Merge branch 'libbpf:master' into master

Syncing latest libbpf commits from kernel repository.
Baseline bpf-next commit:   0e43662e61f2569500ab83b8188c065603530785
Checkpoint bpf-next commit: 7b43df6c6ec38c9097420902a1c8165c4b25bf70
Baseline bpf commit:        f506439ec3dee11e0e77b0a1f3fb3eec22c97873
Checkpoint bpf commit:      54c3f1a81421f85e60ae2eaae7be3727a09916ee

Changbin Du (1):
  libbpf: Show error info about missing ".BTF" section

Christian Ehrig (1):
  bpf: Add flag BPF_F_NO_TUNNEL_KEY to bpf_skb_set_tunnel_key()

Khem Raj (1):
  libbpf: Fix build warning on ref_ctr_off for 32-bit architectures

 include/uapi/linux/bpf.h | 4 ++++
 src/btf.c                | 1 +
 src/libbpf.c             | 2 +-
 3 files changed, 6 insertions(+), 1 deletion(-)

--
2.30.2

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

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

@@ -1,3 +1,5 @@
+# shellcheck shell=bash
+
 # $1 - start or end
 # $2 - fold identifier, no spaces
 # $3 - fold section description

.github/actions/setup/action.yml

@@ -6,7 +6,7 @@ runs:
     - id: variables
       run: |
         export REPO_ROOT=$GITHUB_WORKSPACE
-        export CI_ROOT=$REPO_ROOT/travis-ci
+        export CI_ROOT=$REPO_ROOT/ci
         # this is somewhat ugly, but that is the easiest way to share this code with
         # arch specific docker
         echo 'echo ::group::Env setup' > /tmp/ci_setup
@@ -16,7 +16,7 @@ runs:
         echo export PROJECT_NAME='libbpf' >> /tmp/ci_setup
         echo export AUTHOR_EMAIL="$(git log -1 --pretty=\"%aE\")" >> /tmp/ci_setup
         echo export REPO_ROOT=$GITHUB_WORKSPACE >> /tmp/ci_setup
-        echo export CI_ROOT=$REPO_ROOT/travis-ci >> /tmp/ci_setup
+        echo export CI_ROOT=$REPO_ROOT/ci >> /tmp/ci_setup
         echo export VMTEST_ROOT=$CI_ROOT/vmtest >> /tmp/ci_setup
         echo 'echo ::endgroup::' >> /tmp/ci_setup
       shell: bash

.github/actions/vmtest/action.yml

@@ -36,7 +36,7 @@ runs:
     - name: Patch kernel source
       uses: libbpf/ci/patch-kernel@master
       with:
-        patches-root: '${{ github.workspace }}/travis-ci/diffs'
+        patches-root: '${{ github.workspace }}/ci/diffs'
         repo-root: '.kernel'
     - name: Prepare to build BPF selftests
       shell: bash
@@ -77,11 +77,14 @@ runs:
     # 4. prepare rootfs
     - name: prepare rootfs
       uses: libbpf/ci/prepare-rootfs@master
+      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

.github/workflows/build.yml

@@ -23,14 +23,24 @@ jobs:
             target: RUN
           - name: ASan+UBSan
             target: RUN_ASAN
-          - name: clang
-            target: RUN_CLANG
           - name: clang ASan+UBSan
             target: RUN_CLANG_ASAN
-          - name: gcc-10
-            target: RUN_GCC10
           - name: gcc-10 ASan+UBSan
             target: RUN_GCC10_ASAN
+          - name: clang
+            target: RUN_CLANG
+          - name: clang-14
+            target: RUN_CLANG14
+          - name: clang-15
+            target: RUN_CLANG15
+          - name: clang-16
+            target: RUN_CLANG16
+          - name: gcc-10
+            target: RUN_GCC10
+          - name: gcc-11
+            target: RUN_GCC11
+          - name: gcc-12
+            target: RUN_GCC12
     steps:
       - uses: actions/checkout@v3
         name: Checkout

.github/workflows/codeql.yml

@@ -0,0 +1,52 @@
+---
+# vi: ts=2 sw=2 et:
+
+name: "CodeQL"
+
+on:
+  push:
+    branches:
+      - master
+  pull_request:
+    branches:
+      - master
+
+permissions:
+  contents: read
+
+jobs:
+  analyze:
+    name: Analyze
+    runs-on: ubuntu-22.04
+    concurrency:
+      group: ${{ github.workflow }}-${{ matrix.language }}-${{ github.ref }}
+      cancel-in-progress: true
+    permissions:
+      actions: read
+      security-events: write
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language: ['cpp', 'python']
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      - name: Initialize CodeQL
+        uses: github/codeql-action/init@v2
+        with:
+          languages: ${{ matrix.language }}
+          queries: +security-extended,security-and-quality
+
+      - name: Setup
+        uses: ./.github/actions/setup
+
+      - name: Build
+        run: |
+          source /tmp/ci_setup
+          make -C ./src
+
+      - name: Perform CodeQL Analysis
+        uses: github/codeql-action/analyze@v2

.github/workflows/lint.yml

@@ -0,0 +1,19 @@
+name: "lint"
+
+on:
+  pull_request:
+  push:
+    branches:
+      - master
+
+jobs:
+  shellcheck:
+    name: ShellCheck
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+      - name: Run ShellCheck
+        uses: ludeeus/action-shellcheck@master
+        env:
+          SHELLCHECK_OPTS: --severity=error

.github/workflows/pahole.yml

@@ -7,7 +7,7 @@ on:
 
 jobs:
   vmtest:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-20.04
     name: Kernel LATEST + staging pahole
     env:
       STAGING: tmp.master

.github/workflows/test.yml

@@ -19,16 +19,16 @@ jobs:
       matrix:
         include:
           - kernel: 'LATEST'
-            runs_on: ubuntu-latest
+            runs_on: ubuntu-20.04
             arch: 'x86_64'
           - kernel: '5.5.0'
-            runs_on: ubuntu-latest
+            runs_on: ubuntu-20.04
             arch: 'x86_64'
           - kernel: '4.9.0'
-            runs_on: ubuntu-latest
+            runs_on: ubuntu-20.04
             arch: 'x86_64'
           - kernel: 'LATEST'
-            runs_on: z15
+            runs_on: s390x
             arch: 's390x'
     steps:
       - uses: actions/checkout@v3

.lgtm.yml

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

BPF-CHECKPOINT-COMMIT

@@ -1 +1 @@
-60240bc26114543fcbfcd8a28466e67e77b20388
+54c3f1a81421f85e60ae2eaae7be3727a09916ee

CHECKPOINT-COMMIT

@@ -1 +1 @@
-87dbdc230d162bf9ee1ac77c8ade178b6b1e199e
+7b43df6c6ec38c9097420902a1c8165c4b25bf70

README.md

@@ -5,9 +5,10 @@
 
 libbpf
 [![Github Actions Builds & Tests](https://github.com/libbpf/libbpf/actions/workflows/test.yml/badge.svg)](https://github.com/libbpf/libbpf/actions/workflows/test.yml)
-[![Total alerts](https://img.shields.io/lgtm/alerts/g/libbpf/libbpf.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/libbpf/libbpf/alerts/)
 [![Coverity](https://img.shields.io/coverity/scan/18195.svg)](https://scan.coverity.com/projects/libbpf)
+[![CodeQL](https://github.com/libbpf/libbpf/workflows/CodeQL/badge.svg?branch=master)](https://github.com/libbpf/libbpf/actions?query=workflow%3ACodeQL+branch%3Amaster)
 [![OSS-Fuzz Status](https://oss-fuzz-build-logs.storage.googleapis.com/badges/libbpf.svg)](https://oss-fuzz-build-logs.storage.googleapis.com/index.html#libbpf)
+[![Read the Docs](https://readthedocs.org/projects/libbpf/badge/?version=latest)](https://libbpf.readthedocs.io/en/latest/)
 ======
 
 **This is the official home of the libbpf library.**
@@ -144,7 +145,7 @@ Distributions packaging libbpf from this mirror:
   - [Fedora](https://src.fedoraproject.org/rpms/libbpf)
   - [Gentoo](https://packages.gentoo.org/packages/dev-libs/libbpf)
   - [Debian](https://packages.debian.org/source/sid/libbpf)
-  - [Arch](https://www.archlinux.org/packages/extra/x86_64/libbpf/)
+  - [Arch](https://archlinux.org/packages/core/x86_64/libbpf/)
   - [Ubuntu](https://packages.ubuntu.com/source/impish/libbpf)
   - [Alpine](https://pkgs.alpinelinux.org/packages?name=libbpf)
 

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

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

ci/managers/debian.sh

@@ -6,7 +6,7 @@ CONT_NAME="${CONT_NAME:-libbpf-debian-$DEBIAN_RELEASE}"
 ENV_VARS="${ENV_VARS:-}"
 DOCKER_RUN="${DOCKER_RUN:-docker run}"
 REPO_ROOT="${REPO_ROOT:-$PWD}"
-ADDITIONAL_DEPS=(clang pkg-config gcc-10)
+ADDITIONAL_DEPS=(pkgconf)
 EXTRA_CFLAGS=""
 EXTRA_LDFLAGS=""
 
@@ -43,30 +43,35 @@ for phase in "${PHASES[@]}"; do
             docker_exec bash -c "echo deb-src http://deb.debian.org/debian $DEBIAN_RELEASE main >>/etc/apt/sources.list"
             docker_exec apt-get -y update
             docker_exec apt-get -y install aptitude
-            docker_exec aptitude -y build-dep libelf-dev
-            docker_exec aptitude -y install libelf-dev
+            docker_exec aptitude -y install make libz-dev libelf-dev
             docker_exec aptitude -y install "${ADDITIONAL_DEPS[@]}"
             echo -e "::endgroup::"
             ;;
-        RUN|RUN_CLANG|RUN_GCC10|RUN_ASAN|RUN_CLANG_ASAN|RUN_GCC10_ASAN)
+        RUN|RUN_CLANG|RUN_CLANG14|RUN_CLANG15|RUN_CLANG16|RUN_GCC10|RUN_GCC11|RUN_GCC12|RUN_ASAN|RUN_CLANG_ASAN|RUN_GCC10_ASAN)
             CC="cc"
-            if [[ "$phase" = *"CLANG"* ]]; then
+            if [[ "$phase" =~ "RUN_CLANG(\d+)(_ASAN)?" ]]; then
+                ENV_VARS="-e CC=clang-${BASH_REMATCH[1]} -e CXX=clang++-${BASH_REMATCH[1]}"
+                CC="clang-${BASH_REMATCH[1]}"
+            elif [[ "$phase" = *"CLANG"* ]]; then
                 ENV_VARS="-e CC=clang -e CXX=clang++"
                 CC="clang"
-            elif [[ "$phase" = *"GCC10"* ]]; then
-                ENV_VARS="-e CC=gcc-10 -e CXX=g++-10"
-                CC="gcc-10"
-            else
-                EXTRA_CFLAGS="${EXTRA_CFLAGS} -Wno-stringop-truncation"
+            elif [[ "$phase" =~ "RUN_GCC(\d+)(_ASAN)?" ]]; then
+                ENV_VARS="-e CC=gcc-${BASH_REMATCH[1]} -e CXX=g++-${BASH_REMATCH[1]}"
+                CC="gcc-${BASH_REMATCH[1]}"
             fi
             if [[ "$phase" = *"ASAN"* ]]; then
                 EXTRA_CFLAGS="${EXTRA_CFLAGS} -fsanitize=address,undefined"
                 EXTRA_LDFLAGS="${EXTRA_LDFLAGS} -fsanitize=address,undefined"
             fi
+            if [[ "$CC" != "cc" ]]; then
+                docker_exec aptitude -y install "$CC"
+            else
+                docker_exec aptitude -y install gcc
+            fi
             docker_exec mkdir build install
             docker_exec ${CC} --version
             info "build"
-	    docker_exec make -j$((4*$(nproc))) EXTRA_CFLAGS="${EXTRA_CFLAGS}" EXTRA_LDFLAGS="${EXTRA_LDFLAGS}" -C ./src -B OBJDIR=../build
+            docker_exec make -j$((4*$(nproc))) EXTRA_CFLAGS="${EXTRA_CFLAGS}" EXTRA_LDFLAGS="${EXTRA_LDFLAGS}" -C ./src -B OBJDIR=../build
             info "ldd build/libbpf.so:"
             docker_exec ldd build/libbpf.so
             if ! docker_exec ldd build/libbpf.so | grep -q libelf; then

