Merge branch 'libbpf:master' into master

Update checked in vmlinux.h for 5.5 kernel tests.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>

.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

@@ -2,16 +2,16 @@
 
 set -euo pipefail
 
-source $(cd $(dirname $0) && pwd)/helpers.sh
+THISDIR="$(cd $(dirname $0) && pwd)"
 
-travis_fold start prepare_selftests "Building selftests"
+source ${THISDIR}/helpers.sh
 
-sudo apt-get -y install python-docutils # for rst2man
+foldable start prepare_selftests "Building selftests"
 
-LLVM_VER=14
+LLVM_VER=16
 LIBBPF_PATH="${REPO_ROOT}"
 
-PREPARE_SELFTESTS_SCRIPT=${VMTEST_ROOT}/prepare_selftests-${KERNEL}.sh
+PREPARE_SELFTESTS_SCRIPT=${THISDIR}/prepare_selftests-${KERNEL}.sh
 if [ -f "${PREPARE_SELFTESTS_SCRIPT}" ]; then
 	(cd "${REPO_ROOT}/${REPO_PATH}/tools/testing/selftests/bpf" && ${PREPARE_SELFTESTS_SCRIPT})
 fi
@@ -19,9 +19,10 @@ fi
 if [[ "${KERNEL}" = 'LATEST' ]]; then
 	VMLINUX_H=
 else
-	VMLINUX_H=${VMTEST_ROOT}/vmlinux.h
+	VMLINUX_H=${THISDIR}/vmlinux.h
 fi
 
+cd ${REPO_ROOT}/${REPO_PATH}
 make \
 	CLANG=clang-${LLVM_VER} \
 	LLC=llc-${LLVM_VER} \
@@ -29,7 +30,8 @@ make \
 	VMLINUX_BTF="${VMLINUX_BTF}" \
 	VMLINUX_H=${VMLINUX_H} \
 	-C "${REPO_ROOT}/${REPO_PATH}/tools/testing/selftests/bpf" \
-	-j $((4*$(nproc))) >/dev/null
+	-j $((4*$(nproc))) > /dev/null
+cd -
 mkdir ${LIBBPF_PATH}/selftests
 cp -R "${REPO_ROOT}/${REPO_PATH}/tools/testing/selftests/bpf" \
 	${LIBBPF_PATH}/selftests
@@ -37,6 +39,4 @@ cd ${LIBBPF_PATH}
 rm selftests/bpf/.gitignore
 git add selftests
 
-git add "${VMTEST_ROOT}/configs/blacklist"
-
-travis_fold end prepare_selftests
+foldable end prepare_selftests

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

@@ -0,0 +1,36 @@
+# $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/setup/action.yml

@@ -12,7 +12,7 @@ runs:
         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

.github/actions/vmtest/action.yml

@@ -5,31 +5,92 @@ 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
+    # setup environment
+    - name: Setup environment
+      uses: libbpf/ci/setup-build-env@master
+      with:
+        pahole: ${{ inputs.pahole }}
+    # 1. download CHECKPOINT kernel source
+    - name: Get checkpoint commit
       shell: bash
+      run: |
+        cat CHECKPOINT-COMMIT
+        echo "CHECKPOINT=$(cat CHECKPOINT-COMMIT)" >> $GITHUB_ENV
+    - name: Get kernel source at checkpoint
+      uses: libbpf/ci/get-linux-source@master
+      with:
+        repo: 'https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git'
+        rev: ${{ env.CHECKPOINT }}
+        dest: '${{ github.workspace }}/.kernel'
+    - name: Patch kernel source
+      uses: libbpf/ci/patch-kernel@master
+      with:
+        patches-root: '${{ github.workspace }}/travis-ci/diffs'
+        repo-root: '.kernel'
+    - name: Prepare to build BPF selftests
+      shell: bash
+      run: |
+        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
+        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@master
+      with:
+        kernel: ${{ inputs.kernel }}
+        arch: ${{ inputs.arch }}
+    # 3. build selftests
+    - name: Build BPF selftests
+      uses: ./.github/actions/build-selftests
+      with:
+        repo-path: '.kernel'
+        kernel: ${{ inputs.kernel }}
+    # 4. prepare rootfs
+    - name: prepare rootfs
+      uses: libbpf/ci/prepare-rootfs@master
+      with:
+        project-name: 'libbpf'
+        arch: ${{ inputs.arch }}
+        kernel: ${{ inputs.kernel }}
+        kernel-root: '.kernel'
+        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@master
+      with:
+        arch: ${{ inputs.arch }}
+        img: '/tmp/root.img'
+        vmlinuz: 'vmlinuz'
+        kernel-root: '.kernel'

.github/workflows/build.yml

@@ -0,0 +1,81 @@
+name: libbpf-build
+
+on:
+  pull_request:
+  push:
+  schedule:
+    - cron:  '0 18 * * *'
+
+concurrency:
+  group: ci-build-${{ github.head_ref }}
+  cancel-in-progress: true
+
+jobs:
+
+  debian:
+    runs-on: ubuntu-latest
+    name: Debian Build (${{ matrix.name }})
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - name: default
+            target: RUN
+          - name: ASan+UBSan
+            target: RUN_ASAN
+          - name: clang
+            target: RUN_CLANG
+          - name: clang ASan+UBSan
+            target: RUN_CLANG_ASAN
+          - name: gcc-10
+            target: RUN_GCC10
+          - name: gcc-10 ASan+UBSan
+            target: RUN_GCC10_ASAN
+    steps:
+      - uses: actions/checkout@v3
+        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@v3
+        name: Checkout
+      - uses: ./.github/actions/setup
+        name: Pre-Setup
+      - run: source /tmp/ci_setup && sudo -E $CI_ROOT/managers/ubuntu.sh
+        if: matrix.arch == 'x86'
+        name: Setup
+      - uses: uraimo/run-on-arch-action@v2.0.5
+        name: Build in docker
+        if: matrix.arch != 'x86'
+        with:
+          distro:
+            ubuntu20.04
+          arch:
+            ${{ matrix.arch }}
+          setup:
+            cp /tmp/ci_setup $GITHUB_WORKSPACE
+          dockerRunArgs: |
+            --volume "${GITHUB_WORKSPACE}:${GITHUB_WORKSPACE}"
+          shell: /bin/bash
+          install: |
+            export DEBIAN_FRONTEND=noninteractive
+            export TZ="America/Los_Angeles"
+            apt-get update -y
+            apt-get install -y tzdata build-essential sudo
+          run: source ${GITHUB_WORKSPACE}/ci_setup && $CI_ROOT/managers/ubuntu.sh

.github/workflows/coverity.yml

@@ -11,16 +11,17 @@ jobs:
     if: github.repository == 'libbpf/libbpf'
     name: Coverity
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - 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/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@v3
       - uses: ./.github/actions/setup
       - uses: ./.github/actions/vmtest
         with:

.github/workflows/pahole.yml

@@ -12,7 +12,7 @@ jobs:
     env:
       STAGING: tmp.master
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - 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-latest
+            arch: 'x86_64'
           - kernel: '5.5.0'
+            runs_on: ubuntu-latest
+            arch: 'x86_64'
           - kernel: '4.9.0'
+            runs_on: ubuntu-latest
+            arch: 'x86_64'
+          - kernel: 'LATEST'
+            runs_on: z15
+            arch: 's390x'
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
         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 }}

.readthedocs.yaml

@@ -10,6 +10,11 @@ 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

.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
+60240bc26114543fcbfcd8a28466e67e77b20388

CHECKPOINT-COMMIT

@@ -1 +1 @@
-b8b5cb55f5d3f03cc1479a3768d68173a10359ad
+87dbdc230d162bf9ee1ac77c8ade178b6b1e199e

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 +1,32 @@
-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)
+[![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)
+======
 
-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 +51,8 @@ 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 +84,6 @@ $ 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 +137,48 @@ 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://www.archlinux.org/packages/extra/x86_64/libbpf/)
+  - [Ubuntu](https://packages.ubuntu.com/source/impish/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.
+
+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
 =======
 

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

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

ci/managers/debian.sh

@@ -7,7 +7,8 @@ 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"
+EXTRA_CFLAGS=""
+EXTRA_LDFLAGS=""
 
 function info() {
     echo -e "\033[33;1m$1\033[0m"
@@ -55,17 +56,17 @@ for phase in "${PHASES[@]}"; do
             elif [[ "$phase" = *"GCC10"* ]]; then
                 ENV_VARS="-e CC=gcc-10 -e CXX=g++-10"
                 CC="gcc-10"
-                CFLAGS="${CFLAGS} -Wno-stringop-truncation"
             else
-                CFLAGS="${CFLAGS} -Wno-stringop-truncation"
+                EXTRA_CFLAGS="${EXTRA_CFLAGS} -Wno-stringop-truncation"
             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
             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 +76,7 @@ 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/rootfs/mkrootfs_arch.sh

@@ -80,6 +80,7 @@ packages=(
 	# selftests test_progs dependencies.
 	binutils
 	elfutils
+	ethtool
 	glibc
 	iproute2
 	# selftests test_verifier dependencies.
@@ -100,59 +101,7 @@ rm -rf "$root/var/lib/pacman/sync/"
 # We don't need any documentation.
 rm -rf "$root/usr/share/{doc,help,man,texinfo}"
 
-chroot "${root}" /bin/busybox --install
+"$(dirname "$0")"/mkrootfs_tweak.sh "$root"
 
-cat > "$root/etc/inittab" << "EOF"
-::sysinit:/etc/init.d/rcS
-::ctrlaltdel:/sbin/reboot
-::shutdown:/sbin/swapoff -a
-::shutdown:/bin/umount -a -r
-::restart:/sbin/init
-EOF
-chmod 644 "$root/etc/inittab"
-
-mkdir -m 755 "$root/etc/init.d" "$root/etc/rcS.d"
-cat > "$root/etc/rcS.d/S10-mount" << "EOF"
-#!/bin/sh
-
-set -eux
-
-/bin/mount proc /proc -t proc
-
-# Mount devtmpfs if not mounted
-if [[ -z $(/bin/mount -l -t devtmpfs) ]]; then
-	/bin/mount devtmpfs /dev -t devtmpfs
-fi
-
-/bin/mount sysfs /sys -t sysfs
-/bin/mount bpffs /sys/fs/bpf -t bpf
-/bin/mount debugfs /sys/kernel/debug -t debugfs
-
-echo 'Listing currently mounted file systems'
-/bin/mount
-EOF
-chmod 755 "$root/etc/rcS.d/S10-mount"
-
-cat > "$root/etc/rcS.d/S40-network" << "EOF"
-#!/bin/sh
-
-set -eux
-
-ip link set lo up
-EOF
-chmod 755 "$root/etc/rcS.d/S40-network"
-
-cat > "$root/etc/init.d/rcS" << "EOF"
-#!/bin/sh
-
-set -eux
-
-for path in /etc/rcS.d/S*; do
-	[ -x "$path" ] && "$path"
-done
-EOF
-chmod 755 "$root/etc/init.d/rcS"
-
-chmod 755 "$root"
 tar -C "$root" -c . | zstd -T0 -19 -o "$NAME"
 chmod 644 "$NAME"

ci/rootfs/mkrootfs_debian.sh

@@ -0,0 +1,52 @@
+#!/bin/bash
+# This script builds a Debian root filesystem image for testing libbpf in a
+# virtual machine. Requires debootstrap >= 1.0.95 and zstd.
+
+# Use e.g. ./mkrootfs_debian.sh --arch=s390x to generate a rootfs for a
+# foreign architecture. Requires configured binfmt_misc, e.g. using
+# Debian/Ubuntu's qemu-user-binfmt package or
+# https://github.com/multiarch/qemu-user-static.
+
+set -e -u -x -o pipefail
+
+# Check whether we are root now in order to avoid confusing errors later.
+if [ "$(id -u)" != 0 ]; then
+	echo "$0 must run as root" >&2
+	exit 1
+fi
+
+# Create a working directory and schedule its deletion.
+root=$(mktemp -d -p "$PWD")
+trap 'rm -r "$root"' EXIT
+
+# Install packages.
+packages=(
+	binutils
+	busybox
+	elfutils
+	ethtool
+	iproute2
+	iptables
+	libcap2
+	libelf1
+	strace
+	zlib1g
+)
+packages=$(IFS=, && echo "${packages[*]}")
+debootstrap --include="$packages" --variant=minbase "$@" bookworm "$root"
+
+# Remove the init scripts (tests use their own). Also remove various
+# unnecessary files in order to save space.
+rm -rf \
+	"$root"/etc/rcS.d \
+	"$root"/usr/share/{doc,info,locale,man,zoneinfo} \
+	"$root"/var/cache/apt/archives/* \
+	"$root"/var/lib/apt/lists/*
+
+# Apply common tweaks.
+"$(dirname "$0")"/mkrootfs_tweak.sh "$root"
+
+# Save the result.
+name="libbpf-vmtest-rootfs-$(date +%Y.%m.%d).tar.zst"
+rm -f "$name"
+tar -C "$root" -c . | zstd -T0 -19 -o "$name"

ci/rootfs/mkrootfs_tweak.sh

@@ -0,0 +1,61 @@
+#!/bin/bash
+# This script prepares a mounted root filesystem for testing libbpf in a virtual
+# machine.
+set -e -u -x -o pipefail
+root=$1
+shift
+
+chroot "${root}" /bin/busybox --install
+
+cat > "$root/etc/inittab" << "EOF"
+::sysinit:/etc/init.d/rcS
+::ctrlaltdel:/sbin/reboot
+::shutdown:/sbin/swapoff -a
+::shutdown:/bin/umount -a -r
+::restart:/sbin/init
+EOF
+chmod 644 "$root/etc/inittab"
+
+mkdir -m 755 -p "$root/etc/init.d" "$root/etc/rcS.d"
+cat > "$root/etc/rcS.d/S10-mount" << "EOF"
+#!/bin/sh
+
+set -eux
+
+/bin/mount proc /proc -t proc
+
+# Mount devtmpfs if not mounted
+if [[ -z $(/bin/mount -t devtmpfs) ]]; then
+	/bin/mount devtmpfs /dev -t devtmpfs
+fi
+
+/bin/mount sysfs /sys -t sysfs
+/bin/mount bpffs /sys/fs/bpf -t bpf
+/bin/mount debugfs /sys/kernel/debug -t debugfs
+
+echo 'Listing currently mounted file systems'
+/bin/mount
+EOF
+chmod 755 "$root/etc/rcS.d/S10-mount"
+
+cat > "$root/etc/rcS.d/S40-network" << "EOF"
+#!/bin/sh
+
+set -eux
+
+ip link set lo up
+EOF
+chmod 755 "$root/etc/rcS.d/S40-network"
+
+cat > "$root/etc/init.d/rcS" << "EOF"
+#!/bin/sh
+
+set -eux
+
+for path in /etc/rcS.d/S*; do
+	[ -x "$path" ] && "$path"
+done
+EOF
+chmod 755 "$root/etc/init.d/rcS"
+
+chmod 755 "$root"

ci/rootfs/s390x-self-hosted-builder/README.md

@@ -0,0 +1,108 @@
+# IBM Z self-hosted builder
+
+libbpf CI uses an IBM-provided z15 self-hosted builder. There are no IBM Z
+builds of GitHub (GH) Actions runner, and stable qemu-user has problems with .NET
+apps, so the builder runs the x86_64 runner version with qemu-user built from
+the master branch.
+
+We are currently supporting runners for the following repositories:
+* libbpf/libbpf
+* kernel-patches/bpf
+* kernel-patches/vmtest
+
+Below instructions are directly applicable to libbpf, and require minor
+modifications for kernel-patches repos. Currently, qemu-user-static Docker
+image is shared between all GitHub runners, but separate actions-runner-\*
+service / Docker image is created for each runner type.
+
+## Configuring the builder.
+
+### Install prerequisites.
+
+```
+$ sudo apt install -y docker.io  # Ubuntu
+```
+
+### Add services.
+
+```
+$ sudo cp *.service /etc/systemd/system/
+$ sudo systemctl daemon-reload
+```
+
+### Create a config file.
+
+```
+$ sudo tee /etc/actions-runner-libbpf
+repo=<owner>/<name>
+access_token=<ghp_***>
+runner_name=<hostname>
+```
+
+Access token should have the repo scope, consult
+https://docs.github.com/en/rest/reference/actions#create-a-registration-token-for-a-repository
+for details.
+
+### Autostart the x86_64 emulation support.
+
+This step is important, you would not be able to build docker container
+without having this service running. If container build fails, make sure
+service is running properly.
+
+```
+$ sudo systemctl enable --now qemu-user-static
+```
+
+### Autostart the runner.
+
+```
+$ sudo systemctl enable --now actions-runner-libbpf
+```
+
+## Rebuilding the image
+
+In order to update the `iiilinuxibmcom/actions-runner-libbpf` image, e.g. to
+get the latest OS security fixes, use the following commands:
+
+```
+$ sudo docker build \
+      --pull \
+      -f actions-runner-libbpf.Dockerfile \
+      -t iiilinuxibmcom/actions-runner-libbpf \
+      .
+$ sudo systemctl restart actions-runner-libbpf
+```
+
+## Removing persistent data
+
+The `actions-runner-libbpf` service stores various temporary data, such as
+runner registration information, work directories and logs, in the
+`actions-runner-libbpf` volume. In order to remove it and start from scratch,
+e.g. when upgrading the runner or switching it to a different repository, use
+the following commands:
+
+```
+$ sudo systemctl stop actions-runner-libbpf
+$ sudo docker rm -f actions-runner-libbpf
+$ sudo docker volume rm actions-runner-libbpf
+```
+
+## Troubleshooting
+
+In order to check if service is running, use the following command:
+
+```
+$ sudo systemctl status <service name>
+```
+
+In order to get logs for service:
+
+```
+$ journalctl -u <service name>
+```
+
+In order to check which containers are currently active:
+
+```
+$ sudo docker ps
+```

ci/rootfs/s390x-self-hosted-builder/actions-runner-libbpf.Dockerfile

@@ -0,0 +1,52 @@
+# Self-Hosted IBM Z Github Actions Runner.
+
+# Temporary image: amd64 dependencies.
+FROM amd64/ubuntu:20.04 as ld-prefix
+ENV DEBIAN_FRONTEND=noninteractive
+RUN apt-get update && apt-get -y install ca-certificates libicu66 libssl1.1
+
+# Main image.
+FROM s390x/ubuntu:20.04
+
+# Packages for libbpf testing that are not installed by .github/actions/setup.
+ENV DEBIAN_FRONTEND=noninteractive
+RUN apt-get update && apt-get -y install \
+        bc \
+        bison \
+        cmake \
+        cpu-checker \
+        curl \
+        flex \
+        git \
+        jq \
+        linux-image-generic \
+        qemu-system-s390x \
+        rsync \
+        software-properties-common \
+        sudo \
+        tree \
+        iproute2 \
+        iputils-ping
+
+# amd64 dependencies.
+COPY --from=ld-prefix / /usr/x86_64-linux-gnu/
+RUN ln -fs ../lib/x86_64-linux-gnu/ld-linux-x86-64.so.2 /usr/x86_64-linux-gnu/lib64/
+RUN ln -fs /etc/resolv.conf /usr/x86_64-linux-gnu/etc/
+ENV QEMU_LD_PREFIX=/usr/x86_64-linux-gnu
+
+# amd64 Github Actions Runner.
+ARG version=2.296.0
+RUN useradd -m actions-runner
+RUN echo "actions-runner ALL=(ALL) NOPASSWD: ALL" >>/etc/sudoers
+RUN echo "Defaults env_keep += \"DEBIAN_FRONTEND\"" >>/etc/sudoers
+RUN usermod -a -G kvm actions-runner
+USER actions-runner
+ENV USER=actions-runner
+WORKDIR /home/actions-runner
+RUN curl -L https://github.com/actions/runner/releases/download/v${version}/actions-runner-linux-x64-${version}.tar.gz | tar -xz
+VOLUME /home/actions-runner
+
+# Scripts.
+COPY fs/ /
+ENTRYPOINT ["/usr/bin/entrypoint"]
+CMD ["/usr/bin/actions-runner"]

ci/rootfs/s390x-self-hosted-builder/actions-runner-libbpf.service

@@ -0,0 +1,24 @@
+[Unit]
+Description=Self-Hosted IBM Z Github Actions Runner
+Wants=qemu-user-static
+After=qemu-user-static
+StartLimitIntervalSec=0
+
+[Service]
+Type=simple
+Restart=always
+ExecStart=/usr/bin/docker run \
+              --device=/dev/kvm \
+              --env-file=/etc/actions-runner-libbpf \
+              --init \
+              --interactive \
+              --name=actions-runner-libbpf \
+              --rm \
+              --volume=actions-runner-libbpf:/home/actions-runner \
+              iiilinuxibmcom/actions-runner-libbpf
+ExecStop=/bin/sh -c "docker exec actions-runner-libbpf kill -INT -- -1"
+ExecStop=/bin/sh -c "docker wait actions-runner-libbpf"
+ExecStop=/bin/sh -c "docker rm actions-runner-libbpf"
+
+[Install]
+WantedBy=multi-user.target

ci/rootfs/s390x-self-hosted-builder/fs/usr/bin/actions-runner

@@ -0,0 +1,41 @@
+#!/bin/bash
+
+#
+# Ephemeral runner startup script.
+#
+# Expects the following environment variables:
+#
+# - repo=<owner>/<name>
+# - access_token=<ghp_***>
+# - runner_name=<hostname>
+
+set -e -u
+
+# Check the cached registration token.
+token_file=registration-token.json
+set +e
+expires_at=$(jq --raw-output .expires_at "$token_file" 2>/dev/null)
+status=$?
+set -e
+if [[ $status -ne 0 || $(date +%s) -ge $(date -d "$expires_at" +%s) ]]; then
+    # Refresh the cached registration token.
+    curl \
+        -X POST \
+        -H "Accept: application/vnd.github.v3+json" \
+        -H "Authorization: token $access_token" \
+        "https://api.github.com/repos/$repo/actions/runners/registration-token" \
+        -o "$token_file"
+fi
+
+# (Re-)register the runner.
+registration_token=$(jq --raw-output .token "$token_file")
+./config.sh remove --token "$registration_token" || true
+./config.sh \
+    --url "https://github.com/$repo" \
+    --token "$registration_token" \
+    --labels z15 \
+    --name "$runner_name" \
+    --ephemeral
+
+# Run one job.
+./run.sh

ci/rootfs/s390x-self-hosted-builder/fs/usr/bin/entrypoint

@@ -0,0 +1,35 @@
+#!/bin/bash
+
+#
+# Container entrypoint that waits for all spawned processes.
+#
+
+set -e -u
+
+# /dev/kvm has host permissions, fix it.
+if [ -e /dev/kvm ]; then
+    sudo chown root:kvm /dev/kvm
+fi
+
+# Create a FIFO and start reading from its read end.
+tempdir=$(mktemp -d "/tmp/done.XXXXXXXXXX")
+trap 'rm -r "$tempdir"' EXIT
+done="$tempdir/pipe"
+mkfifo "$done"
+cat "$done" & waiter=$!
+
+# Start the workload. Its descendants will inherit the FIFO's write end.
+status=0
+if [ "$#" -eq 0 ]; then
+    bash 9>"$done" || status=$?
+else
+    "$@" 9>"$done" || status=$?
+fi
+
+# When the workload and all of its descendants exit, the FIFO's write end will
+# be closed and `cat "$done"` will exit. Wait until it happens. This is needed
+# in order to handle SelfUpdater, which the workload may start in background
+# before exiting.
+wait "$waiter"
+
+exit "$status"

ci/rootfs/s390x-self-hosted-builder/qemu-user-static.service

@@ -0,0 +1,11 @@
+[Unit]
+Description=Support for transparent execution of non-native binaries with QEMU user emulation
+
+[Service]
+Type=oneshot
+# The source code for iiilinuxibmcom/qemu-user-static is at https://github.com/iii-i/qemu-user-static/tree/v6.1.0-1
+# TODO: replace it with multiarch/qemu-user-static once version >6.1 is available
+ExecStart=/usr/bin/docker run --rm --interactive --privileged iiilinuxibmcom/qemu-user-static --reset -p yes
+
+[Install]
+WantedBy=multi-user.target

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
@@ -10,7 +10,6 @@ core_reloc
 core_retro
 cpu_mask
 endian
-fexit_stress
 get_branch_snapshot
 get_stackid_cannot_attach
 global_data
@@ -18,6 +17,7 @@ global_data_init
 global_func_args
 hashmap
 l4lb_all
+legacy_printk
 linked_funcs
 linked_maps
 map_lock
@@ -42,13 +42,13 @@ spinlock
 stacktrace_map
 stacktrace_map_raw_tp
 static_linked
-subprogs
 task_fd_query_rawtp
 task_fd_query_tp
 tc_bpf
 tcp_estats
 tcp_rtt
 tp_attach_query
+usdt/urand_pid_attach
 xdp
 xdp_info
 xdp_noinline

ci/vmtest/configs/DENYLIST-5.5.0

@@ -1,3 +1,6 @@
+# This file is not used and is there for historic purposes only.
+# See ALLOWLIST-5.5.0 instead.
+
 # PERMANENTLY DISABLED
 align			# verifier output format changed
 atomics			# new atomic operations (v5.12+)
@@ -68,6 +71,7 @@ sk_lookup		# v5.9+
 sk_storage_tracing	# missing bpf_sk_storage_get() helper
 skb_ctx			# ctx_{size, }_{in, out} in BPF_PROG_TEST_RUN is missing
 skb_helpers		# helpers added in 5.8+
+skeleton		# creates too big ARRAY map
 snprintf		# v5.13+
 snprintf_btf		# v5.10+
 sock_fields		# v5.10+

ci/vmtest/configs/DENYLIST-latest.s390x

@@ -0,0 +1,6 @@
+# TEMPORARY until bpf-next -> bpf merge
+lru_bug                                  # prog 'printk': failed to auto-attach: -524
+
+# TEMPORARY
+usdt/basic                               # failing verifier due to bounds check after LLVM update
+usdt/multispec                           # same as above

ci/vmtest/helpers.sh

@@ -0,0 +1,36 @@
+# $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 +1,87 @@
+#!/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 "$path"
+		fi;
+	done) | cut -d'#' -f1 | tr -s ' \t\n' ','
+}
+
+test_progs() {
+	if [[ "${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
+
+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/index.rst

@@ -3,11 +3,10 @@
 libbpf
 ======
 
-For API documentation see the `versioned API documentation site <https://libbpf.readthedocs.io/en/latest/api.html>`_.
-
 .. toctree::
    :maxdepth: 1
 
+   API Documentation <https://libbpf.readthedocs.io/en/latest/api.html>
    libbpf_naming_convention
    libbpf_build
 

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
 ---
 

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/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/bpf.h

@@ -87,10 +87,29 @@ struct bpf_cgroup_storage_key {
 	__u32	attach_type;		/* program attach type (enum bpf_attach_type) */
 };
 
+enum bpf_cgroup_iter_order {
+	BPF_CGROUP_ITER_ORDER_UNSPEC = 0,
+	BPF_CGROUP_ITER_SELF_ONLY,		/* process only a single object. */
+	BPF_CGROUP_ITER_DESCENDANTS_PRE,	/* walk descendants in pre-order. */
+	BPF_CGROUP_ITER_DESCENDANTS_POST,	/* walk descendants in post-order. */
+	BPF_CGROUP_ITER_ANCESTORS_UP,		/* walk ancestors upward. */
+};
+
 union bpf_iter_link_info {
 	struct {
 		__u32	map_fd;
 	} map;
+	struct {
+		enum bpf_cgroup_iter_order order;
+
+		/* At most one of cgroup_fd and cgroup_id can be non-zero. If
+		 * both are zero, the walk starts from the default cgroup v2
+		 * root. For walking v1 hierarchy, one should always explicitly
+		 * specify cgroup_fd.
+		 */
+		__u32	cgroup_fd;
+		__u64	cgroup_id;
+	} cgroup;
 };
 
 /* BPF syscall commands, see bpf(2) man-page for more details. */
@@ -330,6 +349,8 @@ union bpf_iter_link_info {
  *			*ctx_out*, *data_in* and *data_out* must be NULL.
  *			*repeat* must be zero.
  *
+ *		BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN.
+ *
  *	Return
  *		Returns zero on success. On error, -1 is returned and *errno*
  *		is set appropriately.
@@ -907,6 +928,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_INODE_STORAGE,
 	BPF_MAP_TYPE_TASK_STORAGE,
 	BPF_MAP_TYPE_BLOOM_FILTER,
+	BPF_MAP_TYPE_USER_RINGBUF,
 };
 
 /* Note that tracing related programs such as
@@ -995,6 +1017,8 @@ enum bpf_attach_type {
 	BPF_SK_REUSEPORT_SELECT,
 	BPF_SK_REUSEPORT_SELECT_OR_MIGRATE,
 	BPF_PERF_EVENT,
+	BPF_TRACE_KPROBE_MULTI,
+	BPF_LSM_CGROUP,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -1009,6 +1033,8 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_NETNS = 5,
 	BPF_LINK_TYPE_XDP = 6,
 	BPF_LINK_TYPE_PERF_EVENT = 7,
+	BPF_LINK_TYPE_KPROBE_MULTI = 8,
+	BPF_LINK_TYPE_STRUCT_OPS = 9,
 
