netdata_patch_1_4_1: Add 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/PULL_REQUEST_TEMPLATE.md

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

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

@@ -0,0 +1,31 @@
+name: 'build-selftests'
+description: 'Build BPF selftests'
+inputs:
+  repo-path:
+    description: 'where is the source code'
+    required: true
+  kernel:
+    description: 'kernel version or LATEST'
+    required: true
+    default: 'LATEST'
+  vmlinux:
+    description: 'where is vmlinux file'
+    required: true
+    default: '${{ github.workspace }}/vmlinux'
+
+runs:
+  using: "composite"
+  steps:
+    - shell: bash
+      run: |
+        source $GITHUB_ACTION_PATH/../../../ci/vmtest/helpers.sh
+        foldable start "Setup Env"
+        sudo apt-get install -y qemu-kvm zstd binutils-dev elfutils libcap-dev libelf-dev libdw-dev python3-docutils
+        foldable end
+    - shell: bash
+      run: |
+        export KERNEL=${{ inputs.kernel }}
+        export REPO_ROOT="${{ github.workspace }}"
+        export REPO_PATH="${{ inputs.repo-path }}"
+        export VMLINUX_BTF="${{ inputs.vmlinux }}"
+        ${{ github.action_path }}/build_selftests.sh

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

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

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

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

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

@@ -0,0 +1,5 @@
+#!/bin/bash
+
+printf "all:\n\ttouch bpf_testmod.ko\n\nclean:\n" > bpf_testmod/Makefile
+printf "all:\n\ttouch bpf_test_no_cfi.ko\n\nclean:\n" > bpf_test_no_cfi/Makefile
+

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

@@ -0,0 +1,5 @@
+#!/bin/bash
+
+printf "all:\n\ttouch bpf_testmod.ko\n\nclean:\n" > bpf_testmod/Makefile
+printf "all:\n\ttouch bpf_test_no_cfi.ko\n\nclean:\n" > bpf_test_no_cfi/Makefile
+

.github/actions/vmtest/action.yml

@@ -0,0 +1,118 @@
+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:
+    # Allow CI user to access /dev/kvm (via qemu) w/o group change/relogin
+    # by changing permissions set by udev.
+    - name: Set /dev/kvm permissions
+      shell: bash
+      run: |
+        if [ -e /dev/kvm ]; then
+          echo "/dev/kvm exists"
+          if [ $(id -u) != 0 ]; then
+            echo 'KERNEL=="kvm", GROUP="kvm", MODE="0666", OPTIONS+="static_node=kvm"' \
+              | sudo tee /etc/udev/rules.d/99-kvm4all.rules > /dev/null
+            sudo udevadm control --reload-rules
+            sudo udevadm trigger --name-match=kvm
+          fi
+        else
+          echo "/dev/kvm does not exist"
+        fi
+    # setup environment
+    - name: Setup environment
+      uses: libbpf/ci/setup-build-env@main
+      with:
+        pahole: ${{ inputs.pahole }}
+        arch: ${{ inputs.arch }}
+    # 1. download CHECKPOINT kernel source
+    - name: Get checkpoint commit
+      shell: bash
+      run: |
+        cat CHECKPOINT-COMMIT
+        echo "CHECKPOINT=$(cat CHECKPOINT-COMMIT)" >> $GITHUB_ENV
+    - name: Get kernel source at checkpoint
+      uses: libbpf/ci/get-linux-source@main
+      with:
+        repo: 'https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git'
+        rev: ${{ env.CHECKPOINT }}
+        dest: '${{ github.workspace }}/.kernel'
+    - name: Patch kernel source
+      uses: libbpf/ci/patch-kernel@main
+      with:
+        patches-root: '${{ github.workspace }}/ci/diffs'
+        repo-root: '.kernel'
+    - name: Prepare to build BPF selftests
+      shell: bash
+      run: |
+        source $GITHUB_ACTION_PATH/../../../ci/vmtest/helpers.sh
+        foldable start "Prepare building selftest"
+        cd .kernel
+        cat tools/testing/selftests/bpf/config \
+            tools/testing/selftests/bpf/config.${{ inputs.arch }} > .config
+        # this file might or mihgt not exist depending on kernel version
+        cat tools/testing/selftests/bpf/config.vm >> .config || :
+        make olddefconfig && make prepare
+        cd -
+        foldable end
+    # 2. if kernel == LATEST, build kernel image from tree
+    - name: Build kernel image
+      if: ${{ inputs.kernel == 'LATEST' }}
+      shell: bash
+      run: |
+        source $GITHUB_ACTION_PATH/../../../ci/vmtest/helpers.sh
+        foldable start "Build Kernel Image"
+        cd .kernel
+        make -j $((4*$(nproc))) all > /dev/null
+        cp vmlinux ${{ github.workspace }}
+        cd -
+        foldable end
+    # else, just download prebuilt kernel image
+    - name: Download prebuilt kernel
+      if: ${{ inputs.kernel != 'LATEST' }}
+      uses: libbpf/ci/download-vmlinux@main
+      with:
+        kernel: ${{ inputs.kernel }}
+        arch: ${{ inputs.arch }}
+    # 3. build selftests
+    - name: Build BPF selftests
+      uses: ./.github/actions/build-selftests
+      with:
+        repo-path: '.kernel'
+        kernel: ${{ inputs.kernel }}
+    # 4. prepare rootfs
+    - name: prepare rootfs
+      uses: libbpf/ci/prepare-rootfs@main
+      env:
+        KBUILD_OUTPUT: '.kernel'
+      with:
+        project-name: 'libbpf'
+        arch: ${{ inputs.arch }}
+        kernel: ${{ inputs.kernel }}
+        kernel-root: '.kernel'
+        kbuild-output: ${{ env.KBUILD_OUTPUT }}
+        image-output: '/tmp/root.img'
+    # 5. run selftest in QEMU
+    - name: Run selftests
+      env:
+        KERNEL: ${{ inputs.kernel }}
+        REPO_ROOT: ${{ github.workspace }}
+      uses: libbpf/ci/run-qemu@main
+      with:
+        arch: ${{ inputs.arch }}
+        img: '/tmp/root.img'
+        vmlinuz: 'vmlinuz'
+        kernel-root: '.kernel'

.github/workflows/build.yml

@@ -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
         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
-
-      - name: Build in docker
-        if: matrix.arch != 'amd64'
-        run: |
-          cp /tmp/ci_setup ${GITHUB_WORKSPACE}
-          docker run --rm \
-                 --platform linux/${{ matrix.arch }} \
-                 -v ${GITHUB_WORKSPACE}:${GITHUB_WORKSPACE} \
-                 -e GITHUB_WORKSPACE=${GITHUB_WORKSPACE} \
-                 -w /ci/workspace \
-                 ubuntu:noble \
-                 ${GITHUB_WORKSPACE}/ci/build-in-docker.sh
-
+      - uses: uraimo/run-on-arch-action@v2.7.1
+        name: Build in docker
+        if: matrix.arch != 'x86'
+        with:
+          distro:
+            ubuntu20.04
+          arch:
+            ${{ matrix.arch }}
+          setup:
+            cp /tmp/ci_setup $GITHUB_WORKSPACE
+          dockerRunArgs: |
+            --volume "${GITHUB_WORKSPACE}:${GITHUB_WORKSPACE}"
+          shell: /bin/bash
+          install: |
+            export DEBIAN_FRONTEND=noninteractive
+            export TZ="America/Los_Angeles"
+            apt-get update -y
+            apt-get install -y tzdata build-essential sudo
+          run: source ${GITHUB_WORKSPACE}/ci_setup && $CI_ROOT/managers/ubuntu.sh

.github/workflows/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

.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: ./.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/ondemand.yml