ci/rootfs/mkrootfs_arch.sh

@@ -1,107 +0,0 @@
-#!/bin/bash
-
-# This script is based on drgn script for generating Arch Linux bootstrap
-# images.
-# https://github.com/osandov/drgn/blob/master/scripts/vmtest/mkrootfs.sh
-
-set -euo pipefail
-
-usage () {
-	USAGE_STRING="usage: $0 [NAME]
-       $0 -h
-
-Build an Arch Linux root filesystem image for testing libbpf in a virtual
-machine.
-
-The image is generated as a zstd-compressed tarball.
-
-This must be run as root, as most of the installation is done in a chroot.
-
-Arguments:
-  NAME   name of generated image file (default:
-         libbpf-vmtest-rootfs-\$DATE.tar.zst)
-
-Options:
-  -h     display this help message and exit"
-
-	case "$1" in
-		out)
-			echo "$USAGE_STRING"
-			exit 0
-			;;
-		err)
-			echo "$USAGE_STRING" >&2
-			exit 1
-			;;
-	esac
-}
-
-while getopts "h" OPT; do
-	case "$OPT" in
-		h)
-			usage out
-			;;
-		*)
-			usage err
-			;;
-	esac
-done
-if [[ $OPTIND -eq $# ]]; then
-	NAME="${!OPTIND}"
-elif [[ $OPTIND -gt $# ]]; then
-	NAME="libbpf-vmtest-rootfs-$(date +%Y.%m.%d).tar.zst"
-else
-	usage err
-fi
-
-pacman_conf=
-root=
-trap 'rm -rf "$pacman_conf" "$root"' EXIT
-pacman_conf="$(mktemp -p "$PWD")"
-cat > "$pacman_conf" << "EOF"
-[options]
-Architecture = x86_64
-CheckSpace
-SigLevel = Required DatabaseOptional
-[core]
-Include = /etc/pacman.d/mirrorlist
-[extra]
-Include = /etc/pacman.d/mirrorlist
-[community]
-Include = /etc/pacman.d/mirrorlist
-EOF
-root="$(mktemp -d -p "$PWD")"
-
-packages=(
-	busybox
-	# libbpf dependencies.
-	libelf
-	zlib
-	# selftests test_progs dependencies.
-	binutils
-	elfutils
-	ethtool
-	glibc
-	iproute2
-	# selftests test_verifier dependencies.
-	libcap
-)
-
-pacstrap -C "$pacman_conf" -cGM "$root" "${packages[@]}"
-
-# Remove unnecessary files from the chroot.
-
-# We don't need the pacman databases anymore.
-rm -rf "$root/var/lib/pacman/sync/"
-# We don't need D, Fortran, or Go.
- rm -f "$root/usr/lib/libgdruntime."* \
-	"$root/usr/lib/libgphobos."* \
-	"$root/usr/lib/libgfortran."* \
-	"$root/usr/lib/libgo."*
-# We don't need any documentation.
-rm -rf "$root/usr/share/{doc,help,man,texinfo}"
-
-"$(dirname "$0")"/mkrootfs_tweak.sh "$root"
-
-tar -C "$root" -c . | zstd -T0 -19 -o "$NAME"
-chmod 644 "$NAME"

ci/rootfs/mkrootfs_debian.sh

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

ci/rootfs/mkrootfs_tweak.sh

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

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

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

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

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

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

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

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

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

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

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

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

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

ci/vmtest/configs/DENYLIST-latest.s390x

@@ -1,6 +1,3 @@
-# TEMPORARY until bpf-next -> bpf merge
-lru_bug                                  # prog 'printk': failed to auto-attach: -524
-
 # TEMPORARY
 usdt/basic                               # failing verifier due to bounds check after LLVM update
 usdt/multispec                           # same as above

ci/vmtest/helpers.sh

@@ -1,3 +1,5 @@
+# shellcheck shell=bash
+
 # $1 - start or end
 # $2 - fold identifier, no spaces
 # $3 - fold section description

ci/vmtest/run_selftests.sh

@@ -78,7 +78,7 @@ cd ${PROJECT_NAME}/selftests/bpf
 if [ $# -eq 0 ]; then
 	test_progs
 	test_progs_no_alu32
-	test_maps
+	# test_maps
 	test_verifier
 else
 	for test_name in "$@"; do

docs/index.rst

@@ -1,5 +1,7 @@
 .. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 
+.. _libbpf:
+
 libbpf
 ======
 
@@ -7,6 +9,7 @@ libbpf
    :maxdepth: 1
 
    API Documentation <https://libbpf.readthedocs.io/en/latest/api.html>
+   program_types
    libbpf_naming_convention
    libbpf_build
 

docs/program_types.rst

@@ -0,0 +1,203 @@
+.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+.. _program_types_and_elf:
+
+Program Types and ELF Sections
+==============================
+
+The table below lists the program types, their attach types where relevant and the ELF section
+names supported by libbpf for them. The ELF section names follow these rules:
+
+- ``type`` is an exact match, e.g. ``SEC("socket")``
+- ``type+`` means it can be either exact ``SEC("type")`` or well-formed ``SEC("type/extras")``
+  with a '``/``' separator between ``type`` and ``extras``.
+
+When ``extras`` are specified, they provide details of how to auto-attach the BPF program.  The
+format of ``extras`` depends on the program type, e.g. ``SEC("tracepoint/<category>/<name>")``
+for tracepoints or ``SEC("usdt/<path>:<provider>:<name>")`` for USDT probes. The extras are
+described in more detail in the footnotes.
+
+
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| Program Type                              | Attach Type                            | ELF Section Name                 | Sleepable |
++===========================================+========================================+==================================+===========+
+| ``BPF_PROG_TYPE_CGROUP_DEVICE``           | ``BPF_CGROUP_DEVICE``                  | ``cgroup/dev``                   |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_CGROUP_SKB``              |                                        | ``cgroup/skb``                   |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET_EGRESS``             | ``cgroup_skb/egress``            |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET_INGRESS``            | ``cgroup_skb/ingress``           |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_CGROUP_SOCKOPT``          | ``BPF_CGROUP_GETSOCKOPT``              | ``cgroup/getsockopt``            |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_SETSOCKOPT``              | ``cgroup/setsockopt``            |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_CGROUP_SOCK_ADDR``        | ``BPF_CGROUP_INET4_BIND``              | ``cgroup/bind4``                 |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET4_CONNECT``           | ``cgroup/connect4``              |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET4_GETPEERNAME``       | ``cgroup/getpeername4``          |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET4_GETSOCKNAME``       | ``cgroup/getsockname4``          |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET6_BIND``              | ``cgroup/bind6``                 |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET6_CONNECT``           | ``cgroup/connect6``              |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET6_GETPEERNAME``       | ``cgroup/getpeername6``          |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET6_GETSOCKNAME``       | ``cgroup/getsockname6``          |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_UDP4_RECVMSG``            | ``cgroup/recvmsg4``              |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_UDP4_SENDMSG``            | ``cgroup/sendmsg4``              |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_UDP6_RECVMSG``            | ``cgroup/recvmsg6``              |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_UDP6_SENDMSG``            | ``cgroup/sendmsg6``              |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_CGROUP_SOCK``             | ``BPF_CGROUP_INET4_POST_BIND``         | ``cgroup/post_bind4``            |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET6_POST_BIND``         | ``cgroup/post_bind6``            |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET_SOCK_CREATE``        | ``cgroup/sock_create``           |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``cgroup/sock``                  |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_CGROUP_INET_SOCK_RELEASE``       | ``cgroup/sock_release``          |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_CGROUP_SYSCTL``           | ``BPF_CGROUP_SYSCTL``                  | ``cgroup/sysctl``                |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_EXT``                     |                                        | ``freplace+`` [#fentry]_         |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_FLOW_DISSECTOR``          | ``BPF_FLOW_DISSECTOR``                 | ``flow_dissector``               |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_KPROBE``                  |                                        | ``kprobe+`` [#kprobe]_           |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``kretprobe+`` [#kprobe]_        |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``ksyscall+`` [#ksyscall]_       |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        |  ``kretsyscall+`` [#ksyscall]_   |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``uprobe+`` [#uprobe]_           |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``uprobe.s+`` [#uprobe]_         | Yes       |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``uretprobe+`` [#uprobe]_        |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``uretprobe.s+`` [#uprobe]_      | Yes       |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``usdt+`` [#usdt]_               |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_TRACE_KPROBE_MULTI``             | ``kprobe.multi+`` [#kpmulti]_    |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``kretprobe.multi+`` [#kpmulti]_ |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_LIRC_MODE2``              | ``BPF_LIRC_MODE2``                     | ``lirc_mode2``                   |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_LSM``                     | ``BPF_LSM_CGROUP``                     | ``lsm_cgroup+``                  |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_LSM_MAC``                        | ``lsm+`` [#lsm]_                 |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``lsm.s+`` [#lsm]_               | Yes       |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_LWT_IN``                  |                                        | ``lwt_in``                       |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_LWT_OUT``                 |                                        | ``lwt_out``                      |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_LWT_SEG6LOCAL``           |                                        | ``lwt_seg6local``                |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_LWT_XMIT``                |                                        | ``lwt_xmit``                     |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_PERF_EVENT``              |                                        | ``perf_event``                   |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE`` |                                        | ``raw_tp.w+`` [#rawtp]_          |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``raw_tracepoint.w+``            |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_RAW_TRACEPOINT``          |                                        | ``raw_tp+`` [#rawtp]_            |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``raw_tracepoint+``              |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_SCHED_ACT``               |                                        | ``action``                       |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_SCHED_CLS``               |                                        | ``classifier``                   |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``tc``                           |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_SK_LOOKUP``               | ``BPF_SK_LOOKUP``                      | ``sk_lookup``                    |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_SK_MSG``                  | ``BPF_SK_MSG_VERDICT``                 | ``sk_msg``                       |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_SK_REUSEPORT``            | ``BPF_SK_REUSEPORT_SELECT_OR_MIGRATE`` | ``sk_reuseport/migrate``         |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_SK_REUSEPORT_SELECT``            | ``sk_reuseport``                 |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_SK_SKB``                  |                                        | ``sk_skb``                       |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_SK_SKB_STREAM_PARSER``           | ``sk_skb/stream_parser``         |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_SK_SKB_STREAM_VERDICT``          | ``sk_skb/stream_verdict``        |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_SOCKET_FILTER``           |                                        | ``socket``                       |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_SOCK_OPS``                | ``BPF_CGROUP_SOCK_OPS``                | ``sockops``                      |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_STRUCT_OPS``              |                                        | ``struct_ops+``                  |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_SYSCALL``                 |                                        | ``syscall``                      | Yes       |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_TRACEPOINT``              |                                        | ``tp+`` [#tp]_                   |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``tracepoint+`` [#tp]_           |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_TRACING``                 | ``BPF_MODIFY_RETURN``                  | ``fmod_ret+`` [#fentry]_         |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``fmod_ret.s+`` [#fentry]_       | Yes       |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_TRACE_FENTRY``                   | ``fentry+`` [#fentry]_           |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``fentry.s+`` [#fentry]_         | Yes       |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_TRACE_FEXIT``                    | ``fexit+`` [#fentry]_            |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``fexit.s+`` [#fentry]_          | Yes       |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_TRACE_ITER``                     | ``iter+`` [#iter]_               |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``iter.s+`` [#iter]_             | Yes       |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_TRACE_RAW_TP``                   | ``tp_btf+`` [#fentry]_           |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_XDP``                     | ``BPF_XDP_CPUMAP``                     | ``xdp.frags/cpumap``             |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``xdp/cpumap``                   |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_XDP_DEVMAP``                     | ``xdp.frags/devmap``             |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``xdp/devmap``                   |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_XDP``                            | ``xdp.frags``                    |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``xdp``                          |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+
+
+.. rubric:: Footnotes
+
+.. [#fentry] The ``fentry`` attach format is ``fentry[.s]/<function>``.
+.. [#kprobe] The ``kprobe`` attach format is ``kprobe/<function>[+<offset>]``. Valid
+             characters for ``function`` are ``a-zA-Z0-9_.`` and ``offset`` must be a valid
+             non-negative integer.
+.. [#ksyscall] The ``ksyscall`` attach format is ``ksyscall/<syscall>``.
+.. [#uprobe] The ``uprobe`` attach format is ``uprobe[.s]/<path>:<function>[+<offset>]``.
+.. [#usdt] The ``usdt`` attach format is ``usdt/<path>:<provider>:<name>``.
+.. [#kpmulti] The ``kprobe.multi`` attach format is ``kprobe.multi/<pattern>`` where ``pattern``
+              supports ``*`` and ``?`` wildcards. Valid characters for pattern are
+              ``a-zA-Z0-9_.*?``.
+.. [#lsm] The ``lsm`` attachment format is ``lsm[.s]/<hook>``.
+.. [#rawtp] The ``raw_tp`` attach format is ``raw_tracepoint[.w]/<tracepoint>``.
+.. [#tp] The ``tracepoint`` attach format is ``tracepoint/<category>/<name>``.
+.. [#iter] The ``iter`` attach format is ``iter[.s]/<struct-name>``.

