netdata_patch_1_2_2: Apply patch to run on Debian 10

Upstream bpf-next should be good, so no temporary blocked tests should remain.

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

@@ -0,0 +1,60 @@
+#!/bin/bash
+
+set -euo pipefail
+
+THISDIR="$(cd $(dirname $0) && pwd)"
+
+source ${THISDIR}/helpers.sh
+
+foldable start prepare_selftests "Building selftests"
+
+LIBBPF_PATH="${REPO_ROOT}"
+
+llvm_default_version() {
+	echo "16"
+}
+
+llvm_latest_version() {
+	echo "17"
+}
+
+LLVM_VERSION=$(llvm_default_version)
+if [[ "${LLVM_VERSION}" == $(llvm_latest_version) ]]; then
+	REPO_DISTRO_SUFFIX=""
+else
+	REPO_DISTRO_SUFFIX="-${LLVM_VERSION}"
+fi
+
+echo "deb https://apt.llvm.org/focal/ llvm-toolchain-focal${REPO_DISTRO_SUFFIX} main" \
+	| sudo tee /etc/apt/sources.list.d/llvm.list
+
+PREPARE_SELFTESTS_SCRIPT=${THISDIR}/prepare_selftests-${KERNEL}.sh
+if [ -f "${PREPARE_SELFTESTS_SCRIPT}" ]; then
+	(cd "${REPO_ROOT}/${REPO_PATH}/tools/testing/selftests/bpf" && ${PREPARE_SELFTESTS_SCRIPT})
+fi
+
+if [[ "${KERNEL}" = 'LATEST' ]]; then
+	VMLINUX_H=
+else
+	VMLINUX_H=${THISDIR}/vmlinux.h
+fi
+
+cd ${REPO_ROOT}/${REPO_PATH}
+make headers
+make \
+	CLANG=clang-${LLVM_VERSION} \
+	LLC=llc-${LLVM_VERSION} \
+	LLVM_STRIP=llvm-strip-${LLVM_VERSION} \
+	VMLINUX_BTF="${VMLINUX_BTF}" \
+	VMLINUX_H=${VMLINUX_H} \
+	-C "${REPO_ROOT}/${REPO_PATH}/tools/testing/selftests/bpf" \
+	-j $((4*$(nproc))) > /dev/null
+cd -
+mkdir ${LIBBPF_PATH}/selftests
+cp -R "${REPO_ROOT}/${REPO_PATH}/tools/testing/selftests/bpf" \
+	${LIBBPF_PATH}/selftests
+cd ${LIBBPF_PATH}
+rm selftests/bpf/.gitignore
+git add selftests
+
+foldable end prepare_selftests

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

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

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

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

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

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

.github/actions/vmtest/action.yml

@@ -0,0 +1,99 @@
+name: 'vmtest'
+description: 'Build + run vmtest'
+inputs:
+  kernel:
+    description: 'kernel version or LATEST'
+    required: true
+    default: 'LATEST'
+  arch:
+    description: 'what arch to test'
+    required: true
+    default: 'x86_64'
+  pahole:
+    description: 'pahole rev or master'
+    required: true
+    default: 'master'
+runs:
+  using: "composite"
+  steps:
+    # setup environment
+    - name: Setup environment
+      uses: libbpf/ci/setup-build-env@main
+      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@main
+      with:
+        repo: 'https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git'
+        rev: ${{ env.CHECKPOINT }}
+        dest: '${{ github.workspace }}/.kernel'
+    - name: Patch kernel source
+      uses: libbpf/ci/patch-kernel@main
+      with:
+        patches-root: '${{ github.workspace }}/ci/diffs'
+        repo-root: '.kernel'
+    - name: Prepare to build BPF selftests
+      shell: bash
+      run: |
+        source $GITHUB_ACTION_PATH/../../../ci/vmtest/helpers.sh
+        foldable start "Prepare building selftest"
+        cd .kernel
+        cat tools/testing/selftests/bpf/config \
+            tools/testing/selftests/bpf/config.${{ inputs.arch }} > .config
+        make olddefconfig && make prepare
+        cd -
+        foldable end
+    # 2. if kernel == LATEST, build kernel image from tree
+    - name: Build kernel image
+      if: ${{ inputs.kernel == 'LATEST' }}
+      shell: bash
+      run: |
+        source $GITHUB_ACTION_PATH/../../../ci/vmtest/helpers.sh
+        foldable start "Build Kernel Image"
+        cd .kernel
+        make -j $((4*$(nproc))) all > /dev/null
+        cp vmlinux ${{ github.workspace }}
+        cd -
+        foldable end
+    # else, just download prebuilt kernel image
+    - name: Download prebuilt kernel
+      if: ${{ inputs.kernel != 'LATEST' }}
+      uses: libbpf/ci/download-vmlinux@main
+      with:
+        kernel: ${{ inputs.kernel }}
+        arch: ${{ inputs.arch }}
+    # 3. build selftests
+    - name: Build BPF selftests
+      uses: ./.github/actions/build-selftests
+      with:
+        repo-path: '.kernel'
+        kernel: ${{ inputs.kernel }}
+    # 4. prepare rootfs
+    - name: prepare rootfs
+      uses: libbpf/ci/prepare-rootfs@main
+      env:
+        KBUILD_OUTPUT: '.kernel'
+      with:
+        project-name: 'libbpf'
+        arch: ${{ inputs.arch }}
+        kernel: ${{ inputs.kernel }}
+        kernel-root: '.kernel'
+        kbuild-output: ${{ env.KBUILD_OUTPUT }}
+        image-output: '/tmp/root.img'
+    # 5. run selftest in QEMU
+    - name: Run selftests
+      env:
+        KERNEL: ${{ inputs.kernel }}
+        REPO_ROOT: ${{ github.workspace }}
+      uses: libbpf/ci/run-qemu@main
+      with:
+        arch: ${{ inputs.arch }}
+        img: '/tmp/root.img'
+        vmlinuz: 'vmlinuz'
+        kernel-root: '.kernel'

.github/workflows/build.yml

@@ -42,7 +42,7 @@ jobs:
           - name: gcc-12
             target: RUN_GCC12
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         name: Checkout
       - uses: ./.github/actions/setup
         name: Setup
@@ -53,7 +53,7 @@ jobs:
 
   ubuntu:
     runs-on: ubuntu-latest
-    name: Ubuntu Build (${{ matrix.arch }})
+    name: Ubuntu Focal Build (${{ matrix.arch }})
     strategy:
       fail-fast: false
       matrix:
@@ -61,32 +61,31 @@ jobs:
           - arch: aarch64
           - arch: ppc64le
           - arch: s390x
-          - arch: amd64
+          - arch: x86
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         name: Checkout
-
-      - name: Setup QEMU
-        uses: docker/setup-qemu-action@v3
-        with:
-          image: tonistiigi/binfmt:qemu-v8.1.5
-
       - uses: ./.github/actions/setup
         name: Pre-Setup
-
       - run: source /tmp/ci_setup && sudo -E $CI_ROOT/managers/ubuntu.sh
-        if: matrix.arch == 'amd64'
+        if: matrix.arch == 'x86'
         name: Setup
-
+      - uses: uraimo/run-on-arch-action@v2.0.5
-      - name: Build in docker
+        name: Build in docker
-        if: matrix.arch != 'amd64'
+        if: matrix.arch != 'x86'
-        run: |
+        with:
-          cp /tmp/ci_setup ${GITHUB_WORKSPACE}
+          distro:
-          docker run --rm \
+            ubuntu20.04
-                 --platform linux/${{ matrix.arch }} \
+          arch:
-                 -v ${GITHUB_WORKSPACE}:${GITHUB_WORKSPACE} \
+            ${{ matrix.arch }}
-                 -e GITHUB_WORKSPACE=${GITHUB_WORKSPACE} \
+          setup:
-                 -w /ci/workspace \
+            cp /tmp/ci_setup $GITHUB_WORKSPACE
-                 ubuntu:noble \
+          dockerRunArgs: |
-                 ${GITHUB_WORKSPACE}/ci/build-in-docker.sh
+            --volume "${GITHUB_WORKSPACE}:${GITHUB_WORKSPACE}"
-
+          shell: /bin/bash
+          install: |
+            export DEBIAN_FRONTEND=noninteractive
+            export TZ="America/Los_Angeles"
+            apt-get update -y
+            apt-get install -y tzdata build-essential sudo
+          run: source ${GITHUB_WORKSPACE}/ci_setup && $CI_ROOT/managers/ubuntu.sh

.github/workflows/cifuzz.yml

@@ -33,7 +33,7 @@ jobs:
           dry-run: false
           sanitizer: ${{ matrix.sanitizer }}
       - name: Upload Crash
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v1
         if: failure() && steps.build.outcome == 'success'
         with:
           name: ${{ matrix.sanitizer }}-artifacts

.github/workflows/codeql.yml

@@ -17,7 +17,7 @@ permissions:
 jobs:
   analyze:
     name: Analyze
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04
     concurrency:
       group: ${{ github.workflow }}-${{ matrix.language }}-${{ github.ref }}
       cancel-in-progress: true
@@ -32,7 +32,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
 
       - name: Initialize CodeQL
         uses: github/codeql-action/init@v2

.github/workflows/coverity.yml

@@ -1,30 +1,30 @@
 name: libbpf-ci-coverity
 
 on:
-  push:
-    branches:
-      - master
   schedule:
     - cron:  '0 18 * * *'
 
+
 jobs:
   coverity:
     runs-on: ubuntu-latest
+    if: github.repository == 'libbpf/libbpf'
     name: Coverity
-    env:
-      COVERITY_SCAN_TOKEN: ${{ secrets.COVERITY_SCAN_TOKEN }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: ./.github/actions/setup
       - name: Run coverity
-        if: ${{ env.COVERITY_SCAN_TOKEN }}
         run: |
+          source "${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}
+          foldable end
           scripts/coverity.sh
         env:
+          COVERITY_SCAN_TOKEN: ${{ secrets.COVERITY_SCAN_TOKEN }}
           COVERITY_SCAN_PROJECT_NAME: libbpf
           COVERITY_SCAN_BUILD_COMMAND_PREPEND: 'cd src/'
           COVERITY_SCAN_BUILD_COMMAND: 'make'

.github/workflows/lint.yml

@@ -12,7 +12,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
       - name: Run ShellCheck
         uses: ludeeus/action-shellcheck@master
         env:

.github/workflows/ondemand.yml

@@ -3,29 +3,34 @@ name: ondemand
 on:
   workflow_dispatch:
     inputs:
-      arch:
+      kernel-origin:
-        default: 'x86_64'
+        description: 'git repo for linux kernel'
+        default: 'https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git'
         required: true
-      llvm-version:
+      kernel-rev:
-        default: '18'
+        description: 'rev/tag/branch for linux kernel'
-        required: true
-      kernel:
-        default: 'LATEST'
-        required: true
-      pahole:
         default: "master"
         required: true
-      runs-on:
+      pahole-origin:
-        default: 'ubuntu-24.04'
+        description: 'git repo for pahole'
+        default: 'https://git.kernel.org/pub/scm/devel/pahole/pahole.git'
+        required: true
+      pahole-rev:
+        description: 'ref/tag/branch for pahole'
+        default: "master"
         required: true
 
 jobs:
   vmtest:
-    name: ${{ inputs.kernel }} kernel llvm-${{ inputs.llvm-version }} pahole@${{ inputs.pahole }}
+    runs-on: ubuntu-latest
-    uses: ./.github/workflows/vmtest.yml
+    name: vmtest with customized pahole/Kernel
-    with:
+    steps:
-      runs_on: ${{ inputs.runs-on }}
+      - uses: actions/checkout@v3
-      kernel: ${{ inputs.kernel }}
+      - uses: ./.github/actions/setup
-      arch: ${{ inputs.arch }}
+      - uses: ./.github/actions/vmtest
-      llvm-version: ${{ inputs.llvm-version }}
+        with:
-      pahole: ${{ inputs.pahole }}
+          kernel: 'LATEST'
+          kernel-rev: ${{ github.event.inputs.kernel-rev }}
+          kernel-origin: ${{ github.event.inputs.kernel-origin }}
+          pahole: ${{ github.event.inputs.pahole-rev }}
+          pahole-origin: ${{ github.event.inputs.pahole-origin }}

.github/workflows/pahole.yml

@@ -0,0 +1,20 @@
+name: pahole-staging
+
+on:
+  schedule:
+    - cron:  '0 18 * * *'
+
+
+jobs:
+  vmtest:
+    runs-on: ubuntu-20.04
+    name: Kernel LATEST + staging pahole
+    env:
+      STAGING: tmp.master
+    steps:
+      - uses: actions/checkout@v3
+      - uses: ./.github/actions/setup
+      - uses: ./.github/actions/vmtest
+        with:
+          kernel: LATEST
+          pahole: $STAGING

.github/workflows/test.yml

@@ -1,36 +1,42 @@
 name: libbpf-ci
 
-on:
+on: 
   pull_request:
   push:
   schedule:
     - cron:  '0 18 * * *'
 
-concurrency:
+concurrency: 
   group: ci-test-${{ github.head_ref }}
   cancel-in-progress: true
 
 jobs:
   vmtest:
+    runs-on: ${{ matrix.runs_on }}
+    name: Kernel ${{ matrix.kernel }} on ${{ matrix.runs_on }} + selftests
     strategy:
       fail-fast: false
       matrix:
         include:
           - kernel: 'LATEST'
-            runs_on: 'ubuntu-24.04'
+            runs_on: ubuntu-20.04
+            arch: 'x86_64'
+          - kernel: '5.5.0'
+            runs_on: ubuntu-20.04
+            arch: 'x86_64'
+          - kernel: '4.9.0'
+            runs_on: ubuntu-20.04
             arch: 'x86_64'
-            llvm-version: '18'
-            pahole: 'master'
           - kernel: 'LATEST'
-            runs_on: 'ubuntu-24.04'
+            runs_on: s390x
-            arch: 'x86_64'
+            arch: 's390x'
-            llvm-version: '18'
+    steps:
-            pahole: 'tmp.master'
+      - uses: actions/checkout@v3
-    name: Linux ${{ matrix.kernel }} llvm-${{ matrix.llvm-version }}
+        name: Checkout
-    uses: ./.github/workflows/vmtest.yml
+      - uses: ./.github/actions/setup
-    with:
+        name: Setup
-      runs_on: ${{ matrix.runs_on }}
+      - uses: ./.github/actions/vmtest
-      kernel: ${{ matrix.kernel }}
+        name: vmtest
-      arch: ${{ matrix.arch }}
+        with:
-      llvm-version: ${{ matrix.llvm-version }}
+          kernel: ${{ matrix.kernel }}
-      pahole: ${{ matrix.pahole }}
+          arch: ${{ matrix.arch }}

.github/workflows/vmtest.yml

@@ -1,117 +0,0 @@
-name: 'Build kernel and selftests/bpf, run selftests via vmtest'
-
-on:
-  workflow_call:
-    inputs:
-      runs_on:
-        required: true
-        default: 'ubuntu-24.04'
-        type: string
-      arch:
-        description: 'what arch to test'
-        required: true
-        default: 'x86_64'
-        type: string
-      kernel:
-        description: 'kernel version or LATEST'
-        required: true
-        default: 'LATEST'
-        type: string
-      pahole:
-        description: 'pahole rev or branch'
-        required: false
-        default: 'master'
-        type: string
-      llvm-version:
-        description: 'llvm version'
-        required: false
-        default: '18'
-        type: string
-jobs:
-  vmtest:
-    name: pahole@${{ inputs.pahole }}
-    runs-on: ${{ inputs.runs_on }}
-    steps:
-
-      - uses: actions/checkout@v4
-
-      - name: Setup environment
-        uses: libbpf/ci/setup-build-env@v3
-        with:
-          pahole: ${{ inputs.pahole }}
-          arch: ${{ inputs.arch }}
-          llvm-version: ${{ inputs.llvm-version }}
-
-      - name: Get checkpoint commit
-        shell: bash
-        run: |
-          cat CHECKPOINT-COMMIT
-          echo "CHECKPOINT=$(cat CHECKPOINT-COMMIT)" >> $GITHUB_ENV
-
-      - name: Get kernel source at checkpoint
-        uses: libbpf/ci/get-linux-source@v3
-        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@v3
-        with:
-          patches-root: '${{ github.workspace }}/ci/diffs'
-          repo-root: '.kernel'
-
-      - name: Configure kernel build
-        shell: bash
-        run: |
-          cd .kernel
-          cat tools/testing/selftests/bpf/config \
-              tools/testing/selftests/bpf/config.${{ inputs.arch }} > .config
-          # this file might or might not exist depending on kernel version
-          cat tools/testing/selftests/bpf/config.vm >> .config || :
-          make olddefconfig && make prepare
-          cd -
-
-      - name: Build kernel image
-        if: ${{ inputs.kernel == 'LATEST' }}
-        shell: bash
-        run: |
-          cd .kernel
-          make -j $((4*$(nproc))) all
-          cp vmlinux ${{ github.workspace }}
-          cd -
-
-      - name: Download prebuilt kernel
-        if: ${{ inputs.kernel != 'LATEST' }}
-        uses: libbpf/ci/download-vmlinux@v3
-        with:
-          kernel: ${{ inputs.kernel }}
-          arch: ${{ inputs.arch }}
-
-      - name: Build selftests/bpf
-        uses: libbpf/ci/build-selftests@v3
-        env:
-          MAX_MAKE_JOBS: 32
-          VMLINUX_BTF: ${{ github.workspace }}/vmlinux
-          VMLINUX_H: ${{ inputs.kernel != 'LATEST' && format('{0}/.github/actions/build-selftests/vmlinux.h', github.workspace) || '' }}
-        with:
-          arch: ${{ inputs.arch }}
-          kernel-root: ${{ github.workspace }}/.kernel
-          llvm-version: ${{ inputs.llvm-version }}
-
-      - name: Run selftests
-        env:
-          ALLOWLIST_FILE: /tmp/allowlist
-          DENYLIST_FILE: /tmp/denylist
-          KERNEL: ${{ inputs.kernel }}
-          VMLINUX: ${{ github.workspace }}/vmlinux
-          LLVM_VERSION: ${{ inputs.llvm-version }}
-          SELFTESTS_BPF: ${{ github.workspace }}/.kernel/tools/testing/selftests/bpf
-          VMTEST_CONFIGS: ${{ github.workspace }}/ci/vmtest/configs
-        uses: libbpf/ci/run-vmtest@v3
-        with:
-          arch: ${{ inputs.arch }}
-          kbuild-output: ${{ github.workspace }}/.kernel
-          kernel-root: ${{ github.workspace }}/.kernel
-          vmlinuz: ${{ inputs.arch }}/vmlinuz-${{ inputs.kernel }}
-

.mailmap

@@ -1,22 +0,0 @@
-Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com>
-Antoine Tenart <atenart@kernel.org> <antoine.tenart@bootlin.com>
-Benjamin Tissoires <bentiss@kernel.org> <benjamin.tissoires@redhat.com>
-Björn Töpel <bjorn@kernel.org> <bjorn.topel@intel.com>
-Changbin Du <changbin.du@intel.com> <changbin.du@gmail.com>
-Colin Ian King <colin.i.king@gmail.com> <colin.king@canonical.com>
-Dan Carpenter <error27@gmail.com> <dan.carpenter@oracle.com>
-Geliang Tang <geliang@kernel.org> <geliang.tang@suse.com>
-Herbert Xu <herbert@gondor.apana.org.au>
-Jakub Kicinski <kuba@kernel.org> <jakub.kicinski@netronome.com>
-Jesper Dangaard Brouer <hawk@kernel.org> <brouer@redhat.com>
-Kees Cook <kees@kernel.org> <keescook@chromium.org>
-Leo Yan <leo.yan@linux.dev> <leo.yan@linaro.org>
-Mark Starovoytov <mstarovo@pm.me> <mstarovoitov@marvell.com>
-Maxim Mikityanskiy <maxtram95@gmail.com> <maximmi@mellanox.com>
-Maxim Mikityanskiy <maxtram95@gmail.com> <maximmi@nvidia.com>
-Puranjay Mohan <puranjay@kernel.org> <puranjay12@gmail.com>
-Quentin Monnet <qmo@kernel.org> <quentin@isovalent.com>
-Quentin Monnet <qmo@kernel.org> <quentin.monnet@netronome.com>
-Stanislav Fomichev <sdf@fomichev.me> <sdf@google.com>
-Vadim Fedorenko <vadim.fedorenko@linux.dev> <vadfed@meta.com>
-Vadim Fedorenko <vadim.fedorenko@linux.dev> <vfedorenko@novek.ru>

.readthedocs.yaml

@@ -5,11 +5,6 @@
 # Required
 version: 2
 
-build:
-  os: "ubuntu-22.04"
-  tools:
-    python: "3.11"
-
 # Build documentation in the docs/ directory with Sphinx
 sphinx:
   builder: html
@@ -22,5 +17,6 @@ formats:
 
 # Optionally set the version of Python and requirements required to build your docs
 python:
+   version: 3.7
    install:
-   - requirements: docs/sphinx/requirements.txt
+   - requirements: docs/sphinx/requirements.txt

BPF-CHECKPOINT-COMMIT

@@ -1 +1 @@
-b4432656b36e5cc1d50a1f2dc15357543add530e
+496720b7cfb6574a8f6f4d434f23e3d1e6cfaeb9

CHECKPOINT-COMMIT

@@ -1 +1 @@
-9325d53fe9adff354b6a93fda5f38c165947da0f
+a3e7e6b17946f48badce98d7ac360678a0ea7393

README.md

@@ -146,7 +146,7 @@ Distributions packaging libbpf from this mirror:
   - [Gentoo](https://packages.gentoo.org/packages/dev-libs/libbpf)
   - [Debian](https://packages.debian.org/source/sid/libbpf)
   - [Arch](https://archlinux.org/packages/core/x86_64/libbpf/)
-  - [Ubuntu](https://packages.ubuntu.com/source/jammy/libbpf)
+  - [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:

ci/build-in-docker.sh

@@ -1,14 +0,0 @@
-#!/bin/bash
-
-set -euo pipefail
-
-export DEBIAN_FRONTEND=noninteractive
-export TZ="America/Los_Angeles"
-
-apt-get update -y
-apt-get install -y tzdata build-essential sudo
-source ${GITHUB_WORKSPACE}/ci_setup
-
-$CI_ROOT/managers/ubuntu.sh
-
-exit 0

ci/diffs/0001-s390-define-RUNTIME_DISCARD_EXIT-to-fix-link-error-w.patch

@@ -0,0 +1,70 @@
+From 6fba14e2ed9d159f76b23fa5c16f3ea99acbc003 Mon Sep 17 00:00:00 2001
+From: Masahiro Yamada <masahiroy@kernel.org>
+Date: Thu, 5 Jan 2023 12:13:06 +0900
+Subject: [PATCH] s390: define RUNTIME_DISCARD_EXIT to fix link error with GNU
+ ld < 2.36
+
+Nathan Chancellor reports that the s390 vmlinux fails to link with
+GNU ld < 2.36 since commit 99cb0d917ffa ("arch: fix broken BuildID
+for arm64 and riscv").
+
+It happens for defconfig, or more specifically for CONFIG_EXPOLINE=y.
+
+  $ s390x-linux-gnu-ld --version | head -n1
+  GNU ld (GNU Binutils for Debian) 2.35.2
+  $ make -s ARCH=s390 CROSS_COMPILE=s390x-linux-gnu- allnoconfig
+  $ ./scripts/config -e CONFIG_EXPOLINE
+  $ make -s ARCH=s390 CROSS_COMPILE=s390x-linux-gnu- olddefconfig
+  $ make -s ARCH=s390 CROSS_COMPILE=s390x-linux-gnu-
+  `.exit.text' referenced in section `.s390_return_reg' of drivers/base/dd.o: defined in discarded section `.exit.text' of drivers/base/dd.o
+  make[1]: *** [scripts/Makefile.vmlinux:34: vmlinux] Error 1
+  make: *** [Makefile:1252: vmlinux] Error 2
+
+arch/s390/kernel/vmlinux.lds.S wants to keep EXIT_TEXT:
+
+        .exit.text : {
+                EXIT_TEXT
+        }
+
+But, at the same time, EXIT_TEXT is thrown away by DISCARD because
+s390 does not define RUNTIME_DISCARD_EXIT.
+
+I still do not understand why the latter wins after 99cb0d917ffa,
+but defining RUNTIME_DISCARD_EXIT seems correct because the comment
+line in arch/s390/kernel/vmlinux.lds.S says:
+
+        /*
+         * .exit.text is discarded at runtime, not link time,
+         * to deal with references from __bug_table
+         */
+
+Nathan also found that binutils commit 21401fc7bf67 ("Duplicate output
+sections in scripts") cured this issue, so we cannot reproduce it with
+binutils 2.36+, but it is better to not rely on it.
+
+Fixes: 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv")
+Link: https://lore.kernel.org/all/Y7Jal56f6UBh1abE@dev-arch.thelio-3990X/
+Reported-by: Nathan Chancellor <nathan@kernel.org>
+Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
+Link: https://lore.kernel.org/r/20230105031306.1455409-1-masahiroy@kernel.org
+Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
+---
+ arch/s390/kernel/vmlinux.lds.S | 2 ++
+ 1 file changed, 2 insertions(+)
+
+diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
+index 5ea3830af0cc..6e101e6f499d 100644
+--- a/arch/s390/kernel/vmlinux.lds.S
++++ b/arch/s390/kernel/vmlinux.lds.S
+@@ -17,6 +17,8 @@
+ /* Handle ro_after_init data on our own. */
+ #define RO_AFTER_INIT_DATA
+ 
++#define RUNTIME_DISCARD_EXIT
++
+ #define EMITS_PT_NOTE
+ 
+ #include <asm-generic/vmlinux.lds.h>
+-- 
+2.30.2
+

ci/diffs/0001-selftests-bpf-Check-whether-to-run-selftest.patch

@@ -0,0 +1,37 @@
+From ff8be5401b359e23ec2b74184034082564bac7c5 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Daniel=20M=C3=BCller?= <deso@posteo.net>
+Date: Thu, 25 May 2023 16:04:20 -0700
+Subject: [PATCH] selftests/bpf: Check whether to run selftest
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+The sockopt test invokes test__start_subtest and then unconditionally
+asserts the success. That means that even if deny-listed, any test will
+still run and potentially fail.
+Evaluate the return value of test__start_subtest() to achieve the
+desired behavior, as other tests do.
+
+Signed-off-by: Daniel Müller <deso@posteo.net>
+---
+ tools/testing/selftests/bpf/prog_tests/sockopt.c | 4 +++-
+ 1 file changed, 3 insertions(+), 1 deletion(-)
+
+diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt.c b/tools/testing/selftests/bpf/prog_tests/sockopt.c
+index 33dd45..9e6a5e 100644
+--- a/tools/testing/selftests/bpf/prog_tests/sockopt.c
++++ b/tools/testing/selftests/bpf/prog_tests/sockopt.c
+@@ -1060,7 +1060,9 @@ void test_sockopt(void)
+ 		return;
+ 
+ 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+-		test__start_subtest(tests[i].descr);
++		if (!test__start_subtest(tests[i].descr))
++			continue;
++
+ 		ASSERT_OK(run_test(cgroup_fd, &tests[i]), tests[i].descr);
+ 	}
+ 
+-- 
+2.34.1
+

ci/diffs/0001-selftests-bpf-Select-CONFIG_FUNCTION_ERROR_INJECTION.patch

@@ -0,0 +1,46 @@
+From a8dfde09c90109e3a98af54847e91bde7dc2d5c2 Mon Sep 17 00:00:00 2001
+From: Song Liu <song@kernel.org>
+Date: Tue, 13 Dec 2022 14:05:00 -0800
+Subject: [PATCH] selftests/bpf: Select CONFIG_FUNCTION_ERROR_INJECTION
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+BPF selftests require CONFIG_FUNCTION_ERROR_INJECTION to work. However,
+CONFIG_FUNCTION_ERROR_INJECTION is no longer 'y' by default after recent
+changes. As a result, we are seeing errors like the following from BPF CI:
+
+   bpf_testmod_test_read() is not modifiable
+   __x64_sys_setdomainname is not sleepable
+   __x64_sys_getpgid is not sleepable
+
+Fix this by explicitly selecting CONFIG_FUNCTION_ERROR_INJECTION in the
+selftest config.
+
+Fixes: a4412fdd49dc ("error-injection: Add prompt for function error injection")
+Reported-by: Daniel Müller <deso@posteo.net>
+Signed-off-by: Song Liu <song@kernel.org>
+Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
+Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
+Acked-by: Daniel Müller <deso@posteo.net>
+Link: https://lore.kernel.org/bpf/20221213220500.3427947-1-song@kernel.org
+Signed-off-by: Daniel Müller <deso@posteo.net>
+---
+ tools/testing/selftests/bpf/config | 1 +
+ 1 file changed, 1 insertion(+)
+
+diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
+index 612f69..63cd4a 100644
+--- a/tools/testing/selftests/bpf/config
++++ b/tools/testing/selftests/bpf/config
+@@ -16,6 +16,7 @@ CONFIG_CRYPTO_USER_API_HASH=y
+ CONFIG_DYNAMIC_FTRACE=y
+ CONFIG_FPROBE=y
+ CONFIG_FTRACE_SYSCALLS=y
++CONFIG_FUNCTION_ERROR_INJECTION=y
+ CONFIG_FUNCTION_TRACER=y
+ CONFIG_GENEVE=y
+ CONFIG_IKCONFIG=y
+-- 
+2.30.2
+

ci/diffs/0001-selftests-bpf-set-test-path-for-token-obj_priv_impli.patch

@@ -1,85 +0,0 @@
-From e3a4f5092e847ec00e2b66c060f2cef52b8d0177 Mon Sep 17 00:00:00 2001
-From: Ihor Solodrai <ihor.solodrai@pm.me>
-Date: Thu, 14 Nov 2024 12:49:34 -0800
-Subject: [PATCH bpf-next] selftests/bpf: set test path for
- token/obj_priv_implicit_token_envvar
-
-token/obj_priv_implicit_token_envvar test may fail in an environment
-where the process executing tests can not write to the root path.
-
-Example:
-https://github.com/libbpf/libbpf/actions/runs/11844507007/job/33007897936
-
-Change default path used by the test to /tmp/bpf-token-fs, and make it
-runtime configurable via an environment variable.
-
-Signed-off-by: Ihor Solodrai <ihor.solodrai@pm.me>
----
- tools/testing/selftests/bpf/prog_tests/token.c | 18 +++++++++++-------
- 1 file changed, 11 insertions(+), 7 deletions(-)
-
-diff --git a/tools/testing/selftests/bpf/prog_tests/token.c b/tools/testing/selftests/bpf/prog_tests/token.c
-index fe86e4fdb89c..39f5414b674b 100644
---- a/tools/testing/selftests/bpf/prog_tests/token.c
-+++ b/tools/testing/selftests/bpf/prog_tests/token.c
-@@ -828,8 +828,11 @@ static int userns_obj_priv_btf_success(int mnt_fd, struct token_lsm *lsm_skel)
- 	return validate_struct_ops_load(mnt_fd, true /* should succeed */);
- }
- 
-+static const char* token_bpffs_custom_dir() {
-+	return getenv("BPF_SELFTESTS_BPF_TOKEN_DIR") ? : "/tmp/bpf-token-fs";
-+}
-+
- #define TOKEN_ENVVAR "LIBBPF_BPF_TOKEN_PATH"
--#define TOKEN_BPFFS_CUSTOM "/bpf-token-fs"
- 
- static int userns_obj_priv_implicit_token(int mnt_fd, struct token_lsm *lsm_skel)
- {
-@@ -892,6 +895,7 @@ static int userns_obj_priv_implicit_token(int mnt_fd, struct token_lsm *lsm_skel
- 
- static int userns_obj_priv_implicit_token_envvar(int mnt_fd, struct token_lsm *lsm_skel)
- {
-+	const char *custom_dir = token_bpffs_custom_dir();
- 	LIBBPF_OPTS(bpf_object_open_opts, opts);
- 	struct dummy_st_ops_success *skel;
- 	int err;
-@@ -909,10 +913,10 @@ static int userns_obj_priv_implicit_token_envvar(int mnt_fd, struct token_lsm *l
- 	 * BPF token implicitly, unless pointed to it through
- 	 * LIBBPF_BPF_TOKEN_PATH envvar
- 	 */
--	rmdir(TOKEN_BPFFS_CUSTOM);
--	if (!ASSERT_OK(mkdir(TOKEN_BPFFS_CUSTOM, 0777), "mkdir_bpffs_custom"))
-+	rmdir(custom_dir);
-+	if (!ASSERT_OK(mkdir(custom_dir, 0777), "mkdir_bpffs_custom"))
- 		goto err_out;
--	err = sys_move_mount(mnt_fd, "", AT_FDCWD, TOKEN_BPFFS_CUSTOM, MOVE_MOUNT_F_EMPTY_PATH);
-+	err = sys_move_mount(mnt_fd, "", AT_FDCWD, custom_dir, MOVE_MOUNT_F_EMPTY_PATH);
- 	if (!ASSERT_OK(err, "move_mount_bpffs"))
- 		goto err_out;
- 
-@@ -925,7 +929,7 @@ static int userns_obj_priv_implicit_token_envvar(int mnt_fd, struct token_lsm *l
- 		goto err_out;
- 	}
- 
--	err = setenv(TOKEN_ENVVAR, TOKEN_BPFFS_CUSTOM, 1 /*overwrite*/);
-+	err = setenv(TOKEN_ENVVAR, custom_dir, 1 /*overwrite*/);
- 	if (!ASSERT_OK(err, "setenv_token_path"))
- 		goto err_out;
- 
-@@ -951,11 +955,11 @@ static int userns_obj_priv_implicit_token_envvar(int mnt_fd, struct token_lsm *l
- 	if (!ASSERT_ERR(err, "obj_empty_token_path_load"))
- 		goto err_out;
- 
--	rmdir(TOKEN_BPFFS_CUSTOM);
-+	rmdir(custom_dir);
- 	unsetenv(TOKEN_ENVVAR);
- 	return 0;
- err_out:
--	rmdir(TOKEN_BPFFS_CUSTOM);
-+	rmdir(custom_dir);
- 	unsetenv(TOKEN_ENVVAR);
- 	return -EINVAL;
- }
--- 
-2.47.0
-

ci/diffs/0001-tracing-fprobe-Initialize-ret-valiable-to-fix-smatch.patch

@@ -0,0 +1,68 @@
+From d3484f640bc82cff459beb85a00f7ebab20f0a41 Mon Sep 17 00:00:00 2001
+From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
+Date: Sun, 9 Apr 2023 11:28:31 +0900
+Subject: [PATCH] tracing: fprobe: Initialize ret valiable to fix smatch error
+
+The commit 39d954200bf6 ("fprobe: Skip exit_handler if entry_handler returns
+!0") introduced a hidden dependency of 'ret' local variable in the
+fprobe_handler(), Smatch warns the `ret` can be accessed without
+initialization.
+
+	kernel/trace/fprobe.c:59 fprobe_handler()
+	error: uninitialized symbol 'ret'.
+
+kernel/trace/fprobe.c
+    49                 fpr->entry_ip = ip;
+    50                 if (fp->entry_data_size)
+    51                         entry_data = fpr->data;
+    52         }
+    53
+    54         if (fp->entry_handler)
+    55                 ret = fp->entry_handler(fp, ip, ftrace_get_regs(fregs), entry_data);
+
+ret is only initialized if there is an ->entry_handler
+
+    56
+    57         /* If entry_handler returns !0, nmissed is not counted. */
+    58         if (rh) {
+
+rh is only true if there is an ->exit_handler.  Presumably if you have
+and ->exit_handler that means you also have a ->entry_handler but Smatch
+is not smart enough to figure it out.
+
+--> 59                 if (ret)
+                           ^^^
+Warning here.
+
+    60                         rethook_recycle(rh);
+    61                 else
+    62                         rethook_hook(rh, ftrace_get_regs(fregs), true);
+    63         }
+    64 out:
+    65         ftrace_test_recursion_unlock(bit);
+    66 }
+
+Reported-by: Dan Carpenter <error27@gmail.com>
+Link: https://lore.kernel.org/all/85429a5c-a4b9-499e-b6c0-cbd313291c49@kili.mountain
+Fixes: 39d954200bf6 ("fprobe: Skip exit_handler if entry_handler returns !0")
+Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
+---
+ kernel/trace/fprobe.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
+index 9abb3905bc8e..293184227394 100644
+--- a/kernel/trace/fprobe.c
++++ b/kernel/trace/fprobe.c
+@@ -27,7 +27,7 @@ static void fprobe_handler(unsigned long ip, unsigned long parent_ip,
+ 	struct rethook_node *rh = NULL;
+ 	struct fprobe *fp;
+ 	void *entry_data = NULL;
+-	int bit, ret;
++	int bit, ret = 0;
+ 
+ 	fp = container_of(ops, struct fprobe, ops);
+ 	if (fprobe_disabled(fp))
+-- 
+2.34.1
+

ci/diffs/0001-veth-take-into-account-peer-device-for-NETDEV_XDP_AC.patch

@@ -0,0 +1,83 @@
+From 8267fc71abb2dc47338570e56dd3473a58313fce Mon Sep 17 00:00:00 2001
+From: Lorenzo Bianconi <lorenzo@kernel.org>
+Date: Mon, 17 Apr 2023 23:53:22 +0200
+Subject: [PATCH] veth: take into account peer device for
+ NETDEV_XDP_ACT_NDO_XMIT xdp_features flag
+
+For veth pairs, NETDEV_XDP_ACT_NDO_XMIT is supported by the current
+device if the peer one is running a XDP program or if it has GRO enabled.
+Fix the xdp_features flags reporting considering peer device and not
+current one for NETDEV_XDP_ACT_NDO_XMIT.
+
+Fixes: fccca038f300 ("veth: take into account device reconfiguration for xdp_features flag")
+Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
+Link: https://lore.kernel.org/r/4f1ca6f6f6b42ae125bfdb5c7782217c83968b2e.1681767806.git.lorenzo@kernel.org
+Signed-off-by: Alexei Starovoitov <ast@kernel.org>
+---
+ drivers/net/veth.c | 17 +++++++++++------
+ 1 file changed, 11 insertions(+), 6 deletions(-)
+
+diff --git a/drivers/net/veth.c b/drivers/net/veth.c
+index e1b38fbf1dd9..4b3c6647edc6 100644
+--- a/drivers/net/veth.c
++++ b/drivers/net/veth.c
+@@ -1262,11 +1262,12 @@ static void veth_set_xdp_features(struct net_device *dev)
+ 
+ 	peer = rtnl_dereference(priv->peer);
+ 	if (peer && peer->real_num_tx_queues <= dev->real_num_rx_queues) {
++		struct veth_priv *priv_peer = netdev_priv(peer);
+ 		xdp_features_t val = NETDEV_XDP_ACT_BASIC |
+ 				     NETDEV_XDP_ACT_REDIRECT |
+ 				     NETDEV_XDP_ACT_RX_SG;
+ 
+-		if (priv->_xdp_prog || veth_gro_requested(dev))
++		if (priv_peer->_xdp_prog || veth_gro_requested(peer))
+ 			val |= NETDEV_XDP_ACT_NDO_XMIT |
+ 			       NETDEV_XDP_ACT_NDO_XMIT_SG;
+ 		xdp_set_features_flag(dev, val);
+@@ -1504,19 +1505,23 @@ static int veth_set_features(struct net_device *dev,
+ {
+ 	netdev_features_t changed = features ^ dev->features;
+ 	struct veth_priv *priv = netdev_priv(dev);
++	struct net_device *peer;
+ 	int err;
+ 
+ 	if (!(changed & NETIF_F_GRO) || !(dev->flags & IFF_UP) || priv->_xdp_prog)
+ 		return 0;
+ 
++	peer = rtnl_dereference(priv->peer);
+ 	if (features & NETIF_F_GRO) {
+ 		err = veth_napi_enable(dev);
+ 		if (err)
+ 			return err;
+ 
+-		xdp_features_set_redirect_target(dev, true);
++		if (peer)
++			xdp_features_set_redirect_target(peer, true);
+ 	} else {
+-		xdp_features_clear_redirect_target(dev);
++		if (peer)
++			xdp_features_clear_redirect_target(peer);
+ 		veth_napi_del(dev);
+ 	}
+ 	return 0;
+@@ -1598,13 +1603,13 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
+ 			peer->max_mtu = max_mtu;
+ 		}
+ 
+-		xdp_features_set_redirect_target(dev, true);
++		xdp_features_set_redirect_target(peer, true);
+ 	}
+ 
+ 	if (old_prog) {
+ 		if (!prog) {
+-			if (!veth_gro_requested(dev))
+-				xdp_features_clear_redirect_target(dev);
++			if (peer && !veth_gro_requested(dev))
++				xdp_features_clear_redirect_target(peer);
+ 
+ 			if (dev->flags & IFF_UP)
+ 				veth_disable_xdp(dev);
+-- 
+2.34.1
+

ci/diffs/4000-selftests-bpf-Fix-tests-after-fields-reorder-in-stru.patch

@@ -1,69 +0,0 @@
-From bd06a13f44e15e2e83561ea165061c445a15bd9e Mon Sep 17 00:00:00 2001
-From: Song Liu <song@kernel.org>
-Date: Thu, 27 Mar 2025 11:55:28 -0700
-Subject: [PATCH 4000/4002] selftests/bpf: Fix tests after fields reorder in
- struct file
-
-The change in struct file [1] moved f_ref to the 3rd cache line.
-It made *(u64 *)file dereference invalid from the verifier point of view,
-because btf_struct_walk() walks into f_lock field, which is 4-byte long.
-
-Fix the selftests to deference the file pointer as a 4-byte access.
-
-[1] commit e249056c91a2 ("fs: place f_ref to 3rd cache line in struct file to resolve false sharing")
-Reported-by: Jakub Kicinski <kuba@kernel.org>
-Signed-off-by: Song Liu <song@kernel.org>
-Link: https://lore.kernel.org/r/20250327185528.1740787-1-song@kernel.org
-Signed-off-by: Alexei Starovoitov <ast@kernel.org>
----
- tools/testing/selftests/bpf/progs/test_module_attach.c    | 2 +-
- tools/testing/selftests/bpf/progs/test_subprogs_extable.c | 6 +++---
- 2 files changed, 4 insertions(+), 4 deletions(-)
-
-diff --git a/tools/testing/selftests/bpf/progs/test_module_attach.c b/tools/testing/selftests/bpf/progs/test_module_attach.c
-index fb07f5773888..7f3c233943b3 100644
---- a/tools/testing/selftests/bpf/progs/test_module_attach.c
-+++ b/tools/testing/selftests/bpf/progs/test_module_attach.c
-@@ -117,7 +117,7 @@ int BPF_PROG(handle_fexit_ret, int arg, struct file *ret)
- 
- 	bpf_probe_read_kernel(&buf, 8, ret);
- 	bpf_probe_read_kernel(&buf, 8, (char *)ret + 256);
--	*(volatile long long *)ret;
-+	*(volatile int *)ret;
- 	*(volatile int *)&ret->f_mode;
- 	return 0;
- }
-diff --git a/tools/testing/selftests/bpf/progs/test_subprogs_extable.c b/tools/testing/selftests/bpf/progs/test_subprogs_extable.c
-index e2a21fbd4e44..dcac69f5928a 100644
---- a/tools/testing/selftests/bpf/progs/test_subprogs_extable.c
-+++ b/tools/testing/selftests/bpf/progs/test_subprogs_extable.c
-@@ -21,7 +21,7 @@ static __u64 test_cb(struct bpf_map *map, __u32 *key, __u64 *val, void *data)
- SEC("fexit/bpf_testmod_return_ptr")
- int BPF_PROG(handle_fexit_ret_subprogs, int arg, struct file *ret)
- {
--	*(volatile long *)ret;
-+	*(volatile int *)ret;
- 	*(volatile int *)&ret->f_mode;
- 	bpf_for_each_map_elem(&test_array, test_cb, NULL, 0);
- 	triggered++;
-@@ -31,7 +31,7 @@ int BPF_PROG(handle_fexit_ret_subprogs, int arg, struct file *ret)
- SEC("fexit/bpf_testmod_return_ptr")
- int BPF_PROG(handle_fexit_ret_subprogs2, int arg, struct file *ret)
- {
--	*(volatile long *)ret;
-+	*(volatile int *)ret;
- 	*(volatile int *)&ret->f_mode;
- 	bpf_for_each_map_elem(&test_array, test_cb, NULL, 0);
- 	triggered++;
-@@ -41,7 +41,7 @@ int BPF_PROG(handle_fexit_ret_subprogs2, int arg, struct file *ret)
- SEC("fexit/bpf_testmod_return_ptr")
- int BPF_PROG(handle_fexit_ret_subprogs3, int arg, struct file *ret)
- {
--	*(volatile long *)ret;
-+	*(volatile int *)ret;
- 	*(volatile int *)&ret->f_mode;
- 	bpf_for_each_map_elem(&test_array, test_cb, NULL, 0);
- 	triggered++;
--- 
-2.49.0
-

ci/diffs/4001-selftests-bpf-Fix-verifier_bpf_fastcall-test.patch

@@ -1,71 +0,0 @@
-From 8be3a12f9f266aaf3f06f0cfe0e90cfe4d956f3d Mon Sep 17 00:00:00 2001
-From: Song Liu <song@kernel.org>
-Date: Fri, 28 Mar 2025 12:31:24 -0700
-Subject: [PATCH 4001/4002] selftests/bpf: Fix verifier_bpf_fastcall test
-
-Commit [1] moves percpu data on x86 from address 0x000... to address
-0xfff...
-
-Before [1]:
-
-159020: 0000000000030700     0 OBJECT  GLOBAL DEFAULT   23 pcpu_hot
-
-After [1]:
-
-152602: ffffffff83a3e034     4 OBJECT  GLOBAL DEFAULT   35 pcpu_hot
-
-As a result, verifier_bpf_fastcall tests should now expect a negative
-value for pcpu_hot, IOW, the disassemble should show "r=" instead of
-"w=".
-
-Fix this in the test.
-
-Note that, a later change created a new variable "cpu_number" for
-bpf_get_smp_processor_id() [2]. The inlining logic is updated properly
-as part of this change, so there is no need to fix anything on the
-kernel side.
-
-[1] commit 9d7de2aa8b41 ("x86/percpu/64: Use relative percpu offsets")
-[2] commit 01c7bc5198e9 ("x86/smp: Move cpu number to percpu hot section")
-Reported-by: Jakub Kicinski <kuba@kernel.org>
-Signed-off-by: Song Liu <song@kernel.org>
-Link: https://lore.kernel.org/r/20250328193124.808784-1-song@kernel.org
-Signed-off-by: Alexei Starovoitov <ast@kernel.org>
----
- tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c | 6 +++---
- 1 file changed, 3 insertions(+), 3 deletions(-)
-
-diff --git a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
-index a9be6ae49454..c258b0722e04 100644
---- a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
-+++ b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
-@@ -12,7 +12,7 @@ SEC("raw_tp")
- __arch_x86_64
- __log_level(4) __msg("stack depth 8")
- __xlated("4: r5 = 5")
--__xlated("5: w0 = ")
-+__xlated("5: r0 = ")
- __xlated("6: r0 = &(void __percpu *)(r0)")
- __xlated("7: r0 = *(u32 *)(r0 +0)")
- __xlated("8: exit")
-@@ -704,7 +704,7 @@ SEC("raw_tp")
- __arch_x86_64
- __log_level(4) __msg("stack depth 32+0")
- __xlated("2: r1 = 1")
--__xlated("3: w0 =")
-+__xlated("3: r0 =")
- __xlated("4: r0 = &(void __percpu *)(r0)")
- __xlated("5: r0 = *(u32 *)(r0 +0)")
- /* bpf_loop params setup */
-@@ -753,7 +753,7 @@ __arch_x86_64
- __log_level(4) __msg("stack depth 40+0")
- /* call bpf_get_smp_processor_id */
- __xlated("2: r1 = 42")
--__xlated("3: w0 =")
-+__xlated("3: r0 =")
- __xlated("4: r0 = &(void __percpu *)(r0)")
- __xlated("5: r0 = *(u32 *)(r0 +0)")
- /* call bpf_get_prandom_u32 */
--- 
-2.49.0
-

ci/diffs/4002-selftests-bpf-Fix-verifier_private_stack-test-failur.patch

@@ -1,71 +0,0 @@
-From 07be1f644ff9eeb842fd0490ddd824df0828cb0e Mon Sep 17 00:00:00 2001
-From: Yonghong Song <yonghong.song@linux.dev>
-Date: Sun, 30 Mar 2025 20:38:28 -0700
-Subject: [PATCH 4002/4002] selftests/bpf: Fix verifier_private_stack test
- failure
-
-Several verifier_private_stack tests failed with latest bpf-next.
-For example, for 'Private stack, single prog' subtest, the
-jitted code:
-  func #0:
-  0:      f3 0f 1e fa                             endbr64
-  4:      0f 1f 44 00 00                          nopl    (%rax,%rax)
-  9:      0f 1f 00                                nopl    (%rax)
-  c:      55                                      pushq   %rbp
-  d:      48 89 e5                                movq    %rsp, %rbp
-  10:     f3 0f 1e fa                             endbr64
-  14:     49 b9 58 74 8a 8f 7d 60 00 00           movabsq $0x607d8f8a7458, %r9
-  1e:     65 4c 03 0c 25 28 c0 48 87              addq    %gs:-0x78b73fd8, %r9
-  27:     bf 2a 00 00 00                          movl    $0x2a, %edi
-  2c:     49 89 b9 00 ff ff ff                    movq    %rdi, -0x100(%r9)
-  33:     31 c0                                   xorl    %eax, %eax
-  35:     c9                                      leave
-  36:     e9 20 5d 0f e1                          jmp     0xffffffffe10f5d5b
-
-The insn 'addq %gs:-0x78b73fd8, %r9' does not match the expected
-regex 'addq %gs:0x{{.*}}, %r9' and this caused test failure.
-
-Fix it by changing '%gs:0x{{.*}}' to '%gs:{{.*}}' to accommodate the
-possible negative offset. A few other subtests are fixed in a similar way.
-
-Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
-Link: https://lore.kernel.org/r/20250331033828.365077-1-yonghong.song@linux.dev
-Signed-off-by: Alexei Starovoitov <ast@kernel.org>
----
- tools/testing/selftests/bpf/progs/verifier_private_stack.c | 6 +++---
- 1 file changed, 3 insertions(+), 3 deletions(-)
-
-diff --git a/tools/testing/selftests/bpf/progs/verifier_private_stack.c b/tools/testing/selftests/bpf/progs/verifier_private_stack.c
-index b1fbdf119553..fc91b414364e 100644
---- a/tools/testing/selftests/bpf/progs/verifier_private_stack.c
-+++ b/tools/testing/selftests/bpf/progs/verifier_private_stack.c
-@@ -27,7 +27,7 @@ __description("Private stack, single prog")
- __success
- __arch_x86_64
- __jited("	movabsq	$0x{{.*}}, %r9")
--__jited("	addq	%gs:0x{{.*}}, %r9")
-+__jited("	addq	%gs:{{.*}}, %r9")
- __jited("	movl	$0x2a, %edi")
- __jited("	movq	%rdi, -0x100(%r9)")
- __naked void private_stack_single_prog(void)
-@@ -74,7 +74,7 @@ __success
- __arch_x86_64
- /* private stack fp for the main prog */
- __jited("	movabsq	$0x{{.*}}, %r9")
--__jited("	addq	%gs:0x{{.*}}, %r9")
-+__jited("	addq	%gs:{{.*}}, %r9")
- __jited("	movl	$0x2a, %edi")
- __jited("	movq	%rdi, -0x200(%r9)")
- __jited("	pushq	%r9")
-@@ -122,7 +122,7 @@ __jited("	pushq	%rbp")
- __jited("	movq	%rsp, %rbp")
- __jited("	endbr64")
- __jited("	movabsq	$0x{{.*}}, %r9")
--__jited("	addq	%gs:0x{{.*}}, %r9")
-+__jited("	addq	%gs:{{.*}}, %r9")
- __jited("	pushq	%r9")
- __jited("	callq")
- __jited("	popq	%r9")
--- 
-2.49.0
-

ci/vmtest/configs/ALLOWLIST-4.9.0

@@ -0,0 +1,8 @@
+# btf_dump -- need to disable data dump sub-tests
+core_retro
+cpu_mask
+hashmap
+legacy_printk
+perf_buffer
+section_names
+