 	MAX_BPF_LINK_TYPE,
 };
@@ -1111,6 +1137,16 @@ enum bpf_link_type {
  */
 #define BPF_F_SLEEPABLE		(1U << 4)
 
+/* If BPF_F_XDP_HAS_FRAGS is used in BPF_PROG_LOAD command, the loaded program
+ * fully support xdp frags.
+ */
+#define BPF_F_XDP_HAS_FRAGS	(1U << 5)
+
+/* link_create.kprobe_multi.flags used in LINK_CREATE command for
+ * BPF_TRACE_KPROBE_MULTI attach type to create return probe.
+ */
+#define BPF_F_KPROBE_MULTI_RETURN	(1U << 0)
+
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * the following extensions:
  *
@@ -1217,7 +1253,7 @@ enum {
 
 /* Query effective (directly attached + inherited from ancestor cgroups)
  * programs that will be executed for events within a cgroup.
- * attach_flags with this flag are returned only for directly attached programs.
+ * attach_flags with this flag are always returned 0.
  */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 
@@ -1225,6 +1261,8 @@ enum {
 
 /* If set, run the test on the cpu specified by bpf_attr.test.cpu */
 #define BPF_F_TEST_RUN_ON_CPU	(1U << 0)
+/* If set, XDP frames will be transmitted after processing */
+#define BPF_F_TEST_XDP_LIVE_FRAMES	(1U << 1)
 
 /* type for BPF_ENABLE_STATS */
 enum bpf_stats_type {
@@ -1342,8 +1380,10 @@ union bpf_attr {
 			/* or valid module BTF object fd or 0 to attach to vmlinux */
 			__u32		attach_btf_obj_fd;
 		};
-		__u32		:32;		/* pad */
+		__u32		core_relo_cnt;	/* number of bpf_core_relo */
 		__aligned_u64	fd_array;	/* array of FDs */
+		__aligned_u64	core_relos;
+		__u32		core_relo_rec_size; /* sizeof(struct bpf_core_relo) */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -1384,6 +1424,7 @@ union bpf_attr {
 		__aligned_u64	ctx_out;
 		__u32		flags;
 		__u32		cpu;
+		__u32		batch_size;
 	} test;
 
 	struct { /* anonymous struct used by BPF_*_GET_*_ID */
@@ -1411,6 +1452,10 @@ union bpf_attr {
 		__u32		attach_flags;
 		__aligned_u64	prog_ids;
 		__u32		prog_cnt;
+		/* output: per-program attach_flags.
+		 * not allowed to be set during effective query.
+		 */
+		__aligned_u64	prog_attach_flags;
 	} query;
 
 	struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */
@@ -1463,6 +1508,22 @@ union bpf_attr {
 				 */
 				__u64		bpf_cookie;
 			} perf_event;
+			struct {
+				__u32		flags;
+				__u32		cnt;
+				__aligned_u64	syms;
+				__aligned_u64	addrs;
+				__aligned_u64	cookies;
+			} kprobe_multi;
+			struct {
+				/* this is overlaid with the target_btf_id above. */
+				__u32		target_btf_id;
+				/* black box user-provided value passed through
+				 * to BPF program at the execution time and
+				 * accessible through bpf_get_attach_cookie() BPF helper
+				 */
+				__u64		cookie;
+			} tracing;
 		};
 	} link_create;
 
@@ -1744,7 +1805,7 @@ union bpf_attr {
  * 		if the maximum number of tail calls has been reached for this
  * 		chain of programs. This limit is defined in the kernel by the
  * 		macro **MAX_TAIL_CALL_CNT** (not accessible to user space),
- * 		which is currently set to 32.
+ *		which is currently set to 33.
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
@@ -1773,6 +1834,8 @@ union bpf_attr {
  * 		0 on success, or a negative error in case of failure.
  *
  * u64 bpf_get_current_pid_tgid(void)
+ * 	Description
+ * 		Get the current pid and tgid.
  * 	Return
  * 		A 64-bit integer containing the current tgid and pid, and
  * 		created as such:
@@ -1780,6 +1843,8 @@ union bpf_attr {
  * 		*current_task*\ **->pid**.
  *
  * u64 bpf_get_current_uid_gid(void)
+ * 	Description
+ * 		Get the current uid and gid.
  * 	Return
  * 		A 64-bit integer containing the current GID and UID, and
  * 		created as such: *current_gid* **<< 32 \|** *current_uid*.
@@ -2254,6 +2319,8 @@ union bpf_attr {
  * 		The 32-bit hash.
  *
  * u64 bpf_get_current_task(void)
+ * 	Description
+ * 		Get the current task.
  * 	Return
  * 		A pointer to the current task struct.
  *
@@ -2284,8 +2351,8 @@ union bpf_attr {
  * 	Return
  * 		The return value depends on the result of the test, and can be:
  *
- *		* 0, if current task belongs to the cgroup2.
- *		* 1, if current task does not belong to the cgroup2.
+ *		* 1, if current task belongs to the cgroup2.
+ *		* 0, if current task does not belong to the cgroup2.
  * 		* A negative error code, if an error occurred.
  *
  * long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags)
@@ -2317,7 +2384,8 @@ union bpf_attr {
  * 		Pull in non-linear data in case the *skb* is non-linear and not
  * 		all of *len* are part of the linear section. Make *len* bytes
  * 		from *skb* readable and writable. If a zero value is passed for
- * 		*len*, then the whole length of the *skb* is pulled.
+ *		*len*, then all bytes in the linear part of *skb* will be made
+ *		readable and writable.
  *
  * 		This helper is only needed for reading and writing with direct
  * 		packet access.
@@ -2367,6 +2435,8 @@ union bpf_attr {
  * 		indicate that the hash is outdated and to trigger a
  * 		recalculation the next time the kernel tries to access this
  * 		hash or when the **bpf_get_hash_recalc**\ () helper is called.
+ * 	Return
+ * 		void.
  *
  * long bpf_get_numa_node_id(void)
  * 	Description
@@ -2464,6 +2534,8 @@ union bpf_attr {
  * 		A 8-byte long unique number or 0 if *sk* is NULL.
  *
  * u32 bpf_get_socket_uid(struct sk_buff *skb)
+ * 	Description
+ * 		Get the owner UID of the socked associated to *skb*.
  * 	Return
  * 		The owner UID of the socket associated to *skb*. If the socket
  * 		is **NULL**, or if it is not a full socket (i.e. if it is a
@@ -2524,10 +2596,12 @@ union bpf_attr {
  *		There are two supported modes at this time:
  *
  *		* **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
- *		  (room space is added or removed below the layer 2 header).
+ * 		  (room space is added or removed between the layer 2 and
+ * 		  layer 3 headers).
  *
  * 		* **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
- * 		  (room space is added or removed below the layer 3 header).
+ * 		  (room space is added or removed between the layer 3 and
+ * 		  layer 4 headers).
  *
  *		The following flags are supported at this time:
  *
@@ -2959,8 +3033,18 @@ union bpf_attr {
  * 		**BPF_F_USER_STACK**
  * 			Collect a user space stack instead of a kernel stack.
  * 		**BPF_F_USER_BUILD_ID**
- * 			Collect buildid+offset instead of ips for user stack,
- * 			only valid if **BPF_F_USER_STACK** is also specified.
+ * 			Collect (build_id, file_offset) instead of ips for user
+ * 			stack, only valid if **BPF_F_USER_STACK** is also
+ * 			specified.
+ *
+ * 			*file_offset* is an offset relative to the beginning
+ * 			of the executable or shared object file backing the vma
+ * 			which the *ip* falls in. It is *not* an offset relative
+ * 			to that object's base address. Accordingly, it must be
+ * 			adjusted by adding (sh_addr - sh_offset), where
+ * 			sh_{addr,offset} correspond to the executable section
+ * 			containing *file_offset* in the object, for comparisons
+ * 			to symbols' st_value to be valid.
  *
  * 		**bpf_get_stack**\ () can collect up to
  * 		**PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
@@ -2973,8 +3057,8 @@ union bpf_attr {
  *
  * 			# sysctl kernel.perf_event_max_stack=<new value>
  * 	Return
- * 		A non-negative value equal to or less than *size* on success,
- * 		or a negative error in case of failure.
+ * 		The non-negative copied *buf* length equal to or less than
+ * 		*size* on success, or a negative error in case of failure.
  *
  * long bpf_skb_load_bytes_relative(const void *skb, u32 offset, void *to, u32 len, u32 start_header)
  * 	Description
@@ -3238,6 +3322,9 @@ union bpf_attr {
  * 		The id is returned or 0 in case the id could not be retrieved.
  *
  * u64 bpf_get_current_cgroup_id(void)
+ * 	Description
+ * 		Get the current cgroup id based on the cgroup within which
+ * 		the current task is running.
  * 	Return
  * 		A 64-bit integer containing the current cgroup id based
  * 		on the cgroup within which the current task is running.
@@ -3548,10 +3635,11 @@ union bpf_attr {
  *
  * 		*iph* points to the start of the IPv4 or IPv6 header, while
  * 		*iph_len* contains **sizeof**\ (**struct iphdr**) or
- * 		**sizeof**\ (**struct ip6hdr**).
+ * 		**sizeof**\ (**struct ipv6hdr**).
  *
  * 		*th* points to the start of the TCP header, while *th_len*
- * 		contains **sizeof**\ (**struct tcphdr**).
+ *		contains the length of the TCP header (at least
+ *		**sizeof**\ (**struct tcphdr**)).
  * 	Return
  * 		0 if *iph* and *th* are a valid SYN cookie ACK, or a negative
  * 		error otherwise.
@@ -3734,10 +3822,11 @@ union bpf_attr {
  *
  *		*iph* points to the start of the IPv4 or IPv6 header, while
  *		*iph_len* contains **sizeof**\ (**struct iphdr**) or
- *		**sizeof**\ (**struct ip6hdr**).
+ *		**sizeof**\ (**struct ipv6hdr**).
  *
  *		*th* points to the start of the TCP header, while *th_len*
- *		contains the length of the TCP header.
+ *		contains the length of the TCP header with options (at least
+ *		**sizeof**\ (**struct tcphdr**)).
  *	Return
  *		On success, lower 32 bits hold the generated SYN cookie in
  *		followed by 16 bits which hold the MSS value for that cookie,
@@ -4277,8 +4366,8 @@ union bpf_attr {
  *
  *			# sysctl kernel.perf_event_max_stack=<new value>
  *	Return
- *		A non-negative value equal to or less than *size* on success,
- *		or a negative error in case of failure.
+ * 		The non-negative copied *buf* length equal to or less than
+ * 		*size* on success, or a negative error in case of failure.
  *
  * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags)
  *	Description
@@ -4371,7 +4460,7 @@ union bpf_attr {
  *
  *		**-EEXIST** if the option already exists.
  *
- *		**-EFAULT** on failrue to parse the existing header options.
+ *		**-EFAULT** on failure to parse the existing header options.
  *
  *		**-EPERM** if the helper cannot be used under the current
  *		*skops*\ **->op**.
@@ -4580,7 +4669,7 @@ union bpf_attr {
  *		a *map* with *task* as the **key**.  From this
  *		perspective,  the usage is not much different from
  *		**bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this
- *		helper enforces the key must be an task_struct and the map must also
+ *		helper enforces the key must be a task_struct and the map must also
  *		be a **BPF_MAP_TYPE_TASK_STORAGE**.
  *
  *		Underneath, the value is stored locally at *task* instead of
@@ -4638,7 +4727,7 @@ union bpf_attr {
  *
  * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size)
  *	Description
- *		Returns the stored IMA hash of the *inode* (if it's avaialable).
+ *		Returns the stored IMA hash of the *inode* (if it's available).
  *		If the hash is larger than *size*, then only *size*
  *		bytes will be copied to *dst*
  *	Return
@@ -4662,12 +4751,12 @@ union bpf_attr {
  *
  *		The argument *len_diff* can be used for querying with a planned
  *		size change. This allows to check MTU prior to changing packet
- *		ctx. Providing an *len_diff* adjustment that is larger than the
+ *		ctx. Providing a *len_diff* adjustment that is larger than the
  *		actual packet size (resulting in negative packet size) will in
- *		principle not exceed the MTU, why it is not considered a
- *		failure.  Other BPF-helpers are needed for performing the
- *		planned size change, why the responsability for catch a negative
- *		packet size belong in those helpers.
+ *		principle not exceed the MTU, which is why it is not considered
+ *		a failure.  Other BPF helpers are needed for performing the
+ *		planned size change; therefore the responsibility for catching
+ *		a negative packet size belongs in those helpers.
  *
  *		Specifying *ifindex* zero means the MTU check is performed
  *		against the current net device.  This is practical if this isn't
@@ -4865,6 +4954,7 @@ union bpf_attr {
  * 		Get address of the traced function (for tracing and kprobe programs).
  * 	Return
  * 		Address of the traced function.
+ * 		0 for kprobes placed within the function (not at the entry).
  *
  * u64 bpf_get_attach_cookie(void *ctx)
  * 	Description
@@ -4938,6 +5028,407 @@ union bpf_attr {
  *		**-ENOENT** if symbol is not found.
  *
  *		**-EPERM** if caller does not have permission to obtain kernel address.
+ *
+ * long bpf_find_vma(struct task_struct *task, u64 addr, void *callback_fn, void *callback_ctx, u64 flags)
+ *	Description
+ *		Find vma of *task* that contains *addr*, call *callback_fn*
+ *		function with *task*, *vma*, and *callback_ctx*.
+ *		The *callback_fn* should be a static function and
+ *		the *callback_ctx* should be a pointer to the stack.
+ *		The *flags* is used to control certain aspects of the helper.
+ *		Currently, the *flags* must be 0.
+ *
+ *		The expected callback signature is
+ *
+ *		long (\*callback_fn)(struct task_struct \*task, struct vm_area_struct \*vma, void \*callback_ctx);
+ *
+ *	Return
+ *		0 on success.
+ *		**-ENOENT** if *task->mm* is NULL, or no vma contains *addr*.
+ *		**-EBUSY** if failed to try lock mmap_lock.
+ *		**-EINVAL** for invalid **flags**.
+ *
+ * long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags)
+ *	Description
+ *		For **nr_loops**, call **callback_fn** function
+ *		with **callback_ctx** as the context parameter.
+ *		The **callback_fn** should be a static function and
+ *		the **callback_ctx** should be a pointer to the stack.
+ *		The **flags** is used to control certain aspects of the helper.
+ *		Currently, the **flags** must be 0. Currently, nr_loops is
+ *		limited to 1 << 23 (~8 million) loops.
+ *
+ *		long (\*callback_fn)(u32 index, void \*ctx);
+ *
+ *		where **index** is the current index in the loop. The index
+ *		is zero-indexed.
+ *
+ *		If **callback_fn** returns 0, the helper will continue to the next
+ *		loop. If return value is 1, the helper will skip the rest of
+ *		the loops and return. Other return values are not used now,
+ *		and will be rejected by the verifier.
+ *
+ *	Return
+ *		The number of loops performed, **-EINVAL** for invalid **flags**,
+ *		**-E2BIG** if **nr_loops** exceeds the maximum number of loops.
+ *
+ * long bpf_strncmp(const char *s1, u32 s1_sz, const char *s2)
+ *	Description
+ *		Do strncmp() between **s1** and **s2**. **s1** doesn't need
+ *		to be null-terminated and **s1_sz** is the maximum storage
+ *		size of **s1**. **s2** must be a read-only string.
+ *	Return
+ *		An integer less than, equal to, or greater than zero
+ *		if the first **s1_sz** bytes of **s1** is found to be
+ *		less than, to match, or be greater than **s2**.
+ *
+ * long bpf_get_func_arg(void *ctx, u32 n, u64 *value)
+ *	Description
+ *		Get **n**-th argument register (zero based) of the traced function (for tracing programs)
+ *		returned in **value**.
+ *
+ *	Return
+ *		0 on success.
+ *		**-EINVAL** if n >= argument register count of traced function.
+ *
+ * long bpf_get_func_ret(void *ctx, u64 *value)
+ *	Description
+ *		Get return value of the traced function (for tracing programs)
+ *		in **value**.
+ *
+ *	Return
+ *		0 on success.
+ *		**-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN.
+ *
+ * long bpf_get_func_arg_cnt(void *ctx)
+ *	Description
+ *		Get number of registers of the traced function (for tracing programs) where
+ *		function arguments are stored in these registers.
+ *
+ *	Return
+ *		The number of argument registers of the traced function.
+ *
+ * int bpf_get_retval(void)
+ *	Description
+ *		Get the BPF program's return value that will be returned to the upper layers.
+ *
+ *		This helper is currently supported by cgroup programs and only by the hooks
+ *		where BPF program's return value is returned to the userspace via errno.
+ *	Return
+ *		The BPF program's return value.
+ *
+ * int bpf_set_retval(int retval)
+ *	Description
+ *		Set the BPF program's return value that will be returned to the upper layers.
+ *
+ *		This helper is currently supported by cgroup programs and only by the hooks
+ *		where BPF program's return value is returned to the userspace via errno.
+ *
+ *		Note that there is the following corner case where the program exports an error
+ *		via bpf_set_retval but signals success via 'return 1':
+ *
+ *			bpf_set_retval(-EPERM);
+ *			return 1;
+ *
+ *		In this case, the BPF program's return value will use helper's -EPERM. This
+ *		still holds true for cgroup/bind{4,6} which supports extra 'return 3' success case.
+ *
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md)
+ *	Description
+ *		Get the total size of a given xdp buff (linear and paged area)
+ *	Return
+ *		The total size of a given xdp buffer.
+ *
+ * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len)
+ *	Description
+ *		This helper is provided as an easy way to load data from a
+ *		xdp buffer. It can be used to load *len* bytes from *offset* from
+ *		the frame associated to *xdp_md*, into the buffer pointed by
+ *		*buf*.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len)
+ *	Description
+ *		Store *len* bytes from buffer *buf* into the frame
+ *		associated to *xdp_md*, at *offset*.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * long bpf_copy_from_user_task(void *dst, u32 size, const void *user_ptr, struct task_struct *tsk, u64 flags)
+ *	Description
+ *		Read *size* bytes from user space address *user_ptr* in *tsk*'s
+ *		address space, and stores the data in *dst*. *flags* is not
+ *		used yet and is provided for future extensibility. This helper
+ *		can only be used by sleepable programs.
+ *	Return
+ *		0 on success, or a negative error in case of failure. On error
+ *		*dst* buffer is zeroed out.
+ *
+ * long bpf_skb_set_tstamp(struct sk_buff *skb, u64 tstamp, u32 tstamp_type)
+ *	Description
+ *		Change the __sk_buff->tstamp_type to *tstamp_type*
+ *		and set *tstamp* to the __sk_buff->tstamp together.
+ *
+ *		If there is no need to change the __sk_buff->tstamp_type,
+ *		the tstamp value can be directly written to __sk_buff->tstamp
+ *		instead.
+ *
+ *		BPF_SKB_TSTAMP_DELIVERY_MONO is the only tstamp that
+ *		will be kept during bpf_redirect_*().  A non zero
+ *		*tstamp* must be used with the BPF_SKB_TSTAMP_DELIVERY_MONO
+ *		*tstamp_type*.
+ *
+ *		A BPF_SKB_TSTAMP_UNSPEC *tstamp_type* can only be used
+ *		with a zero *tstamp*.
+ *
+ *		Only IPv4 and IPv6 skb->protocol are supported.
+ *
+ *		This function is most useful when it needs to set a
+ *		mono delivery time to __sk_buff->tstamp and then
+ *		bpf_redirect_*() to the egress of an iface.  For example,
+ *		changing the (rcv) timestamp in __sk_buff->tstamp at
+ *		ingress to a mono delivery time and then bpf_redirect_*()
+ *		to sch_fq@phy-dev.
+ *	Return
+ *		0 on success.
+ *		**-EINVAL** for invalid input
+ *		**-EOPNOTSUPP** for unsupported protocol
+ *
+ * long bpf_ima_file_hash(struct file *file, void *dst, u32 size)
+ *	Description
+ *		Returns a calculated IMA hash of the *file*.
+ *		If the hash is larger than *size*, then only *size*
+ *		bytes will be copied to *dst*
+ *	Return
+ *		The **hash_algo** is returned on success,
+ *		**-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if
+ *		invalid arguments are passed.
+ *
+ * void *bpf_kptr_xchg(void *map_value, void *ptr)
+ *	Description
+ *		Exchange kptr at pointer *map_value* with *ptr*, and return the
+ *		old value. *ptr* can be NULL, otherwise it must be a referenced
+ *		pointer which will be released when this helper is called.
+ *	Return
+ *		The old value of kptr (which can be NULL). The returned pointer
+ *		if not NULL, is a reference which must be released using its
+ *		corresponding release function, or moved into a BPF map before
+ *		program exit.
+ *
+ * void *bpf_map_lookup_percpu_elem(struct bpf_map *map, const void *key, u32 cpu)
+ * 	Description
+ * 		Perform a lookup in *percpu map* for an entry associated to
+ * 		*key* on *cpu*.
+ * 	Return
+ * 		Map value associated to *key* on *cpu*, or **NULL** if no entry
+ * 		was found or *cpu* is invalid.
+ *
+ * struct mptcp_sock *bpf_skc_to_mptcp_sock(void *sk)
+ *	Description
+ *		Dynamically cast a *sk* pointer to a *mptcp_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or **NULL** otherwise.
+ *
+ * long bpf_dynptr_from_mem(void *data, u32 size, u64 flags, struct bpf_dynptr *ptr)
+ *	Description
+ *		Get a dynptr to local memory *data*.
+ *
+ *		*data* must be a ptr to a map value.
+ *		The maximum *size* supported is DYNPTR_MAX_SIZE.
+ *		*flags* is currently unused.
+ *	Return
+ *		0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE,
+ *		-EINVAL if flags is not 0.
+ *
+ * long bpf_ringbuf_reserve_dynptr(void *ringbuf, u32 size, u64 flags, struct bpf_dynptr *ptr)
+ *	Description
+ *		Reserve *size* bytes of payload in a ring buffer *ringbuf*
+ *		through the dynptr interface. *flags* must be 0.
+ *
+ *		Please note that a corresponding bpf_ringbuf_submit_dynptr or
+ *		bpf_ringbuf_discard_dynptr must be called on *ptr*, even if the
+ *		reservation fails. This is enforced by the verifier.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * void bpf_ringbuf_submit_dynptr(struct bpf_dynptr *ptr, u64 flags)
+ *	Description
+ *		Submit reserved ring buffer sample, pointed to by *data*,
+ *		through the dynptr interface. This is a no-op if the dynptr is
+ *		invalid/null.
+ *
+ *		For more information on *flags*, please see
+ *		'bpf_ringbuf_submit'.
+ *	Return
+ *		Nothing. Always succeeds.
+ *
+ * void bpf_ringbuf_discard_dynptr(struct bpf_dynptr *ptr, u64 flags)
+ *	Description
+ *		Discard reserved ring buffer sample through the dynptr
+ *		interface. This is a no-op if the dynptr is invalid/null.
+ *
+ *		For more information on *flags*, please see
+ *		'bpf_ringbuf_discard'.
+ *	Return
+ *		Nothing. Always succeeds.
+ *
+ * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset, u64 flags)
+ *	Description
+ *		Read *len* bytes from *src* into *dst*, starting from *offset*
+ *		into *src*.
+ *		*flags* is currently unused.
+ *	Return
+ *		0 on success, -E2BIG if *offset* + *len* exceeds the length
+ *		of *src*'s data, -EINVAL if *src* is an invalid dynptr or if
+ *		*flags* is not 0.
+ *
+ * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags)
+ *	Description
+ *		Write *len* bytes from *src* into *dst*, starting from *offset*
+ *		into *dst*.
+ *		*flags* is currently unused.
+ *	Return
+ *		0 on success, -E2BIG if *offset* + *len* exceeds the length
+ *		of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst*
+ *		is a read-only dynptr or if *flags* is not 0.
+ *
+ * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len)
+ *	Description
+ *		Get a pointer to the underlying dynptr data.
+ *
+ *		*len* must be a statically known value. The returned data slice
+ *		is invalidated whenever the dynptr is invalidated.
+ *	Return
+ *		Pointer to the underlying dynptr data, NULL if the dynptr is
+ *		read-only, if the dynptr is invalid, or if the offset and length
+ *		is out of bounds.
+ *
+ * s64 bpf_tcp_raw_gen_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th, u32 th_len)
+ *	Description
+ *		Try to issue a SYN cookie for the packet with corresponding
+ *		IPv4/TCP headers, *iph* and *th*, without depending on a
+ *		listening socket.
+ *
+ *		*iph* points to the IPv4 header.
+ *
+ *		*th* points to the start of the TCP header, while *th_len*
+ *		contains the length of the TCP header (at least
+ *		**sizeof**\ (**struct tcphdr**)).
+ *	Return
+ *		On success, lower 32 bits hold the generated SYN cookie in
+ *		followed by 16 bits which hold the MSS value for that cookie,
+ *		and the top 16 bits are unused.
+ *
+ *		On failure, the returned value is one of the following:
+ *
+ *		**-EINVAL** if *th_len* is invalid.
+ *
+ * s64 bpf_tcp_raw_gen_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th, u32 th_len)
+ *	Description
+ *		Try to issue a SYN cookie for the packet with corresponding
+ *		IPv6/TCP headers, *iph* and *th*, without depending on a
+ *		listening socket.
+ *
+ *		*iph* points to the IPv6 header.
+ *
+ *		*th* points to the start of the TCP header, while *th_len*
+ *		contains the length of the TCP header (at least
+ *		**sizeof**\ (**struct tcphdr**)).
+ *	Return
+ *		On success, lower 32 bits hold the generated SYN cookie in
+ *		followed by 16 bits which hold the MSS value for that cookie,
+ *		and the top 16 bits are unused.
+ *
+ *		On failure, the returned value is one of the following:
+ *
+ *		**-EINVAL** if *th_len* is invalid.
+ *
+ *		**-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
+ *
+ * long bpf_tcp_raw_check_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th)
+ *	Description
+ *		Check whether *iph* and *th* contain a valid SYN cookie ACK
+ *		without depending on a listening socket.
+ *
+ *		*iph* points to the IPv4 header.
+ *
+ *		*th* points to the TCP header.
+ *	Return
+ *		0 if *iph* and *th* are a valid SYN cookie ACK.
+ *
+ *		On failure, the returned value is one of the following:
+ *
+ *		**-EACCES** if the SYN cookie is not valid.
+ *
+ * long bpf_tcp_raw_check_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th)
+ *	Description
+ *		Check whether *iph* and *th* contain a valid SYN cookie ACK
+ *		without depending on a listening socket.
+ *
+ *		*iph* points to the IPv6 header.
+ *
+ *		*th* points to the TCP header.
+ *	Return
+ *		0 if *iph* and *th* are a valid SYN cookie ACK.
+ *
+ *		On failure, the returned value is one of the following:
+ *
+ *		**-EACCES** if the SYN cookie is not valid.
+ *
+ *		**-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
+ *
+ * u64 bpf_ktime_get_tai_ns(void)
+ *	Description
+ *		A nonsettable system-wide clock derived from wall-clock time but
+ *		ignoring leap seconds.  This clock does not experience
+ *		discontinuities and backwards jumps caused by NTP inserting leap
+ *		seconds as CLOCK_REALTIME does.
+ *
+ *		See: **clock_gettime**\ (**CLOCK_TAI**)
+ *	Return
+ *		Current *ktime*.
+ *
+ * long bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void *ctx, u64 flags)
+ *	Description
+ *		Drain samples from the specified user ring buffer, and invoke
+ *		the provided callback for each such sample:
+ *
+ *		long (\*callback_fn)(struct bpf_dynptr \*dynptr, void \*ctx);
+ *
+ *		If **callback_fn** returns 0, the helper will continue to try
+ *		and drain the next sample, up to a maximum of
+ *		BPF_MAX_USER_RINGBUF_SAMPLES samples. If the return value is 1,
+ *		the helper will skip the rest of the samples and return. Other
+ *		return values are not used now, and will be rejected by the
+ *		verifier.
+ *	Return
+ *		The number of drained samples if no error was encountered while
+ *		draining samples, or 0 if no samples were present in the ring
+ *		buffer. If a user-space producer was epoll-waiting on this map,
+ *		and at least one sample was drained, they will receive an event
+ *		notification notifying them of available space in the ring
+ *		buffer. If the BPF_RB_NO_WAKEUP flag is passed to this
+ *		function, no wakeup notification will be sent. If the
+ *		BPF_RB_FORCE_WAKEUP flag is passed, a wakeup notification will
+ *		be sent even if no sample was drained.
+ *
+ *		On failure, the returned value is one of the following:
+ *
+ *		**-EBUSY** if the ring buffer is contended, and another calling
+ *		context was concurrently draining the ring buffer.
+ *
+ *		**-EINVAL** if user-space is not properly tracking the ring
+ *		buffer due to the producer position not being aligned to 8
+ *		bytes, a sample not being aligned to 8 bytes, or the producer
+ *		position not matching the advertised length of a sample.
+ *
+ *		**-E2BIG** if user-space has tried to publish a sample which is
+ *		larger than the size of the ring buffer, or which cannot fit
+ *		within a struct bpf_dynptr.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5120,6 +5611,36 @@ union bpf_attr {
 	FN(trace_vprintk),		\
 	FN(skc_to_unix_sock),		\
 	FN(kallsyms_lookup_name),	\
+	FN(find_vma),			\
+	FN(loop),			\
+	FN(strncmp),			\
+	FN(get_func_arg),		\
+	FN(get_func_ret),		\
+	FN(get_func_arg_cnt),		\
+	FN(get_retval),			\
+	FN(set_retval),			\
+	FN(xdp_get_buff_len),		\
+	FN(xdp_load_bytes),		\
+	FN(xdp_store_bytes),		\
+	FN(copy_from_user_task),	\
+	FN(skb_set_tstamp),		\
+	FN(ima_file_hash),		\
+	FN(kptr_xchg),			\
+	FN(map_lookup_percpu_elem),     \
+	FN(skc_to_mptcp_sock),		\
+	FN(dynptr_from_mem),		\
+	FN(ringbuf_reserve_dynptr),	\
+	FN(ringbuf_submit_dynptr),	\
+	FN(ringbuf_discard_dynptr),	\
+	FN(dynptr_read),		\
+	FN(dynptr_write),		\
+	FN(dynptr_data),		\
+	FN(tcp_raw_gen_syncookie_ipv4),	\
+	FN(tcp_raw_gen_syncookie_ipv6),	\
+	FN(tcp_raw_check_syncookie_ipv4),	\
+	FN(tcp_raw_check_syncookie_ipv6),	\
+	FN(ktime_get_tai_ns),		\
+	FN(user_ringbuf_drain),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -5182,6 +5703,11 @@ enum {
 	BPF_F_SEQ_NUMBER		= (1ULL << 3),
 };
 