include/uapi/linux/bpf.h

@@ -110,6 +110,12 @@ union bpf_iter_link_info {
 		__u32	cgroup_fd;
 		__u64	cgroup_id;
 	} cgroup;
+	/* Parameters of task iterators. */
+	struct {
+		__u32	tid;
+		__u32	pid;
+		__u32	pid_fd;
+	} task;
 };
 
 /* BPF syscall commands, see bpf(2) man-page for more details. */
@@ -916,7 +922,14 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_CPUMAP,
 	BPF_MAP_TYPE_XSKMAP,
 	BPF_MAP_TYPE_SOCKHASH,
-	BPF_MAP_TYPE_CGROUP_STORAGE,
+	BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED,
+	/* BPF_MAP_TYPE_CGROUP_STORAGE is available to bpf programs attaching
+	 * to a cgroup. The newer BPF_MAP_TYPE_CGRP_STORAGE is available to
+	 * both cgroup-attached and other progs and supports all functionality
+	 * provided by BPF_MAP_TYPE_CGROUP_STORAGE. So mark
+	 * BPF_MAP_TYPE_CGROUP_STORAGE deprecated.
+	 */
+	BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED,
 	BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
 	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
 	BPF_MAP_TYPE_QUEUE,
@@ -929,6 +942,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_TASK_STORAGE,
 	BPF_MAP_TYPE_BLOOM_FILTER,
 	BPF_MAP_TYPE_USER_RINGBUF,
+	BPF_MAP_TYPE_CGRP_STORAGE,
 };
 