@@ -3,29 +3,34 @@ name: ondemand
 on:
   workflow_dispatch:
     inputs:
-      arch:
-        default: 'x86_64'
+      kernel-origin:
+        description: 'git repo for linux kernel'
+        default: 'https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git'
         required: true
-      llvm-version:
-        default: '18'
-        required: true
-      kernel:
-        default: 'LATEST'
-        required: true
-      pahole:
+      kernel-rev:
+        description: 'rev/tag/branch for linux kernel'
         default: "master"
         required: true
-      runs-on:
-        default: 'ubuntu-24.04'
+      pahole-origin:
+        description: 'git repo for pahole'
+        default: 'https://git.kernel.org/pub/scm/devel/pahole/pahole.git'
+        required: true
+      pahole-rev:
+        description: 'ref/tag/branch for pahole'
+        default: "master"
         required: true
 
 jobs:
   vmtest:
-    name: ${{ inputs.kernel }} kernel llvm-${{ inputs.llvm-version }} pahole@${{ inputs.pahole }}
-    uses: ./.github/workflows/vmtest.yml
-    with:
-      runs_on: ${{ inputs.runs-on }}
-      kernel: ${{ inputs.kernel }}
-      arch: ${{ inputs.arch }}
-      llvm-version: ${{ inputs.llvm-version }}
-      pahole: ${{ inputs.pahole }}
+    runs-on: ubuntu-latest
+    name: vmtest with customized pahole/Kernel
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ./.github/actions/setup
+      - uses: ./.github/actions/vmtest
+        with:
+          kernel: 'LATEST'
+          kernel-rev: ${{ github.event.inputs.kernel-rev }}
+          kernel-origin: ${{ github.event.inputs.kernel-origin }}
+          pahole: ${{ github.event.inputs.pahole-rev }}
+          pahole-origin: ${{ github.event.inputs.pahole-origin }}

.github/workflows/pahole.yml

@@ -0,0 +1,20 @@
+name: pahole-staging
+
+on:
+  schedule:
+    - cron:  '0 18 * * *'
+
+
+jobs:
+  vmtest:
+    runs-on: ubuntu-20.04
+    name: Kernel LATEST + staging pahole
+    env:
+      STAGING: tmp.master
+    steps:
+      - uses: actions/checkout@v4
+      - 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'
-            arch: 'x86_64'
-            llvm-version: '18'
-            pahole: 'tmp.master'
-    name: Linux ${{ matrix.kernel }} llvm-${{ matrix.llvm-version }}
-    uses: ./.github/workflows/vmtest.yml
-    with:
-      runs_on: ${{ matrix.runs_on }}
-      kernel: ${{ matrix.kernel }}
-      arch: ${{ matrix.arch }}
-      llvm-version: ${{ matrix.llvm-version }}
-      pahole: ${{ matrix.pahole }}
+            runs_on: s390x
+            arch: 's390x'
+    steps:
+      - uses: actions/checkout@v4
+        name: Checkout
+      - uses: ./.github/actions/setup
+        name: Setup
+      - uses: ./.github/actions/vmtest
+        name: vmtest
+        with:
+          kernel: ${{ matrix.kernel }}
+          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

@@ -8,15 +8,10 @@ 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>

BPF-CHECKPOINT-COMMIT

@@ -1 +1 @@
-b4432656b36e5cc1d50a1f2dc15357543add530e
+3e9bc0472b910d4115e16e9c2d684c7757cb6c60

CHECKPOINT-COMMIT

@@ -1 +1 @@
-9325d53fe9adff354b6a93fda5f38c165947da0f
+0737df6de94661ae55fd3343ce9abec32c687e62

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-arch-Kconfig-Move-SPECULATION_MITIGATIONS-to-arch-Kc.patch

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

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

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

ci/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 +1,49 @@
+# 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
+sockmap_ktls
+spinlock
+stacktrace_map
+stacktrace_map_raw_tp
+static_linked
+task_fd_query_rawtp
+task_fd_query_tp
+tc_bpf
+tcp_estats
+test_global_funcs/arg_tag_ctx*
+tp_attach_query
+usdt/urand_pid_attach
+xdp
+xdp_noinline
+xdp_perf

ci/vmtest/configs/DENYLIST

@@ -12,4 +12,3 @@ xdp_bonding/xdp_bonding_features     # started failing after net merge from 359e
 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 +1,5 @@
+# This complements ALLOWLIST-5.5.0 but excludes subtest that can't work on 5.5
+
+btf			# "size check test", "func (Non zero vlen)"
+tailcalls		# tailcall_bpf2bpf_1, tailcall_bpf2bpf_2, tailcall_bpf2bpf_3
+tc_bpf/tc_bpf_non_root

ci/vmtest/configs/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/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

@@ -121,8 +121,6 @@ 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 +131,11 @@ 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]_             |           |
-+                                           +----------------------------------------+----------------------------------+-----------+
-|                                           | ``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``                   |           |
+|                                           |                                        | ``tc``                           |           |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
 | ``BPF_PROG_TYPE_SK_LOOKUP``               | ``BPF_SK_LOOKUP``                      | ``sk_lookup``                    |           |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
@@ -169,9 +155,7 @@ 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]_   |           |
-+                                           +                                        +----------------------------------+-----------+
-|                                           |                                        | ``struct_ops.s+`` [#struct_ops]_ | Yes       |
+| ``BPF_PROG_TYPE_STRUCT_OPS``              |                                        | ``struct_ops+``                  |           |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
 | ``BPF_PROG_TYPE_SYSCALL``                 |                                        | ``syscall``                      | Yes       |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
@@ -225,11 +209,5 @@ 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>``.

include/uapi/linux/bpf.h

@@ -51,9 +51,6 @@
 #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,
 };
@@ -1119,15 +1116,11 @@ enum bpf_attach_type {
 	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,
@@ -1210,7 +1203,6 @@ enum bpf_perf_event_type {
 #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
@@ -1433,8 +1425,6 @@ 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 {
@@ -1506,7 +1496,7 @@ union bpf_attr {
 		__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 {
@@ -1577,16 +1567,6 @@ union bpf_attr {
 		 * 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 */
@@ -1652,7 +1632,6 @@ 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 */
@@ -1989,21 +1968,15 @@ 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
- * 		of the following values:
- *
- * 		**BPF_F_RECOMPUTE_CSUM**
- * 			Automatically update *skb*\ **->csum** after storing the
- * 			bytes.
- * 		**BPF_F_INVALIDATE_HASH**
- * 			Set *skb*\ **->hash**, *skb*\ **->swhash** and *skb*\
- * 			**->l4hash** to 0.
+ * 		associated to *skb*, at *offset*. *flags* are a combination of
+ * 		**BPF_F_RECOMPUTE_CSUM** (automatically recompute the
+ * 		checksum for the packet after storing the bytes) and
+ * 		**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 +2028,7 @@ 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
@@ -2876,7 +2849,7 @@ 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**.
@@ -3126,6 +3099,10 @@ 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
  *
@@ -5390,7 +5367,7 @@ 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.
@@ -5540,12 +5517,11 @@ union bpf_attr {
  *		**-EOPNOTSUPP** 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.
- *		*dst* can be map value or local kptr. *ptr* can be NULL, otherwise
- *		it must be a referenced pointer which will be released when this helper
- *		is called.
+ *		Exchange kptr at pointer *map_value* with *ptr*, and return the
+ *		old value. *ptr* can be NULL, otherwise it must be a referenced
+ *		pointer which will be released when this helper is called.
  *	Return
  *		The old value of kptr (which can be NULL). The returned pointer
  *		if not NULL, is a reference which must be released using its
@@ -6028,10 +6004,7 @@ 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 +6044,11 @@ 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 +6195,10 @@ 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), /* used for XDP path */
-	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)
+	BPF_F_BROADCAST		= (1ULL << 3),
+	BPF_F_EXCLUDE_INGRESS	= (1ULL << 4),
 };
 