ci/vmtest/configs/ALLOWLIST-5.5.0

@@ -0,0 +1,51 @@
+# attach_probe
+autoload
+bpf_verif_scale
+cgroup_attach_autodetach
+cgroup_attach_override
+core_autosize
+core_extern
+core_read_macros
+core_reloc
+core_retro
+cpu_mask
+endian
+get_branch_snapshot
+get_stackid_cannot_attach
+global_data
+global_data_init
+global_func_args
+hashmap
+legacy_printk
+linked_funcs
+linked_maps
+map_lock
+obj_name
+perf_buffer
+perf_event_stackmap
+pinning
+pkt_md_access
+probe_user
+queue_stack_map
+raw_tp_writable_reject_nbd_invalid
+raw_tp_writable_test_run
+rdonly_maps
+section_names
+signal_pending
+skeleton
+sockmap_ktls
+sockopt
+spinlock
+stacktrace_map
+stacktrace_map_raw_tp
+static_linked
+task_fd_query_rawtp
+task_fd_query_tp
+tc_bpf
+tcp_estats
+tcp_rtt
+tp_attach_query
+usdt/urand_pid_attach
+xdp
+xdp_noinline
+xdp_perf

ci/vmtest/configs/DENYLIST

@@ -1,15 +0,0 @@
-# TEMPORARY
-btf_dump/btf_dump: syntax
-kprobe_multi_bench_attach
-core_reloc/enum64val
-core_reloc/size___diff_sz
-core_reloc/type_based___diff_sz
-test_ima	# All of CI is broken on it following 6.3-rc1 merge
-
-lwt_reroute      # crashes kernel after netnext merge from 2ab1efad60ad "net/sched: cls_api: complement tcf_tfilter_dump_policy"
-tc_links_ingress # started failing after net-next merge from 2ab1efad60ad "net/sched: cls_api: complement tcf_tfilter_dump_policy"
-xdp_bonding/xdp_bonding_features     # started failing after net merge from 359e54a93ab4 "l2tp: pass correct message length to ip6_append_data"
-tc_redirect/tc_redirect_dtime # uapi breakage after net-next commit 885c36e59f46 ("net: Re-use and set mono_delivery_time bit for userspace tstamp packets")
-migrate_reuseport/IPv4 TCP_NEW_SYN_RECV reqsk_timer_handler # flaky, under investigation
-migrate_reuseport/IPv6 TCP_NEW_SYN_RECV reqsk_timer_handler # flaky, under investigation
-verify_pkcs7_sig # keeps failing

ci/vmtest/configs/DENYLIST-5.5.0

@@ -0,0 +1,120 @@
+# 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+)
+atomic_bounds		# new atomic operations (v5.12+)
+bind_perm		# changed semantics of return values (v5.12+)
+bpf_cookie		# 5.15+
+bpf_iter		# bpf_iter support is missing
+bpf_obj_id		# bpf_link support missing for GET_OBJ_INFO, GET_FD_BY_ID, etc
+bpf_tcp_ca		# STRUCT_OPS is missing
+btf_map_in_map		# inner map leak fixed in 5.8
+btf_skc_cls_ingress	# v5.10+ functionality
+cg_storage_multi	# v5.9+ functionality
+cgroup_attach_multi	# BPF_F_REPLACE_PROG missing
+cgroup_link		# LINK_CREATE is missing
+cgroup_skb_sk_lookup	# bpf_sk_lookup_tcp() helper is missing
+check_mtu		# missing BPF helper (v5.12+)
+cls_redirect		# bpf_csum_level() helper is missing
+connect_force_port	# cgroup/get{peer,sock}name{4,6} support is missing
+d_path			# v5.10+ feature
+enable_stats		# BPF_ENABLE_STATS support is missing
+fentry_fexit		# bpf_prog_test_tracing missing
+fentry_test		# bpf_prog_test_tracing missing
+fexit_bpf2bpf		# freplace is missing
+fexit_sleep		# relies on bpf_trampoline fix in 5.12+
+fexit_test		# bpf_prog_test_tracing missing
+flow_dissector		# bpf_link-based flow dissector is in 5.8+
+flow_dissector_reattach
+for_each		# v5.12+
+get_func_ip_test	# v5.15+
+get_stack_raw_tp	# exercising BPF verifier bug causing infinite loop
+hash_large_key		# v5.11+
+ima			# v5.11+
+kfree_skb		# 32-bit pointer arith in test_pkt_access
+ksyms			# __start_BTF has different name
+kfunc_call		# v5.13+
+link_pinning		# bpf_link is missing
+linked_vars		# v5.13+
+load_bytes_relative	# new functionality in 5.8
+lookup_and_delete	# v5.14+
+map_init		# per-CPU LRU missing
+map_ptr			# test uses BPF_MAP_TYPE_RINGBUF, added in 5.8
+metadata		# v5.10+
+migrate_reuseport	# v5.14+
+mmap			# 5.5 kernel is too permissive with re-mmaping
+modify_return		# fmod_ret support is missing
+module_attach		# module BTF support missing (v5.11+)
+netcnt
+netns_cookie		# v5.15+
+ns_current_pid_tgid	# bpf_get_ns_current_pid_tgid() helper is missing
+pe_preserve_elems	# v5.10+
+perf_branches		# bpf_read_branch_records() helper is missing
+perf_link		# v5.15+
+pkt_access		# 32-bit pointer arith in test_pkt_access
+probe_read_user_str	# kernel bug with garbage bytes at the end
+prog_run_xattr		# 32-bit pointer arith in test_pkt_access
+raw_tp_test_run		# v5.10+
+recursion		# v5.12+
+ringbuf			# BPF_MAP_TYPE_RINGBUF is supported in 5.8+
+
+# bug in verifier w/ tracking references
+#reference_tracking/classifier/sk_lookup_success
+reference_tracking
+
+select_reuseport	# UDP support is missing
+send_signal		# bpf_send_signal_thread() helper is missing
+sk_assign		# bpf_sk_assign helper missing
+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+
+socket_cookie		# v5.12+
+sockmap_basic		# uses new socket fields, 5.8+
+sockmap_listen		# no listen socket supportin SOCKMAP
+sockopt/getsockopt: ignore >PAGE_SIZE optlen
+sockopt/setsockopt: ignore >PAGE_SIZE optlen
+sockopt_sk
+sockopt_qos_to_cc	# v5.15+
+stacktrace_build_id	# v5.9+
+stack_var_off		# v5.12+
+syscall			# v5.14+
+task_local_storage	# v5.12+
+task_pt_regs		# v5.15+
+tcp_hdr_options		# v5.10+, new TCP header options feature in BPF
+tcpbpf_user		# LINK_CREATE is missing
+tc_redirect		# v5.14+
+test_bpffs		# v5.10+, new CONFIG_BPF_PRELOAD=y and CONFIG_BPF_PRELOAD_UMG=y|m
+test_bprm_opts		# v5.11+
+test_global_funcs	# kernel doesn't support BTF linkage=global on FUNCs
+test_local_storage	# v5.10+ feature
+test_lsm		# no BPF_LSM support
+test_overhead		# no fmod_ret support
+test_profiler		# needs verifier logic improvements from v5.10+
+test_skb_pkt_end	# v5.11+
+timer			# v5.15+
+timer_mim		# v5.15+
+trace_ext		# v5.10+
+trace_printk		# v5.14+
+trampoline_count	# v5.12+ have lower allowed limits
+udp_limit		# no cgroup/sock_release BPF program type (5.9+)
+varlen			# verifier bug fixed in later kernels
+vmlinux			# hrtimer_nanosleep() signature changed incompatibly
+xdp_adjust_tail		# new XDP functionality added in 5.8
+xdp_attach		# IFLA_XDP_EXPECTED_FD support is missing
+xdp_bonding		# v5.15+
+xdp_bpf2bpf		# freplace is missing
+xdp_context_test_run	# v5.15+
+xdp_cpumap_attach	# v5.9+
+xdp_devmap_attach	# new feature in 5.8
+xdp_link		# v5.9+
+
+# SUBTESTS FAILING (block entire test until blocking subtests works properly)
+btf			# "size check test", "func (Non zero vlen)"
+tailcalls		# tailcall_bpf2bpf_1, tailcall_bpf2bpf_2, tailcall_bpf2bpf_3

ci/vmtest/configs/DENYLIST-latest

@@ -1,13 +1,4 @@
 decap_sanity  # weird failure with decap_sanity_ns netns already existing, TBD
-empty_skb # waiting the fix in bpf tree to make it to bpf-next
 bpf_nf/tc-bpf-ct # test consistently failing on x86: https://github.com/libbpf/libbpf/pull/698#issuecomment-1590341200
 bpf_nf/xdp-ct   # test consistently failing on x86: https://github.com/libbpf/libbpf/pull/698#issuecomment-1590341200
 kprobe_multi_bench_attach # suspected to cause crashes in CI
-find_vma # test consistently fails on latest kernel, see https://github.com/libbpf/libbpf/issues/754 for details
-bpf_cookie/perf_event
-send_signal/send_signal_nmi
-send_signal/send_signal_nmi_thread
-
-lwt_reroute # crashes kernel, fix pending upstream
-tc_links_ingress # fails, same fix is pending upstream
-tc_redirect		  # enough is enough, banned for life for flakiness

ci/vmtest/configs/DENYLIST-latest.s390x

@@ -2,16 +2,3 @@
 sockmap_listen/sockhash VSOCK test_vsock_redir
 usdt/basic                               # failing verifier due to bounds check after LLVM update
 usdt/multispec                           # same as above
-
-deny_namespace                           # not yet in bpf denylist
-tc_redirect/tc_redirect_dtime            # very flaky
-lru_bug                                  # not yet in bpf-next denylist
-
-# Disabled temporarily for a crash.
-# https://lore.kernel.org/bpf/c9923c1d-971d-4022-8dc8-1364e929d34c@gmail.com/
-dummy_st_ops/dummy_init_ptr_arg
-fexit_bpf2bpf
-tailcalls
-trace_ext
-xdp_bpf2bpf
-xdp_metadata

ci/vmtest/configs/run-vmtest.env

@@ -1,37 +0,0 @@
-#!/bin/bash
-
-# This file is sourced by libbpf/ci/run-vmtest Github Action scripts.
-
-# $SELFTESTS_BPF and $VMTEST_CONFIGS are set in the workflow, before
-# libbpf/ci/run-vmtest action is called
-# See .github/workflows/kernel-test.yml
-
-ALLOWLIST_FILES=(
-    "${SELFTESTS_BPF}/ALLOWLIST"
-    "${SELFTESTS_BPF}/ALLOWLIST.${ARCH}"
-    "${VMTEST_CONFIGS}/ALLOWLIST"
-    "${VMTEST_CONFIGS}/ALLOWLIST-${KERNEL}"
-    "${VMTEST_CONFIGS}/ALLOWLIST-${KERNEL}.${ARCH}"
-)
-
-DENYLIST_FILES=(
-    "${SELFTESTS_BPF}/DENYLIST"
-    "${SELFTESTS_BPF}/DENYLIST.${ARCH}"
-    "${VMTEST_CONFIGS}/DENYLIST"
-    "${VMTEST_CONFIGS}/DENYLIST-${KERNEL}"
-    "${VMTEST_CONFIGS}/DENYLIST-${KERNEL}.${ARCH}"
-)
-
-# Export pipe-separated strings, because bash doesn't support array export
-export SELFTESTS_BPF_ALLOWLIST_FILES=$(IFS="|"; echo "${ALLOWLIST_FILES[*]}")
-export SELFTESTS_BPF_DENYLIST_FILES=$(IFS="|"; echo "${DENYLIST_FILES[*]}")
-
-if [[ "${LLVM_VERSION}" -lt 18 ]]; then
-    echo "KERNEL_TEST=test_progs test_progs_no_alu32 test_maps test_verifier" >> $GITHUB_ENV
-else # all
-    echo "KERNEL_TEST=test_progs test_progs_cpuv4 test_progs_no_alu32 test_maps test_verifier" >> $GITHUB_ENV
-fi
-
-echo "cp -R ${SELFTESTS_BPF} ${GITHUB_WORKSPACE}/selftests"
-mkdir -p "${GITHUB_WORKSPACE}/selftests"
-cp -R "${SELFTESTS_BPF}" "${GITHUB_WORKSPACE}/selftests"

ci/vmtest/helpers.sh

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

ci/vmtest/run_selftests.sh

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

docs/conf.py

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

docs/libbpf_overview.rst

@@ -219,14 +219,6 @@ compilation and skeleton generation. Using Libbpf-rs will make building user
 space part of the BPF application easier. Note that the BPF program themselves
 must still be written in plain C.
 
-libbpf logging
-==============
-
-By default, libbpf logs informational and warning messages to stderr. The
-verbosity of these messages can be controlled by setting the environment
-variable LIBBPF_LOG_LEVEL to either warn, info, or debug. A custom log
-callback can be set using ``libbpf_set_print()``.
-
 Additional Documentation
 ========================
 

docs/program_types.rst

@@ -56,16 +56,6 @@ described in more detail in the footnotes.
 |                                           | ``BPF_CGROUP_UDP6_RECVMSG``            | ``cgroup/recvmsg6``              |           |
 +                                           +----------------------------------------+----------------------------------+-----------+
 |                                           | ``BPF_CGROUP_UDP6_SENDMSG``            | ``cgroup/sendmsg6``              |           |
-|                                           +----------------------------------------+----------------------------------+-----------+
-|                                           | ``BPF_CGROUP_UNIX_CONNECT``            | ``cgroup/connect_unix``          |           |
-|                                           +----------------------------------------+----------------------------------+-----------+
-|                                           | ``BPF_CGROUP_UNIX_SENDMSG``            | ``cgroup/sendmsg_unix``          |           |
-|                                           +----------------------------------------+----------------------------------+-----------+
-|                                           | ``BPF_CGROUP_UNIX_RECVMSG``            | ``cgroup/recvmsg_unix``          |           |
-|                                           +----------------------------------------+----------------------------------+-----------+
-|                                           | ``BPF_CGROUP_UNIX_GETPEERNAME``        | ``cgroup/getpeername_unix``      |           |
-|                                           +----------------------------------------+----------------------------------+-----------+
-|                                           | ``BPF_CGROUP_UNIX_GETSOCKNAME``        | ``cgroup/getsockname_unix``      |           |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
 | ``BPF_PROG_TYPE_CGROUP_SOCK``             | ``BPF_CGROUP_INET4_POST_BIND``         | ``cgroup/post_bind4``            |           |
 +                                           +----------------------------------------+----------------------------------+-----------+
@@ -121,8 +111,6 @@ described in more detail in the footnotes.
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
 | ``BPF_PROG_TYPE_LWT_XMIT``                |                                        | ``lwt_xmit``                     |           |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
-| ``BPF_PROG_TYPE_NETFILTER``               |                                        | ``netfilter``                    |           |
-+-------------------------------------------+----------------------------------------+----------------------------------+-----------+
 | ``BPF_PROG_TYPE_PERF_EVENT``              |                                        | ``perf_event``                   |           |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
 | ``BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE`` |                                        | ``raw_tp.w+`` [#rawtp]_          |           |
@@ -133,23 +121,11 @@ described in more detail in the footnotes.
 +                                           +                                        +----------------------------------+-----------+
 |                                           |                                        | ``raw_tracepoint+``              |           |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
-| ``BPF_PROG_TYPE_SCHED_ACT``               |                                        | ``action`` [#tc_legacy]_         |           |
+| ``BPF_PROG_TYPE_SCHED_ACT``               |                                        | ``action``                       |           |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
-| ``BPF_PROG_TYPE_SCHED_CLS``               |                                        | ``classifier`` [#tc_legacy]_     |           |
+| ``BPF_PROG_TYPE_SCHED_CLS``               |                                        | ``classifier``                   |           |
 +                                           +                                        +----------------------------------+-----------+
-|                                           |                                        | ``tc`` [#tc_legacy]_             |           |
+|                                           |                                        | ``tc``                           |           |
-+                                           +----------------------------------------+----------------------------------+-----------+
-|                                           | ``BPF_NETKIT_PRIMARY``                 | ``netkit/primary``               |           |
-+                                           +----------------------------------------+----------------------------------+-----------+
-|                                           | ``BPF_NETKIT_PEER``                    | ``netkit/peer``                  |           |
-+                                           +----------------------------------------+----------------------------------+-----------+
-|                                           | ``BPF_TCX_INGRESS``                    | ``tc/ingress``                   |           |
-+                                           +----------------------------------------+----------------------------------+-----------+
-|                                           | ``BPF_TCX_EGRESS``                     | ``tc/egress``                    |           |
-+                                           +----------------------------------------+----------------------------------+-----------+
-|                                           | ``BPF_TCX_INGRESS``                    | ``tcx/ingress``                  |           |
-+                                           +----------------------------------------+----------------------------------+-----------+
-|                                           | ``BPF_TCX_EGRESS``                     | ``tcx/egress``                   |           |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
 | ``BPF_PROG_TYPE_SK_LOOKUP``               | ``BPF_SK_LOOKUP``                      | ``sk_lookup``                    |           |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
@@ -169,9 +145,7 @@ described in more detail in the footnotes.
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
 | ``BPF_PROG_TYPE_SOCK_OPS``                | ``BPF_CGROUP_SOCK_OPS``                | ``sockops``                      |           |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
-| ``BPF_PROG_TYPE_STRUCT_OPS``              |                                        | ``struct_ops+`` [#struct_ops]_   |           |
+| ``BPF_PROG_TYPE_STRUCT_OPS``              |                                        | ``struct_ops+``                  |           |
-+                                           +                                        +----------------------------------+-----------+
-|                                           |                                        | ``struct_ops.s+`` [#struct_ops]_ | Yes       |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
 | ``BPF_PROG_TYPE_SYSCALL``                 |                                        | ``syscall``                      | Yes       |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
@@ -225,11 +199,5 @@ described in more detail in the footnotes.
               ``a-zA-Z0-9_.*?``.
 .. [#lsm] The ``lsm`` attachment format is ``lsm[.s]/<hook>``.
 .. [#rawtp] The ``raw_tp`` attach format is ``raw_tracepoint[.w]/<tracepoint>``.
-.. [#tc_legacy] The ``tc``, ``classifier`` and ``action`` attach types are deprecated, use
-                ``tcx/*`` instead.
-.. [#struct_ops] The ``struct_ops`` attach format supports ``struct_ops[.s]/<name>`` convention,
-                 but ``name`` is ignored and it is recommended to just use plain
-                 ``SEC("struct_ops[.s]")``. The attachments are defined in a struct initializer
-                 that is tagged with ``SEC(".struct_ops[.link]")``.
 .. [#tp] The ``tracepoint`` attach format is ``tracepoint/<category>/<name>``.
 .. [#iter] The ``iter`` attach format is ``iter[.s]/<struct-name>``.

docs/sphinx/requirements.txt

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

include/linux/filter.h

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

include/linux/kernel.h

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

include/uapi/linux/bpf.h

@@ -19,7 +19,6 @@
 
 /* ld/ldx fields */
 #define BPF_DW		0x18	/* double word (64-bit) */
-#define BPF_MEMSX	0x80	/* load with sign extension */
 #define BPF_ATOMIC	0xc0	/* atomic memory ops - op type in immediate */
 #define BPF_XADD	0xc0	/* exclusive add - legacy name */
 
@@ -42,7 +41,6 @@
 #define BPF_JSGE	0x70	/* SGE is signed '>=', GE in x86 */
 #define BPF_JSLT	0xc0	/* SLT is signed, '<' */
 #define BPF_JSLE	0xd0	/* SLE is signed, '<=' */
-#define BPF_JCOND	0xe0	/* conditional pseudo jumps: may_goto, goto_or_nop */
 #define BPF_CALL	0x80	/* function call */
 #define BPF_EXIT	0x90	/* function return */
 
@@ -51,13 +49,6 @@
 #define BPF_XCHG	(0xe0 | BPF_FETCH)	/* atomic exchange */
 #define BPF_CMPXCHG	(0xf0 | BPF_FETCH)	/* atomic compare-and-write */
 
-#define BPF_LOAD_ACQ	0x100	/* load-acquire */
-#define BPF_STORE_REL	0x110	/* store-release */
-
-enum bpf_cond_pseudo_jmp {
-	BPF_MAY_GOTO = 0,
-};
-
 /* Register numbers */
 enum {
 	BPF_REG_0 = 0,
@@ -85,29 +76,12 @@ struct bpf_insn {
 	__s32	imm;		/* signed immediate constant */
 };
 
-/* Deprecated: use struct bpf_lpm_trie_key_u8 (when the "data" member is needed for
+/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */
- * byte access) or struct bpf_lpm_trie_key_hdr (when using an alternative type for
- * the trailing flexible array member) instead.
- */
 struct bpf_lpm_trie_key {
 	__u32	prefixlen;	/* up to 32 for AF_INET, 128 for AF_INET6 */
 	__u8	data[0];	/* Arbitrary size */
 };
 
-/* Header for bpf_lpm_trie_key structs */
-struct bpf_lpm_trie_key_hdr {
-	__u32	prefixlen;
-};
-
-/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry, with trailing byte array. */
-struct bpf_lpm_trie_key_u8 {
-	union {
-		struct bpf_lpm_trie_key_hdr	hdr;
-		__u32				prefixlen;
-	};
-	__u8	data[];		/* Arbitrary size */
-};
-
 struct bpf_cgroup_storage_key {
 	__u64	cgroup_inode_id;	/* cgroup inode id */
 	__u32	attach_type;		/* program attach type (enum bpf_attach_type) */
@@ -642,11 +616,7 @@ union bpf_iter_link_info {
  *		to NULL to begin the batched operation. After each subsequent
  *		**BPF_MAP_LOOKUP_BATCH**, the caller should pass the resultant
  *		*out_batch* as the *in_batch* for the next operation to
- *		continue iteration from the current point. Both *in_batch* and
+ *		continue iteration from the current point.
- *		*out_batch* must point to memory large enough to hold a key,
- *		except for maps of type **BPF_MAP_TYPE_{HASH, PERCPU_HASH,
- *		LRU_HASH, LRU_PERCPU_HASH}**, for which batch parameters
- *		must be at least 4 bytes wide regardless of key size.
  *
  *		The *keys* and *values* are output parameters which must point
  *		to memory large enough to hold *count* items based on the key
@@ -876,36 +846,6 @@ union bpf_iter_link_info {
  *		Returns zero on success. On error, -1 is returned and *errno*
  *		is set appropriately.
  *
- * BPF_TOKEN_CREATE
- *	Description
- *		Create BPF token with embedded information about what
- *		BPF-related functionality it allows:
- *		- a set of allowed bpf() syscall commands;
- *		- a set of allowed BPF map types to be created with
- *		BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed;
- *		- a set of allowed BPF program types and BPF program attach
- *		types to be loaded with BPF_PROG_LOAD command, if
- *		BPF_PROG_LOAD itself is allowed.
- *
- *		BPF token is created (derived) from an instance of BPF FS,
- *		assuming it has necessary delegation mount options specified.
- *		This BPF token can be passed as an extra parameter to various
- *		bpf() syscall commands to grant BPF subsystem functionality to
- *		unprivileged processes.
- *
- *		When created, BPF token is "associated" with the owning
- *		user namespace of BPF FS instance (super block) that it was
- *		derived from, and subsequent BPF operations performed with
- *		BPF token would be performing capabilities checks (i.e.,
- *		CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within
- *		that user namespace. Without BPF token, such capabilities
- *		have to be granted in init user namespace, making bpf()
- *		syscall incompatible with user namespace, for the most part.
- *
- *	Return
- *		A new file descriptor (a nonnegative integer), or -1 if an
- *		error occurred (in which case, *errno* is set appropriately).
- *
  * NOTES
  *	eBPF objects (maps and programs) can be shared between processes.
  *
@@ -960,8 +900,6 @@ enum bpf_cmd {
 	BPF_ITER_CREATE,
 	BPF_LINK_DETACH,
 	BPF_PROG_BIND_MAP,
-	BPF_TOKEN_CREATE,
-	__MAX_BPF_CMD,
 };
 
 enum bpf_map_type {
@@ -993,14 +931,7 @@ enum bpf_map_type {
 	 */
 	BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED,
 	BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
-	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED,
+	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
-	/* BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE is available to bpf programs
-	 * attaching to a cgroup. The new mechanism (BPF_MAP_TYPE_CGRP_STORAGE +
-	 * local percpu kptr) supports all BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE
-	 * functionality and more. So mark * BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE
-	 * deprecated.
-	 */
-	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED,
 	BPF_MAP_TYPE_QUEUE,
 	BPF_MAP_TYPE_STACK,
 	BPF_MAP_TYPE_SK_STORAGE,
@@ -1012,8 +943,6 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_BLOOM_FILTER,
 	BPF_MAP_TYPE_USER_RINGBUF,
 	BPF_MAP_TYPE_CGRP_STORAGE,
-	BPF_MAP_TYPE_ARENA,
-	__MAX_BPF_MAP_TYPE
 };
 
 /* Note that tracing related programs such as
@@ -1058,7 +987,6 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_SK_LOOKUP,
 	BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */
 	BPF_PROG_TYPE_NETFILTER,
-	__MAX_BPF_PROG_TYPE
 };
 
 enum bpf_attach_type {
@@ -1108,26 +1036,11 @@ enum bpf_attach_type {
 	BPF_LSM_CGROUP,
 	BPF_STRUCT_OPS,
 	BPF_NETFILTER,
-	BPF_TCX_INGRESS,
-	BPF_TCX_EGRESS,
-	BPF_TRACE_UPROBE_MULTI,
-	BPF_CGROUP_UNIX_CONNECT,
-	BPF_CGROUP_UNIX_SENDMSG,
-	BPF_CGROUP_UNIX_RECVMSG,
-	BPF_CGROUP_UNIX_GETPEERNAME,
-	BPF_CGROUP_UNIX_GETSOCKNAME,
-	BPF_NETKIT_PRIMARY,
-	BPF_NETKIT_PEER,
-	BPF_TRACE_KPROBE_SESSION,
-	BPF_TRACE_UPROBE_SESSION,
 	__MAX_BPF_ATTACH_TYPE
 };
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
-/* Add BPF_LINK_TYPE(type, name) in bpf_types.h to keep bpf_link_type_strs[]
- * in sync with the definitions below.
- */
 enum bpf_link_type {
 	BPF_LINK_TYPE_UNSPEC = 0,
 	BPF_LINK_TYPE_RAW_TRACEPOINT = 1,
@@ -1140,23 +1053,8 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_KPROBE_MULTI = 8,
 	BPF_LINK_TYPE_STRUCT_OPS = 9,
 	BPF_LINK_TYPE_NETFILTER = 10,
-	BPF_LINK_TYPE_TCX = 11,
-	BPF_LINK_TYPE_UPROBE_MULTI = 12,
-	BPF_LINK_TYPE_NETKIT = 13,
-	BPF_LINK_TYPE_SOCKMAP = 14,
-	__MAX_BPF_LINK_TYPE,
-};
 
-#define MAX_BPF_LINK_TYPE __MAX_BPF_LINK_TYPE
+	MAX_BPF_LINK_TYPE,
-
-enum bpf_perf_event_type {
-	BPF_PERF_EVENT_UNSPEC = 0,
-	BPF_PERF_EVENT_UPROBE = 1,
-	BPF_PERF_EVENT_URETPROBE = 2,
-	BPF_PERF_EVENT_KPROBE = 3,
-	BPF_PERF_EVENT_KRETPROBE = 4,
-	BPF_PERF_EVENT_TRACEPOINT = 5,
-	BPF_PERF_EVENT_EVENT = 6,
 };
 
 /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
@@ -1205,13 +1103,7 @@ enum bpf_perf_event_type {
  */
 #define BPF_F_ALLOW_OVERRIDE	(1U << 0)
 #define BPF_F_ALLOW_MULTI	(1U << 1)
-/* Generic attachment flags. */
 #define BPF_F_REPLACE		(1U << 2)
-#define BPF_F_BEFORE		(1U << 3)
-#define BPF_F_AFTER		(1U << 4)
-#define BPF_F_ID		(1U << 5)
-#define BPF_F_PREORDER		(1U << 6)
-#define BPF_F_LINK		BPF_F_LINK /* 1 << 13 */
 
 /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
  * verifier will perform strict alignment checking as if the kernel
@@ -1273,27 +1165,10 @@ enum bpf_perf_event_type {
  */
 #define BPF_F_XDP_DEV_BOUND_ONLY	(1U << 6)
 
-/* The verifier internal test flag. Behavior is undefined */
-#define BPF_F_TEST_REG_INVARIANTS	(1U << 7)
-
 /* link_create.kprobe_multi.flags used in LINK_CREATE command for
  * BPF_TRACE_KPROBE_MULTI attach type to create return probe.
  */
-enum {
+#define BPF_F_KPROBE_MULTI_RETURN	(1U << 0)
-	BPF_F_KPROBE_MULTI_RETURN = (1U << 0)
-};
-
-/* link_create.uprobe_multi.flags used in LINK_CREATE command for
- * BPF_TRACE_UPROBE_MULTI attach type to create return probe.
- */
-enum {
-	BPF_F_UPROBE_MULTI_RETURN = (1U << 0)
-};
-
-/* link_create.netfilter.flags used in LINK_CREATE command for
- * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation.
- */
-#define BPF_F_NETFILTER_IP_DEFRAG (1U << 0)
 
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * the following extensions:
@@ -1349,10 +1224,6 @@ enum {
  */
 #define BPF_PSEUDO_KFUNC_CALL	2
 
-enum bpf_addr_space_cast {
-	BPF_ADDR_SPACE_CAST = 1,
-};
-
 /* flags for BPF_MAP_UPDATE_ELEM command */
 enum {
 	BPF_ANY		= 0, /* create new element or update existing */
@@ -1405,18 +1276,6 @@ enum {
 
 /* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */
 	BPF_F_PATH_FD		= (1U << 14),
-
-/* Flag for value_type_btf_obj_fd, the fd is available */
-	BPF_F_VTYPE_BTF_OBJ_FD	= (1U << 15),
-
-/* BPF token FD is passed in a corresponding command's token_fd field */
-	BPF_F_TOKEN_FD          = (1U << 16),
-
-/* When user space page faults in bpf_arena send SIGSEGV instead of inserting new page */
-	BPF_F_SEGV_ON_FAULT	= (1U << 17),
-
-/* Do not translate kernel bpf_arena pointers to user pointers */
-	BPF_F_NO_USER_CONV	= (1U << 18),
 };
 
 /* Flags for BPF_PROG_QUERY. */
@@ -1433,8 +1292,6 @@ enum {
 #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)
-/* If set, apply CHECKSUM_COMPLETE to skb and validate the checksum */
-#define BPF_F_TEST_SKB_CHECKSUM_COMPLETE	(1U << 2)
 
 /* type for BPF_ENABLE_STATS */
 enum bpf_stats_type {
@@ -1490,23 +1347,11 @@ union bpf_attr {
 		 * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the
 		 * number of hash functions (if 0, the bloom filter will default
 		 * to using 5 hash functions).
-		 *
-		 * BPF_MAP_TYPE_ARENA - contains the address where user space
-		 * is going to mmap() the arena. It has to be page aligned.
 		 */
 		__u64	map_extra;
-
-		__s32   value_type_btf_obj_fd;	/* fd pointing to a BTF
-						 * type data for
-						 * btf_vmlinux_value_type_id.
-						 */
-		/* BPF token FD to use with BPF_MAP_CREATE operation.
-		 * If provided, map_flags should have BPF_F_TOKEN_FD flag set.
-		 */
-		__s32	map_token_fd;
 	};
 
-	struct { /* anonymous struct used by BPF_MAP_*_ELEM and BPF_MAP_FREEZE commands */
+	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
 		__u32		map_fd;
 		__aligned_u64	key;
 		union {
@@ -1573,20 +1418,6 @@ union bpf_attr {
 		 * truncated), or smaller (if log buffer wasn't filled completely).
 		 */
 		__u32		log_true_size;
-		/* BPF token FD to use with BPF_PROG_LOAD operation.
-		 * If provided, prog_flags should have BPF_F_TOKEN_FD flag set.
-		 */
-		__s32		prog_token_fd;
-		/* The fd_array_cnt can be used to pass the length of the
-		 * fd_array array. In this case all the [map] file descriptors
-		 * passed in this array will be bound to the program, even if
-		 * the maps are not referenced directly. The functionality is
-		 * similar to the BPF_PROG_BIND_MAP syscall, but maps can be
-		 * used by the verifier during the program load. If provided,
-		 * then the fd_array[0,...,fd_array_cnt-1] is expected to be
-		 * continuous.
-		 */
-		__u32		fd_array_cnt;
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -1603,19 +1434,14 @@ union bpf_attr {
 	};
 
 	struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
-		union {
+		__u32		target_fd;	/* container object to attach to */
-			__u32	target_fd;	/* target object to attach to or ... */
+		__u32		attach_bpf_fd;	/* eBPF program to attach */
-			__u32	target_ifindex;	/* target ifindex */
-		};
-		__u32		attach_bpf_fd;
 		__u32		attach_type;
 		__u32		attach_flags;
-		__u32		replace_bpf_fd;
+		__u32		replace_bpf_fd;	/* previously attached eBPF
-		union {
+						 * program to replace if
-			__u32	relative_fd;
+						 * BPF_F_REPLACE is used
-			__u32	relative_id;
+						 */
-		};
-		__u64		expected_revision;
 	};
 
 	struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
@@ -1652,7 +1478,6 @@ union bpf_attr {
 		};
 		__u32		next_id;
 		__u32		open_flags;
-		__s32		fd_by_id_token_fd;
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */
@@ -1662,33 +1487,21 @@ union bpf_attr {
 	} info;
 
 	struct { /* anonymous struct used by BPF_PROG_QUERY command */
-		union {
+		__u32		target_fd;	/* container object to query */
-			__u32	target_fd;	/* target object to query or ... */
-			__u32	target_ifindex;	/* target ifindex */
-		};
 		__u32		attach_type;
 		__u32		query_flags;
 		__u32		attach_flags;
 		__aligned_u64	prog_ids;
-		union {
+		__u32		prog_cnt;
-			__u32	prog_cnt;
-			__u32	count;
-		};
-		__u32		:32;
 		/* output: per-program attach_flags.
 		 * not allowed to be set during effective query.
 		 */
 		__aligned_u64	prog_attach_flags;
-		__aligned_u64	link_ids;
-		__aligned_u64	link_attach_flags;
-		__u64		revision;
 	} query;
 
 	struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */
-		__u64		name;
+		__u64 name;
-		__u32		prog_fd;
+		__u32 prog_fd;
-		__u32		:32;
-		__aligned_u64	cookie;
 	} raw_tracepoint;
 
 	struct { /* anonymous struct for BPF_BTF_LOAD */
@@ -1702,11 +1515,6 @@ union bpf_attr {
 		 * truncated), or smaller (if log buffer wasn't filled completely).
 		 */
 		__u32		btf_log_true_size;
-		__u32		btf_flags;
-		/* BPF token FD to use with BPF_BTF_LOAD operation.
-		 * If provided, btf_flags should have BPF_F_TOKEN_FD flag set.
-		 */
-		__s32		btf_token_fd;
 	};
 
 	struct {
@@ -1731,13 +1539,13 @@ union bpf_attr {
 			__u32		map_fd;		/* struct_ops to attach */
 		};
 		union {
-			__u32	target_fd;	/* target object to attach to or ... */
+			__u32		target_fd;	/* object to attach to */
-			__u32	target_ifindex; /* target ifindex */
+			__u32		target_ifindex; /* target ifindex */
 		};
 		__u32		attach_type;	/* attach type */
 		__u32		flags;		/* extra flags */
 		union {
-			__u32	target_btf_id;	/* btf_id of target to attach to */
+			__u32		target_btf_id;	/* btf_id of target to attach to */
 			struct {
 				__aligned_u64	iter_info;	/* extra bpf_iter_link_info */
 				__u32		iter_info_len;	/* iter_info length */
@@ -1771,29 +1579,6 @@ union bpf_attr {
 				__s32		priority;
 				__u32		flags;
 			} netfilter;
-			struct {
-				union {
-					__u32	relative_fd;
-					__u32	relative_id;
-				};
-				__u64		expected_revision;
-			} tcx;
-			struct {
-				__aligned_u64	path;
-				__aligned_u64	offsets;
-				__aligned_u64	ref_ctr_offsets;
-				__aligned_u64	cookies;
-				__u32		cnt;
-				__u32		flags;
-				__u32		pid;
-			} uprobe_multi;
-			struct {
-				union {
-					__u32	relative_fd;
-					__u32	relative_id;
-				};
-				__u64		expected_revision;
-			} netkit;
 		};
 	} link_create;
 
@@ -1837,11 +1622,6 @@ union bpf_attr {
 		__u32		flags;		/* extra flags */
 	} prog_bind_map;
 
-	struct { /* struct used by BPF_TOKEN_CREATE command */
-		__u32		flags;
-		__u32		bpffs_fd;
-	} token_create;
-
 } __attribute__((aligned(8)));
 
 /* The description below is an attempt at providing documentation to eBPF
@@ -1989,21 +1769,15 @@ union bpf_attr {
  * 		program.
  * 	Return
  * 		The SMP id of the processor running the program.
- * 	Attributes
- * 		__bpf_fastcall
  *
  * long bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags)
  * 	Description
  * 		Store *len* bytes from address *from* into the packet
- * 		associated to *skb*, at *offset*. The *flags* are a combination
+ * 		associated to *skb*, at *offset*. *flags* are a combination of
- * 		of the following values:
+ * 		**BPF_F_RECOMPUTE_CSUM** (automatically recompute the
- *
+ * 		checksum for the packet after storing the bytes) and
- * 		**BPF_F_RECOMPUTE_CSUM**
+ * 		**BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\
- * 			Automatically update *skb*\ **->csum** after storing the
+ * 		**->swhash** and *skb*\ **->l4hash** to 0).
- * 			bytes.
- * 		**BPF_F_INVALIDATE_HASH**
- * 			Set *skb*\ **->hash**, *skb*\ **->swhash** and *skb*\
- * 			**->l4hash** to 0.
  *
  * 		A call to this helper is susceptible to change the underlying
  * 		packet buffer. Therefore, at load time, all checks on pointers
@@ -2055,7 +1829,7 @@ union bpf_attr {
  * 		untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and
  * 		for updates resulting in a null checksum the value is set to
  * 		**CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates
- * 		that the modified header field is part of the pseudo-header.
+ * 		the checksum is to be computed against a pseudo-header.
  *
  * 		This helper works in combination with **bpf_csum_diff**\ (),
  * 		which does not update the checksum in-place, but offers more
@@ -2123,9 +1897,7 @@ union bpf_attr {
  * 		performed again, if the helper is used in combination with
  * 		direct packet access.
  * 	Return
- * 		0 on success, or a negative error in case of failure. Positive
+ * 		0 on success, or a negative error in case of failure.
- * 		error indicates a potential drop or congestion in the target
- * 		device. The particular positive error codes are not defined.
  *
  * u64 bpf_get_current_pid_tgid(void)
  * 	Description
@@ -2858,8 +2630,8 @@ union bpf_attr {
  * 		*bpf_socket* should be one of the following:
  *
  * 		* **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
- *		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**,
+ * 		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
- *		  **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**.
+ * 		  and **BPF_CGROUP_INET6_CONNECT**.
  *
  * 		This helper actually implements a subset of **setsockopt()**.
  * 		It supports the following *level*\ s:
@@ -2876,7 +2648,7 @@ union bpf_attr {
  * 		  **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**,
  * 		  **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**,
  * 		  **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**,
- *		  **TCP_BPF_RTO_MIN**, **TCP_BPF_SOCK_OPS_CB_FLAGS**.
+ * 		  **TCP_BPF_RTO_MIN**.
  * 		* **IPPROTO_IP**, which supports *optname* **IP_TOS**.
  * 		* **IPPROTO_IPV6**, which supports the following *optname*\ s:
  * 		  **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**.
@@ -3097,8 +2869,8 @@ union bpf_attr {
  * 		*bpf_socket* should be one of the following:
  *
  * 		* **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
- *		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**,
+ * 		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
- *		  **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**.
+ * 		  and **BPF_CGROUP_INET6_CONNECT**.
  *
  * 		This helper actually implements a subset of **getsockopt()**.
  * 		It supports the same set of *optname*\ s that is supported by
@@ -3126,6 +2898,10 @@ union bpf_attr {
  * 		with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration
  * 		option, and in this case it only works on functions tagged with
  * 		**ALLOW_ERROR_INJECTION** in the kernel code.
+ *
+ * 		Also, the helper is only available for the architectures having
+ * 		the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing,
+ * 		x86 architecture is the only one to support this feature.
  * 	Return
  * 		0
  *
@@ -3414,15 +3190,6 @@ union bpf_attr {
  *			and *params*->smac will not be set as output. A common
  *			use case is to call **bpf_redirect_neigh**\ () after
  *			doing **bpf_fib_lookup**\ ().
- *		**BPF_FIB_LOOKUP_SRC**
- *			Derive and set source IP addr in *params*->ipv{4,6}_src
- *			for the nexthop. If the src addr cannot be derived,
- *			**BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this
- *			case, *params*->dmac and *params*->smac are not set either.
- *		**BPF_FIB_LOOKUP_MARK**
- *			Use the mark present in *params*->mark for the fib lookup.
- *			This option should not be used with BPF_FIB_LOOKUP_DIRECT,
- *			as it only has meaning for full lookups.
  *
  *		*ctx* is either **struct xdp_md** for XDP programs or
  *		**struct sk_buff** tc cls_act programs.
@@ -4392,6 +4159,9 @@ union bpf_attr {
  *		**-EOPNOTSUPP** if the operation is not supported, for example
  *		a call from outside of TC ingress.
  *
+ *		**-ESOCKTNOSUPPORT** if the socket type is not supported
+ *		(reuseport).
+ *
  * long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags)
  *	Description
  *		Helper is overloaded depending on BPF program type. This
@@ -4656,8 +4426,6 @@ union bpf_attr {
  * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags)
  *	Description
  *		Return a user or a kernel stack in bpf program provided buffer.
- *		Note: the user stack will only be populated if the *task* is
- *		the current task; all other tasks will return -EOPNOTSUPP.
  *		To achieve this, the helper needs *task*, which is a valid
  *		pointer to **struct task_struct**. To store the stacktrace, the
  *		bpf program provides *buf* with a nonnegative *size*.
@@ -4669,7 +4437,6 @@ union bpf_attr {
  *
  *		**BPF_F_USER_STACK**
  *			Collect a user space stack instead of a kernel stack.
- *			The *task* must be the current task.
  *		**BPF_F_USER_BUILD_ID**
  *			Collect buildid+offset instead of ips for user stack,
  *			only valid if **BPF_F_USER_STACK** is also specified.
@@ -4973,9 +4740,9 @@ union bpf_attr {
  * 		going through the CPU's backlog queue.
  *
  * 		The *flags* argument is reserved and must be 0. The helper is
- * 		currently only supported for tc BPF program types at the
+ * 		currently only supported for tc BPF program types at the ingress
- * 		ingress hook and for veth and netkit target device types. The
+ * 		hook and for veth device types. The peer device must reside in a
- * 		peer device must reside in a different network namespace.
+ * 		different network namespace.
  * 	Return
  * 		The helper returns **TC_ACT_REDIRECT** on success or
  * 		**TC_ACT_SHOT** on error.
@@ -5051,7 +4818,7 @@ union bpf_attr {
  *		bytes will be copied to *dst*
  *	Return
  *		The **hash_algo** is returned on success,
- *		**-EOPNOTSUPP** if IMA is disabled or **-EINVAL** if
+ *		**-EOPNOTSUP** if IMA is disabled or **-EINVAL** if
  *		invalid arguments are passed.
  *
  * struct socket *bpf_sock_from_file(struct file *file)
@@ -5258,8 +5025,6 @@ union bpf_attr {
  *		**BPF_F_TIMER_ABS**
  *			Start the timer in absolute expire value instead of the
  *			default relative one.
- *		**BPF_F_TIMER_CPU_PIN**
- *			Timer will be pinned to the CPU of the caller.
  *
  *	Return
  *		0 on success.
@@ -5279,14 +5044,9 @@ union bpf_attr {
  * u64 bpf_get_func_ip(void *ctx)
  * 	Description
  * 		Get address of the traced function (for tracing and kprobe programs).
- *
- * 		When called for kprobe program attached as uprobe it returns
- * 		probe address for both entry and return uprobe.
- *
  * 	Return
- * 		Address of the traced function for kprobe.
+ * 		Address of the traced function.
  * 		0 for kprobes placed within the function (not at the entry).
- * 		Address of the probe for uprobe and return uprobe.
  *
  * u64 bpf_get_attach_cookie(void *ctx)
  * 	Description
@@ -5390,7 +5150,7 @@ union bpf_attr {
  *		Currently, the **flags** must be 0. Currently, nr_loops is
  *		limited to 1 << 23 (~8 million) loops.
  *
- *		long (\*callback_fn)(u64 index, void \*ctx);
+ *		long (\*callback_fn)(u32 index, void \*ctx);
  *
  *		where **index** is the current index in the loop. The index
  *		is zero-indexed.
@@ -5537,15 +5297,14 @@ union bpf_attr {
  *		bytes will be copied to *dst*
  *	Return
  *		The **hash_algo** is returned on success,
- *		**-EOPNOTSUPP** if the hash calculation failed or **-EINVAL** if
+ *		**-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if
  *		invalid arguments are passed.
  *
- * void *bpf_kptr_xchg(void *dst, void *ptr)
+ * void *bpf_kptr_xchg(void *map_value, void *ptr)
  *	Description
- *		Exchange kptr at pointer *dst* with *ptr*, and return the old value.
+ *		Exchange kptr at pointer *map_value* with *ptr*, and return the
- *		*dst* can be map value or local kptr. *ptr* can be NULL, otherwise
+ *		old value. *ptr* can be NULL, otherwise it must be a referenced
- *		it must be a referenced pointer which will be released when this helper
+ *		pointer which will be released when this helper is called.
- *		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
@@ -6028,10 +5787,7 @@ union bpf_attr {
 	FN(user_ringbuf_drain, 209, ##ctx)		\
 	FN(cgrp_storage_get, 210, ##ctx)		\
 	FN(cgrp_storage_delete, 211, ##ctx)		\
-	/* This helper list is effectively frozen. If you are trying to	\
+	/* */
-	 * add a new helper, you should add a kfunc instead which has	\
-	 * less stability guarantees. See Documentation/bpf/kfuncs.rst	\
-	 */
 
 /* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't
  * know or care about integer value that is now passed as second argument
@@ -6071,6 +5827,11 @@ enum {
 	BPF_F_MARK_ENFORCE		= (1ULL << 6),
 };
 
+/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */
+enum {
+	BPF_F_INGRESS			= (1ULL << 0),
+};
+
 /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
 enum {
 	BPF_F_TUNINFO_IPV6		= (1ULL << 0),
@@ -6217,12 +5978,10 @@ enum {
 	BPF_F_BPRM_SECUREEXEC	= (1ULL << 0),
 };
 
-/* Flags for bpf_redirect and bpf_redirect_map helpers */
+/* Flags for bpf_redirect_map helper */
 enum {
-	BPF_F_INGRESS		= (1ULL << 0), /* used for skb path */
+	BPF_F_BROADCAST		= (1ULL << 3),
-	BPF_F_BROADCAST		= (1ULL << 3), /* used for XDP path */
+	BPF_F_EXCLUDE_INGRESS	= (1ULL << 4),
-	BPF_F_EXCLUDE_INGRESS	= (1ULL << 4), /* used for XDP path */
-#define BPF_F_REDIRECT_FLAGS (BPF_F_INGRESS | BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS)
 };
 
 #define __bpf_md_ptr(type, name)	\
@@ -6231,17 +5990,12 @@ union {					\
 	__u64 :64;			\
 } __attribute__((aligned(8)))
 
-/* The enum used in skb->tstamp_type. It specifies the clock type
- * of the time stored in the skb->tstamp.
- */
 enum {
-	BPF_SKB_TSTAMP_UNSPEC = 0,		/* DEPRECATED */
+	BPF_SKB_TSTAMP_UNSPEC,
-	BPF_SKB_TSTAMP_DELIVERY_MONO = 1,	/* DEPRECATED */
+	BPF_SKB_TSTAMP_DELIVERY_MONO,	/* tstamp has mono delivery time */
-	BPF_SKB_CLOCK_REALTIME = 0,
+	/* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle,
-	BPF_SKB_CLOCK_MONOTONIC = 1,
+	 * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC
-	BPF_SKB_CLOCK_TAI = 2,
+	 * and try to deduce it by ingress, egress or skb->sk->sk_clockid.
-	/* For any future BPF_SKB_CLOCK_* that the bpf prog cannot handle,
-	 * the bpf prog can try to deduce it by ingress/egress/skb->sk->sk_clockid.
 	 */
 };
 
@@ -6433,19 +6187,6 @@ struct bpf_sock_tuple {
 	};
 };
 
-/* (Simplified) user return codes for tcx prog type.
- * A valid tcx program must return one of these defined values. All other
- * return codes are reserved for future use. Must remain compatible with
- * their TC_ACT_* counter-parts. For compatibility in behavior, unknown
- * return codes are mapped to TCX_NEXT.
- */
-enum tcx_action_base {
-	TCX_NEXT	= -1,
-	TCX_PASS	= 0,
-	TCX_DROP	= 2,
-	TCX_REDIRECT	= 7,
-};
-
 struct bpf_xdp_sock {
 	__u32 queue_id;
 };
@@ -6627,7 +6368,7 @@ struct bpf_map_info {
 	__u32 btf_id;
 	__u32 btf_key_type_id;
 	__u32 btf_value_type_id;
-	__u32 btf_vmlinux_id;
+	__u32 :32;	/* alignment pad */
 	__u64 map_extra;
 } __attribute__((aligned(8)));
 
@@ -6698,68 +6439,6 @@ struct bpf_link_info {
 			__s32 priority;
 			__u32 flags;
 		} netfilter;
-		struct {
-			__aligned_u64 addrs;
-			__u32 count; /* in/out: kprobe_multi function count */
-			__u32 flags;
-			__u64 missed;
-			__aligned_u64 cookies;
-		} kprobe_multi;
-		struct {
-			__aligned_u64 path;
-			__aligned_u64 offsets;
-			__aligned_u64 ref_ctr_offsets;
-			__aligned_u64 cookies;
-			__u32 path_size; /* in/out: real path size on success, including zero byte */
-			__u32 count; /* in/out: uprobe_multi offsets/ref_ctr_offsets/cookies count */
-			__u32 flags;
-			__u32 pid;
-		} uprobe_multi;
-		struct {
-			__u32 type; /* enum bpf_perf_event_type */
-			__u32 :32;
-			union {
-				struct {
-					__aligned_u64 file_name; /* in/out */
-					__u32 name_len;
-					__u32 offset; /* offset from file_name */
-					__u64 cookie;
-					__u64 ref_ctr_offset;
-				} uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */
-				struct {
-					__aligned_u64 func_name; /* in/out */
-					__u32 name_len;
-					__u32 offset; /* offset from func_name */
-					__u64 addr;
-					__u64 missed;
-					__u64 cookie;
-				} kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */
-				struct {
-					__aligned_u64 tp_name;   /* in/out */
-					__u32 name_len;
-					__u32 :32;
-					__u64 cookie;
-				} tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */
-				struct {
-					__u64 config;
-					__u32 type;
-					__u32 :32;
-					__u64 cookie;
-				} event; /* BPF_PERF_EVENT_EVENT */
-			};
-		} perf_event;
-		struct {
-			__u32 ifindex;
-			__u32 attach_type;
-		} tcx;
-		struct {
-			__u32 ifindex;
-			__u32 attach_type;
-		} netkit;
-		struct {
-			__u32 map_id;
-			__u32 attach_type;
-		} sockmap;
 	};
 } __attribute__((aligned(8)));
 
@@ -6926,12 +6605,6 @@ enum {
 	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0x7F,
 };
 