+/* BPF_FUNC_skb_get_tunnel_key flags. */
+enum {
+	BPF_F_TUNINFO_FLAGS		= (1ULL << 4),
+};
+
 /* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
  * BPF_FUNC_perf_event_read_value flags.
  */
@@ -5309,6 +5835,15 @@ union {					\
 	__u64 :64;			\
 } __attribute__((aligned(8)))
 
+enum {
+	BPF_SKB_TSTAMP_UNSPEC,
+	BPF_SKB_TSTAMP_DELIVERY_MONO,	/* tstamp has mono delivery time */
+	/* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle,
+	 * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC
+	 * and try to deduce it by ingress, egress or skb->sk->sk_clockid.
+	 */
+};
+
 /* user accessible mirror of in-kernel sk_buff.
  * new fields can only be added to the end of this structure
  */
@@ -5349,7 +5884,8 @@ struct __sk_buff {
 	__u32 gso_segs;
 	__bpf_md_ptr(struct bpf_sock *, sk);
 	__u32 gso_size;
-	__u32 :32;		/* Padding, future use. */
+	__u8  tstamp_type;
+	__u32 :24;		/* Padding, future use. */
 	__u64 hwtstamp;
 };
 
@@ -5361,8 +5897,15 @@ struct bpf_tunnel_key {
 	};
 	__u8 tunnel_tos;
 	__u8 tunnel_ttl;
-	__u16 tunnel_ext;	/* Padding, future use. */
+	union {
+		__u16 tunnel_ext;	/* compat */
+		__be16 tunnel_flags;
+	};
 	__u32 tunnel_label;
+	union {
+		__u32 local_ipv4;
+		__u32 local_ipv6[4];
+	};
 };
 
 /* user accessible mirror of in-kernel xfrm_state.
@@ -5401,6 +5944,11 @@ enum bpf_ret_code {
 	 *    represented by BPF_REDIRECT above).
 	 */
 	BPF_LWT_REROUTE = 128,
+	/* BPF_FLOW_DISSECTOR_CONTINUE: used by BPF_PROG_TYPE_FLOW_DISSECTOR
+	 *   to indicate that no custom dissection was performed, and
+	 *   fallback to standard dissector is requested.
+	 */
+	BPF_FLOW_DISSECTOR_CONTINUE = 129,
 };
 
 struct bpf_sock {
@@ -5414,7 +5962,8 @@ struct bpf_sock {
 	__u32 src_ip4;
 	__u32 src_ip6[4];
 	__u32 src_port;		/* host byte order */
-	__u32 dst_port;		/* network byte order */
+	__be16 dst_port;	/* network byte order */
+	__u16 :16;		/* zero padding */
 	__u32 dst_ip4;
 	__u32 dst_ip6[4];
 	__u32 state;
@@ -5645,6 +6194,8 @@ struct bpf_prog_info {
 	__u64 run_cnt;
 	__u64 recursion_misses;
 	__u32 verified_insns;
+	__u32 attach_btf_obj_id;
+	__u32 attach_btf_id;
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
@@ -5696,11 +6247,22 @@ struct bpf_link_info {
 		struct {
 			__aligned_u64 target_name; /* in/out: target_name buffer ptr */
 			__u32 target_name_len;	   /* in/out: target_name buffer len */
+
+			/* If the iter specific field is 32 bits, it can be put
+			 * in the first or second union. Otherwise it should be
+			 * put in the second union.
+			 */
 			union {
 				struct {
 					__u32 map_id;
 				} map;
 			};
+			union {
+				struct {
+					__u64 cgroup_id;
+					__u32 order;
+				} cgroup;
+			};
 		} iter;
 		struct  {
 			__u32 netns_ino;
@@ -6256,6 +6818,11 @@ struct bpf_timer {
 	__u64 :64;
 } __attribute__((aligned(8)));
 
+struct bpf_dynptr {
+	__u64 :64;
+	__u64 :64;
+} __attribute__((aligned(8)));
+
 struct bpf_sysctl {
 	__u32	write;		/* Sysctl is being read (= 0) or written (= 1).
 				 * Allows 1,2,4-byte read, but no write.
@@ -6292,10 +6859,12 @@ struct bpf_sk_lookup {
 	__u32 protocol;		/* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */
 	__u32 remote_ip4;	/* Network byte order */
 	__u32 remote_ip6[4];	/* Network byte order */
-	__u32 remote_port;	/* Network byte order */
+	__be16 remote_port;	/* Network byte order */
+	__u16 :16;		/* Zero padding */
 	__u32 local_ip4;	/* Network byte order */
 	__u32 local_ip6[4];	/* Network byte order */
 	__u32 local_port;	/* Host byte order */
+	__u32 ingress_ifindex;		/* The arriving interface. Determined by inet_iif. */
 };
 
 /*
@@ -6328,4 +6897,79 @@ enum {
 	BTF_F_ZERO	=	(1ULL << 3),
 };
 
+/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value
+ * has to be adjusted by relocations. It is emitted by llvm and passed to
+ * libbpf and later to the kernel.
+ */
+enum bpf_core_relo_kind {
+	BPF_CORE_FIELD_BYTE_OFFSET = 0,      /* field byte offset */
+	BPF_CORE_FIELD_BYTE_SIZE = 1,        /* field size in bytes */
+	BPF_CORE_FIELD_EXISTS = 2,           /* field existence in target kernel */
+	BPF_CORE_FIELD_SIGNED = 3,           /* field signedness (0 - unsigned, 1 - signed) */
+	BPF_CORE_FIELD_LSHIFT_U64 = 4,       /* bitfield-specific left bitshift */
+	BPF_CORE_FIELD_RSHIFT_U64 = 5,       /* bitfield-specific right bitshift */
+	BPF_CORE_TYPE_ID_LOCAL = 6,          /* type ID in local BPF object */
+	BPF_CORE_TYPE_ID_TARGET = 7,         /* type ID in target kernel */
+	BPF_CORE_TYPE_EXISTS = 8,            /* type existence in target kernel */
+	BPF_CORE_TYPE_SIZE = 9,              /* type size in bytes */
+	BPF_CORE_ENUMVAL_EXISTS = 10,        /* enum value existence in target kernel */
+	BPF_CORE_ENUMVAL_VALUE = 11,         /* enum value integer value */
+	BPF_CORE_TYPE_MATCHES = 12,          /* type match in target kernel */
+};
+
+/*
+ * "struct bpf_core_relo" is used to pass relocation data form LLVM to libbpf
+ * and from libbpf to the kernel.
+ *
+ * CO-RE relocation captures the following data:
+ * - insn_off - instruction offset (in bytes) within a BPF program that needs
+ *   its insn->imm field to be relocated with actual field info;
+ * - type_id - BTF type ID of the "root" (containing) entity of a relocatable
+ *   type or field;
+ * - access_str_off - offset into corresponding .BTF string section. String
+ *   interpretation depends on specific relocation kind:
+ *     - for field-based relocations, string encodes an accessed field using
+ *       a sequence of field and array indices, separated by colon (:). It's
+ *       conceptually very close to LLVM's getelementptr ([0]) instruction's
+ *       arguments for identifying offset to a field.
+ *     - for type-based relocations, strings is expected to be just "0";
+ *     - for enum value-based relocations, string contains an index of enum
+ *       value within its enum type;
+ * - kind - one of enum bpf_core_relo_kind;
+ *
+ * Example:
+ *   struct sample {
+ *       int a;
+ *       struct {
+ *           int b[10];
+ *       };
+ *   };
+ *
+ *   struct sample *s = ...;
+ *   int *x = &s->a;     // encoded as "0:0" (a is field #0)
+ *   int *y = &s->b[5];  // encoded as "0:1:0:5" (anon struct is field #1,
+ *                       // b is field #0 inside anon struct, accessing elem #5)
+ *   int *z = &s[10]->b; // encoded as "10:1" (ptr is used as an array)
+ *
+ * type_id for all relocs in this example will capture BTF type id of
+ * `struct sample`.
+ *
+ * Such relocation is emitted when using __builtin_preserve_access_index()
+ * Clang built-in, passing expression that captures field address, e.g.:
+ *
+ * bpf_probe_read(&dst, sizeof(dst),
+ *		  __builtin_preserve_access_index(&src->a.b.c));
+ *
+ * In this case Clang will emit field relocation recording necessary data to
+ * be able to find offset of embedded `a.b.c` field within `src` struct.
+ *
+ * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction
+ */
+struct bpf_core_relo {
+	__u32 insn_off;
+	__u32 type_id;
+	__u32 access_str_off;
+	enum bpf_core_relo_kind kind;
+};
+
 #endif /* _UAPI__LINUX_BPF_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/if_link.h

@@ -7,24 +7,23 @@
 
 /* This struct should be in sync with struct rtnl_link_stats64 */
 struct rtnl_link_stats {
-	__u32	rx_packets;		/* total packets received	*/
-	__u32	tx_packets;		/* total packets transmitted	*/
-	__u32	rx_bytes;		/* total bytes received 	*/
-	__u32	tx_bytes;		/* total bytes transmitted	*/
-	__u32	rx_errors;		/* bad packets received		*/
-	__u32	tx_errors;		/* packet transmit problems	*/
-	__u32	rx_dropped;		/* no space in linux buffers	*/
-	__u32	tx_dropped;		/* no space available in linux	*/
-	__u32	multicast;		/* multicast packets received	*/
+	__u32	rx_packets;
+	__u32	tx_packets;
+	__u32	rx_bytes;
+	__u32	tx_bytes;
+	__u32	rx_errors;
+	__u32	tx_errors;
+	__u32	rx_dropped;
+	__u32	tx_dropped;
+	__u32	multicast;
 	__u32	collisions;
-
 	/* detailed rx_errors: */
 	__u32	rx_length_errors;
-	__u32	rx_over_errors;		/* receiver ring buff overflow	*/
-	__u32	rx_crc_errors;		/* recved pkt with crc error	*/
-	__u32	rx_frame_errors;	/* recv'd frame alignment error */
-	__u32	rx_fifo_errors;		/* recv'r fifo overrun		*/
-	__u32	rx_missed_errors;	/* receiver missed packet	*/
+	__u32	rx_over_errors;
+	__u32	rx_crc_errors;
+	__u32	rx_frame_errors;
+	__u32	rx_fifo_errors;
+	__u32	rx_missed_errors;
 
 	/* detailed tx_errors */
 	__u32	tx_aborted_errors;
@@ -37,29 +36,201 @@ struct rtnl_link_stats {
 	__u32	rx_compressed;
 	__u32	tx_compressed;
 
-	__u32	rx_nohandler;		/* dropped, no handler found	*/
+	__u32	rx_nohandler;
 };
 
-/* The main device statistics structure */
+/**
+ * struct rtnl_link_stats64 - The main device statistics structure.
+ *
+ * @rx_packets: Number of good packets received by the interface.
+ *   For hardware interfaces counts all good packets received from the device
+ *   by the host, including packets which host had to drop at various stages
+ *   of processing (even in the driver).
+ *
+ * @tx_packets: Number of packets successfully transmitted.
+ *   For hardware interfaces counts packets which host was able to successfully
+ *   hand over to the device, which does not necessarily mean that packets
+ *   had been successfully transmitted out of the device, only that device
+ *   acknowledged it copied them out of host memory.
+ *
+ * @rx_bytes: Number of good received bytes, corresponding to @rx_packets.
+ *
+ *   For IEEE 802.3 devices should count the length of Ethernet Frames
+ *   excluding the FCS.
+ *
+ * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets.
+ *
+ *   For IEEE 802.3 devices should count the length of Ethernet Frames
+ *   excluding the FCS.
+ *
+ * @rx_errors: Total number of bad packets received on this network device.
+ *   This counter must include events counted by @rx_length_errors,
+ *   @rx_crc_errors, @rx_frame_errors and other errors not otherwise
+ *   counted.
+ *
+ * @tx_errors: Total number of transmit problems.
+ *   This counter must include events counter by @tx_aborted_errors,
+ *   @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors,
+ *   @tx_window_errors and other errors not otherwise counted.
+ *
+ * @rx_dropped: Number of packets received but not processed,
+ *   e.g. due to lack of resources or unsupported protocol.
+ *   For hardware interfaces this counter may include packets discarded
+ *   due to L2 address filtering but should not include packets dropped
+ *   by the device due to buffer exhaustion which are counted separately in
+ *   @rx_missed_errors (since procfs folds those two counters together).
+ *
+ * @tx_dropped: Number of packets dropped on their way to transmission,
+ *   e.g. due to lack of resources.
+ *
+ * @multicast: Multicast packets received.
+ *   For hardware interfaces this statistic is commonly calculated
+ *   at the device level (unlike @rx_packets) and therefore may include
+ *   packets which did not reach the host.
+ *
+ *   For IEEE 802.3 devices this counter may be equivalent to:
+ *
+ *    - 30.3.1.1.21 aMulticastFramesReceivedOK
+ *
+ * @collisions: Number of collisions during packet transmissions.
+ *
+ * @rx_length_errors: Number of packets dropped due to invalid length.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter should be equivalent to a sum
+ *   of the following attributes:
+ *
+ *    - 30.3.1.1.23 aInRangeLengthErrors
+ *    - 30.3.1.1.24 aOutOfRangeLengthField
+ *    - 30.3.1.1.25 aFrameTooLongErrors
+ *
+ * @rx_over_errors: Receiver FIFO overflow event counter.
+ *
+ *   Historically the count of overflow events. Such events may be
+ *   reported in the receive descriptors or via interrupts, and may
+ *   not correspond one-to-one with dropped packets.
+ *
+ *   The recommended interpretation for high speed interfaces is -
+ *   number of packets dropped because they did not fit into buffers
+ *   provided by the host, e.g. packets larger than MTU or next buffer
+ *   in the ring was not available for a scatter transfer.
+ *
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   This statistics was historically used interchangeably with
+ *   @rx_fifo_errors.
+ *
+ *   This statistic corresponds to hardware events and is not commonly used
+ *   on software devices.
+ *
+ * @rx_crc_errors: Number of packets received with a CRC error.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.6 aFrameCheckSequenceErrors
+ *
+ * @rx_frame_errors: Receiver frame alignment errors.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter should be equivalent to:
+ *
+ *    - 30.3.1.1.7 aAlignmentErrors
+ *
+ * @rx_fifo_errors: Receiver FIFO error counter.
+ *
+ *   Historically the count of overflow events. Those events may be
+ *   reported in the receive descriptors or via interrupts, and may
+ *   not correspond one-to-one with dropped packets.
+ *
+ *   This statistics was used interchangeably with @rx_over_errors.
+ *   Not recommended for use in drivers for high speed interfaces.
+ *
+ *   This statistic is used on software devices, e.g. to count software
+ *   packet queue overflow (can) or sequencing errors (GRE).
+ *
+ * @rx_missed_errors: Count of packets missed by the host.
+ *   Folded into the "drop" counter in `/proc/net/dev`.
+ *
+ *   Counts number of packets dropped by the device due to lack
+ *   of buffer space. This usually indicates that the host interface
+ *   is slower than the network interface, or host is not keeping up
+ *   with the receive packet rate.
+ *
+ *   This statistic corresponds to hardware events and is not used
+ *   on software devices.
+ *
+ * @tx_aborted_errors:
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *   For IEEE 802.3 devices capable of half-duplex operation this counter
+ *   must be equivalent to:
+ *
+ *    - 30.3.1.1.11 aFramesAbortedDueToXSColls
+ *
+ *   High speed interfaces may use this counter as a general device
+ *   discard counter.
+ *
+ * @tx_carrier_errors: Number of frame transmission errors due to loss
+ *   of carrier during transmission.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.13 aCarrierSenseErrors
+ *
+ * @tx_fifo_errors: Number of frame transmission errors due to device
+ *   FIFO underrun / underflow. This condition occurs when the device
+ *   begins transmission of a frame but is unable to deliver the
+ *   entire frame to the transmitter in time for transmission.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for
+ *   old half-duplex Ethernet.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices possibly equivalent to:
+ *
+ *    - 30.3.2.1.4 aSQETestErrors
+ *
+ * @tx_window_errors: Number of frame transmission errors due
+ *   to late collisions (for Ethernet - after the first 64B of transmission).
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.10 aLateCollisions
+ *
+ * @rx_compressed: Number of correctly received compressed packets.
+ *   This counters is only meaningful for interfaces which support
+ *   packet compression (e.g. CSLIP, PPP).
+ *
+ * @tx_compressed: Number of transmitted compressed packets.
+ *   This counters is only meaningful for interfaces which support
+ *   packet compression (e.g. CSLIP, PPP).
+ *
+ * @rx_nohandler: Number of packets received on the interface
+ *   but dropped by the networking stack because the device is
+ *   not designated to receive packets (e.g. backup link in a bond).
+ */
 struct rtnl_link_stats64 {
-	__u64	rx_packets;		/* total packets received	*/
-	__u64	tx_packets;		/* total packets transmitted	*/
-	__u64	rx_bytes;		/* total bytes received 	*/
-	__u64	tx_bytes;		/* total bytes transmitted	*/
-	__u64	rx_errors;		/* bad packets received		*/
-	__u64	tx_errors;		/* packet transmit problems	*/
-	__u64	rx_dropped;		/* no space in linux buffers	*/
-	__u64	tx_dropped;		/* no space available in linux	*/
-	__u64	multicast;		/* multicast packets received	*/
+	__u64	rx_packets;
+	__u64	tx_packets;
+	__u64	rx_bytes;
+	__u64	tx_bytes;
+	__u64	rx_errors;
+	__u64	tx_errors;
+	__u64	rx_dropped;
+	__u64	tx_dropped;
+	__u64	multicast;
 	__u64	collisions;
 
 	/* detailed rx_errors: */
 	__u64	rx_length_errors;
-	__u64	rx_over_errors;		/* receiver ring buff overflow	*/
-	__u64	rx_crc_errors;		/* recved pkt with crc error	*/
-	__u64	rx_frame_errors;	/* recv'd frame alignment error */
-	__u64	rx_fifo_errors;		/* recv'r fifo overrun		*/
-	__u64	rx_missed_errors;	/* receiver missed packet	*/
+	__u64	rx_over_errors;
+	__u64	rx_crc_errors;
+	__u64	rx_frame_errors;
+	__u64	rx_fifo_errors;
+	__u64	rx_missed_errors;
 
 	/* detailed tx_errors */
 	__u64	tx_aborted_errors;
@@ -71,8 +242,7 @@ struct rtnl_link_stats64 {
 	/* for cslip etc */
 	__u64	rx_compressed;
 	__u64	tx_compressed;
-
-	__u64	rx_nohandler;		/* dropped, no handler found	*/
+	__u64	rx_nohandler;
 };
 
 /* The struct should be in sync with struct ifmap */
@@ -170,12 +340,32 @@ 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_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 +483,7 @@ 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 +537,8 @@ 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_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -433,6 +626,7 @@ enum macvlan_macaddr_mode {
 };
 
 #define MACVLAN_FLAG_NOPROMISC	1
+#define MACVLAN_FLAG_NODST	2 /* skip dst macvlan if matching src macvlan */
 
 /* VRF section */
 enum {
@@ -597,6 +791,18 @@ 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,
@@ -655,6 +861,8 @@ 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_MAX,
 };
 
@@ -682,6 +890,7 @@ 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 +1108,14 @@ 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 +1125,9 @@ 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,
 };
 
@@ -1033,6 +1252,8 @@ 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 +1269,14 @@ struct ifla_rmnet_flags {
 	__u32	mask;
 };
 
+/* MCTP section */
+
+enum {
+	IFLA_MCTP_UNSPEC,
+	IFLA_MCTP_NET,
+	__IFLA_MCTP_MAX,
+};
+
+#define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1)
+
 #endif /* _UAPI_LINUX_IF_LINK_H */

include/uapi/linux/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 */

scripts/build-fuzzers.sh

@@ -0,0 +1,81 @@
+#!/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 git://sourceware.org/git/elfutils.git
+(
+cd elfutils
+git checkout 83251d4091241acddbdcf16f814e3bc6ef3df49a
+git log --oneline -1
+
+# ASan isn't compatible with -Wl,--no-undefined: https://github.com/google/sanitizers/issues/380
+find -name Makefile.am | xargs sed -i 's/,--no-undefined//'
+
+# ASan isn't compatible with -Wl,-z,defs either:
+# https://clang.llvm.org/docs/AddressSanitizer.html#usage
+sed -i 's/^\(ZDEFS_LDFLAGS=\).*/\1/' configure.ac
+
+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 \
+	    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/sync-kernel.sh

@@ -47,6 +47,7 @@ PATH_MAP=(									\
 	[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						\
 )
 
@@ -263,8 +264,11 @@ 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
 

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 := 1
+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 +34,10 @@ 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 $(EXTRA_CFLAGS)
+ALL_LDFLAGS += $(LDFLAGS) $(EXTRA_LDFLAGS)
+
 ifdef NO_PKG_CONFIG
 	ALL_LDFLAGS += -lelf -lz
 else
@@ -35,9 +50,9 @@ 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
 SHARED_OBJS := $(addprefix $(SHARED_OBJDIR)/,$(OBJS))
 STATIC_OBJS := $(addprefix $(STATIC_OBJDIR)/,$(OBJS))
 
@@ -49,9 +64,10 @@ 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)
 
@@ -99,7 +115,7 @@ $(OBJDIR)/libbpf.so.$(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 +168,7 @@ 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 +178,5 @@ tags:
 	$(call msg,CTAGS)
 	$(Q)rm -f TAGS tags
 	$(Q)ls *.c *.h | xargs $(TAGS_PROG) -a
+
+force:

src/bpf.h

@@ -29,92 +29,99 @@
 #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;
+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;
-	};
 };
+#define bpf_map_create_opts__last_field map_ifindex
 
-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;
 };
+#define bpf_prog_load_opts__last_field log_buf
+
+LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type,
+			     const char *prog_name, const char *license,
+			     const struct bpf_insn *insns, size_t insn_cnt,
+			     const struct bpf_prog_load_opts *opts);
 
 /* 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;
+};
+#define bpf_btf_load_opts__last_field log_size
+
+LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size,
+			    const struct bpf_btf_load_opts *opts);
 
 LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value,
 				   __u64 flags);
@@ -127,6 +134,7 @@ 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);
 
@@ -137,22 +145,144 @@ 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.
+ *
+ * The *keys* and *values* are output parameters which must point to memory large enough to
+ * hold *count* items based on the key and value size of the map *map_fd*. The *keys*
+ * buffer must be of *key_size* * *count*. The *values* buffer must be of
+ * *value_size* * *count*.
+ *
+ * @param fd BPF map file descriptor
+ * @param in_batch address of the first element in batch to read, can pass NULL to
+ * indicate that the batched lookup starts from the beginning of the map.
+ * @param out_batch output parameter that should be passed to next call as *in_batch*
+ * @param keys pointer to an array large enough for *count* keys
+ * @param values pointer to an array large enough for *count* values
+ * @param count input and output parameter; on input it's the number of elements
+ * in the map to read in batch; on output it's the number of elements that were
+ * successfully read.
+ * If a non-EFAULT error is returned, count will be set as the number of elements
+ * that were read before the error occurred.
+ * If EFAULT is returned, **count** should not be trusted to be correct.
+ * @param opts options for configuring the way the batch lookup works
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
 LIBBPF_API int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch,
 				    void *keys, void *values, __u32 *count,
 				    const struct bpf_map_batch_opts *opts);
+
+/**
+ * @brief **bpf_map_lookup_and_delete_batch()** allows for batch lookup and deletion
+ * of BPF map elements where each element is deleted after being retrieved.
+ *
+ * @param fd BPF map file descriptor
+ * @param in_batch address of the first element in batch to read, can pass NULL to
+ * get address of the first element in *out_batch*
+ * @param out_batch output parameter that should be passed to next call as *in_batch*
+ * @param keys pointer to an array of *count* keys
+ * @param values pointer to an array large enough for *count* values
+ * @param count input and output parameter; on input it's the number of elements
+ * in the map to read and delete in batch; on output it represents the number of
+ * elements that were successfully read and deleted
+ * If a non-**EFAULT** error code is returned and if the output **count** value
+ * is not equal to the input **count** value, up to **count** elements may
+ * have been deleted.
+ * if **EFAULT** is returned up to *count* elements may have been deleted without
+ * being returned via the *keys* and *values* output parameters.
+ * @param opts options for configuring the way the batch lookup and delete works
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
 LIBBPF_API int bpf_map_lookup_and_delete_batch(int fd, void *in_batch,
 					void *out_batch, void *keys,
 					void *values, __u32 *count,
 					const struct bpf_map_batch_opts *opts);
-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);
 
+struct bpf_obj_get_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+
+	__u32 file_flags;
+
+	size_t :0;
+};
+#define bpf_obj_get_opts__last_field file_flags
+
 LIBBPF_API int bpf_obj_pin(int fd, const char *pathname);
 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);
 
 struct bpf_prog_attach_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */
@@ -163,7 +293,7 @@ struct bpf_prog_attach_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,
+LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int attachable_fd,
 				     enum bpf_attach_type type,
 				     const struct bpf_prog_attach_opts *opts);
 LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
@@ -181,10 +311,20 @@ 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 {
+			__u64 cookie;
+		} tracing;
 	};
 	size_t :0;
 };
-#define bpf_link_create_opts__last_field perf_event
+#define bpf_link_create_opts__last_field kprobe_multi.cookies
 
 LIBBPF_API int bpf_link_create(int prog_fd, int target_fd,
 			       enum bpf_attach_type attach_type,
@@ -221,15 +361,6 @@ 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);
@@ -239,12 +370,25 @@ LIBBPF_API int bpf_map_get_fd_by_id(__u32 id);
 LIBBPF_API int bpf_btf_get_fd_by_id(__u32 id);
 LIBBPF_API int bpf_link_get_fd_by_id(__u32 id);
 LIBBPF_API int bpf_obj_get_info_by_fd(int bpf_fd, void *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;
+	__u32 prog_cnt; /* input+output argument */
+	__u32 *prog_attach_flags;
+};
+#define bpf_prog_query_opts__last_field prog_attach_flags
+
+LIBBPF_API int bpf_prog_query_opts(int target_fd,
+				   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);
+
 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);
@@ -280,8 +424,9 @@ 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);

src/bpf_core_read.h

@@ -29,6 +29,7 @@ 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 */
@@ -110,21 +111,50 @@ enum bpf_enum_value_kind {
 	val;								      \
 })
 
+#define ___bpf_field_ref1(field)	(field)
+#define ___bpf_field_ref2(type, field)	(((typeof(type) *)0)->field)
+#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
@@ -154,6 +184,16 @@ enum bpf_enum_value_kind {
 #define bpf_core_type_exists(type)					    \
 	__builtin_preserve_type_info(*(typeof(type) *)0, 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(*(typeof(type) *)0, BPF_TYPE_MATCHES)
+
 /*
  * Convenience macro to get the byte size of a provided named type
  * (struct/union/enum/typedef) in a target kernel.

src/bpf_gen_internal.h

@@ -3,6 +3,8 @@
 #ifndef __BPF_GEN_INTERNAL_H
 #define __BPF_GEN_INTERNAL_H
 
+#include "bpf.h"
+
 struct ksym_relo_desc {
 	const char *name;
 	int kind;
@@ -37,6 +39,8 @@ 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 +49,24 @@ 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);
+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_helper_defs.h