 #define __bpf_md_ptr(type, name)	\
@@ -6231,17 +6207,12 @@ 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_DELIVERY_MONO = 1,	/* DEPRECATED */
-	BPF_SKB_CLOCK_REALTIME = 0,
-	BPF_SKB_CLOCK_MONOTONIC = 1,
-	BPF_SKB_CLOCK_TAI = 2,
-	/* 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.
+	BPF_SKB_TSTAMP_UNSPEC,
+	BPF_SKB_TSTAMP_DELIVERY_MONO,	/* tstamp has mono delivery time */
+	/* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle,
+	 * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC
+	 * and try to deduce it by ingress, egress or skb->sk->sk_clockid.
 	 */
 };
 
@@ -6724,7 +6695,6 @@ struct bpf_link_info {
 					__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 */
@@ -6926,12 +6896,6 @@ 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
  */
@@ -7044,29 +7008,6 @@ 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
@@ -7132,8 +7073,6 @@ 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 {
@@ -7566,13 +7505,4 @@ 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,
-	 *             decl_tag and type_tag
+	 *             struct, union, enum, fwd and enum64
 	 */
 	__u32 info;
 	/* "size" is used by INT, ENUM, STRUCT, UNION, DATASEC and ENUM64.

include/uapi/linux/fcntl.h

@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_FCNTL_H
+#define _UAPI_LINUX_FCNTL_H
+
+#include <asm/fcntl.h>
+#include <linux/openat2.h>
+
+#define F_SETLEASE	(F_LINUX_SPECIFIC_BASE + 0)
+#define F_GETLEASE	(F_LINUX_SPECIFIC_BASE + 1)
+
+/*
+ * Cancel a blocking posix lock; internal use only until we expose an
+ * asynchronous lock api to userspace:
+ */
+#define F_CANCELLK	(F_LINUX_SPECIFIC_BASE + 5)
+
+/* Create a file descriptor with FD_CLOEXEC set. */
+#define F_DUPFD_CLOEXEC	(F_LINUX_SPECIFIC_BASE + 6)
+
+/*
+ * Request nofications on a directory.
+ * See below for events that may be notified.
+ */
+#define F_NOTIFY	(F_LINUX_SPECIFIC_BASE+2)
+
+/*
+ * Set and get of pipe page size array
+ */
+#define F_SETPIPE_SZ	(F_LINUX_SPECIFIC_BASE + 7)
+#define F_GETPIPE_SZ	(F_LINUX_SPECIFIC_BASE + 8)
+
+/*
+ * Set/Get seals
+ */
+#define F_ADD_SEALS	(F_LINUX_SPECIFIC_BASE + 9)
+#define F_GET_SEALS	(F_LINUX_SPECIFIC_BASE + 10)
+
+/*
+ * Types of seals
+ */
+#define F_SEAL_SEAL	0x0001	/* prevent further seals from being set */
+#define F_SEAL_SHRINK	0x0002	/* prevent file from shrinking */
+#define F_SEAL_GROW	0x0004	/* prevent file from growing */
+#define F_SEAL_WRITE	0x0008	/* prevent writes */
+#define F_SEAL_FUTURE_WRITE	0x0010  /* prevent future writes while mapped */
+#define F_SEAL_EXEC	0x0020  /* prevent chmod modifying exec bits */
+/* (1U << 31) is reserved for signed error codes */
+
+/*
+ * Set/Get write life time hints. {GET,SET}_RW_HINT operate on the
+ * underlying inode, while {GET,SET}_FILE_RW_HINT operate only on
+ * the specific file.
+ */
+#define F_GET_RW_HINT		(F_LINUX_SPECIFIC_BASE + 11)
+#define F_SET_RW_HINT		(F_LINUX_SPECIFIC_BASE + 12)
+#define F_GET_FILE_RW_HINT	(F_LINUX_SPECIFIC_BASE + 13)
+#define F_SET_FILE_RW_HINT	(F_LINUX_SPECIFIC_BASE + 14)
+
+/*
+ * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be
+ * used to clear any hints previously set.
+ */
+#define RWH_WRITE_LIFE_NOT_SET	0
+#define RWH_WRITE_LIFE_NONE	1
+#define RWH_WRITE_LIFE_SHORT	2
+#define RWH_WRITE_LIFE_MEDIUM	3
+#define RWH_WRITE_LIFE_LONG	4
+#define RWH_WRITE_LIFE_EXTREME	5
+
+/*
+ * The originally introduced spelling is remained from the first
+ * versions of the patch set that introduced the feature, see commit
+ * v4.13-rc1~212^2~51.
+ */
+#define RWF_WRITE_LIFE_NOT_SET	RWH_WRITE_LIFE_NOT_SET
+
+/*
+ * Types of directory notifications that may be requested.
+ */
+#define DN_ACCESS	0x00000001	/* File accessed */
+#define DN_MODIFY	0x00000002	/* File modified */
+#define DN_CREATE	0x00000004	/* File created */
+#define DN_DELETE	0x00000008	/* File removed */
+#define DN_RENAME	0x00000010	/* File renamed */
+#define DN_ATTRIB	0x00000020	/* File changed attibutes */
+#define DN_MULTISHOT	0x80000000	/* Don't remove notifier */
+
+/*
+ * The constants AT_REMOVEDIR and AT_EACCESS have the same value.  AT_EACCESS is
+ * meaningful only to faccessat, while AT_REMOVEDIR is meaningful only to
+ * unlinkat.  The two functions do completely different things and therefore,
+ * the flags can be allowed to overlap.  For example, passing AT_REMOVEDIR to
+ * faccessat would be undefined behavior and thus treating it equivalent to
+ * AT_EACCESS is valid undefined behavior.
+ */
+#define AT_FDCWD		-100    /* Special value used to indicate
+                                           openat should use the current
+                                           working directory. */
+#define AT_SYMLINK_NOFOLLOW	0x100   /* Do not follow symbolic links.  */
+#define AT_EACCESS		0x200	/* Test access permitted for
+                                           effective IDs, not real IDs.  */
+#define AT_REMOVEDIR		0x200   /* Remove directory instead of
+                                           unlinking file.  */
+#define AT_SYMLINK_FOLLOW	0x400   /* Follow symbolic links.  */
+#define AT_NO_AUTOMOUNT		0x800	/* Suppress terminal automount traversal */
+#define AT_EMPTY_PATH		0x1000	/* Allow empty relative pathname */
+
+#define AT_STATX_SYNC_TYPE	0x6000	/* Type of synchronisation required from statx() */
+#define AT_STATX_SYNC_AS_STAT	0x0000	/* - Do whatever stat() does */
+#define AT_STATX_FORCE_SYNC	0x2000	/* - Force the attributes to be sync'd with the server */
+#define AT_STATX_DONT_SYNC	0x4000	/* - Don't sync attributes with the server */
+
+#define AT_RECURSIVE		0x8000	/* Apply to the entire subtree */
+
+/* Flags for name_to_handle_at(2). We reuse AT_ flag space to save bits... */
+#define AT_HANDLE_FID		AT_REMOVEDIR	/* file handle is needed to
+					compare object identity and may not
+					be usable to open_by_handle_at(2) */
+#if defined(__KERNEL__)
+#define AT_GETATTR_NOSEC	0x80000000
+#endif
+
+#endif /* _UAPI_LINUX_FCNTL_H */

include/uapi/linux/if_link.h

@@ -377,7 +377,6 @@ enum {
 	IFLA_GSO_IPV4_MAX_SIZE,
 	IFLA_GRO_IPV4_MAX_SIZE,
 	IFLA_DPLL_PIN,
-	IFLA_MAX_PACING_OFFLOAD_HORIZON,
 	__IFLA_MAX
 };
 
@@ -462,286 +461,6 @@ 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 +510,6 @@ 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 +520,11 @@ 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     */
@@ -1293,19 +769,6 @@ enum netkit_mode {
 	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,
@@ -1313,10 +776,6 @@ enum {
 	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)
@@ -1395,7 +854,6 @@ enum {
 	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 +871,6 @@ 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,
@@ -1484,8 +935,6 @@ enum {
 	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)
@@ -1791,7 +1240,6 @@ enum {
 	IFLA_HSR_PROTOCOL,		/* Indicate different protocol than
 					 * HSR. For example PRP.
 					 */
-	IFLA_HSR_INTERLINK,		/* HSR interlink network device */
 	__IFLA_HSR_MAX,
 };
 