-enum {
-	SK_BPF_CB_TX_TIMESTAMPING	= 1<<0,
-	SK_BPF_CB_MASK			= (SK_BPF_CB_TX_TIMESTAMPING - 1) |
-					   SK_BPF_CB_TX_TIMESTAMPING
-};
-
 /* List of known BPF sock_ops operators.
  * New entries can only be added at the end
  */
@@ -6984,8 +6657,6 @@ enum {
 					 * socket transition to LISTEN state.
 					 */
 	BPF_SOCK_OPS_RTT_CB,		/* Called on every RTT.
-					 * Arg1: measured RTT input (mrtt)
-					 * Arg2: updated srtt
 					 */
 	BPF_SOCK_OPS_PARSE_HDR_OPT_CB,	/* Parse the header option.
 					 * It will be called to handle
@@ -7044,29 +6715,6 @@ enum {
 					 * by the kernel or the
 					 * earlier bpf-progs.
 					 */
-	BPF_SOCK_OPS_TSTAMP_SCHED_CB,	/* Called when skb is passing
-					 * through dev layer when
-					 * SK_BPF_CB_TX_TIMESTAMPING
-					 * feature is on.
-					 */
-	BPF_SOCK_OPS_TSTAMP_SND_SW_CB,	/* Called when skb is about to send
-					 * to the nic when SK_BPF_CB_TX_TIMESTAMPING
-					 * feature is on.
-					 */
-	BPF_SOCK_OPS_TSTAMP_SND_HW_CB,	/* Called in hardware phase when
-					 * SK_BPF_CB_TX_TIMESTAMPING feature
-					 * is on.
-					 */
-	BPF_SOCK_OPS_TSTAMP_ACK_CB,	/* Called when all the skbs in the
-					 * same sendmsg call are acked
-					 * when SK_BPF_CB_TX_TIMESTAMPING
-					 * feature is on.
-					 */
-	BPF_SOCK_OPS_TSTAMP_SENDMSG_CB,	/* Called when every sendmsg syscall
-					 * is triggered. It's used to correlate
-					 * sendmsg timestamp with corresponding
-					 * tskey.
-					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
@@ -7087,7 +6735,6 @@ enum {
 	BPF_TCP_LISTEN,
 	BPF_TCP_CLOSING,	/* Now a valid state */
 	BPF_TCP_NEW_SYN_RECV,
-	BPF_TCP_BOUND_INACTIVE,
 
 	BPF_TCP_MAX_STATES	/* Leave at the end! */
 };
@@ -7132,8 +6779,6 @@ enum {
 	TCP_BPF_SYN		= 1005, /* Copy the TCP header */
 	TCP_BPF_SYN_IP		= 1006, /* Copy the IP[46] and TCP header */
 	TCP_BPF_SYN_MAC         = 1007, /* Copy the MAC, IP[46], and TCP header */
-	TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */
-	SK_BPF_CB_FLAGS		= 1009, /* Get or set sock ops flags in socket */
 };
 
 enum {
@@ -7192,8 +6837,6 @@ enum {
 	BPF_FIB_LOOKUP_OUTPUT  = (1U << 1),
 	BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2),
 	BPF_FIB_LOOKUP_TBID    = (1U << 3),
-	BPF_FIB_LOOKUP_SRC     = (1U << 4),
-	BPF_FIB_LOOKUP_MARK    = (1U << 5),
 };
 
 enum {
@@ -7206,7 +6849,6 @@ enum {
 	BPF_FIB_LKUP_RET_UNSUPP_LWT,   /* fwd requires encapsulation */
 	BPF_FIB_LKUP_RET_NO_NEIGH,     /* no neighbor entry for nh */
 	BPF_FIB_LKUP_RET_FRAG_NEEDED,  /* fragmentation required to fwd */
-	BPF_FIB_LKUP_RET_NO_SRC_ADDR,  /* failed to derive IP src addr */
 };
 
 struct bpf_fib_lookup {
@@ -7226,7 +6868,7 @@ struct bpf_fib_lookup {
 
 		/* output: MTU value */
 		__u16	mtu_result;
-	} __attribute__((packed, aligned(2)));
+	};
 	/* input: L3 device index for lookup
 	 * output: device index from FIB lookup
 	 */
@@ -7241,9 +6883,6 @@ struct bpf_fib_lookup {
 		__u32	rt_metric;
 	};
 
-	/* input: source address to consider for lookup
-	 * output: source address result from lookup
-	 */
 	union {
 		__be32		ipv4_src;
 		__u32		ipv6_src[4];  /* in6_addr; network order */
@@ -7271,19 +6910,8 @@ struct bpf_fib_lookup {
 		__u32	tbid;
 	};
 
-	union {
+	__u8	smac[6];     /* ETH_ALEN */
-		/* input */
+	__u8	dmac[6];     /* ETH_ALEN */
-		struct {
-			__u32	mark;   /* policy routing */
-			/* 2 4-byte holes for input */
-		};
-
-		/* output: source and dest mac */
-		struct {
-			__u8	smac[6];	/* ETH_ALEN */
-			__u8	dmac[6];	/* ETH_ALEN */
-		};
-	};
 };
 
 struct bpf_redir_neigh {
@@ -7367,35 +6995,38 @@ struct bpf_spin_lock {
 };
 
 struct bpf_timer {
-	__u64 __opaque[2];
+	__u64 :64;
-} __attribute__((aligned(8)));
+	__u64 :64;
-
-struct bpf_wq {
-	__u64 __opaque[2];
 } __attribute__((aligned(8)));
 
 struct bpf_dynptr {
-	__u64 __opaque[2];
+	__u64 :64;
+	__u64 :64;
 } __attribute__((aligned(8)));
 
 struct bpf_list_head {
-	__u64 __opaque[2];
+	__u64 :64;
+	__u64 :64;
 } __attribute__((aligned(8)));
 
 struct bpf_list_node {
-	__u64 __opaque[3];
+	__u64 :64;
+	__u64 :64;
 } __attribute__((aligned(8)));
 
 struct bpf_rb_root {
-	__u64 __opaque[2];
+	__u64 :64;
+	__u64 :64;
 } __attribute__((aligned(8)));
 
 struct bpf_rb_node {
-	__u64 __opaque[4];
+	__u64 :64;
+	__u64 :64;
+	__u64 :64;
 } __attribute__((aligned(8)));
 
 struct bpf_refcount {
-	__u32 __opaque[1];
+	__u32 :32;
 } __attribute__((aligned(4)));
 
 struct bpf_sysctl {
@@ -7551,11 +7182,9 @@ struct bpf_core_relo {
  * Flags to control bpf_timer_start() behaviour.
  *     - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is
  *       relative to current time.
- *     - BPF_F_TIMER_CPU_PIN: Timer will be pinned to the CPU of the caller.
  */
 enum {
 	BPF_F_TIMER_ABS = (1ULL << 0),
-	BPF_F_TIMER_CPU_PIN = (1ULL << 1),
 };
 
 /* BPF numbers iterator state */
@@ -7566,13 +7195,4 @@ struct bpf_iter_num {
 	__u64 __opaque[1];
 } __attribute__((aligned(8)));
 
-/*
- * Flags to control BPF kfunc behaviour.
- *     - BPF_F_PAD_ZEROS: Pad destination buffer with zeros. (See the respective
- *       helper documentation for details.)
- */
-enum bpf_kfunc_flags {
-	BPF_F_PAD_ZEROS = (1ULL << 0),
-};
-
 #endif /* _UAPI__LINUX_BPF_H__ */

include/uapi/linux/btf.h

@@ -36,8 +36,7 @@ struct btf_type {
 	 * bits 24-28: kind (e.g. int, ptr, array...etc)
 	 * bits 29-30: unused
 	 * bit     31: kind_flag, currently used by
-	 *             struct, union, enum, fwd, enum64,
+	 *             struct, union, enum, fwd and enum64
-	 *             decl_tag and type_tag
 	 */
 	__u32 info;
 	/* "size" is used by INT, ENUM, STRUCT, UNION, DATASEC and ENUM64.

include/uapi/linux/fcntl.h

@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_FCNTL_H
+#define _UAPI_LINUX_FCNTL_H
+
+#include <asm/fcntl.h>
+#include <linux/openat2.h>
+
+#define F_SETLEASE	(F_LINUX_SPECIFIC_BASE + 0)
+#define F_GETLEASE	(F_LINUX_SPECIFIC_BASE + 1)
+
+/*
+ * Cancel a blocking posix lock; internal use only until we expose an
+ * asynchronous lock api to userspace:
+ */
+#define F_CANCELLK	(F_LINUX_SPECIFIC_BASE + 5)
+
+/* Create a file descriptor with FD_CLOEXEC set. */
+#define F_DUPFD_CLOEXEC	(F_LINUX_SPECIFIC_BASE + 6)
+
+/*
+ * Request nofications on a directory.
+ * See below for events that may be notified.
+ */
+#define F_NOTIFY	(F_LINUX_SPECIFIC_BASE+2)
+
+/*
+ * Set and get of pipe page size array
+ */
+#define F_SETPIPE_SZ	(F_LINUX_SPECIFIC_BASE + 7)
+#define F_GETPIPE_SZ	(F_LINUX_SPECIFIC_BASE + 8)
+
+/*
+ * Set/Get seals
+ */
+#define F_ADD_SEALS	(F_LINUX_SPECIFIC_BASE + 9)
+#define F_GET_SEALS	(F_LINUX_SPECIFIC_BASE + 10)
+
+/*
+ * Types of seals
+ */
+#define F_SEAL_SEAL	0x0001	/* prevent further seals from being set */
+#define F_SEAL_SHRINK	0x0002	/* prevent file from shrinking */
+#define F_SEAL_GROW	0x0004	/* prevent file from growing */
+#define F_SEAL_WRITE	0x0008	/* prevent writes */
+#define F_SEAL_FUTURE_WRITE	0x0010  /* prevent future writes while mapped */
+#define F_SEAL_EXEC	0x0020  /* prevent chmod modifying exec bits */
+/* (1U << 31) is reserved for signed error codes */
+
+/*
+ * Set/Get write life time hints. {GET,SET}_RW_HINT operate on the
+ * underlying inode, while {GET,SET}_FILE_RW_HINT operate only on
+ * the specific file.
+ */
+#define F_GET_RW_HINT		(F_LINUX_SPECIFIC_BASE + 11)
+#define F_SET_RW_HINT		(F_LINUX_SPECIFIC_BASE + 12)
+#define F_GET_FILE_RW_HINT	(F_LINUX_SPECIFIC_BASE + 13)
+#define F_SET_FILE_RW_HINT	(F_LINUX_SPECIFIC_BASE + 14)
+
+/*
+ * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be
+ * used to clear any hints previously set.
+ */
+#define RWH_WRITE_LIFE_NOT_SET	0
+#define RWH_WRITE_LIFE_NONE	1
+#define RWH_WRITE_LIFE_SHORT	2
+#define RWH_WRITE_LIFE_MEDIUM	3
+#define RWH_WRITE_LIFE_LONG	4
+#define RWH_WRITE_LIFE_EXTREME	5
+
+/*
+ * The originally introduced spelling is remained from the first
+ * versions of the patch set that introduced the feature, see commit
+ * v4.13-rc1~212^2~51.
+ */
+#define RWF_WRITE_LIFE_NOT_SET	RWH_WRITE_LIFE_NOT_SET
+
+/*
+ * Types of directory notifications that may be requested.
+ */
+#define DN_ACCESS	0x00000001	/* File accessed */
+#define DN_MODIFY	0x00000002	/* File modified */
+#define DN_CREATE	0x00000004	/* File created */
+#define DN_DELETE	0x00000008	/* File removed */
+#define DN_RENAME	0x00000010	/* File renamed */
+#define DN_ATTRIB	0x00000020	/* File changed attibutes */
+#define DN_MULTISHOT	0x80000000	/* Don't remove notifier */
+
+/*
+ * The constants AT_REMOVEDIR and AT_EACCESS have the same value.  AT_EACCESS is
+ * meaningful only to faccessat, while AT_REMOVEDIR is meaningful only to
+ * unlinkat.  The two functions do completely different things and therefore,
+ * the flags can be allowed to overlap.  For example, passing AT_REMOVEDIR to
+ * faccessat would be undefined behavior and thus treating it equivalent to
+ * AT_EACCESS is valid undefined behavior.
+ */
+#define AT_FDCWD		-100    /* Special value used to indicate
+                                           openat should use the current
+                                           working directory. */
+#define AT_SYMLINK_NOFOLLOW	0x100   /* Do not follow symbolic links.  */
+#define AT_EACCESS		0x200	/* Test access permitted for
+                                           effective IDs, not real IDs.  */
+#define AT_REMOVEDIR		0x200   /* Remove directory instead of
+                                           unlinking file.  */
+#define AT_SYMLINK_FOLLOW	0x400   /* Follow symbolic links.  */
+#define AT_NO_AUTOMOUNT		0x800	/* Suppress terminal automount traversal */
+#define AT_EMPTY_PATH		0x1000	/* Allow empty relative pathname */
+
+#define AT_STATX_SYNC_TYPE	0x6000	/* Type of synchronisation required from statx() */
+#define AT_STATX_SYNC_AS_STAT	0x0000	/* - Do whatever stat() does */
+#define AT_STATX_FORCE_SYNC	0x2000	/* - Force the attributes to be sync'd with the server */
+#define AT_STATX_DONT_SYNC	0x4000	/* - Don't sync attributes with the server */
+
+#define AT_RECURSIVE		0x8000	/* Apply to the entire subtree */
+
+#endif /* _UAPI_LINUX_FCNTL_H */

include/uapi/linux/if_link.h

@@ -211,9 +211,6 @@ struct rtnl_link_stats {
  * @rx_nohandler: Number of packets received on the interface
  *   but dropped by the networking stack because the device is
  *   not designated to receive packets (e.g. backup link in a bond).
- *
- * @rx_otherhost_dropped: Number of packets dropped due to mismatch
- *   in destination MAC address.
  */
 struct rtnl_link_stats64 {
 	__u64	rx_packets;
@@ -246,23 +243,6 @@ struct rtnl_link_stats64 {
 	__u64	rx_compressed;
 	__u64	tx_compressed;
 	__u64	rx_nohandler;
-
-	__u64	rx_otherhost_dropped;
-};
-
-/* Subset of link stats useful for in-HW collection. Meaning of the fields is as
- * for struct rtnl_link_stats64.
- */
-struct rtnl_hw_stats64 {
-	__u64	rx_packets;
-	__u64	tx_packets;
-	__u64	rx_bytes;
-	__u64	tx_bytes;
-	__u64	rx_errors;
-	__u64	tx_errors;
-	__u64	rx_dropped;
-	__u64	tx_dropped;
-	__u64	multicast;
 };
 
 /* The struct should be in sync with struct ifmap */
@@ -370,14 +350,7 @@ enum {
 	IFLA_GRO_MAX_SIZE,
 	IFLA_TSO_MAX_SIZE,
 	IFLA_TSO_MAX_SEGS,
-	IFLA_ALLMULTI,		/* Allmulti count: > 0 means acts ALLMULTI */
 
-	IFLA_DEVLINK_PORT,
-
-	IFLA_GSO_IPV4_MAX_SIZE,
-	IFLA_GRO_IPV4_MAX_SIZE,
-	IFLA_DPLL_PIN,
-	IFLA_MAX_PACING_OFFLOAD_HORIZON,
 	__IFLA_MAX
 };
 
@@ -462,286 +435,6 @@ enum in6_addr_gen_mode {
 
 /* Bridge section */
 
-/**
- * DOC: Bridge enum definition
- *
- * Please *note* that the timer values in the following section are expected
- * in clock_t format, which is seconds multiplied by USER_HZ (generally
- * defined as 100).
- *
- * @IFLA_BR_FORWARD_DELAY
- *   The bridge forwarding delay is the time spent in LISTENING state
- *   (before moving to LEARNING) and in LEARNING state (before moving
- *   to FORWARDING). Only relevant if STP is enabled.
- *
- *   The valid values are between (2 * USER_HZ) and (30 * USER_HZ).
- *   The default value is (15 * USER_HZ).
- *
- * @IFLA_BR_HELLO_TIME
- *   The time between hello packets sent by the bridge, when it is a root
- *   bridge or a designated bridge. Only relevant if STP is enabled.
- *
- *   The valid values are between (1 * USER_HZ) and (10 * USER_HZ).
- *   The default value is (2 * USER_HZ).
- *
- * @IFLA_BR_MAX_AGE
- *   The hello packet timeout is the time until another bridge in the
- *   spanning tree is assumed to be dead, after reception of its last hello
- *   message. Only relevant if STP is enabled.
- *
- *   The valid values are between (6 * USER_HZ) and (40 * USER_HZ).
- *   The default value is (20 * USER_HZ).
- *
- * @IFLA_BR_AGEING_TIME
- *   Configure the bridge's FDB entries aging time. It is the time a MAC
- *   address will be kept in the FDB after a packet has been received from
- *   that address. After this time has passed, entries are cleaned up.
- *   Allow values outside the 802.1 standard specification for special cases:
- *
- *     * 0 - entry never ages (all permanent)
- *     * 1 - entry disappears (no persistence)
- *
- *   The default value is (300 * USER_HZ).
- *
- * @IFLA_BR_STP_STATE
- *   Turn spanning tree protocol on (*IFLA_BR_STP_STATE* > 0) or off
- *   (*IFLA_BR_STP_STATE* == 0) for this bridge.
- *
- *   The default value is 0 (disabled).
- *
- * @IFLA_BR_PRIORITY
- *   Set this bridge's spanning tree priority, used during STP root bridge
- *   election.
- *
- *   The valid values are between 0 and 65535.
- *
- * @IFLA_BR_VLAN_FILTERING
- *   Turn VLAN filtering on (*IFLA_BR_VLAN_FILTERING* > 0) or off
- *   (*IFLA_BR_VLAN_FILTERING* == 0). When disabled, the bridge will not
- *   consider the VLAN tag when handling packets.
- *
- *   The default value is 0 (disabled).
- *
- * @IFLA_BR_VLAN_PROTOCOL
- *   Set the protocol used for VLAN filtering.
- *
- *   The valid values are 0x8100(802.1Q) or 0x88A8(802.1AD). The default value
- *   is 0x8100(802.1Q).
- *
- * @IFLA_BR_GROUP_FWD_MASK
- *   The group forwarding mask. This is the bitmask that is applied to
- *   decide whether to forward incoming frames destined to link-local
- *   addresses (of the form 01:80:C2:00:00:0X).
- *
- *   The default value is 0, which means the bridge does not forward any
- *   link-local frames coming on this port.
- *
- * @IFLA_BR_ROOT_ID
- *   The bridge root id, read only.
- *
- * @IFLA_BR_BRIDGE_ID
- *   The bridge id, read only.
- *
- * @IFLA_BR_ROOT_PORT
- *   The bridge root port, read only.
- *
- * @IFLA_BR_ROOT_PATH_COST
- *   The bridge root path cost, read only.
- *
- * @IFLA_BR_TOPOLOGY_CHANGE
- *   The bridge topology change, read only.
- *
- * @IFLA_BR_TOPOLOGY_CHANGE_DETECTED
- *   The bridge topology change detected, read only.
- *
- * @IFLA_BR_HELLO_TIMER
- *   The bridge hello timer, read only.
- *
- * @IFLA_BR_TCN_TIMER
- *   The bridge tcn timer, read only.
- *
- * @IFLA_BR_TOPOLOGY_CHANGE_TIMER
- *   The bridge topology change timer, read only.
- *
- * @IFLA_BR_GC_TIMER
- *   The bridge gc timer, read only.
- *
- * @IFLA_BR_GROUP_ADDR
- *   Set the MAC address of the multicast group this bridge uses for STP.
- *   The address must be a link-local address in standard Ethernet MAC address
- *   format. It is an address of the form 01:80:C2:00:00:0X, with X in [0, 4..f].
- *
- *   The default value is 0.
- *
- * @IFLA_BR_FDB_FLUSH
- *   Flush bridge's fdb dynamic entries.
- *
- * @IFLA_BR_MCAST_ROUTER
- *   Set bridge's multicast router if IGMP snooping is enabled.
- *   The valid values are:
- *
- *     * 0 - disabled.
- *     * 1 - automatic (queried).
- *     * 2 - permanently enabled.
- *
- *   The default value is 1.
- *
- * @IFLA_BR_MCAST_SNOOPING
- *   Turn multicast snooping on (*IFLA_BR_MCAST_SNOOPING* > 0) or off
- *   (*IFLA_BR_MCAST_SNOOPING* == 0).
- *
- *   The default value is 1.
- *
- * @IFLA_BR_MCAST_QUERY_USE_IFADDR
- *   If enabled use the bridge's own IP address as source address for IGMP
- *   queries (*IFLA_BR_MCAST_QUERY_USE_IFADDR* > 0) or the default of 0.0.0.0
- *   (*IFLA_BR_MCAST_QUERY_USE_IFADDR* == 0).
- *
- *   The default value is 0 (disabled).
- *
- * @IFLA_BR_MCAST_QUERIER
- *   Enable (*IFLA_BR_MULTICAST_QUERIER* > 0) or disable
- *   (*IFLA_BR_MULTICAST_QUERIER* == 0) IGMP querier, ie sending of multicast
- *   queries by the bridge.
- *
- *   The default value is 0 (disabled).
- *
- * @IFLA_BR_MCAST_HASH_ELASTICITY
- *   Set multicast database hash elasticity, It is the maximum chain length in
- *   the multicast hash table. This attribute is *deprecated* and the value
- *   is always 16.
- *
- * @IFLA_BR_MCAST_HASH_MAX
- *   Set maximum size of the multicast hash table
- *
- *   The default value is 4096, the value must be a power of 2.
- *
- * @IFLA_BR_MCAST_LAST_MEMBER_CNT
- *   The Last Member Query Count is the number of Group-Specific Queries
- *   sent before the router assumes there are no local members. The Last
- *   Member Query Count is also the number of Group-and-Source-Specific
- *   Queries sent before the router assumes there are no listeners for a
- *   particular source.
- *
- *   The default value is 2.
- *
- * @IFLA_BR_MCAST_STARTUP_QUERY_CNT
- *   The Startup Query Count is the number of Queries sent out on startup,
- *   separated by the Startup Query Interval.
- *
- *   The default value is 2.
- *
- * @IFLA_BR_MCAST_LAST_MEMBER_INTVL
- *   The Last Member Query Interval is the Max Response Time inserted into
- *   Group-Specific Queries sent in response to Leave Group messages, and
- *   is also the amount of time between Group-Specific Query messages.
- *
- *   The default value is (1 * USER_HZ).
- *
- * @IFLA_BR_MCAST_MEMBERSHIP_INTVL
- *   The interval after which the bridge will leave a group, if no membership
- *   reports for this group are received.
- *
- *   The default value is (260 * USER_HZ).
- *
- * @IFLA_BR_MCAST_QUERIER_INTVL
- *   The interval between queries sent by other routers. if no queries are
- *   seen after this delay has passed, the bridge will start to send its own
- *   queries (as if *IFLA_BR_MCAST_QUERIER_INTVL* was enabled).
- *
- *   The default value is (255 * USER_HZ).
- *
- * @IFLA_BR_MCAST_QUERY_INTVL
- *   The Query Interval is the interval between General Queries sent by
- *   the Querier.
- *
- *   The default value is (125 * USER_HZ). The minimum value is (1 * USER_HZ).
- *
- * @IFLA_BR_MCAST_QUERY_RESPONSE_INTVL
- *   The Max Response Time used to calculate the Max Resp Code inserted
- *   into the periodic General Queries.
- *
- *   The default value is (10 * USER_HZ).
- *
- * @IFLA_BR_MCAST_STARTUP_QUERY_INTVL
- *   The interval between queries in the startup phase.
- *
- *   The default value is (125 * USER_HZ) / 4. The minimum value is (1 * USER_HZ).
- *
- * @IFLA_BR_NF_CALL_IPTABLES
- *   Enable (*NF_CALL_IPTABLES* > 0) or disable (*NF_CALL_IPTABLES* == 0)
- *   iptables hooks on the bridge.
- *
- *   The default value is 0 (disabled).
- *
- * @IFLA_BR_NF_CALL_IP6TABLES
- *   Enable (*NF_CALL_IP6TABLES* > 0) or disable (*NF_CALL_IP6TABLES* == 0)
- *   ip6tables hooks on the bridge.
- *
- *   The default value is 0 (disabled).
- *
- * @IFLA_BR_NF_CALL_ARPTABLES
- *   Enable (*NF_CALL_ARPTABLES* > 0) or disable (*NF_CALL_ARPTABLES* == 0)
- *   arptables hooks on the bridge.
- *
- *   The default value is 0 (disabled).
- *
- * @IFLA_BR_VLAN_DEFAULT_PVID
- *   VLAN ID applied to untagged and priority-tagged incoming packets.
- *
- *   The default value is 1. Setting to the special value 0 makes all ports of
- *   this bridge not have a PVID by default, which means that they will
- *   not accept VLAN-untagged traffic.
- *
- * @IFLA_BR_PAD
- *   Bridge attribute padding type for netlink message.
- *
- * @IFLA_BR_VLAN_STATS_ENABLED
- *   Enable (*IFLA_BR_VLAN_STATS_ENABLED* == 1) or disable
- *   (*IFLA_BR_VLAN_STATS_ENABLED* == 0) per-VLAN stats accounting.
- *
- *   The default value is 0 (disabled).
- *
- * @IFLA_BR_MCAST_STATS_ENABLED
- *   Enable (*IFLA_BR_MCAST_STATS_ENABLED* > 0) or disable
- *   (*IFLA_BR_MCAST_STATS_ENABLED* == 0) multicast (IGMP/MLD) stats
- *   accounting.
- *
- *   The default value is 0 (disabled).
- *
- * @IFLA_BR_MCAST_IGMP_VERSION
- *   Set the IGMP version.
- *
- *   The valid values are 2 and 3. The default value is 2.
- *
- * @IFLA_BR_MCAST_MLD_VERSION
- *   Set the MLD version.
- *
- *   The valid values are 1 and 2. The default value is 1.
- *
- * @IFLA_BR_VLAN_STATS_PER_PORT
- *   Enable (*IFLA_BR_VLAN_STATS_PER_PORT* == 1) or disable
- *   (*IFLA_BR_VLAN_STATS_PER_PORT* == 0) per-VLAN per-port stats accounting.
- *   Can be changed only when there are no port VLANs configured.
- *
- *   The default value is 0 (disabled).
- *
- * @IFLA_BR_MULTI_BOOLOPT
- *   The multi_boolopt is used to control new boolean options to avoid adding
- *   new netlink attributes. You can look at ``enum br_boolopt_id`` for those
- *   options.
- *
- * @IFLA_BR_MCAST_QUERIER_STATE
- *   Bridge mcast querier states, read only.
- *
- * @IFLA_BR_FDB_N_LEARNED
- *   The number of dynamically learned FDB entries for the current bridge,
- *   read only.
- *
- * @IFLA_BR_FDB_MAX_LEARNED
- *   Set the number of max dynamically learned FDB entries for the current
- *   bridge.
- */
 enum {
 	IFLA_BR_UNSPEC,
 	IFLA_BR_FORWARD_DELAY,
@@ -791,8 +484,6 @@ enum {
 	IFLA_BR_VLAN_STATS_PER_PORT,
 	IFLA_BR_MULTI_BOOLOPT,
 	IFLA_BR_MCAST_QUERIER_STATE,
-	IFLA_BR_FDB_N_LEARNED,
-	IFLA_BR_FDB_MAX_LEARNED,
 	__IFLA_BR_MAX,
 };
 
@@ -803,252 +494,11 @@ struct ifla_bridge_id {
 	__u8	addr[6]; /* ETH_ALEN */
 };
 
-/**
- * DOC: Bridge mode enum definition
- *
- * @BRIDGE_MODE_HAIRPIN
- *   Controls whether traffic may be sent back out of the port on which it
- *   was received. This option is also called reflective relay mode, and is
- *   used to support basic VEPA (Virtual Ethernet Port Aggregator)
- *   capabilities. By default, this flag is turned off and the bridge will
- *   not forward traffic back out of the receiving port.
- */
 enum {
 	BRIDGE_MODE_UNSPEC,
 	BRIDGE_MODE_HAIRPIN,
 };
 
-/**
- * DOC: Bridge port enum definition
- *
- * @IFLA_BRPORT_STATE
- *   The operation state of the port. Here are the valid values.
- *
- *     * 0 - port is in STP *DISABLED* state. Make this port completely
- *       inactive for STP. This is also called BPDU filter and could be used
- *       to disable STP on an untrusted port, like a leaf virtual device.
- *       The traffic forwarding is also stopped on this port.
- *     * 1 - port is in STP *LISTENING* state. Only valid if STP is enabled
- *       on the bridge. In this state the port listens for STP BPDUs and
- *       drops all other traffic frames.
- *     * 2 - port is in STP *LEARNING* state. Only valid if STP is enabled on
- *       the bridge. In this state the port will accept traffic only for the
- *       purpose of updating MAC address tables.
- *     * 3 - port is in STP *FORWARDING* state. Port is fully active.
- *     * 4 - port is in STP *BLOCKING* state. Only valid if STP is enabled on
- *       the bridge. This state is used during the STP election process.
- *       In this state, port will only process STP BPDUs.
- *
- * @IFLA_BRPORT_PRIORITY
- *   The STP port priority. The valid values are between 0 and 255.
- *
- * @IFLA_BRPORT_COST
- *   The STP path cost of the port. The valid values are between 1 and 65535.
- *
- * @IFLA_BRPORT_MODE
- *   Set the bridge port mode. See *BRIDGE_MODE_HAIRPIN* for more details.
- *
- * @IFLA_BRPORT_GUARD
- *   Controls whether STP BPDUs will be processed by the bridge port. By
- *   default, the flag is turned off to allow BPDU processing. Turning this
- *   flag on will disable the bridge port if a STP BPDU packet is received.
- *
- *   If the bridge has Spanning Tree enabled, hostile devices on the network
- *   may send BPDU on a port and cause network failure. Setting *guard on*
- *   will detect and stop this by disabling the port. The port will be
- *   restarted if the link is brought down, or removed and reattached.
- *
- * @IFLA_BRPORT_PROTECT
- *   Controls whether a given port is allowed to become a root port or not.
- *   Only used when STP is enabled on the bridge. By default the flag is off.
- *
- *   This feature is also called root port guard. If BPDU is received from a
- *   leaf (edge) port, it should not be elected as root port. This could
- *   be used if using STP on a bridge and the downstream bridges are not fully
- *   trusted; this prevents a hostile guest from rerouting traffic.
- *
- * @IFLA_BRPORT_FAST_LEAVE
- *   This flag allows the bridge to immediately stop multicast traffic
- *   forwarding on a port that receives an IGMP Leave message. It is only used
- *   when IGMP snooping is enabled on the bridge. By default the flag is off.
- *
- * @IFLA_BRPORT_LEARNING
- *   Controls whether a given port will learn *source* MAC addresses from
- *   received traffic or not. Also controls whether dynamic FDB entries
- *   (which can also be added by software) will be refreshed by incoming
- *   traffic. By default this flag is on.
- *
- * @IFLA_BRPORT_UNICAST_FLOOD
- *   Controls whether unicast traffic for which there is no FDB entry will
- *   be flooded towards this port. By default this flag is on.
- *
- * @IFLA_BRPORT_PROXYARP
- *   Enable proxy ARP on this port.
- *
- * @IFLA_BRPORT_LEARNING_SYNC
- *   Controls whether a given port will sync MAC addresses learned on device
- *   port to bridge FDB.
- *
- * @IFLA_BRPORT_PROXYARP_WIFI
- *   Enable proxy ARP on this port which meets extended requirements by
- *   IEEE 802.11 and Hotspot 2.0 specifications.
- *
- * @IFLA_BRPORT_ROOT_ID
- *
- * @IFLA_BRPORT_BRIDGE_ID
- *
- * @IFLA_BRPORT_DESIGNATED_PORT
- *
- * @IFLA_BRPORT_DESIGNATED_COST
- *
- * @IFLA_BRPORT_ID
- *
- * @IFLA_BRPORT_NO
- *
- * @IFLA_BRPORT_TOPOLOGY_CHANGE_ACK
- *
- * @IFLA_BRPORT_CONFIG_PENDING
- *
- * @IFLA_BRPORT_MESSAGE_AGE_TIMER
- *
- * @IFLA_BRPORT_FORWARD_DELAY_TIMER
- *
- * @IFLA_BRPORT_HOLD_TIMER
- *
- * @IFLA_BRPORT_FLUSH
- *   Flush bridge ports' fdb dynamic entries.
- *
- * @IFLA_BRPORT_MULTICAST_ROUTER
- *   Configure the port's multicast router presence. A port with
- *   a multicast router will receive all multicast traffic.
- *   The valid values are:
- *
- *     * 0 disable multicast routers on this port
- *     * 1 let the system detect the presence of routers (default)
- *     * 2 permanently enable multicast traffic forwarding on this port
- *     * 3 enable multicast routers temporarily on this port, not depending
- *         on incoming queries.
- *
- * @IFLA_BRPORT_PAD
- *
- * @IFLA_BRPORT_MCAST_FLOOD
- *   Controls whether a given port will flood multicast traffic for which
- *   there is no MDB entry. By default this flag is on.
- *
- * @IFLA_BRPORT_MCAST_TO_UCAST
- *   Controls whether a given port will replicate packets using unicast
- *   instead of multicast. By default this flag is off.
- *
- *   This is done by copying the packet per host and changing the multicast
- *   destination MAC to a unicast one accordingly.
- *
- *   *mcast_to_unicast* works on top of the multicast snooping feature of the
- *   bridge. Which means unicast copies are only delivered to hosts which
- *   are interested in unicast and signaled this via IGMP/MLD reports previously.
- *
- *   This feature is intended for interface types which have a more reliable
- *   and/or efficient way to deliver unicast packets than broadcast ones
- *   (e.g. WiFi).
- *
- *   However, it should only be enabled on interfaces where no IGMPv2/MLDv1
- *   report suppression takes place. IGMP/MLD report suppression issue is
- *   usually overcome by the network daemon (supplicant) enabling AP isolation
- *   and by that separating all STAs.
- *
- *   Delivery of STA-to-STA IP multicast is made possible again by enabling
- *   and utilizing the bridge hairpin mode, which considers the incoming port
- *   as a potential outgoing port, too (see *BRIDGE_MODE_HAIRPIN* option).
- *   Hairpin mode is performed after multicast snooping, therefore leading
- *   to only deliver reports to STAs running a multicast router.
- *
- * @IFLA_BRPORT_VLAN_TUNNEL
- *   Controls whether vlan to tunnel mapping is enabled on the port.
- *   By default this flag is off.
- *
- * @IFLA_BRPORT_BCAST_FLOOD
- *   Controls flooding of broadcast traffic on the given port. By default
- *   this flag is on.
- *
- * @IFLA_BRPORT_GROUP_FWD_MASK
- *   Set the group forward mask. This is a bitmask that is applied to
- *   decide whether to forward incoming frames destined to link-local
- *   addresses. The addresses of the form are 01:80:C2:00:00:0X (defaults
- *   to 0, which means the bridge does not forward any link-local frames
- *   coming on this port).
- *
- * @IFLA_BRPORT_NEIGH_SUPPRESS
- *   Controls whether neighbor discovery (arp and nd) proxy and suppression
- *   is enabled on the port. By default this flag is off.
- *
- * @IFLA_BRPORT_ISOLATED
- *   Controls whether a given port will be isolated, which means it will be
- *   able to communicate with non-isolated ports only. By default this
- *   flag is off.
- *
- * @IFLA_BRPORT_BACKUP_PORT
- *   Set a backup port. If the port loses carrier all traffic will be
- *   redirected to the configured backup port. Set the value to 0 to disable
- *   it.
- *
- * @IFLA_BRPORT_MRP_RING_OPEN
- *
- * @IFLA_BRPORT_MRP_IN_OPEN
- *
- * @IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT
- *   The number of per-port EHT hosts limit. The default value is 512.
- *   Setting to 0 is not allowed.
- *
- * @IFLA_BRPORT_MCAST_EHT_HOSTS_CNT
- *   The current number of tracked hosts, read only.
- *
- * @IFLA_BRPORT_LOCKED
- *   Controls whether a port will be locked, meaning that hosts behind the
- *   port will not be able to communicate through the port unless an FDB
- *   entry with the unit's MAC address is in the FDB. The common use case is
- *   that hosts are allowed access through authentication with the IEEE 802.1X
- *   protocol or based on whitelists. By default this flag is off.
- *
- *   Please note that secure 802.1X deployments should always use the
- *   *BR_BOOLOPT_NO_LL_LEARN* flag, to not permit the bridge to populate its
- *   FDB based on link-local (EAPOL) traffic received on the port.
- *
- * @IFLA_BRPORT_MAB
- *   Controls whether a port will use MAC Authentication Bypass (MAB), a
- *   technique through which select MAC addresses may be allowed on a locked
- *   port, without using 802.1X authentication. Packets with an unknown source
- *   MAC address generates a "locked" FDB entry on the incoming bridge port.
- *   The common use case is for user space to react to these bridge FDB
- *   notifications and optionally replace the locked FDB entry with a normal
- *   one, allowing traffic to pass for whitelisted MAC addresses.
- *
- *   Setting this flag also requires *IFLA_BRPORT_LOCKED* and
- *   *IFLA_BRPORT_LEARNING*. *IFLA_BRPORT_LOCKED* ensures that unauthorized
- *   data packets are dropped, and *IFLA_BRPORT_LEARNING* allows the dynamic
- *   FDB entries installed by user space (as replacements for the locked FDB
- *   entries) to be refreshed and/or aged out.
- *
- * @IFLA_BRPORT_MCAST_N_GROUPS
- *
- * @IFLA_BRPORT_MCAST_MAX_GROUPS
- *   Sets the maximum number of MDB entries that can be registered for a
- *   given port. Attempts to register more MDB entries at the port than this
- *   limit allows will be rejected, whether they are done through netlink
- *   (e.g. the bridge tool), or IGMP or MLD membership reports. Setting a
- *   limit of 0 disables the limit. The default value is 0.
- *
- * @IFLA_BRPORT_NEIGH_VLAN_SUPPRESS
- *   Controls whether neighbor discovery (arp and nd) proxy and suppression is
- *   enabled for a given port. By default this flag is off.
- *
- *   Note that this option only takes effect when *IFLA_BRPORT_NEIGH_SUPPRESS*
- *   is enabled for a given port.
- *
- * @IFLA_BRPORT_BACKUP_NHID
- *   The FDB nexthop object ID to attach to packets being redirected to a
- *   backup port that has VLAN tunnel mapping enabled (via the
- *   *IFLA_BRPORT_VLAN_TUNNEL* option). Setting a value of 0 (default) has
- *   the effect of not attaching any ID.
- */
 enum {
 	IFLA_BRPORT_UNSPEC,
 	IFLA_BRPORT_STATE,	/* Spanning tree state     */
@@ -1089,12 +539,6 @@ enum {
 	IFLA_BRPORT_MRP_IN_OPEN,
 	IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT,
 	IFLA_BRPORT_MCAST_EHT_HOSTS_CNT,
-	IFLA_BRPORT_LOCKED,
-	IFLA_BRPORT_MAB,
-	IFLA_BRPORT_MCAST_N_GROUPS,
-	IFLA_BRPORT_MCAST_MAX_GROUPS,
-	IFLA_BRPORT_NEIGH_VLAN_SUPPRESS,
-	IFLA_BRPORT_BACKUP_NHID,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -1272,96 +716,7 @@ enum ipvlan_mode {
 #define IPVLAN_F_PRIVATE	0x01
 #define IPVLAN_F_VEPA		0x02
 
-/* Tunnel RTM header */
-struct tunnel_msg {
-	__u8 family;
-	__u8 flags;
-	__u16 reserved2;
-	__u32 ifindex;
-};
-
-/* netkit section */
-enum netkit_action {
-	NETKIT_NEXT	= -1,
-	NETKIT_PASS	= 0,
-	NETKIT_DROP	= 2,
-	NETKIT_REDIRECT	= 7,
-};
-
-enum netkit_mode {
-	NETKIT_L2,
-	NETKIT_L3,
-};
-
-/* NETKIT_SCRUB_NONE leaves clearing skb->{mark,priority} up to
- * the BPF program if attached. This also means the latter can
- * consume the two fields if they were populated earlier.
- *
- * NETKIT_SCRUB_DEFAULT zeroes skb->{mark,priority} fields before
- * invoking the attached BPF program when the peer device resides
- * in a different network namespace. This is the default behavior.
- */
-enum netkit_scrub {
-	NETKIT_SCRUB_NONE,
-	NETKIT_SCRUB_DEFAULT,
-};
-
-enum {
-	IFLA_NETKIT_UNSPEC,
-	IFLA_NETKIT_PEER_INFO,
-	IFLA_NETKIT_PRIMARY,
-	IFLA_NETKIT_POLICY,
-	IFLA_NETKIT_PEER_POLICY,
-	IFLA_NETKIT_MODE,
-	IFLA_NETKIT_SCRUB,
-	IFLA_NETKIT_PEER_SCRUB,
-	IFLA_NETKIT_HEADROOM,
-	IFLA_NETKIT_TAILROOM,
-	__IFLA_NETKIT_MAX,
-};
-#define IFLA_NETKIT_MAX	(__IFLA_NETKIT_MAX - 1)
-
 /* VXLAN section */
-
-/* include statistics in the dump */
-#define TUNNEL_MSG_FLAG_STATS	0x01
-
-#define TUNNEL_MSG_VALID_USER_FLAGS TUNNEL_MSG_FLAG_STATS
-
-/* Embedded inside VXLAN_VNIFILTER_ENTRY_STATS */
-enum {
-	VNIFILTER_ENTRY_STATS_UNSPEC,
-	VNIFILTER_ENTRY_STATS_RX_BYTES,
-	VNIFILTER_ENTRY_STATS_RX_PKTS,
-	VNIFILTER_ENTRY_STATS_RX_DROPS,
-	VNIFILTER_ENTRY_STATS_RX_ERRORS,
-	VNIFILTER_ENTRY_STATS_TX_BYTES,
-	VNIFILTER_ENTRY_STATS_TX_PKTS,
-	VNIFILTER_ENTRY_STATS_TX_DROPS,
-	VNIFILTER_ENTRY_STATS_TX_ERRORS,
-	VNIFILTER_ENTRY_STATS_PAD,
-	__VNIFILTER_ENTRY_STATS_MAX
-};
-#define VNIFILTER_ENTRY_STATS_MAX (__VNIFILTER_ENTRY_STATS_MAX - 1)
-
-enum {
-	VXLAN_VNIFILTER_ENTRY_UNSPEC,
-	VXLAN_VNIFILTER_ENTRY_START,
-	VXLAN_VNIFILTER_ENTRY_END,
-	VXLAN_VNIFILTER_ENTRY_GROUP,
-	VXLAN_VNIFILTER_ENTRY_GROUP6,
-	VXLAN_VNIFILTER_ENTRY_STATS,
-	__VXLAN_VNIFILTER_ENTRY_MAX
-};
-#define VXLAN_VNIFILTER_ENTRY_MAX	(__VXLAN_VNIFILTER_ENTRY_MAX - 1)
-
-enum {
-	VXLAN_VNIFILTER_UNSPEC,
-	VXLAN_VNIFILTER_ENTRY,
-	__VXLAN_VNIFILTER_MAX
-};
-#define VXLAN_VNIFILTER_MAX	(__VXLAN_VNIFILTER_MAX - 1)
-
 enum {
 	IFLA_VXLAN_UNSPEC,
 	IFLA_VXLAN_ID,
@@ -1393,9 +748,6 @@ enum {
 	IFLA_VXLAN_GPE,
 	IFLA_VXLAN_TTL_INHERIT,
 	IFLA_VXLAN_DF,
-	IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */
-	IFLA_VXLAN_LOCALBYPASS,
-	IFLA_VXLAN_LABEL_POLICY, /* IPv6 flow label policy; ifla_vxlan_label_policy */
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
@@ -1413,13 +765,6 @@ enum ifla_vxlan_df {
 	VXLAN_DF_MAX = __VXLAN_DF_END - 1,
 };
 
-enum ifla_vxlan_label_policy {
-	VXLAN_LABEL_FIXED = 0,
-	VXLAN_LABEL_INHERIT = 1,
-	__VXLAN_LABEL_END,
-	VXLAN_LABEL_MAX = __VXLAN_LABEL_END - 1,
-};
-
 /* GENEVE section */
 enum {
 	IFLA_GENEVE_UNSPEC,
@@ -1436,7 +781,6 @@ enum {
 	IFLA_GENEVE_LABEL,
 	IFLA_GENEVE_TTL_INHERIT,
 	IFLA_GENEVE_DF,
-	IFLA_GENEVE_INNER_PROTO_INHERIT,
 	__IFLA_GENEVE_MAX
 };
 #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
@@ -1482,10 +826,6 @@ enum {
 	IFLA_GTP_FD1,
 	IFLA_GTP_PDP_HASHSIZE,
 	IFLA_GTP_ROLE,
-	IFLA_GTP_CREATE_SOCKETS,
-	IFLA_GTP_RESTART_COUNT,
-	IFLA_GTP_LOCAL,
-	IFLA_GTP_LOCAL6,
 	__IFLA_GTP_MAX,
 };
 #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1)
@@ -1525,7 +865,6 @@ enum {
 	IFLA_BOND_AD_LACP_ACTIVE,
 	IFLA_BOND_MISSED_MAX,
 	IFLA_BOND_NS_IP6_TARGET,
-	IFLA_BOND_COUPLED_CONTROL,
 	__IFLA_BOND_MAX,
 };
 
@@ -1791,7 +1130,6 @@ enum {
 	IFLA_HSR_PROTOCOL,		/* Indicate different protocol than
 					 * HSR. For example PRP.
 					 */
-	IFLA_HSR_INTERLINK,		/* HSR interlink network device */
 	__IFLA_HSR_MAX,
 };
 
@@ -1824,17 +1162,6 @@ enum {
 
 #define IFLA_STATS_FILTER_BIT(ATTR)	(1 << (ATTR - 1))
 
-enum {
-	IFLA_STATS_GETSET_UNSPEC,
-	IFLA_STATS_GET_FILTERS, /* Nest of IFLA_STATS_LINK_xxx, each a u32 with
-				 * a filter mask for the corresponding group.
-				 */
-	IFLA_STATS_SET_OFFLOAD_XSTATS_L3_STATS, /* 0 or 1 as u8 */
-	__IFLA_STATS_GETSET_MAX,
-};
-
-#define IFLA_STATS_GETSET_MAX (__IFLA_STATS_GETSET_MAX - 1)
-
 /* These are embedded into IFLA_STATS_LINK_XSTATS:
  * [IFLA_STATS_LINK_XSTATS]
  * -> [LINK_XSTATS_TYPE_xxx]
@@ -1852,21 +1179,10 @@ enum {
 enum {
 	IFLA_OFFLOAD_XSTATS_UNSPEC,
 	IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */
-	IFLA_OFFLOAD_XSTATS_HW_S_INFO,	/* HW stats info. A nest */
-	IFLA_OFFLOAD_XSTATS_L3_STATS,	/* struct rtnl_hw_stats64 */
 	__IFLA_OFFLOAD_XSTATS_MAX
 };
 #define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1)
 
-enum {
-	IFLA_OFFLOAD_XSTATS_HW_S_INFO_UNSPEC,
-	IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST,		/* u8 */
-	IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED,		/* u8 */
-	__IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX,
-};
-#define IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX \
-	(__IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX - 1)
-
 /* XDP section */
 
 #define XDP_FLAGS_UPDATE_IF_NOEXIST	(1U << 0)
@@ -1965,16 +1281,4 @@ enum {
 
 #define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1)
 
-/* DSA section */
-
-enum {
-	IFLA_DSA_UNSPEC,
-	IFLA_DSA_CONDUIT,
-	/* Deprecated, use IFLA_DSA_CONDUIT instead */
-	IFLA_DSA_MASTER = IFLA_DSA_CONDUIT,
-	__IFLA_DSA_MAX,
-};
-
-#define IFLA_DSA_MAX	(__IFLA_DSA_MAX - 1)
-
 #endif /* _UAPI_LINUX_IF_LINK_H */

include/uapi/linux/if_xdp.h

@@ -25,25 +25,9 @@
  * application.
  */
 #define XDP_USE_NEED_WAKEUP (1 << 3)
-/* By setting this option, userspace application indicates that it can
- * handle multiple descriptors per packet thus enabling AF_XDP to split
- * multi-buffer XDP frames into multiple Rx descriptors. Without this set
- * such frames will be dropped.
- */
-#define XDP_USE_SG	(1 << 4)
 
 /* Flags for xsk_umem_config flags */
-#define XDP_UMEM_UNALIGNED_CHUNK_FLAG	(1 << 0)
+#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
-
-/* Force checksum calculation in software. Can be used for testing or
- * working around potential HW issues. This option causes performance
- * degradation and only works in XDP_COPY mode.
- */
-#define XDP_UMEM_TX_SW_CSUM		(1 << 1)
-
-/* Request to reserve tx_metadata_len bytes of per-chunk metadata.
- */
-#define XDP_UMEM_TX_METADATA_LEN	(1 << 2)
 
 struct sockaddr_xdp {
 	__u16 sxdp_family;
@@ -86,7 +70,6 @@ struct xdp_umem_reg {
 	__u32 chunk_size;
 	__u32 headroom;
 	__u32 flags;
-	__u32 tx_metadata_len;
 };
 
 struct xdp_statistics {
@@ -116,51 +99,6 @@ struct xdp_options {
 #define XSK_UNALIGNED_BUF_ADDR_MASK \
 	((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1)
 
-/* Request transmit timestamp. Upon completion, put it into tx_timestamp
- * field of struct xsk_tx_metadata.
- */
-#define XDP_TXMD_FLAGS_TIMESTAMP		(1 << 0)
-
-/* Request transmit checksum offload. Checksum start position and offset
- * are communicated via csum_start and csum_offset fields of struct
- * xsk_tx_metadata.
- */
-#define XDP_TXMD_FLAGS_CHECKSUM			(1 << 1)
-
-/* Request launch time hardware offload. The device will schedule the packet for
- * transmission at a pre-determined time called launch time. The value of
- * launch time is communicated via launch_time field of struct xsk_tx_metadata.
- */
-#define XDP_TXMD_FLAGS_LAUNCH_TIME		(1 << 2)
-
-/* AF_XDP offloads request. 'request' union member is consumed by the driver
- * when the packet is being transmitted. 'completion' union member is
- * filled by the driver when the transmit completion arrives.
- */
-struct xsk_tx_metadata {
-	__u64 flags;
-
-	union {
-		struct {
-			/* XDP_TXMD_FLAGS_CHECKSUM */
-
-			/* Offset from desc->addr where checksumming should start. */
-			__u16 csum_start;
-			/* Offset from csum_start where checksum should be stored. */
-			__u16 csum_offset;
-
-			/* XDP_TXMD_FLAGS_LAUNCH_TIME */
-			/* Launch time in nanosecond against the PTP HW Clock */
-			__u64 launch_time;
-		} request;
-
-		struct {
-			/* XDP_TXMD_FLAGS_TIMESTAMP */
-			__u64 tx_timestamp;
-		} completion;
-	};
-};
-
 /* Rx/Tx descriptor */
 struct xdp_desc {
 	__u64 addr;
@@ -170,14 +108,4 @@ struct xdp_desc {
 
 /* UMEM descriptor is __u64 */
 
-/* Flag indicating that the packet continues with the buffer pointed out by the
- * next frame in the ring. The end of the packet is signalled by setting this
- * bit to zero. For single buffer packets, every descriptor has 'options' set
- * to 0 and this maintains backward compatibility.
- */
-#define XDP_PKT_CONTD (1 << 0)
-
-/* TX packet carries valid metadata. */
-#define XDP_TX_METADATA (1 << 1)
-
 #endif /* _LINUX_IF_XDP_H */

include/uapi/linux/netdev.h

@@ -11,7 +11,7 @@
 
 /**
  * enum netdev_xdp_act
- * @NETDEV_XDP_ACT_BASIC: XDP features set supported by all drivers
+ * @NETDEV_XDP_ACT_BASIC: XDP feautues set supported by all drivers
  *   (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX)
  * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT
  * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements
@@ -34,197 +34,28 @@ enum netdev_xdp_act {
 	NETDEV_XDP_ACT_RX_SG = 32,
 	NETDEV_XDP_ACT_NDO_XMIT_SG = 64,
 
-	/* private: */
 	NETDEV_XDP_ACT_MASK = 127,
 };
 