@@ -38,6 +38,10 @@ struct inode;
 struct socket;
 struct file;
 struct bpf_timer;
+struct mptcp_sock;
+struct bpf_dynptr;
+struct iphdr;
+struct ipv6hdr;
 
 /*
  * bpf_map_lookup_elem
@@ -314,7 +318,7 @@ static long (*bpf_l4_csum_replace)(struct __sk_buff *skb, __u32 offset, __u64 fr
  * 	if the maximum number of tail calls has been reached for this
  * 	chain of programs. This limit is defined in the kernel by the
  * 	macro **MAX_TAIL_CALL_CNT** (not accessible to user space),
- * 	which is currently set to 32.
+ * 	which is currently set to 33.
  *
  * Returns
  * 	0 on success, or a negative error in case of failure.
@@ -352,6 +356,7 @@ static long (*bpf_clone_redirect)(struct __sk_buff *skb, __u32 ifindex, __u64 fl
 /*
  * bpf_get_current_pid_tgid
  *
+ * 	Get the current pid and tgid.
  *
  * Returns
  * 	A 64-bit integer containing the current tgid and pid, and
@@ -364,6 +369,7 @@ static __u64 (*bpf_get_current_pid_tgid)(void) = (void *) 14;
 /*
  * bpf_get_current_uid_gid
  *
+ * 	Get the current uid and gid.
  *
  * Returns
  * 	A 64-bit integer containing the current GID and UID, and
@@ -919,6 +925,7 @@ static __u32 (*bpf_get_hash_recalc)(struct __sk_buff *skb) = (void *) 34;
 /*
  * bpf_get_current_task
  *
+ * 	Get the current task.
  *
  * Returns
  * 	A pointer to the current task struct.
@@ -958,8 +965,8 @@ static long (*bpf_probe_write_user)(void *dst, const void *src, __u32 len) = (vo
  * Returns
  * 	The return value depends on the result of the test, and can be:
  *
- * 	* 0, if current task belongs to the cgroup2.
- * 	* 1, if current task does not belong to the cgroup2.
+ * 	* 1, if current task belongs to the cgroup2.
+ * 	* 0, if current task does not belong to the cgroup2.
  * 	* A negative error code, if an error occurred.
  */
 static long (*bpf_current_task_under_cgroup)(void *map, __u32 index) = (void *) 37;
@@ -998,7 +1005,8 @@ static long (*bpf_skb_change_tail)(struct __sk_buff *skb, __u32 len, __u64 flags
  * 	Pull in non-linear data in case the *skb* is non-linear and not
  * 	all of *len* are part of the linear section. Make *len* bytes
  * 	from *skb* readable and writable. If a zero value is passed for
- * 	*len*, then the whole length of the *skb* is pulled.
+ * 	*len*, then all bytes in the linear part of *skb* will be made
+ * 	readable and writable.
  *
  * 	This helper is only needed for reading and writing with direct
  * 	packet access.
@@ -1057,6 +1065,8 @@ static __s64 (*bpf_csum_update)(struct __sk_buff *skb, __wsum csum) = (void *) 4
  * 	recalculation the next time the kernel tries to access this
  * 	hash or when the **bpf_get_hash_recalc**\ () helper is called.
  *
+ * Returns
+ * 	void.
  */
 static void (*bpf_set_hash_invalid)(struct __sk_buff *skb) = (void *) 41;
 
@@ -1156,6 +1166,7 @@ static __u64 (*bpf_get_socket_cookie)(void *ctx) = (void *) 46;
 /*
  * bpf_get_socket_uid
  *
+ * 	Get the owner UID of the socked associated to *skb*.
  *
  * Returns
  * 	The owner UID of the socket associated to *skb*. If the socket
@@ -1228,10 +1239,12 @@ static long (*bpf_setsockopt)(void *bpf_socket, int level, int optname, void *op
  * 	There are two supported modes at this time:
  *
  * 	* **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
- * 	  (room space is added or removed below the layer 2 header).
+ * 	  (room space is added or removed between the layer 2 and
+ * 	  layer 3 headers).
  *
  * 	* **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
- * 	  (room space is added or removed below the layer 3 header).
+ * 	  (room space is added or removed between the layer 3 and
+ * 	  layer 4 headers).
  *
  * 	The following flags are supported at this time:
  *
@@ -1731,8 +1744,18 @@ static long (*bpf_skb_get_xfrm_state)(struct __sk_buff *skb, __u32 index, struct
  * 	**BPF_F_USER_STACK**
  * 		Collect a user space stack instead of a kernel stack.
  * 	**BPF_F_USER_BUILD_ID**
- * 		Collect buildid+offset instead of ips for user stack,
- * 		only valid if **BPF_F_USER_STACK** is also specified.
+ * 		Collect (build_id, file_offset) instead of ips for user
+ * 		stack, only valid if **BPF_F_USER_STACK** is also
+ * 		specified.
+ *
+ * 		*file_offset* is an offset relative to the beginning
+ * 		of the executable or shared object file backing the vma
+ * 		which the *ip* falls in. It is *not* an offset relative
+ * 		to that object's base address. Accordingly, it must be
+ * 		adjusted by adding (sh_addr - sh_offset), where
+ * 		sh_{addr,offset} correspond to the executable section
+ * 		containing *file_offset* in the object, for comparisons
+ * 		to symbols' st_value to be valid.
  *
  * 	**bpf_get_stack**\ () can collect up to
  * 	**PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
@@ -1746,8 +1769,8 @@ static long (*bpf_skb_get_xfrm_state)(struct __sk_buff *skb, __u32 index, struct
  * 		# sysctl kernel.perf_event_max_stack=<new value>
  *
  * Returns
- * 	A non-negative value equal to or less than *size* on success,
- * 	or a negative error in case of failure.
+ * 	The non-negative copied *buf* length equal to or less than
+ * 	*size* on success, or a negative error in case of failure.
  */
 static long (*bpf_get_stack)(void *ctx, void *buf, __u32 size, __u64 flags) = (void *) 67;
 
@@ -2063,6 +2086,8 @@ static __u64 (*bpf_skb_cgroup_id)(struct __sk_buff *skb) = (void *) 79;
 /*
  * bpf_get_current_cgroup_id
  *
+ * 	Get the current cgroup id based on the cgroup within which
+ * 	the current task is running.
  *
  * Returns
  * 	A 64-bit integer containing the current cgroup id based
@@ -2453,10 +2478,11 @@ static struct bpf_sock *(*bpf_skc_lookup_tcp)(void *ctx, struct bpf_sock_tuple *
  *
  * 	*iph* points to the start of the IPv4 or IPv6 header, while
  * 	*iph_len* contains **sizeof**\ (**struct iphdr**) or
- * 	**sizeof**\ (**struct ip6hdr**).
+ * 	**sizeof**\ (**struct ipv6hdr**).
  *
  * 	*th* points to the start of the TCP header, while *th_len*
- * 	contains **sizeof**\ (**struct tcphdr**).
+ * 	contains the length of the TCP header (at least
+ * 	**sizeof**\ (**struct tcphdr**)).
  *
  * Returns
  * 	0 if *iph* and *th* are a valid SYN cookie ACK, or a negative
@@ -2679,10 +2705,11 @@ static long (*bpf_send_signal)(__u32 sig) = (void *) 109;
  *
  * 	*iph* points to the start of the IPv4 or IPv6 header, while
  * 	*iph_len* contains **sizeof**\ (**struct iphdr**) or
- * 	**sizeof**\ (**struct ip6hdr**).
+ * 	**sizeof**\ (**struct ipv6hdr**).
  *
  * 	*th* points to the start of the TCP header, while *th_len*
- * 	contains the length of the TCP header.
+ * 	contains the length of the TCP header with options (at least
+ * 	**sizeof**\ (**struct tcphdr**)).
  *
  * Returns
  * 	On success, lower 32 bits hold the generated SYN cookie in
@@ -3297,8 +3324,8 @@ static struct udp6_sock *(*bpf_skc_to_udp6_sock)(void *sk) = (void *) 140;
  * 		# sysctl kernel.perf_event_max_stack=<new value>
  *
  * Returns
- * 	A non-negative value equal to or less than *size* on success,
- * 	or a negative error in case of failure.
+ * 	The non-negative copied *buf* length equal to or less than
+ * 	*size* on success, or a negative error in case of failure.
  */
 static long (*bpf_get_task_stack)(struct task_struct *task, void *buf, __u32 size, __u64 flags) = (void *) 141;
 
@@ -3399,7 +3426,7 @@ static long (*bpf_load_hdr_opt)(struct bpf_sock_ops *skops, void *searchby_res,
  *
  * 	**-EEXIST** if the option already exists.
  *
- * 	**-EFAULT** on failrue to parse the existing header options.
+ * 	**-EFAULT** on failure to parse the existing header options.
  *
  * 	**-EPERM** if the helper cannot be used under the current
  * 	*skops*\ **->op**.
@@ -3659,7 +3686,7 @@ static long (*bpf_redirect_peer)(__u32 ifindex, __u64 flags) = (void *) 155;
  * 	a *map* with *task* as the **key**.  From this
  * 	perspective,  the usage is not much different from
  * 	**bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this
- * 	helper enforces the key must be an task_struct and the map must also
+ * 	helper enforces the key must be a task_struct and the map must also
  * 	be a **BPF_MAP_TYPE_TASK_STORAGE**.
  *
  * 	Underneath, the value is stored locally at *task* instead of
@@ -3737,7 +3764,7 @@ static __u64 (*bpf_ktime_get_coarse_ns)(void) = (void *) 160;
 /*
  * bpf_ima_inode_hash
  *
- * 	Returns the stored IMA hash of the *inode* (if it's avaialable).
+ * 	Returns the stored IMA hash of the *inode* (if it's available).
  * 	If the hash is larger than *size*, then only *size*
  * 	bytes will be copied to *dst*
  *
@@ -3769,12 +3796,12 @@ static struct socket *(*bpf_sock_from_file)(struct file *file) = (void *) 162;
  *
  * 	The argument *len_diff* can be used for querying with a planned
  * 	size change. This allows to check MTU prior to changing packet
- * 	ctx. Providing an *len_diff* adjustment that is larger than the
+ * 	ctx. Providing a *len_diff* adjustment that is larger than the
  * 	actual packet size (resulting in negative packet size) will in
- * 	principle not exceed the MTU, why it is not considered a
- * 	failure.  Other BPF-helpers are needed for performing the
- * 	planned size change, why the responsability for catch a negative
- * 	packet size belong in those helpers.
+ * 	principle not exceed the MTU, which is why it is not considered
+ * 	a failure.  Other BPF helpers are needed for performing the
+ * 	planned size change; therefore the responsibility for catching
+ * 	a negative packet size belongs in those helpers.
  *
  * 	Specifying *ifindex* zero means the MTU check is performed
  * 	against the current net device.  This is practical if this isn't
@@ -4013,6 +4040,7 @@ static long (*bpf_timer_cancel)(struct bpf_timer *timer) = (void *) 172;
  *
  * Returns
  * 	Address of the traced function.
+ * 	0 for kprobes placed within the function (not at the entry).
  */
 static __u64 (*bpf_get_func_ip)(void *ctx) = (void *) 173;
 
@@ -4113,4 +4141,525 @@ static struct unix_sock *(*bpf_skc_to_unix_sock)(void *sk) = (void *) 178;
  */
 static long (*bpf_kallsyms_lookup_name)(const char *name, int name_sz, int flags, __u64 *res) = (void *) 179;
 
+/*
+ * bpf_find_vma
+ *
+ * 	Find vma of *task* that contains *addr*, call *callback_fn*
+ * 	function with *task*, *vma*, and *callback_ctx*.
+ * 	The *callback_fn* should be a static function and
+ * 	the *callback_ctx* should be a pointer to the stack.
+ * 	The *flags* is used to control certain aspects of the helper.
+ * 	Currently, the *flags* must be 0.
+ *
+ * 	The expected callback signature is
+ *
+ * 	long (\*callback_fn)(struct task_struct \*task, struct vm_area_struct \*vma, void \*callback_ctx);
+ *
+ *
+ * Returns
+ * 	0 on success.
+ * 	**-ENOENT** if *task->mm* is NULL, or no vma contains *addr*.
+ * 	**-EBUSY** if failed to try lock mmap_lock.
+ * 	**-EINVAL** for invalid **flags**.
+ */
+static long (*bpf_find_vma)(struct task_struct *task, __u64 addr, void *callback_fn, void *callback_ctx, __u64 flags) = (void *) 180;
+
+/*
+ * bpf_loop
+ *
+ * 	For **nr_loops**, call **callback_fn** function
+ * 	with **callback_ctx** as the context parameter.
+ * 	The **callback_fn** should be a static function and
+ * 	the **callback_ctx** should be a pointer to the stack.
+ * 	The **flags** is used to control certain aspects of the helper.
+ * 	Currently, the **flags** must be 0. Currently, nr_loops is
+ * 	limited to 1 << 23 (~8 million) loops.
+ *
+ * 	long (\*callback_fn)(u32 index, void \*ctx);
+ *
+ * 	where **index** is the current index in the loop. The index
+ * 	is zero-indexed.
+ *
+ * 	If **callback_fn** returns 0, the helper will continue to the next
+ * 	loop. If return value is 1, the helper will skip the rest of
+ * 	the loops and return. Other return values are not used now,
+ * 	and will be rejected by the verifier.
+ *
+ *
+ * Returns
+ * 	The number of loops performed, **-EINVAL** for invalid **flags**,
+ * 	**-E2BIG** if **nr_loops** exceeds the maximum number of loops.
+ */
+static long (*bpf_loop)(__u32 nr_loops, void *callback_fn, void *callback_ctx, __u64 flags) = (void *) 181;
+
+/*
+ * bpf_strncmp
+ *
+ * 	Do strncmp() between **s1** and **s2**. **s1** doesn't need
+ * 	to be null-terminated and **s1_sz** is the maximum storage
+ * 	size of **s1**. **s2** must be a read-only string.
+ *
+ * Returns
+ * 	An integer less than, equal to, or greater than zero
+ * 	if the first **s1_sz** bytes of **s1** is found to be
+ * 	less than, to match, or be greater than **s2**.
+ */
+static long (*bpf_strncmp)(const char *s1, __u32 s1_sz, const char *s2) = (void *) 182;
+
+/*
+ * bpf_get_func_arg
+ *
+ * 	Get **n**-th argument register (zero based) of the traced function (for tracing programs)
+ * 	returned in **value**.
+ *
+ *
+ * Returns
+ * 	0 on success.
+ * 	**-EINVAL** if n >= argument register count of traced function.
+ */
+static long (*bpf_get_func_arg)(void *ctx, __u32 n, __u64 *value) = (void *) 183;
+
+/*
+ * bpf_get_func_ret
+ *
+ * 	Get return value of the traced function (for tracing programs)
+ * 	in **value**.
+ *
+ *
+ * Returns
+ * 	0 on success.
+ * 	**-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN.
+ */
+static long (*bpf_get_func_ret)(void *ctx, __u64 *value) = (void *) 184;
+
+/*
+ * bpf_get_func_arg_cnt
+ *
+ * 	Get number of registers of the traced function (for tracing programs) where
+ * 	function arguments are stored in these registers.
+ *
+ *
+ * Returns
+ * 	The number of argument registers of the traced function.
+ */
+static long (*bpf_get_func_arg_cnt)(void *ctx) = (void *) 185;
+
+/*
+ * bpf_get_retval
+ *
+ * 	Get the BPF program's return value that will be returned to the upper layers.
+ *
+ * 	This helper is currently supported by cgroup programs and only by the hooks
+ * 	where BPF program's return value is returned to the userspace via errno.
+ *
+ * Returns
+ * 	The BPF program's return value.
+ */
+static int (*bpf_get_retval)(void) = (void *) 186;
+
+/*
+ * bpf_set_retval
+ *
+ * 	Set the BPF program's return value that will be returned to the upper layers.
+ *
+ * 	This helper is currently supported by cgroup programs and only by the hooks
+ * 	where BPF program's return value is returned to the userspace via errno.
+ *
+ * 	Note that there is the following corner case where the program exports an error
+ * 	via bpf_set_retval but signals success via 'return 1':
+ *
+ * 		bpf_set_retval(-EPERM);
+ * 		return 1;
+ *
+ * 	In this case, the BPF program's return value will use helper's -EPERM. This
+ * 	still holds true for cgroup/bind{4,6} which supports extra 'return 3' success case.
+ *
+ *
+ * Returns
+ * 	0 on success, or a negative error in case of failure.
+ */
+static int (*bpf_set_retval)(int retval) = (void *) 187;
+
+/*
+ * bpf_xdp_get_buff_len
+ *
+ * 	Get the total size of a given xdp buff (linear and paged area)
+ *
+ * Returns
+ * 	The total size of a given xdp buffer.
+ */
+static __u64 (*bpf_xdp_get_buff_len)(struct xdp_md *xdp_md) = (void *) 188;
+
+/*
+ * bpf_xdp_load_bytes
+ *
+ * 	This helper is provided as an easy way to load data from a
+ * 	xdp buffer. It can be used to load *len* bytes from *offset* from
+ * 	the frame associated to *xdp_md*, into the buffer pointed by
+ * 	*buf*.
+ *
+ * Returns
+ * 	0 on success, or a negative error in case of failure.
+ */
+static long (*bpf_xdp_load_bytes)(struct xdp_md *xdp_md, __u32 offset, void *buf, __u32 len) = (void *) 189;
+
+/*
+ * bpf_xdp_store_bytes
+ *
+ * 	Store *len* bytes from buffer *buf* into the frame
+ * 	associated to *xdp_md*, at *offset*.
+ *
+ * Returns
+ * 	0 on success, or a negative error in case of failure.
+ */
+static long (*bpf_xdp_store_bytes)(struct xdp_md *xdp_md, __u32 offset, void *buf, __u32 len) = (void *) 190;
+
+/*
+ * bpf_copy_from_user_task
+ *
+ * 	Read *size* bytes from user space address *user_ptr* in *tsk*'s
+ * 	address space, and stores the data in *dst*. *flags* is not
+ * 	used yet and is provided for future extensibility. This helper
+ * 	can only be used by sleepable programs.
+ *
+ * Returns
+ * 	0 on success, or a negative error in case of failure. On error
+ * 	*dst* buffer is zeroed out.
+ */
+static long (*bpf_copy_from_user_task)(void *dst, __u32 size, const void *user_ptr, struct task_struct *tsk, __u64 flags) = (void *) 191;
+
+/*
+ * bpf_skb_set_tstamp
+ *
+ * 	Change the __sk_buff->tstamp_type to *tstamp_type*
+ * 	and set *tstamp* to the __sk_buff->tstamp together.
+ *
+ * 	If there is no need to change the __sk_buff->tstamp_type,
+ * 	the tstamp value can be directly written to __sk_buff->tstamp
+ * 	instead.
+ *
+ * 	BPF_SKB_TSTAMP_DELIVERY_MONO is the only tstamp that
+ * 	will be kept during bpf_redirect_*().  A non zero
+ * 	*tstamp* must be used with the BPF_SKB_TSTAMP_DELIVERY_MONO
+ * 	*tstamp_type*.
+ *
+ * 	A BPF_SKB_TSTAMP_UNSPEC *tstamp_type* can only be used
+ * 	with a zero *tstamp*.
+ *
+ * 	Only IPv4 and IPv6 skb->protocol are supported.
+ *
+ * 	This function is most useful when it needs to set a
+ * 	mono delivery time to __sk_buff->tstamp and then
+ * 	bpf_redirect_*() to the egress of an iface.  For example,
+ * 	changing the (rcv) timestamp in __sk_buff->tstamp at
+ * 	ingress to a mono delivery time and then bpf_redirect_*()
+ * 	to sch_fq@phy-dev.
+ *
+ * Returns
+ * 	0 on success.
+ * 	**-EINVAL** for invalid input
+ * 	**-EOPNOTSUPP** for unsupported protocol
+ */
+static long (*bpf_skb_set_tstamp)(struct __sk_buff *skb, __u64 tstamp, __u32 tstamp_type) = (void *) 192;
+
+/*
+ * bpf_ima_file_hash
+ *
+ * 	Returns a calculated IMA hash of the *file*.
+ * 	If the hash is larger than *size*, then only *size*
+ * 	bytes will be copied to *dst*
+ *
+ * Returns
+ * 	The **hash_algo** is returned on success,
+ * 	**-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if
+ * 	invalid arguments are passed.
+ */
+static long (*bpf_ima_file_hash)(struct file *file, void *dst, __u32 size) = (void *) 193;
+
+/*
+ * bpf_kptr_xchg
+ *
+ * 	Exchange kptr at pointer *map_value* with *ptr*, and return the
+ * 	old value. *ptr* can be NULL, otherwise it must be a referenced
+ * 	pointer which will be released when this helper is called.
+ *
+ * Returns
+ * 	The old value of kptr (which can be NULL). The returned pointer
+ * 	if not NULL, is a reference which must be released using its
+ * 	corresponding release function, or moved into a BPF map before
+ * 	program exit.
+ */
+static void *(*bpf_kptr_xchg)(void *map_value, void *ptr) = (void *) 194;
+
+/*
+ * bpf_map_lookup_percpu_elem
+ *
+ * 	Perform a lookup in *percpu map* for an entry associated to
+ * 	*key* on *cpu*.
+ *
+ * Returns
+ * 	Map value associated to *key* on *cpu*, or **NULL** if no entry
+ * 	was found or *cpu* is invalid.
+ */
+static void *(*bpf_map_lookup_percpu_elem)(void *map, const void *key, __u32 cpu) = (void *) 195;
+
+/*
+ * bpf_skc_to_mptcp_sock
+ *
+ * 	Dynamically cast a *sk* pointer to a *mptcp_sock* pointer.
+ *
+ * Returns
+ * 	*sk* if casting is valid, or **NULL** otherwise.
+ */
+static struct mptcp_sock *(*bpf_skc_to_mptcp_sock)(void *sk) = (void *) 196;
+
+/*
+ * bpf_dynptr_from_mem
+ *
+ * 	Get a dynptr to local memory *data*.
+ *
+ * 	*data* must be a ptr to a map value.
+ * 	The maximum *size* supported is DYNPTR_MAX_SIZE.
+ * 	*flags* is currently unused.
+ *
+ * Returns
+ * 	0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE,
+ * 	-EINVAL if flags is not 0.
+ */
+static long (*bpf_dynptr_from_mem)(void *data, __u32 size, __u64 flags, struct bpf_dynptr *ptr) = (void *) 197;
+
+/*
+ * bpf_ringbuf_reserve_dynptr
+ *
+ * 	Reserve *size* bytes of payload in a ring buffer *ringbuf*
+ * 	through the dynptr interface. *flags* must be 0.
+ *
+ * 	Please note that a corresponding bpf_ringbuf_submit_dynptr or
+ * 	bpf_ringbuf_discard_dynptr must be called on *ptr*, even if the
+ * 	reservation fails. This is enforced by the verifier.
+ *
+ * Returns
+ * 	0 on success, or a negative error in case of failure.
+ */
+static long (*bpf_ringbuf_reserve_dynptr)(void *ringbuf, __u32 size, __u64 flags, struct bpf_dynptr *ptr) = (void *) 198;
+
+/*
+ * bpf_ringbuf_submit_dynptr
+ *
+ * 	Submit reserved ring buffer sample, pointed to by *data*,
+ * 	through the dynptr interface. This is a no-op if the dynptr is
+ * 	invalid/null.
+ *
+ * 	For more information on *flags*, please see
+ * 	'bpf_ringbuf_submit'.
+ *
+ * Returns
+ * 	Nothing. Always succeeds.
+ */
+static void (*bpf_ringbuf_submit_dynptr)(struct bpf_dynptr *ptr, __u64 flags) = (void *) 199;
+
+/*
+ * bpf_ringbuf_discard_dynptr
+ *
+ * 	Discard reserved ring buffer sample through the dynptr
+ * 	interface. This is a no-op if the dynptr is invalid/null.
+ *
+ * 	For more information on *flags*, please see
+ * 	'bpf_ringbuf_discard'.
+ *
+ * Returns
+ * 	Nothing. Always succeeds.
+ */
+static void (*bpf_ringbuf_discard_dynptr)(struct bpf_dynptr *ptr, __u64 flags) = (void *) 200;
+
+/*
+ * bpf_dynptr_read
+ *
+ * 	Read *len* bytes from *src* into *dst*, starting from *offset*
+ * 	into *src*.
+ * 	*flags* is currently unused.
+ *
+ * Returns
+ * 	0 on success, -E2BIG if *offset* + *len* exceeds the length
+ * 	of *src*'s data, -EINVAL if *src* is an invalid dynptr or if
+ * 	*flags* is not 0.
+ */
+static long (*bpf_dynptr_read)(void *dst, __u32 len, struct bpf_dynptr *src, __u32 offset, __u64 flags) = (void *) 201;
+
+/*
+ * bpf_dynptr_write
+ *
+ * 	Write *len* bytes from *src* into *dst*, starting from *offset*
+ * 	into *dst*.
+ * 	*flags* is currently unused.
+ *
+ * Returns
+ * 	0 on success, -E2BIG if *offset* + *len* exceeds the length
+ * 	of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst*
+ * 	is a read-only dynptr or if *flags* is not 0.
+ */
+static long (*bpf_dynptr_write)(struct bpf_dynptr *dst, __u32 offset, void *src, __u32 len, __u64 flags) = (void *) 202;
+
+/*
+ * bpf_dynptr_data
+ *
+ * 	Get a pointer to the underlying dynptr data.
+ *
+ * 	*len* must be a statically known value. The returned data slice
+ * 	is invalidated whenever the dynptr is invalidated.
+ *
+ * Returns
+ * 	Pointer to the underlying dynptr data, NULL if the dynptr is
+ * 	read-only, if the dynptr is invalid, or if the offset and length
+ * 	is out of bounds.
+ */
+static void *(*bpf_dynptr_data)(struct bpf_dynptr *ptr, __u32 offset, __u32 len) = (void *) 203;
+
+/*
+ * bpf_tcp_raw_gen_syncookie_ipv4
+ *
+ * 	Try to issue a SYN cookie for the packet with corresponding
+ * 	IPv4/TCP headers, *iph* and *th*, without depending on a
+ * 	listening socket.
+ *
+ * 	*iph* points to the IPv4 header.
+ *
+ * 	*th* points to the start of the TCP header, while *th_len*
+ * 	contains the length of the TCP header (at least
+ * 	**sizeof**\ (**struct tcphdr**)).
+ *
+ * Returns
+ * 	On success, lower 32 bits hold the generated SYN cookie in
+ * 	followed by 16 bits which hold the MSS value for that cookie,
+ * 	and the top 16 bits are unused.
+ *
+ * 	On failure, the returned value is one of the following:
+ *
+ * 	**-EINVAL** if *th_len* is invalid.
+ */
+static __s64 (*bpf_tcp_raw_gen_syncookie_ipv4)(struct iphdr *iph, struct tcphdr *th, __u32 th_len) = (void *) 204;
+
+/*
+ * bpf_tcp_raw_gen_syncookie_ipv6
+ *
+ * 	Try to issue a SYN cookie for the packet with corresponding
+ * 	IPv6/TCP headers, *iph* and *th*, without depending on a
+ * 	listening socket.
+ *
+ * 	*iph* points to the IPv6 header.
+ *
+ * 	*th* points to the start of the TCP header, while *th_len*
+ * 	contains the length of the TCP header (at least
+ * 	**sizeof**\ (**struct tcphdr**)).
+ *
+ * Returns
+ * 	On success, lower 32 bits hold the generated SYN cookie in
+ * 	followed by 16 bits which hold the MSS value for that cookie,
+ * 	and the top 16 bits are unused.
+ *
+ * 	On failure, the returned value is one of the following:
+ *
+ * 	**-EINVAL** if *th_len* is invalid.
+ *
+ * 	**-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
+ */
+static __s64 (*bpf_tcp_raw_gen_syncookie_ipv6)(struct ipv6hdr *iph, struct tcphdr *th, __u32 th_len) = (void *) 205;
+
+/*
+ * bpf_tcp_raw_check_syncookie_ipv4
+ *
+ * 	Check whether *iph* and *th* contain a valid SYN cookie ACK
+ * 	without depending on a listening socket.
+ *
+ * 	*iph* points to the IPv4 header.
+ *
+ * 	*th* points to the TCP header.
+ *
+ * Returns
+ * 	0 if *iph* and *th* are a valid SYN cookie ACK.
+ *
+ * 	On failure, the returned value is one of the following:
+ *
+ * 	**-EACCES** if the SYN cookie is not valid.
+ */
+static long (*bpf_tcp_raw_check_syncookie_ipv4)(struct iphdr *iph, struct tcphdr *th) = (void *) 206;
+
+/*
+ * bpf_tcp_raw_check_syncookie_ipv6
+ *
+ * 	Check whether *iph* and *th* contain a valid SYN cookie ACK
+ * 	without depending on a listening socket.
+ *
+ * 	*iph* points to the IPv6 header.
+ *
+ * 	*th* points to the TCP header.
+ *
+ * Returns
+ * 	0 if *iph* and *th* are a valid SYN cookie ACK.
+ *
+ * 	On failure, the returned value is one of the following:
+ *
+ * 	**-EACCES** if the SYN cookie is not valid.
+ *
+ * 	**-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
+ */
+static long (*bpf_tcp_raw_check_syncookie_ipv6)(struct ipv6hdr *iph, struct tcphdr *th) = (void *) 207;
+
+/*
+ * bpf_ktime_get_tai_ns
+ *
+ * 	A nonsettable system-wide clock derived from wall-clock time but
+ * 	ignoring leap seconds.  This clock does not experience
+ * 	discontinuities and backwards jumps caused by NTP inserting leap
+ * 	seconds as CLOCK_REALTIME does.
+ *
+ * 	See: **clock_gettime**\ (**CLOCK_TAI**)
+ *
+ * Returns
+ * 	Current *ktime*.
+ */
+static __u64 (*bpf_ktime_get_tai_ns)(void) = (void *) 208;
+
+/*
+ * bpf_user_ringbuf_drain
+ *
+ * 	Drain samples from the specified user ring buffer, and invoke
+ * 	the provided callback for each such sample:
+ *
+ * 	long (\*callback_fn)(struct bpf_dynptr \*dynptr, void \*ctx);
+ *
+ * 	If **callback_fn** returns 0, the helper will continue to try
+ * 	and drain the next sample, up to a maximum of
+ * 	BPF_MAX_USER_RINGBUF_SAMPLES samples. If the return value is 1,
+ * 	the helper will skip the rest of the samples and return. Other
+ * 	return values are not used now, and will be rejected by the
+ * 	verifier.
+ *
+ * Returns
+ * 	The number of drained samples if no error was encountered while
+ * 	draining samples, or 0 if no samples were present in the ring
+ * 	buffer. If a user-space producer was epoll-waiting on this map,
+ * 	and at least one sample was drained, they will receive an event
+ * 	notification notifying them of available space in the ring
+ * 	buffer. If the BPF_RB_NO_WAKEUP flag is passed to this
+ * 	function, no wakeup notification will be sent. If the
+ * 	BPF_RB_FORCE_WAKEUP flag is passed, a wakeup notification will
+ * 	be sent even if no sample was drained.
+ *
+ * 	On failure, the returned value is one of the following:
+ *
+ * 	**-EBUSY** if the ring buffer is contended, and another calling
+ * 	context was concurrently draining the ring buffer.
+ *
+ * 	**-EINVAL** if user-space is not properly tracking the ring
+ * 	buffer due to the producer position not being aligned to 8
+ * 	bytes, a sample not being aligned to 8 bytes, or the producer
+ * 	position not matching the advertised length of a sample.
+ *
+ * 	**-E2BIG** if user-space has tried to publish a sample which is
+ * 	larger than the size of the ring buffer, or which cannot fit
+ * 	within a struct bpf_dynptr.
+ */
+static long (*bpf_user_ringbuf_drain)(void *map, void *callback_fn, void *ctx, __u64 flags) = (void *) 209;
+
 

src/bpf_helpers.h

@@ -22,12 +22,25 @@
  * 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))
@@ -75,6 +88,30 @@
 	})
 #endif
 