@@ -1969,9 +1417,7 @@ enum {
 
 enum {
 	IFLA_DSA_UNSPEC,
-	IFLA_DSA_CONDUIT,
-	/* Deprecated, use IFLA_DSA_CONDUIT instead */
-	IFLA_DSA_MASTER = IFLA_DSA_CONDUIT,
+	IFLA_DSA_MASTER,
 	__IFLA_DSA_MAX,
 };
 

include/uapi/linux/if_xdp.h

@@ -41,10 +41,6 @@
  */
 #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;
 	__u16 sxdp_flags;
@@ -117,22 +113,16 @@ struct xdp_options {
 	((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1)
 
 /* Request transmit timestamp. Upon completion, put it into tx_timestamp
- * field of struct xsk_tx_metadata.
+ * field of union xsk_tx_metadata.
  */
 #define XDP_TXMD_FLAGS_TIMESTAMP		(1 << 0)
 
 /* Request transmit checksum offload. Checksum start position and offset
- * are communicated via csum_start and csum_offset fields of struct
+ * are communicated via csum_start and csum_offset fields of union
  * 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.
@@ -148,10 +138,6 @@ struct xsk_tx_metadata {
 			__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 {

include/uapi/linux/netdev.h

@@ -59,13 +59,10 @@ enum netdev_xdp_rx_metadata {
  *   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 {
@@ -89,11 +86,6 @@ enum {
 	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,
@@ -101,8 +93,6 @@ enum {
 	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)
@@ -131,27 +121,16 @@ enum {
 	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)
@@ -167,43 +146,11 @@ enum {
 	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,
@@ -217,8 +164,6 @@ enum {
 	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)

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

@@ -385,8 +385,6 @@ 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 +511,7 @@ struct perf_event_attr {
 	__u16	sample_max_stack;
 	__u16	__reserved_2;
 	__u32	aux_sample_size;
-
-	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;
-		};
-	};
+	__u32	__reserved_3;
 
 	/*
 	 * User provided data if sigtrap=1, passed back to user via
@@ -1360,14 +1349,12 @@ 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 */
-#define PERF_MEM_LVLNUM_MSC	0x06 /* Memory-side Cache */
-/* 0x7 available */
+/* 5-0x7 available */
 #define PERF_MEM_LVLNUM_UNC	0x08 /* Uncached */
 #define PERF_MEM_LVLNUM_CXL	0x09 /* CXL */
 #define PERF_MEM_LVLNUM_IO	0x0a /* I/O */
 #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */
-#define PERF_MEM_LVLNUM_LFB	0x0c /* LFB / 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 */

src/Makefile

@@ -9,7 +9,7 @@ else
 endif
 
 LIBBPF_MAJOR_VERSION := 1
-LIBBPF_MINOR_VERSION := 6
+LIBBPF_MINOR_VERSION := 5
 LIBBPF_PATCH_VERSION := 0
 LIBBPF_VERSION := $(LIBBPF_MAJOR_VERSION).$(LIBBPF_MINOR_VERSION).$(LIBBPF_PATCH_VERSION)
 LIBBPF_MAJMIN_VERSION := $(LIBBPF_MAJOR_VERSION).$(LIBBPF_MINOR_VERSION).0
@@ -26,7 +26,6 @@ endef
 
 $(call allow-override,CC,$(CROSS_COMPILE)cc)
 $(call allow-override,LD,$(CROSS_COMPILE)ld)
-PKG_CONFIG ?= pkg-config
 
 TOPDIR = ..
 
@@ -42,12 +41,10 @@ ALL_CFLAGS += $(CFLAGS) 						\
 	      $(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 +55,7 @@ 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 elf.o features.o
 SHARED_OBJS := $(addprefix $(SHARED_OBJDIR)/,$(OBJS))
 STATIC_OBJS := $(addprefix $(STATIC_OBJDIR)/,$(OBJS))
 
@@ -122,13 +119,13 @@ $(OBJDIR)/libbpf.so.$(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

@@ -105,7 +105,7 @@ int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts)
  */
 int probe_memcg_account(int token_fd)
 {
-	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(),
@@ -238,7 +238,7 @@ 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, prog_token_fd);
 	void *finfo = NULL, *linfo = NULL;
 	const char *func_info, *line_info;
 	__u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd;
@@ -311,7 +311,6 @@ 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);
@@ -777,7 +776,6 @@ int bpf_link_create(int prog_fd, int target_fd,
 			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));
@@ -1097,7 +1095,7 @@ 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 +1105,6 @@ 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);

src/bpf.h

@@ -100,19 +100,16 @@ 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 token_fd
 
 LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type,
 			     const char *prog_name, const char *license,
@@ -132,7 +129,7 @@ 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.
@@ -487,10 +484,9 @@ 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,

src/bpf_core_read.h

@@ -104,7 +104,6 @@ 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))				      \
@@ -388,13 +387,7 @@ 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_helper_defs.h

@@ -44,14 +44,6 @@ struct bpf_dynptr;
 struct iphdr;
 struct ipv6hdr;
 
-#ifndef __bpf_fastcall
-#if __has_attribute(bpf_fastcall)
-#define __bpf_fastcall __attribute__((bpf_fastcall))
-#else
-#define __bpf_fastcall
-#endif
-#endif
-
 /*
  * bpf_map_lookup_elem
  *
@@ -211,21 +203,17 @@ static __u32 (* const bpf_get_prandom_u32)(void) = (void *) 7;
  * Returns
  * 	The SMP id of the processor running the program.
  */
-static __bpf_fastcall __u32 (* const bpf_get_smp_processor_id)(void) = (void *) 8;
+static __u32 (* const bpf_get_smp_processor_id)(void) = (void *) 8;
 
 /*
  * bpf_skb_store_bytes
  *
  * 	Store *len* bytes from address *from* into the packet
- * 	associated to *skb*, at *offset*. The *flags* are a combination
- * 	of the following values:
- *
- * 	**BPF_F_RECOMPUTE_CSUM**
- * 		Automatically update *skb*\ **->csum** after storing the
- * 		bytes.
- * 	**BPF_F_INVALIDATE_HASH**
- * 		Set *skb*\ **->hash**, *skb*\ **->swhash** and *skb*\
- * 		**->l4hash** to 0.
+ * 	associated to *skb*, at *offset*. *flags* are a combination of
+ * 	**BPF_F_RECOMPUTE_CSUM** (automatically recompute the
+ * 	checksum for the packet after storing the bytes) and
+ * 	**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
@@ -285,7 +273,7 @@ static long (* const bpf_l3_csum_replace)(struct __sk_buff *skb, __u32 offset, _
  * 	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
@@ -1236,7 +1224,7 @@ static long (* const bpf_set_hash)(struct __sk_buff *skb, __u32 hash) = (void *)
  * 	  **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**.
@@ -1523,6 +1511,10 @@ static long (* const bpf_getsockopt)(void *bpf_socket, int level, int optname, v
  * 	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.
+ *
  * Returns
  * 	0
  */
@@ -4228,7 +4220,7 @@ static long (* const bpf_find_vma)(struct task_struct *task, __u64 addr, void *c
  * 	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.
@@ -4432,10 +4424,9 @@ static long (* const bpf_ima_file_hash)(struct file *file, void *dst, __u32 size
 /*
  * bpf_kptr_xchg
  *
- * 	Exchange kptr at pointer *dst* with *ptr*, and return the old value.
- * 	*dst* can be map value or local kptr. *ptr* can be NULL, otherwise
- * 	it must be a referenced pointer which will be released when this helper
- * 	is called.
+ * 	Exchange kptr at pointer *map_value* with *ptr*, and return the
+ * 	old value. *ptr* can be NULL, otherwise it must be a referenced
+ * 	pointer which will be released when this helper is called.
  *
  * Returns
  * 	The old value of kptr (which can be NULL). The returned pointer
@@ -4443,7 +4434,7 @@ static long (* const bpf_ima_file_hash)(struct file *file, void *dst, __u32 size
  * 	corresponding release function, or moved into a BPF map before
  * 	program exit.
  */
-static void *(* const bpf_kptr_xchg)(void *dst, void *ptr) = (void *) 194;
+static void *(* const bpf_kptr_xchg)(void *map_value, void *ptr) = (void *) 194;
 