-/**
- * enum netdev_xdp_rx_metadata
- * @NETDEV_XDP_RX_METADATA_TIMESTAMP: Device is capable of exposing receive HW
- *   timestamp via bpf_xdp_metadata_rx_timestamp().
- * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet
- *   hash via bpf_xdp_metadata_rx_hash().
- * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive
- *   packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag().
- */
-enum netdev_xdp_rx_metadata {
-	NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
-	NETDEV_XDP_RX_METADATA_HASH = 2,
-	NETDEV_XDP_RX_METADATA_VLAN_TAG = 4,
-};
-
-/**
- * enum netdev_xsk_flags
- * @NETDEV_XSK_FLAGS_TX_TIMESTAMP: HW timestamping egress packets is supported
- *   by the driver.
- * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the
- *   driver.
- * @NETDEV_XSK_FLAGS_TX_LAUNCH_TIME_FIFO: Launch time HW offload is supported
- *   by the driver.
- */
-enum netdev_xsk_flags {
-	NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1,
-	NETDEV_XSK_FLAGS_TX_CHECKSUM = 2,
-	NETDEV_XSK_FLAGS_TX_LAUNCH_TIME_FIFO = 4,
-};
-
-enum netdev_queue_type {
-	NETDEV_QUEUE_TYPE_RX,
-	NETDEV_QUEUE_TYPE_TX,
-};
-
-enum netdev_qstats_scope {
-	NETDEV_QSTATS_SCOPE_QUEUE = 1,
-};
-
 enum {
 	NETDEV_A_DEV_IFINDEX = 1,
 	NETDEV_A_DEV_PAD,
 	NETDEV_A_DEV_XDP_FEATURES,
-	NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
-	NETDEV_A_DEV_XDP_RX_METADATA_FEATURES,
-	NETDEV_A_DEV_XSK_FEATURES,
 
 	__NETDEV_A_DEV_MAX,
 	NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
 };
 
-enum {
-	__NETDEV_A_IO_URING_PROVIDER_INFO_MAX,
-	NETDEV_A_IO_URING_PROVIDER_INFO_MAX = (__NETDEV_A_IO_URING_PROVIDER_INFO_MAX - 1)
-};
-
-enum {
-	NETDEV_A_PAGE_POOL_ID = 1,
-	NETDEV_A_PAGE_POOL_IFINDEX,
-	NETDEV_A_PAGE_POOL_NAPI_ID,
-	NETDEV_A_PAGE_POOL_INFLIGHT,
-	NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
-	NETDEV_A_PAGE_POOL_DETACH_TIME,
-	NETDEV_A_PAGE_POOL_DMABUF,
-	NETDEV_A_PAGE_POOL_IO_URING,
-
-	__NETDEV_A_PAGE_POOL_MAX,
-	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
-};
-
-enum {
-	NETDEV_A_PAGE_POOL_STATS_INFO = 1,
-	NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST = 8,
-	NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW,
-	NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER,
-	NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY,
-	NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL,
-	NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE,
-	NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED,
-	NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL,
-	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING,
-	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL,
-	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT,
-
-	__NETDEV_A_PAGE_POOL_STATS_MAX,
-	NETDEV_A_PAGE_POOL_STATS_MAX = (__NETDEV_A_PAGE_POOL_STATS_MAX - 1)
-};
-
-enum {
-	NETDEV_A_NAPI_IFINDEX = 1,
-	NETDEV_A_NAPI_ID,
-	NETDEV_A_NAPI_IRQ,
-	NETDEV_A_NAPI_PID,
-	NETDEV_A_NAPI_DEFER_HARD_IRQS,
-	NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT,
-	NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT,
-
-	__NETDEV_A_NAPI_MAX,
-	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
-};
-
-enum {
-	__NETDEV_A_XSK_INFO_MAX,
-	NETDEV_A_XSK_INFO_MAX = (__NETDEV_A_XSK_INFO_MAX - 1)
-};
-
-enum {
-	NETDEV_A_QUEUE_ID = 1,
-	NETDEV_A_QUEUE_IFINDEX,
-	NETDEV_A_QUEUE_TYPE,
-	NETDEV_A_QUEUE_NAPI_ID,
-	NETDEV_A_QUEUE_DMABUF,
-	NETDEV_A_QUEUE_IO_URING,
-	NETDEV_A_QUEUE_XSK,
-
-	__NETDEV_A_QUEUE_MAX,
-	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
-};
-
-enum {
-	NETDEV_A_QSTATS_IFINDEX = 1,
-	NETDEV_A_QSTATS_QUEUE_TYPE,
-	NETDEV_A_QSTATS_QUEUE_ID,
-	NETDEV_A_QSTATS_SCOPE,
-	NETDEV_A_QSTATS_RX_PACKETS = 8,
-	NETDEV_A_QSTATS_RX_BYTES,
-	NETDEV_A_QSTATS_TX_PACKETS,
-	NETDEV_A_QSTATS_TX_BYTES,
-	NETDEV_A_QSTATS_RX_ALLOC_FAIL,
-	NETDEV_A_QSTATS_RX_HW_DROPS,
-	NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS,
-	NETDEV_A_QSTATS_RX_CSUM_COMPLETE,
-	NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY,
-	NETDEV_A_QSTATS_RX_CSUM_NONE,
-	NETDEV_A_QSTATS_RX_CSUM_BAD,
-	NETDEV_A_QSTATS_RX_HW_GRO_PACKETS,
-	NETDEV_A_QSTATS_RX_HW_GRO_BYTES,
-	NETDEV_A_QSTATS_RX_HW_GRO_WIRE_PACKETS,
-	NETDEV_A_QSTATS_RX_HW_GRO_WIRE_BYTES,
-	NETDEV_A_QSTATS_RX_HW_DROP_RATELIMITS,
-	NETDEV_A_QSTATS_TX_HW_DROPS,
-	NETDEV_A_QSTATS_TX_HW_DROP_ERRORS,
-	NETDEV_A_QSTATS_TX_CSUM_NONE,
-	NETDEV_A_QSTATS_TX_NEEDS_CSUM,
-	NETDEV_A_QSTATS_TX_HW_GSO_PACKETS,
-	NETDEV_A_QSTATS_TX_HW_GSO_BYTES,
-	NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS,
-	NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES,
-	NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS,
-	NETDEV_A_QSTATS_TX_STOP,
-	NETDEV_A_QSTATS_TX_WAKE,
-
-	__NETDEV_A_QSTATS_MAX,
-	NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1)
-};
-
-enum {
-	NETDEV_A_DMABUF_IFINDEX = 1,
-	NETDEV_A_DMABUF_QUEUES,
-	NETDEV_A_DMABUF_FD,
-	NETDEV_A_DMABUF_ID,
-
-	__NETDEV_A_DMABUF_MAX,
-	NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1)
-};
-
 enum {
 	NETDEV_CMD_DEV_GET = 1,
 	NETDEV_CMD_DEV_ADD_NTF,
 	NETDEV_CMD_DEV_DEL_NTF,
 	NETDEV_CMD_DEV_CHANGE_NTF,
-	NETDEV_CMD_PAGE_POOL_GET,
-	NETDEV_CMD_PAGE_POOL_ADD_NTF,
-	NETDEV_CMD_PAGE_POOL_DEL_NTF,
-	NETDEV_CMD_PAGE_POOL_CHANGE_NTF,
-	NETDEV_CMD_PAGE_POOL_STATS_GET,
-	NETDEV_CMD_QUEUE_GET,
-	NETDEV_CMD_NAPI_GET,
-	NETDEV_CMD_QSTATS_GET,
-	NETDEV_CMD_BIND_RX,
-	NETDEV_CMD_NAPI_SET,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
 };
 
 #define NETDEV_MCGRP_MGMT	"mgmt"
-#define NETDEV_MCGRP_PAGE_POOL	"page-pool"
 
 #endif /* _UAPI_LINUX_NETDEV_H */

include/uapi/linux/openat2.h

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

include/uapi/linux/perf_event.h

@@ -204,8 +204,6 @@ enum perf_branch_sample_type_shift {
 
 	PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT	= 18, /* save privilege mode */
 
-	PERF_SAMPLE_BRANCH_COUNTERS_SHIFT	= 19, /* save occurrences of events on a branch */
-
 	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
 };
 
@@ -237,8 +235,6 @@ enum perf_branch_sample_type {
 
 	PERF_SAMPLE_BRANCH_PRIV_SAVE	= 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT,
 
-	PERF_SAMPLE_BRANCH_COUNTERS	= 1U << PERF_SAMPLE_BRANCH_COUNTERS_SHIFT,
-
 	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
 
@@ -385,8 +381,6 @@ enum perf_event_read_format {
  *
  * @sample_max_stack: Max number of frame pointers in a callchain,
  *		      should be < /proc/sys/kernel/perf_event_max_stack
- *		      Max number of entries of branch stack
- *		      should be < hardware limit
  */
 struct perf_event_attr {
 
@@ -513,16 +507,7 @@ struct perf_event_attr {
 	__u16	sample_max_stack;
 	__u16	__reserved_2;
 	__u32	aux_sample_size;
-
+	__u32	__reserved_3;
-	union {
-		__u32	aux_action;
-		struct {
-			__u32	aux_start_paused :  1, /* start AUX area tracing paused */
-				aux_pause        :  1, /* on overflow, pause AUX area tracing */
-				aux_resume       :  1, /* on overflow, resume AUX area tracing */
-				__reserved_3     : 29;
-		};
-	};
 
 	/*
 	 * User provided data if sigtrap=1, passed back to user via
@@ -997,12 +982,6 @@ enum perf_event_type {
 	 *	{ u64                   nr;
 	 *	  { u64	hw_idx; } && PERF_SAMPLE_BRANCH_HW_INDEX
 	 *        { u64 from, to, flags } lbr[nr];
-	 *        #
-	 *        # The format of the counters is decided by the
-	 *        # "branch_counter_nr" and "branch_counter_width",
-	 *        # which are defined in the ABI.
-	 *        #
-	 *        { u64 counters; } cntr[nr] && PERF_SAMPLE_BRANCH_COUNTERS
 	 *      } && PERF_SAMPLE_BRANCH_STACK
 	 *
 	 * 	{ u64			abi; # enum perf_sample_regs_abi
@@ -1360,14 +1339,11 @@ union perf_mem_data_src {
 #define PERF_MEM_LVLNUM_L2	0x02 /* L2 */
 #define PERF_MEM_LVLNUM_L3	0x03 /* L3 */
 #define PERF_MEM_LVLNUM_L4	0x04 /* L4 */
-#define PERF_MEM_LVLNUM_L2_MHB	0x05 /* L2 Miss Handling Buffer */
+/* 5-0x8 available */
-#define PERF_MEM_LVLNUM_MSC	0x06 /* Memory-side Cache */
-/* 0x7 available */
-#define PERF_MEM_LVLNUM_UNC	0x08 /* Uncached */
 #define PERF_MEM_LVLNUM_CXL	0x09 /* CXL */
 #define PERF_MEM_LVLNUM_IO	0x0a /* I/O */
 #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */
-#define PERF_MEM_LVLNUM_LFB	0x0c /* LFB / L1 Miss Handling Buffer */
+#define PERF_MEM_LVLNUM_LFB	0x0c /* LFB */
 #define PERF_MEM_LVLNUM_RAM	0x0d /* RAM */
 #define PERF_MEM_LVLNUM_PMEM	0x0e /* PMEM */
 #define PERF_MEM_LVLNUM_NA	0x0f /* N/A */
@@ -1450,9 +1426,6 @@ struct perf_branch_entry {
 		reserved:31;
 };
 
-/* Size of used info bits in struct perf_branch_entry */
-#define PERF_BRANCH_ENTRY_INFO_BITS_MAX		33
-
 union perf_sample_weight {
 	__u64		full;
 #if defined(__LITTLE_ENDIAN_BITFIELD)

include/uapi/linux/pkt_cls.h

@@ -204,6 +204,37 @@ struct tc_u32_pcnt {
 
 #define TC_U32_MAXDEPTH 8
 
+
+/* RSVP filter */
+
+enum {
+	TCA_RSVP_UNSPEC,
+	TCA_RSVP_CLASSID,
+	TCA_RSVP_DST,
+	TCA_RSVP_SRC,
+	TCA_RSVP_PINFO,
+	TCA_RSVP_POLICE,
+	TCA_RSVP_ACT,
+	__TCA_RSVP_MAX
+};
+
+#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 )
+
+struct tc_rsvp_gpi {
+	__u32	key;
+	__u32	mask;
+	int	offset;
+};
+
+struct tc_rsvp_pinfo {
+	struct tc_rsvp_gpi dpi;
+	struct tc_rsvp_gpi spi;
+	__u8	protocol;
+	__u8	tunnelid;
+	__u8	tunnelhdr;
+	__u8	pad;
+};
+
 /* ROUTE filter */
 
 enum {
@@ -234,6 +265,22 @@ enum {
 
 #define TCA_FW_MAX (__TCA_FW_MAX - 1)
 
+/* TC index filter */
+
+enum {
+	TCA_TCINDEX_UNSPEC,
+	TCA_TCINDEX_HASH,
+	TCA_TCINDEX_MASK,
+	TCA_TCINDEX_SHIFT,
+	TCA_TCINDEX_FALL_THROUGH,
+	TCA_TCINDEX_CLASSID,
+	TCA_TCINDEX_POLICE,
+	TCA_TCINDEX_ACT,
+	__TCA_TCINDEX_MAX
+};
+
+#define TCA_TCINDEX_MAX     (__TCA_TCINDEX_MAX - 1)
+
 /* Flow filter */
 
 enum {

include/uapi/linux/pkt_sched.h

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

scripts/build-fuzzers.sh

@@ -41,7 +41,7 @@ fi
 # due to https://bugs.gentoo.org/794601) so let's just point the script to
 # commits referring to versions of libelf that actually can be built
 rm -rf elfutils
-git clone https://sourceware.org/git/elfutils.git
+git clone git://sourceware.org/git/elfutils.git
 (
 cd elfutils
 git checkout 67a187d4c1790058fc7fd218317851cb68bb087c

scripts/mailmap-update.sh

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

scripts/sync-kernel.sh

@@ -295,22 +295,6 @@ Latest changes to BPF helper definitions.
 " -- src/bpf_helper_defs.h
 fi
 
-echo "Regenerating .mailmap..."
-cd_to "${LINUX_REPO}"
-git checkout "${TIP_SYM_REF}"
-cd_to "${LIBBPF_REPO}"
-"${LIBBPF_REPO}"/scripts/mailmap-update.sh "${LIBBPF_REPO}" "${LINUX_REPO}"
-# if anything changed, commit it
-mailmap_changes=$(git status --porcelain .mailmap | wc -l)
-if ((${mailmap_changes} == 1)); then
-	git add .mailmap
-	git commit -s -m "sync: update .mailmap
-
-Update .mailmap based on libbpf's list of contributors and on the latest
-.mailmap version in the upstream repository.
-" -- .mailmap
-fi
-
 # Use generated cover-letter as a template for "sync commit" with
 # baseline and checkpoint commits from kernel repo (and leave summary
 # from cover letter intact, of course)

src/Makefile

@@ -9,7 +9,7 @@ else
 endif
 
 LIBBPF_MAJOR_VERSION := 1
-LIBBPF_MINOR_VERSION := 6
+LIBBPF_MINOR_VERSION := 3
 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
@@ -26,7 +26,6 @@ endef
 
 $(call allow-override,CC,$(CROSS_COMPILE)cc)
 $(call allow-override,LD,$(CROSS_COMPILE)ld)
-PKG_CONFIG ?= pkg-config
 
 TOPDIR = ..
 
@@ -36,18 +35,13 @@ ALL_CFLAGS := $(INCLUDES)
 SHARED_CFLAGS += -fPIC -fvisibility=hidden -DSHARED
 
 CFLAGS ?= -g -O2 -Werror -Wall -std=gnu89
-ALL_CFLAGS += $(CFLAGS) 						\
+ALL_CFLAGS += $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 $(EXTRA_CFLAGS)
-	      -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64		\
-	      -Wno-unknown-warning-option -Wno-format-overflow		\
-	      $(EXTRA_CFLAGS)
 ALL_LDFLAGS += $(LDFLAGS) $(EXTRA_LDFLAGS)
 
-ifeq ($(shell command -v $(PKG_CONFIG) 2> /dev/null),)
-NO_PKG_CONFIG := 1
-endif
 ifdef NO_PKG_CONFIG
 	ALL_LDFLAGS += -lelf -lz
 else
+	PKG_CONFIG ?= pkg-config
 	ALL_CFLAGS += $(shell $(PKG_CONFIG) --cflags libelf zlib)
 	ALL_LDFLAGS += $(shell $(PKG_CONFIG) --libs libelf zlib)
 endif
@@ -58,7 +52,7 @@ 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 \
 	btf_dump.o hashmap.o ringbuf.o strset.o linker.o gen_loader.o \
-	relo_core.o usdt.o zip.o elf.o features.o btf_iter.o btf_relocate.o
+	relo_core.o usdt.o zip.o
 SHARED_OBJS := $(addprefix $(SHARED_OBJDIR)/,$(OBJS))
 STATIC_OBJS := $(addprefix $(STATIC_OBJDIR)/,$(OBJS))
 
@@ -122,13 +116,13 @@ $(OBJDIR)/libbpf.so.$(LIBBPF_VERSION): $(SHARED_OBJS)
 		  -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \
 		  $^ $(ALL_LDFLAGS) -o $@
 
-$(OBJDIR)/libbpf.pc: force | $(OBJDIR)
+$(OBJDIR)/libbpf.pc: force
 	$(Q)sed -e "s|@PREFIX@|$(PREFIX)|" \
 		-e "s|@LIBDIR@|$(LIBDIR_PC)|" \
 		-e "s|@VERSION@|$(LIBBPF_VERSION)|" \
 		< libbpf.pc.template > $@
 
-$(OBJDIR) $(STATIC_OBJDIR) $(SHARED_OBJDIR):
+$(STATIC_OBJDIR) $(SHARED_OBJDIR):
 	$(call msg,MKDIR,$@)
 	$(Q)mkdir -p $@
 

src/bpf.c

@@ -103,9 +103,9 @@ int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts)
  *   [0] https://lore.kernel.org/bpf/20201201215900.3569844-1-guro@fb.com/
  *   [1] d05512618056 ("bpf: Add bpf_ktime_get_coarse_ns helper")
  */
-int probe_memcg_account(int token_fd)
+int probe_memcg_account(void)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, prog_token_fd);
+	const size_t attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd);
 	struct bpf_insn insns[] = {
 		BPF_EMIT_CALL(BPF_FUNC_ktime_get_coarse_ns),
 		BPF_EXIT_INSN(),
@@ -120,9 +120,6 @@ int probe_memcg_account(int token_fd)
 	attr.insns = ptr_to_u64(insns);
 	attr.insn_cnt = insn_cnt;
 	attr.license = ptr_to_u64("GPL");
-	attr.prog_token_fd = token_fd;
-	if (token_fd)
-		attr.prog_flags |= BPF_F_TOKEN_FD;
 
 	prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, attr_sz);
 	if (prog_fd >= 0) {
@@ -149,7 +146,7 @@ int bump_rlimit_memlock(void)
 	struct rlimit rlim;
 
 	/* if kernel supports memcg-based accounting, skip bumping RLIMIT_MEMLOCK */
-	if (memlock_bumped || feat_supported(NULL, FEAT_MEMCG_ACCOUNT))
+	if (memlock_bumped || kernel_supports(NULL, FEAT_MEMCG_ACCOUNT))
 		return 0;
 
 	memlock_bumped = true;
@@ -172,7 +169,7 @@ int bpf_map_create(enum bpf_map_type map_type,
 		   __u32 max_entries,
 		   const struct bpf_map_create_opts *opts)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, map_token_fd);
+	const size_t attr_sz = offsetofend(union bpf_attr, map_extra);
 	union bpf_attr attr;
 	int fd;
 
@@ -184,7 +181,7 @@ int bpf_map_create(enum bpf_map_type map_type,
 		return libbpf_err(-EINVAL);
 
 	attr.map_type = map_type;
-	if (map_name && feat_supported(NULL, FEAT_PROG_NAME))
+	if (map_name && kernel_supports(NULL, FEAT_PROG_NAME))
 		libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name));
 	attr.key_size = key_size;
 	attr.value_size = value_size;
@@ -194,7 +191,6 @@ int bpf_map_create(enum bpf_map_type map_type,
 	attr.btf_key_type_id = OPTS_GET(opts, btf_key_type_id, 0);
 	attr.btf_value_type_id = OPTS_GET(opts, btf_value_type_id, 0);
 	attr.btf_vmlinux_value_type_id = OPTS_GET(opts, btf_vmlinux_value_type_id, 0);
-	attr.value_type_btf_obj_fd = OPTS_GET(opts, value_type_btf_obj_fd, 0);
 
 	attr.inner_map_fd = OPTS_GET(opts, inner_map_fd, 0);
 	attr.map_flags = OPTS_GET(opts, map_flags, 0);
@@ -202,8 +198,6 @@ int bpf_map_create(enum bpf_map_type map_type,
 	attr.numa_node = OPTS_GET(opts, numa_node, 0);
 	attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0);
 
-	attr.map_token_fd = OPTS_GET(opts, token_fd, 0);
-
 	fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
@@ -238,7 +232,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 		  const struct bpf_insn *insns, size_t insn_cnt,
 		  struct bpf_prog_load_opts *opts)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, fd_array_cnt);
+	const size_t attr_sz = offsetofend(union bpf_attr, log_true_size);
 	void *finfo = NULL, *linfo = NULL;
 	const char *func_info, *line_info;
 	__u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd;
@@ -267,9 +261,8 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 	attr.prog_flags = OPTS_GET(opts, prog_flags, 0);
 	attr.prog_ifindex = OPTS_GET(opts, prog_ifindex, 0);
 	attr.kern_version = OPTS_GET(opts, kern_version, 0);
-	attr.prog_token_fd = OPTS_GET(opts, token_fd, 0);
 
-	if (prog_name && feat_supported(NULL, FEAT_PROG_NAME))
+	if (prog_name && kernel_supports(NULL, FEAT_PROG_NAME))
 		libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
 	attr.license = ptr_to_u64(license);
 
@@ -311,7 +304,6 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 	attr.line_info_cnt = OPTS_GET(opts, line_info_cnt, 0);
 
 	attr.fd_array = ptr_to_u64(OPTS_GET(opts, fd_array, NULL));
-	attr.fd_array_cnt = OPTS_GET(opts, fd_array_cnt, 0);
 
 	if (log_level) {
 		attr.log_buf = ptr_to_u64(log_buf);
@@ -637,89 +629,55 @@ int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
 	return bpf_prog_attach_opts(prog_fd, target_fd, type, &opts);
 }
 
-int bpf_prog_attach_opts(int prog_fd, int target, enum bpf_attach_type type,
+int bpf_prog_attach_opts(int prog_fd, int target_fd,
-			 const struct bpf_prog_attach_opts *opts)
+			  enum bpf_attach_type type,
+			  const struct bpf_prog_attach_opts *opts)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, expected_revision);
+	const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd);
-	__u32 relative_id, flags;
-	int ret, relative_fd;
 	union bpf_attr attr;
+	int ret;
 
 	if (!OPTS_VALID(opts, bpf_prog_attach_opts))
 		return libbpf_err(-EINVAL);
 
-	relative_id = OPTS_GET(opts, relative_id, 0);
-	relative_fd = OPTS_GET(opts, relative_fd, 0);
-	flags = OPTS_GET(opts, flags, 0);
-
-	/* validate we don't have unexpected combinations of non-zero fields */
-	if (relative_fd && relative_id)
-		return libbpf_err(-EINVAL);
-
 	memset(&attr, 0, attr_sz);
-	attr.target_fd		= target;
+	attr.target_fd	   = target_fd;
-	attr.attach_bpf_fd	= prog_fd;
+	attr.attach_bpf_fd = prog_fd;
-	attr.attach_type	= type;
+	attr.attach_type   = type;
-	attr.replace_bpf_fd	= OPTS_GET(opts, replace_fd, 0);
+	attr.attach_flags  = OPTS_GET(opts, flags, 0);
-	attr.expected_revision	= OPTS_GET(opts, expected_revision, 0);
+	attr.replace_bpf_fd = OPTS_GET(opts, replace_prog_fd, 0);
-
-	if (relative_id) {
-		attr.attach_flags = flags | BPF_F_ID;
-		attr.relative_id  = relative_id;
-	} else {
-		attr.attach_flags = flags;
-		attr.relative_fd  = relative_fd;
-	}
 
 	ret = sys_bpf(BPF_PROG_ATTACH, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
-int bpf_prog_detach_opts(int prog_fd, int target, enum bpf_attach_type type,
+int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
-			 const struct bpf_prog_detach_opts *opts)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, expected_revision);
+	const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd);
-	__u32 relative_id, flags;
-	int ret, relative_fd;
 	union bpf_attr attr;
-
+	int ret;
-	if (!OPTS_VALID(opts, bpf_prog_detach_opts))
-		return libbpf_err(-EINVAL);
-
-	relative_id = OPTS_GET(opts, relative_id, 0);
-	relative_fd = OPTS_GET(opts, relative_fd, 0);
-	flags = OPTS_GET(opts, flags, 0);
-
-	/* validate we don't have unexpected combinations of non-zero fields */
-	if (relative_fd && relative_id)
-		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, attr_sz);
-	attr.target_fd		= target;
+	attr.target_fd	 = target_fd;
-	attr.attach_bpf_fd	= prog_fd;
+	attr.attach_type = type;
-	attr.attach_type	= type;
-	attr.expected_revision	= OPTS_GET(opts, expected_revision, 0);
-
-	if (relative_id) {
-		attr.attach_flags = flags | BPF_F_ID;
-		attr.relative_id  = relative_id;
-	} else {
-		attr.attach_flags = flags;
-		attr.relative_fd  = relative_fd;
-	}
 
 	ret = sys_bpf(BPF_PROG_DETACH, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
-int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
-{
-	return bpf_prog_detach_opts(0, target_fd, type, NULL);
-}
-
 int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type)
 {
-	return bpf_prog_detach_opts(prog_fd, target_fd, type, NULL);
+	const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd);
+	union bpf_attr attr;
+	int ret;
+
+	memset(&attr, 0, attr_sz);
+	attr.target_fd	 = target_fd;
+	attr.attach_bpf_fd = prog_fd;
+	attr.attach_type = type;
+
+	ret = sys_bpf(BPF_PROG_DETACH, &attr, attr_sz);
+	return libbpf_err_errno(ret);
 }
 
 int bpf_link_create(int prog_fd, int target_fd,
@@ -727,9 +685,9 @@ int bpf_link_create(int prog_fd, int target_fd,
 		    const struct bpf_link_create_opts *opts)
 {
 	const size_t attr_sz = offsetofend(union bpf_attr, link_create);
-	__u32 target_btf_id, iter_info_len, relative_id;
+	__u32 target_btf_id, iter_info_len;
-	int fd, err, relative_fd;
 	union bpf_attr attr;
+	int fd, err;
 
 	if (!OPTS_VALID(opts, bpf_link_create_opts))
 		return libbpf_err(-EINVAL);
@@ -767,7 +725,6 @@ int bpf_link_create(int prog_fd, int target_fd,
 			return libbpf_err(-EINVAL);
 		break;
 	case BPF_TRACE_KPROBE_MULTI:
-	case BPF_TRACE_KPROBE_SESSION:
 		attr.link_create.kprobe_multi.flags = OPTS_GET(opts, kprobe_multi.flags, 0);
 		attr.link_create.kprobe_multi.cnt = OPTS_GET(opts, kprobe_multi.cnt, 0);
 		attr.link_create.kprobe_multi.syms = ptr_to_u64(OPTS_GET(opts, kprobe_multi.syms, 0));
@@ -776,19 +733,6 @@ int bpf_link_create(int prog_fd, int target_fd,
 		if (!OPTS_ZEROED(opts, kprobe_multi))
 			return libbpf_err(-EINVAL);
 		break;
-	case BPF_TRACE_UPROBE_MULTI:
-	case BPF_TRACE_UPROBE_SESSION:
-		attr.link_create.uprobe_multi.flags = OPTS_GET(opts, uprobe_multi.flags, 0);
-		attr.link_create.uprobe_multi.cnt = OPTS_GET(opts, uprobe_multi.cnt, 0);
-		attr.link_create.uprobe_multi.path = ptr_to_u64(OPTS_GET(opts, uprobe_multi.path, 0));
-		attr.link_create.uprobe_multi.offsets = ptr_to_u64(OPTS_GET(opts, uprobe_multi.offsets, 0));
-		attr.link_create.uprobe_multi.ref_ctr_offsets = ptr_to_u64(OPTS_GET(opts, uprobe_multi.ref_ctr_offsets, 0));
-		attr.link_create.uprobe_multi.cookies = ptr_to_u64(OPTS_GET(opts, uprobe_multi.cookies, 0));
-		attr.link_create.uprobe_multi.pid = OPTS_GET(opts, uprobe_multi.pid, 0);
-		if (!OPTS_ZEROED(opts, uprobe_multi))
-			return libbpf_err(-EINVAL);
-		break;
-	case BPF_TRACE_RAW_TP:
 	case BPF_TRACE_FENTRY:
 	case BPF_TRACE_FEXIT:
 	case BPF_MODIFY_RETURN:
@@ -805,38 +749,6 @@ int bpf_link_create(int prog_fd, int target_fd,
 		if (!OPTS_ZEROED(opts, netfilter))
 			return libbpf_err(-EINVAL);
 		break;
-	case BPF_TCX_INGRESS:
-	case BPF_TCX_EGRESS:
-		relative_fd = OPTS_GET(opts, tcx.relative_fd, 0);
-		relative_id = OPTS_GET(opts, tcx.relative_id, 0);
-		if (relative_fd && relative_id)
-			return libbpf_err(-EINVAL);
-		if (relative_id) {
-			attr.link_create.tcx.relative_id = relative_id;
-			attr.link_create.flags |= BPF_F_ID;
-		} else {
-			attr.link_create.tcx.relative_fd = relative_fd;
-		}
-		attr.link_create.tcx.expected_revision = OPTS_GET(opts, tcx.expected_revision, 0);
-		if (!OPTS_ZEROED(opts, tcx))
-			return libbpf_err(-EINVAL);
-		break;
-	case BPF_NETKIT_PRIMARY:
-	case BPF_NETKIT_PEER:
-		relative_fd = OPTS_GET(opts, netkit.relative_fd, 0);
-		relative_id = OPTS_GET(opts, netkit.relative_id, 0);
-		if (relative_fd && relative_id)
-			return libbpf_err(-EINVAL);
-		if (relative_id) {
-			attr.link_create.netkit.relative_id = relative_id;
-			attr.link_create.flags |= BPF_F_ID;
-		} else {
-			attr.link_create.netkit.relative_fd = relative_fd;
-		}
-		attr.link_create.netkit.expected_revision = OPTS_GET(opts, netkit.expected_revision, 0);
-		if (!OPTS_ZEROED(opts, netkit))
-			return libbpf_err(-EINVAL);
-		break;
 	default:
 		if (!OPTS_ZEROED(opts, flags))
 			return libbpf_err(-EINVAL);
@@ -929,7 +841,8 @@ int bpf_iter_create(int link_fd)
 	return libbpf_err_errno(fd);
 }
 
-int bpf_prog_query_opts(int target, enum bpf_attach_type type,
+int bpf_prog_query_opts(int target_fd,
+			enum bpf_attach_type type,
 			struct bpf_prog_query_opts *opts)
 {
 	const size_t attr_sz = offsetofend(union bpf_attr, query);
@@ -940,20 +853,18 @@ int bpf_prog_query_opts(int target, enum bpf_attach_type type,
 		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, attr_sz);
-	attr.query.target_fd		= target;
+
-	attr.query.attach_type		= type;
+	attr.query.target_fd	= target_fd;
-	attr.query.query_flags		= OPTS_GET(opts, query_flags, 0);
+	attr.query.attach_type	= type;
-	attr.query.count		= OPTS_GET(opts, count, 0);
+	attr.query.query_flags	= OPTS_GET(opts, query_flags, 0);
-	attr.query.prog_ids		= ptr_to_u64(OPTS_GET(opts, prog_ids, NULL));
+	attr.query.prog_cnt	= OPTS_GET(opts, prog_cnt, 0);
-	attr.query.link_ids		= ptr_to_u64(OPTS_GET(opts, link_ids, NULL));
+	attr.query.prog_ids	= ptr_to_u64(OPTS_GET(opts, prog_ids, NULL));
-	attr.query.prog_attach_flags	= ptr_to_u64(OPTS_GET(opts, prog_attach_flags, NULL));
+	attr.query.prog_attach_flags = ptr_to_u64(OPTS_GET(opts, prog_attach_flags, NULL));
-	attr.query.link_attach_flags	= ptr_to_u64(OPTS_GET(opts, link_attach_flags, NULL));
 
 	ret = sys_bpf(BPF_PROG_QUERY, &attr, attr_sz);
 
 	OPTS_SET(opts, attach_flags, attr.query.attach_flags);
-	OPTS_SET(opts, revision, attr.query.revision);
+	OPTS_SET(opts, prog_cnt, attr.query.prog_cnt);
-	OPTS_SET(opts, count, attr.query.count);
 
 	return libbpf_err_errno(ret);
 }
@@ -1097,7 +1008,7 @@ int bpf_map_get_fd_by_id(__u32 id)
 int bpf_btf_get_fd_by_id_opts(__u32 id,
 			      const struct bpf_get_fd_by_id_opts *opts)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, fd_by_id_token_fd);
+	const size_t attr_sz = offsetofend(union bpf_attr, open_flags);
 	union bpf_attr attr;
 	int fd;
 
@@ -1107,7 +1018,6 @@ int bpf_btf_get_fd_by_id_opts(__u32 id,
 	memset(&attr, 0, attr_sz);
 	attr.btf_id = id;
 	attr.open_flags = OPTS_GET(opts, open_flags, 0);
-	attr.fd_by_id_token_fd = OPTS_GET(opts, token_fd, 0);
 
 	fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, attr_sz);
 	return libbpf_err_errno(fd);
@@ -1178,34 +1088,23 @@ int bpf_link_get_info_by_fd(int link_fd, struct bpf_link_info *info, __u32 *info
 	return bpf_obj_get_info_by_fd(link_fd, info, info_len);
 }
 
-int bpf_raw_tracepoint_open_opts(int prog_fd, struct bpf_raw_tp_opts *opts)
+int bpf_raw_tracepoint_open(const char *name, int prog_fd)
 {
 	const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint);
 	union bpf_attr attr;
 	int fd;
 
-	if (!OPTS_VALID(opts, bpf_raw_tp_opts))
-		return libbpf_err(-EINVAL);
-
 	memset(&attr, 0, attr_sz);
+	attr.raw_tracepoint.name = ptr_to_u64(name);
 	attr.raw_tracepoint.prog_fd = prog_fd;
-	attr.raw_tracepoint.name = ptr_to_u64(OPTS_GET(opts, tp_name, NULL));
-	attr.raw_tracepoint.cookie = OPTS_GET(opts, cookie, 0);
 
 	fd = sys_bpf_fd(BPF_RAW_TRACEPOINT_OPEN, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
-int bpf_raw_tracepoint_open(const char *name, int prog_fd)
-{
-	LIBBPF_OPTS(bpf_raw_tp_opts, opts, .tp_name = name);
-
-	return bpf_raw_tracepoint_open_opts(prog_fd, &opts);
-}
-
 int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, btf_token_fd);
+	const size_t attr_sz = offsetofend(union bpf_attr, btf_log_true_size);
 	union bpf_attr attr;
 	char *log_buf;
 	size_t log_size;
@@ -1230,10 +1129,6 @@ int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts
 
 	attr.btf = ptr_to_u64(btf_data);
 	attr.btf_size = btf_size;
-
-	attr.btf_flags = OPTS_GET(opts, btf_flags, 0);
-	attr.btf_token_fd = OPTS_GET(opts, token_fd, 0);
-
 	/* log_level == 0 and log_buf != NULL means "try loading without
 	 * log_buf, but retry with log_buf and log_level=1 on error", which is
 	 * consistent across low-level and high-level BTF and program loading
@@ -1314,20 +1209,3 @@ int bpf_prog_bind_map(int prog_fd, int map_fd,
 	ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
-
-int bpf_token_create(int bpffs_fd, struct bpf_token_create_opts *opts)
-{
-	const size_t attr_sz = offsetofend(union bpf_attr, token_create);
-	union bpf_attr attr;
-	int fd;
-
-	if (!OPTS_VALID(opts, bpf_token_create_opts))
-		return libbpf_err(-EINVAL);
-
-	memset(&attr, 0, attr_sz);
-	attr.token_create.bpffs_fd = bpffs_fd;
-	attr.token_create.flags = OPTS_GET(opts, flags, 0);
-
-	fd = sys_bpf_fd(BPF_TOKEN_CREATE, &attr, attr_sz);
-	return libbpf_err_errno(fd);
-}

src/bpf.h

@@ -35,7 +35,7 @@
 extern "C" {
 #endif
 
-LIBBPF_API int libbpf_set_memlock_rlim(size_t memlock_bytes);
+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 */
@@ -51,12 +51,8 @@ struct bpf_map_create_opts {
 
 	__u32 numa_node;
 	__u32 map_ifindex;
-	__s32 value_type_btf_obj_fd;
-
-	__u32 token_fd;
-	size_t :0;
 };
-#define bpf_map_create_opts__last_field token_fd
+#define bpf_map_create_opts__last_field map_ifindex
 
 LIBBPF_API int bpf_map_create(enum bpf_map_type map_type,
 			      const char *map_name,
@@ -100,19 +96,15 @@ struct bpf_prog_load_opts {
 	__u32 log_level;
 	__u32 log_size;
 	char *log_buf;
-	/* output: actual total log contents size (including terminating zero).
+	/* output: actual total log contents size (including termintaing zero).
 	 * It could be both larger than original log_size (if log was
 	 * truncated), or smaller (if log buffer wasn't filled completely).
 	 * If kernel doesn't support this feature, log_size is left unchanged.
 	 */
 	__u32 log_true_size;
-	__u32 token_fd;
-
-	/* if set, provides the length of fd_array */
-	__u32 fd_array_cnt;
 	size_t :0;
 };
-#define bpf_prog_load_opts__last_field fd_array_cnt
+#define bpf_prog_load_opts__last_field log_true_size
 
 LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type,
 			     const char *prog_name, const char *license,
@@ -132,18 +124,15 @@ struct bpf_btf_load_opts {
 	char *log_buf;
 	__u32 log_level;
 	__u32 log_size;
-	/* output: actual total log contents size (including terminating zero).
+	/* output: actual total log contents size (including termintaing zero).
 	 * It could be both larger than original log_size (if log was
 	 * truncated), or smaller (if log buffer wasn't filled completely).
 	 * If kernel doesn't support this feature, log_size is left unchanged.
 	 */
 	__u32 log_true_size;
-
-	__u32 btf_flags;
-	__u32 token_fd;
 	size_t :0;
 };
-#define bpf_btf_load_opts__last_field token_fd
+#define bpf_btf_load_opts__last_field log_true_size
 
 LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size,
 			    struct bpf_btf_load_opts *opts);
@@ -193,14 +182,10 @@ LIBBPF_API int bpf_map_delete_batch(int fd, const void *keys,
 /**
  * @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
+ * The parameter *in_batch* is the address of the first element in the batch to read.
- * read. *out_batch* is an output parameter that should be passed as *in_batch*
+ * *out_batch* is an output parameter that should be passed as *in_batch* to subsequent
- * to subsequent calls to **bpf_map_lookup_batch()**. NULL can be passed for
+ * calls to **bpf_map_lookup_batch()**. NULL can be passed for *in_batch* to indicate
- * *in_batch* to indicate that the batched lookup starts from the beginning of
+ * that the batched lookup starts from the beginning of the map.
- * the map. Both *in_batch* and *out_batch* must point to memory large enough to
- * hold a single key, except for maps of type **BPF_MAP_TYPE_{HASH, PERCPU_HASH,
- * LRU_HASH, LRU_PERCPU_HASH}**, for which the memory size must be at
- * least 4 bytes wide regardless of key size.
  *
  * The *keys* and *values* are output parameters which must point to memory large enough to
  * hold *count* items based on the key and value size of the map *map_fd*. The *keys*
@@ -233,10 +218,7 @@ LIBBPF_API int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch,
  *
  * @param fd BPF map file descriptor
  * @param in_batch address of the first element in batch to read, can pass NULL to
- * get address of the first element in *out_batch*. If not NULL, must be large
+ * get address of the first element in *out_batch*
- * enough to hold a key. For **BPF_MAP_TYPE_{HASH, PERCPU_HASH, LRU_HASH,
- * LRU_PERCPU_HASH}**, the memory size must be at least 4 bytes wide regardless
- * of key size.
  * @param out_batch output parameter that should be passed to next call as *in_batch*
  * @param keys pointer to an array of *count* keys
  * @param values pointer to an array large enough for *count* values
@@ -330,68 +312,22 @@ 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 */
+	unsigned int flags;
+	int replace_prog_fd;
+};
+#define bpf_prog_attach_opts__last_field replace_prog_fd
+
 LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd,
 			       enum bpf_attach_type type, unsigned int flags);
+LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int attachable_fd,
+				     enum bpf_attach_type type,
+				     const struct bpf_prog_attach_opts *opts);
 LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
 LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd,
 				enum bpf_attach_type type);
 
-struct bpf_prog_attach_opts {
-	size_t sz; /* size of this struct for forward/backward compatibility */
-	__u32 flags;
-	union {
-		int replace_prog_fd;
-		int replace_fd;
-	};
-	int relative_fd;
-	__u32 relative_id;
-	__u64 expected_revision;
-	size_t :0;
-};
-#define bpf_prog_attach_opts__last_field expected_revision
-
-struct bpf_prog_detach_opts {
-	size_t sz; /* size of this struct for forward/backward compatibility */
-	__u32 flags;
-	int relative_fd;
-	__u32 relative_id;
-	__u64 expected_revision;
-	size_t :0;
-};
-#define bpf_prog_detach_opts__last_field expected_revision
-
-/**
- * @brief **bpf_prog_attach_opts()** attaches the BPF program corresponding to
- * *prog_fd* to a *target* which can represent a file descriptor or netdevice
- * ifindex.
- *
- * @param prog_fd BPF program file descriptor
- * @param target attach location file descriptor or ifindex
- * @param type attach type for the BPF program
- * @param opts options for configuring the attachment
- * @return 0, on success; negative error code, otherwise (errno is also set to
- * the error code)
- */
-LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int target,
-				    enum bpf_attach_type type,
-				    const struct bpf_prog_attach_opts *opts);
-
-/**
- * @brief **bpf_prog_detach_opts()** detaches the BPF program corresponding to
- * *prog_fd* from a *target* which can represent a file descriptor or netdevice
- * ifindex.
- *
- * @param prog_fd BPF program file descriptor
- * @param target detach location file descriptor or ifindex
- * @param type detach type for the BPF program
- * @param opts options for configuring the detachment
- * @return 0, on success; negative error code, otherwise (errno is also set to
- * the error code)
- */
-LIBBPF_API int bpf_prog_detach_opts(int prog_fd, int target,
-				    enum bpf_attach_type type,
-				    const struct bpf_prog_detach_opts *opts);
-
 union bpf_iter_link_info; /* defined in up-to-date linux/bpf.h */
 struct bpf_link_create_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */
@@ -410,15 +346,6 @@ struct bpf_link_create_opts {
 			const unsigned long *addrs;
 			const __u64 *cookies;
 		} kprobe_multi;
-		struct {
-			__u32 flags;
-			__u32 cnt;
-			const char *path;
-			const unsigned long *offsets;
-			const unsigned long *ref_ctr_offsets;
-			const __u64 *cookies;
-			__u32 pid;
-		} uprobe_multi;
 		struct {
 			__u64 cookie;
 		} tracing;
@@ -428,20 +355,10 @@ struct bpf_link_create_opts {
 			__s32 priority;
 			__u32 flags;
 		} netfilter;
-		struct {
-			__u32 relative_fd;
-			__u32 relative_id;
-			__u64 expected_revision;
-		} tcx;
-		struct {
-			__u32 relative_fd;
-			__u32 relative_id;
-			__u64 expected_revision;
-		} netkit;
 	};
 	size_t :0;
 };
-#define bpf_link_create_opts__last_field uprobe_multi.pid
+#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,
@@ -487,10 +404,9 @@ LIBBPF_API int bpf_link_get_next_id(__u32 start_id, __u32 *next_id);
 struct bpf_get_fd_by_id_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */
 	__u32 open_flags; /* permissions requested for the operation on fd */
-	__u32 token_fd;
 	size_t :0;
 };
-#define bpf_get_fd_by_id_opts__last_field token_fd
+#define bpf_get_fd_by_id_opts__last_field open_flags
 
 LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id);
 LIBBPF_API int bpf_prog_get_fd_by_id_opts(__u32 id,
@@ -511,10 +427,7 @@ LIBBPF_API int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len);
  * program corresponding to *prog_fd*.
  *
  * Populates up to *info_len* bytes of *info* and updates *info_len* with the
- * actual number of bytes written to *info*. Note that *info* should be
+ * actual number of bytes written to *info*.
- * zero-initialized or initialized as expected by the requested *info*
- * type. Failing to (zero-)initialize *info* under certain circumstances can
- * result in this helper returning an error.
  *
  * @param prog_fd BPF program file descriptor
  * @param info pointer to **struct bpf_prog_info** that will be populated with
@@ -531,10 +444,7 @@ LIBBPF_API int bpf_prog_get_info_by_fd(int prog_fd, struct bpf_prog_info *info,
  * map corresponding to *map_fd*.
  *
  * Populates up to *info_len* bytes of *info* and updates *info_len* with the
- * actual number of bytes written to *info*. Note that *info* should be
+ * actual number of bytes written to *info*.
- * zero-initialized or initialized as expected by the requested *info*
- * type. Failing to (zero-)initialize *info* under certain circumstances can
- * result in this helper returning an error.
  *
  * @param map_fd BPF map file descriptor
  * @param info pointer to **struct bpf_map_info** that will be populated with
@@ -547,14 +457,11 @@ LIBBPF_API int bpf_prog_get_info_by_fd(int prog_fd, struct bpf_prog_info *info,
 LIBBPF_API int bpf_map_get_info_by_fd(int map_fd, struct bpf_map_info *info, __u32 *info_len);
 
 /**
- * @brief **bpf_btf_get_info_by_fd()** obtains information about the
+ * @brief **bpf_btf_get_info_by_fd()** obtains information about the 
  * BTF object corresponding to *btf_fd*.
  *
  * Populates up to *info_len* bytes of *info* and updates *info_len* with the
- * actual number of bytes written to *info*. Note that *info* should be
+ * actual number of bytes written to *info*.
- * zero-initialized or initialized as expected by the requested *info*
- * type. Failing to (zero-)initialize *info* under certain circumstances can
- * result in this helper returning an error.
  *
  * @param btf_fd BTF object file descriptor
  * @param info pointer to **struct bpf_btf_info** that will be populated with
@@ -571,10 +478,7 @@ LIBBPF_API int bpf_btf_get_info_by_fd(int btf_fd, struct bpf_btf_info *info, __u
  * link corresponding to *link_fd*.
  *
  * Populates up to *info_len* bytes of *info* and updates *info_len* with the
- * actual number of bytes written to *info*. Note that *info* should be
+ * actual number of bytes written to *info*.
- * zero-initialized or initialized as expected by the requested *info*
- * type. Failing to (zero-)initialize *info* under certain circumstances can
- * result in this helper returning an error.
  *
  * @param link_fd BPF link file descriptor
  * @param info pointer to **struct bpf_link_info** that will be populated with
@@ -591,45 +495,18 @@ struct bpf_prog_query_opts {
 	__u32 query_flags;
 	__u32 attach_flags; /* output argument */
 	__u32 *prog_ids;
-	union {
+	__u32 prog_cnt; /* input+output argument */
-		/* input+output argument */
-		__u32 prog_cnt;
-		__u32 count;
-	};
 	__u32 *prog_attach_flags;
-	__u32 *link_ids;
-	__u32 *link_attach_flags;
-	__u64 revision;
-	size_t :0;
 };
-#define bpf_prog_query_opts__last_field revision
+#define bpf_prog_query_opts__last_field prog_attach_flags
 
-/**
+LIBBPF_API int bpf_prog_query_opts(int target_fd,
- * @brief **bpf_prog_query_opts()** queries the BPF programs and BPF links
+				   enum bpf_attach_type type,
- * which are attached to *target* which can represent a file descriptor or
- * netdevice ifindex.
- *
- * @param target query location file descriptor or ifindex
- * @param type attach type for the BPF program
- * @param opts options for configuring the query
- * @return 0, on success; negative error code, otherwise (errno is also set to
- * the error code)
- */
-LIBBPF_API int bpf_prog_query_opts(int target, enum bpf_attach_type type,
 				   struct bpf_prog_query_opts *opts);
 LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type,
 			      __u32 query_flags, __u32 *attach_flags,
 			      __u32 *prog_ids, __u32 *prog_cnt);
 
-struct bpf_raw_tp_opts {
-	size_t sz; /* size of this struct for forward/backward compatibility */
-	const char *tp_name;
-	__u64 cookie;
-	size_t :0;
-};
-#define bpf_raw_tp_opts__last_field cookie
-
-LIBBPF_API int bpf_raw_tracepoint_open_opts(int prog_fd, struct bpf_raw_tp_opts *opts);
 LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd);
 LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf,
 				 __u32 *buf_len, __u32 *prog_id, __u32 *fd_type,
@@ -680,30 +557,6 @@ struct bpf_test_run_opts {
 LIBBPF_API int bpf_prog_test_run_opts(int prog_fd,
 				      struct bpf_test_run_opts *opts);
 
-struct bpf_token_create_opts {
-	size_t sz; /* size of this struct for forward/backward compatibility */
-	__u32 flags;
-	size_t :0;
-};
-#define bpf_token_create_opts__last_field flags
-
-/**
- * @brief **bpf_token_create()** creates a new instance of BPF token derived
- * from specified BPF FS mount point.
- *
- * BPF token created with this API can be passed to bpf() syscall for
- * commands like BPF_PROG_LOAD, BPF_MAP_CREATE, etc.
- *
- * @param bpffs_fd FD for BPF FS instance from which to derive a BPF token
- * instance.
- * @param opts optional BPF token creation options, can be NULL
- *
- * @return BPF token FD > 0, on success; negative error code, otherwise (errno
- * is also set to the error code)
- */
-LIBBPF_API int bpf_token_create(int bpffs_fd,
-				struct bpf_token_create_opts *opts);
-
 #ifdef __cplusplus
 } /* extern "C" */
 #endif

src/bpf_core_read.h

@@ -2,8 +2,6 @@
 #ifndef __BPF_CORE_READ_H__
 #define __BPF_CORE_READ_H__
 
-#include "bpf_helpers.h"
-
 /*
  * enum bpf_field_info_kind is passed as a second argument into
  * __builtin_preserve_field_info() built-in to get a specific aspect of
@@ -46,7 +44,7 @@ enum bpf_enum_value_kind {
 #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 #define __CORE_BITFIELD_PROBE_READ(dst, src, fld)			      \
 	bpf_probe_read_kernel(						      \
-			(void *)dst,					      \
+			(void *)dst,				      \
 			__CORE_RELO(src, fld, BYTE_SIZE),		      \
 			(const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET))
 #else
@@ -104,7 +102,6 @@ enum bpf_enum_value_kind {
 	case 2: val = *(const unsigned short *)p; break;		      \
 	case 4: val = *(const unsigned int *)p; break;			      \
 	case 8: val = *(const unsigned long long *)p; break;		      \
-	default: val = 0; break;					      \
 	}								      \
 	val <<= __CORE_RELO(s, field, LSHIFT_U64);			      \
 	if (__CORE_RELO(s, field, SIGNED))				      \
@@ -114,61 +111,8 @@ enum bpf_enum_value_kind {
 	val;								      \
 })
 