+/*
+ * 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) : "0"(var))
+#endif
+
 /*
  * Helper macro to throw a compilation error if __bpf_unreachable() gets
  * built into the resulting code. This works given BPF back end does not
@@ -123,18 +160,6 @@ bpf_tail_call_static(void *ctx, const void *map, const __u32 slot)
 }
 #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;
-};
-
 enum libbpf_pin_type {
 	LIBBPF_PIN_NONE,
 	/* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */
@@ -149,6 +174,8 @@ enum libbpf_tristate {
 
 #define __kconfig __attribute__((section(".kconfig")))
 #define __ksym __attribute__((section(".ksyms")))
+#define __kptr __attribute__((btf_type_tag("kptr")))
+#define __kptr_ref __attribute__((btf_type_tag("kptr_ref")))
 
 #ifndef ___bpf_concat
 #define ___bpf_concat(a, b) a ## b

src/bpf_tracing.h

@@ -2,6 +2,8 @@
 #ifndef __BPF_TRACING_H__
 #define __BPF_TRACING_H__
 
+#include <bpf/bpf_helpers.h>
+
 /* Scan the ARCH passed in from ARCH env variable (see Makefile) */
 #if defined(__TARGET_ARCH_x86)
 	#define bpf_target_x86
@@ -27,6 +29,9 @@
 #elif defined(__TARGET_ARCH_riscv)
 	#define bpf_target_riscv
 	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_arc)
+	#define bpf_target_arc
+	#define bpf_target_defined
 #else
 
 /* Fall back to what the compiler says */
@@ -54,6 +59,9 @@
 #elif defined(__riscv) && __riscv_xlen == 64
 	#define bpf_target_riscv
 	#define bpf_target_defined
+#elif defined(__arc__)
+	#define bpf_target_arc
+	#define bpf_target_defined
 #endif /* no compiler target */
 
 #endif
@@ -66,277 +74,263 @@
 
 #if defined(__KERNEL__) || defined(__VMLINUX_H__)
 
-#define PT_REGS_PARM1(x) ((x)->di)
-#define PT_REGS_PARM2(x) ((x)->si)
-#define PT_REGS_PARM3(x) ((x)->dx)
-#define PT_REGS_PARM4(x) ((x)->cx)
-#define PT_REGS_PARM5(x) ((x)->r8)
-#define PT_REGS_RET(x) ((x)->sp)
-#define PT_REGS_FP(x) ((x)->bp)
-#define PT_REGS_RC(x) ((x)->ax)
-#define PT_REGS_SP(x) ((x)->sp)
-#define PT_REGS_IP(x) ((x)->ip)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), di)
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), si)
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), dx)
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), cx)
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8)
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), sp)
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), bp)
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), ax)
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), ip)
+#define __PT_PARM1_REG di
+#define __PT_PARM2_REG si
+#define __PT_PARM3_REG dx
+#define __PT_PARM4_REG cx
+#define __PT_PARM5_REG r8
+#define __PT_RET_REG sp
+#define __PT_FP_REG bp
+#define __PT_RC_REG ax
+#define __PT_SP_REG sp
+#define __PT_IP_REG ip
+/* syscall uses r10 for PARM4 */
+#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10)
+#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10)
 
 #else
 
 #ifdef __i386__
+
+#define __PT_PARM1_REG eax
+#define __PT_PARM2_REG edx
+#define __PT_PARM3_REG ecx
 /* i386 kernel is built with -mregparm=3 */
-#define PT_REGS_PARM1(x) ((x)->eax)
-#define PT_REGS_PARM2(x) ((x)->edx)
-#define PT_REGS_PARM3(x) ((x)->ecx)
-#define PT_REGS_PARM4(x) 0
-#define PT_REGS_PARM5(x) 0
-#define PT_REGS_RET(x) ((x)->esp)
-#define PT_REGS_FP(x) ((x)->ebp)
-#define PT_REGS_RC(x) ((x)->eax)
-#define PT_REGS_SP(x) ((x)->esp)
-#define PT_REGS_IP(x) ((x)->eip)
+#define __PT_PARM4_REG __unsupported__
+#define __PT_PARM5_REG __unsupported__
+#define __PT_RET_REG esp
+#define __PT_FP_REG ebp
+#define __PT_RC_REG eax
+#define __PT_SP_REG esp
+#define __PT_IP_REG eip
 
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), eax)
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), edx)
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), ecx)
-#define PT_REGS_PARM4_CORE(x) 0
-#define PT_REGS_PARM5_CORE(x) 0
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), esp)
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), ebp)
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), eax)
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), esp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), eip)
+#else /* __i386__ */
 
-#else
+#define __PT_PARM1_REG rdi
+#define __PT_PARM2_REG rsi
+#define __PT_PARM3_REG rdx
+#define __PT_PARM4_REG rcx
+#define __PT_PARM5_REG r8
+#define __PT_RET_REG rsp
+#define __PT_FP_REG rbp
+#define __PT_RC_REG rax
+#define __PT_SP_REG rsp
+#define __PT_IP_REG rip
+/* syscall uses r10 for PARM4 */
+#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10)
+#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10)
 
-#define PT_REGS_PARM1(x) ((x)->rdi)
-#define PT_REGS_PARM2(x) ((x)->rsi)
-#define PT_REGS_PARM3(x) ((x)->rdx)
-#define PT_REGS_PARM4(x) ((x)->rcx)
-#define PT_REGS_PARM5(x) ((x)->r8)
-#define PT_REGS_RET(x) ((x)->rsp)
-#define PT_REGS_FP(x) ((x)->rbp)
-#define PT_REGS_RC(x) ((x)->rax)
-#define PT_REGS_SP(x) ((x)->rsp)
-#define PT_REGS_IP(x) ((x)->rip)
+#endif /* __i386__ */
 
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), rdi)
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), rsi)
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), rdx)
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), rcx)
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8)
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), rsp)
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), rbp)
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), rax)
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), rsp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), rip)
-
-#endif
-#endif
+#endif /* __KERNEL__ || __VMLINUX_H__ */
 
 #elif defined(bpf_target_s390)
 
-/* s390 provides user_pt_regs instead of struct pt_regs to userspace */
-struct pt_regs;
-#define PT_REGS_S390 const volatile user_pt_regs
-#define PT_REGS_PARM1(x) (((PT_REGS_S390 *)(x))->gprs[2])
-#define PT_REGS_PARM2(x) (((PT_REGS_S390 *)(x))->gprs[3])
-#define PT_REGS_PARM3(x) (((PT_REGS_S390 *)(x))->gprs[4])
-#define PT_REGS_PARM4(x) (((PT_REGS_S390 *)(x))->gprs[5])
-#define PT_REGS_PARM5(x) (((PT_REGS_S390 *)(x))->gprs[6])
-#define PT_REGS_RET(x) (((PT_REGS_S390 *)(x))->gprs[14])
-/* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_FP(x) (((PT_REGS_S390 *)(x))->gprs[11])
-#define PT_REGS_RC(x) (((PT_REGS_S390 *)(x))->gprs[2])
-#define PT_REGS_SP(x) (((PT_REGS_S390 *)(x))->gprs[15])
-#define PT_REGS_IP(x) (((PT_REGS_S390 *)(x))->psw.addr)
+struct pt_regs___s390 {
+	unsigned long orig_gpr2;
+};
 
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[3])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[4])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[5])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[6])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[14])
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[11])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[15])
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), psw.addr)
+/* s390 provides user_pt_regs instead of struct pt_regs to userspace */
+#define __PT_REGS_CAST(x) ((const user_pt_regs *)(x))
+#define __PT_PARM1_REG gprs[2]
+#define __PT_PARM2_REG gprs[3]
+#define __PT_PARM3_REG gprs[4]
+#define __PT_PARM4_REG gprs[5]
+#define __PT_PARM5_REG gprs[6]
+#define __PT_RET_REG grps[14]
+#define __PT_FP_REG gprs[11]	/* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG gprs[2]
+#define __PT_SP_REG gprs[15]
+#define __PT_IP_REG psw.addr
+#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x)
+#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___s390 *)(x), orig_gpr2)
 
 #elif defined(bpf_target_arm)
 
-#define PT_REGS_PARM1(x) ((x)->uregs[0])
-#define PT_REGS_PARM2(x) ((x)->uregs[1])
-#define PT_REGS_PARM3(x) ((x)->uregs[2])
-#define PT_REGS_PARM4(x) ((x)->uregs[3])
-#define PT_REGS_PARM5(x) ((x)->uregs[4])
-#define PT_REGS_RET(x) ((x)->uregs[14])
-#define PT_REGS_FP(x) ((x)->uregs[11]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->uregs[0])
-#define PT_REGS_SP(x) ((x)->uregs[13])
-#define PT_REGS_IP(x) ((x)->uregs[12])
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), uregs[0])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), uregs[1])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), uregs[2])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), uregs[3])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), uregs[4])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), uregs[14])
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), uregs[11])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), uregs[0])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), uregs[13])
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), uregs[12])
+#define __PT_PARM1_REG uregs[0]
+#define __PT_PARM2_REG uregs[1]
+#define __PT_PARM3_REG uregs[2]
+#define __PT_PARM4_REG uregs[3]
+#define __PT_PARM5_REG uregs[4]
+#define __PT_RET_REG uregs[14]
+#define __PT_FP_REG uregs[11]	/* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG uregs[0]
+#define __PT_SP_REG uregs[13]
+#define __PT_IP_REG uregs[12]
 
 #elif defined(bpf_target_arm64)
 
-/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
-struct pt_regs;
-#define PT_REGS_ARM64 const volatile struct user_pt_regs
-#define PT_REGS_PARM1(x) (((PT_REGS_ARM64 *)(x))->regs[0])
-#define PT_REGS_PARM2(x) (((PT_REGS_ARM64 *)(x))->regs[1])
-#define PT_REGS_PARM3(x) (((PT_REGS_ARM64 *)(x))->regs[2])
-#define PT_REGS_PARM4(x) (((PT_REGS_ARM64 *)(x))->regs[3])
-#define PT_REGS_PARM5(x) (((PT_REGS_ARM64 *)(x))->regs[4])
-#define PT_REGS_RET(x) (((PT_REGS_ARM64 *)(x))->regs[30])
-/* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_FP(x) (((PT_REGS_ARM64 *)(x))->regs[29])
-#define PT_REGS_RC(x) (((PT_REGS_ARM64 *)(x))->regs[0])
-#define PT_REGS_SP(x) (((PT_REGS_ARM64 *)(x))->sp)
-#define PT_REGS_IP(x) (((PT_REGS_ARM64 *)(x))->pc)
+struct pt_regs___arm64 {
+	unsigned long orig_x0;
+};
 
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[1])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[2])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[3])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[4])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[30])
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[29])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), sp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), pc)
+/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
+#define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x))
+#define __PT_PARM1_REG regs[0]
+#define __PT_PARM2_REG regs[1]
+#define __PT_PARM3_REG regs[2]
+#define __PT_PARM4_REG regs[3]
+#define __PT_PARM5_REG regs[4]
+#define __PT_RET_REG regs[30]
+#define __PT_FP_REG regs[29]	/* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG regs[0]
+#define __PT_SP_REG sp
+#define __PT_IP_REG pc
+#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x)
+#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___arm64 *)(x), orig_x0)
 
 #elif defined(bpf_target_mips)
 
-#define PT_REGS_PARM1(x) ((x)->regs[4])
-#define PT_REGS_PARM2(x) ((x)->regs[5])
-#define PT_REGS_PARM3(x) ((x)->regs[6])
-#define PT_REGS_PARM4(x) ((x)->regs[7])
-#define PT_REGS_PARM5(x) ((x)->regs[8])
-#define PT_REGS_RET(x) ((x)->regs[31])
-#define PT_REGS_FP(x) ((x)->regs[30]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->regs[2])
-#define PT_REGS_SP(x) ((x)->regs[29])
-#define PT_REGS_IP(x) ((x)->cp0_epc)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), regs[4])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), regs[5])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), regs[6])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), regs[7])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), regs[8])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), regs[31])
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), regs[30])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), regs[2])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), regs[29])
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), cp0_epc)
+#define __PT_PARM1_REG regs[4]
+#define __PT_PARM2_REG regs[5]
+#define __PT_PARM3_REG regs[6]
+#define __PT_PARM4_REG regs[7]
+#define __PT_PARM5_REG regs[8]
+#define __PT_RET_REG regs[31]
+#define __PT_FP_REG regs[30]	/* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG regs[2]
+#define __PT_SP_REG regs[29]
+#define __PT_IP_REG cp0_epc
 
 #elif defined(bpf_target_powerpc)
 
-#define PT_REGS_PARM1(x) ((x)->gpr[3])
-#define PT_REGS_PARM2(x) ((x)->gpr[4])
-#define PT_REGS_PARM3(x) ((x)->gpr[5])
-#define PT_REGS_PARM4(x) ((x)->gpr[6])
-#define PT_REGS_PARM5(x) ((x)->gpr[7])
-#define PT_REGS_RC(x) ((x)->gpr[3])
-#define PT_REGS_SP(x) ((x)->sp)
-#define PT_REGS_IP(x) ((x)->nip)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), gpr[3])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), gpr[4])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), gpr[5])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), gpr[6])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), gpr[7])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), gpr[3])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), nip)
+#define __PT_PARM1_REG gpr[3]
+#define __PT_PARM2_REG gpr[4]
+#define __PT_PARM3_REG gpr[5]
+#define __PT_PARM4_REG gpr[6]
+#define __PT_PARM5_REG gpr[7]
+#define __PT_RET_REG regs[31]
+#define __PT_FP_REG __unsupported__
+#define __PT_RC_REG gpr[3]
+#define __PT_SP_REG sp
+#define __PT_IP_REG nip
+/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx
 
 #elif defined(bpf_target_sparc)
 
-#define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0])
-#define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1])
-#define PT_REGS_PARM3(x) ((x)->u_regs[UREG_I2])
-#define PT_REGS_PARM4(x) ((x)->u_regs[UREG_I3])
-#define PT_REGS_PARM5(x) ((x)->u_regs[UREG_I4])
-#define PT_REGS_RET(x) ((x)->u_regs[UREG_I7])
-#define PT_REGS_RC(x) ((x)->u_regs[UREG_I0])
-#define PT_REGS_SP(x) ((x)->u_regs[UREG_FP])
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I1])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I2])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I3])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I4])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I7])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), u_regs[UREG_FP])
-
+#define __PT_PARM1_REG u_regs[UREG_I0]
+#define __PT_PARM2_REG u_regs[UREG_I1]
+#define __PT_PARM3_REG u_regs[UREG_I2]
+#define __PT_PARM4_REG u_regs[UREG_I3]
+#define __PT_PARM5_REG u_regs[UREG_I4]
+#define __PT_RET_REG u_regs[UREG_I7]
+#define __PT_FP_REG __unsupported__
+#define __PT_RC_REG u_regs[UREG_I0]
+#define __PT_SP_REG u_regs[UREG_FP]
 /* Should this also be a bpf_target check for the sparc case? */
 #if defined(__arch64__)
-#define PT_REGS_IP(x) ((x)->tpc)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), tpc)
+#define __PT_IP_REG tpc
 #else
-#define PT_REGS_IP(x) ((x)->pc)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), pc)
+#define __PT_IP_REG pc
 #endif
 
 #elif defined(bpf_target_riscv)
 
-struct pt_regs;
-#define PT_REGS_RV const volatile struct user_regs_struct
-#define PT_REGS_PARM1(x) (((PT_REGS_RV *)(x))->a0)
-#define PT_REGS_PARM2(x) (((PT_REGS_RV *)(x))->a1)
-#define PT_REGS_PARM3(x) (((PT_REGS_RV *)(x))->a2)
-#define PT_REGS_PARM4(x) (((PT_REGS_RV *)(x))->a3)
-#define PT_REGS_PARM5(x) (((PT_REGS_RV *)(x))->a4)
-#define PT_REGS_RET(x) (((PT_REGS_RV *)(x))->ra)
-#define PT_REGS_FP(x) (((PT_REGS_RV *)(x))->s5)
-#define PT_REGS_RC(x) (((PT_REGS_RV *)(x))->a5)
-#define PT_REGS_SP(x) (((PT_REGS_RV *)(x))->sp)
-#define PT_REGS_IP(x) (((PT_REGS_RV *)(x))->epc)
+#define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x))
+#define __PT_PARM1_REG a0
+#define __PT_PARM2_REG a1
+#define __PT_PARM3_REG a2
+#define __PT_PARM4_REG a3
+#define __PT_PARM5_REG a4
+#define __PT_RET_REG ra
+#define __PT_FP_REG s0
+#define __PT_RC_REG a0
+#define __PT_SP_REG sp
+#define __PT_IP_REG pc
+/* riscv does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx
 
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a0)
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a1)
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a2)
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a3)
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a4)
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), ra)
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), fp)
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a5)
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), sp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), epc)
+#elif defined(bpf_target_arc)
+
+/* arc provides struct user_pt_regs instead of struct pt_regs to userspace */
+#define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x))
+#define __PT_PARM1_REG scratch.r0
+#define __PT_PARM2_REG scratch.r1
+#define __PT_PARM3_REG scratch.r2
+#define __PT_PARM4_REG scratch.r3
+#define __PT_PARM5_REG scratch.r4
+#define __PT_RET_REG scratch.blink
+#define __PT_FP_REG __unsupported__
+#define __PT_RC_REG scratch.r0
+#define __PT_SP_REG scratch.sp
+#define __PT_IP_REG scratch.ret
+/* arc does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx
 
 #endif
 
+#if defined(bpf_target_defined)
+
+struct pt_regs;
+
+/* allow some architecutres to override `struct pt_regs` */
+#ifndef __PT_REGS_CAST
+#define __PT_REGS_CAST(x) (x)
+#endif
+
+#define PT_REGS_PARM1(x) (__PT_REGS_CAST(x)->__PT_PARM1_REG)
+#define PT_REGS_PARM2(x) (__PT_REGS_CAST(x)->__PT_PARM2_REG)
+#define PT_REGS_PARM3(x) (__PT_REGS_CAST(x)->__PT_PARM3_REG)
+#define PT_REGS_PARM4(x) (__PT_REGS_CAST(x)->__PT_PARM4_REG)
+#define PT_REGS_PARM5(x) (__PT_REGS_CAST(x)->__PT_PARM5_REG)
+#define PT_REGS_RET(x) (__PT_REGS_CAST(x)->__PT_RET_REG)
+#define PT_REGS_FP(x) (__PT_REGS_CAST(x)->__PT_FP_REG)
+#define PT_REGS_RC(x) (__PT_REGS_CAST(x)->__PT_RC_REG)
+#define PT_REGS_SP(x) (__PT_REGS_CAST(x)->__PT_SP_REG)
+#define PT_REGS_IP(x) (__PT_REGS_CAST(x)->__PT_IP_REG)
+
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM1_REG)
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM2_REG)
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM3_REG)
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM4_REG)
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM5_REG)
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RET_REG)
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_FP_REG)
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RC_REG)
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_SP_REG)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_IP_REG)
+
 #if defined(bpf_target_powerpc)
+
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = (ctx)->link; })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
+
 #elif defined(bpf_target_sparc)
+
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = PT_REGS_RET(ctx); })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
-#elif defined(bpf_target_defined)
+
+#else
+
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)					    \
 	({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); })
 #define BPF_KRETPROBE_READ_RET_IP(ip, ctx)				    \
-	({ bpf_probe_read_kernel(&(ip), sizeof(ip),			    \
-			  (void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
+	({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
+
 #endif
 
-#if !defined(bpf_target_defined)
+#ifndef PT_REGS_PARM1_SYSCALL
+#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1(x)
+#endif
+#define PT_REGS_PARM2_SYSCALL(x) PT_REGS_PARM2(x)
+#define PT_REGS_PARM3_SYSCALL(x) PT_REGS_PARM3(x)
+#ifndef PT_REGS_PARM4_SYSCALL
+#define PT_REGS_PARM4_SYSCALL(x) PT_REGS_PARM4(x)
+#endif
+#define PT_REGS_PARM5_SYSCALL(x) PT_REGS_PARM5(x)
+
+#ifndef PT_REGS_PARM1_CORE_SYSCALL
+#define PT_REGS_PARM1_CORE_SYSCALL(x) PT_REGS_PARM1_CORE(x)
+#endif
+#define PT_REGS_PARM2_CORE_SYSCALL(x) PT_REGS_PARM2_CORE(x)
+#define PT_REGS_PARM3_CORE_SYSCALL(x) PT_REGS_PARM3_CORE(x)
+#ifndef PT_REGS_PARM4_CORE_SYSCALL
+#define PT_REGS_PARM4_CORE_SYSCALL(x) PT_REGS_PARM4_CORE(x)
+#endif
+#define PT_REGS_PARM5_CORE_SYSCALL(x) PT_REGS_PARM5_CORE(x)
+
+#else /* defined(bpf_target_defined) */
 
 #define PT_REGS_PARM1(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define PT_REGS_PARM2(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
@@ -363,7 +357,29 @@ struct pt_regs;
 #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define BPF_KRETPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 
-#endif /* !defined(bpf_target_defined) */
+#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM2_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM3_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM4_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM5_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+
+#define PT_REGS_PARM1_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM2_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM3_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM4_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM5_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+
+#endif /* defined(bpf_target_defined) */
+
+/*
+ * When invoked from a syscall handler kprobe, returns a pointer to a
+ * struct pt_regs containing syscall arguments and suitable for passing to
+ * PT_REGS_PARMn_SYSCALL() and PT_REGS_PARMn_CORE_SYSCALL().
+ */
+#ifndef PT_REGS_SYSCALL_REGS
+/* By default, assume that the arch selects ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ((struct pt_regs *)PT_REGS_PARM1(ctx))
+#endif
 
 #ifndef ___bpf_concat
 #define ___bpf_concat(a, b) a ## b
@@ -375,25 +391,23 @@ struct pt_regs;
 #define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N
 #endif
 #ifndef ___bpf_narg
-#define ___bpf_narg(...) \
-	___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+#define ___bpf_narg(...) ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
 #endif
 
-#define ___bpf_ctx_cast0() ctx
-#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0]
-#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1]
-#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2]
-#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3]
-#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4]
-#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5]
-#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6]
-#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7]
-#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8]
+#define ___bpf_ctx_cast0()            ctx
+#define ___bpf_ctx_cast1(x)           ___bpf_ctx_cast0(), (void *)ctx[0]
+#define ___bpf_ctx_cast2(x, args...)  ___bpf_ctx_cast1(args), (void *)ctx[1]
+#define ___bpf_ctx_cast3(x, args...)  ___bpf_ctx_cast2(args), (void *)ctx[2]
+#define ___bpf_ctx_cast4(x, args...)  ___bpf_ctx_cast3(args), (void *)ctx[3]
+#define ___bpf_ctx_cast5(x, args...)  ___bpf_ctx_cast4(args), (void *)ctx[4]
+#define ___bpf_ctx_cast6(x, args...)  ___bpf_ctx_cast5(args), (void *)ctx[5]
+#define ___bpf_ctx_cast7(x, args...)  ___bpf_ctx_cast6(args), (void *)ctx[6]
+#define ___bpf_ctx_cast8(x, args...)  ___bpf_ctx_cast7(args), (void *)ctx[7]
+#define ___bpf_ctx_cast9(x, args...)  ___bpf_ctx_cast8(args), (void *)ctx[8]
 #define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9]
 #define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10]
 #define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11]
-#define ___bpf_ctx_cast(args...) \
-	___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args)
+#define ___bpf_ctx_cast(args...)      ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args)
 
 /*
  * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and
@@ -412,7 +426,7 @@ struct pt_regs;
  */
 #define BPF_PROG(name, args...)						    \
 name(unsigned long long *ctx);						    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(unsigned long long *ctx, ##args);				    \
 typeof(name(0)) name(unsigned long long *ctx)				    \
 {									    \
@@ -421,24 +435,125 @@ typeof(name(0)) name(unsigned long long *ctx)				    \
 	return ____##name(___bpf_ctx_cast(args));			    \
 	_Pragma("GCC diagnostic pop")					    \
 }									    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(unsigned long long *ctx, ##args)
 