 /*
  * bpf_map_lookup_percpu_elem

src/bpf_helpers.h

@@ -15,14 +15,6 @@
 #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
  * different sections in elf_bpf file. Section names
@@ -193,23 +185,11 @@ enum libbpf_tristate {
 #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) ({						\
-	_Static_assert(!__builtin_constant_p(!!sym),			\
-		       #sym " should be marked as __weak");		\
-	!!sym;								\
+#define bpf_ksym_exists(sym) ({									\
+	_Static_assert(!__builtin_constant_p(!!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")))
@@ -350,7 +330,7 @@ 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

@@ -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 +362,12 @@ struct pt_regs___riscv {
 #define __PT_PARM7_REG a6
 #define __PT_PARM8_REG a7
 
-#define __PT_PARM1_SYSCALL_REG orig_a0
+#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 +473,7 @@ 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 +515,7 @@ 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 +633,25 @@ struct pt_regs;
 #endif
 
 #define ___bpf_ctx_cast0()            ctx
-#define ___bpf_ctx_cast1(x)           ___bpf_ctx_cast0(), ctx[0]
-#define ___bpf_ctx_cast2(x, args...)  ___bpf_ctx_cast1(args), ctx[1]
-#define ___bpf_ctx_cast3(x, args...)  ___bpf_ctx_cast2(args), ctx[2]
-#define ___bpf_ctx_cast4(x, args...)  ___bpf_ctx_cast3(args), ctx[3]
-#define ___bpf_ctx_cast5(x, args...)  ___bpf_ctx_cast4(args), ctx[4]
-#define ___bpf_ctx_cast6(x, args...)  ___bpf_ctx_cast5(args), ctx[5]
-#define ___bpf_ctx_cast7(x, args...)  ___bpf_ctx_cast6(args), ctx[6]
-#define ___bpf_ctx_cast8(x, args...)  ___bpf_ctx_cast7(args), ctx[7]
-#define ___bpf_ctx_cast9(x, args...)  ___bpf_ctx_cast8(args), ctx[8]
-#define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), ctx[9]
-#define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), ctx[10]
-#define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), ctx[11]
+#define ___bpf_ctx_cast1(x)           ___bpf_ctx_cast0(), (void *)ctx[0]
+#define ___bpf_ctx_cast2(x, args...)  ___bpf_ctx_cast1(args), (void *)ctx[1]
+#define ___bpf_ctx_cast3(x, args...)  ___bpf_ctx_cast2(args), (void *)ctx[2]
+#define ___bpf_ctx_cast4(x, args...)  ___bpf_ctx_cast3(args), (void *)ctx[3]
+#define ___bpf_ctx_cast5(x, args...)  ___bpf_ctx_cast4(args), (void *)ctx[4]
+#define ___bpf_ctx_cast6(x, args...)  ___bpf_ctx_cast5(args), (void *)ctx[5]
+#define ___bpf_ctx_cast7(x, args...)  ___bpf_ctx_cast6(args), (void *)ctx[6]
+#define ___bpf_ctx_cast8(x, args...)  ___bpf_ctx_cast7(args), (void *)ctx[7]
+#define ___bpf_ctx_cast9(x, args...)  ___bpf_ctx_cast8(args), (void *)ctx[8]
+#define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9]
+#define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10]
+#define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11]
 #define ___bpf_ctx_cast(args...)      ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args)
 
 /*
  * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and
  * similar kinds of BPF programs, that accept input arguments as a single
  * pointer to untyped u64 array, where each u64 can actually be a typed
- * pointer or integer of different size. Instead of 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 +786,14 @@ ____##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_args2(x, args...) ___bpf_kprobe_args1(args), (unsigned long long)PT_REGS_PARM2(ctx)
-#define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (unsigned long long)PT_REGS_PARM3(ctx)
-#define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (unsigned long long)PT_REGS_PARM4(ctx)
-#define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (unsigned long long)PT_REGS_PARM5(ctx)
-#define ___bpf_kprobe_args6(x, args...) ___bpf_kprobe_args5(args), (unsigned long long)PT_REGS_PARM6(ctx)
-#define ___bpf_kprobe_args7(x, args...) ___bpf_kprobe_args6(args), (unsigned long long)PT_REGS_PARM7(ctx)
-#define ___bpf_kprobe_args8(x, args...) ___bpf_kprobe_args7(args), (unsigned long long)PT_REGS_PARM8(ctx)
+#define ___bpf_kprobe_args1(x)          ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx)
+#define ___bpf_kprobe_args2(x, args...) ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx)
+#define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx)
+#define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx)
+#define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx)
+#define ___bpf_kprobe_args6(x, args...) ___bpf_kprobe_args5(args), (void *)PT_REGS_PARM6(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), (void *)PT_REGS_PARM8(ctx)
 #define ___bpf_kprobe_args(args...)     ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)
 
 /*
@@ -808,7 +801,7 @@ 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 +821,7 @@ 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 +845,24 @@ 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_args2(x, args...) ___bpf_syscall_args1(args), (unsigned long long)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_args4(x, args...) ___bpf_syscall_args3(args), (unsigned long long)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_args6(x, args...) ___bpf_syscall_args5(args), (unsigned long long)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_args1(x)          ___bpf_syscall_args0(), (void *)PT_REGS_PARM1_SYSCALL(regs)
+#define ___bpf_syscall_args2(x, args...) ___bpf_syscall_args1(args), (void *)PT_REGS_PARM2_SYSCALL(regs)
+#define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (void *)PT_REGS_PARM3_SYSCALL(regs)
+#define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (void *)PT_REGS_PARM4_SYSCALL(regs)
+#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (void *)PT_REGS_PARM5_SYSCALL(regs)
+#define ___bpf_syscall_args6(x, args...) ___bpf_syscall_args5(args), (void *)PT_REGS_PARM6_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_args2(x, args...) ___bpf_syswrap_args1(args), (unsigned long long)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_args4(x, args...) ___bpf_syswrap_args3(args), (unsigned long long)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_args6(x, args...) ___bpf_syswrap_args5(args), (unsigned long long)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_args1(x)          ___bpf_syswrap_args0(), (void *)PT_REGS_PARM1_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args2(x, args...) ___bpf_syswrap_args1(args), (void *)PT_REGS_PARM2_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args3(x, args...) ___bpf_syswrap_args2(args), (void *)PT_REGS_PARM3_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args4(x, args...) ___bpf_syswrap_args3(args), (void *)PT_REGS_PARM4_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args5(x, args...) ___bpf_syswrap_args4(args), (void *)PT_REGS_PARM5_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args6(x, args...) ___bpf_syswrap_args5(args), (void *)PT_REGS_PARM6_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;
-	const char *pad_type = NULL;
+	int new_off, pad_bits, bits, i;
+	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__((%s))", name);
-			else
-				btf_dump_printf(d, " __attribute__((btf_type_tag(\"%s\")))", name);
+			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
-			 * such case. Similarly and conveniently, valid
-			 * no args case can be special-cased here as well.
+			 * going to pretend there are no args for such case.
 			 */
-			if (vlen == 0 || (vlen == 1 && p->type == 0)) {
-				btf_dump_printf(d, "void)");
+			if (vlen == 1 && p->type == 0) {
+				btf_dump_printf(d, ")");
 				return;
 			}
 