 /* Note that tracing related programs such as
@@ -1987,6 +2001,9 @@ union bpf_attr {
  * 			sending the packet. This flag was added for GRE
  * 			encapsulation, but might be used with other protocols
  * 			as well in the future.
+ * 		**BPF_F_NO_TUNNEL_KEY**
+ * 			Add a flag to tunnel metadata indicating that no tunnel
+ * 			key should be set in the resulting tunnel header.
  *
  * 		Here is a typical usage on the transmit path:
  *
@@ -2570,14 +2587,19 @@ union bpf_attr {
  * 		* **SOL_SOCKET**, which supports the following *optname*\ s:
  * 		  **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**,
  * 		  **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**,
- * 		  **SO_BINDTODEVICE**, **SO_KEEPALIVE**.
+ * 		  **SO_BINDTODEVICE**, **SO_KEEPALIVE**, **SO_REUSEADDR**,
+ * 		  **SO_REUSEPORT**, **SO_BINDTOIFINDEX**, **SO_TXREHASH**.
  * 		* **IPPROTO_TCP**, which supports the following *optname*\ s:
  * 		  **TCP_CONGESTION**, **TCP_BPF_IW**,
  * 		  **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**,
  * 		  **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**,
- *		  **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**.
+ * 		  **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**.
  * 		* **IPPROTO_IP**, which supports *optname* **IP_TOS**.
- * 		* **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**.
+ * 		* **IPPROTO_IPV6**, which supports the following *optname*\ s:
+ * 		  **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**.
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
@@ -2633,7 +2655,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * long bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags)
+ * long bpf_redirect_map(struct bpf_map *map, u64 key, u64 flags)
  * 	Description
  * 		Redirect the packet to the endpoint referenced by *map* at
  * 		index *key*. Depending on its type, this *map* can contain
@@ -2794,12 +2816,10 @@ union bpf_attr {
  * 		  and **BPF_CGROUP_INET6_CONNECT**.
  *
  * 		This helper actually implements a subset of **getsockopt()**.
- * 		It supports the following *level*\ s:
- *
- * 		* **IPPROTO_TCP**, which supports *optname*
- * 		  **TCP_CONGESTION**.
- * 		* **IPPROTO_IP**, which supports *optname* **IP_TOS**.
- * 		* **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**.
+ * 		It supports the same set of *optname*\ s that is supported by
+ * 		the **bpf_setsockopt**\ () helper.  The exceptions are
+ * 		**TCP_BPF_*** is **bpf_setsockopt**\ () only and
+ * 		**TCP_SAVED_SYN** is **bpf_getsockopt**\ () only.
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
@@ -5276,7 +5296,7 @@ union bpf_attr {
  *	Return
  *		Nothing. Always succeeds.
  *
- * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset, u64 flags)
+ * long bpf_dynptr_read(void *dst, u32 len, const struct bpf_dynptr *src, u32 offset, u64 flags)
  *	Description
  *		Read *len* bytes from *src* into *dst*, starting from *offset*
  *		into *src*.
@@ -5286,7 +5306,7 @@ union bpf_attr {
  *		of *src*'s data, -EINVAL if *src* is an invalid dynptr or if
  *		*flags* is not 0.
  *
- * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags)
+ * long bpf_dynptr_write(const struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags)
  *	Description
  *		Write *len* bytes from *src* into *dst*, starting from *offset*
  *		into *dst*.
@@ -5296,7 +5316,7 @@ union bpf_attr {
  *		of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst*
  *		is a read-only dynptr or if *flags* is not 0.
  *
- * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len)
+ * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u32 offset, u32 len)
  *	Description
  *		Get a pointer to the underlying dynptr data.
  *
@@ -5397,7 +5417,7 @@ union bpf_attr {
  *		Drain samples from the specified user ring buffer, and invoke
  *		the provided callback for each such sample:
  *
- *		long (\*callback_fn)(struct bpf_dynptr \*dynptr, void \*ctx);
+ *		long (\*callback_fn)(const struct bpf_dynptr \*dynptr, void \*ctx);
  *
  *		If **callback_fn** returns 0, the helper will continue to try
  *		and drain the next sample, up to a maximum of
@@ -5429,226 +5449,272 @@ union bpf_attr {
  *		**-E2BIG** if user-space has tried to publish a sample which is
  *		larger than the size of the ring buffer, or which cannot fit
  *		within a struct bpf_dynptr.
+ *
+ * void *bpf_cgrp_storage_get(struct bpf_map *map, struct cgroup *cgroup, void *value, u64 flags)
+ *	Description
+ *		Get a bpf_local_storage from the *cgroup*.
+ *
+ *		Logically, it could be thought of as getting the value from
+ *		a *map* with *cgroup* as the **key**.  From this
+ *		perspective,  the usage is not much different from
+ *		**bpf_map_lookup_elem**\ (*map*, **&**\ *cgroup*) except this
+ *		helper enforces the key must be a cgroup struct and the map must also
+ *		be a **BPF_MAP_TYPE_CGRP_STORAGE**.
+ *
+ *		In reality, the local-storage value is embedded directly inside of the
+ *		*cgroup* object itself, rather than being located in the
+ *		**BPF_MAP_TYPE_CGRP_STORAGE** map. When the local-storage value is
+ *		queried for some *map* on a *cgroup* object, the kernel will perform an
+ *		O(n) iteration over all of the live local-storage values for that
+ *		*cgroup* object until the local-storage value for the *map* is found.
+ *
+ *		An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ *		used such that a new bpf_local_storage will be
+ *		created if one does not exist.  *value* can be used
+ *		together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ *		the initial value of a bpf_local_storage.  If *value* is
+ *		**NULL**, the new bpf_local_storage will be zero initialized.
+ *	Return
+ *		A bpf_local_storage pointer is returned on success.
+ *
+ *		**NULL** if not found or there was an error in adding
+ *		a new bpf_local_storage.
+ *
+ * long bpf_cgrp_storage_delete(struct bpf_map *map, struct cgroup *cgroup)
+ *	Description
+ *		Delete a bpf_local_storage from a *cgroup*.
+ *	Return
+ *		0 on success.
+ *
+ *		**-ENOENT** if the bpf_local_storage cannot be found.
  */
-#define __BPF_FUNC_MAPPER(FN)		\
-	FN(unspec),			\
-	FN(map_lookup_elem),		\
-	FN(map_update_elem),		\
-	FN(map_delete_elem),		\
-	FN(probe_read),			\
-	FN(ktime_get_ns),		\
-	FN(trace_printk),		\
-	FN(get_prandom_u32),		\
-	FN(get_smp_processor_id),	\
-	FN(skb_store_bytes),		\
-	FN(l3_csum_replace),		\
-	FN(l4_csum_replace),		\
-	FN(tail_call),			\
-	FN(clone_redirect),		\
-	FN(get_current_pid_tgid),	\
-	FN(get_current_uid_gid),	\
-	FN(get_current_comm),		\
-	FN(get_cgroup_classid),		\
-	FN(skb_vlan_push),		\
-	FN(skb_vlan_pop),		\
-	FN(skb_get_tunnel_key),		\
-	FN(skb_set_tunnel_key),		\
-	FN(perf_event_read),		\
-	FN(redirect),			\
-	FN(get_route_realm),		\
-	FN(perf_event_output),		\
-	FN(skb_load_bytes),		\
-	FN(get_stackid),		\
-	FN(csum_diff),			\
-	FN(skb_get_tunnel_opt),		\
-	FN(skb_set_tunnel_opt),		\
-	FN(skb_change_proto),		\
-	FN(skb_change_type),		\
-	FN(skb_under_cgroup),		\
-	FN(get_hash_recalc),		\
-	FN(get_current_task),		\
-	FN(probe_write_user),		\
-	FN(current_task_under_cgroup),	\
-	FN(skb_change_tail),		\
-	FN(skb_pull_data),		\
-	FN(csum_update),		\
-	FN(set_hash_invalid),		\
-	FN(get_numa_node_id),		\
-	FN(skb_change_head),		\
-	FN(xdp_adjust_head),		\
-	FN(probe_read_str),		\
-	FN(get_socket_cookie),		\
-	FN(get_socket_uid),		\
-	FN(set_hash),			\
-	FN(setsockopt),			\
-	FN(skb_adjust_room),		\
-	FN(redirect_map),		\
-	FN(sk_redirect_map),		\
-	FN(sock_map_update),		\
-	FN(xdp_adjust_meta),		\
-	FN(perf_event_read_value),	\
-	FN(perf_prog_read_value),	\
-	FN(getsockopt),			\
-	FN(override_return),		\
-	FN(sock_ops_cb_flags_set),	\
-	FN(msg_redirect_map),		\
-	FN(msg_apply_bytes),		\
-	FN(msg_cork_bytes),		\
-	FN(msg_pull_data),		\
-	FN(bind),			\
-	FN(xdp_adjust_tail),		\
-	FN(skb_get_xfrm_state),		\
-	FN(get_stack),			\
-	FN(skb_load_bytes_relative),	\
-	FN(fib_lookup),			\
-	FN(sock_hash_update),		\
-	FN(msg_redirect_hash),		\
-	FN(sk_redirect_hash),		\
-	FN(lwt_push_encap),		\
-	FN(lwt_seg6_store_bytes),	\
-	FN(lwt_seg6_adjust_srh),	\
-	FN(lwt_seg6_action),		\
-	FN(rc_repeat),			\
-	FN(rc_keydown),			\
-	FN(skb_cgroup_id),		\
-	FN(get_current_cgroup_id),	\
-	FN(get_local_storage),		\
-	FN(sk_select_reuseport),	\
-	FN(skb_ancestor_cgroup_id),	\
-	FN(sk_lookup_tcp),		\
-	FN(sk_lookup_udp),		\
-	FN(sk_release),			\
-	FN(map_push_elem),		\
-	FN(map_pop_elem),		\
-	FN(map_peek_elem),		\
-	FN(msg_push_data),		\
-	FN(msg_pop_data),		\
-	FN(rc_pointer_rel),		\
-	FN(spin_lock),			\
-	FN(spin_unlock),		\
-	FN(sk_fullsock),		\
-	FN(tcp_sock),			\
-	FN(skb_ecn_set_ce),		\
-	FN(get_listener_sock),		\
-	FN(skc_lookup_tcp),		\
-	FN(tcp_check_syncookie),	\
-	FN(sysctl_get_name),		\
-	FN(sysctl_get_current_value),	\
-	FN(sysctl_get_new_value),	\
-	FN(sysctl_set_new_value),	\
-	FN(strtol),			\
-	FN(strtoul),			\
-	FN(sk_storage_get),		\
-	FN(sk_storage_delete),		\
-	FN(send_signal),		\
-	FN(tcp_gen_syncookie),		\
-	FN(skb_output),			\
-	FN(probe_read_user),		\
-	FN(probe_read_kernel),		\
-	FN(probe_read_user_str),	\
-	FN(probe_read_kernel_str),	\
-	FN(tcp_send_ack),		\
-	FN(send_signal_thread),		\
-	FN(jiffies64),			\
-	FN(read_branch_records),	\
-	FN(get_ns_current_pid_tgid),	\
-	FN(xdp_output),			\
-	FN(get_netns_cookie),		\
-	FN(get_current_ancestor_cgroup_id),	\
-	FN(sk_assign),			\
-	FN(ktime_get_boot_ns),		\
-	FN(seq_printf),			\
-	FN(seq_write),			\
-	FN(sk_cgroup_id),		\
-	FN(sk_ancestor_cgroup_id),	\
-	FN(ringbuf_output),		\
-	FN(ringbuf_reserve),		\
-	FN(ringbuf_submit),		\
-	FN(ringbuf_discard),		\
-	FN(ringbuf_query),		\
-	FN(csum_level),			\
-	FN(skc_to_tcp6_sock),		\
-	FN(skc_to_tcp_sock),		\
-	FN(skc_to_tcp_timewait_sock),	\
-	FN(skc_to_tcp_request_sock),	\