+#ifndef ___bpf_nth2
+#define ___bpf_nth2(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _13,	\
+		    _14, _15, _16, _17, _18, _19, _20, _21, _22, _23, _24, N, ...) N
+#endif
+#ifndef ___bpf_narg2
+#define ___bpf_narg2(...)	\
+	___bpf_nth2(_, ##__VA_ARGS__, 12, 12, 11, 11, 10, 10, 9, 9, 8, 8, 7, 7,	\
+		    6, 6, 5, 5, 4, 4, 3, 3, 2, 2, 1, 1, 0)
+#endif
+
+#define ___bpf_treg_cnt(t) \
+	__builtin_choose_expr(sizeof(t) == 1, 1,	\
+	__builtin_choose_expr(sizeof(t) == 2, 1,	\
+	__builtin_choose_expr(sizeof(t) == 4, 1,	\
+	__builtin_choose_expr(sizeof(t) == 8, 1,	\
+	__builtin_choose_expr(sizeof(t) == 16, 2,	\
+			      (void)0)))))
+
+#define ___bpf_reg_cnt0()		(0)
+#define ___bpf_reg_cnt1(t, x)		(___bpf_reg_cnt0() + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt2(t, x, args...)	(___bpf_reg_cnt1(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt3(t, x, args...)	(___bpf_reg_cnt2(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt4(t, x, args...)	(___bpf_reg_cnt3(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt5(t, x, args...)	(___bpf_reg_cnt4(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt6(t, x, args...)	(___bpf_reg_cnt5(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt7(t, x, args...)	(___bpf_reg_cnt6(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt8(t, x, args...)	(___bpf_reg_cnt7(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt9(t, x, args...)	(___bpf_reg_cnt8(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt10(t, x, args...)	(___bpf_reg_cnt9(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt11(t, x, args...)	(___bpf_reg_cnt10(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt12(t, x, args...)	(___bpf_reg_cnt11(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt(args...)	 ___bpf_apply(___bpf_reg_cnt, ___bpf_narg2(args))(args)
+
+#define ___bpf_union_arg(t, x, n) \
+	__builtin_choose_expr(sizeof(t) == 1, ({ union { __u8 z[1]; t x; } ___t = { .z = {ctx[n]}}; ___t.x; }), \
+	__builtin_choose_expr(sizeof(t) == 2, ({ union { __u16 z[1]; t x; } ___t = { .z = {ctx[n]} }; ___t.x; }), \
+	__builtin_choose_expr(sizeof(t) == 4, ({ union { __u32 z[1]; t x; } ___t = { .z = {ctx[n]} }; ___t.x; }), \
+	__builtin_choose_expr(sizeof(t) == 8, ({ union { __u64 z[1]; t x; } ___t = {.z = {ctx[n]} }; ___t.x; }), \
+	__builtin_choose_expr(sizeof(t) == 16, ({ union { __u64 z[2]; t x; } ___t = {.z = {ctx[n], ctx[n + 1]} }; ___t.x; }), \
+			      (void)0)))))
+
+#define ___bpf_ctx_arg0(n, args...)
+#define ___bpf_ctx_arg1(n, t, x)		, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt1(t, x))
+#define ___bpf_ctx_arg2(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt2(t, x, args)) ___bpf_ctx_arg1(n, args)
+#define ___bpf_ctx_arg3(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt3(t, x, args)) ___bpf_ctx_arg2(n, args)
+#define ___bpf_ctx_arg4(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt4(t, x, args)) ___bpf_ctx_arg3(n, args)
+#define ___bpf_ctx_arg5(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt5(t, x, args)) ___bpf_ctx_arg4(n, args)
+#define ___bpf_ctx_arg6(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt6(t, x, args)) ___bpf_ctx_arg5(n, args)
+#define ___bpf_ctx_arg7(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt7(t, x, args)) ___bpf_ctx_arg6(n, args)
+#define ___bpf_ctx_arg8(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt8(t, x, args)) ___bpf_ctx_arg7(n, args)
+#define ___bpf_ctx_arg9(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt9(t, x, args)) ___bpf_ctx_arg8(n, args)
+#define ___bpf_ctx_arg10(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt10(t, x, args)) ___bpf_ctx_arg9(n, args)
+#define ___bpf_ctx_arg11(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt11(t, x, args)) ___bpf_ctx_arg10(n, args)
+#define ___bpf_ctx_arg12(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt12(t, x, args)) ___bpf_ctx_arg11(n, args)
+#define ___bpf_ctx_arg(args...)	___bpf_apply(___bpf_ctx_arg, ___bpf_narg2(args))(___bpf_reg_cnt(args), args)
+
+#define ___bpf_ctx_decl0()
+#define ___bpf_ctx_decl1(t, x)			, t x
+#define ___bpf_ctx_decl2(t, x, args...)		, t x ___bpf_ctx_decl1(args)
+#define ___bpf_ctx_decl3(t, x, args...)		, t x ___bpf_ctx_decl2(args)
+#define ___bpf_ctx_decl4(t, x, args...)		, t x ___bpf_ctx_decl3(args)
+#define ___bpf_ctx_decl5(t, x, args...)		, t x ___bpf_ctx_decl4(args)
+#define ___bpf_ctx_decl6(t, x, args...)		, t x ___bpf_ctx_decl5(args)
+#define ___bpf_ctx_decl7(t, x, args...)		, t x ___bpf_ctx_decl6(args)
+#define ___bpf_ctx_decl8(t, x, args...)		, t x ___bpf_ctx_decl7(args)
+#define ___bpf_ctx_decl9(t, x, args...)		, t x ___bpf_ctx_decl8(args)
+#define ___bpf_ctx_decl10(t, x, args...)	, t x ___bpf_ctx_decl9(args)
+#define ___bpf_ctx_decl11(t, x, args...)	, t x ___bpf_ctx_decl10(args)
+#define ___bpf_ctx_decl12(t, x, args...)	, t x ___bpf_ctx_decl11(args)
+#define ___bpf_ctx_decl(args...)	___bpf_apply(___bpf_ctx_decl, ___bpf_narg2(args))(args)
+
+/*
+ * BPF_PROG2 is an enhanced version of BPF_PROG in order to handle struct
+ * arguments. Since each struct argument might take one or two u64 values
+ * in the trampoline stack, argument type size is needed to place proper number
+ * of u64 values for each argument. Therefore, BPF_PROG2 has different
+ * syntax from BPF_PROG. For example, for the following BPF_PROG syntax:
+ *
+ *   int BPF_PROG(test2, int a, int b) { ... }
+ *
+ * the corresponding BPF_PROG2 syntax is:
+ *
+ *   int BPF_PROG2(test2, int, a, int, b) { ... }
+ *
+ * where type and the corresponding argument name are separated by comma.
+ *
+ * Use BPF_PROG2 macro if one of the arguments might be a struct/union larger
+ * than 8 bytes:
+ *
+ *   int BPF_PROG2(test_struct_arg, struct bpf_testmod_struct_arg_1, a, int, b,
+ *		   int, c, int, d, struct bpf_testmod_struct_arg_2, e, int, ret)
+ *   {
+ *        // access a, b, c, d, e, and ret directly
+ *        ...
+ *   }
+ */
+#define BPF_PROG2(name, args...)						\
+name(unsigned long long *ctx);							\
+static __always_inline typeof(name(0))						\
+____##name(unsigned long long *ctx ___bpf_ctx_decl(args));			\
+typeof(name(0)) name(unsigned long long *ctx)					\
+{										\
+	return ____##name(ctx ___bpf_ctx_arg(args));				\
+}										\
+static __always_inline typeof(name(0))						\
+____##name(unsigned long long *ctx ___bpf_ctx_decl(args))
+
 struct pt_regs;
 
-#define ___bpf_kprobe_args0() ctx
-#define ___bpf_kprobe_args1(x) \
-	___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx)
-#define ___bpf_kprobe_args2(x, args...) \
-	___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx)
-#define ___bpf_kprobe_args3(x, args...) \
-	___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx)
-#define ___bpf_kprobe_args4(x, args...) \
-	___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx)
-#define ___bpf_kprobe_args5(x, args...) \
-	___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx)
-#define ___bpf_kprobe_args(args...) \
-	___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)
+#define ___bpf_kprobe_args0()           ctx
+#define ___bpf_kprobe_args1(x)          ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx)
+#define ___bpf_kprobe_args2(x, args...) ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx)
+#define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx)
+#define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx)
+#define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx)
+#define ___bpf_kprobe_args(args...)     ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)
 
 /*
  * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for
@@ -452,7 +567,7 @@ struct pt_regs;
  */
 #define BPF_KPROBE(name, args...)					    \
 name(struct pt_regs *ctx);						    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(struct pt_regs *ctx, ##args);				    \
 typeof(name(0)) name(struct pt_regs *ctx)				    \
 {									    \
@@ -461,14 +576,12 @@ typeof(name(0)) name(struct pt_regs *ctx)				    \
 	return ____##name(___bpf_kprobe_args(args));			    \
 	_Pragma("GCC diagnostic pop")					    \
 }									    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(struct pt_regs *ctx, ##args)
 
-#define ___bpf_kretprobe_args0() ctx
-#define ___bpf_kretprobe_args1(x) \
-	___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx)
-#define ___bpf_kretprobe_args(args...) \
-	___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args)
+#define ___bpf_kretprobe_args0()       ctx
+#define ___bpf_kretprobe_args1(x)      ___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx)
+#define ___bpf_kretprobe_args(args...) ___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args)
 
 /*
  * BPF_KRETPROBE is similar to BPF_KPROBE, except, it only provides optional
@@ -478,7 +591,7 @@ ____##name(struct pt_regs *ctx, ##args)
  */
 #define BPF_KRETPROBE(name, args...)					    \
 name(struct pt_regs *ctx);						    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(struct pt_regs *ctx, ##args);				    \
 typeof(name(0)) name(struct pt_regs *ctx)				    \
 {									    \
@@ -489,4 +602,69 @@ typeof(name(0)) name(struct pt_regs *ctx)				    \
 }									    \
 static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
 
+/* If kernel has CONFIG_ARCH_HAS_SYSCALL_WRAPPER, read pt_regs directly */
+#define ___bpf_syscall_args0()           ctx
+#define ___bpf_syscall_args1(x)          ___bpf_syscall_args0(), (void *)PT_REGS_PARM1_SYSCALL(regs)
+#define ___bpf_syscall_args2(x, args...) ___bpf_syscall_args1(args), (void *)PT_REGS_PARM2_SYSCALL(regs)
+#define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (void *)PT_REGS_PARM3_SYSCALL(regs)
+#define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (void *)PT_REGS_PARM4_SYSCALL(regs)
+#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (void *)PT_REGS_PARM5_SYSCALL(regs)
+#define ___bpf_syscall_args(args...)     ___bpf_apply(___bpf_syscall_args, ___bpf_narg(args))(args)
+
+/* If kernel doesn't have CONFIG_ARCH_HAS_SYSCALL_WRAPPER, we have to BPF_CORE_READ from pt_regs */
+#define ___bpf_syswrap_args0()           ctx
+#define ___bpf_syswrap_args1(x)          ___bpf_syswrap_args0(), (void *)PT_REGS_PARM1_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args2(x, args...) ___bpf_syswrap_args1(args), (void *)PT_REGS_PARM2_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args3(x, args...) ___bpf_syswrap_args2(args), (void *)PT_REGS_PARM3_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args4(x, args...) ___bpf_syswrap_args3(args), (void *)PT_REGS_PARM4_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args5(x, args...) ___bpf_syswrap_args4(args), (void *)PT_REGS_PARM5_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args(args...)     ___bpf_apply(___bpf_syswrap_args, ___bpf_narg(args))(args)
+
+/*
+ * BPF_KSYSCALL is a variant of BPF_KPROBE, which is intended for
+ * tracing syscall functions, like __x64_sys_close. It hides the underlying
+ * platform-specific low-level way of getting syscall input arguments from
+ * struct pt_regs, and provides a familiar typed and named function arguments
+ * syntax and semantics of accessing syscall input parameters.
+ *
+ * Original struct pt_regs * context is preserved as 'ctx' argument. This might
+ * be necessary when using BPF helpers like bpf_perf_event_output().
+ *
+ * At the moment BPF_KSYSCALL does not transparently handle all the calling
+ * convention quirks for the following syscalls:
+ *
+ * - mmap(): __ARCH_WANT_SYS_OLD_MMAP.
+ * - clone(): CONFIG_CLONE_BACKWARDS, CONFIG_CLONE_BACKWARDS2 and
+ *            CONFIG_CLONE_BACKWARDS3.
+ * - socket-related syscalls: __ARCH_WANT_SYS_SOCKETCALL.
+ * - compat syscalls.
+ *
+ * This may or may not change in the future. User needs to take extra measures
+ * to handle such quirks explicitly, if necessary.
+ *
+ * This macro relies on BPF CO-RE support and virtual __kconfig externs.
+ */
+#define BPF_KSYSCALL(name, args...)					    \
+name(struct pt_regs *ctx);						    \
+extern _Bool LINUX_HAS_SYSCALL_WRAPPER __kconfig;			    \
+static __always_inline typeof(name(0))					    \
+____##name(struct pt_regs *ctx, ##args);				    \
+typeof(name(0)) name(struct pt_regs *ctx)				    \
+{									    \
+	struct pt_regs *regs = LINUX_HAS_SYSCALL_WRAPPER		    \
+			       ? (struct pt_regs *)PT_REGS_PARM1(ctx)	    \
+			       : ctx;					    \
+	_Pragma("GCC diagnostic push")					    \
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")		    \
+	if (LINUX_HAS_SYSCALL_WRAPPER)					    \
+		return ____##name(___bpf_syswrap_args(args));		    \
+	else								    \
+		return ____##name(___bpf_syscall_args(args));		    \
+	_Pragma("GCC diagnostic pop")					    \
+}									    \
+static __always_inline typeof(name(0))					    \
+____##name(struct pt_regs *ctx, ##args)
+
+#define BPF_KPROBE_SYSCALL BPF_KSYSCALL
+
 #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

@@ -77,9 +77,8 @@ 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;
@@ -138,7 +137,7 @@ 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 +145,26 @@ 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);
@@ -305,6 +309,7 @@ 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 +322,7 @@ 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 +530,7 @@ 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 +567,7 @@ 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 +732,7 @@ 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 +743,7 @@ 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:
@@ -973,38 +983,81 @@ 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);
-			}
-		}
-		btf_dump_printf(d, "\n%s}", pfx(lvl));
-	}
+	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));
 }
 
 static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id,
@@ -1154,6 +1207,7 @@ 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 +1215,7 @@ 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 +1350,7 @@ 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 +1378,11 @@ 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;
@@ -1483,6 +1544,11 @@ 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;
@@ -1839,14 +1905,16 @@ 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;
 
 	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;
 	}
 
@@ -1959,7 +2027,8 @@ 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 +2045,13 @@ 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 +2064,7 @@ 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 +2072,31 @@ 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;
 }
 
@@ -2070,6 +2156,7 @@ 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 +2261,7 @@ 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;
@@ -2194,7 +2282,7 @@ 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);
 	if (size < 0)
@@ -2246,6 +2334,7 @@ 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 +2385,11 @@ 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/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;
 }
 
@@ -688,27 +687,29 @@ 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));
+	/* jump to fd_array 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 BTF fd store for vmlinux BTF */
+	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 4));
 	/* 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));
 	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_9, 0));
-	/* set a 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));
 	/* 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:
@@ -807,9 +808,8 @@ static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo,
 			       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));
+		/* jump over src_reg adjustment if imm is not 0, reuse BPF_REG_0 from move_blob2blob */
+		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 */
@@ -817,17 +817,20 @@ 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)));
+	/* skip src_reg adjustment */
 	emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3));
 clear_src_reg:
 	/* clear bpf_object__relocate_data's src_reg assignment, otherwise we get a verifier failure */
@@ -839,6 +842,22 @@ 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;
@@ -871,6 +890,15 @@ 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)
 {
 	int i, insn;
@@ -898,30 +926,32 @@ 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 +964,19 @@ 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 +984,9 @@ 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 +1011,17 @@ 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 +1043,27 @@ 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 +1076,33 @@ 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);
@@ -238,4 +238,3 @@ bool hashmap__delete(struct hashmap *map, const void *key,
 
 	return true;
 }
-

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 {
@@ -347,8 +247,6 @@ LIBBPF_0.3.0 {
 		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 +289,92 @@ 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;
+		btf_ext__raw_data;
+		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_1.1.0 {
+	global:
+		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;

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) {						    \

src/libbpf_internal.h

@@ -15,7 +15,6 @@
 #include <linux/err.h>
 #include <fcntl.h>
 #include <unistd.h>
-#include "libbpf_legacy.h"
 #include "relo_core.h"
 
 /* make sure libbpf doesn't use kernel-only integer typedefs */
@@ -73,6 +72,8 @@
 	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 +91,9 @@
 # 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 +102,17 @@
 #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 +158,15 @@ 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 +191,31 @@ 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 +315,57 @@ 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,
+	__FEAT_CNT,
+};
+
+int probe_memcg_account(void);
+bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id);
+int bump_rlimit_memlock(void);
 
 int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz);
 int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz);
 int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
 			 const char *str_sec, size_t str_len);
-
-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);
+int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level);
 
 struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf);
 void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type,
@@ -340,6 +379,13 @@ 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)					\
@@ -433,7 +479,10 @@ 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;
+typedef int (*kallsyms_cb_t)(unsigned long long sym_addr, char sym_type,
+			     const char *sym_name, void *ctx);
+
+int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *arg);
 
 /* handle direct returned errors */
 static inline int libbpf_err(int ret)
@@ -448,12 +497,8 @@ 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 +506,7 @@ 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 +516,7 @@ 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)
@@ -515,4 +551,29 @@ static inline int ensure_good_fd(int fd)
 	return fd;
 }
 
+/* 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);
+
 #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

@@ -17,72 +17,63 @@
 #include "libbpf.h"
 #include "libbpf_internal.h"
 
-static bool grep(const char *buffer, const char *pattern)
+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)
 {
-	return !!strstr(buffer, pattern);
-}
-
-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))
-		return 0;
-
-	if (sscanf(utsn.release, "%d.%d.%d",
-		   &version, &subversion, &patchlevel) != 3)
-		return 0;
-
-	return (version << 16) + (subversion << 8) + patchlevel;
-}
-
-static void
-probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
-	   size_t insns_cnt, char *buf, size_t buf_len, __u32 ifindex)
-{
-	struct bpf_load_program_attr xattr = {};
-	int fd;
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		.log_buf = log_buf,
+		.log_size = log_buf_sz,
+		.log_level = log_buf ? 1 : 0,
+	);
+	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:
@@ -103,44 +94,42 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
 	case BPF_PROG_TYPE_RAW_TRACEPOINT:
 	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
 	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
-	case BPF_PROG_TYPE_LIRC_MODE2:
 	case BPF_PROG_TYPE_SK_REUSEPORT:
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
-	case BPF_PROG_TYPE_TRACING:
-	case BPF_PROG_TYPE_STRUCT_OPS:
-	case BPF_PROG_TYPE_EXT:
-	case BPF_PROG_TYPE_LSM:
-	default:
 		break;
+	default:
+		return -EOPNOTSUPP;
 	}
 
-	xattr.prog_type = prog_type;
-	xattr.insns = insns;
-	xattr.insns_cnt = insns_cnt;
-	xattr.license = "GPL";
-	xattr.prog_ifindex = ifindex;
-
-	fd = bpf_load_program_xattr(&xattr, buf, buf_len);
+	fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, &opts);
+	err = -errno;
 	if (fd >= 0)
 		close(fd);
+	if (exp_err) {
+		if (fd >= 0 || err != exp_err)
+			return 0;
+		if (exp_msg && !strstr(buf, exp_msg))
+			return 0;
+		return 1;
+	}
+	return fd >= 0 ? 1 : 0;
 }
 
-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,
@@ -166,7 +155,7 @@ 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, NULL);
 
 	free(raw_btf);
 	return btf_fd;
@@ -199,17 +188,16 @@ static int load_local_storage_btf(void)
 				     strs, sizeof(strs));
 }
 
-bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
+static int probe_map_create(enum bpf_map_type map_type)
 {
-	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 +206,7 @@ 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:
@@ -237,17 +225,26 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 		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;
 		break;
-	case BPF_MAP_TYPE_UNSPEC:
+	case BPF_MAP_TYPE_STRUCT_OPS:
+		/* we'll get -ENOTSUPP for invalid BTF type ID for struct_ops */
+		opts.btf_vmlinux_value_type_id = 1;
+		exp_err = -524; /* -ENOTSUPP */
+		break;
+	case BPF_MAP_TYPE_BLOOM_FILTER:
+		key_size = 0;
+		max_entries = 1;
+		break;
 	case BPF_MAP_TYPE_HASH:
 	case BPF_MAP_TYPE_ARRAY:
 	case BPF_MAP_TYPE_PROG_ARRAY:
@@ -266,95 +263,101 @@ 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".
+	 * In both cases, provided combination of BPF program type and BPF
+	 * helper is not supported by the kernel.
+	 * In all other cases, probe_prog_load() above will either succeed (e.g.,
+	 * because BPF helper happens to accept no input arguments or it
+	 * accepts one input argument and initial PTR_TO_CTX is fine for
+	 * that), or we'll get some more specific BPF verifier error about
+	 * some unsatisfied conditions.
+	 */
+	if (ret == 0 && (strstr(buf, "invalid func ") || strstr(buf, "unknown func ")))
+		return 0;
+	return 1; /* assume supported */
 }

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 1
 
 #endif /* __LIBBPF_VERSION_H */

src/linker.c

@@ -210,6 +210,7 @@ void bpf_linker__free(struct bpf_linker *linker)
 	}
 	free(linker->secs);
 
+	free(linker->glob_syms);
 	free(linker);
 }
 
@@ -696,11 +697,6 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename,
 	return err;
 }
 
-static bool is_pow_of_2(size_t x)
-{
-	return x && (x & (x - 1)) == 0;
-}
-
 static int linker_sanity_check_elf(struct src_obj *obj)
 {
 	struct src_sec *sec;
@@ -1339,6 +1335,7 @@ recur:
 	case BTF_KIND_STRUCT:
 	case BTF_KIND_UNION:
 	case BTF_KIND_ENUM:
+	case BTF_KIND_ENUM64:
 	case BTF_KIND_FWD:
 	case BTF_KIND_FUNC:
 	case BTF_KIND_VAR:
@@ -1361,6 +1358,7 @@ recur:
 	case BTF_KIND_INT:
 	case BTF_KIND_FLOAT:
 	case BTF_KIND_ENUM:
+	case BTF_KIND_ENUM64:
 		/* ignore encoding for int and enum values for enum */
 		if (t1->size != t2->size) {
 			pr_warn("global '%s': incompatible %s '%s' size %u and %u\n",
@@ -1999,7 +1997,7 @@ add_sym:
 static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *obj)
 {
 	struct src_sec *src_symtab = &obj->secs[obj->symtab_sec_idx];
-	struct dst_sec *dst_symtab = &linker->secs[linker->symtab_sec_idx];
+	struct dst_sec *dst_symtab;
 	int i, err;
 
 	for (i = 1; i < obj->sec_cnt; i++) {
@@ -2032,6 +2030,9 @@ static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *ob
 			return -1;
 		}
 
+		/* add_dst_sec() above could have invalidated linker->secs */
+		dst_symtab = &linker->secs[linker->symtab_sec_idx];
+
 		/* shdr->sh_link points to SYMTAB */
 		dst_sec->shdr->sh_link = linker->symtab_sec_idx;
 
@@ -2650,6 +2651,7 @@ static int emit_elf_data_sec(struct bpf_linker *linker, const char *sec_name,
 
 static int finalize_btf(struct bpf_linker *linker)
 {
+	LIBBPF_OPTS(btf_dedup_opts, opts);
 	struct btf *btf = linker->btf;
 	const void *raw_data;
 	int i, j, id, err;
@@ -2686,7 +2688,8 @@ static int finalize_btf(struct bpf_linker *linker)
 		return err;
 	}
 
-	err = btf__dedup(linker->btf, linker->btf_ext, NULL);
+	opts.btf_ext = linker->btf_ext;
+	err = btf__dedup(linker->btf, &opts);
 	if (err) {
 		pr_warn("BTF dedup failed: %d\n", err);
 		return err;

src/netlink.c

@@ -27,6 +27,14 @@ typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);
 typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, libbpf_dump_nlmsg_t,
 			      void *cookie);
 
+struct xdp_link_info {
+	__u32 prog_id;
+	__u32 drv_prog_id;
+	__u32 hw_prog_id;
+	__u32 skb_prog_id;
+	__u8 attach_mode;
+};
+
 struct xdp_id_md {
 	int ifindex;
 	__u32 flags;
@@ -87,29 +95,75 @@ enum {
 	NL_DONE,
 };
 
+static int netlink_recvmsg(int sock, struct msghdr *mhdr, int flags)
+{
+	int len;
+
+	do {
+		len = recvmsg(sock, mhdr, flags);
+	} while (len < 0 && (errno == EINTR || errno == EAGAIN));
+
+	if (len < 0)
+		return -errno;
+	return len;
+}
+
+static int alloc_iov(struct iovec *iov, int len)
+{
+	void *nbuf;
+
+	nbuf = realloc(iov->iov_base, len);
+	if (!nbuf)
+		return -ENOMEM;
+
+	iov->iov_base = nbuf;
+	iov->iov_len = len;
+	return 0;
+}
+
 static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq,
 			       __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn,
 			       void *cookie)
 {
+	struct iovec iov = {};
+	struct msghdr mhdr = {
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+	};
 	bool multipart = true;
 	struct nlmsgerr *err;
 	struct nlmsghdr *nh;
-	char buf[4096];
 	int len, ret;
 
+	ret = alloc_iov(&iov, 4096);
+	if (ret)
+		goto done;
+
 	while (multipart) {
 start:
 		multipart = false;
-		len = recv(sock, buf, sizeof(buf), 0);
+		len = netlink_recvmsg(sock, &mhdr, MSG_PEEK | MSG_TRUNC);
 		if (len < 0) {
-			ret = -errno;
+			ret = len;
+			goto done;
+		}
+
+		if (len > iov.iov_len) {
+			ret = alloc_iov(&iov, len);
+			if (ret)
+				goto done;
+		}
+
+		len = netlink_recvmsg(sock, &mhdr, 0);
+		if (len < 0) {
+			ret = len;
 			goto done;
 		}
 
 		if (len == 0)
 			break;
 
-		for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
+		for (nh = (struct nlmsghdr *)iov.iov_base; NLMSG_OK(nh, len);
 		     nh = NLMSG_NEXT(nh, len)) {
 			if (nh->nlmsg_pid != nl_pid) {
 				ret = -LIBBPF_ERRNO__WRNGPID;
@@ -130,7 +184,8 @@ start:
 				libbpf_nla_dump_errormsg(nh);
 				goto done;
 			case NLMSG_DONE:
-				return 0;
+				ret = 0;
+				goto done;
 			default:
 				break;
 			}
@@ -142,15 +197,17 @@ start:
 				case NL_NEXT:
 					goto start;
 				case NL_DONE:
-					return 0;
+					ret = 0;
+					goto done;
 				default:
-					return ret;
+					goto done;
 				}
 			}
 		}
 	}
 	ret = 0;
 done:
+	free(iov.iov_base);
 	return ret;
 }
 
@@ -217,29 +274,26 @@ static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd,
 	return libbpf_netlink_send_recv(&req, NULL, NULL, NULL);
 }
 
-int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags,
-			     const struct bpf_xdp_set_link_opts *opts)
+int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts)
 {
-	int old_fd = -1, ret;
+	int old_prog_fd, err;
 
-	if (!OPTS_VALID(opts, bpf_xdp_set_link_opts))
+	if (!OPTS_VALID(opts, bpf_xdp_attach_opts))
 		return libbpf_err(-EINVAL);
 
-	if (OPTS_HAS(opts, old_fd)) {
-		old_fd = OPTS_GET(opts, old_fd, -1);
+	old_prog_fd = OPTS_GET(opts, old_prog_fd, 0);
+	if (old_prog_fd)
 		flags |= XDP_FLAGS_REPLACE;
-	}
+	else
+		old_prog_fd = -1;
 
-	ret = __bpf_set_link_xdp_fd_replace(ifindex, fd, old_fd, flags);
-	return libbpf_err(ret);
+	err = __bpf_set_link_xdp_fd_replace(ifindex, prog_fd, old_prog_fd, flags);
+	return libbpf_err(err);
 }
 
-int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
+int bpf_xdp_detach(int ifindex, __u32 flags, const struct bpf_xdp_attach_opts *opts)
 {
-	int ret;
-
-	ret = __bpf_set_link_xdp_fd_replace(ifindex, fd, 0, flags);
-	return libbpf_err(ret);
+	return bpf_xdp_attach(ifindex, -1, flags, opts);
 }
 
 static int __dump_link_nlmsg(struct nlmsghdr *nlh,
@@ -303,71 +357,71 @@ static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb)
 	return 0;
 }
 
-int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
-			  size_t info_size, __u32 flags)
+int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
 {
-	struct xdp_id_md xdp_id = {};
-	__u32 mask;
-	int ret;
 	struct libbpf_nla_req req = {
 		.nh.nlmsg_len      = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
 		.nh.nlmsg_type     = RTM_GETLINK,
 		.nh.nlmsg_flags    = NLM_F_DUMP | NLM_F_REQUEST,
 		.ifinfo.ifi_family = AF_PACKET,
 	};
+	struct xdp_id_md xdp_id = {};
+	int err;
 
-	if (flags & ~XDP_FLAGS_MASK || !info_size)
+	if (!OPTS_VALID(opts, bpf_xdp_query_opts))
+		return libbpf_err(-EINVAL);
+
+	if (xdp_flags & ~XDP_FLAGS_MASK)
 		return libbpf_err(-EINVAL);
 
 	/* Check whether the single {HW,DRV,SKB} mode is set */
-	flags &= (XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE);
-	mask = flags - 1;
-	if (flags && flags & mask)
+	xdp_flags &= XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE;
+	if (xdp_flags & (xdp_flags - 1))
 		return libbpf_err(-EINVAL);
 
 	xdp_id.ifindex = ifindex;
-	xdp_id.flags = flags;
+	xdp_id.flags = xdp_flags;
 
-	ret = libbpf_netlink_send_recv(&req, __dump_link_nlmsg,
+	err = libbpf_netlink_send_recv(&req, __dump_link_nlmsg,
 				       get_xdp_info, &xdp_id);
-	if (!ret) {
-		size_t sz = min(info_size, sizeof(xdp_id.info));
+	if (err)
+		return libbpf_err(err);
 