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

@@ -24,12 +24,10 @@
 
 int elf_open(const char *binary_path, struct elf_fd *elf_fd)
 {
+	char errmsg[STRERR_BUFSIZE];
 	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;
@@ -37,7 +35,8 @@ int elf_open(const char *binary_path, struct elf_fd *elf_fd)
 	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));
+		pr_warn("elf: failed to open %s: %s\n", binary_path,
+			libbpf_strerror_r(ret, errmsg, sizeof(errmsg)));
 		return ret;
 	}
 	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);

src/features.c

@@ -22,7 +22,7 @@ int probe_fd(int fd)
 
 static int probe_kern_prog_name(int token_fd)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, prog_token_fd);
+	const size_t attr_sz = offsetofend(union bpf_attr, prog_name);
 	struct bpf_insn insns[] = {
 		BPF_MOV64_IMM(BPF_REG_0, 0),
 		BPF_EXIT_INSN(),
@@ -47,6 +47,7 @@ static int probe_kern_prog_name(int token_fd)
 
 static int probe_kern_global_data(int token_fd)
 {
+	char *cp, errmsg[STRERR_BUFSIZE];
 	struct bpf_insn insns[] = {
 		BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16),
 		BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42),
@@ -66,8 +67,9 @@ static int probe_kern_global_data(int token_fd)
 	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));
+		cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
+		pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n",
+			__func__, cp, -ret);
 		return ret;
 	}
 
@@ -265,6 +267,7 @@ static int probe_kern_probe_read_kernel(int token_fd)
 
 static int probe_prog_bind_map(int token_fd)
 {
+	char *cp, errmsg[STRERR_BUFSIZE];
 	struct bpf_insn insns[] = {
 		BPF_MOV64_IMM(BPF_REG_0, 0),
 		BPF_EXIT_INSN(),
@@ -282,8 +285,9 @@ static int probe_prog_bind_map(int token_fd)
 	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));
+		cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
+		pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n",
+			__func__, cp, -ret);
 		return ret;
 	}
 
@@ -388,41 +392,11 @@ static int probe_uprobe_multi_link(int token_fd)
 	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;
+	return link_fd < 0 && err == -EBADF;
 }
 
 static int probe_kern_bpf_cookie(int token_fd)
@@ -600,8 +574,7 @@ bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_
 		} 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));
+			pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret);
 			WRITE_ONCE(cache->res[feat_id], FEAT_MISSING);
 		}
 	}

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.key_size = tgt_endian(key_size);
-	attr.value_size = tgt_endian(value_size);
-	attr.map_flags = tgt_endian(map_attr->map_flags);
-	attr.map_extra = tgt_endian(map_attr->map_extra);
+	attr.map_type = map_type;
+	attr.key_size = key_size;
+	attr.value_size = value_size;
+	attr.map_flags = map_attr->map_flags;
+	attr.map_extra = map_attr->map_extra;
 	if (map_name)
 		libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name));
-	attr.numa_node = tgt_endian(map_attr->numa_node);
-	attr.map_ifindex = tgt_endian(map_attr->map_ifindex);
-	attr.max_entries = tgt_endian(max_entries);
-	attr.btf_key_type_id = tgt_endian(map_attr->btf_key_type_id);
-	attr.btf_value_type_id = tgt_endian(map_attr->btf_value_type_id);
+	attr.numa_node = map_attr->numa_node;
+	attr.map_ifindex = map_attr->map_ifindex;
+	attr.max_entries = max_entries;
+	attr.btf_key_type_id = map_attr->btf_key_type_id;
+	attr.btf_value_type_id = map_attr->btf_value_type_id;
+
+	pr_debug("gen: map_create: %s idx %d type %d value_type_id %d\n",
+		 attr.map_name, map_idx, map_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",
-		 map_name, map_idx, map_type, map_attr->btf_value_type_id,
-		 map_create_attr, attr_size);
-
-	if (map_attr->btf_value_type_id)
+	if (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,
-		  map_attr->btf_value_type_id);
+		  attr.map_name, map_idx, map_type, value_size,
+		  attr.btf_value_type_id);
 	emit_check_err(gen);
 	/* remember map_fd in the stack, if successful */
 	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,... */
-	return gen->swapped_endian ? 0xf0 : 0x0f;
-#elif defined(__BIG_ENDIAN_BITFIELD) /* dst_reg,src_reg,... */
-	return gen->swapped_endian ? 0x0f : 0xf0;
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	return 0x0f; /* src_reg,dst_reg,... */
+#elif defined(__BIG_ENDIAN_BITFIELD)
+	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 */
-	if (gen->swapped_endian) {
-		struct bpf_insn *insn = gen->data_start + insns_off;
-		int i;
-
-		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.prog_type = prog_type;
+	attr.expected_attach_type = load_attr->expected_attach_type;
+	attr.attach_btf_id = load_attr->attach_btf_id;
+	attr.prog_ifindex = load_attr->prog_ifindex;
 	attr.kern_version = 0;
-	attr.insn_cnt = tgt_endian((__u32)insn_cnt);
-	attr.prog_flags = tgt_endian(load_attr->prog_flags);
+	attr.insn_cnt = (__u32)insn_cnt;
+	attr.prog_flags = load_attr->prog_flags;
 
-	attr.func_info_rec_size = tgt_endian(load_attr->func_info_rec_size);
-	attr.func_info_cnt = tgt_endian(load_attr->func_info_cnt);
-	func_info = add_data(gen, load_attr->func_info, func_info_tot_sz);
-	pr_debug("gen: prog_load: func_info: off %d cnt %d rec size %d\n",
-		 func_info, load_attr->func_info_cnt,
-		 load_attr->func_info_rec_size);
+	attr.func_info_rec_size = load_attr->func_info_rec_size;
+	attr.func_info_cnt = load_attr->func_info_cnt;
+	func_info = add_data(gen, load_attr->func_info,
+			     attr.func_info_cnt * attr.func_info_rec_size);
 
-	attr.line_info_rec_size = tgt_endian(load_attr->line_info_rec_size);
-	attr.line_info_cnt = tgt_endian(load_attr->line_info_cnt);
-	line_info = add_data(gen, load_attr->line_info, line_info_tot_sz);
-	pr_debug("gen: prog_load: line_info: off %d cnt %d rec size %d\n",
-		 line_info, load_attr->line_info_cnt,
-		 load_attr->line_info_rec_size);
+	attr.line_info_rec_size = load_attr->line_info_rec_size;
+	attr.line_info_cnt = load_attr->line_info_cnt;
+	line_info = add_data(gen, load_attr->line_info,
+			     attr.line_info_cnt * attr.line_info_rec_size);
 
-	attr.core_relo_rec_size = tgt_endian((__u32)sizeof(struct bpf_core_relo));
-	attr.core_relo_cnt = tgt_endian(gen->core_relo_cnt);
-	core_relos = add_data(gen, gen->core_relos, core_relo_tot_sz);
-	pr_debug("gen: prog_load: core_relos: off %d cnt %d rec size %zd\n",
-		 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);
+	attr.core_relo_rec_size = sizeof(struct bpf_core_relo);
+	attr.core_relo_cnt = gen->core_relo_cnt;
+	core_relos = add_data(gen, gen->core_relos,
+			     attr.core_relo_cnt * attr.core_relo_rec_size);
 
 	libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
 	prog_load_attr = add_data(gen, &attr, attr_size);
-	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, &tgt_slot, sizeof(tgt_slot));
+	key = add_data(gen, &slot, sizeof(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 (cur = (map)->buckets[bkt]; cur; cur = cur->next)
+	for (bkt = 0; bkt < map->cap; bkt++)				    \
+		for (cur = map->buckets[bkt]; cur; cur = cur->next)
 
 /*
  * hashmap__for_each_entry_safe - iterate over all entries in hashmap, safe
@@ -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 (cur = (map)->buckets[bkt];				    \
+	for (bkt = 0; bkt < map->cap; 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					    \
-		     ? (map)->buckets[hash_bits((map)->hash_fn((_key), (map)->ctx), (map)->cap_bits)] \
+	for (cur = map->buckets						    \
+		     ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
 		     : NULL;						    \
 	     cur;							    \
 	     cur = cur->next)						    \
-		if ((map)->equal_fn(cur->key, (_key), (map)->ctx))
+		if (map->equal_fn(cur->key, (_key), map->ctx))
 