-	FN(skc_to_udp6_sock),		\
-	FN(get_task_stack),		\
-	FN(load_hdr_opt),		\
-	FN(store_hdr_opt),		\
-	FN(reserve_hdr_opt),		\
-	FN(inode_storage_get),		\
-	FN(inode_storage_delete),	\
-	FN(d_path),			\
-	FN(copy_from_user),		\
-	FN(snprintf_btf),		\
-	FN(seq_printf_btf),		\
-	FN(skb_cgroup_classid),		\
-	FN(redirect_neigh),		\
-	FN(per_cpu_ptr),		\
-	FN(this_cpu_ptr),		\
-	FN(redirect_peer),		\
-	FN(task_storage_get),		\
-	FN(task_storage_delete),	\
-	FN(get_current_task_btf),	\
-	FN(bprm_opts_set),		\
-	FN(ktime_get_coarse_ns),	\
-	FN(ima_inode_hash),		\
-	FN(sock_from_file),		\
-	FN(check_mtu),			\
-	FN(for_each_map_elem),		\
-	FN(snprintf),			\
-	FN(sys_bpf),			\
-	FN(btf_find_by_name_kind),	\
-	FN(sys_close),			\
-	FN(timer_init),			\
-	FN(timer_set_callback),		\
-	FN(timer_start),		\
-	FN(timer_cancel),		\
-	FN(get_func_ip),		\
-	FN(get_attach_cookie),		\
-	FN(task_pt_regs),		\
-	FN(get_branch_snapshot),	\
-	FN(trace_vprintk),		\
-	FN(skc_to_unix_sock),		\
-	FN(kallsyms_lookup_name),	\
-	FN(find_vma),			\
-	FN(loop),			\
-	FN(strncmp),			\
-	FN(get_func_arg),		\
-	FN(get_func_ret),		\
-	FN(get_func_arg_cnt),		\
-	FN(get_retval),			\
-	FN(set_retval),			\
-	FN(xdp_get_buff_len),		\
-	FN(xdp_load_bytes),		\
-	FN(xdp_store_bytes),		\
-	FN(copy_from_user_task),	\
-	FN(skb_set_tstamp),		\
-	FN(ima_file_hash),		\
-	FN(kptr_xchg),			\
-	FN(map_lookup_percpu_elem),     \
-	FN(skc_to_mptcp_sock),		\
-	FN(dynptr_from_mem),		\
-	FN(ringbuf_reserve_dynptr),	\
-	FN(ringbuf_submit_dynptr),	\
-	FN(ringbuf_discard_dynptr),	\
-	FN(dynptr_read),		\
-	FN(dynptr_write),		\
-	FN(dynptr_data),		\
-	FN(tcp_raw_gen_syncookie_ipv4),	\
-	FN(tcp_raw_gen_syncookie_ipv6),	\
-	FN(tcp_raw_check_syncookie_ipv4),	\
-	FN(tcp_raw_check_syncookie_ipv6),	\
-	FN(ktime_get_tai_ns),		\
-	FN(user_ringbuf_drain),		\
+#define ___BPF_FUNC_MAPPER(FN, ctx...)			\
+	FN(unspec, 0, ##ctx)				\
+	FN(map_lookup_elem, 1, ##ctx)			\
+	FN(map_update_elem, 2, ##ctx)			\
+	FN(map_delete_elem, 3, ##ctx)			\
+	FN(probe_read, 4, ##ctx)			\
+	FN(ktime_get_ns, 5, ##ctx)			\
+	FN(trace_printk, 6, ##ctx)			\
+	FN(get_prandom_u32, 7, ##ctx)			\
+	FN(get_smp_processor_id, 8, ##ctx)		\
+	FN(skb_store_bytes, 9, ##ctx)			\
+	FN(l3_csum_replace, 10, ##ctx)			\
+	FN(l4_csum_replace, 11, ##ctx)			\
+	FN(tail_call, 12, ##ctx)			\
+	FN(clone_redirect, 13, ##ctx)			\
+	FN(get_current_pid_tgid, 14, ##ctx)		\
+	FN(get_current_uid_gid, 15, ##ctx)		\
+	FN(get_current_comm, 16, ##ctx)			\
+	FN(get_cgroup_classid, 17, ##ctx)		\
+	FN(skb_vlan_push, 18, ##ctx)			\
+	FN(skb_vlan_pop, 19, ##ctx)			\
+	FN(skb_get_tunnel_key, 20, ##ctx)		\
+	FN(skb_set_tunnel_key, 21, ##ctx)		\
+	FN(perf_event_read, 22, ##ctx)			\
+	FN(redirect, 23, ##ctx)				\
+	FN(get_route_realm, 24, ##ctx)			\
+	FN(perf_event_output, 25, ##ctx)		\
+	FN(skb_load_bytes, 26, ##ctx)			\
+	FN(get_stackid, 27, ##ctx)			\
+	FN(csum_diff, 28, ##ctx)			\
+	FN(skb_get_tunnel_opt, 29, ##ctx)		\
+	FN(skb_set_tunnel_opt, 30, ##ctx)		\
+	FN(skb_change_proto, 31, ##ctx)			\
+	FN(skb_change_type, 32, ##ctx)			\
+	FN(skb_under_cgroup, 33, ##ctx)			\
+	FN(get_hash_recalc, 34, ##ctx)			\
+	FN(get_current_task, 35, ##ctx)			\
+	FN(probe_write_user, 36, ##ctx)			\
+	FN(current_task_under_cgroup, 37, ##ctx)	\
+	FN(skb_change_tail, 38, ##ctx)			\
+	FN(skb_pull_data, 39, ##ctx)			\
+	FN(csum_update, 40, ##ctx)			\
+	FN(set_hash_invalid, 41, ##ctx)			\
+	FN(get_numa_node_id, 42, ##ctx)			\
+	FN(skb_change_head, 43, ##ctx)			\
+	FN(xdp_adjust_head, 44, ##ctx)			\
+	FN(probe_read_str, 45, ##ctx)			\
+	FN(get_socket_cookie, 46, ##ctx)		\
+	FN(get_socket_uid, 47, ##ctx)			\
+	FN(set_hash, 48, ##ctx)				\
+	FN(setsockopt, 49, ##ctx)			\
+	FN(skb_adjust_room, 50, ##ctx)			\
+	FN(redirect_map, 51, ##ctx)			\
+	FN(sk_redirect_map, 52, ##ctx)			\
+	FN(sock_map_update, 53, ##ctx)			\
+	FN(xdp_adjust_meta, 54, ##ctx)			\
+	FN(perf_event_read_value, 55, ##ctx)		\
+	FN(perf_prog_read_value, 56, ##ctx)		\
+	FN(getsockopt, 57, ##ctx)			\
+	FN(override_return, 58, ##ctx)			\
+	FN(sock_ops_cb_flags_set, 59, ##ctx)		\
+	FN(msg_redirect_map, 60, ##ctx)			\
+	FN(msg_apply_bytes, 61, ##ctx)			\
+	FN(msg_cork_bytes, 62, ##ctx)			\
+	FN(msg_pull_data, 63, ##ctx)			\
+	FN(bind, 64, ##ctx)				\
+	FN(xdp_adjust_tail, 65, ##ctx)			\
+	FN(skb_get_xfrm_state, 66, ##ctx)		\
+	FN(get_stack, 67, ##ctx)			\
+	FN(skb_load_bytes_relative, 68, ##ctx)		\
+	FN(fib_lookup, 69, ##ctx)			\
+	FN(sock_hash_update, 70, ##ctx)			\
+	FN(msg_redirect_hash, 71, ##ctx)		\
+	FN(sk_redirect_hash, 72, ##ctx)			\
+	FN(lwt_push_encap, 73, ##ctx)			\
+	FN(lwt_seg6_store_bytes, 74, ##ctx)		\
+	FN(lwt_seg6_adjust_srh, 75, ##ctx)		\
+	FN(lwt_seg6_action, 76, ##ctx)			\
+	FN(rc_repeat, 77, ##ctx)			\
+	FN(rc_keydown, 78, ##ctx)			\
+	FN(skb_cgroup_id, 79, ##ctx)			\
+	FN(get_current_cgroup_id, 80, ##ctx)		\
+	FN(get_local_storage, 81, ##ctx)		\
+	FN(sk_select_reuseport, 82, ##ctx)		\
+	FN(skb_ancestor_cgroup_id, 83, ##ctx)		\
+	FN(sk_lookup_tcp, 84, ##ctx)			\
+	FN(sk_lookup_udp, 85, ##ctx)			\
+	FN(sk_release, 86, ##ctx)			\
+	FN(map_push_elem, 87, ##ctx)			\
+	FN(map_pop_elem, 88, ##ctx)			\
+	FN(map_peek_elem, 89, ##ctx)			\
+	FN(msg_push_data, 90, ##ctx)			\
+	FN(msg_pop_data, 91, ##ctx)			\
+	FN(rc_pointer_rel, 92, ##ctx)			\
+	FN(spin_lock, 93, ##ctx)			\
+	FN(spin_unlock, 94, ##ctx)			\
+	FN(sk_fullsock, 95, ##ctx)			\
+	FN(tcp_sock, 96, ##ctx)				\
+	FN(skb_ecn_set_ce, 97, ##ctx)			\
+	FN(get_listener_sock, 98, ##ctx)		\
+	FN(skc_lookup_tcp, 99, ##ctx)			\
+	FN(tcp_check_syncookie, 100, ##ctx)		\
+	FN(sysctl_get_name, 101, ##ctx)			\
+	FN(sysctl_get_current_value, 102, ##ctx)	\
+	FN(sysctl_get_new_value, 103, ##ctx)		\
+	FN(sysctl_set_new_value, 104, ##ctx)		\
+	FN(strtol, 105, ##ctx)				\
+	FN(strtoul, 106, ##ctx)				\
+	FN(sk_storage_get, 107, ##ctx)			\
+	FN(sk_storage_delete, 108, ##ctx)		\
+	FN(send_signal, 109, ##ctx)			\
+	FN(tcp_gen_syncookie, 110, ##ctx)		\
+	FN(skb_output, 111, ##ctx)			\
+	FN(probe_read_user, 112, ##ctx)			\
+	FN(probe_read_kernel, 113, ##ctx)		\
+	FN(probe_read_user_str, 114, ##ctx)		\
+	FN(probe_read_kernel_str, 115, ##ctx)		\
+	FN(tcp_send_ack, 116, ##ctx)			\
+	FN(send_signal_thread, 117, ##ctx)		\
+	FN(jiffies64, 118, ##ctx)			\
+	FN(read_branch_records, 119, ##ctx)		\
+	FN(get_ns_current_pid_tgid, 120, ##ctx)		\
+	FN(xdp_output, 121, ##ctx)			\
+	FN(get_netns_cookie, 122, ##ctx)		\
+	FN(get_current_ancestor_cgroup_id, 123, ##ctx)	\
+	FN(sk_assign, 124, ##ctx)			\
+	FN(ktime_get_boot_ns, 125, ##ctx)		\
+	FN(seq_printf, 126, ##ctx)			\
+	FN(seq_write, 127, ##ctx)			\
+	FN(sk_cgroup_id, 128, ##ctx)			\
+	FN(sk_ancestor_cgroup_id, 129, ##ctx)		\
+	FN(ringbuf_output, 130, ##ctx)			\
+	FN(ringbuf_reserve, 131, ##ctx)			\
+	FN(ringbuf_submit, 132, ##ctx)			\
+	FN(ringbuf_discard, 133, ##ctx)			\
+	FN(ringbuf_query, 134, ##ctx)			\
+	FN(csum_level, 135, ##ctx)			\
+	FN(skc_to_tcp6_sock, 136, ##ctx)		\
+	FN(skc_to_tcp_sock, 137, ##ctx)			\
+	FN(skc_to_tcp_timewait_sock, 138, ##ctx)	\
+	FN(skc_to_tcp_request_sock, 139, ##ctx)		\
+	FN(skc_to_udp6_sock, 140, ##ctx)		\
+	FN(get_task_stack, 141, ##ctx)			\
+	FN(load_hdr_opt, 142, ##ctx)			\
+	FN(store_hdr_opt, 143, ##ctx)			\
+	FN(reserve_hdr_opt, 144, ##ctx)			\
+	FN(inode_storage_get, 145, ##ctx)		\
+	FN(inode_storage_delete, 146, ##ctx)		\
+	FN(d_path, 147, ##ctx)				\
+	FN(copy_from_user, 148, ##ctx)			\
+	FN(snprintf_btf, 149, ##ctx)			\
+	FN(seq_printf_btf, 150, ##ctx)			\
+	FN(skb_cgroup_classid, 151, ##ctx)		\
+	FN(redirect_neigh, 152, ##ctx)			\
+	FN(per_cpu_ptr, 153, ##ctx)			\
+	FN(this_cpu_ptr, 154, ##ctx)			\
+	FN(redirect_peer, 155, ##ctx)			\
+	FN(task_storage_get, 156, ##ctx)		\
+	FN(task_storage_delete, 157, ##ctx)		\
+	FN(get_current_task_btf, 158, ##ctx)		\
+	FN(bprm_opts_set, 159, ##ctx)			\
+	FN(ktime_get_coarse_ns, 160, ##ctx)		\
+	FN(ima_inode_hash, 161, ##ctx)			\
+	FN(sock_from_file, 162, ##ctx)			\
+	FN(check_mtu, 163, ##ctx)			\
+	FN(for_each_map_elem, 164, ##ctx)		\
+	FN(snprintf, 165, ##ctx)			\
+	FN(sys_bpf, 166, ##ctx)				\
+	FN(btf_find_by_name_kind, 167, ##ctx)		\
+	FN(sys_close, 168, ##ctx)			\
+	FN(timer_init, 169, ##ctx)			\
+	FN(timer_set_callback, 170, ##ctx)		\
+	FN(timer_start, 171, ##ctx)			\
+	FN(timer_cancel, 172, ##ctx)			\
+	FN(get_func_ip, 173, ##ctx)			\
+	FN(get_attach_cookie, 174, ##ctx)		\
+	FN(task_pt_regs, 175, ##ctx)			\
+	FN(get_branch_snapshot, 176, ##ctx)		\
+	FN(trace_vprintk, 177, ##ctx)			\
+	FN(skc_to_unix_sock, 178, ##ctx)		\
+	FN(kallsyms_lookup_name, 179, ##ctx)		\
+	FN(find_vma, 180, ##ctx)			\
+	FN(loop, 181, ##ctx)				\
+	FN(strncmp, 182, ##ctx)				\
+	FN(get_func_arg, 183, ##ctx)			\
+	FN(get_func_ret, 184, ##ctx)			\
+	FN(get_func_arg_cnt, 185, ##ctx)		\
+	FN(get_retval, 186, ##ctx)			\
+	FN(set_retval, 187, ##ctx)			\
+	FN(xdp_get_buff_len, 188, ##ctx)		\
+	FN(xdp_load_bytes, 189, ##ctx)			\
+	FN(xdp_store_bytes, 190, ##ctx)			\
+	FN(copy_from_user_task, 191, ##ctx)		\
+	FN(skb_set_tstamp, 192, ##ctx)			\
+	FN(ima_file_hash, 193, ##ctx)			\
+	FN(kptr_xchg, 194, ##ctx)			\
+	FN(map_lookup_percpu_elem, 195, ##ctx)		\
+	FN(skc_to_mptcp_sock, 196, ##ctx)		\
+	FN(dynptr_from_mem, 197, ##ctx)			\
+	FN(ringbuf_reserve_dynptr, 198, ##ctx)		\
+	FN(ringbuf_submit_dynptr, 199, ##ctx)		\
+	FN(ringbuf_discard_dynptr, 200, ##ctx)		\
+	FN(dynptr_read, 201, ##ctx)			\
+	FN(dynptr_write, 202, ##ctx)			\
+	FN(dynptr_data, 203, ##ctx)			\
+	FN(tcp_raw_gen_syncookie_ipv4, 204, ##ctx)	\
+	FN(tcp_raw_gen_syncookie_ipv6, 205, ##ctx)	\
+	FN(tcp_raw_check_syncookie_ipv4, 206, ##ctx)	\
+	FN(tcp_raw_check_syncookie_ipv6, 207, ##ctx)	\
+	FN(ktime_get_tai_ns, 208, ##ctx)		\
+	FN(user_ringbuf_drain, 209, ##ctx)		\
+	FN(cgrp_storage_get, 210, ##ctx)		\
+	FN(cgrp_storage_delete, 211, ##ctx)		\
 	/* */
 