-		memcpy(info, &xdp_id.info, sz);
-		memset((void *) info + sz, 0, info_size - sz);
-	}
-
-	return libbpf_err(ret);
-}
-
-static __u32 get_xdp_id(struct xdp_link_info *info, __u32 flags)
-{
-	flags &= XDP_FLAGS_MODES;
-
-	if (info->attach_mode != XDP_ATTACHED_MULTI && !flags)
-		return info->prog_id;
-	if (flags & XDP_FLAGS_DRV_MODE)
-		return info->drv_prog_id;
-	if (flags & XDP_FLAGS_HW_MODE)
-		return info->hw_prog_id;
-	if (flags & XDP_FLAGS_SKB_MODE)
-		return info->skb_prog_id;
+	OPTS_SET(opts, prog_id, xdp_id.info.prog_id);
+	OPTS_SET(opts, drv_prog_id, xdp_id.info.drv_prog_id);
+	OPTS_SET(opts, hw_prog_id, xdp_id.info.hw_prog_id);
+	OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id);
+	OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode);
 
 	return 0;
 }
 
-int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags)
+int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id)
 {
-	struct xdp_link_info info;
+	LIBBPF_OPTS(bpf_xdp_query_opts, opts);
 	int ret;
 
-	ret = bpf_get_link_xdp_info(ifindex, &info, sizeof(info), flags);
-	if (!ret)
-		*prog_id = get_xdp_id(&info, flags);
+	ret = bpf_xdp_query(ifindex, flags, &opts);
+	if (ret)
+		return libbpf_err(ret);
 
-	return libbpf_err(ret);
+	flags &= XDP_FLAGS_MODES;
+
+	if (opts.attach_mode != XDP_ATTACHED_MULTI && !flags)
+		*prog_id = opts.prog_id;
+	else if (flags & XDP_FLAGS_DRV_MODE)
+		*prog_id = opts.drv_prog_id;
+	else if (flags & XDP_FLAGS_HW_MODE)
+		*prog_id = opts.hw_prog_id;
+	else if (flags & XDP_FLAGS_SKB_MODE)
+		*prog_id = opts.skb_prog_id;
+	else
+		*prog_id = 0;
+
+	return 0;
 }
 
+
 typedef int (*qdisc_config_t)(struct libbpf_nla_req *req);
 
 static int clsact_config(struct libbpf_nla_req *req)
@@ -533,11 +587,12 @@ static int get_tc_info(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn,
 
 static int tc_add_fd_and_name(struct libbpf_nla_req *req, int fd)
 {
-	struct bpf_prog_info info = {};
+	struct bpf_prog_info info;
 	__u32 info_len = sizeof(info);
 	char name[256];
 	int len, ret;
 
+	memset(&info, 0, info_len);
 	ret = bpf_obj_get_info_by_fd(fd, &info, &info_len);
 	if (ret < 0)
 		return ret;

src/relo_core.h

@@ -4,81 +4,10 @@
 #ifndef __RELO_CORE_H
 #define __RELO_CORE_H
 
-/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value
- * has to be adjusted by relocations.
- */
-enum bpf_core_relo_kind {
-	BPF_FIELD_BYTE_OFFSET = 0,	/* field byte offset */
-	BPF_FIELD_BYTE_SIZE = 1,	/* field size in bytes */
-	BPF_FIELD_EXISTS = 2,		/* field existence in target kernel */
-	BPF_FIELD_SIGNED = 3,		/* field signedness (0 - unsigned, 1 - signed) */
-	BPF_FIELD_LSHIFT_U64 = 4,	/* bitfield-specific left bitshift */
-	BPF_FIELD_RSHIFT_U64 = 5,	/* bitfield-specific right bitshift */
-	BPF_TYPE_ID_LOCAL = 6,		/* type ID in local BPF object */
-	BPF_TYPE_ID_TARGET = 7,		/* type ID in target kernel */
-	BPF_TYPE_EXISTS = 8,		/* type existence in target kernel */
-	BPF_TYPE_SIZE = 9,		/* type size in bytes */
-	BPF_ENUMVAL_EXISTS = 10,	/* enum value existence in target kernel */
-	BPF_ENUMVAL_VALUE = 11,		/* enum value integer value */
-};
-
-/* The minimum bpf_core_relo checked by the loader
- *
- * CO-RE relocation captures the following data:
- * - insn_off - instruction offset (in bytes) within a BPF program that needs
- *   its insn->imm field to be relocated with actual field info;
- * - type_id - BTF type ID of the "root" (containing) entity of a relocatable
- *   type or field;
- * - access_str_off - offset into corresponding .BTF string section. String
- *   interpretation depends on specific relocation kind:
- *     - for field-based relocations, string encodes an accessed field using
- *     a sequence of field and array indices, separated by colon (:). It's
- *     conceptually very close to LLVM's getelementptr ([0]) instruction's
- *     arguments for identifying offset to a field.
- *     - for type-based relocations, strings is expected to be just "0";
- *     - for enum value-based relocations, string contains an index of enum
- *     value within its enum type;
- *
- * Example to provide a better feel.
- *
- *   struct sample {
- *       int a;
- *       struct {
- *           int b[10];
- *       };
- *   };
- *
- *   struct sample *s = ...;
- *   int x = &s->a;     // encoded as "0:0" (a is field #0)
- *   int y = &s->b[5];  // encoded as "0:1:0:5" (anon struct is field #1,
- *                      // b is field #0 inside anon struct, accessing elem #5)
- *   int z = &s[10]->b; // encoded as "10:1" (ptr is used as an array)
- *
- * type_id for all relocs in this example  will capture BTF type id of
- * `struct sample`.
- *
- * Such relocation is emitted when using __builtin_preserve_access_index()
- * Clang built-in, passing expression that captures field address, e.g.:
- *
- * bpf_probe_read(&dst, sizeof(dst),
- *		  __builtin_preserve_access_index(&src->a.b.c));
- *
- * In this case Clang will emit field relocation recording necessary data to
- * be able to find offset of embedded `a.b.c` field within `src` struct.
- *
- *   [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction
- */
-struct bpf_core_relo {
-	__u32   insn_off;
-	__u32   type_id;
-	__u32   access_str_off;
-	enum bpf_core_relo_kind kind;
-};
+#include <linux/bpf.h>
 
 struct bpf_core_cand {
 	const struct btf *btf;
-	const struct btf_type *t;
-	const char *name;
 	__u32 id;
 };
 
@@ -88,13 +17,83 @@ struct bpf_core_cand_list {
 	int len;
 };
 
-int bpf_core_apply_relo_insn(const char *prog_name,
-			     struct bpf_insn *insn, int insn_idx,
-			     const struct bpf_core_relo *relo, int relo_idx,
-			     const struct btf *local_btf,
-			     struct bpf_core_cand_list *cands);
+#define BPF_CORE_SPEC_MAX_LEN 64
+
+/* represents BPF CO-RE field or array element accessor */
+struct bpf_core_accessor {
+	__u32 type_id;		/* struct/union type or array element type */
+	__u32 idx;		/* field index or array index */
+	const char *name;	/* field name or NULL for array accessor */
+};
+
+struct bpf_core_spec {
+	const struct btf *btf;
+	/* high-level spec: named fields and array indices only */
+	struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN];
+	/* original unresolved (no skip_mods_or_typedefs) root type ID */
+	__u32 root_type_id;
+	/* CO-RE relocation kind */
+	enum bpf_core_relo_kind relo_kind;
+	/* high-level spec length */
+	int len;
+	/* raw, low-level spec: 1-to-1 with accessor spec string */
+	int raw_spec[BPF_CORE_SPEC_MAX_LEN];
+	/* raw spec length */
+	int raw_len;
+	/* field bit offset represented by spec */
+	__u32 bit_offset;
+};
+
+struct bpf_core_relo_res {
+	/* expected value in the instruction, unless validate == false */
+	__u64 orig_val;
+	/* new value that needs to be patched up to */
+	__u64 new_val;
+	/* relocation unsuccessful, poison instruction, but don't fail load */
+	bool poison;
+	/* some relocations can't be validated against orig_val */
+	bool validate;
+	/* for field byte offset relocations or the forms:
+	 *     *(T *)(rX + <off>) = rY
+	 *     rX = *(T *)(rY + <off>),
+	 * we remember original and resolved field size to adjust direct
+	 * memory loads of pointers and integers; this is necessary for 32-bit
+	 * host kernel architectures, but also allows to automatically
+	 * relocate fields that were resized from, e.g., u32 to u64, etc.
+	 */
+	bool fail_memsz_adjust;
+	__u32 orig_sz;
+	__u32 orig_type_id;
+	__u32 new_sz;
+	__u32 new_type_id;
+};
+
+int __bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id,
+				const struct btf *targ_btf, __u32 targ_id, int level);
 int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id,
 			      const struct btf *targ_btf, __u32 targ_id);
+int __bpf_core_types_match(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf,
+			   __u32 targ_id, bool behind_ptr, int level);
+int bpf_core_types_match(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf,
+			 __u32 targ_id);
 
 size_t bpf_core_essential_name_len(const char *name);
+
+int bpf_core_calc_relo_insn(const char *prog_name,
+			    const struct bpf_core_relo *relo, int relo_idx,
+			    const struct btf *local_btf,
+			    struct bpf_core_cand_list *cands,
+			    struct bpf_core_spec *specs_scratch,
+			    struct bpf_core_relo_res *targ_res);
+
+int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn,
+			int insn_idx, const struct bpf_core_relo *relo,
+			int relo_idx, const struct bpf_core_relo_res *res);
+
+int bpf_core_parse_spec(const char *prog_name, const struct btf *btf,
+		        const struct bpf_core_relo *relo,
+		        struct bpf_core_spec *spec);
+
+int bpf_core_format_spec(char *buf, size_t buf_sz, const struct bpf_core_spec *spec);
+
 #endif

src/ringbuf.c

@@ -16,6 +16,7 @@
 #include <asm/barrier.h>
 #include <sys/mman.h>
 #include <sys/epoll.h>
+#include <time.h>
 
 #include "libbpf.h"
 #include "libbpf_internal.h"
@@ -39,6 +40,23 @@ struct ring_buffer {
 	int ring_cnt;
 };
 
+struct user_ring_buffer {
+	struct epoll_event event;
+	unsigned long *consumer_pos;
+	unsigned long *producer_pos;
+	void *data;
+	unsigned long mask;
+	size_t page_size;
+	int map_fd;
+	int epoll_fd;
+};
+
+/* 8-byte ring buffer header structure */
+struct ringbuf_hdr {
+	__u32 len;
+	__u32 pad;
+};
+
 static void ringbuf_unmap_ring(struct ring_buffer *rb, struct ring *r)
 {
 	if (r->consumer_pos) {
@@ -300,3 +318,256 @@ int ring_buffer__epoll_fd(const struct ring_buffer *rb)
 {
 	return rb->epoll_fd;
 }
+
+static void user_ringbuf_unmap_ring(struct user_ring_buffer *rb)
+{
+	if (rb->consumer_pos) {
+		munmap(rb->consumer_pos, rb->page_size);
+		rb->consumer_pos = NULL;
+	}
+	if (rb->producer_pos) {
+		munmap(rb->producer_pos, rb->page_size + 2 * (rb->mask + 1));
+		rb->producer_pos = NULL;
+	}
+}
+
+void user_ring_buffer__free(struct user_ring_buffer *rb)
+{
+	if (!rb)
+		return;
+
+	user_ringbuf_unmap_ring(rb);
+
+	if (rb->epoll_fd >= 0)
+		close(rb->epoll_fd);
+
+	free(rb);
+}
+
+static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd)
+{
+	struct bpf_map_info info;
+	__u32 len = sizeof(info);
+	void *tmp;
+	struct epoll_event *rb_epoll;
+	int err;
+
+	memset(&info, 0, sizeof(info));
+
+	err = bpf_obj_get_info_by_fd(map_fd, &info, &len);
+	if (err) {
+		err = -errno;
+		pr_warn("user ringbuf: failed to get map info for fd=%d: %d\n", map_fd, err);
+		return err;
+	}
+
+	if (info.type != BPF_MAP_TYPE_USER_RINGBUF) {
+		pr_warn("user ringbuf: map fd=%d is not BPF_MAP_TYPE_USER_RINGBUF\n", map_fd);
+		return -EINVAL;
+	}
+
+	rb->map_fd = map_fd;
+	rb->mask = info.max_entries - 1;
+
+	/* Map read-only consumer page */
+	tmp = mmap(NULL, rb->page_size, PROT_READ, MAP_SHARED, map_fd, 0);
+	if (tmp == MAP_FAILED) {
+		err = -errno;
+		pr_warn("user ringbuf: failed to mmap consumer page for map fd=%d: %d\n",
+			map_fd, err);
+		return err;
+	}
+	rb->consumer_pos = tmp;
+
+	/* Map read-write the producer page and data pages. We map the data
+	 * region as twice the total size of the ring buffer to allow the
+	 * simple reading and writing of samples that wrap around the end of
+	 * the buffer.  See the kernel implementation for details.
+	 */
+	tmp = mmap(NULL, rb->page_size + 2 * info.max_entries,
+		   PROT_READ | PROT_WRITE, MAP_SHARED, map_fd, rb->page_size);
+	if (tmp == MAP_FAILED) {
+		err = -errno;
+		pr_warn("user ringbuf: failed to mmap data pages for map fd=%d: %d\n",
+			map_fd, err);
+		return err;
+	}
+
+	rb->producer_pos = tmp;
+	rb->data = tmp + rb->page_size;
+
+	rb_epoll = &rb->event;
+	rb_epoll->events = EPOLLOUT;
+	if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, rb_epoll) < 0) {
+		err = -errno;
+		pr_warn("user ringbuf: failed to epoll add map fd=%d: %d\n", map_fd, err);
+		return err;
+	}
+
+	return 0;
+}
+
+struct user_ring_buffer *
+user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts)
+{
+	struct user_ring_buffer *rb;
+	int err;
+
+	if (!OPTS_VALID(opts, user_ring_buffer_opts))
+		return errno = EINVAL, NULL;
+
+	rb = calloc(1, sizeof(*rb));
+	if (!rb)
+		return errno = ENOMEM, NULL;
+
+	rb->page_size = getpagesize();
+
+	rb->epoll_fd = epoll_create1(EPOLL_CLOEXEC);
+	if (rb->epoll_fd < 0) {
+		err = -errno;
+		pr_warn("user ringbuf: failed to create epoll instance: %d\n", err);
+		goto err_out;
+	}
+
+	err = user_ringbuf_map(rb, map_fd);
+	if (err)
+		goto err_out;
+
+	return rb;
+
+err_out:
+	user_ring_buffer__free(rb);
+	return errno = -err, NULL;
+}
+
+static void user_ringbuf_commit(struct user_ring_buffer *rb, void *sample, bool discard)
+{
+	__u32 new_len;
+	struct ringbuf_hdr *hdr;
+	uintptr_t hdr_offset;
+
+	hdr_offset = rb->mask + 1 + (sample - rb->data) - BPF_RINGBUF_HDR_SZ;
+	hdr = rb->data + (hdr_offset & rb->mask);
+
+	new_len = hdr->len & ~BPF_RINGBUF_BUSY_BIT;
+	if (discard)
+		new_len |= BPF_RINGBUF_DISCARD_BIT;
+
+	/* Synchronizes with smp_load_acquire() in __bpf_user_ringbuf_peek() in
+	 * the kernel.
+	 */
+	__atomic_exchange_n(&hdr->len, new_len, __ATOMIC_ACQ_REL);
+}
+
+void user_ring_buffer__discard(struct user_ring_buffer *rb, void *sample)
+{
+	user_ringbuf_commit(rb, sample, true);
+}
+
+void user_ring_buffer__submit(struct user_ring_buffer *rb, void *sample)
+{
+	user_ringbuf_commit(rb, sample, false);
+}
+
+void *user_ring_buffer__reserve(struct user_ring_buffer *rb, __u32 size)
+{
+	__u32 avail_size, total_size, max_size;
+	/* 64-bit to avoid overflow in case of extreme application behavior */
+	__u64 cons_pos, prod_pos;
+	struct ringbuf_hdr *hdr;
+
+	/* Synchronizes with smp_store_release() in __bpf_user_ringbuf_peek() in
+	 * the kernel.
+	 */
+	cons_pos = smp_load_acquire(rb->consumer_pos);
+	/* Synchronizes with smp_store_release() in user_ringbuf_commit() */
+	prod_pos = smp_load_acquire(rb->producer_pos);
+
+	max_size = rb->mask + 1;
+	avail_size = max_size - (prod_pos - cons_pos);
+	/* Round up total size to a multiple of 8. */
+	total_size = (size + BPF_RINGBUF_HDR_SZ + 7) / 8 * 8;
+
+	if (total_size > max_size)
+		return errno = E2BIG, NULL;
+
+	if (avail_size < total_size)
+		return errno = ENOSPC, NULL;
+
+	hdr = rb->data + (prod_pos & rb->mask);
+	hdr->len = size | BPF_RINGBUF_BUSY_BIT;
+	hdr->pad = 0;
+
+	/* Synchronizes with smp_load_acquire() in __bpf_user_ringbuf_peek() in
+	 * the kernel.
+	 */
+	smp_store_release(rb->producer_pos, prod_pos + total_size);
+
+	return (void *)rb->data + ((prod_pos + BPF_RINGBUF_HDR_SZ) & rb->mask);
+}
+
+static __u64 ns_elapsed_timespec(const struct timespec *start, const struct timespec *end)
+{
+	__u64 start_ns, end_ns, ns_per_s = 1000000000;
+
+	start_ns = (__u64)start->tv_sec * ns_per_s + start->tv_nsec;
+	end_ns = (__u64)end->tv_sec * ns_per_s + end->tv_nsec;
+
+	return end_ns - start_ns;
+}
+
+void *user_ring_buffer__reserve_blocking(struct user_ring_buffer *rb, __u32 size, int timeout_ms)
+{
+	void *sample;
+	int err, ms_remaining = timeout_ms;
+	struct timespec start;
+
+	if (timeout_ms < 0 && timeout_ms != -1)
+		return errno = EINVAL, NULL;
+
+	if (timeout_ms != -1) {
+		err = clock_gettime(CLOCK_MONOTONIC, &start);
+		if (err)
+			return NULL;
+	}
+
+	do {
+		int cnt, ms_elapsed;
+		struct timespec curr;
+		__u64 ns_per_ms = 1000000;
+
+		sample = user_ring_buffer__reserve(rb, size);
+		if (sample)
+			return sample;
+		else if (errno != ENOSPC)
+			return NULL;
+
+		/* The kernel guarantees at least one event notification
+		 * delivery whenever at least one sample is drained from the
+		 * ring buffer in an invocation to bpf_ringbuf_drain(). Other
+		 * additional events may be delivered at any time, but only one
+		 * event is guaranteed per bpf_ringbuf_drain() invocation,
+		 * provided that a sample is drained, and the BPF program did
+		 * not pass BPF_RB_NO_WAKEUP to bpf_ringbuf_drain(). If
+		 * BPF_RB_FORCE_WAKEUP is passed to bpf_ringbuf_drain(), a
+		 * wakeup event will be delivered even if no samples are
+		 * drained.
+		 */
+		cnt = epoll_wait(rb->epoll_fd, &rb->event, 1, ms_remaining);
+		if (cnt < 0)
+			return NULL;
+
+		if (timeout_ms == -1)
+			continue;
+
+		err = clock_gettime(CLOCK_MONOTONIC, &curr);
+		if (err)
+			return NULL;
+
+		ms_elapsed = ns_elapsed_timespec(&start, &curr) / ns_per_ms;
+		ms_remaining = timeout_ms - ms_elapsed;
+	} while (ms_remaining > 0);
+
+	/* Try one more time to reserve a sample after the specified timeout has elapsed. */
+	return user_ring_buffer__reserve(rb, size);
+}

src/skel_internal.h

@@ -3,9 +3,29 @@
 #ifndef __SKEL_INTERNAL_H
 #define __SKEL_INTERNAL_H
 
+#ifdef __KERNEL__
+#include <linux/fdtable.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/slab.h>
+#include <linux/bpf.h>
+#else
 #include <unistd.h>
 #include <sys/syscall.h>
 #include <sys/mman.h>
+#include <stdlib.h>
+#include "bpf.h"
+#endif
+
+#ifndef __NR_bpf
+# if defined(__mips__) && defined(_ABIO32)
+#  define __NR_bpf 4355
+# elif defined(__mips__) && defined(_ABIN32)
+#  define __NR_bpf 6319
+# elif defined(__mips__) && defined(_ABI64)
+#  define __NR_bpf 5315
+# endif
+#endif
 
 /* This file is a base header for auto-generated *.lskel.h files.
  * Its contents will change and may become part of auto-generation in the future.
@@ -15,24 +35,23 @@
  * requested during loader program generation.
  */
 struct bpf_map_desc {
-	union {
-		/* input for the loader prog */
-		struct {
-			__aligned_u64 initial_value;
-			__u32 max_entries;
-		};
-		/* output of the loader prog */
-		struct {
-			int map_fd;
-		};
-	};
+	/* output of the loader prog */
+	int map_fd;
+	/* input for the loader prog */
+	__u32 max_entries;
+	__aligned_u64 initial_value;
 };
 struct bpf_prog_desc {
 	int prog_fd;
 };
 
+enum {
+	BPF_SKEL_KERNEL = (1ULL << 0),
+};
+
 struct bpf_loader_ctx {
-	size_t sz;
+	__u32 sz;
+	__u32 flags;
 	__u32 log_level;
 	__u32 log_size;
 	__u64 log_buf;
@@ -47,12 +66,144 @@ struct bpf_load_and_run_opts {
 	const char *errstr;
 };
 
+long kern_sys_bpf(__u32 cmd, void *attr, __u32 attr_size);
+
 static inline int skel_sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
 			  unsigned int size)
 {
+#ifdef __KERNEL__
+	return kern_sys_bpf(cmd, attr, size);
+#else
 	return syscall(__NR_bpf, cmd, attr, size);
+#endif
 }
 
+#ifdef __KERNEL__
+static inline int close(int fd)
+{
+	return close_fd(fd);
+}
+
+static inline void *skel_alloc(size_t size)
+{
+	struct bpf_loader_ctx *ctx = kzalloc(size, GFP_KERNEL);
+
+	if (!ctx)
+		return NULL;
+	ctx->flags |= BPF_SKEL_KERNEL;
+	return ctx;
+}
+
+static inline void skel_free(const void *p)
+{
+	kfree(p);
+}
+
+/* skel->bss/rodata maps are populated the following way:
+ *
+ * For kernel use:
+ * skel_prep_map_data() allocates kernel memory that kernel module can directly access.
+ * Generated lskel stores the pointer in skel->rodata and in skel->maps.rodata.initial_value.
+ * The loader program will perform probe_read_kernel() from maps.rodata.initial_value.
+ * skel_finalize_map_data() sets skel->rodata to point to actual value in a bpf map and
+ * does maps.rodata.initial_value = ~0ULL to signal skel_free_map_data() that kvfree
+ * is not nessary.
+ *
+ * For user space:
+ * skel_prep_map_data() mmaps anon memory into skel->rodata that can be accessed directly.
+ * Generated lskel stores the pointer in skel->rodata and in skel->maps.rodata.initial_value.
+ * The loader program will perform copy_from_user() from maps.rodata.initial_value.
+ * skel_finalize_map_data() remaps bpf array map value from the kernel memory into
+ * skel->rodata address.
+ *
+ * The "bpftool gen skeleton -L" command generates lskel.h that is suitable for
+ * both kernel and user space. The generated loader program does
+ * either bpf_probe_read_kernel() or bpf_copy_from_user() from initial_value
+ * depending on bpf_loader_ctx->flags.
+ */
+static inline void skel_free_map_data(void *p, __u64 addr, size_t sz)
+{
+	if (addr != ~0ULL)
+		kvfree(p);
+	/* When addr == ~0ULL the 'p' points to
+	 * ((struct bpf_array *)map)->value. See skel_finalize_map_data.
+	 */
+}
+
+static inline void *skel_prep_map_data(const void *val, size_t mmap_sz, size_t val_sz)
+{
+	void *addr;
+
+	addr = kvmalloc(val_sz, GFP_KERNEL);
+	if (!addr)
+		return NULL;
+	memcpy(addr, val, val_sz);
+	return addr;
+}
+
+static inline void *skel_finalize_map_data(__u64 *init_val, size_t mmap_sz, int flags, int fd)
+{
+	struct bpf_map *map;
+	void *addr = NULL;
+
+	kvfree((void *) (long) *init_val);
+	*init_val = ~0ULL;
+
+	/* At this point bpf_load_and_run() finished without error and
+	 * 'fd' is a valid bpf map FD. All sanity checks below should succeed.
+	 */
+	map = bpf_map_get(fd);
+	if (IS_ERR(map))
+		return NULL;
+	if (map->map_type != BPF_MAP_TYPE_ARRAY)
+		goto out;
+	addr = ((struct bpf_array *)map)->value;
+	/* the addr stays valid, since FD is not closed */
+out:
+	bpf_map_put(map);
+	return addr;
+}
+
+#else
+
+static inline void *skel_alloc(size_t size)
+{
+	return calloc(1, size);
+}
+
+static inline void skel_free(void *p)
+{
+	free(p);
+}
+
+static inline void skel_free_map_data(void *p, __u64 addr, size_t sz)
+{
+	munmap(p, sz);
+}
+
+static inline void *skel_prep_map_data(const void *val, size_t mmap_sz, size_t val_sz)
+{
+	void *addr;
+
+	addr = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE,
+		    MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	if (addr == (void *) -1)
+		return NULL;
+	memcpy(addr, val, val_sz);
+	return addr;
+}
+
+static inline void *skel_finalize_map_data(__u64 *init_val, size_t mmap_sz, int flags, int fd)
+{
+	void *addr;
+
+	addr = mmap((void *) (long) *init_val, mmap_sz, flags, MAP_SHARED | MAP_FIXED, fd, 0);
+	if (addr == (void *) -1)
+		return NULL;
+	return addr;
+}
+#endif
+
 static inline int skel_closenz(int fd)
 {
 	if (fd > 0)
@@ -60,27 +211,123 @@ static inline int skel_closenz(int fd)
 	return -EINVAL;
 }
 
+#ifndef offsetofend
+#define offsetofend(TYPE, MEMBER) \
+	(offsetof(TYPE, MEMBER)	+ sizeof((((TYPE *)0)->MEMBER)))
+#endif
+
+static inline int skel_map_create(enum bpf_map_type map_type,
+				  const char *map_name,
+				  __u32 key_size,
+				  __u32 value_size,
+				  __u32 max_entries)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, map_extra);
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_sz);
+
+	attr.map_type = map_type;
+	strncpy(attr.map_name, map_name, sizeof(attr.map_name));
+	attr.key_size = key_size;
+	attr.value_size = value_size;
+	attr.max_entries = max_entries;
+
+	return skel_sys_bpf(BPF_MAP_CREATE, &attr, attr_sz);
+}
+
+static inline int skel_map_update_elem(int fd, const void *key,
+				       const void *value, __u64 flags)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_sz);
+	attr.map_fd = fd;
+	attr.key = (long) key;
+	attr.value = (long) value;
+	attr.flags = flags;
+
+	return skel_sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, attr_sz);
+}
+
+static inline int skel_map_delete_elem(int fd, const void *key)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_sz);
+	attr.map_fd = fd;
+	attr.key = (long)key;
+
+	return skel_sys_bpf(BPF_MAP_DELETE_ELEM, &attr, attr_sz);
+}
+
+static inline int skel_map_get_fd_by_id(__u32 id)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_sz);
+	attr.map_id = id;
+
+	return skel_sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, attr_sz);
+}
+
+static inline int skel_raw_tracepoint_open(const char *name, int prog_fd)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint.prog_fd);
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_sz);
+	attr.raw_tracepoint.name = (long) name;
+	attr.raw_tracepoint.prog_fd = prog_fd;
+
+	return skel_sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, attr_sz);
+}
+
+static inline int skel_link_create(int prog_fd, int target_fd,
+				   enum bpf_attach_type attach_type)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, link_create.iter_info_len);
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_sz);
+	attr.link_create.prog_fd = prog_fd;
+	attr.link_create.target_fd = target_fd;
+	attr.link_create.attach_type = attach_type;
+
+	return skel_sys_bpf(BPF_LINK_CREATE, &attr, attr_sz);
+}
+
+#ifdef __KERNEL__
+#define set_err
+#else
+#define set_err err = -errno
+#endif
+
 static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
 {
+	const size_t prog_load_attr_sz = offsetofend(union bpf_attr, fd_array);
+	const size_t test_run_attr_sz = offsetofend(union bpf_attr, test);
 	int map_fd = -1, prog_fd = -1, key = 0, err;
 	union bpf_attr attr;
 
-	map_fd = bpf_create_map_name(BPF_MAP_TYPE_ARRAY, "__loader.map", 4,
-				     opts->data_sz, 1, 0);
+	err = map_fd = skel_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1);
 	if (map_fd < 0) {
 		opts->errstr = "failed to create loader map";
-		err = -errno;
+		set_err;
 		goto out;
 	}
 