-/*
- * Write to a bitfield, identified by s->field.
- * This is the inverse of BPF_CORE_WRITE_BITFIELD().
- */
-#define BPF_CORE_WRITE_BITFIELD(s, field, new_val) ({			\
-	void *p = (void *)s + __CORE_RELO(s, field, BYTE_OFFSET);	\
-	unsigned int byte_size = __CORE_RELO(s, field, BYTE_SIZE);	\
-	unsigned int lshift = __CORE_RELO(s, field, LSHIFT_U64);	\
-	unsigned int rshift = __CORE_RELO(s, field, RSHIFT_U64);	\
-	unsigned long long mask, val, nval = new_val;			\
-	unsigned int rpad = rshift - lshift;				\
-									\
-	asm volatile("" : "+r"(p));					\
-									\
-	switch (byte_size) {						\
-	case 1: val = *(unsigned char *)p; break;			\
-	case 2: val = *(unsigned short *)p; break;			\
-	case 4: val = *(unsigned int *)p; break;			\
-	case 8: val = *(unsigned long long *)p; break;			\
-	}								\
-									\
-	mask = (~0ULL << rshift) >> lshift;				\
-	val = (val & ~mask) | ((nval << rpad) & mask);			\
-									\
-	switch (byte_size) {						\
-	case 1: *(unsigned char *)p      = val; break;			\
-	case 2: *(unsigned short *)p     = val; break;			\
-	case 4: *(unsigned int *)p       = val; break;			\
-	case 8: *(unsigned long long *)p = val; break;			\
-	}								\
-})
-
-/* Differentiator between compilers builtin implementations. This is a
- * requirement due to the compiler parsing differences where GCC optimizes
- * early in parsing those constructs of type pointers to the builtin specific
- * type, resulting in not being possible to collect the required type
- * information in the builtin expansion.
- */
-#ifdef __clang__
-#define ___bpf_typeof(type) ((typeof(type) *) 0)
-#else
-#define ___bpf_typeof1(type, NR) ({					    \
-	extern typeof(type) *___concat(bpf_type_tmp_, NR);		    \
-	___concat(bpf_type_tmp_, NR);					    \
-})
-#define ___bpf_typeof(type) ___bpf_typeof1(type, __COUNTER__)
-#endif
-
-#ifdef __clang__
 #define ___bpf_field_ref1(field)	(field)
-#define ___bpf_field_ref2(type, field)	(___bpf_typeof(type)->field)
+#define ___bpf_field_ref2(type, field)	(((typeof(type) *)0)->field)
-#else
-#define ___bpf_field_ref1(field)	(&(field))
-#define ___bpf_field_ref2(type, field)	(&(___bpf_typeof(type)->field))
-#endif
 #define ___bpf_field_ref(args...)					    \
 	___bpf_apply(___bpf_field_ref, ___bpf_narg(args))(args)
 
@@ -218,7 +162,7 @@ enum bpf_enum_value_kind {
  * BTF. Always succeeds.
  */
 #define bpf_core_type_id_local(type)					    \
-	__builtin_btf_type_id(*___bpf_typeof(type), BPF_TYPE_ID_LOCAL)
+	__builtin_btf_type_id(*(typeof(type) *)0, BPF_TYPE_ID_LOCAL)
 
 /*
  * Convenience macro to get BTF type ID of a target kernel's type that matches
@@ -228,7 +172,7 @@ enum bpf_enum_value_kind {
  *    - 0, if no matching type was found in a target kernel BTF.
  */
 #define bpf_core_type_id_kernel(type)					    \
-	__builtin_btf_type_id(*___bpf_typeof(type), BPF_TYPE_ID_TARGET)
+	__builtin_btf_type_id(*(typeof(type) *)0, BPF_TYPE_ID_TARGET)
 
 /*
  * Convenience macro to check that provided named type
@@ -238,7 +182,7 @@ enum bpf_enum_value_kind {
  *    0, if no matching type is found.
  */
 #define bpf_core_type_exists(type)					    \
-	__builtin_preserve_type_info(*___bpf_typeof(type), BPF_TYPE_EXISTS)
+	__builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_EXISTS)
 
 /*
  * Convenience macro to check that provided named type
@@ -248,7 +192,7 @@ enum bpf_enum_value_kind {
  *    0, if the type does not match any in the target kernel
  */
 #define bpf_core_type_matches(type)					    \
-	__builtin_preserve_type_info(*___bpf_typeof(type), BPF_TYPE_MATCHES)
+	__builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_MATCHES)
 
 /*
  * Convenience macro to get the byte size of a provided named type
@@ -258,7 +202,7 @@ enum bpf_enum_value_kind {
  *    0, if no matching type is found.
  */
 #define bpf_core_type_size(type)					    \
-	__builtin_preserve_type_info(*___bpf_typeof(type), BPF_TYPE_SIZE)
+	__builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_SIZE)
 
 /*
  * Convenience macro to check that provided enumerator value is defined in
@@ -268,13 +212,8 @@ enum bpf_enum_value_kind {
  *    kernel's BTF;
  *    0, if no matching enum and/or enum value within that enum is found.
  */
-#ifdef __clang__
 #define bpf_core_enum_value_exists(enum_type, enum_value)		    \
 	__builtin_preserve_enum_value(*(typeof(enum_type) *)enum_value, BPF_ENUMVAL_EXISTS)
-#else
-#define bpf_core_enum_value_exists(enum_type, enum_value)		    \
-	__builtin_preserve_enum_value(___bpf_typeof(enum_type), enum_value, BPF_ENUMVAL_EXISTS)
-#endif
 
 /*
  * Convenience macro to get the integer value of an enumerator value in
@@ -284,13 +223,8 @@ enum bpf_enum_value_kind {
  *    present in target kernel's BTF;
  *    0, if no matching enum and/or enum value within that enum is found.
  */
-#ifdef __clang__
 #define bpf_core_enum_value(enum_type, enum_value)			    \
 	__builtin_preserve_enum_value(*(typeof(enum_type) *)enum_value, BPF_ENUMVAL_VALUE)
-#else
-#define bpf_core_enum_value(enum_type, enum_value)			    \
-	__builtin_preserve_enum_value(___bpf_typeof(enum_type), enum_value, BPF_ENUMVAL_VALUE)
-#endif
 
 /*
  * bpf_core_read() abstracts away bpf_probe_read_kernel() call and captures
@@ -302,7 +236,7 @@ enum bpf_enum_value_kind {
  * a relocation, which records BTF type ID describing root struct/union and an
  * accessor string which describes exact embedded field that was used to take
  * an address. See detailed description of this relocation format and
- * semantics in comments to struct bpf_core_relo in include/uapi/linux/bpf.h.
+ * semantics in comments to struct bpf_field_reloc in libbpf_internal.h.
  *
  * This relocation allows libbpf to adjust BPF instruction to use correct
  * actual field offset, based on target kernel BTF type that matches original
@@ -326,17 +260,6 @@ enum bpf_enum_value_kind {
 #define bpf_core_read_user_str(dst, sz, src)				    \
 	bpf_probe_read_user_str(dst, sz, (const void *)__builtin_preserve_access_index(src))
 
-extern void *bpf_rdonly_cast(const void *obj, __u32 btf_id) __ksym __weak;
-
-/*
- * Cast provided pointer *ptr* into a pointer to a specified *type* in such
- * a way that BPF verifier will become aware of associated kernel-side BTF
- * type. This allows to access members of kernel types directly without the
- * need to use BPF_CORE_READ() macros.
- */
-#define bpf_core_cast(ptr, type)					    \
-	((typeof(type) *)bpf_rdonly_cast((ptr), bpf_core_type_id_kernel(type)))
-
 #define ___concat(a, b) a ## b
 #define ___apply(fn, n) ___concat(fn, n)
 #define ___nth(_1, _2, _3, _4, _5, _6, _7, _8, _9, _10, __11, N, ...) N
@@ -388,13 +311,7 @@ extern void *bpf_rdonly_cast(const void *obj, __u32 btf_id) __ksym __weak;
 #define ___arrow10(a, b, c, d, e, f, g, h, i, j) a->b->c->d->e->f->g->h->i->j
 #define ___arrow(...) ___apply(___arrow, ___narg(__VA_ARGS__))(__VA_ARGS__)
 
-#if defined(__clang__) && (__clang_major__ >= 19)
-#define ___type(...) __typeof_unqual__(___arrow(__VA_ARGS__))
-#elif defined(__GNUC__) && (__GNUC__ >= 14)
-#define ___type(...) __typeof_unqual__(___arrow(__VA_ARGS__))
-#else
 #define ___type(...) typeof(___arrow(__VA_ARGS__))
-#endif
 
 #define ___read(read_fn, dst, src_type, src, accessor)			    \
 	read_fn((void *)(dst), sizeof(*(dst)), &((src_type)(src))->accessor)

src/bpf_gen_internal.h

@@ -34,7 +34,6 @@ struct bpf_gen {
 	void *data_cur;
 	void *insn_start;
 	void *insn_cur;
-	bool swapped_endian;
 	ssize_t cleanup_label;
 	__u32 nr_progs;
 	__u32 nr_maps;

src/bpf_helpers.h

@@ -13,15 +13,6 @@
 #define __uint(name, val) int (*name)[val]
 #define __type(name, val) typeof(val) *name
 #define __array(name, val) typeof(val) *name[]
-#define __ulong(name, val) enum { ___bpf_concat(__unique_value, __COUNTER__) = val } name
-
-#ifndef likely
-#define likely(x)      (__builtin_expect(!!(x), 1))
-#endif
-
-#ifndef unlikely
-#define unlikely(x)    (__builtin_expect(!!(x), 0))
-#endif
 
 /*
  * Helper macro to place programs, maps, license in
@@ -145,8 +136,7 @@
 /*
  * Helper function to perform a tail call with a constant/immediate map slot.
  */
-#if (defined(__clang__) && __clang_major__ >= 8) || (!defined(__clang__) && __GNUC__ > 12)
+#if __clang_major__ >= 8 && defined(__bpf__)
-#if defined(__bpf__)
 static __always_inline void
 bpf_tail_call_static(void *ctx, const void *map, const __u32 slot)
 {
@@ -174,7 +164,6 @@ bpf_tail_call_static(void *ctx, const void *map, const __u32 slot)
 		     : "r0", "r1", "r2", "r3", "r4", "r5");
 }
 #endif
-#endif
 
 enum libbpf_pin_type {
 	LIBBPF_PIN_NONE,
@@ -192,30 +181,11 @@ enum libbpf_tristate {
 #define __ksym __attribute__((section(".ksyms")))
 #define __kptr_untrusted __attribute__((btf_type_tag("kptr_untrusted")))
 #define __kptr __attribute__((btf_type_tag("kptr")))
-#define __percpu_kptr __attribute__((btf_type_tag("percpu_kptr")))
-#define __uptr __attribute__((btf_type_tag("uptr")))
 
-#if defined (__clang__)
+#define bpf_ksym_exists(sym) ({									\
-#define bpf_ksym_exists(sym) ({						\
+	_Static_assert(!__builtin_constant_p(!!sym), #sym " should be marked as __weak");	\
-	_Static_assert(!__builtin_constant_p(!!sym),			\
+	!!sym;											\
-		       #sym " should be marked as __weak");		\
-	!!sym;								\
 })
-#elif __GNUC__ > 8
-#define bpf_ksym_exists(sym) ({						\
-	_Static_assert(__builtin_has_attribute (*sym, __weak__),	\
-		       #sym " should be marked as __weak");		\
-	!!sym;								\
-})
-#else
-#define bpf_ksym_exists(sym) !!sym
-#endif
-
-#define __arg_ctx __attribute__((btf_decl_tag("arg:ctx")))
-#define __arg_nonnull __attribute((btf_decl_tag("arg:nonnull")))
-#define __arg_nullable __attribute((btf_decl_tag("arg:nullable")))
-#define __arg_trusted __attribute((btf_decl_tag("arg:trusted")))
-#define __arg_arena __attribute((btf_decl_tag("arg:arena")))
 
 #ifndef ___bpf_concat
 #define ___bpf_concat(a, b) a ## b
@@ -350,7 +320,7 @@ extern void bpf_iter_num_destroy(struct bpf_iter_num *it) __weak __ksym;
  * I.e., it looks almost like high-level for each loop in other languages,
  * supports continue/break, and is verifiable by BPF verifier.
  *
- * For iterating integers, the difference between bpf_for_each(num, i, N, M)
+ * For iterating integers, the difference betwen bpf_for_each(num, i, N, M)
  * and bpf_for(i, N, M) is in that bpf_for() provides additional proof to
  * verifier that i is in [N, M) range, and in bpf_for_each() case i is `int
  * *`, not just `int`. So for integers bpf_for() is more convenient.

src/bpf_tracing.h

@@ -2,7 +2,7 @@
 #ifndef __BPF_TRACING_H__
 #define __BPF_TRACING_H__
 
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 /* Scan the ARCH passed in from ARCH env variable (see Makefile) */
 #if defined(__TARGET_ARCH_x86)
@@ -163,7 +163,7 @@
 
 struct pt_regs___s390 {
 	unsigned long orig_gpr2;
-} __attribute__((preserve_access_index));
+};
 
 /* s390 provides user_pt_regs instead of struct pt_regs to userspace */
 #define __PT_REGS_CAST(x) ((const user_pt_regs *)(x))
@@ -179,7 +179,7 @@ struct pt_regs___s390 {
 #define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
 #define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
 #define __PT_PARM6_SYSCALL_REG gprs[7]
-#define PT_REGS_PARM1_SYSCALL(x) (((const struct pt_regs___s390 *)(x))->__PT_PARM1_SYSCALL_REG)
+#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), __PT_PARM1_SYSCALL_REG)
 
@@ -222,7 +222,7 @@ struct pt_regs___s390 {
 
 struct pt_regs___arm64 {
 	unsigned long orig_x0;
-} __attribute__((preserve_access_index));
+};
 
 /* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
 #define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x))
@@ -241,7 +241,7 @@ struct pt_regs___arm64 {
 #define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
 #define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
 #define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
-#define PT_REGS_PARM1_SYSCALL(x) (((const struct pt_regs___arm64 *)(x))->__PT_PARM1_SYSCALL_REG)
+#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), __PT_PARM1_SYSCALL_REG)
 
@@ -351,10 +351,6 @@ struct pt_regs___arm64 {
  * https://github.com/riscv-non-isa/riscv-elf-psabi-doc/blob/master/riscv-cc.adoc#risc-v-calling-conventions
  */
 
-struct pt_regs___riscv {
-	unsigned long orig_a0;
-} __attribute__((preserve_access_index));
-
 /* riscv provides struct user_regs_struct instead of struct pt_regs to userspace */
 #define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x))
 #define __PT_PARM1_REG a0
@@ -366,15 +362,14 @@ struct pt_regs___riscv {
 #define __PT_PARM7_REG a6
 #define __PT_PARM8_REG a7
 
-#define __PT_PARM1_SYSCALL_REG orig_a0
+/* riscv does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx
+#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG
 #define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
 #define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
 #define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
 #define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
 #define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
-#define PT_REGS_PARM1_SYSCALL(x) (((const struct pt_regs___riscv *)(x))->__PT_PARM1_SYSCALL_REG)
-#define PT_REGS_PARM1_CORE_SYSCALL(x) \
-	BPF_CORE_READ((const struct pt_regs___riscv *)(x), __PT_PARM1_SYSCALL_REG)
 
 #define __PT_RET_REG ra
 #define __PT_FP_REG s0
@@ -480,7 +475,7 @@ struct pt_regs;
 #endif
 /*
  * Similarly, syscall-specific conventions might differ between function call
- * conventions within each architecture. All supported architectures pass
+ * conventions within each architecutre. All supported architectures pass
  * either 6 or 7 syscall arguments in registers.
  *
  * See syscall(2) manpage for succinct table with information on each arch.
@@ -522,7 +517,7 @@ struct pt_regs;
 #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) || defined(bpf_target_arm64)
+#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
@@ -640,25 +635,25 @@ struct pt_regs;
 #endif
 
 #define ___bpf_ctx_cast0()            ctx
-#define ___bpf_ctx_cast1(x)           ___bpf_ctx_cast0(), ctx[0]
+#define ___bpf_ctx_cast1(x)           ___bpf_ctx_cast0(), (void *)ctx[0]
-#define ___bpf_ctx_cast2(x, args...)  ___bpf_ctx_cast1(args), ctx[1]
+#define ___bpf_ctx_cast2(x, args...)  ___bpf_ctx_cast1(args), (void *)ctx[1]
-#define ___bpf_ctx_cast3(x, args...)  ___bpf_ctx_cast2(args), ctx[2]
+#define ___bpf_ctx_cast3(x, args...)  ___bpf_ctx_cast2(args), (void *)ctx[2]
-#define ___bpf_ctx_cast4(x, args...)  ___bpf_ctx_cast3(args), ctx[3]
+#define ___bpf_ctx_cast4(x, args...)  ___bpf_ctx_cast3(args), (void *)ctx[3]
-#define ___bpf_ctx_cast5(x, args...)  ___bpf_ctx_cast4(args), ctx[4]
+#define ___bpf_ctx_cast5(x, args...)  ___bpf_ctx_cast4(args), (void *)ctx[4]
-#define ___bpf_ctx_cast6(x, args...)  ___bpf_ctx_cast5(args), ctx[5]
+#define ___bpf_ctx_cast6(x, args...)  ___bpf_ctx_cast5(args), (void *)ctx[5]
-#define ___bpf_ctx_cast7(x, args...)  ___bpf_ctx_cast6(args), ctx[6]
+#define ___bpf_ctx_cast7(x, args...)  ___bpf_ctx_cast6(args), (void *)ctx[6]
-#define ___bpf_ctx_cast8(x, args...)  ___bpf_ctx_cast7(args), ctx[7]
+#define ___bpf_ctx_cast8(x, args...)  ___bpf_ctx_cast7(args), (void *)ctx[7]
-#define ___bpf_ctx_cast9(x, args...)  ___bpf_ctx_cast8(args), ctx[8]
+#define ___bpf_ctx_cast9(x, args...)  ___bpf_ctx_cast8(args), (void *)ctx[8]
-#define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), ctx[9]
+#define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9]
-#define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), ctx[10]
+#define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10]
-#define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), ctx[11]
+#define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11]
 #define ___bpf_ctx_cast(args...)      ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args)
 
 /*
  * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and
  * similar kinds of BPF programs, that accept input arguments as a single
  * pointer to untyped u64 array, where each u64 can actually be a typed
- * pointer or integer of different size. Instead of requiring user to write
+ * pointer or integer of different size. Instead of requring user to write
  * manual casts and work with array elements by index, BPF_PROG macro
  * allows user to declare a list of named and typed input arguments in the
  * same syntax as for normal C function. All the casting is hidden and
@@ -793,14 +788,14 @@ ____##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(), (unsigned long long)PT_REGS_PARM1(ctx)
+#define ___bpf_kprobe_args1(x)          ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx)
-#define ___bpf_kprobe_args2(x, args...) ___bpf_kprobe_args1(args), (unsigned long long)PT_REGS_PARM2(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), (unsigned long long)PT_REGS_PARM3(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), (unsigned long long)PT_REGS_PARM4(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), (unsigned long long)PT_REGS_PARM5(ctx)
+#define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx)
-#define ___bpf_kprobe_args6(x, args...) ___bpf_kprobe_args5(args), (unsigned long long)PT_REGS_PARM6(ctx)
+#define ___bpf_kprobe_args6(x, args...) ___bpf_kprobe_args5(args), (void *)PT_REGS_PARM6(ctx)
-#define ___bpf_kprobe_args7(x, args...) ___bpf_kprobe_args6(args), (unsigned long long)PT_REGS_PARM7(ctx)
+#define ___bpf_kprobe_args7(x, args...) ___bpf_kprobe_args6(args), (void *)PT_REGS_PARM7(ctx)
-#define ___bpf_kprobe_args8(x, args...) ___bpf_kprobe_args7(args), (unsigned long long)PT_REGS_PARM8(ctx)
+#define ___bpf_kprobe_args8(x, args...) ___bpf_kprobe_args7(args), (void *)PT_REGS_PARM8(ctx)
 #define ___bpf_kprobe_args(args...)     ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)
 
 /*
@@ -808,7 +803,7 @@ struct pt_regs;
  * tp_btf/fentry/fexit BPF programs. It hides the underlying platform-specific
  * low-level way of getting kprobe input arguments from struct pt_regs, and
  * provides a familiar typed and named function arguments syntax and
- * semantics of accessing kprobe input parameters.
+ * semantics of accessing kprobe input paremeters.
  *
  * Original struct pt_regs* context is preserved as 'ctx' argument. This might
  * be necessary when using BPF helpers like bpf_perf_event_output().
@@ -828,7 +823,7 @@ 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(), (unsigned long long)PT_REGS_RC(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)
 
 /*
@@ -852,24 +847,24 @@ 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(), (unsigned long long)PT_REGS_PARM1_SYSCALL(regs)
+#define ___bpf_syscall_args1(x)          ___bpf_syscall_args0(), (void *)PT_REGS_PARM1_SYSCALL(regs)
-#define ___bpf_syscall_args2(x, args...) ___bpf_syscall_args1(args), (unsigned long long)PT_REGS_PARM2_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), (unsigned long long)PT_REGS_PARM3_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), (unsigned long long)PT_REGS_PARM4_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), (unsigned long long)PT_REGS_PARM5_SYSCALL(regs)
+#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (void *)PT_REGS_PARM5_SYSCALL(regs)
-#define ___bpf_syscall_args6(x, args...) ___bpf_syscall_args5(args), (unsigned long long)PT_REGS_PARM6_SYSCALL(regs)
+#define ___bpf_syscall_args6(x, args...) ___bpf_syscall_args5(args), (void *)PT_REGS_PARM6_SYSCALL(regs)
-#define ___bpf_syscall_args7(x, args...) ___bpf_syscall_args6(args), (unsigned long long)PT_REGS_PARM7_SYSCALL(regs)
+#define ___bpf_syscall_args7(x, args...) ___bpf_syscall_args6(args), (void *)PT_REGS_PARM7_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(), (unsigned long long)PT_REGS_PARM1_CORE_SYSCALL(regs)
+#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), (unsigned long long)PT_REGS_PARM2_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), (unsigned long long)PT_REGS_PARM3_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), (unsigned long long)PT_REGS_PARM4_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), (unsigned long long)PT_REGS_PARM5_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args5(x, args...) ___bpf_syswrap_args4(args), (void *)PT_REGS_PARM5_CORE_SYSCALL(regs)
-#define ___bpf_syswrap_args6(x, args...) ___bpf_syswrap_args5(args), (unsigned long long)PT_REGS_PARM6_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args6(x, args...) ___bpf_syswrap_args5(args), (void *)PT_REGS_PARM6_CORE_SYSCALL(regs)
-#define ___bpf_syswrap_args7(x, args...) ___bpf_syswrap_args6(args), (unsigned long long)PT_REGS_PARM7_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args7(x, args...) ___bpf_syswrap_args6(args), (void *)PT_REGS_PARM7_CORE_SYSCALL(regs)
 #define ___bpf_syswrap_args(args...)     ___bpf_apply(___bpf_syswrap_args, ___bpf_narg(args))(args)
 
 /*

src/btf.h

@@ -18,7 +18,6 @@ extern "C" {
 
 #define BTF_ELF_SEC ".BTF"
 #define BTF_EXT_ELF_SEC ".BTF.ext"
-#define BTF_BASE_ELF_SEC ".BTF.base"
 #define MAPS_ELF_SEC ".maps"
 
 struct btf;
@@ -108,27 +107,6 @@ LIBBPF_API struct btf *btf__new_empty(void);
  */
 LIBBPF_API struct btf *btf__new_empty_split(struct btf *base_btf);
 
-/**
- * @brief **btf__distill_base()** creates new versions of the split BTF
- * *src_btf* and its base BTF. The new base BTF will only contain the types
- * needed to improve robustness of the split BTF to small changes in base BTF.
- * When that split BTF is loaded against a (possibly changed) base, this
- * distilled base BTF will help update references to that (possibly changed)
- * base BTF.
- *
- * Both the new split and its associated new base BTF must be freed by
- * the caller.
- *
- * If successful, 0 is returned and **new_base_btf** and **new_split_btf**
- * will point at new base/split BTF. Both the new split and its associated
- * new base BTF must be freed by the caller.
- *
- * A negative value is returned on error and the thread-local `errno` variable
- * is set to the error code as well.
- */
-LIBBPF_API int btf__distill_base(const struct btf *src_btf, struct btf **new_base_btf,
-				 struct btf **new_split_btf);
-
 LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext);
 LIBBPF_API struct btf *btf__parse_split(const char *path, struct btf *base_btf);
 LIBBPF_API struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext);
@@ -167,9 +145,6 @@ LIBBPF_API const char *btf__str_by_offset(const struct btf *btf, __u32 offset);
 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__raw_data(const struct btf_ext *btf_ext, __u32 *size);
-LIBBPF_API enum btf_endianness btf_ext__endianness(const struct btf_ext *btf_ext);
-LIBBPF_API int btf_ext__set_endianness(struct btf_ext *btf_ext,
-				       enum btf_endianness endian);
 
 LIBBPF_API int btf__find_str(struct btf *btf, const char *s);
 LIBBPF_API int btf__add_str(struct btf *btf, const char *s);
@@ -227,7 +202,6 @@ 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);
-LIBBPF_API int btf__add_type_attr(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,
@@ -244,8 +218,6 @@ LIBBPF_API int btf__add_datasec_var_info(struct btf *btf, int var_type_id,
 /* tag construction API */
 LIBBPF_API int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id,
 			    int component_idx);
-LIBBPF_API int btf__add_decl_attr(struct btf *btf, const char *value, int ref_type_id,
-				  int component_idx);
 
 struct btf_dedup_opts {
 	size_t sz;
@@ -259,20 +231,6 @@ struct btf_dedup_opts {
 
 LIBBPF_API int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts);
 
-/**
- * @brief **btf__relocate()** will check the split BTF *btf* for references
- * to base BTF kinds, and verify those references are compatible with
- * *base_btf*; if they are, *btf* is adjusted such that is re-parented to
- * *base_btf* and type ids and strings are adjusted to accommodate this.
- *
- * If successful, 0 is returned and **btf** now has **base_btf** as its
- * base.
- *
- * A negative value is returned on error and the thread-local `errno` variable
- * is set to the error code as well.
- */
-LIBBPF_API int btf__relocate(struct btf *btf, const struct btf *base_btf);
-
 struct btf_dump;
 
 struct btf_dump_opts {
@@ -292,7 +250,7 @@ LIBBPF_API void btf_dump__free(struct btf_dump *d);
 LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id);
 
 struct btf_dump_emit_type_decl_opts {
-	/* size of this struct, for forward/backward compatibility */
+	/* size of this struct, for forward/backward compatiblity */
 	size_t sz;
 	/* optional field name for type declaration, e.g.:
 	 * - struct my_struct <FNAME>

src/btf_dump.c

@@ -21,7 +21,6 @@
 #include "hashmap.h"
 #include "libbpf.h"
 #include "libbpf_internal.h"
-#include "str_error.h"
 
 static const char PREFIXES[] = "\t\t\t\t\t\t\t\t\t\t\t\t\t";
 static const size_t PREFIX_CNT = sizeof(PREFIXES) - 1;
@@ -305,7 +304,7 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id)
  * definition, in which case they have to be declared inline as part of field
  * type declaration; or as a top-level anonymous enum, typically used for
  * declaring global constants. It's impossible to distinguish between two
- * without knowing whether given enum type was referenced from other type:
+ * without knowning whether given enum type was referenced from other type:
  * top-level anonymous enum won't be referenced by anything, while embedded
  * one will.
  */
@@ -868,8 +867,8 @@ static void btf_dump_emit_bit_padding(const struct btf_dump *d,
 	} pads[] = {
 		{"long", d->ptr_sz * 8}, {"int", 32}, {"short", 16}, {"char", 8}
 	};
-	int new_off = 0, pad_bits = 0, bits, i;
+	int new_off, pad_bits, bits, i;
-	const char *pad_type = NULL;
+	const char *pad_type;
 
 	if (cur_off >= next_off)
 		return; /* no gap */
@@ -1305,7 +1304,7 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id,
 			 * chain, restore stack, emit warning, and try to
 			 * proceed nevertheless
 			 */
-			pr_warn("not enough memory for decl stack: %s\n", errstr(err));
+			pr_warn("not enough memory for decl stack:%d", err);
 			d->decl_stack_cnt = stack_start;
 			return;
 		}
@@ -1494,10 +1493,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 		case BTF_KIND_TYPE_TAG:
 			btf_dump_emit_mods(d, decls);
 			name = btf_name_of(d, t->name_off);
-			if (btf_kflag(t))
+			btf_dump_printf(d, " __attribute__((btf_type_tag(\"%s\")))", name);
-				btf_dump_printf(d, " __attribute__((%s))", name);
-			else
-				btf_dump_printf(d, " __attribute__((btf_type_tag(\"%s\")))", name);
 			break;
 		case BTF_KIND_ARRAY: {
 			const struct btf_array *a = btf_array(t);
@@ -1563,12 +1559,10 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 			 * Clang for BPF target generates func_proto with no
 			 * args as a func_proto with a single void arg (e.g.,
 			 * `int (*f)(void)` vs just `int (*f)()`). We are
-			 * going to emit valid empty args (void) syntax for
+			 * going to pretend there are no args for such case.
-			 * such case. Similarly and conveniently, valid
-			 * no args case can be special-cased here as well.
 			 */
-			if (vlen == 0 || (vlen == 1 && p->type == 0)) {
+			if (vlen == 1 && p->type == 0) {
-				btf_dump_printf(d, "void)");
+				btf_dump_printf(d, ")");
 				return;
 			}
 
@@ -1935,7 +1929,6 @@ static int btf_dump_int_data(struct btf_dump *d,
 			if (d->typed_dump->is_array_terminated)
 				break;
 			if (*(char *)data == '\0') {
-				btf_dump_type_values(d, "'\\0'");
 				d->typed_dump->is_array_terminated = true;
 				break;
 			}
@@ -2038,7 +2031,6 @@ static int btf_dump_array_data(struct btf_dump *d,
 	__u32 i, elem_type_id;
 	__s64 elem_size;
 	bool is_array_member;
-	bool is_array_terminated;
 
 	elem_type_id = array->type;
 	elem_type = skip_mods_and_typedefs(d->btf, elem_type_id, NULL);
@@ -2074,15 +2066,12 @@ static int btf_dump_array_data(struct btf_dump *d,
 	 */
 	is_array_member = d->typed_dump->is_array_member;
 	d->typed_dump->is_array_member = true;
-	is_array_terminated = d->typed_dump->is_array_terminated;
-	d->typed_dump->is_array_terminated = false;
 	for (i = 0; i < array->nelems; i++, data += elem_size) {
 		if (d->typed_dump->is_array_terminated)
 			break;
 		btf_dump_dump_type_data(d, NULL, elem_type, elem_type_id, data, 0, 0);
 	}
 	d->typed_dump->is_array_member = is_array_member;
-	d->typed_dump->is_array_terminated = is_array_terminated;
 	d->typed_dump->depth--;
 	btf_dump_data_pfx(d);
 	btf_dump_type_values(d, "]");

src/btf_iter.c

@@ -1,177 +0,0 @@
-// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-/* Copyright (c) 2021 Facebook */
-/* Copyright (c) 2024, Oracle and/or its affiliates. */
-
-#ifdef __KERNEL__
-#include <linux/bpf.h>
-#include <linux/btf.h>
-
-#define btf_var_secinfos(t)	(struct btf_var_secinfo *)btf_type_var_secinfo(t)
-
-#else
-#include "btf.h"
-#include "libbpf_internal.h"
-#endif
-
-int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t,
-			enum btf_field_iter_kind iter_kind)
-{
-	it->p = NULL;
-	it->m_idx = -1;
-	it->off_idx = 0;
-	it->vlen = 0;
-
-	switch (iter_kind) {
-	case BTF_FIELD_ITER_IDS:
-		switch (btf_kind(t)) {
-		case BTF_KIND_UNKN:
-		case BTF_KIND_INT:
-		case BTF_KIND_FLOAT:
-		case BTF_KIND_ENUM:
-		case BTF_KIND_ENUM64:
-			it->desc = (struct btf_field_desc) {};
-			break;
-		case BTF_KIND_FWD:
-		case BTF_KIND_CONST:
-		case BTF_KIND_VOLATILE:
-		case BTF_KIND_RESTRICT:
-		case BTF_KIND_PTR:
-		case BTF_KIND_TYPEDEF:
-		case BTF_KIND_FUNC:
-		case BTF_KIND_VAR:
-		case BTF_KIND_DECL_TAG:
-		case BTF_KIND_TYPE_TAG:
-			it->desc = (struct btf_field_desc) { 1, {offsetof(struct btf_type, type)} };
-			break;
-		case BTF_KIND_ARRAY:
-			it->desc = (struct btf_field_desc) {
-				2, {sizeof(struct btf_type) + offsetof(struct btf_array, type),
-				sizeof(struct btf_type) + offsetof(struct btf_array, index_type)}
-			};
-			break;
-		case BTF_KIND_STRUCT:
-		case BTF_KIND_UNION:
-			it->desc = (struct btf_field_desc) {
-				0, {},
-				sizeof(struct btf_member),
-				1, {offsetof(struct btf_member, type)}
-			};
-			break;
-		case BTF_KIND_FUNC_PROTO:
-			it->desc = (struct btf_field_desc) {
-				1, {offsetof(struct btf_type, type)},
-				sizeof(struct btf_param),
-				1, {offsetof(struct btf_param, type)}
-			};
-			break;
-		case BTF_KIND_DATASEC:
-			it->desc = (struct btf_field_desc) {
-				0, {},
-				sizeof(struct btf_var_secinfo),
-				1, {offsetof(struct btf_var_secinfo, type)}
-			};
-			break;
-		default:
-			return -EINVAL;
-		}
-		break;
-	case BTF_FIELD_ITER_STRS:
-		switch (btf_kind(t)) {
-		case BTF_KIND_UNKN:
-			it->desc = (struct btf_field_desc) {};
-			break;
-		case BTF_KIND_INT:
-		case BTF_KIND_FLOAT:
-		case BTF_KIND_FWD:
-		case BTF_KIND_ARRAY:
-		case BTF_KIND_CONST:
-		case BTF_KIND_VOLATILE:
-		case BTF_KIND_RESTRICT:
-		case BTF_KIND_PTR:
-		case BTF_KIND_TYPEDEF:
-		case BTF_KIND_FUNC:
-		case BTF_KIND_VAR:
-		case BTF_KIND_DECL_TAG:
-		case BTF_KIND_TYPE_TAG:
-		case BTF_KIND_DATASEC:
-			it->desc = (struct btf_field_desc) {
-				1, {offsetof(struct btf_type, name_off)}
-			};
-			break;
-		case BTF_KIND_ENUM:
-			it->desc = (struct btf_field_desc) {
-				1, {offsetof(struct btf_type, name_off)},
-				sizeof(struct btf_enum),
-				1, {offsetof(struct btf_enum, name_off)}
-			};
-			break;
-		case BTF_KIND_ENUM64:
-			it->desc = (struct btf_field_desc) {
-				1, {offsetof(struct btf_type, name_off)},
-				sizeof(struct btf_enum64),
-				1, {offsetof(struct btf_enum64, name_off)}
-			};
-			break;
-		case BTF_KIND_STRUCT:
-		case BTF_KIND_UNION:
-			it->desc = (struct btf_field_desc) {
-				1, {offsetof(struct btf_type, name_off)},
-				sizeof(struct btf_member),
-				1, {offsetof(struct btf_member, name_off)}
-			};
-			break;
-		case BTF_KIND_FUNC_PROTO:
-			it->desc = (struct btf_field_desc) {
-				1, {offsetof(struct btf_type, name_off)},
-				sizeof(struct btf_param),
-				1, {offsetof(struct btf_param, name_off)}
-			};
-			break;
-		default:
-			return -EINVAL;
-		}
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if (it->desc.m_sz)
-		it->vlen = btf_vlen(t);
-
-	it->p = t;
-	return 0;
-}
-
-__u32 *btf_field_iter_next(struct btf_field_iter *it)
-{
-	if (!it->p)
-		return NULL;
-
-	if (it->m_idx < 0) {
-		if (it->off_idx < it->desc.t_off_cnt)
-			return it->p + it->desc.t_offs[it->off_idx++];
-		/* move to per-member iteration */
-		it->m_idx = 0;
-		it->p += sizeof(struct btf_type);
-		it->off_idx = 0;
-	}
-
-	/* if type doesn't have members, stop */
-	if (it->desc.m_sz == 0) {
-		it->p = NULL;
-		return NULL;
-	}
-
-	if (it->off_idx >= it->desc.m_off_cnt) {
-		/* exhausted this member's fields, go to the next member */
-		it->m_idx++;
-		it->p += it->desc.m_sz;
-		it->off_idx = 0;
-	}
-
-	if (it->m_idx < it->vlen)
-		return it->p + it->desc.m_offs[it->off_idx++];
-
-	it->p = NULL;
-	return NULL;
-}

src/btf_relocate.c

@@ -1,519 +0,0 @@
-// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-/* Copyright (c) 2024, Oracle and/or its affiliates. */
-
-#ifndef _GNU_SOURCE
-#define _GNU_SOURCE
-#endif
-
-#ifdef __KERNEL__
-#include <linux/bpf.h>
-#include <linux/bsearch.h>
-#include <linux/btf.h>
-#include <linux/sort.h>
-#include <linux/string.h>
-#include <linux/bpf_verifier.h>
-
-#define btf_type_by_id				(struct btf_type *)btf_type_by_id
-#define btf__type_cnt				btf_nr_types
-#define btf__base_btf				btf_base_btf
-#define btf__name_by_offset			btf_name_by_offset
-#define btf__str_by_offset			btf_str_by_offset
-#define btf_kflag				btf_type_kflag
-
-#define calloc(nmemb, sz)			kvcalloc(nmemb, sz, GFP_KERNEL | __GFP_NOWARN)
-#define free(ptr)				kvfree(ptr)
-#define qsort(base, num, sz, cmp)		sort(base, num, sz, cmp, NULL)
-
-#else
-
-#include "btf.h"
-#include "bpf.h"
-#include "libbpf.h"
-#include "libbpf_internal.h"
-
-#endif /* __KERNEL__ */
-
-struct btf;
-
-struct btf_relocate {
-	struct btf *btf;
-	const struct btf *base_btf;
-	const struct btf *dist_base_btf;
-	unsigned int nr_base_types;
-	unsigned int nr_split_types;
-	unsigned int nr_dist_base_types;
-	int dist_str_len;
-	int base_str_len;
-	__u32 *id_map;
-	__u32 *str_map;
-};
-
-/* Set temporarily in relocation id_map if distilled base struct/union is
- * embedded in a split BTF struct/union; in such a case, size information must
- * match between distilled base BTF and base BTF representation of type.
- */
-#define BTF_IS_EMBEDDED ((__u32)-1)
-
-/* <name, size, id> triple used in sorting/searching distilled base BTF. */
-struct btf_name_info {
-	const char *name;
-	/* set when search requires a size match */
-	bool needs_size: 1;
-	unsigned int size: 31;
-	__u32 id;
-};
-
-static int btf_relocate_rewrite_type_id(struct btf_relocate *r, __u32 i)
-{
-	struct btf_type *t = btf_type_by_id(r->btf, i);
-	struct btf_field_iter it;
-	__u32 *id;
-	int err;
-
-	err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS);
-	if (err)
-		return err;
-
-	while ((id = btf_field_iter_next(&it)))
-		*id = r->id_map[*id];
-	return 0;
-}
-
-/* Simple string comparison used for sorting within BTF, since all distilled
- * types are named.  If strings match, and size is non-zero for both elements
- * fall back to using size for ordering.
- */
-static int cmp_btf_name_size(const void *n1, const void *n2)
-{
-	const struct btf_name_info *ni1 = n1;
-	const struct btf_name_info *ni2 = n2;
-	int name_diff = strcmp(ni1->name, ni2->name);
-
-	if (!name_diff && ni1->needs_size && ni2->needs_size)
-		return ni2->size - ni1->size;
-	return name_diff;
-}
-
-/* Binary search with a small twist; find leftmost element that matches
- * so that we can then iterate through all exact matches.  So for example
- * searching { "a", "bb", "bb", "c" }  we would always match on the
- * leftmost "bb".
- */
-static struct btf_name_info *search_btf_name_size(struct btf_name_info *key,
-						  struct btf_name_info *vals,
-						  int nelems)
-{
-	struct btf_name_info *ret = NULL;
-	int high = nelems - 1;
-	int low = 0;
-
-	while (low <= high) {
-		int mid = (low + high)/2;
-		struct btf_name_info *val = &vals[mid];
-		int diff = cmp_btf_name_size(key, val);
-
-		if (diff == 0)
-			ret = val;
-		/* even if found, keep searching for leftmost match */
-		if (diff <= 0)
-			high = mid - 1;
-		else
-			low = mid + 1;
-	}
-	return ret;
-}
-
-/* If a member of a split BTF struct/union refers to a base BTF
- * struct/union, mark that struct/union id temporarily in the id_map
- * with BTF_IS_EMBEDDED.  Members can be const/restrict/volatile/typedef
- * reference types, but if a pointer is encountered, the type is no longer
- * considered embedded.
- */
-static int btf_mark_embedded_composite_type_ids(struct btf_relocate *r, __u32 i)
-{
-	struct btf_type *t = btf_type_by_id(r->btf, i);
-	struct btf_field_iter it;
-	__u32 *id;
-	int err;
-
-	if (!btf_is_composite(t))
-		return 0;
-
-	err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS);
-	if (err)
-		return err;
-
-	while ((id = btf_field_iter_next(&it))) {
-		__u32 next_id = *id;
-
-		while (next_id) {
-			t = btf_type_by_id(r->btf, next_id);
-			switch (btf_kind(t)) {
-			case BTF_KIND_CONST:
-			case BTF_KIND_RESTRICT:
-			case BTF_KIND_VOLATILE:
-			case BTF_KIND_TYPEDEF:
-			case BTF_KIND_TYPE_TAG:
-				next_id = t->type;
-				break;
-			case BTF_KIND_ARRAY: {
-				struct btf_array *a = btf_array(t);
-
-				next_id = a->type;
-				break;
-			}
-			case BTF_KIND_STRUCT:
-			case BTF_KIND_UNION:
-				if (next_id < r->nr_dist_base_types)
-					r->id_map[next_id] = BTF_IS_EMBEDDED;
-				next_id = 0;
-				break;
-			default:
-				next_id = 0;
-				break;
-			}
-		}
-	}
-
-	return 0;
-}
-
-/* Build a map from distilled base BTF ids to base BTF ids. To do so, iterate
- * through base BTF looking up distilled type (using binary search) equivalents.
- */
-static int btf_relocate_map_distilled_base(struct btf_relocate *r)
-{
-	struct btf_name_info *info, *info_end;
-	struct btf_type *base_t, *dist_t;
-	__u8 *base_name_cnt = NULL;
-	int err = 0;
-	__u32 id;
-
-	/* generate a sort index array of name/type ids sorted by name for
-	 * distilled base BTF to speed name-based lookups.
-	 */
-	info = calloc(r->nr_dist_base_types, sizeof(*info));
-	if (!info) {
-		err = -ENOMEM;
-		goto done;
-	}
-	info_end = info + r->nr_dist_base_types;
-	for (id = 0; id < r->nr_dist_base_types; id++) {
-		dist_t = btf_type_by_id(r->dist_base_btf, id);
-		info[id].name = btf__name_by_offset(r->dist_base_btf, dist_t->name_off);
-		info[id].id = id;
-		info[id].size = dist_t->size;
-		info[id].needs_size = true;
-	}
-	qsort(info, r->nr_dist_base_types, sizeof(*info), cmp_btf_name_size);
-
-	/* Mark distilled base struct/union members of split BTF structs/unions
-	 * in id_map with BTF_IS_EMBEDDED; this signals that these types
-	 * need to match both name and size, otherwise embedding the base
-	 * struct/union in the split type is invalid.
-	 */
-	for (id = r->nr_dist_base_types; id < r->nr_dist_base_types + r->nr_split_types; id++) {
-		err = btf_mark_embedded_composite_type_ids(r, id);
-		if (err)
-			goto done;
-	}
-
-	/* Collect name counts for composite types in base BTF.  If multiple
-	 * instances of a struct/union of the same name exist, we need to use
-	 * size to determine which to map to since name alone is ambiguous.
-	 */
-	base_name_cnt = calloc(r->base_str_len, sizeof(*base_name_cnt));
-	if (!base_name_cnt) {
-		err = -ENOMEM;
-		goto done;
-	}
-	for (id = 1; id < r->nr_base_types; id++) {
-		base_t = btf_type_by_id(r->base_btf, id);
-		if (!btf_is_composite(base_t) || !base_t->name_off)
-			continue;
-		if (base_name_cnt[base_t->name_off] < 255)
-			base_name_cnt[base_t->name_off]++;
-	}
-
-	/* Now search base BTF for matching distilled base BTF types. */
-	for (id = 1; id < r->nr_base_types; id++) {
-		struct btf_name_info *dist_info, base_info = {};
-		int dist_kind, base_kind;
-
-		base_t = btf_type_by_id(r->base_btf, id);
-		/* distilled base consists of named types only. */
-		if (!base_t->name_off)
-			continue;
-		base_kind = btf_kind(base_t);
-		base_info.id = id;
-		base_info.name = btf__name_by_offset(r->base_btf, base_t->name_off);
-		switch (base_kind) {
-		case BTF_KIND_INT:
-		case BTF_KIND_FLOAT:
-		case BTF_KIND_ENUM:
-		case BTF_KIND_ENUM64:
-			/* These types should match both name and size */
-			base_info.needs_size = true;
-			base_info.size = base_t->size;
-			break;
-		case BTF_KIND_FWD:
-			/* No size considerations for fwds. */
-			break;
-		case BTF_KIND_STRUCT:
-		case BTF_KIND_UNION:
-			/* Size only needs to be used for struct/union if there
-			 * are multiple types in base BTF with the same name.
-			 * If there are multiple _distilled_ types with the same
-			 * name (a very unlikely scenario), that doesn't matter
-			 * unless corresponding _base_ types to match them are
-			 * missing.
-			 */
-			base_info.needs_size = base_name_cnt[base_t->name_off] > 1;
-			base_info.size = base_t->size;
-			break;
-		default:
-			continue;
-		}
-		/* iterate over all matching distilled base types */
-		for (dist_info = search_btf_name_size(&base_info, info, r->nr_dist_base_types);
-		     dist_info != NULL && dist_info < info_end &&
-		     cmp_btf_name_size(&base_info, dist_info) == 0;
-		     dist_info++) {
-			if (!dist_info->id || dist_info->id >= r->nr_dist_base_types) {
-				pr_warn("base BTF id [%d] maps to invalid distilled base BTF id [%d]\n",
-					id, dist_info->id);
-				err = -EINVAL;
-				goto done;
-			}
-			dist_t = btf_type_by_id(r->dist_base_btf, dist_info->id);
-			dist_kind = btf_kind(dist_t);
-
-			/* Validate that the found distilled type is compatible.
-			 * Do not error out on mismatch as another match may
-			 * occur for an identically-named type.
-			 */
-			switch (dist_kind) {
-			case BTF_KIND_FWD:
-				switch (base_kind) {
-				case BTF_KIND_FWD:
-					if (btf_kflag(dist_t) != btf_kflag(base_t))
-						continue;
-					break;
-				case BTF_KIND_STRUCT:
-					if (btf_kflag(base_t))
-						continue;
-					break;
-				case BTF_KIND_UNION:
-					if (!btf_kflag(base_t))
-						continue;
-					break;
-				default:
-					continue;
-				}
-				break;
-			case BTF_KIND_INT:
-				if (dist_kind != base_kind ||
-				    btf_int_encoding(base_t) != btf_int_encoding(dist_t))
-					continue;
-				break;
-			case BTF_KIND_FLOAT:
-				if (dist_kind != base_kind)
-					continue;
-				break;
-			case BTF_KIND_ENUM:
-				/* ENUM and ENUM64 are encoded as sized ENUM in
-				 * distilled base BTF.
-				 */
-				if (base_kind != dist_kind && base_kind != BTF_KIND_ENUM64)
-					continue;
-				break;
-			case BTF_KIND_STRUCT:
-			case BTF_KIND_UNION:
-				/* size verification is required for embedded
-				 * struct/unions.
-				 */
-				if (r->id_map[dist_info->id] == BTF_IS_EMBEDDED &&
-				    base_t->size != dist_t->size)
-					continue;
-				break;
-			default:
-				continue;
-			}
-			if (r->id_map[dist_info->id] &&
-			    r->id_map[dist_info->id] != BTF_IS_EMBEDDED) {
-				/* we already have a match; this tells us that
-				 * multiple base types of the same name
-				 * have the same size, since for cases where
-				 * multiple types have the same name we match
-				 * on name and size.  In this case, we have
-				 * no way of determining which to relocate
-				 * to in base BTF, so error out.
-				 */
-				pr_warn("distilled base BTF type '%s' [%u], size %u has multiple candidates of the same size (ids [%u, %u]) in base BTF\n",
-					base_info.name, dist_info->id,
-					base_t->size, id, r->id_map[dist_info->id]);
-				err = -EINVAL;
-				goto done;
-			}
-			/* map id and name */
-			r->id_map[dist_info->id] = id;
-			r->str_map[dist_t->name_off] = base_t->name_off;
-		}
-	}
-	/* ensure all distilled BTF ids now have a mapping... */
-	for (id = 1; id < r->nr_dist_base_types; id++) {
-		const char *name;
-
-		if (r->id_map[id] && r->id_map[id] != BTF_IS_EMBEDDED)
-			continue;
-		dist_t = btf_type_by_id(r->dist_base_btf, id);
-		name = btf__name_by_offset(r->dist_base_btf, dist_t->name_off);
-		pr_warn("distilled base BTF type '%s' [%d] is not mapped to base BTF id\n",
-			name, id);
-		err = -EINVAL;
-		break;
-	}
-done:
-	free(base_name_cnt);
-	free(info);
-	return err;
-}
-
-/* distilled base should only have named int/float/enum/fwd/struct/union types. */
-static int btf_relocate_validate_distilled_base(struct btf_relocate *r)
-{
-	unsigned int i;
-
-	for (i = 1; i < r->nr_dist_base_types; i++) {
-		struct btf_type *t = btf_type_by_id(r->dist_base_btf, i);
-		int kind = btf_kind(t);
-
-		switch (kind) {
-		case BTF_KIND_INT:
-		case BTF_KIND_FLOAT:
-		case BTF_KIND_ENUM:
-		case BTF_KIND_STRUCT:
-		case BTF_KIND_UNION:
-		case BTF_KIND_FWD:
-			if (t->name_off)
-				break;
-			pr_warn("type [%d], kind [%d] is invalid for distilled base BTF; it is anonymous\n",
-				i, kind);
-			return -EINVAL;
-		default:
-			pr_warn("type [%d] in distilled based BTF has unexpected kind [%d]\n",
-				i, kind);
-			return -EINVAL;
-		}
-	}
-	return 0;
-}
-
-static int btf_relocate_rewrite_strs(struct btf_relocate *r, __u32 i)
-{
-	struct btf_type *t = btf_type_by_id(r->btf, i);
-	struct btf_field_iter it;
-	__u32 *str_off;
-	int off, err;
-
-	err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_STRS);
-	if (err)
-		return err;
-
-	while ((str_off = btf_field_iter_next(&it))) {
-		if (!*str_off)
-			continue;
-		if (*str_off >= r->dist_str_len) {
-			*str_off += r->base_str_len - r->dist_str_len;
-		} else {
-			off = r->str_map[*str_off];
-			if (!off) {
-				pr_warn("string '%s' [offset %u] is not mapped to base BTF\n",
-					btf__str_by_offset(r->btf, off), *str_off);
-				return -ENOENT;
-			}
-			*str_off = off;
-		}
-	}
-	return 0;
-}
-
-/* If successful, output of relocation is updated BTF with base BTF pointing
- * at base_btf, and type ids, strings adjusted accordingly.
- */
-int btf_relocate(struct btf *btf, const struct btf *base_btf, __u32 **id_map)
-{
-	unsigned int nr_types = btf__type_cnt(btf);
-	const struct btf_header *dist_base_hdr;
-	const struct btf_header *base_hdr;
-	struct btf_relocate r = {};
-	int err = 0;
-	__u32 id, i;
-
-	r.dist_base_btf = btf__base_btf(btf);
-	if (!base_btf || r.dist_base_btf == base_btf)
-		return -EINVAL;
-
-	r.nr_dist_base_types = btf__type_cnt(r.dist_base_btf);
-	r.nr_base_types = btf__type_cnt(base_btf);
-	r.nr_split_types = nr_types - r.nr_dist_base_types;
-	r.btf = btf;
-	r.base_btf = base_btf;
-
-	r.id_map = calloc(nr_types, sizeof(*r.id_map));
-	r.str_map = calloc(btf_header(r.dist_base_btf)->str_len, sizeof(*r.str_map));
-	dist_base_hdr = btf_header(r.dist_base_btf);
-	base_hdr = btf_header(r.base_btf);
-	r.dist_str_len = dist_base_hdr->str_len;
-	r.base_str_len = base_hdr->str_len;
-	if (!r.id_map || !r.str_map) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-
-	err = btf_relocate_validate_distilled_base(&r);
-	if (err)
-		goto err_out;
-
-	/* Split BTF ids need to be adjusted as base and distilled base
-	 * have different numbers of types, changing the start id of split
-	 * BTF.
-	 */
-	for (id = r.nr_dist_base_types; id < nr_types; id++)
-		r.id_map[id] = id + r.nr_base_types - r.nr_dist_base_types;
-
-	/* Build a map from distilled base ids to actual base BTF ids; it is used
-	 * to update split BTF id references.  Also build a str_map mapping from
-	 * distilled base BTF names to base BTF names.
-	 */
-	err = btf_relocate_map_distilled_base(&r);
-	if (err)
-		goto err_out;
-
-	/* Next, rewrite type ids in split BTF, replacing split ids with updated
-	 * ids based on number of types in base BTF, and base ids with
-	 * relocated ids from base_btf.
-	 */
-	for (i = 0, id = r.nr_dist_base_types; i < r.nr_split_types; i++, id++) {
-		err = btf_relocate_rewrite_type_id(&r, id);
-		if (err)
-			goto err_out;
-	}
-	/* String offsets now need to be updated using the str_map. */
-	for (i = 0; i < r.nr_split_types; i++) {
-		err = btf_relocate_rewrite_strs(&r, i + r.nr_dist_base_types);
-		if (err)
-			goto err_out;
-	}
-	/* Finally reset base BTF to be base_btf */
-	btf_set_base_btf(btf, base_btf);
-
-	if (id_map) {
-		*id_map = r.id_map;
-		r.id_map = NULL;
-	}
-err_out:
-	free(r.id_map);
-	free(r.str_map);
-	return err;
-}

