token_fd);
 
 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,
@@ -340,6 +418,13 @@ struct btf_ext_info {
 	void *info;
 	__u32 rec_size;
 	__u32 len;
+	/* optional (maintained internally by libbpf) mapping between .BTF.ext
+	 * section and corresponding ELF section. This is used to join
+	 * information like CO-RE relocation records with corresponding BPF
+	 * programs defined in ELF sections
+	 */
+	__u32 *sec_idxs;
+	int sec_cnt;
 };
 
 #define for_each_btf_ext_sec(seg, sec)					\
@@ -433,8 +518,6 @@ int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void
 __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)
 {
@@ -448,12 +531,8 @@ static inline int libbpf_err(int ret)
  */
 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;
+	/* errno is already assumed to be set on error */
+	return ret < 0 ? -errno : ret;
 }
 
 /* handle error for pointer-returning APIs, err is assumed to be < 0 always */
@@ -461,12 +540,7 @@ 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);
+	return NULL;
 }
 
 /* handle pointer-returning APIs' error handling */
@@ -476,11 +550,7 @@ static inline void *libbpf_ptr(void *ret)
 	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;
+	return IS_ERR(ret) ? NULL : ret;
 }
 
 static inline bool str_is_empty(const char *s)
@@ -493,6 +563,17 @@ static inline bool is_ldimm64_insn(struct bpf_insn *insn)
 	return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
 }
 
+/* Unconditionally dup FD, ensuring it doesn't use [0, 2] range.
+ * Original FD is not closed or altered in any other way.
+ * Preserves original FD value, if it's invalid (negative).
+ */
+static inline int dup_good_fd(int fd)
+{
+	if (fd < 0)
+		return fd;
+	return fcntl(fd, F_DUPFD_CLOEXEC, 3);
+}
+
 /* 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).
@@ -504,9 +585,10 @@ static inline int ensure_good_fd(int fd)
 	if (fd < 0)
 		return fd;
 	if (fd < 3) {
-		fd = fcntl(fd, F_DUPFD_CLOEXEC, 3);
+		fd = dup_good_fd(fd);
 		saved_errno = errno;
 		close(old_fd);
+		errno = saved_errno;
 		if (fd < 0) {
 			pr_warn("failed to dup FD %d to FD > 2: %d\n", old_fd, -saved_errno);
 			errno = saved_errno;
@@ -515,4 +597,73 @@ static inline int ensure_good_fd(int fd)
 	return fd;
 }
 
+static inline int sys_dup2(int oldfd, int newfd)
+{
+#ifdef __NR_dup2
+	return syscall(__NR_dup2, oldfd, newfd);
+#else
+	return syscall(__NR_dup3, oldfd, newfd, 0);
+#endif
+}
+
+/* Point *fixed_fd* to the same file that *tmp_fd* points to.
+ * Regardless of success, *tmp_fd* is closed.
+ * Whatever *fixed_fd* pointed to is closed silently.
+ */
+static inline int reuse_fd(int fixed_fd, int tmp_fd)
+{
+	int err;
+
+	err = sys_dup2(tmp_fd, fixed_fd);
+	err = err < 0 ? -errno : 0;
+	close(tmp_fd); /* clean up temporary FD */
+	return err;
+}
+
+/* The following two functions are exposed to bpftool */
+int bpf_core_add_cands(struct bpf_core_cand *local_cand,
+		       size_t local_essent_len,
+		       const struct btf *targ_btf,
+		       const char *targ_btf_name,
+		       int targ_start_id,
+		       struct bpf_core_cand_list *cands);
+void bpf_core_free_cands(struct bpf_core_cand_list *cands);
+
+struct usdt_manager *usdt_manager_new(struct bpf_object *obj);
+void usdt_manager_free(struct usdt_manager *man);
+struct bpf_link * usdt_manager_attach_usdt(struct usdt_manager *man,
+					   const struct bpf_program *prog,
+					   pid_t pid, const char *path,
+					   const char *usdt_provider, const char *usdt_name,
+					   __u64 usdt_cookie);
+
+static inline bool is_pow_of_2(size_t x)
+{
+	return x && (x & (x - 1)) == 0;
+}
+
+#define PROG_LOAD_ATTEMPTS 5
+int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts);
+
+bool glob_match(const char *str, const char *pat);
+
+long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name);
+long elf_find_func_offset_from_file(const char *binary_path, const char *name);
+
+struct elf_fd {
+	Elf *elf;
+	int fd;
+};
+
+int elf_open(const char *binary_path, struct elf_fd *elf_fd);
+void elf_close(struct elf_fd *elf_fd);
+
+int elf_resolve_syms_offsets(const char *binary_path, int cnt,
+			     const char **syms, unsigned long **poffsets,
+			     int st_type);
+int elf_resolve_pattern_offsets(const char *binary_path, const char *pattern,
+				 unsigned long **poffsets, size_t *pcnt);
+
+int probe_fd(int fd);
+
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */

src/libbpf_legacy.h

@@ -20,6 +20,11 @@
 extern "C" {
 #endif
 
+/* As of libbpf 1.0 libbpf_set_strict_mode() and enum libbpf_struct_mode have
+ * no effect. But they are left in libbpf_legacy.h so that applications that
+ * prepared for libbpf 1.0 before final release by using
+ * libbpf_set_strict_mode() still work with libbpf 1.0+ without any changes.
+ */
 enum libbpf_strict_mode {
 	/* Turn on all supported strict features of libbpf to simulate libbpf
 	 * v1.0 behavior.
@@ -45,7 +50,6 @@ enum libbpf_strict_mode {
 	 * (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
@@ -55,6 +59,10 @@ enum libbpf_strict_mode {
 	 *
 	 * Note, in this mode the program pin path will be based on the
 	 * function name instead of section name.
+	 *
+	 * Additionally, routines in the .text section are always considered
+	 * sub-programs. Legacy behavior allows for a single routine in .text
+	 * to be a program.
 	 */
 	LIBBPF_STRICT_SEC_NAME = 0x04,
 	/*
@@ -63,12 +71,67 @@ enum libbpf_strict_mode {
 	 * 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() API.
+	 * Note that libbpf_set_memlock_rlim() 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);
 
+/**
+ * @brief **libbpf_get_error()** extracts the error code from the passed
+ * pointer
+ * @param ptr pointer returned from libbpf API function
+ * @return error code; or 0 if no error occured
+ *
+ * Note, as of libbpf 1.0 this function is not necessary and not recommended
+ * to be used. Libbpf doesn't return error code embedded into the pointer
+ * itself. Instead, NULL is returned on error and error code is passed through
+ * thread-local errno variable. **libbpf_get_error()** is just returning -errno
+ * value if it receives NULL, which is correct only if errno hasn't been
+ * modified between libbpf API call and corresponding **libbpf_get_error()**
+ * call. Prefer to check return for NULL and use errno directly.
+ *
+ * This API is left in libbpf 1.0 to allow applications that were 1.0-ready
+ * before final libbpf 1.0 without needing to change them.
+ */
+LIBBPF_API long libbpf_get_error(const void *ptr);
+
+#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 struct btf *libbpf_find_kernel_btf(void);
+
+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" */

src/libbpf_probes.c

@@ -12,77 +12,154 @@
 #include <linux/btf.h>
 #include <linux/filter.h>
 #include <linux/kernel.h>
+#include <linux/version.h>
 
 #include "bpf.h"
 #include "libbpf.h"
 #include "libbpf_internal.h"
 
-static bool grep(const char *buffer, const char *pattern)
+/* On Ubuntu LINUX_VERSION_CODE doesn't correspond to info.release,
+ * but Ubuntu provides /proc/version_signature file, as described at
+ * https://ubuntu.com/kernel, with an example contents below, which we
+ * can use to get a proper LINUX_VERSION_CODE.
+ *
+ *   Ubuntu 5.4.0-12.15-generic 5.4.8
+ *
+ * In the above, 5.4.8 is what kernel is actually expecting, while
+ * uname() call will return 5.4.0 in info.release.
+ */
+static __u32 get_ubuntu_kernel_version(void)
 {
-	return !!strstr(buffer, pattern);
-}
+	const char *ubuntu_kver_file = "/proc/version_signature";
+	__u32 major, minor, patch;
+	int ret;
+	FILE *f;
 
-static int get_vendor_id(int ifindex)
-{
-	char ifname[IF_NAMESIZE], path[64], buf[8];
-	ssize_t len;
-	int fd;
-
-	if (!if_indextoname(ifindex, ifname))
-		return -1;
-
-	snprintf(path, sizeof(path), "/sys/class/net/%s/device/vendor", ifname);
-
-	fd = open(path, O_RDONLY | O_CLOEXEC);
-	if (fd < 0)
-		return -1;
-
-	len = read(fd, buf, sizeof(buf));
-	close(fd);
-	if (len < 0)
-		return -1;
-	if (len >= (ssize_t)sizeof(buf))
-		return -1;
-	buf[len] = '\0';
-
-	return strtol(buf, NULL, 0);
-}
-
-static int get_kernel_version(void)
-{
-	int version, subversion, patchlevel;
-	struct utsname utsn;
-
-	/* Return 0 on failure, and attempt to probe with empty kversion */
-	if (uname(&utsn))
+	if (faccessat(AT_FDCWD, ubuntu_kver_file, R_OK, AT_EACCESS) != 0)
 		return 0;
 