+/* 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
+ */
+#define __BPF_FUNC_MAPPER_APPLY(name, value, FN) FN(name),
+#define __BPF_FUNC_MAPPER(FN) ___BPF_FUNC_MAPPER(__BPF_FUNC_MAPPER_APPLY, FN)
+
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
  */
-#define __BPF_ENUM_FN(x) BPF_FUNC_ ## x
+#define __BPF_ENUM_FN(x, y) BPF_FUNC_ ## x = y,
 enum bpf_func_id {
-	__BPF_FUNC_MAPPER(__BPF_ENUM_FN)
+	___BPF_FUNC_MAPPER(__BPF_ENUM_FN)
 	__BPF_FUNC_MAX_ID,
 };
 #undef __BPF_ENUM_FN
@@ -5701,6 +5767,7 @@ enum {
 	BPF_F_ZERO_CSUM_TX		= (1ULL << 1),
 	BPF_F_DONT_FRAGMENT		= (1ULL << 2),
 	BPF_F_SEQ_NUMBER		= (1ULL << 3),
+	BPF_F_NO_TUNNEL_KEY		= (1ULL << 4),
 };
 
 /* BPF_FUNC_skb_get_tunnel_key flags. */
@@ -6262,6 +6329,10 @@ struct bpf_link_info {
 					__u64 cgroup_id;
 					__u32 order;
 				} cgroup;
+				struct {
+					__u32 tid;
+					__u32 pid;
+				} task;
 			};
 		} iter;
 		struct  {
@@ -6381,6 +6452,7 @@ struct bpf_sock_ops {
 				 * the outgoing header has not
 				 * been written yet.
 				 */
+	__u64 skb_hwtstamp;
 };
 
 /* Definitions for bpf_sock_ops_cb_flags */
@@ -6823,6 +6895,16 @@ struct bpf_dynptr {
 	__u64 :64;
 } __attribute__((aligned(8)));
 
+struct bpf_list_head {
+	__u64 :64;
+	__u64 :64;
+} __attribute__((aligned(8)));
+
+struct bpf_list_node {
+	__u64 :64;
+	__u64 :64;
+} __attribute__((aligned(8)));
+
 struct bpf_sysctl {
 	__u32	write;		/* Sysctl is being read (= 0) or written (= 1).
 				 * Allows 1,2,4-byte read, but no write.

include/uapi/linux/fcntl.h

@@ -0,0 +1,114 @@
+/* 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 */
+/* (1U << 31) is reserved for signed error codes */
+
+/*
+ * Set/Get write life time hints. {GET,SET}_RW_HINT operate on the
+ * underlying inode, while {GET,SET}_FILE_RW_HINT operate only on
+ * the specific file.
+ */
+#define F_GET_RW_HINT		(F_LINUX_SPECIFIC_BASE + 11)
+#define F_SET_RW_HINT		(F_LINUX_SPECIFIC_BASE + 12)
+#define F_GET_FILE_RW_HINT	(F_LINUX_SPECIFIC_BASE + 13)
+#define F_SET_FILE_RW_HINT	(F_LINUX_SPECIFIC_BASE + 14)
+
+/*
+ * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be
+ * used to clear any hints previously set.
+ */
+#define RWH_WRITE_LIFE_NOT_SET	0
+#define RWH_WRITE_LIFE_NONE	1
+#define RWH_WRITE_LIFE_SHORT	2
+#define RWH_WRITE_LIFE_MEDIUM	3
+#define RWH_WRITE_LIFE_LONG	4
+#define RWH_WRITE_LIFE_EXTREME	5
+
+/*
+ * The originally introduced spelling is remained from the first
+ * versions of the patch set that introduced the feature, see commit
+ * v4.13-rc1~212^2~51.
+ */
+#define RWF_WRITE_LIFE_NOT_SET	RWH_WRITE_LIFE_NOT_SET
+
+/*
+ * Types of directory notifications that may be requested.
+ */
+#define DN_ACCESS	0x00000001	/* File accessed */
+#define DN_MODIFY	0x00000002	/* File modified */
+#define DN_CREATE	0x00000004	/* File created */
+#define DN_DELETE	0x00000008	/* File removed */
+#define DN_RENAME	0x00000010	/* File renamed */
+#define DN_ATTRIB	0x00000020	/* File changed attibutes */
+#define DN_MULTISHOT	0x80000000	/* Don't remove notifier */
+
+/*
+ * The constants AT_REMOVEDIR and AT_EACCESS have the same value.  AT_EACCESS is
+ * meaningful only to faccessat, while AT_REMOVEDIR is meaningful only to
+ * unlinkat.  The two functions do completely different things and therefore,
+ * the flags can be allowed to overlap.  For example, passing AT_REMOVEDIR to
+ * faccessat would be undefined behavior and thus treating it equivalent to
+ * AT_EACCESS is valid undefined behavior.
+ */
+#define AT_FDCWD		-100    /* Special value used to indicate
+                                           openat should use the current
+                                           working directory. */
+#define AT_SYMLINK_NOFOLLOW	0x100   /* Do not follow symbolic links.  */
+#define AT_EACCESS		0x200	/* Test access permitted for
+                                           effective IDs, not real IDs.  */
+#define AT_REMOVEDIR		0x200   /* Remove directory instead of
+                                           unlinking file.  */
+#define AT_SYMLINK_FOLLOW	0x400   /* Follow symbolic links.  */
+#define AT_NO_AUTOMOUNT		0x800	/* Suppress terminal automount traversal */
+#define AT_EMPTY_PATH		0x1000	/* Allow empty relative pathname */
+
+#define AT_STATX_SYNC_TYPE	0x6000	/* Type of synchronisation required from statx() */
+#define AT_STATX_SYNC_AS_STAT	0x0000	/* - Do whatever stat() does */
+#define AT_STATX_FORCE_SYNC	0x2000	/* - Force the attributes to be sync'd with the server */
+#define AT_STATX_DONT_SYNC	0x4000	/* - Don't sync attributes with the server */
+
+#define AT_RECURSIVE		0x8000	/* Apply to the entire subtree */
+
+#endif /* _UAPI_LINUX_FCNTL_H */

include/uapi/linux/if_link.h

@@ -673,6 +673,7 @@ enum {
 	IFLA_XFRM_UNSPEC,
 	IFLA_XFRM_LINK,
 	IFLA_XFRM_IF_ID,
+	IFLA_XFRM_COLLECT_METADATA,
 	__IFLA_XFRM_MAX
 };
 

include/uapi/linux/perf_event.h

@@ -164,8 +164,6 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_WEIGHT_STRUCT		= 1U << 24,
 
 	PERF_SAMPLE_MAX = 1U << 25,		/* non-ABI */
-
-	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63, /* non-ABI; internal use */
 };
 
 #define PERF_SAMPLE_WEIGHT_TYPE	(PERF_SAMPLE_WEIGHT | PERF_SAMPLE_WEIGHT_STRUCT)
@@ -204,6 +202,8 @@ enum perf_branch_sample_type_shift {
 
 	PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT	= 17, /* save low level index of raw branch records */
 
+	PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT	= 18, /* save privilege mode */
+
 	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
 };
 
@@ -233,6 +233,8 @@ enum perf_branch_sample_type {
 
 	PERF_SAMPLE_BRANCH_HW_INDEX	= 1U << PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT,
 
+	PERF_SAMPLE_BRANCH_PRIV_SAVE	= 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT,
+
 	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
 
@@ -253,9 +255,48 @@ enum {
 	PERF_BR_COND_RET	= 10,	/* conditional function return */
 	PERF_BR_ERET		= 11,	/* exception return */
 	PERF_BR_IRQ		= 12,	/* irq */
+	PERF_BR_SERROR		= 13,	/* system error */
+	PERF_BR_NO_TX		= 14,	/* not in transaction */
+	PERF_BR_EXTEND_ABI	= 15,	/* extend ABI */
 	PERF_BR_MAX,
 };
 
+/*
+ * Common branch speculation outcome classification
+ */
+enum {
+	PERF_BR_SPEC_NA			= 0,	/* Not available */
+	PERF_BR_SPEC_WRONG_PATH		= 1,	/* Speculative but on wrong path */
+	PERF_BR_NON_SPEC_CORRECT_PATH	= 2,	/* Non-speculative but on correct path */
+	PERF_BR_SPEC_CORRECT_PATH	= 3,	/* Speculative and on correct path */
+	PERF_BR_SPEC_MAX,
+};
+
+enum {
+	PERF_BR_NEW_FAULT_ALGN		= 0,    /* Alignment fault */
+	PERF_BR_NEW_FAULT_DATA		= 1,    /* Data fault */
+	PERF_BR_NEW_FAULT_INST		= 2,    /* Inst fault */
+	PERF_BR_NEW_ARCH_1		= 3,    /* Architecture specific */
+	PERF_BR_NEW_ARCH_2		= 4,    /* Architecture specific */
+	PERF_BR_NEW_ARCH_3		= 5,    /* Architecture specific */
+	PERF_BR_NEW_ARCH_4		= 6,    /* Architecture specific */
+	PERF_BR_NEW_ARCH_5		= 7,    /* Architecture specific */
+	PERF_BR_NEW_MAX,
+};
+
+enum {
+	PERF_BR_PRIV_UNKNOWN	= 0,
+	PERF_BR_PRIV_USER	= 1,
+	PERF_BR_PRIV_KERNEL	= 2,
+	PERF_BR_PRIV_HV		= 3,
+};
+
+#define PERF_BR_ARM64_FIQ		PERF_BR_NEW_ARCH_1
+#define PERF_BR_ARM64_DEBUG_HALT	PERF_BR_NEW_ARCH_2
+#define PERF_BR_ARM64_DEBUG_EXIT	PERF_BR_NEW_ARCH_3
+#define PERF_BR_ARM64_DEBUG_INST	PERF_BR_NEW_ARCH_4
+#define PERF_BR_ARM64_DEBUG_DATA	PERF_BR_NEW_ARCH_5
+
 #define PERF_SAMPLE_BRANCH_PLM_ALL \
 	(PERF_SAMPLE_BRANCH_USER|\
 	 PERF_SAMPLE_BRANCH_KERNEL|\
@@ -1295,7 +1336,9 @@ 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 */
-/* 5-0xa available */
+/* 5-0x8 available */
+#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 */
 #define PERF_MEM_LVLNUM_RAM	0x0d /* RAM */
@@ -1313,7 +1356,7 @@ union perf_mem_data_src {
 #define PERF_MEM_SNOOP_SHIFT	19
 