src/elf.c

@@ -1,559 +0,0 @@
-// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-
-#ifndef _GNU_SOURCE
-#define _GNU_SOURCE
-#endif
-#include <libelf.h>
-#include <gelf.h>
-#include <fcntl.h>
-#include <linux/kernel.h>
-
-#include "libbpf_internal.h"
-#include "str_error.h"
-
-/* A SHT_GNU_versym section holds 16-bit words. This bit is set if
- * the symbol is hidden and can only be seen when referenced using an
- * explicit version number. This is a GNU extension.
- */
-#define VERSYM_HIDDEN	0x8000
-
-/* This is the mask for the rest of the data in a word read from a
- * SHT_GNU_versym section.
- */
-#define VERSYM_VERSION	0x7fff
-
-int elf_open(const char *binary_path, struct elf_fd *elf_fd)
-{
-	int fd, ret;
-	Elf *elf;
-
-	elf_fd->elf = NULL;
-	elf_fd->fd = -1;
-
-	if (elf_version(EV_CURRENT) == EV_NONE) {
-		pr_warn("elf: failed to init libelf for %s\n", binary_path);
-		return -LIBBPF_ERRNO__LIBELF;
-	}
-	fd = open(binary_path, O_RDONLY | O_CLOEXEC);
-	if (fd < 0) {
-		ret = -errno;
-		pr_warn("elf: failed to open %s: %s\n", binary_path, errstr(ret));
-		return ret;
-	}
-	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
-	if (!elf) {
-		pr_warn("elf: could not read elf from %s: %s\n", binary_path, elf_errmsg(-1));
-		close(fd);
-		return -LIBBPF_ERRNO__FORMAT;
-	}
-	elf_fd->fd = fd;
-	elf_fd->elf = elf;
-	return 0;
-}
-
-void elf_close(struct elf_fd *elf_fd)
-{
-	if (!elf_fd)
-		return;
-	elf_end(elf_fd->elf);
-	close(elf_fd->fd);
-}
-
-/* Return next ELF section of sh_type after scn, or first of that type if scn is NULL. */
-static Elf_Scn *elf_find_next_scn_by_type(Elf *elf, int sh_type, Elf_Scn *scn)
-{
-	while ((scn = elf_nextscn(elf, scn)) != NULL) {
-		GElf_Shdr sh;
-
-		if (!gelf_getshdr(scn, &sh))
-			continue;
-		if (sh.sh_type == sh_type)
-			return scn;
-	}
-	return NULL;
-}
-
-struct elf_sym {
-	const char *name;
-	GElf_Sym sym;
-	GElf_Shdr sh;
-	int ver;
-	bool hidden;
-};
-
-struct elf_sym_iter {
-	Elf *elf;
-	Elf_Data *syms;
-	Elf_Data *versyms;
-	Elf_Data *verdefs;
-	size_t nr_syms;
-	size_t strtabidx;
-	size_t verdef_strtabidx;
-	size_t next_sym_idx;
-	struct elf_sym sym;
-	int st_type;
-};
-
-static int elf_sym_iter_new(struct elf_sym_iter *iter,
-			    Elf *elf, const char *binary_path,
-			    int sh_type, int st_type)
-{
-	Elf_Scn *scn = NULL;
-	GElf_Ehdr ehdr;
-	GElf_Shdr sh;
-
-	memset(iter, 0, sizeof(*iter));
-
-	if (!gelf_getehdr(elf, &ehdr)) {
-		pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1));
-		return -EINVAL;
-	}
-
-	scn = elf_find_next_scn_by_type(elf, sh_type, NULL);
-	if (!scn) {
-		pr_debug("elf: failed to find symbol table ELF sections in '%s'\n",
-			 binary_path);
-		return -ENOENT;
-	}
-
-	if (!gelf_getshdr(scn, &sh))
-		return -EINVAL;
-
-	iter->strtabidx = sh.sh_link;
-	iter->syms = elf_getdata(scn, 0);
-	if (!iter->syms) {
-		pr_warn("elf: failed to get symbols for symtab section in '%s': %s\n",
-			binary_path, elf_errmsg(-1));
-		return -EINVAL;
-	}
-	iter->nr_syms = iter->syms->d_size / sh.sh_entsize;
-	iter->elf = elf;
-	iter->st_type = st_type;
-
-	/* Version symbol table is meaningful to dynsym only */
-	if (sh_type != SHT_DYNSYM)
-		return 0;
-
-	scn = elf_find_next_scn_by_type(elf, SHT_GNU_versym, NULL);
-	if (!scn)
-		return 0;
-	iter->versyms = elf_getdata(scn, 0);
-
-	scn = elf_find_next_scn_by_type(elf, SHT_GNU_verdef, NULL);
-	if (!scn)
-		return 0;
-
-	iter->verdefs = elf_getdata(scn, 0);
-	if (!iter->verdefs || !gelf_getshdr(scn, &sh)) {
-		pr_warn("elf: failed to get verdef ELF section in '%s'\n", binary_path);
-		return -EINVAL;
-	}
-	iter->verdef_strtabidx = sh.sh_link;
-
-	return 0;
-}
-
-static struct elf_sym *elf_sym_iter_next(struct elf_sym_iter *iter)
-{
-	struct elf_sym *ret = &iter->sym;
-	GElf_Sym *sym = &ret->sym;
-	const char *name = NULL;
-	GElf_Versym versym;
-	Elf_Scn *sym_scn;
-	size_t idx;
-
-	for (idx = iter->next_sym_idx; idx < iter->nr_syms; idx++) {
-		if (!gelf_getsym(iter->syms, idx, sym))
-			continue;
-		if (GELF_ST_TYPE(sym->st_info) != iter->st_type)
-			continue;
-		name = elf_strptr(iter->elf, iter->strtabidx, sym->st_name);
-		if (!name)
-			continue;
-		sym_scn = elf_getscn(iter->elf, sym->st_shndx);
-		if (!sym_scn)
-			continue;
-		if (!gelf_getshdr(sym_scn, &ret->sh))
-			continue;
-
-		iter->next_sym_idx = idx + 1;
-		ret->name = name;
-		ret->ver = 0;
-		ret->hidden = false;
-
-		if (iter->versyms) {
-			if (!gelf_getversym(iter->versyms, idx, &versym))
-				continue;
-			ret->ver = versym & VERSYM_VERSION;
-			ret->hidden = versym & VERSYM_HIDDEN;
-		}
-		return ret;
-	}
-
-	return NULL;
-}
-
-static const char *elf_get_vername(struct elf_sym_iter *iter, int ver)
-{
-	GElf_Verdaux verdaux;
-	GElf_Verdef verdef;
-	int offset;
-
-	if (!iter->verdefs)
-		return NULL;
-
-	offset = 0;
-	while (gelf_getverdef(iter->verdefs, offset, &verdef)) {
-		if (verdef.vd_ndx != ver) {
-			if (!verdef.vd_next)
-				break;
-
-			offset += verdef.vd_next;
-			continue;
-		}
-
-		if (!gelf_getverdaux(iter->verdefs, offset + verdef.vd_aux, &verdaux))
-			break;
-
-		return elf_strptr(iter->elf, iter->verdef_strtabidx, verdaux.vda_name);
-
-	}
-	return NULL;
-}
-
-static bool symbol_match(struct elf_sym_iter *iter, int sh_type, struct elf_sym *sym,
-			 const char *name, size_t name_len, const char *lib_ver)
-{
-	const char *ver_name;
-
-	/* Symbols are in forms of func, func@LIB_VER or func@@LIB_VER
-	 * make sure the func part matches the user specified name
-	 */
-	if (strncmp(sym->name, name, name_len) != 0)
-		return false;
-
-	/* ...but we don't want a search for "foo" to match 'foo2" also, so any
-	 * additional characters in sname should be of the form "@@LIB".
-	 */
-	if (sym->name[name_len] != '\0' && sym->name[name_len] != '@')
-		return false;
-
-	/* If user does not specify symbol version, then we got a match */
-	if (!lib_ver)
-		return true;
-
-	/* If user specifies symbol version, for dynamic symbols,
-	 * get version name from ELF verdef section for comparison.
-	 */
-	if (sh_type == SHT_DYNSYM) {
-		ver_name = elf_get_vername(iter, sym->ver);
-		if (!ver_name)
-			return false;
-		return strcmp(ver_name, lib_ver) == 0;
-	}
-
-	/* For normal symbols, it is already in form of func@LIB_VER */
-	return strcmp(sym->name, name) == 0;
-}
-
-/* Transform symbol's virtual address (absolute for binaries and relative
- * for shared libs) into file offset, which is what kernel is expecting
- * for uprobe/uretprobe attachment.
- * See Documentation/trace/uprobetracer.rst for more details. This is done
- * by looking up symbol's containing section's header and using iter's virtual
- * address (sh_addr) and corresponding file offset (sh_offset) to transform
- * sym.st_value (virtual address) into desired final file offset.
- */
-static unsigned long elf_sym_offset(struct elf_sym *sym)
-{
-	return sym->sym.st_value - sym->sh.sh_addr + sym->sh.sh_offset;
-}
-
-/* Find offset of function name in the provided ELF object. "binary_path" is
- * the path to the ELF binary represented by "elf", and only used for error
- * reporting matters. "name" matches symbol name or name@@LIB for library
- * functions.
- */
-long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name)
-{
-	int i, sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB };
-	const char *at_symbol, *lib_ver;
-	bool is_shared_lib;
-	long ret = -ENOENT;
-	size_t name_len;
-	GElf_Ehdr ehdr;
-
-	if (!gelf_getehdr(elf, &ehdr)) {
-		pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1));
-		ret = -LIBBPF_ERRNO__FORMAT;
-		goto out;
-	}
-	/* for shared lib case, we do not need to calculate relative offset */
-	is_shared_lib = ehdr.e_type == ET_DYN;
-
-	/* Does name specify "@@LIB_VER" or "@LIB_VER" ? */
-	at_symbol = strchr(name, '@');
-	if (at_symbol) {
-		name_len = at_symbol - name;
-		/* skip second @ if it's @@LIB_VER case */
-		if (at_symbol[1] == '@')
-			at_symbol++;
-		lib_ver = at_symbol + 1;
-	} else {
-		name_len = strlen(name);
-		lib_ver = NULL;
-	}
-
-	/* Search SHT_DYNSYM, SHT_SYMTAB for symbol. This search order is used because if
-	 * a binary is stripped, it may only have SHT_DYNSYM, and a fully-statically
-	 * linked binary may not have SHT_DYMSYM, so absence of a section should not be
-	 * reported as a warning/error.
-	 */
-	for (i = 0; i < ARRAY_SIZE(sh_types); i++) {
-		struct elf_sym_iter iter;
-		struct elf_sym *sym;
-		int last_bind = -1;
-		int cur_bind;
-
-		ret = elf_sym_iter_new(&iter, elf, binary_path, sh_types[i], STT_FUNC);
-		if (ret == -ENOENT)
-			continue;
-		if (ret)
-			goto out;
-
-		while ((sym = elf_sym_iter_next(&iter))) {
-			if (!symbol_match(&iter, sh_types[i], sym, name, name_len, lib_ver))
-				continue;
-
-			cur_bind = GELF_ST_BIND(sym->sym.st_info);
-
-			if (ret > 0) {
-				/* handle multiple matches */
-				if (elf_sym_offset(sym) == ret) {
-					/* same offset, no problem */
-					continue;
-				} else if (last_bind != STB_WEAK && cur_bind != STB_WEAK) {
-					/* Only accept one non-weak bind. */
-					pr_warn("elf: ambiguous match for '%s', '%s' in '%s'\n",
-						sym->name, name, binary_path);
-					ret = -LIBBPF_ERRNO__FORMAT;
-					goto out;
-				} else if (cur_bind == STB_WEAK) {
-					/* already have a non-weak bind, and
-					 * this is a weak bind, so ignore.
-					 */
-					continue;
-				}
-			}
-
-			ret = elf_sym_offset(sym);
-			last_bind = cur_bind;
-		}
-		if (ret > 0)
-			break;
-	}
-
-	if (ret > 0) {
-		pr_debug("elf: symbol address match for '%s' in '%s': 0x%lx\n", name, binary_path,
-			 ret);
-	} else {
-		if (ret == 0) {
-			pr_warn("elf: '%s' is 0 in symtab for '%s': %s\n", name, binary_path,
-				is_shared_lib ? "should not be 0 in a shared library" :
-						"try using shared library path instead");
-			ret = -ENOENT;
-		} else {
-			pr_warn("elf: failed to find symbol '%s' in '%s'\n", name, binary_path);
-		}
-	}
-out:
-	return ret;
-}
-
-/* Find offset of function name in ELF object specified by path. "name" matches
- * symbol name or name@@LIB for library functions.
- */
-long elf_find_func_offset_from_file(const char *binary_path, const char *name)
-{
-	struct elf_fd elf_fd;
-	long ret = -ENOENT;
-
-	ret = elf_open(binary_path, &elf_fd);
-	if (ret)
-		return ret;
-	ret = elf_find_func_offset(elf_fd.elf, binary_path, name);
-	elf_close(&elf_fd);
-	return ret;
-}
-
-struct symbol {
-	const char *name;
-	int bind;
-	int idx;
-};
-
-static int symbol_cmp(const void *a, const void *b)
-{
-	const struct symbol *sym_a = a;
-	const struct symbol *sym_b = b;
-
-	return strcmp(sym_a->name, sym_b->name);
-}
-
-/*
- * Return offsets in @poffsets for symbols specified in @syms array argument.
- * On success returns 0 and offsets are returned in allocated array with @cnt
- * size, that needs to be released by the caller.
- */
-int elf_resolve_syms_offsets(const char *binary_path, int cnt,
-			     const char **syms, unsigned long **poffsets,
-			     int st_type)
-{
-	int sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB };
-	int err = 0, i, cnt_done = 0;
-	unsigned long *offsets;
-	struct symbol *symbols;
-	struct elf_fd elf_fd;
-
-	err = elf_open(binary_path, &elf_fd);
-	if (err)
-		return err;
-
-	offsets = calloc(cnt, sizeof(*offsets));
-	symbols = calloc(cnt, sizeof(*symbols));
-
-	if (!offsets || !symbols) {
-		err = -ENOMEM;
-		goto out;
-	}
-
-	for (i = 0; i < cnt; i++) {
-		symbols[i].name = syms[i];
-		symbols[i].idx = i;
-	}
-
-	qsort(symbols, cnt, sizeof(*symbols), symbol_cmp);
-
-	for (i = 0; i < ARRAY_SIZE(sh_types); i++) {
-		struct elf_sym_iter iter;
-		struct elf_sym *sym;
-
-		err = elf_sym_iter_new(&iter, elf_fd.elf, binary_path, sh_types[i], st_type);
-		if (err == -ENOENT)
-			continue;
-		if (err)
-			goto out;
-
-		while ((sym = elf_sym_iter_next(&iter))) {
-			unsigned long sym_offset = elf_sym_offset(sym);
-			int bind = GELF_ST_BIND(sym->sym.st_info);
-			struct symbol *found, tmp = {
-				.name = sym->name,
-			};
-			unsigned long *offset;
-
-			found = bsearch(&tmp, symbols, cnt, sizeof(*symbols), symbol_cmp);
-			if (!found)
-				continue;
-
-			offset = &offsets[found->idx];
-			if (*offset > 0) {
-				/* same offset, no problem */
-				if (*offset == sym_offset)
-					continue;
-				/* handle multiple matches */
-				if (found->bind != STB_WEAK && bind != STB_WEAK) {
-					/* Only accept one non-weak bind. */
-					pr_warn("elf: ambiguous match found '%s@%lu' in '%s' previous offset %lu\n",
-						sym->name, sym_offset, binary_path, *offset);
-					err = -ESRCH;
-					goto out;
-				} else if (bind == STB_WEAK) {
-					/* already have a non-weak bind, and
-					 * this is a weak bind, so ignore.
-					 */
-					continue;
-				}
-			} else {
-				cnt_done++;
-			}
-			*offset = sym_offset;
-			found->bind = bind;
-		}
-	}
-
-	if (cnt != cnt_done) {
-		err = -ENOENT;
-		goto out;
-	}
-
-	*poffsets = offsets;
-
-out:
-	free(symbols);
-	if (err)
-		free(offsets);
-	elf_close(&elf_fd);
-	return err;
-}
-
-/*
- * Return offsets in @poffsets for symbols specified by @pattern argument.
- * On success returns 0 and offsets are returned in allocated @poffsets
- * array with the @pctn size, that needs to be released by the caller.
- */
-int elf_resolve_pattern_offsets(const char *binary_path, const char *pattern,
-				unsigned long **poffsets, size_t *pcnt)
-{
-	int sh_types[2] = { SHT_SYMTAB, SHT_DYNSYM };
-	unsigned long *offsets = NULL;
-	size_t cap = 0, cnt = 0;
-	struct elf_fd elf_fd;
-	int err = 0, i;
-
-	err = elf_open(binary_path, &elf_fd);
-	if (err)
-		return err;
-
-	for (i = 0; i < ARRAY_SIZE(sh_types); i++) {
-		struct elf_sym_iter iter;
-		struct elf_sym *sym;
-
-		err = elf_sym_iter_new(&iter, elf_fd.elf, binary_path, sh_types[i], STT_FUNC);
-		if (err == -ENOENT)
-			continue;
-		if (err)
-			goto out;
-
-		while ((sym = elf_sym_iter_next(&iter))) {
-			if (!glob_match(sym->name, pattern))
-				continue;
-
-			err = libbpf_ensure_mem((void **) &offsets, &cap, sizeof(*offsets),
-						cnt + 1);
-			if (err)
-				goto out;
-
-			offsets[cnt++] = elf_sym_offset(sym);
-		}
-
-		/* If we found anything in the first symbol section,
-		 * do not search others to avoid duplicates.
-		 */
-		if (cnt)
-			break;
-	}
-
-	if (cnt) {
-		*poffsets = offsets;
-		*pcnt = cnt;
-	} else {
-		err = -ENOENT;
-	}
-
-out:
-	if (err)
-		free(offsets);
-	elf_close(&elf_fd);
-	return err;
-}

src/features.c

@@ -1,610 +0,0 @@
-// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
-#include <linux/kernel.h>
-#include <linux/filter.h>
-#include "bpf.h"
-#include "libbpf.h"
-#include "libbpf_common.h"
-#include "libbpf_internal.h"
-#include "str_error.h"
-
-static inline __u64 ptr_to_u64(const void *ptr)
-{
-	return (__u64)(unsigned long)ptr;
-}
-
-int probe_fd(int fd)
-{
-	if (fd >= 0)
-		close(fd);
-	return fd >= 0;
-}
-
-static int probe_kern_prog_name(int token_fd)
-{
-	const size_t attr_sz = offsetofend(union bpf_attr, prog_token_fd);
-	struct bpf_insn insns[] = {
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	};
-	union bpf_attr attr;
-	int ret;
-
-	memset(&attr, 0, attr_sz);
-	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
-	attr.license = ptr_to_u64("GPL");
-	attr.insns = ptr_to_u64(insns);
-	attr.insn_cnt = (__u32)ARRAY_SIZE(insns);
-	attr.prog_token_fd = token_fd;
-	if (token_fd)
-		attr.prog_flags |= BPF_F_TOKEN_FD;
-	libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name));
-
-	/* make sure loading with name works */
-	ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS);
-	return probe_fd(ret);
-}
-
-static int probe_kern_global_data(int token_fd)
-{
-	struct bpf_insn insns[] = {
-		BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16),
-		BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	};
-	LIBBPF_OPTS(bpf_map_create_opts, map_opts,
-		.token_fd = token_fd,
-		.map_flags = token_fd ? BPF_F_TOKEN_FD : 0,
-	);
-	LIBBPF_OPTS(bpf_prog_load_opts, prog_opts,
-		.token_fd = token_fd,
-		.prog_flags = token_fd ? BPF_F_TOKEN_FD : 0,
-	);
-	int ret, map, insn_cnt = ARRAY_SIZE(insns);
-
-	map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, &map_opts);
-	if (map < 0) {
-		ret = -errno;
-		pr_warn("Error in %s(): %s. Couldn't create simple array map.\n",
-			__func__, errstr(ret));
-		return ret;
-	}
-
-	insns[0].imm = map;
-
-	ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts);
-	close(map);
-	return probe_fd(ret);
-}
-
-static int probe_kern_btf(int token_fd)
-{
-	static const char strs[] = "\0int";
-	__u32 types[] = {
-		/* int */
-		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),
-	};
-
-	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
-					     strs, sizeof(strs), token_fd));
-}
-
-static int probe_kern_btf_func(int token_fd)
-{
-	static const char strs[] = "\0int\0x\0a";
-	/* void x(int a) {} */
-	__u32 types[] = {
-		/* int */
-		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
-		/* FUNC_PROTO */                                /* [2] */
-		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0),
-		BTF_PARAM_ENC(7, 1),
-		/* FUNC x */                                    /* [3] */
-		BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2),
-	};
-
-	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
-					     strs, sizeof(strs), token_fd));
-}
-
-static int probe_kern_btf_func_global(int token_fd)
-{
-	static const char strs[] = "\0int\0x\0a";
-	/* static void x(int a) {} */
-	__u32 types[] = {
-		/* int */
-		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
-		/* FUNC_PROTO */                                /* [2] */
-		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0),
-		BTF_PARAM_ENC(7, 1),
-		/* FUNC x BTF_FUNC_GLOBAL */                    /* [3] */
-		BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2),
-	};
-
-	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
-					     strs, sizeof(strs), token_fd));
-}
-
-static int probe_kern_btf_datasec(int token_fd)
-{
-	static const char strs[] = "\0x\0.data";
-	/* static int a; */
-	__u32 types[] = {
-		/* int */
-		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
-		/* VAR x */                                     /* [2] */
-		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
-		BTF_VAR_STATIC,
-		/* DATASEC val */                               /* [3] */
-		BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
-		BTF_VAR_SECINFO_ENC(2, 0, 4),
-	};
-
-	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
-					     strs, sizeof(strs), token_fd));
-}
-
-static int probe_kern_btf_qmark_datasec(int token_fd)
-{
-	static const char strs[] = "\0x\0?.data";
-	/* static int a; */
-	__u32 types[] = {
-		/* int */
-		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
-		/* VAR x */                                     /* [2] */
-		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
-		BTF_VAR_STATIC,
-		/* DATASEC ?.data */                            /* [3] */
-		BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
-		BTF_VAR_SECINFO_ENC(2, 0, 4),
-	};
-
-	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
-					     strs, sizeof(strs), token_fd));
-}
-
-static int probe_kern_btf_float(int token_fd)
-{
-	static const char strs[] = "\0float";
-	__u32 types[] = {
-		/* float */
-		BTF_TYPE_FLOAT_ENC(1, 4),
-	};
-
-	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
-					     strs, sizeof(strs), token_fd));
-}
-
-static int probe_kern_btf_decl_tag(int token_fd)
-{
-	static const char strs[] = "\0tag";
-	__u32 types[] = {
-		/* int */
-		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
-		/* VAR x */                                     /* [2] */
-		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
-		BTF_VAR_STATIC,
-		/* attr */
-		BTF_TYPE_DECL_TAG_ENC(1, 2, -1),
-	};
-
-	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
-					     strs, sizeof(strs), token_fd));
-}
-
-static int probe_kern_btf_type_tag(int token_fd)
-{
-	static const char strs[] = "\0tag";
-	__u32 types[] = {
-		/* int */
-		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
-		/* attr */
-		BTF_TYPE_TYPE_TAG_ENC(1, 1),				/* [2] */
-		/* ptr */
-		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2),	/* [3] */
-	};
-
-	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
-					     strs, sizeof(strs), token_fd));
-}
-
-static int probe_kern_array_mmap(int token_fd)
-{
-	LIBBPF_OPTS(bpf_map_create_opts, opts,
-		.map_flags = BPF_F_MMAPABLE | (token_fd ? BPF_F_TOKEN_FD : 0),
-		.token_fd = token_fd,
-	);
-	int fd;
-
-	fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts);
-	return probe_fd(fd);
-}
-
-static int probe_kern_exp_attach_type(int token_fd)
-{
-	LIBBPF_OPTS(bpf_prog_load_opts, opts,
-		.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE,
-		.token_fd = token_fd,
-		.prog_flags = token_fd ? BPF_F_TOKEN_FD : 0,
-	);
-	struct bpf_insn insns[] = {
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	};
-	int fd, insn_cnt = ARRAY_SIZE(insns);
-
-	/* use any valid combination of program type and (optional)
-	 * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS)
-	 * to see if kernel supports expected_attach_type field for
-	 * BPF_PROG_LOAD command
-	 */
-	fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, insn_cnt, &opts);
-	return probe_fd(fd);
-}
-
-static int probe_kern_probe_read_kernel(int token_fd)
-{
-	LIBBPF_OPTS(bpf_prog_load_opts, opts,
-		.token_fd = token_fd,
-		.prog_flags = token_fd ? BPF_F_TOKEN_FD : 0,
-	);
-	struct bpf_insn insns[] = {
-		BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),	/* r1 = r10 (fp) */
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),	/* r1 += -8 */
-		BPF_MOV64_IMM(BPF_REG_2, 8),		/* r2 = 8 */
-		BPF_MOV64_IMM(BPF_REG_3, 0),		/* r3 = 0 */
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel),
-		BPF_EXIT_INSN(),
-	};
-	int fd, insn_cnt = ARRAY_SIZE(insns);
-
-	fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts);
-	return probe_fd(fd);
-}
-
-static int probe_prog_bind_map(int token_fd)
-{
-	struct bpf_insn insns[] = {
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	};
-	LIBBPF_OPTS(bpf_map_create_opts, map_opts,
-		.token_fd = token_fd,
-		.map_flags = token_fd ? BPF_F_TOKEN_FD : 0,
-	);
-	LIBBPF_OPTS(bpf_prog_load_opts, prog_opts,
-		.token_fd = token_fd,
-		.prog_flags = token_fd ? BPF_F_TOKEN_FD : 0,
-	);
-	int ret, map, prog, insn_cnt = ARRAY_SIZE(insns);
-
-	map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, &map_opts);
-	if (map < 0) {
-		ret = -errno;
-		pr_warn("Error in %s(): %s. Couldn't create simple array map.\n",
-			__func__, errstr(ret));
-		return ret;
-	}
-
-	prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts);
-	if (prog < 0) {
-		close(map);
-		return 0;
-	}
-
-	ret = bpf_prog_bind_map(prog, map, NULL);
-
-	close(map);
-	close(prog);
-
-	return ret >= 0;
-}
-
-static int probe_module_btf(int token_fd)
-{
-	static const char strs[] = "\0int";
-	__u32 types[] = {
-		/* int */
-		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),
-	};
-	struct bpf_btf_info info;
-	__u32 len = sizeof(info);
-	char name[16];
-	int fd, err;
-
-	fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs), token_fd);
-	if (fd < 0)
-		return 0; /* BTF not supported at all */
-
-	memset(&info, 0, sizeof(info));
-	info.name = ptr_to_u64(name);
-	info.name_len = sizeof(name);
-
-	/* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer;
-	 * kernel's module BTF support coincides with support for
-	 * name/name_len fields in struct bpf_btf_info.
-	 */
-	err = bpf_btf_get_info_by_fd(fd, &info, &len);
-	close(fd);
-	return !err;
-}
-
-static int probe_perf_link(int token_fd)
-{
-	struct bpf_insn insns[] = {
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	};
-	LIBBPF_OPTS(bpf_prog_load_opts, opts,
-		.token_fd = token_fd,
-		.prog_flags = token_fd ? BPF_F_TOKEN_FD : 0,
-	);
-	int prog_fd, link_fd, err;
-
-	prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL",
-				insns, ARRAY_SIZE(insns), &opts);
-	if (prog_fd < 0)
-		return -errno;
-
-	/* use invalid perf_event FD to get EBADF, if link is supported;
-	 * otherwise EINVAL should be returned
-	 */
-	link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL);
-	err = -errno; /* close() can clobber errno */
-
-	if (link_fd >= 0)
-		close(link_fd);
-	close(prog_fd);
-
-	return link_fd < 0 && err == -EBADF;
-}
-
-static int probe_uprobe_multi_link(int token_fd)
-{
-	LIBBPF_OPTS(bpf_prog_load_opts, load_opts,
-		.expected_attach_type = BPF_TRACE_UPROBE_MULTI,
-		.token_fd = token_fd,
-		.prog_flags = token_fd ? BPF_F_TOKEN_FD : 0,
-	);
-	LIBBPF_OPTS(bpf_link_create_opts, link_opts);
-	struct bpf_insn insns[] = {
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	};
-	int prog_fd, link_fd, err;
-	unsigned long offset = 0;
-
-	prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL",
-				insns, ARRAY_SIZE(insns), &load_opts);
-	if (prog_fd < 0)
-		return -errno;
-
-	/* Creating uprobe in '/' binary should fail with -EBADF. */
-	link_opts.uprobe_multi.path = "/";
-	link_opts.uprobe_multi.offsets = &offset;
-	link_opts.uprobe_multi.cnt = 1;
-
-	link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts);
-	err = -errno; /* close() can clobber errno */
-
-	if (link_fd >= 0 || err != -EBADF) {
-		if (link_fd >= 0)
-			close(link_fd);
-		close(prog_fd);
-		return 0;
-	}
-
-	/* Initial multi-uprobe support in kernel didn't handle PID filtering
-	 * correctly (it was doing thread filtering, not process filtering).
-	 * So now we'll detect if PID filtering logic was fixed, and, if not,
-	 * we'll pretend multi-uprobes are not supported, if not.
-	 * Multi-uprobes are used in USDT attachment logic, and we need to be
-	 * conservative here, because multi-uprobe selection happens early at
-	 * load time, while the use of PID filtering is known late at
-	 * attachment time, at which point it's too late to undo multi-uprobe
-	 * selection.
-	 *
-	 * Creating uprobe with pid == -1 for (invalid) '/' binary will fail
-	 * early with -EINVAL on kernels with fixed PID filtering logic;
-	 * otherwise -ESRCH would be returned if passed correct binary path
-	 * (but we'll just get -BADF, of course).
-	 */
-	link_opts.uprobe_multi.pid = -1; /* invalid PID */
-	link_opts.uprobe_multi.path = "/"; /* invalid path */
-	link_opts.uprobe_multi.offsets = &offset;
-	link_opts.uprobe_multi.cnt = 1;
-
-	link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts);
-	err = -errno; /* close() can clobber errno */
-
-	if (link_fd >= 0)
-		close(link_fd);
-	close(prog_fd);
-
-	return link_fd < 0 && err == -EINVAL;
-}
-
-static int probe_kern_bpf_cookie(int token_fd)
-{
-	struct bpf_insn insns[] = {
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie),
-		BPF_EXIT_INSN(),
-	};
-	LIBBPF_OPTS(bpf_prog_load_opts, opts,
-		.token_fd = token_fd,
-		.prog_flags = token_fd ? BPF_F_TOKEN_FD : 0,
-	);
-	int ret, insn_cnt = ARRAY_SIZE(insns);
-
-	ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts);
-	return probe_fd(ret);
-}
-
-static int probe_kern_btf_enum64(int token_fd)
-{
-	static const char strs[] = "\0enum64";
-	__u32 types[] = {
-		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8),
-	};
-
-	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
-					     strs, sizeof(strs), token_fd));
-}
-
-static int probe_kern_arg_ctx_tag(int token_fd)
-{
-	static const char strs[] = "\0a\0b\0arg:ctx\0";
-	const __u32 types[] = {
-		/* [1] INT */
-		BTF_TYPE_INT_ENC(1 /* "a" */, BTF_INT_SIGNED, 0, 32, 4),
-		/* [2] PTR -> VOID */
-		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 0),
-		/* [3] FUNC_PROTO `int(void *a)` */
-		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 1),
-		BTF_PARAM_ENC(1 /* "a" */, 2),
-		/* [4] FUNC 'a' -> FUNC_PROTO (main prog) */
-		BTF_TYPE_ENC(1 /* "a" */, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 3),
-		/* [5] FUNC_PROTO `int(void *b __arg_ctx)` */
-		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 1),
-		BTF_PARAM_ENC(3 /* "b" */, 2),
-		/* [6] FUNC 'b' -> FUNC_PROTO (subprog) */
-		BTF_TYPE_ENC(3 /* "b" */, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 5),
-		/* [7] DECL_TAG 'arg:ctx' -> func 'b' arg 'b' */
-		BTF_TYPE_DECL_TAG_ENC(5 /* "arg:ctx" */, 6, 0),
-	};
-	const struct bpf_insn insns[] = {
-		/* main prog */
-		BPF_CALL_REL(+1),
-		BPF_EXIT_INSN(),
-		/* global subprog */
-		BPF_EMIT_CALL(BPF_FUNC_get_func_ip), /* needs PTR_TO_CTX */
-		BPF_EXIT_INSN(),
-	};
-	const struct bpf_func_info_min func_infos[] = {
-		{ 0, 4 }, /* main prog -> FUNC 'a' */
-		{ 2, 6 }, /* subprog -> FUNC 'b' */
-	};
-	LIBBPF_OPTS(bpf_prog_load_opts, opts,
-		.token_fd = token_fd,
-		.prog_flags = token_fd ? BPF_F_TOKEN_FD : 0,
-	);
-	int prog_fd, btf_fd, insn_cnt = ARRAY_SIZE(insns);
-
-	btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs), token_fd);
-	if (btf_fd < 0)
-		return 0;
-
-	opts.prog_btf_fd = btf_fd;
-	opts.func_info = &func_infos;
-	opts.func_info_cnt = ARRAY_SIZE(func_infos);
-	opts.func_info_rec_size = sizeof(func_infos[0]);
-
-	prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, "det_arg_ctx",
-				"GPL", insns, insn_cnt, &opts);
-	close(btf_fd);
-
-	return probe_fd(prog_fd);
-}
-
-typedef int (*feature_probe_fn)(int /* token_fd */);
-
-static struct kern_feature_cache feature_cache;
-
-static struct kern_feature_desc {
-	const char *desc;
-	feature_probe_fn probe;
-} feature_probes[__FEAT_CNT] = {
-	[FEAT_PROG_NAME] = {
-		"BPF program name", probe_kern_prog_name,
-	},
-	[FEAT_GLOBAL_DATA] = {
-		"global variables", probe_kern_global_data,
-	},
-	[FEAT_BTF] = {
-		"minimal BTF", probe_kern_btf,
-	},
-	[FEAT_BTF_FUNC] = {
-		"BTF functions", probe_kern_btf_func,
-	},
-	[FEAT_BTF_GLOBAL_FUNC] = {
-		"BTF global function", probe_kern_btf_func_global,
-	},
-	[FEAT_BTF_DATASEC] = {
-		"BTF data section and variable", probe_kern_btf_datasec,
-	},
-	[FEAT_ARRAY_MMAP] = {
-		"ARRAY map mmap()", probe_kern_array_mmap,
-	},
-	[FEAT_EXP_ATTACH_TYPE] = {
-		"BPF_PROG_LOAD expected_attach_type attribute",
-		probe_kern_exp_attach_type,
-	},
-	[FEAT_PROBE_READ_KERN] = {
-		"bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel,
-	},
-	[FEAT_PROG_BIND_MAP] = {
-		"BPF_PROG_BIND_MAP support", probe_prog_bind_map,
-	},
-	[FEAT_MODULE_BTF] = {
-		"module BTF support", probe_module_btf,
-	},
-	[FEAT_BTF_FLOAT] = {
-		"BTF_KIND_FLOAT support", probe_kern_btf_float,
-	},
-	[FEAT_PERF_LINK] = {
-		"BPF perf link support", probe_perf_link,
-	},
-	[FEAT_BTF_DECL_TAG] = {
-		"BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag,
-	},
-	[FEAT_BTF_TYPE_TAG] = {
-		"BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag,
-	},
-	[FEAT_MEMCG_ACCOUNT] = {
-		"memcg-based memory accounting", probe_memcg_account,
-	},
-	[FEAT_BPF_COOKIE] = {
-		"BPF cookie support", probe_kern_bpf_cookie,
-	},
-	[FEAT_BTF_ENUM64] = {
-		"BTF_KIND_ENUM64 support", probe_kern_btf_enum64,
-	},
-	[FEAT_SYSCALL_WRAPPER] = {
-		"Kernel using syscall wrapper", probe_kern_syscall_wrapper,
-	},
-	[FEAT_UPROBE_MULTI_LINK] = {
-		"BPF multi-uprobe link support", probe_uprobe_multi_link,
-	},
-	[FEAT_ARG_CTX_TAG] = {
-		"kernel-side __arg_ctx tag", probe_kern_arg_ctx_tag,
-	},
-	[FEAT_BTF_QMARK_DATASEC] = {
-		"BTF DATASEC names starting from '?'", probe_kern_btf_qmark_datasec,
-	},
-};
-
-bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id)
-{
-	struct kern_feature_desc *feat = &feature_probes[feat_id];
-	int ret;
-
-	/* assume global feature cache, unless custom one is provided */
-	if (!cache)
-		cache = &feature_cache;
-
-	if (READ_ONCE(cache->res[feat_id]) == FEAT_UNKNOWN) {
-		ret = feat->probe(cache->token_fd);
-		if (ret > 0) {
-			WRITE_ONCE(cache->res[feat_id], FEAT_SUPPORTED);
-		} else if (ret == 0) {
-			WRITE_ONCE(cache->res[feat_id], FEAT_MISSING);
-		} else {
-			pr_warn("Detection of kernel %s support failed: %s\n",
-				feat->desc, errstr(ret));
-			WRITE_ONCE(cache->res[feat_id], FEAT_MISSING);
-		}
-	}
-
-	return READ_ONCE(cache->res[feat_id]) == FEAT_SUPPORTED;
-}

src/gen_loader.c

@@ -14,7 +14,6 @@
 #include "bpf_gen_internal.h"
 #include "skel_internal.h"
 #include <asm/byteorder.h>
-#include "str_error.h"
 
 #define MAX_USED_MAPS	64
 #define MAX_USED_PROGS	32
@@ -394,7 +393,7 @@ int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps)
 			      blob_fd_array_off(gen, i));
 	emit(gen, BPF_MOV64_IMM(BPF_REG_0, 0));
 	emit(gen, BPF_EXIT_INSN());
-	pr_debug("gen: finish %s\n", errstr(gen->error));
+	pr_debug("gen: finish %d\n", gen->error);
 	if (!gen->error) {
 		struct gen_loader_opts *opts = gen->opts;
 
@@ -402,15 +401,6 @@ int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps)
 		opts->insns_sz = gen->insn_cur - gen->insn_start;
 		opts->data = gen->data_start;
 		opts->data_sz = gen->data_cur - gen->data_start;
-
-		/* use target endianness for embedded loader */
-		if (gen->swapped_endian) {
-			struct bpf_insn *insn = (struct bpf_insn *)opts->insns;
-			int insn_cnt = opts->insns_sz / sizeof(struct bpf_insn);
-
-			for (i = 0; i < insn_cnt; i++)
-				bpf_insn_bswap(insn++);
-		}
 	}
 	return gen->error;
 }
@@ -424,28 +414,6 @@ void bpf_gen__free(struct bpf_gen *gen)
 	free(gen);
 }
 
-/*
- * Fields of bpf_attr are set to values in native byte-order before being
- * written to the target-bound data blob, and may need endian conversion.
- * This macro allows providing the correct value in situ more simply than
- * writing a separate converter for *all fields* of *all records* included
- * in union bpf_attr. Note that sizeof(rval) should match the assignment
- * target to avoid runtime problems.
- */
-#define tgt_endian(rval) ({					\
-	typeof(rval) _val = (rval);				\
-	if (gen->swapped_endian) {				\
-		switch (sizeof(_val)) {				\
-		case 1: break;					\
-		case 2: _val = bswap_16(_val); break;		\
-		case 4: _val = bswap_32(_val); break;		\
-		case 8: _val = bswap_64(_val); break;		\
-		default: pr_warn("unsupported bswap size!\n");	\
-		}						\
-	}							\
-	_val;							\
-})
-
 void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data,
 		       __u32 btf_raw_size)
 {
@@ -454,12 +422,11 @@ void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data,
 	union bpf_attr attr;
 
 	memset(&attr, 0, attr_size);
+	pr_debug("gen: load_btf: size %d\n", btf_raw_size);
 	btf_data = add_data(gen, btf_raw_data, btf_raw_size);
 
-	attr.btf_size = tgt_endian(btf_raw_size);
+	attr.btf_size = btf_raw_size;
 	btf_load_attr = add_data(gen, &attr, attr_size);
-	pr_debug("gen: load_btf: off %d size %d, attr: off %d size %d\n",
-		 btf_data, btf_raw_size, btf_load_attr, attr_size);
 
 	/* populate union bpf_attr with user provided log details */
 	move_ctx2blob(gen, attr_field(btf_load_attr, btf_log_level), 4,
@@ -490,29 +457,28 @@ void bpf_gen__map_create(struct bpf_gen *gen,
 	union bpf_attr attr;
 
 	memset(&attr, 0, attr_size);
-	attr.map_type = tgt_endian(map_type);
+	attr.map_type = map_type;
-	attr.key_size = tgt_endian(key_size);
+	attr.key_size = key_size;
-	attr.value_size = tgt_endian(value_size);
+	attr.value_size = value_size;
-	attr.map_flags = tgt_endian(map_attr->map_flags);
+	attr.map_flags = map_attr->map_flags;
-	attr.map_extra = tgt_endian(map_attr->map_extra);
+	attr.map_extra = map_attr->map_extra;
 	if (map_name)
 		libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name));
-	attr.numa_node = tgt_endian(map_attr->numa_node);
+	attr.numa_node = map_attr->numa_node;
-	attr.map_ifindex = tgt_endian(map_attr->map_ifindex);
+	attr.map_ifindex = map_attr->map_ifindex;
-	attr.max_entries = tgt_endian(max_entries);
+	attr.max_entries = max_entries;
-	attr.btf_key_type_id = tgt_endian(map_attr->btf_key_type_id);
+	attr.btf_key_type_id = map_attr->btf_key_type_id;
-	attr.btf_value_type_id = tgt_endian(map_attr->btf_value_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_type, attr.btf_value_type_id);
 
 	map_create_attr = add_data(gen, &attr, attr_size);
-	pr_debug("gen: map_create: %s idx %d type %d value_type_id %d, attr: off %d size %d\n",
+	if (attr.btf_value_type_id)
-		 map_name, map_idx, map_type, map_attr->btf_value_type_id,
-		 map_create_attr, attr_size);
-
-	if (map_attr->btf_value_type_id)
 		/* populate union bpf_attr with btf_fd saved in the stack earlier */
 		move_stack2blob(gen, attr_field(map_create_attr, btf_fd), 4,
 				stack_off(btf_fd));
-	switch (map_type) {
+	switch (attr.map_type) {
 	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
 	case BPF_MAP_TYPE_HASH_OF_MAPS:
 		move_stack2blob(gen, attr_field(map_create_attr, inner_map_fd), 4,
@@ -532,8 +498,8 @@ 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",
-		  map_name, map_idx, map_type, value_size,
+		  attr.map_name, map_idx, map_type, value_size,
-		  map_attr->btf_value_type_id);
+		  attr.btf_value_type_id);
 	emit_check_err(gen);
 	/* remember map_fd in the stack, if successful */
 	if (map_idx < 0) {
@@ -818,12 +784,12 @@ log:
 	emit_ksym_relo_log(gen, relo, kdesc->ref);
 }
 
-static __u32 src_reg_mask(struct bpf_gen *gen)
+static __u32 src_reg_mask(void)
 {
-#if defined(__LITTLE_ENDIAN_BITFIELD) /* src_reg,dst_reg,... */
+#if defined(__LITTLE_ENDIAN_BITFIELD)
-	return gen->swapped_endian ? 0xf0 : 0x0f;
+	return 0x0f; /* src_reg,dst_reg,... */
-#elif defined(__BIG_ENDIAN_BITFIELD) /* dst_reg,src_reg,... */
+#elif defined(__BIG_ENDIAN_BITFIELD)
-	return gen->swapped_endian ? 0x0f : 0xf0;
+	return 0xf0; /* dst_reg,src_reg,... */
 #else
 #error "Unsupported bit endianness, cannot proceed"
 #endif
@@ -874,7 +840,7 @@ static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo,
 	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 3));
 clear_src_reg:
 	/* clear bpf_object__relocate_data's src_reg assignment, otherwise we get a verifier failure */
-	reg_mask = src_reg_mask(gen);
+	reg_mask = src_reg_mask();
 	emit(gen, BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_8, offsetofend(struct bpf_insn, code)));
 	emit(gen, BPF_ALU32_IMM(BPF_AND, BPF_REG_9, reg_mask));
 	emit(gen, BPF_STX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, offsetofend(struct bpf_insn, code)));
@@ -965,94 +931,48 @@ static void cleanup_relos(struct bpf_gen *gen, int insns)
 	cleanup_core_relo(gen);
 }
 
-/* Convert func, line, and core relo info blobs to target endianness */
-static void info_blob_bswap(struct bpf_gen *gen, int func_info, int line_info,
-			    int core_relos, struct bpf_prog_load_opts *load_attr)
-{
-	struct bpf_func_info *fi = gen->data_start + func_info;
-	struct bpf_line_info *li = gen->data_start + line_info;
-	struct bpf_core_relo *cr = gen->data_start + core_relos;
-	int i;
-
-	for (i = 0; i < load_attr->func_info_cnt; i++)
-		bpf_func_info_bswap(fi++);
-
-	for (i = 0; i < load_attr->line_info_cnt; i++)
-		bpf_line_info_bswap(li++);
-
-	for (i = 0; i < gen->core_relo_cnt; i++)
-		bpf_core_relo_bswap(cr++);
-}
-
 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)
 {
-	int func_info_tot_sz = load_attr->func_info_cnt *
-			       load_attr->func_info_rec_size;
-	int line_info_tot_sz = load_attr->line_info_cnt *
-			       load_attr->line_info_rec_size;
-	int core_relo_tot_sz = gen->core_relo_cnt *
-			       sizeof(struct bpf_core_relo);
 	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 progi_idx %d\n",
+		 prog_type, insn_cnt, prog_idx);
 	/* add license string to blob of bytes */
 	license_off = add_data(gen, license, strlen(license) + 1);
 	/* add insns to blob of bytes */
 	insns_off = add_data(gen, insns, insn_cnt * sizeof(struct bpf_insn));
-	pr_debug("gen: prog_load: prog_idx %d type %d insn off %d insns_cnt %zd license off %d\n",
-		 prog_idx, prog_type, insns_off, insn_cnt, license_off);
 
-	/* convert blob insns to target endianness */
+	attr.prog_type = prog_type;
-	if (gen->swapped_endian) {
+	attr.expected_attach_type = load_attr->expected_attach_type;
-		struct bpf_insn *insn = gen->data_start + insns_off;
+	attr.attach_btf_id = load_attr->attach_btf_id;
-		int i;
+	attr.prog_ifindex = load_attr->prog_ifindex;
-
-		for (i = 0; i < insn_cnt; i++, insn++)
-			bpf_insn_bswap(insn);
-	}
-
-	attr.prog_type = tgt_endian(prog_type);
-	attr.expected_attach_type = tgt_endian(load_attr->expected_attach_type);
-	attr.attach_btf_id = tgt_endian(load_attr->attach_btf_id);
-	attr.prog_ifindex = tgt_endian(load_attr->prog_ifindex);
 	attr.kern_version = 0;
-	attr.insn_cnt = tgt_endian((__u32)insn_cnt);
+	attr.insn_cnt = (__u32)insn_cnt;
-	attr.prog_flags = tgt_endian(load_attr->prog_flags);
+	attr.prog_flags = load_attr->prog_flags;
 
-	attr.func_info_rec_size = tgt_endian(load_attr->func_info_rec_size);
+	attr.func_info_rec_size = load_attr->func_info_rec_size;
-	attr.func_info_cnt = tgt_endian(load_attr->func_info_cnt);
+	attr.func_info_cnt = load_attr->func_info_cnt;
-	func_info = add_data(gen, load_attr->func_info, func_info_tot_sz);
+	func_info = add_data(gen, load_attr->func_info,
-	pr_debug("gen: prog_load: func_info: off %d cnt %d rec size %d\n",
+			     attr.func_info_cnt * attr.func_info_rec_size);
-		 func_info, load_attr->func_info_cnt,
-		 load_attr->func_info_rec_size);
 
-	attr.line_info_rec_size = tgt_endian(load_attr->line_info_rec_size);
+	attr.line_info_rec_size = load_attr->line_info_rec_size;
-	attr.line_info_cnt = tgt_endian(load_attr->line_info_cnt);
+	attr.line_info_cnt = load_attr->line_info_cnt;
-	line_info = add_data(gen, load_attr->line_info, line_info_tot_sz);
+	line_info = add_data(gen, load_attr->line_info,
-	pr_debug("gen: prog_load: line_info: off %d cnt %d rec size %d\n",
+			     attr.line_info_cnt * attr.line_info_rec_size);
-		 line_info, load_attr->line_info_cnt,
-		 load_attr->line_info_rec_size);
 
-	attr.core_relo_rec_size = tgt_endian((__u32)sizeof(struct bpf_core_relo));
+	attr.core_relo_rec_size = sizeof(struct bpf_core_relo);
-	attr.core_relo_cnt = tgt_endian(gen->core_relo_cnt);
+	attr.core_relo_cnt = gen->core_relo_cnt;
-	core_relos = add_data(gen, gen->core_relos, core_relo_tot_sz);
+	core_relos = add_data(gen, gen->core_relos,
-	pr_debug("gen: prog_load: core_relos: off %d cnt %d rec size %zd\n",
+			     attr.core_relo_cnt * attr.core_relo_rec_size);
-		 core_relos, gen->core_relo_cnt,
-		 sizeof(struct bpf_core_relo));
-
-	/* convert all info blobs to target endianness */
-	if (gen->swapped_endian)
-		info_blob_bswap(gen, func_info, line_info, core_relos, load_attr);
 
 	libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
 	prog_load_attr = add_data(gen, &attr, attr_size);
-	pr_debug("gen: prog_load: attr: off %d size %d\n",
-		 prog_load_attr, attr_size);
 
 	/* populate union bpf_attr with a pointer to license */
 	emit_rel_store(gen, attr_field(prog_load_attr, license), license_off);
@@ -1120,6 +1040,7 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue,
 	int zero = 0;
 
 	memset(&attr, 0, attr_size);
+	pr_debug("gen: map_update_elem: idx %d\n", map_idx);
 
 	value = add_data(gen, pvalue, value_size);
 	key = add_data(gen, &zero, sizeof(zero));
@@ -1147,8 +1068,6 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue,
 	emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel));
 
 	map_update_attr = add_data(gen, &attr, attr_size);
-	pr_debug("gen: map_update_elem: idx %d, value: off %d size %d, attr: off %d size %d\n",
-		 map_idx, value, value_size, map_update_attr, attr_size);
 	move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4,
 		       blob_fd_array_off(gen, map_idx));
 	emit_rel_store(gen, attr_field(map_update_attr, key), key);
@@ -1165,16 +1084,14 @@ void bpf_gen__populate_outer_map(struct bpf_gen *gen, int outer_map_idx, int slo
 	int attr_size = offsetofend(union bpf_attr, flags);
 	int map_update_attr, key;
 	union bpf_attr attr;
-	int tgt_slot;
 