-	err = bpf_map_update_elem(map_fd, &key, opts->data, 0);
+	err = skel_map_update_elem(map_fd, &key, opts->data, 0);
 	if (err < 0) {
 		opts->errstr = "failed to update loader map";
-		err = -errno;
+		set_err;
 		goto out;
 	}
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, prog_load_attr_sz);
 	attr.prog_type = BPF_PROG_TYPE_SYSCALL;
 	attr.insns = (long) opts->insns;
 	attr.insn_cnt = opts->insns_sz / sizeof(struct bpf_insn);
@@ -91,25 +338,27 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
 	attr.log_size = opts->ctx->log_size;
 	attr.log_buf = opts->ctx->log_buf;
 	attr.prog_flags = BPF_F_SLEEPABLE;
-	prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+	err = prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, prog_load_attr_sz);
 	if (prog_fd < 0) {
 		opts->errstr = "failed to load loader prog";
-		err = -errno;
+		set_err;
 		goto out;
 	}
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, test_run_attr_sz);
 	attr.test.prog_fd = prog_fd;
 	attr.test.ctx_in = (long) opts->ctx;
 	attr.test.ctx_size_in = opts->ctx->sz;
-	err = skel_sys_bpf(BPF_PROG_RUN, &attr, sizeof(attr));
+	err = skel_sys_bpf(BPF_PROG_RUN, &attr, test_run_attr_sz);
 	if (err < 0 || (int)attr.test.retval < 0) {
 		opts->errstr = "failed to execute loader prog";
 		if (err < 0) {
-			err = -errno;
+			set_err;
 		} else {
 			err = (int)attr.test.retval;
+#ifndef __KERNEL__
 			errno = -err;
+#endif
 		}
 		goto out;
 	}

src/usdt.bpf.h

@@ -0,0 +1,247 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+#ifndef __USDT_BPF_H__
+#define __USDT_BPF_H__
+
+#include <linux/errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+/* Below types and maps are internal implementation details of libbpf's USDT
+ * support and are subjects to change. Also, bpf_usdt_xxx() API helpers should
+ * be considered an unstable API as well and might be adjusted based on user
+ * feedback from using libbpf's USDT support in production.
+ */
+
+/* User can override BPF_USDT_MAX_SPEC_CNT to change default size of internal
+ * map that keeps track of USDT argument specifications. This might be
+ * necessary if there are a lot of USDT attachments.
+ */
+#ifndef BPF_USDT_MAX_SPEC_CNT
+#define BPF_USDT_MAX_SPEC_CNT 256
+#endif
+/* User can override BPF_USDT_MAX_IP_CNT to change default size of internal
+ * map that keeps track of IP (memory address) mapping to USDT argument
+ * specification.
+ * Note, if kernel supports BPF cookies, this map is not used and could be
+ * resized all the way to 1 to save a bit of memory.
+ */
+#ifndef BPF_USDT_MAX_IP_CNT
+#define BPF_USDT_MAX_IP_CNT (4 * BPF_USDT_MAX_SPEC_CNT)
+#endif
+
+enum __bpf_usdt_arg_type {
+	BPF_USDT_ARG_CONST,
+	BPF_USDT_ARG_REG,
+	BPF_USDT_ARG_REG_DEREF,
+};
+
+struct __bpf_usdt_arg_spec {
+	/* u64 scalar interpreted depending on arg_type, see below */
+	__u64 val_off;
+	/* arg location case, see bpf_udst_arg() for details */
+	enum __bpf_usdt_arg_type arg_type;
+	/* offset of referenced register within struct pt_regs */
+	short reg_off;
+	/* whether arg should be interpreted as signed value */
+	bool arg_signed;
+	/* number of bits that need to be cleared and, optionally,
+	 * sign-extended to cast arguments that are 1, 2, or 4 bytes
+	 * long into final 8-byte u64/s64 value returned to user
+	 */
+	char arg_bitshift;
+};
+
+/* should match USDT_MAX_ARG_CNT in usdt.c exactly */
+#define BPF_USDT_MAX_ARG_CNT 12
+struct __bpf_usdt_spec {
+	struct __bpf_usdt_arg_spec args[BPF_USDT_MAX_ARG_CNT];
+	__u64 usdt_cookie;
+	short arg_cnt;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, BPF_USDT_MAX_SPEC_CNT);
+	__type(key, int);
+	__type(value, struct __bpf_usdt_spec);
+} __bpf_usdt_specs SEC(".maps") __weak;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, BPF_USDT_MAX_IP_CNT);
+	__type(key, long);
+	__type(value, __u32);
+} __bpf_usdt_ip_to_spec_id SEC(".maps") __weak;
+
+extern const _Bool LINUX_HAS_BPF_COOKIE __kconfig;
+
+static __always_inline
+int __bpf_usdt_spec_id(struct pt_regs *ctx)
+{
+	if (!LINUX_HAS_BPF_COOKIE) {
+		long ip = PT_REGS_IP(ctx);
+		int *spec_id_ptr;
+
+		spec_id_ptr = bpf_map_lookup_elem(&__bpf_usdt_ip_to_spec_id, &ip);
+		return spec_id_ptr ? *spec_id_ptr : -ESRCH;
+	}
+
+	return bpf_get_attach_cookie(ctx);
+}
+
+/* Return number of USDT arguments defined for currently traced USDT. */
+__weak __hidden
+int bpf_usdt_arg_cnt(struct pt_regs *ctx)
+{
+	struct __bpf_usdt_spec *spec;
+	int spec_id;
+
+	spec_id = __bpf_usdt_spec_id(ctx);
+	if (spec_id < 0)
+		return -ESRCH;
+
+	spec = bpf_map_lookup_elem(&__bpf_usdt_specs, &spec_id);
+	if (!spec)
+		return -ESRCH;
+
+	return spec->arg_cnt;
+}
+
+/* Fetch USDT argument #*arg_num* (zero-indexed) and put its value into *res.
+ * Returns 0 on success; negative error, otherwise.
+ * On error *res is guaranteed to be set to zero.
+ */
+__weak __hidden
+int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res)
+{
+	struct __bpf_usdt_spec *spec;
+	struct __bpf_usdt_arg_spec *arg_spec;
+	unsigned long val;
+	int err, spec_id;
+
+	*res = 0;
+
+	spec_id = __bpf_usdt_spec_id(ctx);
+	if (spec_id < 0)
+		return -ESRCH;
+
+	spec = bpf_map_lookup_elem(&__bpf_usdt_specs, &spec_id);
+	if (!spec)
+		return -ESRCH;
+
+	if (arg_num >= BPF_USDT_MAX_ARG_CNT || arg_num >= spec->arg_cnt)
+		return -ENOENT;
+
+	arg_spec = &spec->args[arg_num];
+	switch (arg_spec->arg_type) {
+	case BPF_USDT_ARG_CONST:
+		/* Arg is just a constant ("-4@$-9" in USDT arg spec).
+		 * value is recorded in arg_spec->val_off directly.
+		 */
+		val = arg_spec->val_off;
+		break;
+	case BPF_USDT_ARG_REG:
+		/* Arg is in a register (e.g, "8@%rax" in USDT arg spec),
+		 * so we read the contents of that register directly from
+		 * struct pt_regs. To keep things simple user-space parts
+		 * record offsetof(struct pt_regs, <regname>) in arg_spec->reg_off.
+		 */
+		err = bpf_probe_read_kernel(&val, sizeof(val), (void *)ctx + arg_spec->reg_off);
+		if (err)
+			return err;
+		break;
+	case BPF_USDT_ARG_REG_DEREF:
+		/* Arg is in memory addressed by register, plus some offset
+		 * (e.g., "-4@-1204(%rbp)" in USDT arg spec). Register is
+		 * identified like with BPF_USDT_ARG_REG case, and the offset
+		 * is in arg_spec->val_off. We first fetch register contents
+		 * from pt_regs, then do another user-space probe read to
+		 * fetch argument value itself.
+		 */
+		err = bpf_probe_read_kernel(&val, sizeof(val), (void *)ctx + arg_spec->reg_off);
+		if (err)
+			return err;
+		err = bpf_probe_read_user(&val, sizeof(val), (void *)val + arg_spec->val_off);
+		if (err)
+			return err;
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+		val >>= arg_spec->arg_bitshift;
+#endif
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* cast arg from 1, 2, or 4 bytes to final 8 byte size clearing
+	 * necessary upper arg_bitshift bits, with sign extension if argument
+	 * is signed
+	 */
+	val <<= arg_spec->arg_bitshift;
+	if (arg_spec->arg_signed)
+		val = ((long)val) >> arg_spec->arg_bitshift;
+	else
+		val = val >> arg_spec->arg_bitshift;
+	*res = val;
+	return 0;
+}
+
+/* Retrieve user-specified cookie value provided during attach as
+ * bpf_usdt_opts.usdt_cookie. This serves the same purpose as BPF cookie
+ * returned by bpf_get_attach_cookie(). Libbpf's support for USDT is itself
+ * utilizing BPF cookies internally, so user can't use BPF cookie directly
+ * for USDT programs and has to use bpf_usdt_cookie() API instead.
+ */
+__weak __hidden
+long bpf_usdt_cookie(struct pt_regs *ctx)
+{
+	struct __bpf_usdt_spec *spec;
+	int spec_id;
+
+	spec_id = __bpf_usdt_spec_id(ctx);
+	if (spec_id < 0)
+		return 0;
+
+	spec = bpf_map_lookup_elem(&__bpf_usdt_specs, &spec_id);
+	if (!spec)
+		return 0;
+
+	return spec->usdt_cookie;
+}
+
+/* we rely on ___bpf_apply() and ___bpf_narg() macros already defined in bpf_tracing.h */
+#define ___bpf_usdt_args0() ctx
+#define ___bpf_usdt_args1(x) ___bpf_usdt_args0(), ({ long _x; bpf_usdt_arg(ctx, 0, &_x); (void *)_x; })
+#define ___bpf_usdt_args2(x, args...) ___bpf_usdt_args1(args), ({ long _x; bpf_usdt_arg(ctx, 1, &_x); (void *)_x; })
+#define ___bpf_usdt_args3(x, args...) ___bpf_usdt_args2(args), ({ long _x; bpf_usdt_arg(ctx, 2, &_x); (void *)_x; })
+#define ___bpf_usdt_args4(x, args...) ___bpf_usdt_args3(args), ({ long _x; bpf_usdt_arg(ctx, 3, &_x); (void *)_x; })
+#define ___bpf_usdt_args5(x, args...) ___bpf_usdt_args4(args), ({ long _x; bpf_usdt_arg(ctx, 4, &_x); (void *)_x; })
+#define ___bpf_usdt_args6(x, args...) ___bpf_usdt_args5(args), ({ long _x; bpf_usdt_arg(ctx, 5, &_x); (void *)_x; })
+#define ___bpf_usdt_args7(x, args...) ___bpf_usdt_args6(args), ({ long _x; bpf_usdt_arg(ctx, 6, &_x); (void *)_x; })
+#define ___bpf_usdt_args8(x, args...) ___bpf_usdt_args7(args), ({ long _x; bpf_usdt_arg(ctx, 7, &_x); (void *)_x; })
+#define ___bpf_usdt_args9(x, args...) ___bpf_usdt_args8(args), ({ long _x; bpf_usdt_arg(ctx, 8, &_x); (void *)_x; })
+#define ___bpf_usdt_args10(x, args...) ___bpf_usdt_args9(args), ({ long _x; bpf_usdt_arg(ctx, 9, &_x); (void *)_x; })
+#define ___bpf_usdt_args11(x, args...) ___bpf_usdt_args10(args), ({ long _x; bpf_usdt_arg(ctx, 10, &_x); (void *)_x; })
+#define ___bpf_usdt_args12(x, args...) ___bpf_usdt_args11(args), ({ long _x; bpf_usdt_arg(ctx, 11, &_x); (void *)_x; })
+#define ___bpf_usdt_args(args...) ___bpf_apply(___bpf_usdt_args, ___bpf_narg(args))(args)
+
+/*
+ * BPF_USDT serves the same purpose for USDT handlers as BPF_PROG for
+ * tp_btf/fentry/fexit BPF programs and BPF_KPROBE for kprobes.
+ * Original struct pt_regs * context is preserved as 'ctx' argument.
+ */
+#define BPF_USDT(name, args...)						    \
+name(struct pt_regs *ctx);						    \
+static __always_inline typeof(name(0))					    \
+____##name(struct pt_regs *ctx, ##args);				    \
+typeof(name(0)) name(struct pt_regs *ctx)				    \
+{									    \
+        _Pragma("GCC diagnostic push")					    \
+        _Pragma("GCC diagnostic ignored \"-Wint-conversion\"")		    \
+        return ____##name(___bpf_usdt_args(args));			    \
+        _Pragma("GCC diagnostic pop")					    \
+}									    \
+static __always_inline typeof(name(0))					    \
+____##name(struct pt_regs *ctx, ##args)
+
+#endif /* __USDT_BPF_H__ */

src/xsk.h

@@ -1,336 +0,0 @@
-/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
-
-/*
- * AF_XDP user-space access library.
- *
- * Copyright (c) 2018 - 2019 Intel Corporation.
- * Copyright (c) 2019 Facebook
- *
- * Author(s): Magnus Karlsson <magnus.karlsson@intel.com>
- */
-
-#ifndef __LIBBPF_XSK_H
-#define __LIBBPF_XSK_H
-
-#include <stdio.h>
-#include <stdint.h>
-#include <stdbool.h>
-#include <linux/if_xdp.h>
-
-#include "libbpf.h"
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-/* This whole API has been deprecated and moved to libxdp that can be found at
- * https://github.com/xdp-project/xdp-tools. The APIs are exactly the same so
- * it should just be linking with libxdp instead of libbpf for this set of
- * functionality. If not, please submit a bug report on the aforementioned page.
- */
-
-/* Load-Acquire Store-Release barriers used by the XDP socket
- * library. The following macros should *NOT* be considered part of
- * the xsk.h API, and is subject to change anytime.
- *
- * LIBRARY INTERNAL
- */
-
-#define __XSK_READ_ONCE(x) (*(volatile typeof(x) *)&x)
-#define __XSK_WRITE_ONCE(x, v) (*(volatile typeof(x) *)&x) = (v)
-
-#if defined(__i386__) || defined(__x86_64__)
-# define libbpf_smp_store_release(p, v)					\
-	do {								\
-		asm volatile("" : : : "memory");			\
-		__XSK_WRITE_ONCE(*p, v);				\
-	} while (0)
-# define libbpf_smp_load_acquire(p)					\
-	({								\
-		typeof(*p) ___p1 = __XSK_READ_ONCE(*p);			\
-		asm volatile("" : : : "memory");			\
-		___p1;							\
-	})
-#elif defined(__aarch64__)
-# define libbpf_smp_store_release(p, v)					\
-		asm volatile ("stlr %w1, %0" : "=Q" (*p) : "r" (v) : "memory")
-# define libbpf_smp_load_acquire(p)					\
-	({								\
-		typeof(*p) ___p1;					\
-		asm volatile ("ldar %w0, %1"				\
-			      : "=r" (___p1) : "Q" (*p) : "memory");	\
-		___p1;							\
-	})
-#elif defined(__riscv)
-# define libbpf_smp_store_release(p, v)					\
-	do {								\
-		asm volatile ("fence rw,w" : : : "memory");		\
-		__XSK_WRITE_ONCE(*p, v);				\
-	} while (0)
-# define libbpf_smp_load_acquire(p)					\
-	({								\
-		typeof(*p) ___p1 = __XSK_READ_ONCE(*p);			\
-		asm volatile ("fence r,rw" : : : "memory");		\
-		___p1;							\
-	})
-#endif
-
-#ifndef libbpf_smp_store_release
-#define libbpf_smp_store_release(p, v)					\
-	do {								\
-		__sync_synchronize();					\
-		__XSK_WRITE_ONCE(*p, v);				\
-	} while (0)
-#endif
-
-#ifndef libbpf_smp_load_acquire
-#define libbpf_smp_load_acquire(p)					\
-	({								\
-		typeof(*p) ___p1 = __XSK_READ_ONCE(*p);			\
-		__sync_synchronize();					\
-		___p1;							\
-	})
-#endif
-
-/* LIBRARY INTERNAL -- END */
-
-/* Do not access these members directly. Use the functions below. */
-#define DEFINE_XSK_RING(name) \
-struct name { \
-	__u32 cached_prod; \
-	__u32 cached_cons; \
-	__u32 mask; \
-	__u32 size; \
-	__u32 *producer; \
-	__u32 *consumer; \
-	void *ring; \
-	__u32 *flags; \
-}
-
-DEFINE_XSK_RING(xsk_ring_prod);
-DEFINE_XSK_RING(xsk_ring_cons);
-
-/* For a detailed explanation on the memory barriers associated with the
- * ring, please take a look at net/xdp/xsk_queue.h.
- */
-
-struct xsk_umem;
-struct xsk_socket;
-
-static inline __u64 *xsk_ring_prod__fill_addr(struct xsk_ring_prod *fill,
-					      __u32 idx)
-{
-	__u64 *addrs = (__u64 *)fill->ring;
-
-	return &addrs[idx & fill->mask];
-}
-
-static inline const __u64 *
-xsk_ring_cons__comp_addr(const struct xsk_ring_cons *comp, __u32 idx)
-{
-	const __u64 *addrs = (const __u64 *)comp->ring;
-
-	return &addrs[idx & comp->mask];
-}
-
-static inline struct xdp_desc *xsk_ring_prod__tx_desc(struct xsk_ring_prod *tx,
-						      __u32 idx)
-{
-	struct xdp_desc *descs = (struct xdp_desc *)tx->ring;
-
-	return &descs[idx & tx->mask];
-}
-
-static inline const struct xdp_desc *
-xsk_ring_cons__rx_desc(const struct xsk_ring_cons *rx, __u32 idx)
-{
-	const struct xdp_desc *descs = (const struct xdp_desc *)rx->ring;
-
-	return &descs[idx & rx->mask];
-}
-
-static inline int xsk_ring_prod__needs_wakeup(const struct xsk_ring_prod *r)
-{
-	return *r->flags & XDP_RING_NEED_WAKEUP;
-}
-
-static inline __u32 xsk_prod_nb_free(struct xsk_ring_prod *r, __u32 nb)
-{
-	__u32 free_entries = r->cached_cons - r->cached_prod;
-
-	if (free_entries >= nb)
-		return free_entries;
-
-	/* Refresh the local tail pointer.
-	 * cached_cons is r->size bigger than the real consumer pointer so
-	 * that this addition can be avoided in the more frequently
-	 * executed code that computs free_entries in the beginning of
-	 * this function. Without this optimization it whould have been
-	 * free_entries = r->cached_prod - r->cached_cons + r->size.
-	 */
-	r->cached_cons = libbpf_smp_load_acquire(r->consumer);
-	r->cached_cons += r->size;
-
-	return r->cached_cons - r->cached_prod;
-}
-
-static inline __u32 xsk_cons_nb_avail(struct xsk_ring_cons *r, __u32 nb)
-{
-	__u32 entries = r->cached_prod - r->cached_cons;
-
-	if (entries == 0) {
-		r->cached_prod = libbpf_smp_load_acquire(r->producer);
-		entries = r->cached_prod - r->cached_cons;
-	}
-
-	return (entries > nb) ? nb : entries;
-}
-
-static inline __u32 xsk_ring_prod__reserve(struct xsk_ring_prod *prod, __u32 nb, __u32 *idx)
-{
-	if (xsk_prod_nb_free(prod, nb) < nb)
-		return 0;
-
-	*idx = prod->cached_prod;
-	prod->cached_prod += nb;
-
-	return nb;
-}
-
-static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, __u32 nb)
-{
-	/* Make sure everything has been written to the ring before indicating
-	 * this to the kernel by writing the producer pointer.
-	 */
-	libbpf_smp_store_release(prod->producer, *prod->producer + nb);
-}
-
-static inline __u32 xsk_ring_cons__peek(struct xsk_ring_cons *cons, __u32 nb, __u32 *idx)
-{
-	__u32 entries = xsk_cons_nb_avail(cons, nb);
-
-	if (entries > 0) {
-		*idx = cons->cached_cons;
-		cons->cached_cons += entries;
-	}
-
-	return entries;
-}
-
-static inline void xsk_ring_cons__cancel(struct xsk_ring_cons *cons, __u32 nb)
-{
-	cons->cached_cons -= nb;
-}
-
-static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, __u32 nb)
-{
-	/* Make sure data has been read before indicating we are done
-	 * with the entries by updating the consumer pointer.
-	 */
-	libbpf_smp_store_release(cons->consumer, *cons->consumer + nb);
-
-}
-
-static inline void *xsk_umem__get_data(void *umem_area, __u64 addr)
-{
-	return &((char *)umem_area)[addr];
-}
-
-static inline __u64 xsk_umem__extract_addr(__u64 addr)
-{
-	return addr & XSK_UNALIGNED_BUF_ADDR_MASK;
-}
-
-static inline __u64 xsk_umem__extract_offset(__u64 addr)
-{
-	return addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT;
-}
-
-static inline __u64 xsk_umem__add_offset_to_addr(__u64 addr)
-{
-	return xsk_umem__extract_addr(addr) + xsk_umem__extract_offset(addr);
-}
-
-LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
-int xsk_umem__fd(const struct xsk_umem *umem);
-LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
-int xsk_socket__fd(const struct xsk_socket *xsk);
-
-#define XSK_RING_CONS__DEFAULT_NUM_DESCS      2048
-#define XSK_RING_PROD__DEFAULT_NUM_DESCS      2048
-#define XSK_UMEM__DEFAULT_FRAME_SHIFT    12 /* 4096 bytes */
-#define XSK_UMEM__DEFAULT_FRAME_SIZE     (1 << XSK_UMEM__DEFAULT_FRAME_SHIFT)
-#define XSK_UMEM__DEFAULT_FRAME_HEADROOM 0
-#define XSK_UMEM__DEFAULT_FLAGS 0
-
-struct xsk_umem_config {
-	__u32 fill_size;
-	__u32 comp_size;
-	__u32 frame_size;
-	__u32 frame_headroom;
-	__u32 flags;
-};
-
-LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
-int xsk_setup_xdp_prog(int ifindex, int *xsks_map_fd);
-LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
-int xsk_socket__update_xskmap(struct xsk_socket *xsk, int xsks_map_fd);
-
-/* Flags for the libbpf_flags field. */
-#define XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD (1 << 0)
-
-struct xsk_socket_config {
-	__u32 rx_size;
-	__u32 tx_size;
-	__u32 libbpf_flags;
-	__u32 xdp_flags;
-	__u16 bind_flags;
-};
-
-/* Set config to NULL to get the default configuration. */
-LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
-int xsk_umem__create(struct xsk_umem **umem,
-		     void *umem_area, __u64 size,
-		     struct xsk_ring_prod *fill,
-		     struct xsk_ring_cons *comp,
-		     const struct xsk_umem_config *config);
-LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
-int xsk_umem__create_v0_0_2(struct xsk_umem **umem,
-			    void *umem_area, __u64 size,
-			    struct xsk_ring_prod *fill,
-			    struct xsk_ring_cons *comp,
-			    const struct xsk_umem_config *config);
-LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
-int xsk_umem__create_v0_0_4(struct xsk_umem **umem,
-			    void *umem_area, __u64 size,
-			    struct xsk_ring_prod *fill,
-			    struct xsk_ring_cons *comp,
-			    const struct xsk_umem_config *config);
-LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
-int xsk_socket__create(struct xsk_socket **xsk,
-		       const char *ifname, __u32 queue_id,
-		       struct xsk_umem *umem,
-		       struct xsk_ring_cons *rx,
-		       struct xsk_ring_prod *tx,
-		       const struct xsk_socket_config *config);
-LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
-int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
-			      const char *ifname,
-			      __u32 queue_id, struct xsk_umem *umem,
-			      struct xsk_ring_cons *rx,
-			      struct xsk_ring_prod *tx,
-			      struct xsk_ring_prod *fill,
-			      struct xsk_ring_cons *comp,
-			      const struct xsk_socket_config *config);
-
-/* Returns 0 for success and -EBUSY if the umem is still in use. */
-LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
-int xsk_umem__delete(struct xsk_umem *umem);
-LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
-void xsk_socket__delete(struct xsk_socket *xsk);
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif
-
-#endif /* __LIBBPF_XSK_H */

travis-ci

@@ -0,0 +1 @@
+ci

travis-ci/managers/test_compile.sh

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

travis-ci/vmtest/build_pahole.sh

@@ -1,34 +0,0 @@
-#!/bin/bash
-
-set -eu
-
-source $(cd $(dirname $0) && pwd)/helpers.sh
-
-CWD=$(pwd)
-REPO_PATH=$1
-PAHOLE_ORIGIN=${PAHOLE_ORIGIN:-https://git.kernel.org/pub/scm/devel/pahole/pahole.git}
-PAHOLE_BRANCH=${PAHOLE_BRANCH:-master}
-
-travis_fold start build_pahole "Building pahole ${PAHOLE_ORIGIN} ${PAHOLE_BRANCH}"
-
-mkdir -p ${REPO_PATH}
-cd ${REPO_PATH}
-git init
-git remote add origin ${PAHOLE_ORIGIN}
-git fetch origin
-git checkout ${PAHOLE_BRANCH}
-
-# temporary work-around to bump pahole to 1.22 before it is officially released
-sed -i 's/DDWARVES_MINOR_VERSION=21/DDWARVES_MINOR_VERSION=22/' CMakeLists.txt
-
-mkdir -p build
-cd build
-cmake -DCMAKE_BUILD_TYPE=RelWithDebInfo -D__LIB=lib ..
-make -j$((4*$(nproc))) all
-sudo make install
-
-export LD_LIBRARY_PATH=${LD_LIBRARY_PATH:-}:/usr/local/lib
-ldd $(which pahole)
-pahole --version
-
-travis_fold end build_pahole

travis-ci/vmtest/checkout_latest_kernel.sh

@@ -1,54 +0,0 @@
-#!/bin/bash
-
-set -eu
-
-source $(cd $(dirname $0) && pwd)/helpers.sh
-
-CWD=$(pwd)
-LIBBPF_PATH=$(pwd)
-REPO_PATH=$1
-
-KERNEL_ORIGIN=${KERNEL_ORIGIN:-https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git}
-KERNEL_BRANCH=${KERNEL_BRANCH:-CHECKPOINT}
-if [[ "${KERNEL_BRANCH}" = 'CHECKPOINT' ]]; then
-  echo "using CHECKPOINT sha1"
-  LINUX_SHA=$(cat ${LIBBPF_PATH}/CHECKPOINT-COMMIT)
-else
-  echo "using ${KERNEL_BRANCH} sha1"
-  LINUX_SHA=$(git ls-remote ${KERNEL_ORIGIN} ${KERNEL_BRANCH} | awk '{print $1}')
-fi
-SNAPSHOT_URL=${KERNEL_ORIGIN}/snapshot/bpf-next-${LINUX_SHA}.tar.gz
-
-echo REPO_PATH = ${REPO_PATH}
-
-echo KERNEL_ORIGIN = ${KERNEL_ORIGIN}
-echo LINUX_SHA = ${LINUX_SHA}
-echo SNAPSHOT_URL = ${SNAPSHOT_URL}
-
-if [ ! -d "${REPO_PATH}" ]; then
-	echo
-	travis_fold start pull_kernel_srcs "Fetching kernel sources"
-
-	mkdir -p $(dirname "${REPO_PATH}")
-	cd $(dirname "${REPO_PATH}")
-	# attempt to fetch desired bpf-next repo snapshot
-	if wget -nv ${SNAPSHOT_URL} && tar xf bpf-next-${LINUX_SHA}.tar.gz --totals ; then
-		mv bpf-next-${LINUX_SHA} $(basename ${REPO_PATH})
-	else
-		# but fallback to git fetch approach if that fails
-		mkdir -p $(basename ${REPO_PATH})
-		cd $(basename ${REPO_PATH})
-		git init
-		git remote add bpf-next ${KERNEL_ORIGIN}
-		# try shallow clone first
-		git fetch --depth 32 bpf-next
-		# check if desired SHA exists
-		if ! git cat-file -e ${LINUX_SHA}^{commit} ; then
-			# if not, fetch all of bpf-next; slow and painful
-			git fetch bpf-next
-		fi
-		git reset --hard ${LINUX_SHA}
-	fi
-
-	travis_fold end pull_kernel_srcs
-fi

travis-ci/vmtest/configs/INDEX

@@ -1,8 +0,0 @@
-INDEX	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/INDEX
-libbpf-vmtest-rootfs-2020.09.27.tar.zst	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/libbpf-vmtest-rootfs-2020.09.27.tar.zst
-vmlinux-4.9.0.zst	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/vmlinux-4.9.0.zst
-vmlinux-5.5.0-rc6.zst	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/vmlinux-5.5.0-rc6.zst
-vmlinux-5.5.0.zst	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/vmlinux-5.5.0.zst
-vmlinuz-5.5.0-rc6	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/vmlinuz-5.5.0-rc6
-vmlinuz-5.5.0	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/vmlinuz-5.5.0
-vmlinuz-4.9.0	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/vmlinuz-4.9.0

travis-ci/vmtest/configs/blacklist/BLACKLIST-latest

@@ -1,5 +0,0 @@
-# TEMPORARY
-get_stack_raw_tp    # spams with kernel warnings until next bpf -> bpf-next merge
-stacktrace_build_id_nmi
-stacktrace_build_id
-task_fd_query_rawtp