 #define PERF_MEM_SNOOPX_FWD	0x01 /* forward */
-/* 1 free */
+#define PERF_MEM_SNOOPX_PEER	0x02 /* xfer from peer */
 #define PERF_MEM_SNOOPX_SHIFT  38
 
 /* locked instruction */
@@ -1363,6 +1406,7 @@ union perf_mem_data_src {
  *     abort: aborting a hardware transaction
  *    cycles: cycles from last branch (or 0 if not supported)
  *      type: branch type
+ *      spec: branch speculation info (or 0 if not supported)
  */
 struct perf_branch_entry {
 	__u64	from;
@@ -1373,7 +1417,10 @@ struct perf_branch_entry {
 		abort:1,    /* transaction abort */
 		cycles:16,  /* cycle count to last branch */
 		type:4,     /* branch type */
-		reserved:40;
+		spec:2,     /* branch speculation info */
+		new_type:4, /* additional branch type */
+		priv:3,     /* privilege level */
+		reserved:31;
 };
 
 union perf_sample_weight {

scripts/build-fuzzers.sh

@@ -44,7 +44,7 @@ rm -rf elfutils
 git clone git://sourceware.org/git/elfutils.git
 (
 cd elfutils
-git checkout 83251d4091241acddbdcf16f814e3bc6ef3df49a
+git checkout e9f3045caa5c4498f371383e5519151942d48b6d
 git log --oneline -1
 
 # ASan isn't compatible with -Wl,--no-undefined: https://github.com/google/sanitizers/issues/380

scripts/sync-kernel.sh

@@ -42,6 +42,7 @@ PATH_MAP=(									\
 	[tools/include/uapi/linux/bpf_common.h]=include/uapi/linux/bpf_common.h	\
 	[tools/include/uapi/linux/bpf.h]=include/uapi/linux/bpf.h		\
 	[tools/include/uapi/linux/btf.h]=include/uapi/linux/btf.h		\
+	[tools/include/uapi/linux/fcntl.h]=include/uapi/linux/fcntl.h		\
 	[tools/include/uapi/linux/if_link.h]=include/uapi/linux/if_link.h	\
 	[tools/include/uapi/linux/if_xdp.h]=include/uapi/linux/if_xdp.h		\
 	[tools/include/uapi/linux/netlink.h]=include/uapi/linux/netlink.h	\
@@ -51,8 +52,8 @@ PATH_MAP=(									\
 	[Documentation/bpf/libbpf]=docs						\
 )
 
-LIBBPF_PATHS="${!PATH_MAP[@]} :^tools/lib/bpf/Makefile :^tools/lib/bpf/Build :^tools/lib/bpf/.gitignore :^tools/include/tools/libc_compat.h"
-LIBBPF_VIEW_PATHS="${PATH_MAP[@]}"
+LIBBPF_PATHS=("${!PATH_MAP[@]}" ":^tools/lib/bpf/Makefile" ":^tools/lib/bpf/Build" ":^tools/lib/bpf/.gitignore" ":^tools/include/tools/libc_compat.h")
+LIBBPF_VIEW_PATHS=("${PATH_MAP[@]}")
 LIBBPF_VIEW_EXCLUDE_REGEX='^src/(Makefile|Build|test_libbpf\.c|bpf_helper_defs\.h|\.gitignore)$|^docs/(\.gitignore|api\.rst|conf\.py)$|^docs/sphinx/.*'
 LINUX_VIEW_EXCLUDE_REGEX='^include/tools/libc_compat.h$'
 
@@ -85,7 +86,9 @@ commit_desc()
 # $2 - paths filter
 commit_signature()
 {
-	git show --pretty='("%s")|%aI|%b' --shortstat $1 -- ${2-.} | tr '\n' '|'
+	local ref=$1
+	shift
+	git show --pretty='("%s")|%aI|%b' --shortstat $ref -- "${@-.}" | tr '\n' '|'
 }
 
 # Cherry-pick commits touching libbpf-related files
@@ -104,7 +107,7 @@ cherry_pick_commits()
 	local libbpf_conflict_cnt
 	local desc
 
-	new_commits=$(git rev-list --no-merges --topo-order --reverse ${baseline_tag}..${tip_tag} ${LIBBPF_PATHS[@]})
+	new_commits=$(git rev-list --no-merges --topo-order --reverse ${baseline_tag}..${tip_tag} -- "${LIBBPF_PATHS[@]}")
 	for new_commit in ${new_commits}; do
 		desc="$(commit_desc ${new_commit})"
 		signature="$(commit_signature ${new_commit} "${LIBBPF_PATHS[@]}")"
@@ -138,7 +141,7 @@ cherry_pick_commits()
 		echo "Picking '${desc}'..."
 		if ! git cherry-pick ${new_commit} &>/dev/null; then
 			echo "Warning! Cherry-picking '${desc} failed, checking if it's non-libbpf files causing problems..."
-			libbpf_conflict_cnt=$(git diff --name-only --diff-filter=U -- ${LIBBPF_PATHS[@]} | wc -l)
+			libbpf_conflict_cnt=$(git diff --name-only --diff-filter=U -- "${LIBBPF_PATHS[@]}" | wc -l)
 			conflict_cnt=$(git diff --name-only | wc -l)
 			prompt_resolution=1
 
@@ -284,7 +287,7 @@ cd_to ${LIBBPF_REPO}
 helpers_changes=$(git status --porcelain src/bpf_helper_defs.h | wc -l)
 if ((${helpers_changes} == 1)); then
 	git add src/bpf_helper_defs.h
-	git commit -m "sync: auto-generate latest BPF helpers
+	git commit -s -m "sync: auto-generate latest BPF helpers
 
 Latest changes to BPF helper definitions.
 " -- src/bpf_helper_defs.h
@@ -306,7 +309,7 @@ Baseline bpf-next commit:   ${BASELINE_COMMIT}\n\
 Checkpoint bpf-next commit: ${TIP_COMMIT}\n\
 Baseline bpf commit:        ${BPF_BASELINE_COMMIT}\n\
 Checkpoint bpf commit:      ${BPF_TIP_COMMIT}/" |				      \
-git commit --file=-
+git commit -s --file=-
 
 echo "SUCCESS! ${COMMIT_CNT} commits synced."
 
@@ -316,10 +319,10 @@ cd_to ${LINUX_REPO}
 git checkout -b ${VIEW_TAG} ${TIP_COMMIT}
 FILTER_BRANCH_SQUELCH_WARNING=1 git filter-branch -f --tree-filter "${LIBBPF_TREE_FILTER}" ${VIEW_TAG}^..${VIEW_TAG}
 FILTER_BRANCH_SQUELCH_WARNING=1 git filter-branch -f --subdirectory-filter __libbpf ${VIEW_TAG}^..${VIEW_TAG}
-git ls-files -- ${LIBBPF_VIEW_PATHS[@]} | grep -v -E "${LINUX_VIEW_EXCLUDE_REGEX}" > ${TMP_DIR}/linux-view.ls
+git ls-files -- "${LIBBPF_VIEW_PATHS[@]}" | grep -v -E "${LINUX_VIEW_EXCLUDE_REGEX}" > ${TMP_DIR}/linux-view.ls
 
 cd_to ${LIBBPF_REPO}
-git ls-files -- ${LIBBPF_VIEW_PATHS[@]} | grep -v -E "${LIBBPF_VIEW_EXCLUDE_REGEX}" > ${TMP_DIR}/github-view.ls
+git ls-files -- "${LIBBPF_VIEW_PATHS[@]}" | grep -v -E "${LIBBPF_VIEW_EXCLUDE_REGEX}" > ${TMP_DIR}/github-view.ls
 
 echo "Comparing list of files..."
 diff -u ${TMP_DIR}/linux-view.ls ${TMP_DIR}/github-view.ls

src/Makefile

@@ -77,7 +77,8 @@ INSTALL = install
 
 DESTDIR ?=
 
-ifeq ($(filter-out %64 %64be %64eb %64le %64el s390x, $(shell uname -m)),)
+HOSTARCH = $(firstword $(subst -, ,$(shell $(CC) -dumpmachine)))
+ifeq ($(filter-out %64 %64be %64eb %64le %64el s390x, $(HOSTARCH)),)
 	LIBSUBDIR := lib64
 else
 	LIBSUBDIR := lib

src/bpf.c

@@ -935,58 +935,98 @@ int bpf_link_get_next_id(__u32 start_id, __u32 *next_id)
 	return bpf_obj_get_next_id(start_id, next_id, BPF_LINK_GET_NEXT_ID);
 }
 
-int bpf_prog_get_fd_by_id(__u32 id)
+int bpf_prog_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, open_flags);
 	union bpf_attr attr;
 	int fd;
 
+	if (!OPTS_VALID(opts, bpf_get_fd_by_id_opts))
+		return libbpf_err(-EINVAL);
+
 	memset(&attr, 0, attr_sz);
 	attr.prog_id = id;
+	attr.open_flags = OPTS_GET(opts, open_flags, 0);
 
 	fd = sys_bpf_fd(BPF_PROG_GET_FD_BY_ID, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
-int bpf_map_get_fd_by_id(__u32 id)
+int bpf_prog_get_fd_by_id(__u32 id)
+{
+	return bpf_prog_get_fd_by_id_opts(id, NULL);
+}
+
+int bpf_map_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, open_flags);
 	union bpf_attr attr;
 	int fd;
 
+	if (!OPTS_VALID(opts, bpf_get_fd_by_id_opts))
+		return libbpf_err(-EINVAL);
+
 	memset(&attr, 0, attr_sz);
 	attr.map_id = id;
+	attr.open_flags = OPTS_GET(opts, open_flags, 0);
 
 	fd = sys_bpf_fd(BPF_MAP_GET_FD_BY_ID, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
-int bpf_btf_get_fd_by_id(__u32 id)
+int bpf_map_get_fd_by_id(__u32 id)
+{
+	return bpf_map_get_fd_by_id_opts(id, NULL);
+}
+
+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, open_flags);
 	union bpf_attr attr;
 	int fd;
 
+	if (!OPTS_VALID(opts, bpf_get_fd_by_id_opts))
+		return libbpf_err(-EINVAL);
+
 	memset(&attr, 0, attr_sz);
 	attr.btf_id = id;
+	attr.open_flags = OPTS_GET(opts, open_flags, 0);
 
 	fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
-int bpf_link_get_fd_by_id(__u32 id)
+int bpf_btf_get_fd_by_id(__u32 id)
+{
+	return bpf_btf_get_fd_by_id_opts(id, NULL);
+}
+
+int bpf_link_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, open_flags);
 	union bpf_attr attr;
 	int fd;
 