 	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);
 
-	tgt_slot = tgt_endian(slot);
+	key = add_data(gen, &slot, sizeof(slot));
-	key = add_data(gen, &tgt_slot, sizeof(tgt_slot));
 
 	map_update_attr = add_data(gen, &attr, attr_size);
-	pr_debug("gen: populate_outer_map: outer %d key %d inner %d, attr: off %d size %d\n",
-		 outer_map_idx, slot, inner_map_idx, map_update_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);
@@ -1195,9 +1112,8 @@ void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx)
 	union bpf_attr attr;
 
 	memset(&attr, 0, attr_size);
+	pr_debug("gen: map_freeze: idx %d\n", map_idx);
 	map_freeze_attr = add_data(gen, &attr, attr_size);
-	pr_debug("gen: map_freeze: idx %d, attr: off %d size %d\n",
-		 map_idx, map_freeze_attr, attr_size);
 	move_blob2blob(gen, attr_field(map_freeze_attr, map_fd), 4,
 		       blob_fd_array_off(gen, map_idx));
 	/* emit MAP_FREEZE command */

src/hashmap.h

@@ -166,8 +166,8 @@ bool hashmap_find(const struct hashmap *map, long key, long *value);
  * @bkt: integer used as a bucket loop cursor
  */
 #define hashmap__for_each_entry(map, cur, bkt)				    \
-	for (bkt = 0; bkt < (map)->cap; bkt++)				    \
+	for (bkt = 0; bkt < map->cap; bkt++)				    \
-		for (cur = (map)->buckets[bkt]; cur; cur = cur->next)
+		for (cur = map->buckets[bkt]; cur; cur = cur->next)
 
 /*
  * hashmap__for_each_entry_safe - iterate over all entries in hashmap, safe
@@ -178,8 +178,8 @@ bool hashmap_find(const struct hashmap *map, long key, long *value);
  * @bkt: integer used as a bucket loop cursor
  */
 #define hashmap__for_each_entry_safe(map, cur, tmp, bkt)		    \
-	for (bkt = 0; bkt < (map)->cap; bkt++)				    \
+	for (bkt = 0; bkt < map->cap; bkt++)				    \
-		for (cur = (map)->buckets[bkt];				    \
+		for (cur = map->buckets[bkt];				    \
 		     cur && ({tmp = cur->next; true; });		    \
 		     cur = tmp)
 
@@ -190,19 +190,19 @@ bool hashmap_find(const struct hashmap *map, long key, long *value);
  * @key: key to iterate entries for
  */
 #define hashmap__for_each_key_entry(map, cur, _key)			    \
-	for (cur = (map)->buckets					    \
+	for (cur = map->buckets						    \
-		     ? (map)->buckets[hash_bits((map)->hash_fn((_key), (map)->ctx), (map)->cap_bits)] \
+		     ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
 		     : NULL;						    \
 	     cur;							    \
 	     cur = cur->next)						    \
-		if ((map)->equal_fn(cur->key, (_key), (map)->ctx))
+		if (map->equal_fn(cur->key, (_key), map->ctx))
 
 #define hashmap__for_each_key_entry_safe(map, cur, tmp, _key)		    \
-	for (cur = (map)->buckets					    \
+	for (cur = map->buckets						    \
-		     ? (map)->buckets[hash_bits((map)->hash_fn((_key), (map)->ctx), (map)->cap_bits)] \
+		     ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
 		     : NULL;						    \
 	     cur && ({ tmp = cur->next; true; });			    \
 	     cur = tmp)							    \
-		if ((map)->equal_fn(cur->key, (_key), (map)->ctx))
+		if (map->equal_fn(cur->key, (_key), map->ctx))
 
 #endif /* __LIBBPF_HASHMAP_H */

src/libbpf.h

@@ -98,10 +98,7 @@ typedef int (*libbpf_print_fn_t)(enum libbpf_print_level level,
 
 /**
  * @brief **libbpf_set_print()** sets user-provided log callback function to
- * be used for libbpf warnings and informational messages. If the user callback
+ * be used for libbpf warnings and informational messages.
- * is not set, messages are logged to stderr by default. The verbosity of these
- * messages can be controlled by setting the environment variable
- * LIBBPF_LOG_LEVEL to either warn, info, or debug.
  * @param fn The log print function. If NULL, libbpf won't print anything.
  * @return Pointer to old print function.
  *
@@ -152,7 +149,7 @@ struct bpf_object_open_opts {
 	 * log_buf and log_level settings.
 	 *
 	 * If specified, this log buffer will be passed for:
-	 *   - each BPF progral load (BPF_PROG_LOAD) attempt, unless overridden
+	 *   - each BPF progral load (BPF_PROG_LOAD) attempt, unless overriden
 	 *     with bpf_program__set_log() on per-program level, to get
 	 *     BPF verifier log output.
 	 *   - during BPF object's BTF load into kernel (BPF_BTF_LOAD) to get
@@ -180,29 +177,10 @@ struct bpf_object_open_opts {
 	 * logs through its print callback.
 	 */
 	__u32 kernel_log_level;
-	/* Path to BPF FS mount point to derive BPF token from.
-	 *
-	 * Created BPF token will be used for all bpf() syscall operations
-	 * that accept BPF token (e.g., map creation, BTF and program loads,
-	 * etc) automatically within instantiated BPF object.
-	 *
-	 * If bpf_token_path is not specified, libbpf will consult
-	 * LIBBPF_BPF_TOKEN_PATH environment variable. If set, it will be
-	 * taken as a value of bpf_token_path option and will force libbpf to
-	 * either create BPF token from provided custom BPF FS path, or will
-	 * disable implicit BPF token creation, if envvar value is an empty
-	 * string. bpf_token_path overrides LIBBPF_BPF_TOKEN_PATH, if both are
-	 * set at the same time.
-	 *
-	 * Setting bpf_token_path option to empty string disables libbpf's
-	 * automatic attempt to create BPF token from default BPF FS mount
-	 * point (/sys/fs/bpf), in case this default behavior is undesirable.
-	 */
-	const char *bpf_token_path;
 
 	size_t :0;
 };
-#define bpf_object_open_opts__last_field bpf_token_path
+#define bpf_object_open_opts__last_field kernel_log_level
 
 /**
  * @brief **bpf_object__open()** creates a bpf_object by opening
@@ -241,19 +219,6 @@ LIBBPF_API struct bpf_object *
 bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz,
 		     const struct bpf_object_open_opts *opts);
 
-/**
- * @brief **bpf_object__prepare()** prepares BPF object for loading:
- * performs ELF processing, relocations, prepares final state of BPF program
- * instructions (accessible with bpf_program__insns()), creates and
- * (potentially) pins maps. Leaves BPF object in the state ready for program
- * loading.
- * @param obj Pointer to a valid BPF object instance returned by
- * **bpf_object__open*()** API
- * @return 0, on success; negative error code, otherwise, error code is
- * stored in errno
- */
-int bpf_object__prepare(struct bpf_object *obj);
-
 /**
  * @brief **bpf_object__load()** loads BPF object into kernel.
  * @param obj Pointer to a valid BPF object instance returned by
@@ -301,20 +266,11 @@ LIBBPF_API int bpf_object__pin_programs(struct bpf_object *obj,
 LIBBPF_API int bpf_object__unpin_programs(struct bpf_object *obj,
 					  const char *path);
 LIBBPF_API int bpf_object__pin(struct bpf_object *object, const char *path);
-LIBBPF_API int bpf_object__unpin(struct bpf_object *object, const char *path);
 
 LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj);
 LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj);
 LIBBPF_API int bpf_object__set_kversion(struct bpf_object *obj, __u32 kern_version);
 
-/**
- * @brief **bpf_object__token_fd** is an accessor for BPF token FD associated
- * with BPF object.
- * @param obj Pointer to a valid BPF object
- * @return BPF token FD or -1, if it wasn't set
- */
-LIBBPF_API int bpf_object__token_fd(const struct bpf_object *obj);
-
 struct btf;
 LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj);
 LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj);
@@ -476,7 +432,7 @@ LIBBPF_API int bpf_link__destroy(struct bpf_link *link);
 /**
  * @brief **bpf_program__attach()** is a generic function for attaching
  * a BPF program based on auto-detection of program type, attach type,
- * and extra parameters, where applicable.
+ * and extra paremeters, where applicable.
  *
  * @param prog BPF program to attach
  * @return Reference to the newly created BPF link; or NULL is returned on error,
@@ -563,73 +519,16 @@ struct bpf_kprobe_multi_opts {
 	size_t cnt;
 	/* create return kprobes */
 	bool retprobe;
-	/* create session kprobes */
-	bool session;
-	/* enforce unique match */
-	bool unique_match;
 	size_t :0;
 };
 
-#define bpf_kprobe_multi_opts__last_field unique_match
+#define bpf_kprobe_multi_opts__last_field retprobe
 
 LIBBPF_API struct bpf_link *
 bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
 				      const char *pattern,
 				      const struct bpf_kprobe_multi_opts *opts);
 
-struct bpf_uprobe_multi_opts {
-	/* size of this struct, for forward/backward compatibility */
-	size_t sz;
-	/* array of function symbols to attach to */
-	const char **syms;
-	/* array of function addresses to attach to */
-	const unsigned long *offsets;
-	/* optional, array of associated ref counter offsets */
-	const unsigned long *ref_ctr_offsets;
-	/* optional, array of associated BPF cookies */
-	const __u64 *cookies;
-	/* number of elements in syms/addrs/cookies arrays */
-	size_t cnt;
-	/* create return uprobes */
-	bool retprobe;
-	/* create session kprobes */
-	bool session;
-	size_t :0;
-};
-
-#define bpf_uprobe_multi_opts__last_field session
-
-/**
- * @brief **bpf_program__attach_uprobe_multi()** attaches a BPF program
- * to multiple uprobes with uprobe_multi link.
- *
- * User can specify 2 mutually exclusive set of inputs:
- *
- *   1) use only path/func_pattern/pid arguments
- *
- *   2) use path/pid with allowed combinations of
- *      syms/offsets/ref_ctr_offsets/cookies/cnt
- *
- *      - syms and offsets are mutually exclusive
- *      - ref_ctr_offsets and cookies are optional
- *
- *
- * @param prog BPF program to attach
- * @param pid Process ID to attach the uprobe to, 0 for self (own process),
- * -1 for all processes
- * @param binary_path Path to binary
- * @param func_pattern Regular expression to specify functions to attach
- * BPF program to
- * @param opts Additional options (see **struct bpf_uprobe_multi_opts**)
- * @return 0, on success; negative error code, otherwise
- */
-LIBBPF_API struct bpf_link *
-bpf_program__attach_uprobe_multi(const struct bpf_program *prog,
-				 pid_t pid,
-				 const char *binary_path,
-				 const char *func_pattern,
-				 const struct bpf_uprobe_multi_opts *opts);
-
 struct bpf_ksyscall_opts {
 	/* size of this struct, for forward/backward compatibility */
 	size_t sz;
@@ -704,7 +603,7 @@ struct bpf_uprobe_opts {
 /**
  * @brief **bpf_program__attach_uprobe()** attaches a BPF program
  * to the userspace function which is found by binary path and
- * offset. You can optionally specify a particular process to attach
+ * offset. You can optionally specify a particular proccess to attach
  * to. You can also optionally attach the program to the function
  * exit instead of entry.
  *
@@ -790,20 +689,9 @@ bpf_program__attach_tracepoint_opts(const struct bpf_program *prog,
 				    const char *tp_name,
 				    const struct bpf_tracepoint_opts *opts);
 
-struct bpf_raw_tracepoint_opts {
-	size_t sz; /* size of this struct for forward/backward compatibility */
-	__u64 cookie;
-	size_t :0;
-};
-#define bpf_raw_tracepoint_opts__last_field cookie
-
 LIBBPF_API struct bpf_link *
 bpf_program__attach_raw_tracepoint(const struct bpf_program *prog,
 				   const char *tp_name);
-LIBBPF_API struct bpf_link *
-bpf_program__attach_raw_tracepoint_opts(const struct bpf_program *prog,
-					const char *tp_name,
-					struct bpf_raw_tracepoint_opts *opts);
 
 struct bpf_trace_opts {
 	/* size of this struct, for forward/backward compatibility */
@@ -825,8 +713,6 @@ bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd);
 LIBBPF_API struct bpf_link *
 bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_sockmap(const struct bpf_program *prog, int map_fd);
-LIBBPF_API struct bpf_link *
 bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex);
 LIBBPF_API struct bpf_link *
 bpf_program__attach_freplace(const struct bpf_program *prog,
@@ -847,36 +733,6 @@ LIBBPF_API struct bpf_link *
 bpf_program__attach_netfilter(const struct bpf_program *prog,
 			      const struct bpf_netfilter_opts *opts);
 
-struct bpf_tcx_opts {
-	/* size of this struct, for forward/backward compatibility */
-	size_t sz;
-	__u32 flags;
-	__u32 relative_fd;
-	__u32 relative_id;
-	__u64 expected_revision;
-	size_t :0;
-};
-#define bpf_tcx_opts__last_field expected_revision
-
-LIBBPF_API struct bpf_link *
-bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex,
-			const struct bpf_tcx_opts *opts);
-
-struct bpf_netkit_opts {
-	/* size of this struct, for forward/backward compatibility */
-	size_t sz;
-	__u32 flags;
-	__u32 relative_fd;
-	__u32 relative_id;
-	__u64 expected_revision;
-	size_t :0;
-};
-#define bpf_netkit_opts__last_field expected_revision
-
-LIBBPF_API struct bpf_link *
-bpf_program__attach_netkit(const struct bpf_program *prog, int ifindex,
-			   const struct bpf_netkit_opts *opts);
-
 struct bpf_map;
 
 LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map);
@@ -940,12 +796,6 @@ LIBBPF_API int bpf_program__set_log_level(struct bpf_program *prog, __u32 log_le
 LIBBPF_API const char *bpf_program__log_buf(const struct bpf_program *prog, size_t *log_size);
 LIBBPF_API int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log_size);
 
-LIBBPF_API struct bpf_func_info *bpf_program__func_info(const struct bpf_program *prog);
-LIBBPF_API __u32 bpf_program__func_info_cnt(const struct bpf_program *prog);
-
-LIBBPF_API struct bpf_line_info *bpf_program__line_info(const struct bpf_program *prog);
-LIBBPF_API __u32 bpf_program__line_info_cnt(const struct bpf_program *prog);
-
 /**
  * @brief **bpf_program__set_attach_target()** sets BTF-based attach target
  * for supported BPF program types:
@@ -1009,23 +859,6 @@ bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *map);
 LIBBPF_API int bpf_map__set_autocreate(struct bpf_map *map, bool autocreate);
 LIBBPF_API bool bpf_map__autocreate(const struct bpf_map *map);
 
-/**
- * @brief **bpf_map__set_autoattach()** sets whether libbpf has to auto-attach
- * map during BPF skeleton attach phase.
- * @param map the BPF map instance
- * @param autoattach whether to attach map during BPF skeleton attach phase
- * @return 0 on success; negative error code, otherwise
- */
-LIBBPF_API int bpf_map__set_autoattach(struct bpf_map *map, bool autoattach);
-
-/**
- * @brief **bpf_map__autoattach()** returns whether BPF map is configured to
- * auto-attach during BPF skeleton attach phase.
- * @param map the BPF map instance
- * @return true if map is set to auto-attach during skeleton attach phase; false, otherwise
- */
-LIBBPF_API bool bpf_map__autoattach(const struct bpf_map *map);
-
 /**
  * @brief **bpf_map__fd()** gets the file descriptor of the passed
  * BPF map
@@ -1080,7 +913,7 @@ LIBBPF_API int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra);
 
 LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map,
 					  const void *data, size_t size);
-LIBBPF_API void *bpf_map__initial_value(const struct bpf_map *map, size_t *psize);
+LIBBPF_API void *bpf_map__initial_value(struct bpf_map *map, size_t *psize);
 
 /**
  * @brief **bpf_map__is_internal()** tells the caller whether or not the
@@ -1272,10 +1105,9 @@ struct bpf_xdp_query_opts {
 	__u32 skb_prog_id;	/* output */
 	__u8 attach_mode;	/* output */
 	__u64 feature_flags;	/* output */
-	__u32 xdp_zc_max_segs;	/* output */
 	size_t :0;
 };
-#define bpf_xdp_query_opts__last_field xdp_zc_max_segs
+#define bpf_xdp_query_opts__last_field feature_flags
 
 LIBBPF_API int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags,
 			      const struct bpf_xdp_attach_opts *opts);
@@ -1329,7 +1161,6 @@ LIBBPF_API int bpf_tc_query(const struct bpf_tc_hook *hook,
 
 /* Ring buffer APIs */
 struct ring_buffer;
-struct ring;
 struct user_ring_buffer;
 
 typedef int (*ring_buffer_sample_fn)(void *ctx, void *data, size_t size);
@@ -1348,92 +1179,8 @@ LIBBPF_API int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 				ring_buffer_sample_fn sample_cb, void *ctx);
 LIBBPF_API int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms);
 LIBBPF_API int ring_buffer__consume(struct ring_buffer *rb);
-LIBBPF_API int ring_buffer__consume_n(struct ring_buffer *rb, size_t n);
 LIBBPF_API int ring_buffer__epoll_fd(const struct ring_buffer *rb);
 
-/**
- * @brief **ring_buffer__ring()** returns the ringbuffer object inside a given
- * ringbuffer manager representing a single BPF_MAP_TYPE_RINGBUF map instance.
- *
- * @param rb A ringbuffer manager object.
- * @param idx An index into the ringbuffers contained within the ringbuffer
- * manager object. The index is 0-based and corresponds to the order in which
- * ring_buffer__add was called.
- * @return A ringbuffer object on success; NULL and errno set if the index is
- * invalid.
- */
-LIBBPF_API struct ring *ring_buffer__ring(struct ring_buffer *rb,
-					  unsigned int idx);
-
-/**
- * @brief **ring__consumer_pos()** returns the current consumer position in the
- * given ringbuffer.
- *
- * @param r A ringbuffer object.
- * @return The current consumer position.
- */
-LIBBPF_API unsigned long ring__consumer_pos(const struct ring *r);
-
-/**
- * @brief **ring__producer_pos()** returns the current producer position in the
- * given ringbuffer.
- *
- * @param r A ringbuffer object.
- * @return The current producer position.
- */
-LIBBPF_API unsigned long ring__producer_pos(const struct ring *r);
-
-/**
- * @brief **ring__avail_data_size()** returns the number of bytes in the
- * ringbuffer not yet consumed. This has no locking associated with it, so it
- * can be inaccurate if operations are ongoing while this is called. However, it
- * should still show the correct trend over the long-term.
- *
- * @param r A ringbuffer object.
- * @return The number of bytes not yet consumed.
- */
-LIBBPF_API size_t ring__avail_data_size(const struct ring *r);
-
-/**
- * @brief **ring__size()** returns the total size of the ringbuffer's map data
- * area (excluding special producer/consumer pages). Effectively this gives the
- * amount of usable bytes of data inside the ringbuffer.
- *
- * @param r A ringbuffer object.
- * @return The total size of the ringbuffer map data area.
- */
-LIBBPF_API size_t ring__size(const struct ring *r);
-
-/**
- * @brief **ring__map_fd()** returns the file descriptor underlying the given
- * ringbuffer.
- *
- * @param r A ringbuffer object.
- * @return The underlying ringbuffer file descriptor
- */
-LIBBPF_API int ring__map_fd(const struct ring *r);
-
-/**
- * @brief **ring__consume()** consumes available ringbuffer data without event
- * polling.
- *
- * @param r A ringbuffer object.
- * @return The number of records consumed (or INT_MAX, whichever is less), or
- * a negative number if any of the callbacks return an error.
- */
-LIBBPF_API int ring__consume(struct ring *r);
-
-/**
- * @brief **ring__consume_n()** consumes up to a requested amount of items from
- * a ringbuffer without event polling.
- *
- * @param r A ringbuffer object.
- * @param n Maximum amount of items to consume.
- * @return The number of items consumed, or a negative number if any of the
- * callbacks return an error.
- */
-LIBBPF_API int ring__consume_n(struct ring *r, size_t n);
-
 struct user_ring_buffer_opts {
 	size_t sz; /* size of this struct, for forward/backward compatibility */
 };
@@ -1624,11 +1371,11 @@ LIBBPF_API int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_i
  * memory region of the ring buffer.
  * This ring buffer can be used to implement a custom events consumer.
  * The ring buffer starts with the *struct perf_event_mmap_page*, which
- * holds the ring buffer management fields, when accessing the header
+ * holds the ring buffer managment fields, when accessing the header
  * structure it's important to be SMP aware.
  * You can refer to *perf_event_read_simple* for a simple example.
  * @param pb the perf buffer structure
- * @param buf_idx the buffer index to retrieve
+ * @param buf_idx the buffer index to retreive
  * @param buf (out) gets the base pointer of the mmap()'ed memory
  * @param buf_size (out) gets the size of the mmap()'ed region
  * @return 0 on success, negative error code for failure
@@ -1720,7 +1467,6 @@ struct bpf_map_skeleton {
 	const char *name;
 	struct bpf_map **map;
 	void **mmaped;
-	struct bpf_link **link;
 };
 
 struct bpf_prog_skeleton {
@@ -1817,14 +1563,9 @@ struct bpf_linker_file_opts {
 struct bpf_linker;
 
 LIBBPF_API struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts *opts);
-LIBBPF_API struct bpf_linker *bpf_linker__new_fd(int fd, struct bpf_linker_opts *opts);
 LIBBPF_API int bpf_linker__add_file(struct bpf_linker *linker,
 				    const char *filename,
 				    const struct bpf_linker_file_opts *opts);
-LIBBPF_API int bpf_linker__add_fd(struct bpf_linker *linker, int fd,
-				  const struct bpf_linker_file_opts *opts);
-LIBBPF_API int bpf_linker__add_buf(struct bpf_linker *linker, void *buf, size_t buf_sz,
-				   const struct bpf_linker_file_opts *opts);
 LIBBPF_API int bpf_linker__finalize(struct bpf_linker *linker);
 LIBBPF_API void bpf_linker__free(struct bpf_linker *linker);
 

src/libbpf.map

@@ -245,6 +245,7 @@ LIBBPF_0.3.0 {
 		btf__parse_raw_split;
 		btf__parse_split;
 		btf__new_empty_split;
+		btf__new_split;
 		ring_buffer__epoll_fd;
 } LIBBPF_0.2.0;
 
@@ -325,6 +326,7 @@ LIBBPF_0.7.0 {
 		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;
@@ -393,54 +395,5 @@ LIBBPF_1.2.0 {
 LIBBPF_1.3.0 {
 	global:
 		bpf_obj_pin_opts;
-		bpf_object__unpin;
-		bpf_prog_detach_opts;
 		bpf_program__attach_netfilter;
-		bpf_program__attach_netkit;
-		bpf_program__attach_tcx;
-		bpf_program__attach_uprobe_multi;
-		ring__avail_data_size;
-		ring__consume;
-		ring__consumer_pos;
-		ring__map_fd;
-		ring__producer_pos;
-		ring__size;
-		ring_buffer__ring;
 } LIBBPF_1.2.0;
-
-LIBBPF_1.4.0 {
-	global:
-		bpf_program__attach_raw_tracepoint_opts;
-		bpf_raw_tracepoint_open_opts;
-		bpf_token_create;
-		btf__new_split;
-		btf_ext__raw_data;
-} LIBBPF_1.3.0;
-
-LIBBPF_1.5.0 {
-	global:
-		btf__distill_base;
-		btf__relocate;
-		btf_ext__endianness;
-		btf_ext__set_endianness;
-		bpf_map__autoattach;
-		bpf_map__set_autoattach;
-		bpf_object__token_fd;
-		bpf_program__attach_sockmap;
-		ring__consume_n;
-		ring_buffer__consume_n;
-} LIBBPF_1.4.0;
-
-LIBBPF_1.6.0 {
-	global:
-		bpf_linker__add_buf;
-		bpf_linker__add_fd;
-		bpf_linker__new_fd;
-		bpf_object__prepare;
-		bpf_program__func_info;
-		bpf_program__func_info_cnt;
-		bpf_program__line_info;
-		bpf_program__line_info_cnt;
-		btf__add_decl_attr;
-		btf__add_type_attr;
-} LIBBPF_1.5.0;

src/libbpf_common.h

@@ -70,23 +70,4 @@
 		};							    \
 	})
 
-/* Helper macro to clear and optionally reinitialize libbpf options struct
- *
- * Small helper macro to reset all fields and to reinitialize the common
- * structure size member. Values provided by users in struct initializer-
- * syntax as varargs can be provided as well to reinitialize options struct
- * specific members.
- */
-#define LIBBPF_OPTS_RESET(NAME, ...)					    \
-	do {								    \
-		typeof(NAME) ___##NAME = ({ 				    \
-			memset(&___##NAME, 0, sizeof(NAME));		    \
-			(typeof(NAME)) {				    \
-				.sz = sizeof(NAME),			    \
-				__VA_ARGS__				    \
-			};						    \
-		});							    \
-		memcpy(&NAME, &___##NAME, sizeof(NAME));		    \
-	} while (0)
-
 #endif /* __LIBBPF_LIBBPF_COMMON_H */

src/libbpf_internal.h

@@ -10,30 +10,13 @@
 #define __LIBBPF_LIBBPF_INTERNAL_H
 
 #include <stdlib.h>
-#include <byteswap.h>
 #include <limits.h>
 #include <errno.h>
 #include <linux/err.h>
 #include <fcntl.h>
 #include <unistd.h>
-#include <sys/syscall.h>
-#include <libelf.h>
 #include "relo_core.h"
 
-/* Android's libc doesn't support AT_EACCESS in faccessat() implementation
- * ([0]), and just returns -EINVAL even if file exists and is accessible.
- * See [1] for issues caused by this.
- *
- * So just redefine it to 0 on Android.
- *
- * [0] https://android.googlesource.com/platform/bionic/+/refs/heads/android13-release/libc/bionic/faccessat.cpp#50
- * [1] https://github.com/libbpf/libbpf-bootstrap/issues/250#issuecomment-1911324250
- */
-#ifdef __ANDROID__
-#undef AT_EACCESS
-#define AT_EACCESS 0
-#endif
-
 /* make sure libbpf doesn't use kernel-only integer typedefs */
 #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
 
@@ -235,9 +218,6 @@ struct btf_type;
 struct btf_type *btf_type_by_id(const struct btf *btf, __u32 type_id);
 const char *btf_kind_str(const struct btf_type *t);
 const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id);
-const struct btf_header *btf_header(const struct btf *btf);
-void btf_set_base_btf(struct btf *btf, const struct btf *base_btf);
-int btf_relocate(struct btf *btf, const struct btf *base_btf, __u32 **id_map);
 
 static inline enum btf_func_linkage btf_func_linkage(const struct btf_type *t)
 {
@@ -374,42 +354,18 @@ enum kern_feature_id {
 	FEAT_BTF_ENUM64,
 	/* Kernel uses syscall wrapper (CONFIG_ARCH_HAS_SYSCALL_WRAPPER) */
 	FEAT_SYSCALL_WRAPPER,
-	/* BPF multi-uprobe link support */
-	FEAT_UPROBE_MULTI_LINK,
-	/* Kernel supports arg:ctx tag (__arg_ctx) for global subprogs natively */
-	FEAT_ARG_CTX_TAG,
-	/* Kernel supports '?' at the front of datasec names */
-	FEAT_BTF_QMARK_DATASEC,
 	__FEAT_CNT,
 };
 
-enum kern_feature_result {
+int probe_memcg_account(void);
-	FEAT_UNKNOWN = 0,
-	FEAT_SUPPORTED = 1,
-	FEAT_MISSING = 2,
-};
-
-struct kern_feature_cache {
-	enum kern_feature_result res[__FEAT_CNT];
-	int token_fd;
-};
-
-bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id);
 bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id);
-
-int probe_kern_syscall_wrapper(int token_fd);
-int probe_memcg_account(int token_fd);
 int bump_rlimit_memlock(void);
 
 int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz);
 int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz);
 int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
-			 const char *str_sec, size_t str_len,
+			 const char *str_sec, size_t str_len);
-			 int token_fd);
+int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level);
-int btf_load_into_kernel(struct btf *btf,
-			 char *log_buf, size_t log_sz, __u32 log_level,
-			 int token_fd);
-struct btf *btf_load_from_kernel(__u32 id, struct btf *base_btf, int token_fd);
 
 struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf);
 void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type,
@@ -450,11 +406,11 @@ struct btf_ext_info {
  *
  * The func_info subsection layout:
  *   record size for struct bpf_func_info in the func_info subsection
- *   struct btf_ext_info_sec for section #1
+ *   struct btf_sec_func_info for section #1
  *   a list of bpf_func_info records for section #1
  *     where struct bpf_func_info mimics one in include/uapi/linux/bpf.h
  *     but may not be identical
- *   struct btf_ext_info_sec for section #2
+ *   struct btf_sec_func_info for section #2
  *   a list of bpf_func_info records for section #2
  *   ......
  *
@@ -486,8 +442,6 @@ struct btf_ext {
 		struct btf_ext_header *hdr;
 		void *data;
 	};
-	void *data_swapped;
-	bool swapped_endian;
 	struct btf_ext_info func_info;
 	struct btf_ext_info line_info;
 	struct btf_ext_info core_relo_info;
@@ -515,64 +469,21 @@ struct bpf_line_info_min {
 	__u32	line_col;
 };
 
-/* Functions to byte-swap info records */
-
-typedef void (*info_rec_bswap_fn)(void *);
-
-static inline void bpf_func_info_bswap(struct bpf_func_info *i)
-{
-	i->insn_off = bswap_32(i->insn_off);
-	i->type_id = bswap_32(i->type_id);
-}
-
-static inline void bpf_line_info_bswap(struct bpf_line_info *i)
-{
-	i->insn_off = bswap_32(i->insn_off);
-	i->file_name_off = bswap_32(i->file_name_off);
-	i->line_off = bswap_32(i->line_off);
-	i->line_col = bswap_32(i->line_col);
-}
-
-static inline void bpf_core_relo_bswap(struct bpf_core_relo *i)
-{
-	i->insn_off = bswap_32(i->insn_off);
-	i->type_id = bswap_32(i->type_id);
-	i->access_str_off = bswap_32(i->access_str_off);
-	i->kind = bswap_32(i->kind);
-}
-
-enum btf_field_iter_kind {
-	BTF_FIELD_ITER_IDS,
-	BTF_FIELD_ITER_STRS,
-};
-
-struct btf_field_desc {
-	/* once-per-type offsets */
-	int t_off_cnt, t_offs[2];
-	/* member struct size, or zero, if no members */
-	int m_sz;
-	/* repeated per-member offsets */
-	int m_off_cnt, m_offs[1];
-};
-
-struct btf_field_iter {
-	struct btf_field_desc desc;
-	void *p;
-	int m_idx;
-	int off_idx;
-	int vlen;
-};
-
-int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t, enum btf_field_iter_kind iter_kind);
-__u32 *btf_field_iter_next(struct btf_field_iter *it);
 
 typedef int (*type_id_visit_fn)(__u32 *type_id, void *ctx);
 typedef int (*str_off_visit_fn)(__u32 *str_off, void *ctx);
+int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ctx);
+int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ctx);
 int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx);
 int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void *ctx);
 __s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name,
 				 __u32 kind);
 
+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)
 {
@@ -618,27 +529,6 @@ static inline bool is_ldimm64_insn(struct bpf_insn *insn)
 	return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
 }
 
-static inline void bpf_insn_bswap(struct bpf_insn *insn)
-{
-	__u8 tmp_reg = insn->dst_reg;
-
-	insn->dst_reg = insn->src_reg;
-	insn->src_reg = tmp_reg;
-	insn->off = bswap_16(insn->off);
-	insn->imm = bswap_32(insn->imm);
-}
-
-/* Unconditionally dup FD, ensuring it doesn't use [0, 2] range.
- * Original FD is not closed or altered in any other way.
- * Preserves original FD value, if it's invalid (negative).
- */
-static inline int dup_good_fd(int fd)
-{
-	if (fd < 0)
-		return fd;
-	return fcntl(fd, F_DUPFD_CLOEXEC, 3);
-}
-
 /* if fd is stdin, stdout, or stderr, dup to a fd greater than 2
  * Takes ownership of the fd passed in, and closes it if calling
  * fcntl(fd, F_DUPFD_CLOEXEC, 3).
@@ -650,7 +540,7 @@ static inline int ensure_good_fd(int fd)
 	if (fd < 0)
 		return fd;
 	if (fd < 3) {
-		fd = dup_good_fd(fd);
+		fd = fcntl(fd, F_DUPFD_CLOEXEC, 3);
 		saved_errno = errno;
 		close(old_fd);
 		errno = saved_errno;
@@ -662,34 +552,6 @@ static inline int ensure_good_fd(int fd)
 	return fd;
 }
 
-static inline int sys_dup3(int oldfd, int newfd, int flags)
-{
-	return syscall(__NR_dup3, oldfd, newfd, flags);
-}
-
-/* Some versions of Android don't provide memfd_create() in their libc
- * implementation, so avoid complications and just go straight to Linux
- * syscall.
- */
-static inline int sys_memfd_create(const char *name, unsigned flags)
-{
-	return syscall(__NR_memfd_create, name, flags);
-}
-
-/* Point *fixed_fd* to the same file that *tmp_fd* points to.
- * Regardless of success, *tmp_fd* is closed.
- * Whatever *fixed_fd* pointed to is closed silently.
- */
-static inline int reuse_fd(int fixed_fd, int tmp_fd)
-{
-	int err;
-
-	err = sys_dup3(tmp_fd, fixed_fd, O_CLOEXEC);
-	err = err < 0 ? -errno : 0;
-	close(tmp_fd); /* clean up temporary FD */
-	return err;
-}
-
 /* The following two functions are exposed to bpftool */
 int bpf_core_add_cands(struct bpf_core_cand *local_cand,
 		       size_t local_essent_len,
@@ -715,25 +577,4 @@ static inline bool is_pow_of_2(size_t x)
 #define PROG_LOAD_ATTEMPTS 5
 int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts);
 
-bool glob_match(const char *str, const char *pat);
-
-long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name);
-long elf_find_func_offset_from_file(const char *binary_path, const char *name);
-
-struct elf_fd {
-	Elf *elf;
-	int fd;
-};
-
-int elf_open(const char *binary_path, struct elf_fd *elf_fd);
-void elf_close(struct elf_fd *elf_fd);
-
-int elf_resolve_syms_offsets(const char *binary_path, int cnt,
-			     const char **syms, unsigned long **poffsets,
-			     int st_type);
-int elf_resolve_pattern_offsets(const char *binary_path, const char *pattern,
-				 unsigned long **poffsets, size_t *pcnt);
-
-int probe_fd(int fd);
-
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */

src/libbpf_legacy.h

@@ -76,7 +76,7 @@ enum libbpf_strict_mode {
 	 * 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 overridden with libbpf_set_memlock_rlim() API.
+	 * 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.
@@ -97,7 +97,7 @@ 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 occurred
+ * @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

src/libbpf_probes.c

@@ -74,6 +74,10 @@ static __u32 get_debian_kernel_version(struct utsname *info)
 	if (sscanf(p, "Debian %u.%u.%u", &major, &minor, &patch) != 3)
 		return 0;
 
+	// Patch to run on Debian 10
+	if (major == 4 && minor == 19 && patch > 255)
+                return KERNEL_VERSION(major, minor, 255);
+
 	return KERNEL_VERSION(major, minor, patch);
 }
 
@@ -219,8 +223,7 @@ int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts)
 }
 
 int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
-			 const char *str_sec, size_t str_len,
+			 const char *str_sec, size_t str_len)
-			 int token_fd)
 {
 	struct btf_header hdr = {
 		.magic = BTF_MAGIC,
@@ -230,10 +233,6 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
 		.str_off = types_len,
 		.str_len = str_len,
 	};
-	LIBBPF_OPTS(bpf_btf_load_opts, opts,
-		.token_fd = token_fd,
-		.btf_flags = token_fd ? BPF_F_TOKEN_FD : 0,
-	);
 	int btf_fd, btf_len;
 	__u8 *raw_btf;
 
@@ -246,7 +245,7 @@ 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_btf_load(raw_btf, btf_len, &opts);
+	btf_fd = bpf_btf_load(raw_btf, btf_len, NULL);
 
 	free(raw_btf);
 	return btf_fd;
@@ -276,7 +275,7 @@ static int load_local_storage_btf(void)
 	};
 
 	return libbpf__load_raw_btf((char *)types, sizeof(types),
-				     strs, sizeof(strs), 0);
+				     strs, sizeof(strs));
 }
 
 static int probe_map_create(enum bpf_map_type map_type)
@@ -331,20 +330,12 @@ static int probe_map_create(enum bpf_map_type map_type)
 	case BPF_MAP_TYPE_STRUCT_OPS:
 		/* we'll get -ENOTSUPP for invalid BTF type ID for struct_ops */
 		opts.btf_vmlinux_value_type_id = 1;
-		opts.value_type_btf_obj_fd = -1;
 		exp_err = -524; /* -ENOTSUPP */
 		break;
 	case BPF_MAP_TYPE_BLOOM_FILTER:
 		key_size = 0;
 		max_entries = 1;
 		break;
-	case BPF_MAP_TYPE_ARENA:
-		key_size	= 0;
-		value_size	= 0;
-		max_entries	= 1; /* one page */
-		opts.map_extra	= 0; /* can mmap() at any address */
-		opts.map_flags	= BPF_F_MMAPABLE;
-		break;
 	case BPF_MAP_TYPE_HASH:
 	case BPF_MAP_TYPE_ARRAY:
 	case BPF_MAP_TYPE_PROG_ARRAY:
@@ -448,8 +439,7 @@ int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, enum bpf_func_id helpe
 	/* 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"
+	 * given BPF program type, it will emit "unknown func bpf_sys_bpf#166".
-	 * or "program of this type cannot use helper bpf_sys_bpf#166".
 	 * In both cases, provided combination of BPF program type and BPF
 	 * helper is not supported by the kernel.
 	 * In all other cases, probe_prog_load() above will either succeed (e.g.,
@@ -458,8 +448,7 @@ int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, enum bpf_func_id helpe
 	 * 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 ") ||
+	if (ret == 0 && (strstr(buf, "invalid func ") || strstr(buf, "unknown func ")))
-			 strstr(buf, "program of this type cannot use helper ")))
 		return 0;
 	return 1; /* assume supported */
 }

src/libbpf_version.h

@@ -4,6 +4,6 @@
 #define __LIBBPF_VERSION_H
 
 #define LIBBPF_MAJOR_VERSION 1
-#define LIBBPF_MINOR_VERSION 6
+#define LIBBPF_MINOR_VERSION 3
 
 #endif /* __LIBBPF_VERSION_H */

src/linker.c

@@ -4,10 +4,6 @@
  *
  * Copyright (c) 2021 Facebook
  */
-#ifndef _GNU_SOURCE
-#define _GNU_SOURCE
-#endif
-
 #include <stdbool.h>
 #include <stddef.h>
 #include <stdio.h>
@@ -20,12 +16,10 @@
 #include <elf.h>
 #include <libelf.h>
 #include <fcntl.h>
-#include <sys/mman.h>
 #include "libbpf.h"
 #include "btf.h"
 #include "libbpf_internal.h"
 #include "strset.h"
-#include "str_error.h"
 
 #define BTF_EXTERN_SEC ".extern"
 
@@ -141,7 +135,6 @@ struct bpf_linker {
 	int fd;
 	Elf *elf;
 	Elf64_Ehdr *elf_hdr;
-	bool swapped_endian;
 
 	/* Output sections metadata */
 	struct dst_sec *secs;
@@ -157,19 +150,15 @@ struct bpf_linker {
 	/* global (including extern) ELF symbols */
 	int glob_sym_cnt;
 	struct glob_sym *glob_syms;
-
-	bool fd_is_owned;
 };
 
 #define pr_warn_elf(fmt, ...)									\
 	libbpf_print(LIBBPF_WARN, "libbpf: " fmt ": %s\n", ##__VA_ARGS__, elf_errmsg(-1))
 
-static int init_output_elf(struct bpf_linker *linker);
+static int init_output_elf(struct bpf_linker *linker, const char *file);
 
-static int bpf_linker_add_file(struct bpf_linker *linker, int fd,
+static int linker_load_obj_file(struct bpf_linker *linker, const char *filename,
-			       const char *filename);
+				const struct bpf_linker_file_opts *opts,
-
-static int linker_load_obj_file(struct bpf_linker *linker,
 				struct src_obj *obj);
 static int linker_sanity_check_elf(struct src_obj *obj);
 static int linker_sanity_check_elf_symtab(struct src_obj *obj, struct src_sec *sec);
@@ -200,7 +189,7 @@ void bpf_linker__free(struct bpf_linker *linker)
 	if (linker->elf)
 		elf_end(linker->elf);
 
-	if (linker->fd >= 0 && linker->fd_is_owned)
+	if (linker->fd >= 0)
 		close(linker->fd);
 
 	strset__free(linker->strtab_strs);
@@ -242,63 +231,9 @@ struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts
 	if (!linker)
 		return errno = ENOMEM, NULL;
 
-	linker->filename = strdup(filename);
+	linker->fd = -1;
-	if (!linker->filename) {
-		err = -ENOMEM;
-		goto err_out;
-	}
 
-	linker->fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644);
+	err = init_output_elf(linker, filename);
-	if (linker->fd < 0) {
-		err = -errno;
-		pr_warn("failed to create '%s': %d\n", filename, err);
-		goto err_out;
-	}
-	linker->fd_is_owned = true;
-
-	err = init_output_elf(linker);
-	if (err)
-		goto err_out;
-
-	return linker;
-
-err_out:
-	bpf_linker__free(linker);
-	return errno = -err, NULL;
-}
-
-struct bpf_linker *bpf_linker__new_fd(int fd, struct bpf_linker_opts *opts)
-{
-	struct bpf_linker *linker;
-	char filename[32];
-	int err;
-
-	if (fd < 0)
-		return errno = EINVAL, NULL;
-
-	if (!OPTS_VALID(opts, bpf_linker_opts))
-		return errno = EINVAL, NULL;
-
-	if (elf_version(EV_CURRENT) == EV_NONE) {
-		pr_warn_elf("libelf initialization failed");
-		return errno = EINVAL, NULL;
-	}
-
-	linker = calloc(1, sizeof(*linker));
-	if (!linker)
-		return errno = ENOMEM, NULL;
-
-	snprintf(filename, sizeof(filename), "fd:%d", fd);
-	linker->filename = strdup(filename);
-	if (!linker->filename) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-
-	linker->fd = fd;
-	linker->fd_is_owned = false;
-
-	err = init_output_elf(linker);
 	if (err)
 		goto err_out;
 
@@ -357,12 +292,23 @@ static Elf64_Sym *add_new_sym(struct bpf_linker *linker, size_t *sym_idx)
 	return sym;
 }
 
-static int init_output_elf(struct bpf_linker *linker)
+static int init_output_elf(struct bpf_linker *linker, const char *file)
 {
 	int err, str_off;
 	Elf64_Sym *init_sym;
 	struct dst_sec *sec;
 
+	linker->filename = strdup(file);
+	if (!linker->filename)
+		return -ENOMEM;
+
+	linker->fd = open(file, O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644);
+	if (linker->fd < 0) {
+		err = -errno;
+		pr_warn("failed to create '%s': %d\n", file, err);
+		return err;
+	}
+
 	linker->elf = elf_begin(linker->fd, ELF_C_WRITE, NULL);
 	if (!linker->elf) {
 		pr_warn_elf("failed to create ELF object");
@@ -378,8 +324,13 @@ static int init_output_elf(struct bpf_linker *linker)
 
 	linker->elf_hdr->e_machine = EM_BPF;
 	linker->elf_hdr->e_type = ET_REL;
-	/* Set unknown ELF endianness, assign later from input files */
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
-	linker->elf_hdr->e_ident[EI_DATA] = ELFDATANONE;
+	linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2LSB;
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+	linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2MSB;
+#else
+#error "Unknown __BYTE_ORDER__"
+#endif
 
 	/* STRTAB */
 	/* initialize strset with an empty string to conform to ELF */
@@ -445,8 +396,6 @@ static int init_output_elf(struct bpf_linker *linker)
 		pr_warn_elf("failed to create SYMTAB data");
 		return -EINVAL;
 	}
-	/* Ensure libelf translates byte-order of symbol records */
-	sec->data->d_type = ELF_T_SYM;
 
 	str_off = strset__add_str(linker->strtab_strs, sec->sec_name);
 	if (str_off < 0)
@@ -488,16 +437,19 @@ static int init_output_elf(struct bpf_linker *linker)
 	return 0;
 }
 
-static int bpf_linker_add_file(struct bpf_linker *linker, int fd,
+int bpf_linker__add_file(struct bpf_linker *linker, const char *filename,
-			       const char *filename)
+			 const struct bpf_linker_file_opts *opts)
 {
 	struct src_obj obj = {};
 	int err = 0;
 
-	obj.filename = filename;
+	if (!OPTS_VALID(opts, bpf_linker_file_opts))
-	obj.fd = fd;
+		return libbpf_err(-EINVAL);
 
-	err = err ?: linker_load_obj_file(linker, &obj);
+	if (!linker->elf)
+		return libbpf_err(-EINVAL);
+
+	err = err ?: linker_load_obj_file(linker, filename, opts, &obj);
 	err = err ?: linker_append_sec_data(linker, &obj);
 	err = err ?: linker_append_elf_syms(linker, &obj);
 	err = err ?: linker_append_elf_relos(linker, &obj);
@@ -512,91 +464,12 @@ static int bpf_linker_add_file(struct bpf_linker *linker, int fd,
 	free(obj.sym_map);
 	if (obj.elf)
 		elf_end(obj.elf);
+	if (obj.fd >= 0)
+		close(obj.fd);
 
-	return err;
-}
-
-int bpf_linker__add_file(struct bpf_linker *linker, const char *filename,
-			 const struct bpf_linker_file_opts *opts)
-{
-	int fd, err;
-
-	if (!OPTS_VALID(opts, bpf_linker_file_opts))
-		return libbpf_err(-EINVAL);
-
-	if (!linker->elf)
-		return libbpf_err(-EINVAL);
-
-	fd = open(filename, O_RDONLY | O_CLOEXEC);
-	if (fd < 0) {
-		err = -errno;
-		pr_warn("failed to open file '%s': %s\n", filename, errstr(err));
-		return libbpf_err(err);
-	}
-
-	err = bpf_linker_add_file(linker, fd, filename);
-	close(fd);
 	return libbpf_err(err);
 }
 
-int bpf_linker__add_fd(struct bpf_linker *linker, int fd,
-		       const struct bpf_linker_file_opts *opts)
-{
-	char filename[32];
-	int err;
-
-	if (!OPTS_VALID(opts, bpf_linker_file_opts))
-		return libbpf_err(-EINVAL);
-
-	if (!linker->elf)
-		return libbpf_err(-EINVAL);
-
-	if (fd < 0)
-		return libbpf_err(-EINVAL);
-
-	snprintf(filename, sizeof(filename), "fd:%d", fd);
-	err = bpf_linker_add_file(linker, fd, filename);
-	return libbpf_err(err);
-}
-
-int bpf_linker__add_buf(struct bpf_linker *linker, void *buf, size_t buf_sz,
-			const struct bpf_linker_file_opts *opts)
-{
-	char filename[32];
-	int fd, written, ret;
-
-	if (!OPTS_VALID(opts, bpf_linker_file_opts))
-		return libbpf_err(-EINVAL);
-
-	if (!linker->elf)
-		return libbpf_err(-EINVAL);
-
-	snprintf(filename, sizeof(filename), "mem:%p+%zu", buf, buf_sz);
-
-	fd = sys_memfd_create(filename, 0);
-	if (fd < 0) {
-		ret = -errno;
-		pr_warn("failed to create memfd '%s': %s\n", filename, errstr(ret));
-		return libbpf_err(ret);
-	}
-
-	written = 0;
-	while (written < buf_sz) {
-		ret = write(fd, buf, buf_sz);
-		if (ret < 0) {
-			ret = -errno;
-			pr_warn("failed to write '%s': %s\n", filename, errstr(ret));
-			goto err_out;
-		}
-		written += ret;
-	}
-
-	ret = bpf_linker_add_file(linker, fd, filename);
-err_out:
-	close(fd);
-	return libbpf_err(ret);
-}
-
 static bool is_dwarf_sec_name(const char *name)
 {
 	/* approximation, but the actual list is too long */
@@ -662,69 +535,65 @@ static struct src_sec *add_src_sec(struct src_obj *obj, const char *sec_name)
 	return sec;
 }
 
-static int linker_load_obj_file(struct bpf_linker *linker,
+static int linker_load_obj_file(struct bpf_linker *linker, const char *filename,
+				const struct bpf_linker_file_opts *opts,
 				struct src_obj *obj)
 {
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	const int host_endianness = ELFDATA2LSB;
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+	const int host_endianness = ELFDATA2MSB;
+#else
+#error "Unknown __BYTE_ORDER__"
+#endif
 	int err = 0;
 	Elf_Scn *scn;
 	Elf_Data *data;
 	Elf64_Ehdr *ehdr;
 	Elf64_Shdr *shdr;
 	struct src_sec *sec;
-	unsigned char obj_byteorder;
-	unsigned char link_byteorder = linker->elf_hdr->e_ident[EI_DATA];
-#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
-	const unsigned char host_byteorder = ELFDATA2LSB;
-#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
-	const unsigned char host_byteorder = ELFDATA2MSB;
-#else
-#error "Unknown __BYTE_ORDER__"
-#endif
 
-	pr_debug("linker: adding object file '%s'...\n", obj->filename);
+	pr_debug("linker: adding object file '%s'...\n", filename);
 
+	obj->filename = filename;
+
+	obj->fd = open(filename, O_RDONLY | O_CLOEXEC);
+	if (obj->fd < 0) {
+		err = -errno;
+		pr_warn("failed to open file '%s': %d\n", filename, err);
+		return err;
+	}
 	obj->elf = elf_begin(obj->fd, ELF_C_READ_MMAP, NULL);
 	if (!obj->elf) {
-		pr_warn_elf("failed to parse ELF file '%s'", obj->filename);
+		err = -errno;
-		return -EINVAL;
+		pr_warn_elf("failed to parse ELF file '%s'", filename);
+		return err;
 	}
 