 #define hashmap__for_each_key_entry_safe(map, cur, tmp, _key)		    \
-	for (cur = (map)->buckets					    \
-		     ? (map)->buckets[hash_bits((map)->hash_fn((_key), (map)->ctx), (map)->cap_bits)] \
+	for (cur = map->buckets						    \
+		     ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
 		     : NULL;						    \
 	     cur && ({ tmp = cur->next; true; });			    \
 	     cur = tmp)							    \
-		if ((map)->equal_fn(cur->key, (_key), (map)->ctx))
+		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
- * 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.
+ * be used for libbpf warnings and informational messages.
  * @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
@@ -241,19 +238,6 @@ 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
@@ -307,14 +291,6 @@ 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 +452,7 @@ 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,
@@ -565,12 +541,10 @@ struct bpf_kprobe_multi_opts {
 	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 session
 
 LIBBPF_API struct bpf_link *
 bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
@@ -592,12 +566,10 @@ struct bpf_uprobe_multi_opts {
 	size_t cnt;
 	/* create return uprobes */
 	bool retprobe;
-	/* create session kprobes */
-	bool session;
 	size_t :0;
 };
 
-#define bpf_uprobe_multi_opts__last_field session
+#define bpf_uprobe_multi_opts__last_field retprobe
 
 /**
  * @brief **bpf_program__attach_uprobe_multi()** attaches a BPF program
@@ -704,7 +676,7 @@ 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.
  *
@@ -940,12 +912,6 @@ 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 +975,6 @@ 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
@@ -1624,11 +1573,11 @@ 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 +1669,6 @@ struct bpf_map_skeleton {
 	const char *name;
 	struct bpf_map **map;
 	void **mmaped;
-	struct bpf_link **link;
 };
 
 struct bpf_prog_skeleton {
@@ -1817,14 +1765,9 @@ 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

@@ -419,28 +419,7 @@ LIBBPF_1.4.0 {
 
 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_internal.h

@@ -10,7 +10,6 @@
 #define __LIBBPF_LIBBPF_INTERNAL_H
 
 #include <stdlib.h>
-#include <byteswap.h>
 #include <limits.h>
 #include <errno.h>
 #include <linux/err.h>
@@ -235,9 +234,6 @@ 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)
 {
@@ -409,7 +405,6 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
 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 +445,11 @@ 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 +481,6 @@ 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;
@@ -515,59 +508,11 @@ 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,
@@ -618,16 +563,6 @@ 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).
@@ -662,18 +597,13 @@ static inline int ensure_good_fd(int fd)
 	return fd;
 }
 
-static inline int sys_dup3(int oldfd, int newfd, int flags)
+static inline int sys_dup2(int oldfd, int newfd)
 {
-	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);
+#ifdef __NR_dup2
+	return syscall(__NR_dup2, oldfd, newfd);
+#else
+	return syscall(__NR_dup3, oldfd, newfd, 0);
+#endif
 }
 
 /* Point *fixed_fd* to the same file that *tmp_fd* points to.
@@ -684,7 +614,7 @@ static inline int reuse_fd(int fixed_fd, int tmp_fd)
 {
 	int err;
 
-	err = sys_dup3(tmp_fd, fixed_fd, O_CLOEXEC);
+	err = sys_dup2(tmp_fd, fixed_fd);
 	err = err < 0 ? -errno : 0;
 	close(tmp_fd); /* clean up temporary FD */
 	return err;

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

@@ -98,7 +98,7 @@ __u32 get_kernel_version(void)
 		return 0;
 
 	if (major == 4 && minor == 19 && patch > 255)
-		return KERNEL_VERSION(major, minor, 255);
+		return KERNEL_VERSION(major, minor, 255);;
 
 	return KERNEL_VERSION(major, minor, patch);
 }

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 5
 
 #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,
-			       const char *filename);
-
-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);
 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);
-	if (!linker->filename) {
-		err = -ENOMEM;
-		goto err_out;
-	}
+	linker->fd = -1;
 
-	linker->fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644);
-	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);
+	err = init_output_elf(linker, filename);
 	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 */
-	linker->elf_hdr->e_ident[EI_DATA] = ELFDATANONE;
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	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,
-			       const char *filename)
+int bpf_linker__add_file(struct bpf_linker *linker, const char *filename,
+			 const struct bpf_linker_file_opts *opts)
 {
 	struct src_obj obj = {};
 	int err = 0;
 
-	obj.filename = filename;
-	obj.fd = fd;
+	if (!OPTS_VALID(opts, bpf_linker_file_opts))
+		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);
-		return -EINVAL;
+		err = -errno;
+		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);
-		return -EINVAL;
-	}
-
-	/* 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);
+		err = -errno;
+		pr_warn_elf("failed to get ELF header for %s", filename);
 		return err;
 	}
-	if (link_byteorder == ELFDATANONE) {
-		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) {
+	if (ehdr->e_ident[EI_DATA] != host_endianness) {
 		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);
-		return -EINVAL;
+		err = -errno;
+		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);
-			return -EINVAL;
+				    sec_idx, filename);
+			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);
-			return -EINVAL;
+				    sec_idx, filename);
+			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);
-			return -EINVAL;
+				    sec_idx, sec_name, filename);
+			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",
-						obj->filename, errstr(err));
+					pr_warn("failed to parse .BTF from %s: %d\n", filename, 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",
-						obj->filename, errstr(err));
+					pr_warn("failed to parse .BTF.ext from '%s': %d\n", filename, 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;
 		}
@@ -1087,33 +957,19 @@ 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 +1095,6 @@ 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 +1154,6 @@ 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 +1210,7 @@ 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 +1399,7 @@ 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 +1948,7 @@ 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 +1997,7 @@ 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 +2057,7 @@ 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 +2213,10 @@ 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;
-			int var_linkage;
+			const char *var_name = btf__str_by_offset(obj->btf, vt->name_off);
+			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 +2234,26 @@ 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 +2324,9 @@ 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 (err)
-			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];
-		}
+		if (btf_type_visit_type_ids(dst_t, remap_type_id, obj->btf_type_map))
+			return -EINVAL;
 	}
 
 	/* Rewrite VAR/FUNC underlying types (i.e., FUNC's FUNC_PROTO and VAR's
@@ -2567,10 +2394,6 @@ 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 +2607,27 @@ 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)
-		close(linker->fd);
+	linker->elf = NULL;
 	linker->fd = -1;
 
 	return 0;
@@ -2857,7 +2675,6 @@ 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 +2708,17 @@ 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)
@@ -2916,7 +2726,7 @@ 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;
 	}
 
@@ -2928,7 +2738,7 @@ static int finalize_btf(struct bpf_linker *linker)
 
 		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 +2914,7 @@ 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/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;
-			 * note, for arrays we care about individual element
-			 * 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);
+			/* remember field size for load/store mem size */
+			sz = btf__resolve_size(spec->btf, acc->type_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;
-			 * 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;
+			*field_sz = byte_sz;
 			*type_id = field_type_id;
 		}
 		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;
@@ -89,8 +88,8 @@ 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",
-			map_fd, errstr(err));
+		pr_warn("ringbuf: failed to get map info for fd=%d: %d\n",
+			map_fd, err);
 		return libbpf_err(err);
 	}
 
@@ -124,8 +123,8 @@ 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",
-			map_fd, errstr(err));
+		pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %d\n",
+			map_fd, err);
 		goto err_out;
 	}
 	r->consumer_pos = tmp;
@@ -143,8 +142,8 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 	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",
-			map_fd, errstr(err));
+		pr_warn("ringbuf: failed to mmap data pages for map fd=%d: %d\n",
+			map_fd, err);
 		goto err_out;
 	}
 	r->producer_pos = tmp;
@@ -157,8 +156,8 @@ 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",
-			map_fd, errstr(err));
+		pr_warn("ringbuf: failed to epoll add map fd=%d: %d\n",
+			map_fd, err);
 		goto err_out;
 	}
 