-	if (sscanf(utsn.release, "%d.%d.%d",
-		   &version, &subversion, &patchlevel) != 3)
+	f = fopen(ubuntu_kver_file, "re");
+	if (!f)
 		return 0;
 
-	return (version << 16) + (subversion << 8) + patchlevel;
+	ret = fscanf(f, "%*s %*s %u.%u.%u\n", &major, &minor, &patch);
+	fclose(f);
+	if (ret != 3)
+		return 0;
+
+	return KERNEL_VERSION(major, minor, patch);
 }
 
-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)
+/* On Debian LINUX_VERSION_CODE doesn't correspond to info.release.
+ * Instead, it is provided in info.version. An example content of
+ * Debian 10 looks like the below.
+ *
+ *   utsname::release   4.19.0-22-amd64
+ *   utsname::version   #1 SMP Debian 4.19.260-1 (2022-09-29)
+ *
+ * In the above, 4.19.260 is what kernel is actually expecting, while
+ * uname() call will return 4.19.0 in info.release.
+ */
+static __u32 get_debian_kernel_version(struct utsname *info)
 {
-	struct bpf_load_program_attr xattr = {};
-	int fd;
+	__u32 major, minor, patch;
+	char *p;
+
+	p = strstr(info->version, "Debian ");
+	if (!p) {
+		/* This is not a Debian kernel. */
+		return 0;
+	}
+
+	if (sscanf(p, "Debian %u.%u.%u", &major, &minor, &patch) != 3)
+		return 0;
+
+	return KERNEL_VERSION(major, minor, patch);
+}
+
+__u32 get_kernel_version(void)
+{
+	__u32 major, minor, patch, version;
+	struct utsname info;
+
+	/* Check if this is an Ubuntu kernel. */
+	version = get_ubuntu_kernel_version();
+	if (version != 0)
+		return version;
+
+	uname(&info);
+
+	/* Check if this is a Debian kernel. */
+	version = get_debian_kernel_version(&info);
+	if (version != 0)
+		return version;
+
+	if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3)
+		return 0;
+
+	if (major == 4 && minor == 19 && patch > 255)
+		return KERNEL_VERSION(major, minor, 255);;
+
+	return KERNEL_VERSION(major, minor, patch);
+}
+
+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)
+{
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		.log_buf = log_buf,
+		.log_size = log_buf_sz,
+		.log_level = log_buf ? 1 : 0,
+	);
+	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:
-		xattr.expected_attach_type = BPF_CGROUP_GETSOCKOPT;
+		opts.expected_attach_type = BPF_CGROUP_GETSOCKOPT;
 		break;
 	case BPF_PROG_TYPE_SK_LOOKUP:
-		xattr.expected_attach_type = BPF_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:
@@ -103,48 +180,50 @@ 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:
-	case BPF_PROG_TYPE_TRACING:
-	case BPF_PROG_TYPE_STRUCT_OPS:
-	case BPF_PROG_TYPE_EXT:
-	case BPF_PROG_TYPE_LSM:
-	default:
 		break;
+	case BPF_PROG_TYPE_NETFILTER:
+		opts.expected_attach_type = BPF_NETFILTER;
+		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;
 }
 
-bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex)
+int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts)
 {
-	struct bpf_insn insns[2] = {
+	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 (ifindex && prog_type == BPF_PROG_TYPE_SCHED_CLS)
-		/* nfp returns -EINVAL on exit(0) with TC offload */
-		insns[0].imm = 2;
+	if (opts)
+		return libbpf_err(-EINVAL);
 
-	errno = 0;
-	probe_load(prog_type, insns, ARRAY_SIZE(insns), NULL, 0, ifindex);
-
-	return errno != EINVAL && errno != EOPNOTSUPP;
+	ret = probe_prog_load(prog_type, insns, insn_cnt, NULL, 0);
+	return libbpf_err(ret);
 }
 
 int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
-			 const char *str_sec, size_t str_len)
+			 const char *str_sec, size_t str_len,
+			 int token_fd)
 {
 	struct btf_header hdr = {
 		.magic = BTF_MAGIC,
@@ -154,6 +233,10 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
 		.str_off = types_len,
 		.str_len = str_len,
 	};
+	LIBBPF_OPTS(bpf_btf_load_opts, opts,
+		.token_fd = token_fd,
+		.btf_flags = token_fd ? BPF_F_TOKEN_FD : 0,
+	);
 	int btf_fd, btf_len;
 	__u8 *raw_btf;
 
@@ -166,7 +249,7 @@ int libbpf__load_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);
+	btf_fd = bpf_btf_load(raw_btf, btf_len, &opts);
 
 	free(raw_btf);
 	return btf_fd;
@@ -196,20 +279,19 @@ static int load_local_storage_btf(void)
 	};
 
 	return libbpf__load_raw_btf((char *)types, sizeof(types),
-				     strs, sizeof(strs));
+				     strs, sizeof(strs), 0);
 }
 
-bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
+static int probe_map_create(enum bpf_map_type map_type)
 {
-	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 = 0;
 
 	key_size	= sizeof(__u32);
 	value_size	= sizeof(__u32);
 	max_entries	= 1;
-	map_flags	= 0;
 
 	switch (map_type) {
 	case BPF_MAP_TYPE_STACK_TRACE:
@@ -218,7 +300,7 @@ 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:
@@ -233,21 +315,39 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 	case BPF_MAP_TYPE_SK_STORAGE:
 	case BPF_MAP_TYPE_INODE_STORAGE:
 	case BPF_MAP_TYPE_TASK_STORAGE:
+	case BPF_MAP_TYPE_CGRP_STORAGE:
 		btf_key_type_id = 1;
 		btf_value_type_id = 3;
 		value_size = 8;
 		max_entries = 0;
-		map_flags = BPF_F_NO_PREALLOC;
+		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:
+	case BPF_MAP_TYPE_USER_RINGBUF:
 		key_size = 0;
 		value_size = 0;
-		max_entries = 4096;
+		max_entries = sysconf(_SC_PAGE_SIZE);
+		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;
+		opts.value_type_btf_obj_fd = -1;
+		exp_err = -524; /* -ENOTSUPP */
+		break;
+	case BPF_MAP_TYPE_BLOOM_FILTER:
+		key_size = 0;
+		max_entries = 1;
+		break;
+	case BPF_MAP_TYPE_ARENA:
+		key_size	= 0;
+		value_size	= 0;
+		max_entries	= 1; /* one page */
+		opts.map_extra	= 0; /* can mmap() at any address */
+		opts.map_flags	= BPF_F_MMAPABLE;
 		break;
-	case BPF_MAP_TYPE_UNSPEC:
 	case BPF_MAP_TYPE_HASH:
 	case BPF_MAP_TYPE_ARRAY:
 	case BPF_MAP_TYPE_PROG_ARRAY:
@@ -266,95 +366,103 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 	case BPF_MAP_TYPE_XSKMAP:
 	case BPF_MAP_TYPE_SOCKHASH:
 	case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
-	case BPF_MAP_TYPE_STRUCT_OPS:
-	default:
 		break;
+	case BPF_MAP_TYPE_UNSPEC:
+	default:
+		return -EOPNOTSUPP;
 	}
 
 	if (map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
 	    map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
-		/* TODO: probe for device, once libbpf has a function to create
-		 * map-in-map for offload
-		 */
-		if (ifindex)
-			return false;
-
-		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;
 }
 
-bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type,
-		      __u32 ifindex)
+int libbpf_probe_bpf_map_type(enum bpf_map_type map_type, const void *opts)
 {
-	struct bpf_insn insns[2] = {
-		BPF_EMIT_CALL(id),
-		BPF_EXIT_INSN()
+	int ret;
+
+	if (opts)
+		return libbpf_err(-EINVAL);
+
+	ret = probe_map_create(map_type);
+	return libbpf_err(ret);
+}
+
+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(),
 	};
-	char buf[4096] = {};
-	bool res;
+	const size_t insn_cnt = ARRAY_SIZE(insns);
+	char buf[4096];
+	int ret;
 
-	probe_load(prog_type, insns, ARRAY_SIZE(insns), buf, sizeof(buf),
-		   ifindex);
-	res = !grep(buf, "invalid func ") && !grep(buf, "unknown func ");
+	if (opts)
+		return libbpf_err(-EINVAL);
 
-	if (ifindex) {
-		switch (get_vendor_id(ifindex)) {
-		case 0x19ee: /* Netronome specific */
-			res = res && !grep(buf, "not supported by FW") &&
-				!grep(buf, "unsupported function id");
-			break;
-		default:
-			break;
-		}
+	/* 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;
 	}
 
-	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_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0,
-		   ifindex);
-
-	return errno != E2BIG && errno != EINVAL;
+	buf[0] = '\0';
+	ret = probe_prog_load(prog_type, insns, insn_cnt, buf, sizeof(buf));
+	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"
+	 * or "program of this type cannot use helper 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 ") ||
+			 strstr(buf, "program of this type cannot use helper ")))
+		return 0;
+	return 1; /* assume supported */
 }

src/libbpf_version.h

@@ -3,7 +3,7 @@
 #ifndef __LIBBPF_VERSION_H
 #define __LIBBPF_VERSION_H
 
-#define LIBBPF_MAJOR_VERSION 0
-#define LIBBPF_MINOR_VERSION 6
+#define LIBBPF_MAJOR_VERSION 1
+#define LIBBPF_MINOR_VERSION 5
 
 #endif /* __LIBBPF_VERSION_H */