 	/* Sanity check ELF file high-level properties */
 	ehdr = elf64_getehdr(obj->elf);
 	if (!ehdr) {
-		pr_warn_elf("failed to get ELF header for %s", obj->filename);
+		err = -errno;
-		return -EINVAL;
+		pr_warn_elf("failed to get ELF header for %s", filename);
-	}
-
-	/* Linker output endianness set by first input object */
-	obj_byteorder = ehdr->e_ident[EI_DATA];
-	if (obj_byteorder != ELFDATA2LSB && obj_byteorder != ELFDATA2MSB) {
-		err = -EOPNOTSUPP;
-		pr_warn("unknown byte order of ELF file %s\n", obj->filename);
 		return err;
 	}
-	if (link_byteorder == ELFDATANONE) {
+	if (ehdr->e_ident[EI_DATA] != host_endianness) {
-		linker->elf_hdr->e_ident[EI_DATA] = obj_byteorder;
-		linker->swapped_endian = obj_byteorder != host_byteorder;
-		pr_debug("linker: set %s-endian output byte order\n",
-			 obj_byteorder == ELFDATA2MSB ? "big" : "little");
-	} else if (link_byteorder != obj_byteorder) {
 		err = -EOPNOTSUPP;
-		pr_warn("byte order mismatch with ELF file %s\n", obj->filename);
+		pr_warn_elf("unsupported byte order of ELF file %s", filename);
 		return err;
 	}
-
 	if (ehdr->e_type != ET_REL
 	    || ehdr->e_machine != EM_BPF
 	    || ehdr->e_ident[EI_CLASS] != ELFCLASS64) {
 		err = -EOPNOTSUPP;
-		pr_warn_elf("unsupported kind of ELF file %s", obj->filename);
+		pr_warn_elf("unsupported kind of ELF file %s", filename);
 		return err;
 	}
 
 	if (elf_getshdrstrndx(obj->elf, &obj->shstrs_sec_idx)) {
-		pr_warn_elf("failed to get SHSTRTAB section index for %s", obj->filename);
+		err = -errno;
-		return -EINVAL;
+		pr_warn_elf("failed to get SHSTRTAB section index for %s", filename);
+		return err;
 	}
 
 	scn = NULL;
@@ -734,23 +603,26 @@ static int linker_load_obj_file(struct bpf_linker *linker,
 
 		shdr = elf64_getshdr(scn);
 		if (!shdr) {
+			err = -errno;
 			pr_warn_elf("failed to get section #%zu header for %s",
-				    sec_idx, obj->filename);
+				    sec_idx, filename);
-			return -EINVAL;
+			return err;
 		}
 
 		sec_name = elf_strptr(obj->elf, obj->shstrs_sec_idx, shdr->sh_name);
 		if (!sec_name) {
+			err = -errno;
 			pr_warn_elf("failed to get section #%zu name for %s",
-				    sec_idx, obj->filename);
+				    sec_idx, filename);
-			return -EINVAL;
+			return err;
 		}
 
 		data = elf_getdata(scn, 0);
 		if (!data) {
+			err = -errno;
 			pr_warn_elf("failed to get section #%zu (%s) data from %s",
-				    sec_idx, sec_name, obj->filename);
+				    sec_idx, sec_name, filename);
-			return -EINVAL;
+			return err;
 		}
 
 		sec = add_src_sec(obj, sec_name);
@@ -784,8 +656,7 @@ static int linker_load_obj_file(struct bpf_linker *linker,
 				obj->btf = btf__new(data->d_buf, shdr->sh_size);
 				err = libbpf_get_error(obj->btf);
 				if (err) {
-					pr_warn("failed to parse .BTF from %s: %s\n",
+					pr_warn("failed to parse .BTF from %s: %d\n", filename, err);
-						obj->filename, errstr(err));
 					return err;
 				}
 				sec->skipped = true;
@@ -795,8 +666,7 @@ static int linker_load_obj_file(struct bpf_linker *linker,
 				obj->btf_ext = btf_ext__new(data->d_buf, shdr->sh_size);
 				err = libbpf_get_error(obj->btf_ext);
 				if (err) {
-					pr_warn("failed to parse .BTF.ext from '%s': %s\n",
+					pr_warn("failed to parse .BTF.ext from '%s': %d\n", filename, err);
-						obj->filename, errstr(err));
 					return err;
 				}
 				sec->skipped = true;
@@ -813,7 +683,7 @@ static int linker_load_obj_file(struct bpf_linker *linker,
 			break;
 		default:
 			pr_warn("unrecognized section #%zu (%s) in %s\n",
-				sec_idx, sec_name, obj->filename);
+				sec_idx, sec_name, filename);
 			err = -EINVAL;
 			return err;
 		}
@@ -849,28 +719,13 @@ static int linker_sanity_check_elf(struct src_obj *obj)
 			return -EINVAL;
 		}
 
-		if (is_dwarf_sec_name(sec->sec_name))
+		if (sec->shdr->sh_addralign && !is_pow_of_2(sec->shdr->sh_addralign))
-			continue;
+			return -EINVAL;
+		if (sec->shdr->sh_addralign != sec->data->d_align)
+			return -EINVAL;
 
-		if (sec->shdr->sh_addralign && !is_pow_of_2(sec->shdr->sh_addralign)) {
+		if (sec->shdr->sh_size != sec->data->d_size)
-			pr_warn("ELF section #%zu alignment %llu is non pow-of-2 alignment in %s\n",
-				sec->sec_idx, (long long unsigned)sec->shdr->sh_addralign,
-				obj->filename);
 			return -EINVAL;
-		}
-		if (sec->shdr->sh_addralign != sec->data->d_align) {
-			pr_warn("ELF section #%zu has inconsistent alignment addr=%llu != d=%llu in %s\n",
-				sec->sec_idx, (long long unsigned)sec->shdr->sh_addralign,
-				(long long unsigned)sec->data->d_align, obj->filename);
-			return -EINVAL;
-		}
-
-		if (sec->shdr->sh_size != sec->data->d_size) {
-			pr_warn("ELF section #%zu has inconsistent section size sh=%llu != d=%llu in %s\n",
-				sec->sec_idx, (long long unsigned)sec->shdr->sh_size,
-				(long long unsigned)sec->data->d_size, obj->filename);
-			return -EINVAL;
-		}
 
 		switch (sec->shdr->sh_type) {
 		case SHT_SYMTAB:
@@ -882,12 +737,8 @@ static int linker_sanity_check_elf(struct src_obj *obj)
 			break;
 		case SHT_PROGBITS:
 			if (sec->shdr->sh_flags & SHF_EXECINSTR) {
-				if (sec->shdr->sh_size % sizeof(struct bpf_insn) != 0) {
+				if (sec->shdr->sh_size % sizeof(struct bpf_insn) != 0)
-					pr_warn("ELF section #%zu has unexpected size alignment %llu in %s\n",
-						sec->sec_idx, (long long unsigned)sec->shdr->sh_size,
-						obj->filename);
 					return -EINVAL;
-				}
 			}
 			break;
 		case SHT_NOBITS:
@@ -1087,33 +938,19 @@ static int check_btf_str_off(__u32 *str_off, void *ctx)
 static int linker_sanity_check_btf(struct src_obj *obj)
 {
 	struct btf_type *t;
-	int i, n, err;
+	int i, n, err = 0;
 
 	if (!obj->btf)
 		return 0;
 
 	n = btf__type_cnt(obj->btf);
 	for (i = 1; i < n; i++) {
-		struct btf_field_iter it;
-		__u32 *type_id, *str_off;
-
 		t = btf_type_by_id(obj->btf, i);
 
-		err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS);
+		err = err ?: btf_type_visit_type_ids(t, check_btf_type_id, obj->btf);
+		err = err ?: btf_type_visit_str_offs(t, check_btf_str_off, obj->btf);
 		if (err)
 			return err;
-		while ((type_id = btf_field_iter_next(&it))) {
-			if (*type_id >= n)
-				return -EINVAL;
-		}
-
-		err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_STRS);
-		if (err)
-			return err;
-		while ((str_off = btf_field_iter_next(&it))) {
-			if (!btf__str_by_offset(obj->btf, *str_off))
-				return -EINVAL;
-		}
 	}
 
 	return 0;
@@ -1239,24 +1076,6 @@ static bool sec_content_is_same(struct dst_sec *dst_sec, struct src_sec *src_sec
 	return true;
 }
 
-static bool is_exec_sec(struct dst_sec *sec)
-{
-	if (!sec || sec->ephemeral)
-		return false;
-	return (sec->shdr->sh_type == SHT_PROGBITS) &&
-	       (sec->shdr->sh_flags & SHF_EXECINSTR);
-}
-
-static void exec_sec_bswap(void *raw_data, int size)
-{
-	const int insn_cnt = size / sizeof(struct bpf_insn);
-	struct bpf_insn *insn = raw_data;
-	int i;
-
-	for (i = 0; i < insn_cnt; i++, insn++)
-		bpf_insn_bswap(insn);
-}
-
 static int extend_sec(struct bpf_linker *linker, struct dst_sec *dst, struct src_sec *src)
 {
 	void *tmp;
@@ -1316,10 +1135,6 @@ static int extend_sec(struct bpf_linker *linker, struct dst_sec *dst, struct src
 		memset(dst->raw_data + dst->sec_sz, 0, dst_align_sz - dst->sec_sz);
 		/* now copy src data at a properly aligned offset */
 		memcpy(dst->raw_data + dst_align_sz, src->data->d_buf, src->shdr->sh_size);
-
-		/* convert added bpf insns to native byte-order */
-		if (linker->swapped_endian && is_exec_sec(dst))
-			exec_sec_bswap(dst->raw_data + dst_align_sz, src->shdr->sh_size);
 	}
 
 	dst->sec_sz = dst_final_sz;
@@ -1376,7 +1191,7 @@ static int linker_append_sec_data(struct bpf_linker *linker, struct src_obj *obj
 		} else {
 			if (!secs_match(dst_sec, src_sec)) {
 				pr_warn("ELF sections %s are incompatible\n", src_sec->sec_name);
-				return -EINVAL;
+				return -1;
 			}
 
 			/* "license" and "version" sections are deduped */
@@ -1565,7 +1380,7 @@ recur:
 		return true;
 	case BTF_KIND_PTR:
 		/* just validate overall shape of the referenced type, so no
-		 * contents comparison for struct/union, and allowed fwd vs
+		 * contents comparison for struct/union, and allowd fwd vs
 		 * struct/union
 		 */
 		exact = false;
@@ -2114,7 +1929,7 @@ static int linker_append_elf_sym(struct bpf_linker *linker, struct src_obj *obj,
 
 		/* If existing symbol is a strong resolved symbol, bail out,
 		 * because we lost resolution battle have nothing to
-		 * contribute. We already checked above that there is no
+		 * contribute. We already checked abover that there is no
 		 * strong-strong conflict. We also already tightened binding
 		 * and visibility, so nothing else to contribute at that point.
 		 */
@@ -2163,7 +1978,7 @@ add_sym:
 
 	obj->sym_map[src_sym_idx] = dst_sym_idx;
 
-	if (sym_type == STT_SECTION && dst_sec) {
+	if (sym_type == STT_SECTION && dst_sym) {
 		dst_sec->sec_sym_idx = dst_sym_idx;
 		dst_sym->st_value = 0;
 	}
@@ -2223,7 +2038,7 @@ static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *ob
 			}
 		} else if (!secs_match(dst_sec, src_sec)) {
 			pr_warn("sections %s are not compatible\n", src_sec->sec_name);
-			return -EINVAL;
+			return -1;
 		}
 
 		/* shdr->sh_link points to SYMTAB */
@@ -2379,17 +2194,10 @@ static int linker_fixup_btf(struct src_obj *obj)
 		vi = btf_var_secinfos(t);
 		for (j = 0, m = btf_vlen(t); j < m; j++, vi++) {
 			const struct btf_type *vt = btf__type_by_id(obj->btf, vi->type);
-			const char *var_name;
+			const char *var_name = btf__str_by_offset(obj->btf, vt->name_off);
-			int var_linkage;
+			int var_linkage = btf_var(vt)->linkage;
 			Elf64_Sym *sym;
 
-			/* could be a variable or function */
-			if (!btf_is_var(vt))
-				continue;
-
-			var_name = btf__str_by_offset(obj->btf, vt->name_off);
-			var_linkage = btf_var(vt)->linkage;
-
 			/* no need to patch up static or extern vars */
 			if (var_linkage != BTF_VAR_GLOBAL_ALLOCATED)
 				continue;
@@ -2407,10 +2215,26 @@ static int linker_fixup_btf(struct src_obj *obj)
 	return 0;
 }
 
+static int remap_type_id(__u32 *type_id, void *ctx)
+{
+	int *id_map = ctx;
+	int new_id = id_map[*type_id];
+
+	/* Error out if the type wasn't remapped. Ignore VOID which stays VOID. */
+	if (new_id == 0 && *type_id != 0) {
+		pr_warn("failed to find new ID mapping for original BTF type ID %u\n", *type_id);
+		return -EINVAL;
+	}
+
+	*type_id = id_map[*type_id];
+
+	return 0;
+}
+
 static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
 {
 	const struct btf_type *t;
-	int i, j, n, start_id, id, err;
+	int i, j, n, start_id, id;
 	const char *name;
 
 	if (!obj->btf)
@@ -2481,25 +2305,9 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
 	n = btf__type_cnt(linker->btf);
 	for (i = start_id; i < n; i++) {
 		struct btf_type *dst_t = btf_type_by_id(linker->btf, i);
-		struct btf_field_iter it;
-		__u32 *type_id;
 
-		err = btf_field_iter_init(&it, dst_t, BTF_FIELD_ITER_IDS);
+		if (btf_type_visit_type_ids(dst_t, remap_type_id, obj->btf_type_map))
-		if (err)
+			return -EINVAL;
-			return err;
-
-		while ((type_id = btf_field_iter_next(&it))) {
-			int new_id = obj->btf_type_map[*type_id];
-
-			/* Error out if the type wasn't remapped. Ignore VOID which stays VOID. */
-			if (new_id == 0 && *type_id != 0) {
-				pr_warn("failed to find new ID mapping for original BTF type ID %u\n",
-					*type_id);
-				return -EINVAL;
-			}
-
-			*type_id = obj->btf_type_map[*type_id];
-		}
 	}
 
 	/* Rewrite VAR/FUNC underlying types (i.e., FUNC's FUNC_PROTO and VAR's
@@ -2567,10 +2375,6 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
 			if (glob_sym && glob_sym->var_idx >= 0) {
 				__s64 sz;
 
-				/* FUNCs don't have size, nothing to update */
-				if (btf_is_func(t))
-					continue;
-
 				dst_var = &dst_sec->sec_vars[glob_sym->var_idx];
 				/* Because underlying BTF type might have
 				 * changed, so might its size have changed, so
@@ -2784,32 +2588,27 @@ int bpf_linker__finalize(struct bpf_linker *linker)
 		if (!sec->scn)
 			continue;
 
-		/* restore sections with bpf insns to target byte-order */
-		if (linker->swapped_endian && is_exec_sec(sec))
-			exec_sec_bswap(sec->raw_data, sec->sec_sz);
-
 		sec->data->d_buf = sec->raw_data;
 	}
 
 	/* Finalize ELF layout */
 	if (elf_update(linker->elf, ELF_C_NULL) < 0) {
-		err = -EINVAL;
+		err = -errno;
 		pr_warn_elf("failed to finalize ELF layout");
 		return libbpf_err(err);
 	}
 
 	/* Write out final ELF contents */
 	if (elf_update(linker->elf, ELF_C_WRITE) < 0) {
-		err = -EINVAL;
+		err = -errno;
 		pr_warn_elf("failed to write ELF contents");
 		return libbpf_err(err);
 	}
 
 	elf_end(linker->elf);
-	linker->elf = NULL;
+	close(linker->fd);
 
-	if (linker->fd_is_owned)
+	linker->elf = NULL;
-		close(linker->fd);
 	linker->fd = -1;
 
 	return 0;
@@ -2857,7 +2656,6 @@ static int emit_elf_data_sec(struct bpf_linker *linker, const char *sec_name,
 
 static int finalize_btf(struct bpf_linker *linker)
 {
-	enum btf_endianness link_endianness;
 	LIBBPF_OPTS(btf_dedup_opts, opts);
 	struct btf *btf = linker->btf;
 	const void *raw_data;
@@ -2891,24 +2689,17 @@ static int finalize_btf(struct bpf_linker *linker)
 
 	err = finalize_btf_ext(linker);
 	if (err) {
-		pr_warn(".BTF.ext generation failed: %s\n", errstr(err));
+		pr_warn(".BTF.ext generation failed: %d\n", err);
 		return err;
 	}
 
 	opts.btf_ext = linker->btf_ext;
 	err = btf__dedup(linker->btf, &opts);
 	if (err) {
-		pr_warn("BTF dedup failed: %s\n", errstr(err));
+		pr_warn("BTF dedup failed: %d\n", err);
 		return err;
 	}
 
-	/* Set .BTF and .BTF.ext output byte order */
-	link_endianness = linker->elf_hdr->e_ident[EI_DATA] == ELFDATA2MSB ?
-			  BTF_BIG_ENDIAN : BTF_LITTLE_ENDIAN;
-	btf__set_endianness(linker->btf, link_endianness);
-	if (linker->btf_ext)
-		btf_ext__set_endianness(linker->btf_ext, link_endianness);
-
 	/* Emit .BTF section */
 	raw_data = btf__raw_data(linker->btf, &raw_sz);
 	if (!raw_data)
@@ -2916,19 +2707,19 @@ static int finalize_btf(struct bpf_linker *linker)
 
 	err = emit_elf_data_sec(linker, BTF_ELF_SEC, 8, raw_data, raw_sz);
 	if (err) {
-		pr_warn("failed to write out .BTF ELF section: %s\n", errstr(err));
+		pr_warn("failed to write out .BTF ELF section: %d\n", err);
 		return err;
 	}
 
 	/* Emit .BTF.ext section */
 	if (linker->btf_ext) {
-		raw_data = btf_ext__raw_data(linker->btf_ext, &raw_sz);
+		raw_data = btf_ext__get_raw_data(linker->btf_ext, &raw_sz);
 		if (!raw_data)
 			return -ENOMEM;
 
 		err = emit_elf_data_sec(linker, BTF_EXT_ELF_SEC, 8, raw_data, raw_sz);
 		if (err) {
-			pr_warn("failed to write out .BTF.ext ELF section: %s\n", errstr(err));
+			pr_warn("failed to write out .BTF.ext ELF section: %d\n", err);
 			return err;
 		}
 	}
@@ -3104,7 +2895,7 @@ static int finalize_btf_ext(struct bpf_linker *linker)
 	err = libbpf_get_error(linker->btf_ext);
 	if (err) {
 		linker->btf_ext = NULL;
-		pr_warn("failed to parse final .BTF.ext data: %s\n", errstr(err));
+		pr_warn("failed to parse final .BTF.ext data: %d\n", err);
 		goto out;
 	}
 

src/netlink.c

@@ -45,7 +45,6 @@ struct xdp_id_md {
 
 struct xdp_features_md {
 	int ifindex;
-	__u32 xdp_zc_max_segs;
 	__u64 flags;
 };
 
@@ -422,9 +421,6 @@ static int parse_xdp_features(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn,
 		return NL_CONT;
 
 	md->flags = libbpf_nla_getattr_u64(tb[NETDEV_A_DEV_XDP_FEATURES]);
-	if (tb[NETDEV_A_DEV_XDP_ZC_MAX_SEGS])
-		md->xdp_zc_max_segs =
-			libbpf_nla_getattr_u32(tb[NETDEV_A_DEV_XDP_ZC_MAX_SEGS]);
 	return NL_DONE;
 }
 
@@ -496,8 +492,7 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
 	if (err)
 		return libbpf_err(err);
 
-	OPTS_SET(opts, feature_flags, md.flags);
+	opts->feature_flags = md.flags;
-	OPTS_SET(opts, xdp_zc_max_segs, md.xdp_zc_max_segs);
 
 skip_feature_flags:
 	return 0;

src/nlattr.c

@@ -63,16 +63,16 @@ static int validate_nla(struct nlattr *nla, int maxtype,
 		minlen = nla_attr_minlen[pt->type];
 
 	if (libbpf_nla_len(nla) < minlen)
-		return -EINVAL;
+		return -1;
 
 	if (pt->maxlen && libbpf_nla_len(nla) > pt->maxlen)
-		return -EINVAL;
+		return -1;
 
 	if (pt->type == LIBBPF_NLA_STRING) {
 		char *data = libbpf_nla_data(nla);
 
 		if (data[libbpf_nla_len(nla) - 1] != '\0')
-			return -EINVAL;
+			return -1;
 	}
 
 	return 0;
@@ -118,18 +118,19 @@ int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head,
 		if (policy) {
 			err = validate_nla(nla, maxtype, policy);
 			if (err < 0)
-				return err;
+				goto errout;
 		}
 
-		if (tb[type]) {
+		if (tb[type])
 			pr_warn("Attribute of type %#x found multiple times in message, "
 				"previous attribute is being ignored.\n", type);
-		}
 
 		tb[type] = nla;
 	}
 
-	return 0;
+	err = 0;
+errout:
+	return err;
 }
 
 /**

src/relo_core.c

@@ -683,7 +683,7 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 {
 	const struct bpf_core_accessor *acc;
 	const struct btf_type *t;
-	__u32 byte_off, byte_sz, bit_off, bit_sz, field_type_id, elem_id;
+	__u32 byte_off, byte_sz, bit_off, bit_sz, field_type_id;
 	const struct btf_member *m;
 	const struct btf_type *mt;
 	bool bitfield;
@@ -706,14 +706,8 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 	if (!acc->name) {
 		if (relo->kind == BPF_CORE_FIELD_BYTE_OFFSET) {
 			*val = spec->bit_offset / 8;
-			/* remember field size for load/store mem size;
+			/* remember field size for load/store mem size */
-			 * note, for arrays we care about individual element
+			sz = btf__resolve_size(spec->btf, acc->type_id);
-			 * sizes, not the overall array size
-			 */
-			t = skip_mods_and_typedefs(spec->btf, acc->type_id, &elem_id);
-			while (btf_is_array(t))
-				t = skip_mods_and_typedefs(spec->btf, btf_array(t)->type, &elem_id);
-			sz = btf__resolve_size(spec->btf, elem_id);
 			if (sz < 0)
 				return -EINVAL;
 			*field_sz = sz;
@@ -773,17 +767,7 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 	case BPF_CORE_FIELD_BYTE_OFFSET:
 		*val = byte_off;
 		if (!bitfield) {
-			/* remember field size for load/store mem size;
+			*field_sz = byte_sz;
-			 * note, for arrays we care about individual element
-			 * sizes, not the overall array size
-			 */
-			t = skip_mods_and_typedefs(spec->btf, field_type_id, &elem_id);
-			while (btf_is_array(t))
-				t = skip_mods_and_typedefs(spec->btf, btf_array(t)->type, &elem_id);
-			sz = btf__resolve_size(spec->btf, elem_id);
-			if (sz < 0)
-				return -EINVAL;
-			*field_sz = sz;
 			*type_id = field_type_id;
 		}
 		break;
@@ -792,7 +776,7 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 		break;
 	case BPF_CORE_FIELD_SIGNED:
 		*val = (btf_is_any_enum(mt) && BTF_INFO_KFLAG(mt->info)) ||
-		       (btf_is_int(mt) && (btf_int_encoding(mt) & BTF_INT_SIGNED));
+		       (btf_int_encoding(mt) & BTF_INT_SIGNED);
 		if (validate)
 			*validate = true; /* signedness is never ambiguous */
 		break;
@@ -1355,7 +1339,7 @@ int bpf_core_calc_relo_insn(const char *prog_name,
 					  cands->cands[i].id, cand_spec);
 		if (err < 0) {
 			bpf_core_format_spec(spec_buf, sizeof(spec_buf), cand_spec);
-			pr_warn("prog '%s': relo #%d: error matching candidate #%d %s: %d\n",
+			pr_warn("prog '%s': relo #%d: error matching candidate #%d %s: %d\n ",
 				prog_name, relo_idx, i, spec_buf, err);
 			return err;
 		}

src/ringbuf.c

@@ -21,7 +21,6 @@
 #include "libbpf.h"
 #include "libbpf_internal.h"
 #include "bpf.h"
-#include "str_error.h"
 
 struct ring {
 	ring_buffer_sample_fn sample_cb;
@@ -35,7 +34,7 @@ struct ring {
 
 struct ring_buffer {
 	struct epoll_event *events;
-	struct ring **rings;
+	struct ring *rings;
 	size_t page_size;
 	int epoll_fd;
 	int ring_cnt;
@@ -58,7 +57,7 @@ struct ringbuf_hdr {
 	__u32 pad;
 };
 
-static void ringbuf_free_ring(struct ring_buffer *rb, struct ring *r)
+static void ringbuf_unmap_ring(struct ring_buffer *rb, struct ring *r)
 {
 	if (r->consumer_pos) {
 		munmap(r->consumer_pos, rb->page_size);
@@ -68,8 +67,6 @@ static void ringbuf_free_ring(struct ring_buffer *rb, struct ring *r)
 		munmap(r->producer_pos, rb->page_size + 2 * (r->mask + 1));
 		r->producer_pos = NULL;
 	}
-
-	free(r);
 }
 
 /* Add extra RINGBUF maps to this ring buffer manager */
@@ -89,8 +86,8 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 	err = bpf_map_get_info_by_fd(map_fd, &info, &len);
 	if (err) {
 		err = -errno;
-		pr_warn("ringbuf: failed to get map info for fd=%d: %s\n",
+		pr_warn("ringbuf: failed to get map info for fd=%d: %d\n",
-			map_fd, errstr(err));
+			map_fd, err);
 		return libbpf_err(err);
 	}
 
@@ -110,10 +107,8 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 		return libbpf_err(-ENOMEM);
 	rb->events = tmp;
 
-	r = calloc(1, sizeof(*r));
+	r = &rb->rings[rb->ring_cnt];
-	if (!r)
+	memset(r, 0, sizeof(*r));
-		return libbpf_err(-ENOMEM);
-	rb->rings[rb->ring_cnt] = r;
 
 	r->map_fd = map_fd;
 	r->sample_cb = sample_cb;
@@ -124,9 +119,9 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 	tmp = mmap(NULL, rb->page_size, PROT_READ | PROT_WRITE, MAP_SHARED, map_fd, 0);
 	if (tmp == MAP_FAILED) {
 		err = -errno;
-		pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %s\n",
+		pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %d\n",
-			map_fd, errstr(err));
+			map_fd, err);
-		goto err_out;
+		return libbpf_err(err);
 	}
 	r->consumer_pos = tmp;
 
@@ -136,16 +131,16 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 	 */
 	mmap_sz = rb->page_size + 2 * (__u64)info.max_entries;
 	if (mmap_sz != (__u64)(size_t)mmap_sz) {
-		err = -E2BIG;
 		pr_warn("ringbuf: ring buffer size (%u) is too big\n", info.max_entries);
-		goto err_out;
+		return libbpf_err(-E2BIG);
 	}
 	tmp = mmap(NULL, (size_t)mmap_sz, PROT_READ, MAP_SHARED, map_fd, rb->page_size);
 	if (tmp == MAP_FAILED) {
 		err = -errno;
-		pr_warn("ringbuf: failed to mmap data pages for map fd=%d: %s\n",
+		ringbuf_unmap_ring(rb, r);
-			map_fd, errstr(err));
+		pr_warn("ringbuf: failed to mmap data pages for map fd=%d: %d\n",
-		goto err_out;
+			map_fd, err);
+		return libbpf_err(err);
 	}
 	r->producer_pos = tmp;
 	r->data = tmp + rb->page_size;
@@ -157,17 +152,14 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 	e->data.fd = rb->ring_cnt;
 	if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, e) < 0) {
 		err = -errno;
-		pr_warn("ringbuf: failed to epoll add map fd=%d: %s\n",
+		ringbuf_unmap_ring(rb, r);
-			map_fd, errstr(err));
+		pr_warn("ringbuf: failed to epoll add map fd=%d: %d\n",
-		goto err_out;
+			map_fd, err);
+		return libbpf_err(err);
 	}
 
 	rb->ring_cnt++;
 	return 0;
-
-err_out:
-	ringbuf_free_ring(rb, r);
-	return libbpf_err(err);
 }
 
 void ring_buffer__free(struct ring_buffer *rb)
@@ -178,7 +170,7 @@ void ring_buffer__free(struct ring_buffer *rb)
 		return;
 
 	for (i = 0; i < rb->ring_cnt; ++i)
-		ringbuf_free_ring(rb, rb->rings[i]);
+		ringbuf_unmap_ring(rb, &rb->rings[i]);
 	if (rb->epoll_fd >= 0)
 		close(rb->epoll_fd);
 
@@ -206,7 +198,7 @@ ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx,
 	rb->epoll_fd = epoll_create1(EPOLL_CLOEXEC);
 	if (rb->epoll_fd < 0) {
 		err = -errno;
-		pr_warn("ringbuf: failed to create epoll instance: %s\n", errstr(err));
+		pr_warn("ringbuf: failed to create epoll instance: %d\n", err);
 		goto err_out;
 	}
 
@@ -232,7 +224,7 @@ static inline int roundup_len(__u32 len)
 	return (len + 7) / 8 * 8;
 }
 
-static int64_t ringbuf_process_ring(struct ring *r, size_t n)
+static int64_t ringbuf_process_ring(struct ring *r)
 {
 	int *len_ptr, len, err;
 	/* 64-bit to avoid overflow in case of extreme application behavior */
@@ -269,42 +261,12 @@ static int64_t ringbuf_process_ring(struct ring *r, size_t n)
 			}
 
 			smp_store_release(r->consumer_pos, cons_pos);
-
-			if (cnt >= n)
-				goto done;
 		}
 	} while (got_new_data);
 done:
 	return cnt;
 }
 
-/* Consume available ring buffer(s) data without event polling, up to n
- * records.
- *
- * Returns number of records consumed across all registered ring buffers (or
- * n, whichever is less), or negative number if any of the callbacks return
- * error.
- */
-int ring_buffer__consume_n(struct ring_buffer *rb, size_t n)
-{
-	int64_t err, res = 0;
-	int i;
-
-	for (i = 0; i < rb->ring_cnt; i++) {
-		struct ring *ring = rb->rings[i];
-
-		err = ringbuf_process_ring(ring, n);
-		if (err < 0)
-			return libbpf_err(err);
-		res += err;
-		n -= err;
-
-		if (n == 0)
-			break;
-	}
-	return res > INT_MAX ? INT_MAX : res;
-}
-
 /* Consume available ring buffer(s) data without event polling.
  * Returns number of records consumed across all registered ring buffers (or
  * INT_MAX, whichever is less), or negative number if any of the callbacks
@@ -316,17 +278,15 @@ int ring_buffer__consume(struct ring_buffer *rb)
 	int i;
 
 	for (i = 0; i < rb->ring_cnt; i++) {
-		struct ring *ring = rb->rings[i];
+		struct ring *ring = &rb->rings[i];
 
-		err = ringbuf_process_ring(ring, INT_MAX);
+		err = ringbuf_process_ring(ring);
 		if (err < 0)
 			return libbpf_err(err);
 		res += err;
-		if (res > INT_MAX) {
-			res = INT_MAX;
-			break;
-		}
 	}
+	if (res > INT_MAX)
+		return INT_MAX;
 	return res;
 }
 
@@ -345,15 +305,15 @@ int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms)
 
 	for (i = 0; i < cnt; i++) {
 		__u32 ring_id = rb->events[i].data.fd;
-		struct ring *ring = rb->rings[ring_id];
+		struct ring *ring = &rb->rings[ring_id];
 
-		err = ringbuf_process_ring(ring, INT_MAX);
+		err = ringbuf_process_ring(ring);
 		if (err < 0)
 			return libbpf_err(err);
 		res += err;
 	}
 	if (res > INT_MAX)
-		res = INT_MAX;
+		return INT_MAX;
 	return res;
 }
 
@@ -363,63 +323,6 @@ int ring_buffer__epoll_fd(const struct ring_buffer *rb)
 	return rb->epoll_fd;
 }
 
-struct ring *ring_buffer__ring(struct ring_buffer *rb, unsigned int idx)
-{
-	if (idx >= rb->ring_cnt)
-		return errno = ERANGE, NULL;
-
-	return rb->rings[idx];
-}
-
-unsigned long ring__consumer_pos(const struct ring *r)
-{
-	/* Synchronizes with smp_store_release() in ringbuf_process_ring(). */
-	return smp_load_acquire(r->consumer_pos);
-}
-
-unsigned long ring__producer_pos(const struct ring *r)
-{
-	/* Synchronizes with smp_store_release() in __bpf_ringbuf_reserve() in
-	 * the kernel.
-	 */
-	return smp_load_acquire(r->producer_pos);
-}
-
-size_t ring__avail_data_size(const struct ring *r)
-{
-	unsigned long cons_pos, prod_pos;
-
-	cons_pos = ring__consumer_pos(r);
-	prod_pos = ring__producer_pos(r);
-	return prod_pos - cons_pos;
-}
-
-size_t ring__size(const struct ring *r)
-{
-	return r->mask + 1;
-}
-
-int ring__map_fd(const struct ring *r)
-{
-	return r->map_fd;
-}
-
-int ring__consume_n(struct ring *r, size_t n)
-{
-	int64_t res;
-
-	res = ringbuf_process_ring(r, n);
-	if (res < 0)
-		return libbpf_err(res);
-
-	return res > INT_MAX ? INT_MAX : res;
-}
-
-int ring__consume(struct ring *r)
-{
-	return ring__consume_n(r, INT_MAX);
-}
-
 static void user_ringbuf_unmap_ring(struct user_ring_buffer *rb)
 {
 	if (rb->consumer_pos) {
@@ -459,8 +362,7 @@ static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd)
 	err = bpf_map_get_info_by_fd(map_fd, &info, &len);
 	if (err) {
 		err = -errno;
-		pr_warn("user ringbuf: failed to get map info for fd=%d: %s\n",
+		pr_warn("user ringbuf: failed to get map info for fd=%d: %d\n", map_fd, err);
-			map_fd, errstr(err));
 		return err;
 	}
 
@@ -476,8 +378,8 @@ static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd)
 	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: %s\n",
+		pr_warn("user ringbuf: failed to mmap consumer page for map fd=%d: %d\n",
-			map_fd, errstr(err));
+			map_fd, err);
 		return err;
 	}
 	rb->consumer_pos = tmp;
@@ -496,8 +398,8 @@ static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd)
 		   map_fd, rb->page_size);
 	if (tmp == MAP_FAILED) {
 		err = -errno;
-		pr_warn("user ringbuf: failed to mmap data pages for map fd=%d: %s\n",
+		pr_warn("user ringbuf: failed to mmap data pages for map fd=%d: %d\n",
-			map_fd, errstr(err));
+			map_fd, err);
 		return err;
 	}
 
@@ -508,7 +410,7 @@ static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd)
 	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: %s\n", map_fd, errstr(err));
+		pr_warn("user ringbuf: failed to epoll add map fd=%d: %d\n", map_fd, err);
 		return err;
 	}
 
@@ -533,7 +435,7 @@ user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts)
 	rb->epoll_fd = epoll_create1(EPOLL_CLOEXEC);
 	if (rb->epoll_fd < 0) {
 		err = -errno;
-		pr_warn("user ringbuf: failed to create epoll instance: %s\n", errstr(err));
+		pr_warn("user ringbuf: failed to create epoll instance: %d\n", err);
 		goto err_out;
 	}
 

src/skel_internal.h

@@ -107,7 +107,7 @@ static inline void skel_free(const void *p)
  * 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 necessary.
+ * is not nessary.
  *
  * For user space:
  * skel_prep_map_data() mmaps anon memory into skel->rodata that can be accessed directly.
@@ -351,11 +351,10 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
 	attr.test.ctx_size_in = opts->ctx->sz;
 	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) {
-			opts->errstr = "failed to execute loader prog";
 			set_err;
 		} else {
-			opts->errstr = "error returned by loader prog";
 			err = (int)attr.test.retval;
 #ifndef __KERNEL__
 			errno = -err;

src/str_error.c

@@ -2,13 +2,8 @@
 #undef _GNU_SOURCE
 #include <string.h>
 #include <stdio.h>
-#include <errno.h>
 #include "str_error.h"
 
-#ifndef ENOTSUPP
-#define ENOTSUPP	524
-#endif
-
 /* make sure libbpf doesn't use kernel-only integer typedefs */
 #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
 
@@ -20,85 +15,7 @@
 char *libbpf_strerror_r(int err, char *dst, int len)
 {
 	int ret = strerror_r(err < 0 ? -err : err, dst, len);
-	/* on glibc <2.13, ret == -1 and errno is set, if strerror_r() can't
+	if (ret)
-	 * handle the error, on glibc >=2.13 *positive* (errno-like) error
+		snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret);
-	 * code is returned directly
-	 */
-	if (ret == -1)
-		ret = errno;
-	if (ret) {
-		if (ret == EINVAL)
-			/* strerror_r() doesn't recognize this specific error */
-			snprintf(dst, len, "unknown error (%d)", err < 0 ? err : -err);
-		else
-			snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret);
-	}
 	return dst;
 }
-
-const char *libbpf_errstr(int err)
-{
-	static __thread char buf[12];
-
-	if (err > 0)
-		err = -err;
-
-	switch (err) {
-	case -E2BIG:		return "-E2BIG";
-	case -EACCES:		return "-EACCES";
-	case -EADDRINUSE:	return "-EADDRINUSE";
-	case -EADDRNOTAVAIL:	return "-EADDRNOTAVAIL";
-	case -EAGAIN:		return "-EAGAIN";
-	case -EALREADY:		return "-EALREADY";
-	case -EBADF:		return "-EBADF";
-	case -EBADFD:		return "-EBADFD";
-	case -EBUSY:		return "-EBUSY";
-	case -ECANCELED:	return "-ECANCELED";
-	case -ECHILD:		return "-ECHILD";
-	case -EDEADLK:		return "-EDEADLK";
-	case -EDOM:		return "-EDOM";
-	case -EEXIST:		return "-EEXIST";
-	case -EFAULT:		return "-EFAULT";
-	case -EFBIG:		return "-EFBIG";
-	case -EILSEQ:		return "-EILSEQ";
-	case -EINPROGRESS:	return "-EINPROGRESS";
-	case -EINTR:		return "-EINTR";
-	case -EINVAL:		return "-EINVAL";
-	case -EIO:		return "-EIO";
-	case -EISDIR:		return "-EISDIR";
-	case -ELOOP:		return "-ELOOP";
-	case -EMFILE:		return "-EMFILE";
-	case -EMLINK:		return "-EMLINK";
-	case -EMSGSIZE:		return "-EMSGSIZE";
-	case -ENAMETOOLONG:	return "-ENAMETOOLONG";
-	case -ENFILE:		return "-ENFILE";
-	case -ENODATA:		return "-ENODATA";
-	case -ENODEV:		return "-ENODEV";
-	case -ENOENT:		return "-ENOENT";
-	case -ENOEXEC:		return "-ENOEXEC";
-	case -ENOLINK:		return "-ENOLINK";
-	case -ENOMEM:		return "-ENOMEM";
-	case -ENOSPC:		return "-ENOSPC";
-	case -ENOTBLK:		return "-ENOTBLK";
-	case -ENOTDIR:		return "-ENOTDIR";
-	case -ENOTSUPP:		return "-ENOTSUPP";
-	case -ENOTTY:		return "-ENOTTY";
-	case -ENXIO:		return "-ENXIO";
-	case -EOPNOTSUPP:	return "-EOPNOTSUPP";
-	case -EOVERFLOW:	return "-EOVERFLOW";
-	case -EPERM:		return "-EPERM";
-	case -EPIPE:		return "-EPIPE";
-	case -EPROTO:		return "-EPROTO";
-	case -EPROTONOSUPPORT:	return "-EPROTONOSUPPORT";
-	case -ERANGE:		return "-ERANGE";
-	case -EROFS:		return "-EROFS";
-	case -ESPIPE:		return "-ESPIPE";
-	case -ESRCH:		return "-ESRCH";
-	case -ETXTBSY:		return "-ETXTBSY";
-	case -EUCLEAN:		return "-EUCLEAN";
-	case -EXDEV:		return "-EXDEV";
-	default:
-		snprintf(buf, sizeof(buf), "%d", err);
-		return buf;
-	}
-}

src/str_error.h

@@ -2,18 +2,5 @@
 #ifndef __LIBBPF_STR_ERROR_H
 #define __LIBBPF_STR_ERROR_H
 
-#define STRERR_BUFSIZE  128
-
 char *libbpf_strerror_r(int err, char *dst, int len);
-
-/**
- * @brief **libbpf_errstr()** returns string corresponding to numeric errno
- * @param err negative numeric errno
- * @return pointer to string representation of the errno, that is invalidated
- * upon the next call.
- */
-const char *libbpf_errstr(int err);
-
-#define errstr(err) libbpf_errstr(err)
-
 #endif /* __LIBBPF_STR_ERROR_H */

src/usdt.bpf.h

@@ -4,8 +4,8 @@
 #define __USDT_BPF_H__
 
 #include <linux/errno.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
-#include "bpf_tracing.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
@@ -39,7 +39,7 @@ enum __bpf_usdt_arg_type {
 struct __bpf_usdt_arg_spec {
 	/* u64 scalar interpreted depending on arg_type, see below */
 	__u64 val_off;
-	/* arg location case, see bpf_usdt_arg() for details */
+	/* 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;
@@ -108,38 +108,6 @@ int bpf_usdt_arg_cnt(struct pt_regs *ctx)
 	return spec->arg_cnt;
 }
 
-/* Returns the size in bytes of the #*arg_num* (zero-indexed) USDT argument.
- * Returns negative error if argument is not found or arg_num is invalid.
- */
-static __always_inline
-int bpf_usdt_arg_size(struct pt_regs *ctx, __u64 arg_num)
-{
-	struct __bpf_usdt_arg_spec *arg_spec;
-	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;
-
-	if (arg_num >= BPF_USDT_MAX_ARG_CNT)
-		return -ENOENT;
-	barrier_var(arg_num);
-	if (arg_num >= spec->arg_cnt)
-		return -ENOENT;
-
-	arg_spec = &spec->args[arg_num];
-
-	/* arg_spec->arg_bitshift = 64 - arg_sz * 8
-	 * so: arg_sz = (64 - arg_spec->arg_bitshift) / 8
-	 */
-	return (unsigned int)(64 - arg_spec->arg_bitshift) / 8;
-}
-
 /* 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.
@@ -246,18 +214,18 @@ long bpf_usdt_cookie(struct pt_regs *ctx)
 
 /* 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); _x; })
+#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); _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); _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); _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); _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); _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); _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); _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); _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); _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); _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); _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)
 
 /*

src/usdt.c

@@ -20,7 +20,6 @@
 #include "libbpf_common.h"
 #include "libbpf_internal.h"
 #include "hashmap.h"
-#include "str_error.h"
 
 /* libbpf's USDT support consists of BPF-side state/code and user-space
  * state/code working together in concert. BPF-side parts are defined in
@@ -251,7 +250,6 @@ struct usdt_manager {
 
 	bool has_bpf_cookie;
 	bool has_sema_refcnt;
-	bool has_uprobe_multi;
 };
 
 struct usdt_manager *usdt_manager_new(struct bpf_object *obj)
@@ -286,11 +284,6 @@ struct usdt_manager *usdt_manager_new(struct bpf_object *obj)
 	 */
 	man->has_sema_refcnt = faccessat(AT_FDCWD, ref_ctr_sysfs_path, F_OK, AT_EACCESS) == 0;
 
-	/*
-	 * Detect kernel support for uprobe multi link to be used for attaching
-	 * usdt probes.
-	 */
-	man->has_uprobe_multi = kernel_supports(obj, FEAT_UPROBE_MULTI_LINK);
 	return man;
 }
 
@@ -466,8 +459,8 @@ static int parse_vma_segs(int pid, const char *lib_path, struct elf_seg **segs,
 		goto proceed;
 
 	if (!realpath(lib_path, path)) {
-		pr_warn("usdt: failed to get absolute path of '%s' (err %s), using path as is...\n",
+		pr_warn("usdt: failed to get absolute path of '%s' (err %d), using path as is...\n",
-			lib_path, errstr(-errno));
+			lib_path, -errno);
 		libbpf_strlcpy(path, lib_path, sizeof(path));
 	}
 
@@ -476,8 +469,8 @@ proceed:
 	f = fopen(line, "re");
 	if (!f) {
 		err = -errno;
-		pr_warn("usdt: failed to open '%s' to get base addr of '%s': %s\n",
+		pr_warn("usdt: failed to open '%s' to get base addr of '%s': %d\n",
-			line, lib_path, errstr(err));
+			line, lib_path, err);
 		return err;
 	}
 
@@ -607,8 +600,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char *
 
 	err = parse_elf_segs(elf, path, &segs, &seg_cnt);
 	if (err) {
-		pr_warn("usdt: failed to process ELF program segments for '%s': %s\n",
+		pr_warn("usdt: failed to process ELF program segments for '%s': %d\n", path, err);
-			path, errstr(err));
 		goto err_out;
 	}
 
@@ -661,7 +653,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char *
 		 *   [0] https://sourceware.org/systemtap/wiki/UserSpaceProbeImplementation
 		 */
 		usdt_abs_ip = note.loc_addr;
-		if (base_addr && note.base_addr)
+		if (base_addr)
 			usdt_abs_ip += base_addr - note.base_addr;
 
 		/* When attaching uprobes (which is what USDTs basically are)
@@ -710,8 +702,8 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char *
 			if (vma_seg_cnt == 0) {
 				err = parse_vma_segs(pid, path, &vma_segs, &vma_seg_cnt);
 				if (err) {
-					pr_warn("usdt: failed to get memory segments in PID %d for shared library '%s': %s\n",
+					pr_warn("usdt: failed to get memory segments in PID %d for shared library '%s': %d\n",
-						pid, path, errstr(err));
+						pid, path, err);
 					goto err_out;
 				}
 			}
@@ -816,8 +808,6 @@ struct bpf_link_usdt {
 		long abs_ip;
 		struct bpf_link *link;
 	} *uprobes;
-
-	struct bpf_link *multi_link;
 };
 
 static int bpf_link_usdt_detach(struct bpf_link *link)
@@ -826,9 +816,6 @@ static int bpf_link_usdt_detach(struct bpf_link *link)
 	struct usdt_manager *man = usdt_link->usdt_man;
 	int i;
 
-	bpf_link__destroy(usdt_link->multi_link);
-
-	/* When having multi_link, uprobe_cnt is 0 */
 	for (i = 0; i < usdt_link->uprobe_cnt; i++) {
 		/* detach underlying uprobe link */
 		bpf_link__destroy(usdt_link->uprobes[i].link);
@@ -959,24 +946,32 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct
 					  const char *usdt_provider, const char *usdt_name,
 					  __u64 usdt_cookie)
 {
-	unsigned long *offsets = NULL, *ref_ctr_offsets = NULL;
+	int i, fd, err, spec_map_fd, ip_map_fd;
-	int i, err, spec_map_fd, ip_map_fd;
 	LIBBPF_OPTS(bpf_uprobe_opts, opts);
 	struct hashmap *specs_hash = NULL;
 	struct bpf_link_usdt *link = NULL;
 	struct usdt_target *targets = NULL;
-	__u64 *cookies = NULL;
-	struct elf_fd elf_fd;
 	size_t target_cnt;
+	Elf *elf;
 
 	spec_map_fd = bpf_map__fd(man->specs_map);
 	ip_map_fd = bpf_map__fd(man->ip_to_spec_id_map);
 
-	err = elf_open(path, &elf_fd);
+	fd = open(path, O_RDONLY | O_CLOEXEC);
-	if (err)
+	if (fd < 0) {
+		err = -errno;
+		pr_warn("usdt: failed to open ELF binary '%s': %d\n", path, err);
 		return libbpf_err_ptr(err);
+	}
 
-	err = sanity_check_usdt_elf(elf_fd.elf, path);
+	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
+	if (!elf) {
+		err = -EBADF;
+		pr_warn("usdt: failed to parse ELF binary '%s': %s\n", path, elf_errmsg(-1));
+		goto err_out;
+	}
+
+	err = sanity_check_usdt_elf(elf, path);
 	if (err)
 		goto err_out;
 
@@ -989,7 +984,7 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct
 	/* discover USDT in given binary, optionally limiting
 	 * activations to a given PID, if pid > 0
 	 */
-	err = collect_usdt_targets(man, elf_fd.elf, path, pid, usdt_provider, usdt_name,
+	err = collect_usdt_targets(man, elf, path, pid, usdt_provider, usdt_name,
 				   usdt_cookie, &targets, &target_cnt);
 	if (err <= 0) {
 		err = (err == 0) ? -ENOENT : err;
@@ -1012,21 +1007,10 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct
 	link->link.detach = &bpf_link_usdt_detach;
 	link->link.dealloc = &bpf_link_usdt_dealloc;
 
-	if (man->has_uprobe_multi) {
+	link->uprobes = calloc(target_cnt, sizeof(*link->uprobes));
-		offsets = calloc(target_cnt, sizeof(*offsets));
+	if (!link->uprobes) {
-		cookies = calloc(target_cnt, sizeof(*cookies));
+		err = -ENOMEM;
-		ref_ctr_offsets = calloc(target_cnt, sizeof(*ref_ctr_offsets));
+		goto err_out;
-
-		if (!offsets || !ref_ctr_offsets || !cookies) {
-			err = -ENOMEM;
-			goto err_out;
-		}
-	} else {
-		link->uprobes = calloc(target_cnt, sizeof(*link->uprobes));
-		if (!link->uprobes) {
-			err = -ENOMEM;
-			goto err_out;
-		}
 	}
 
 	for (i = 0; i < target_cnt; i++) {
@@ -1049,8 +1033,8 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct
 
 		if (is_new && bpf_map_update_elem(spec_map_fd, &spec_id, &target->spec, BPF_ANY)) {
 			err = -errno;
-			pr_warn("usdt: failed to set USDT spec #%d for '%s:%s' in '%s': %s\n",
+			pr_warn("usdt: failed to set USDT spec #%d for '%s:%s' in '%s': %d\n",
-				spec_id, usdt_provider, usdt_name, path, errstr(err));
+				spec_id, usdt_provider, usdt_name, path, err);
 			goto err_out;
 		}
 		if (!man->has_bpf_cookie &&
@@ -1060,72 +1044,44 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct
 				pr_warn("usdt: IP collision detected for spec #%d for '%s:%s' in '%s'\n",
 				        spec_id, usdt_provider, usdt_name, path);
 			} else {
-				pr_warn("usdt: failed to map IP 0x%lx to spec #%d for '%s:%s' in '%s': %s\n",
+				pr_warn("usdt: failed to map IP 0x%lx to spec #%d for '%s:%s' in '%s': %d\n",
 					target->abs_ip, spec_id, usdt_provider, usdt_name,
-					path, errstr(err));
+					path, err);
 			}
 			goto err_out;
 		}
 
-		if (man->has_uprobe_multi) {
+		opts.ref_ctr_offset = target->sema_off;
-			offsets[i] = target->rel_ip;
+		opts.bpf_cookie = man->has_bpf_cookie ? spec_id : 0;
-			ref_ctr_offsets[i] = target->sema_off;
+		uprobe_link = bpf_program__attach_uprobe_opts(prog, pid, path,
-			cookies[i] = spec_id;
+							      target->rel_ip, &opts);
-		} else {
+		err = libbpf_get_error(uprobe_link);
-			opts.ref_ctr_offset = target->sema_off;
+		if (err) {
-			opts.bpf_cookie = man->has_bpf_cookie ? spec_id : 0;
+			pr_warn("usdt: failed to attach uprobe #%d for '%s:%s' in '%s': %d\n",
-			uprobe_link = bpf_program__attach_uprobe_opts(prog, pid, path,
+				i, usdt_provider, usdt_name, path, err);
-								      target->rel_ip, &opts);
-			err = libbpf_get_error(uprobe_link);
-			if (err) {
-				pr_warn("usdt: failed to attach uprobe #%d for '%s:%s' in '%s': %s\n",
-					i, usdt_provider, usdt_name, path, errstr(err));
-				goto err_out;
-			}
-
-			link->uprobes[i].link = uprobe_link;
-			link->uprobes[i].abs_ip = target->abs_ip;
-			link->uprobe_cnt++;
-		}
-	}
-
-	if (man->has_uprobe_multi) {
-		LIBBPF_OPTS(bpf_uprobe_multi_opts, opts_multi,
-			.ref_ctr_offsets = ref_ctr_offsets,
-			.offsets = offsets,
-			.cookies = cookies,
-			.cnt = target_cnt,
-		);
-
-		link->multi_link = bpf_program__attach_uprobe_multi(prog, pid, path,
-								    NULL, &opts_multi);
-		if (!link->multi_link) {
-			err = -errno;
-			pr_warn("usdt: failed to attach uprobe multi for '%s:%s' in '%s': %s\n",
-				usdt_provider, usdt_name, path, errstr(err));
 			goto err_out;
 		}
 
-		free(offsets);
+		link->uprobes[i].link = uprobe_link;
-		free(ref_ctr_offsets);
+		link->uprobes[i].abs_ip = target->abs_ip;
-		free(cookies);
+		link->uprobe_cnt++;
 	}
 
 	free(targets);
 	hashmap__free(specs_hash);
-	elf_close(&elf_fd);
+	elf_end(elf);
+	close(fd);
+
 	return &link->link;
 
 err_out:
-	free(offsets);
-	free(ref_ctr_offsets);
-	free(cookies);
-
 	if (link)
 		bpf_link__destroy(&link->link);
 	free(targets);
 	hashmap__free(specs_hash);
-	elf_close(&elf_fd);
+	if (elf)
+		elf_end(elf);
+	close(fd);
 	return libbpf_err_ptr(err);
 }
 

src/zip.c

@@ -223,7 +223,7 @@ struct zip_archive *zip_archive_open(const char *path)
 	if (!archive) {
 		munmap(data, size);
 		return ERR_PTR(-ENOMEM);
-	}
+	};
 
 	archive->data = data;
 	archive->size = size;