@@ -206,7 +205,7 @@ 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;
 	}
 
@@ -302,7 +301,7 @@ int ring_buffer__consume_n(struct ring_buffer *rb, size_t n)
 		if (n == 0)
 			break;
 	}
-	return res > INT_MAX ? INT_MAX : res;
+	return res;
 }
 
 /* Consume available ring buffer(s) data without event polling.
@@ -406,7 +405,7 @@ int ring__map_fd(const struct ring *r)
 
 int ring__consume_n(struct ring *r, size_t n)
 {
-	int64_t res;
+	int res;
 
 	res = ringbuf_process_ring(r, n);
 	if (res < 0)
@@ -459,8 +458,7 @@ 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",
-			map_fd, errstr(err));
+		pr_warn("user ringbuf: failed to get map info for fd=%d: %d\n", map_fd, err);
 		return err;
 	}
 
@@ -476,8 +474,8 @@ 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",
-			map_fd, errstr(err));
+		pr_warn("user ringbuf: failed to mmap consumer page for map fd=%d: %d\n",
+			map_fd, err);
 		return err;
 	}
 	rb->consumer_pos = tmp;
@@ -496,8 +494,8 @@ 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",
-			map_fd, errstr(err));
+		pr_warn("user ringbuf: failed to mmap data pages for map fd=%d: %d\n",
+			map_fd, err);
 		return err;
 	}
 
@@ -508,7 +506,7 @@ 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 +531,7 @@ 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
-	 * handle the error, on glibc >=2.13 *positive* (errno-like) error
-	 * 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);
-	}
+	if (ret)
+		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

@@ -6,14 +6,4 @@
 
 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

@@ -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_args2(x, args...) ___bpf_usdt_args1(args), ({ long _x; bpf_usdt_arg(ctx, 1, &_x); _x; })
-#define ___bpf_usdt_args3(x, args...) ___bpf_usdt_args2(args), ({ long _x; bpf_usdt_arg(ctx, 2, &_x); _x; })
-#define ___bpf_usdt_args4(x, args...) ___bpf_usdt_args3(args), ({ long _x; bpf_usdt_arg(ctx, 3, &_x); _x; })
-#define ___bpf_usdt_args5(x, args...) ___bpf_usdt_args4(args), ({ long _x; bpf_usdt_arg(ctx, 4, &_x); _x; })
-#define ___bpf_usdt_args6(x, args...) ___bpf_usdt_args5(args), ({ long _x; bpf_usdt_arg(ctx, 5, &_x); _x; })
-#define ___bpf_usdt_args7(x, args...) ___bpf_usdt_args6(args), ({ long _x; bpf_usdt_arg(ctx, 6, &_x); _x; })
-#define ___bpf_usdt_args8(x, args...) ___bpf_usdt_args7(args), ({ long _x; bpf_usdt_arg(ctx, 7, &_x); _x; })
-#define ___bpf_usdt_args9(x, args...) ___bpf_usdt_args8(args), ({ long _x; bpf_usdt_arg(ctx, 8, &_x); _x; })
-#define ___bpf_usdt_args10(x, args...) ___bpf_usdt_args9(args), ({ long _x; bpf_usdt_arg(ctx, 9, &_x); _x; })
-#define ___bpf_usdt_args11(x, args...) ___bpf_usdt_args10(args), ({ long _x; bpf_usdt_arg(ctx, 10, &_x); _x; })
-#define ___bpf_usdt_args12(x, args...) ___bpf_usdt_args11(args), ({ long _x; bpf_usdt_arg(ctx, 11, &_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); (void *)_x; })
+#define ___bpf_usdt_args3(x, args...) ___bpf_usdt_args2(args), ({ long _x; bpf_usdt_arg(ctx, 2, &_x); (void *)_x; })
+#define ___bpf_usdt_args4(x, args...) ___bpf_usdt_args3(args), ({ long _x; bpf_usdt_arg(ctx, 3, &_x); (void *)_x; })
+#define ___bpf_usdt_args5(x, args...) ___bpf_usdt_args4(args), ({ long _x; bpf_usdt_arg(ctx, 4, &_x); (void *)_x; })
+#define ___bpf_usdt_args6(x, args...) ___bpf_usdt_args5(args), ({ long _x; bpf_usdt_arg(ctx, 5, &_x); (void *)_x; })
+#define ___bpf_usdt_args7(x, args...) ___bpf_usdt_args6(args), ({ long _x; bpf_usdt_arg(ctx, 6, &_x); (void *)_x; })
+#define ___bpf_usdt_args8(x, args...) ___bpf_usdt_args7(args), ({ long _x; bpf_usdt_arg(ctx, 7, &_x); (void *)_x; })
+#define ___bpf_usdt_args9(x, args...) ___bpf_usdt_args8(args), ({ long _x; bpf_usdt_arg(ctx, 8, &_x); (void *)_x; })
+#define ___bpf_usdt_args10(x, args...) ___bpf_usdt_args9(args), ({ long _x; bpf_usdt_arg(ctx, 9, &_x); (void *)_x; })
+#define ___bpf_usdt_args11(x, args...) ___bpf_usdt_args10(args), ({ long _x; bpf_usdt_arg(ctx, 10, &_x); (void *)_x; })
+#define ___bpf_usdt_args12(x, args...) ___bpf_usdt_args11(args), ({ long _x; bpf_usdt_arg(ctx, 11, &_x); (void *)_x; })
 #define ___bpf_usdt_args(args...) ___bpf_apply(___bpf_usdt_args, ___bpf_narg(args))(args)
 
 /*

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
@@ -466,8 +465,8 @@ 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",
-			lib_path, errstr(-errno));
+		pr_warn("usdt: failed to get absolute path of '%s' (err %d), using path as is...\n",
+			lib_path, -errno);
 		libbpf_strlcpy(path, lib_path, sizeof(path));
 	}
 
@@ -476,8 +475,8 @@ proceed:
 	f = fopen(line, "re");
 	if (!f) {
 		err = -errno;
-		pr_warn("usdt: failed to open '%s' to get base addr of '%s': %s\n",
-			line, lib_path, errstr(err));
+		pr_warn("usdt: failed to open '%s' to get base addr of '%s': %d\n",
+			line, lib_path, err);
 		return err;
 	}
 
@@ -607,8 +606,7 @@ 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",
-			path, errstr(err));
+		pr_warn("usdt: failed to process ELF program segments for '%s': %d\n", path, err);
 		goto err_out;
 	}
 
@@ -661,7 +659,7 @@ 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 +708,8 @@ 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",
-						pid, path, errstr(err));
+					pr_warn("usdt: failed to get memory segments in PID %d for shared library '%s': %d\n",
+						pid, path, err);
 					goto err_out;
 				}
 			}
@@ -1049,8 +1047,8 @@ 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",
-				spec_id, usdt_provider, usdt_name, path, errstr(err));
+			pr_warn("usdt: failed to set USDT spec #%d for '%s:%s' in '%s': %d\n",
+				spec_id, usdt_provider, usdt_name, path, err);
 			goto err_out;
 		}
 		if (!man->has_bpf_cookie &&
@@ -1060,9 +1058,9 @@ 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;
 		}
@@ -1078,8 +1076,8 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct
 								      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));
+				pr_warn("usdt: failed to attach uprobe #%d for '%s:%s' in '%s': %d\n",
+					i, usdt_provider, usdt_name, path, err);
 				goto err_out;
 			}
 
@@ -1101,8 +1099,8 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct
 								    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));
+			pr_warn("usdt: failed to attach uprobe multi for '%s:%s' in '%s': %d\n",
+				usdt_provider, usdt_name, path, err);
 			goto err_out;
 		}
 

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;