+	if (!OPTS_VALID(opts, bpf_get_fd_by_id_opts))
+		return libbpf_err(-EINVAL);
+
 	memset(&attr, 0, attr_sz);
 	attr.link_id = id;
+	attr.open_flags = OPTS_GET(opts, open_flags, 0);
 
 	fd = sys_bpf_fd(BPF_LINK_GET_FD_BY_ID, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
+int bpf_link_get_fd_by_id(__u32 id)
+{
+	return bpf_link_get_fd_by_id_opts(id, NULL);
+}
+
 int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len)
 {
 	const size_t attr_sz = offsetofend(union bpf_attr, info);

src/bpf.h

@@ -365,10 +365,26 @@ LIBBPF_API int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id);
 LIBBPF_API int bpf_map_get_next_id(__u32 start_id, __u32 *next_id);
 LIBBPF_API int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id);
 LIBBPF_API int bpf_link_get_next_id(__u32 start_id, __u32 *next_id);
+
+struct bpf_get_fd_by_id_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u32 open_flags; /* permissions requested for the operation on fd */
+	size_t :0;
+};
+#define bpf_get_fd_by_id_opts__last_field open_flags
+
 LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_prog_get_fd_by_id_opts(__u32 id,
+				const struct bpf_get_fd_by_id_opts *opts);
 LIBBPF_API int bpf_map_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_map_get_fd_by_id_opts(__u32 id,
+				const struct bpf_get_fd_by_id_opts *opts);
 LIBBPF_API int bpf_btf_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_btf_get_fd_by_id_opts(__u32 id,
+				const struct bpf_get_fd_by_id_opts *opts);
 LIBBPF_API int bpf_link_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_link_get_fd_by_id_opts(__u32 id,
+				const struct bpf_get_fd_by_id_opts *opts);
 LIBBPF_API int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len);
 
 struct bpf_prog_query_opts {
@@ -393,8 +409,15 @@ LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf,
 				 __u32 *buf_len, __u32 *prog_id, __u32 *fd_type,
 				 __u64 *probe_offset, __u64 *probe_addr);
 
+#ifdef __cplusplus
+/* forward-declaring enums in C++ isn't compatible with pure C enums, so
+ * instead define bpf_enable_stats() as accepting int as an input
+ */
+LIBBPF_API int bpf_enable_stats(int type);
+#else
 enum bpf_stats_type; /* defined in up-to-date linux/bpf.h */
 LIBBPF_API int bpf_enable_stats(enum bpf_stats_type type);
+#endif
 
 struct bpf_prog_bind_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */

src/bpf_helper_defs.h

@@ -29,6 +29,7 @@ struct tcp_request_sock;
 struct udp6_sock;
 struct unix_sock;
 struct task_struct;
+struct cgroup;
 struct __sk_buff;
 struct sk_msg_md;
 struct xdp_md;
@@ -536,6 +537,9 @@ static long (*bpf_skb_get_tunnel_key)(struct __sk_buff *skb, struct bpf_tunnel_k
  * 		sending the packet. This flag was added for GRE
  * 		encapsulation, but might be used with other protocols
  * 		as well in the future.
+ * 	**BPF_F_NO_TUNNEL_KEY**
+ * 		Add a flag to tunnel metadata indicating that no tunnel
+ * 		key should be set in the resulting tunnel header.
  *
  * 	Here is a typical usage on the transmit path:
  *
@@ -1209,14 +1213,19 @@ static long (*bpf_set_hash)(struct __sk_buff *skb, __u32 hash) = (void *) 48;
  * 	* **SOL_SOCKET**, which supports the following *optname*\ s:
  * 	  **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**,
  * 	  **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**,
- * 	  **SO_BINDTODEVICE**, **SO_KEEPALIVE**.
+ * 	  **SO_BINDTODEVICE**, **SO_KEEPALIVE**, **SO_REUSEADDR**,
+ * 	  **SO_REUSEPORT**, **SO_BINDTOIFINDEX**, **SO_TXREHASH**.
  * 	* **IPPROTO_TCP**, which supports the following *optname*\ s:
  * 	  **TCP_CONGESTION**, **TCP_BPF_IW**,
  * 	  **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**,
  * 	  **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**,
- * 	  **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**.
+ * 	  **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**.
  * 	* **IPPROTO_IP**, which supports *optname* **IP_TOS**.
- * 	* **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**.
+ * 	* **IPPROTO_IPV6**, which supports the following *optname*\ s:
+ * 	  **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**.
  *
  * Returns
  * 	0 on success, or a negative error in case of failure.
@@ -1306,7 +1315,7 @@ static long (*bpf_skb_adjust_room)(struct __sk_buff *skb, __s32 len_diff, __u32
  * 	**XDP_REDIRECT** on success, or the value of the two lower bits
  * 	of the *flags* argument on error.
  */
-static long (*bpf_redirect_map)(void *map, __u32 key, __u64 flags) = (void *) 51;
+static long (*bpf_redirect_map)(void *map, __u64 key, __u64 flags) = (void *) 51;
 
 /*
  * bpf_sk_redirect_map
@@ -1465,12 +1474,10 @@ static long (*bpf_perf_prog_read_value)(struct bpf_perf_event_data *ctx, struct
  * 	  and **BPF_CGROUP_INET6_CONNECT**.
  *
  * 	This helper actually implements a subset of **getsockopt()**.
- * 	It supports the following *level*\ s:
- *
- * 	* **IPPROTO_TCP**, which supports *optname*
- * 	  **TCP_CONGESTION**.
- * 	* **IPPROTO_IP**, which supports *optname* **IP_TOS**.
- * 	* **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**.
+ * 	It supports the same set of *optname*\ s that is supported by
+ * 	the **bpf_setsockopt**\ () helper.  The exceptions are
+ * 	**TCP_BPF_*** is **bpf_setsockopt**\ () only and
+ * 	**TCP_SAVED_SYN** is **bpf_getsockopt**\ () only.
  *
  * Returns
  * 	0 on success, or a negative error in case of failure.
@@ -4484,7 +4491,7 @@ static void (*bpf_ringbuf_discard_dynptr)(struct bpf_dynptr *ptr, __u64 flags) =
  * 	of *src*'s data, -EINVAL if *src* is an invalid dynptr or if
  * 	*flags* is not 0.
  */
-static long (*bpf_dynptr_read)(void *dst, __u32 len, struct bpf_dynptr *src, __u32 offset, __u64 flags) = (void *) 201;
+static long (*bpf_dynptr_read)(void *dst, __u32 len, const struct bpf_dynptr *src, __u32 offset, __u64 flags) = (void *) 201;
 
 /*
  * bpf_dynptr_write
@@ -4498,7 +4505,7 @@ static long (*bpf_dynptr_read)(void *dst, __u32 len, struct bpf_dynptr *src, __u
  * 	of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst*
  * 	is a read-only dynptr or if *flags* is not 0.
  */
-static long (*bpf_dynptr_write)(struct bpf_dynptr *dst, __u32 offset, void *src, __u32 len, __u64 flags) = (void *) 202;
+static long (*bpf_dynptr_write)(const struct bpf_dynptr *dst, __u32 offset, void *src, __u32 len, __u64 flags) = (void *) 202;
 
 /*
  * bpf_dynptr_data
@@ -4513,7 +4520,7 @@ static long (*bpf_dynptr_write)(struct bpf_dynptr *dst, __u32 offset, void *src,
  * 	read-only, if the dynptr is invalid, or if the offset and length
  * 	is out of bounds.
  */
-static void *(*bpf_dynptr_data)(struct bpf_dynptr *ptr, __u32 offset, __u32 len) = (void *) 203;
+static void *(*bpf_dynptr_data)(const struct bpf_dynptr *ptr, __u32 offset, __u32 len) = (void *) 203;
 
 /*
  * bpf_tcp_raw_gen_syncookie_ipv4
@@ -4626,7 +4633,7 @@ static __u64 (*bpf_ktime_get_tai_ns)(void) = (void *) 208;
  * 	Drain samples from the specified user ring buffer, and invoke
  * 	the provided callback for each such sample:
  *
- * 	long (\*callback_fn)(struct bpf_dynptr \*dynptr, void \*ctx);
+ * 	long (\*callback_fn)(const struct bpf_dynptr \*dynptr, void \*ctx);
  *
  * 	If **callback_fn** returns 0, the helper will continue to try
  * 	and drain the next sample, up to a maximum of
@@ -4662,4 +4669,50 @@ static __u64 (*bpf_ktime_get_tai_ns)(void) = (void *) 208;
  */
 static long (*bpf_user_ringbuf_drain)(void *map, void *callback_fn, void *ctx, __u64 flags) = (void *) 209;
 
+/*
+ * bpf_cgrp_storage_get
+ *
+ * 	Get a bpf_local_storage from the *cgroup*.
+ *
+ * 	Logically, it could be thought of as getting the value from
+ * 	a *map* with *cgroup* as the **key**.  From this
+ * 	perspective,  the usage is not much different from
+ * 	**bpf_map_lookup_elem**\ (*map*, **&**\ *cgroup*) except this
+ * 	helper enforces the key must be a cgroup struct and the map must also
+ * 	be a **BPF_MAP_TYPE_CGRP_STORAGE**.
+ *
+ * 	In reality, the local-storage value is embedded directly inside of the
+ * 	*cgroup* object itself, rather than being located in the
+ * 	**BPF_MAP_TYPE_CGRP_STORAGE** map. When the local-storage value is
+ * 	queried for some *map* on a *cgroup* object, the kernel will perform an
+ * 	O(n) iteration over all of the live local-storage values for that
+ * 	*cgroup* object until the local-storage value for the *map* is found.
+ *
+ * 	An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ * 	used such that a new bpf_local_storage will be
+ * 	created if one does not exist.  *value* can be used
+ * 	together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ * 	the initial value of a bpf_local_storage.  If *value* is
+ * 	**NULL**, the new bpf_local_storage will be zero initialized.
+ *
+ * Returns
+ * 	A bpf_local_storage pointer is returned on success.
+ *
+ * 	**NULL** if not found or there was an error in adding
+ * 	a new bpf_local_storage.
+ */
+static void *(*bpf_cgrp_storage_get)(void *map, struct cgroup *cgroup, void *value, __u64 flags) = (void *) 210;
+
+/*
+ * bpf_cgrp_storage_delete
+ *
+ * 	Delete a bpf_local_storage from a *cgroup*.
+ *
+ * Returns
+ * 	0 on success.
+ *
+ * 	**-ENOENT** if the bpf_local_storage cannot be found.
+ */
+static long (*bpf_cgrp_storage_delete)(void *map, struct cgroup *cgroup) = (void *) 211;
+
 

src/btf.c

@@ -688,8 +688,21 @@ int btf__align_of(const struct btf *btf, __u32 id)
 			if (align <= 0)
 				return libbpf_err(align);
 			max_align = max(max_align, align);
+
+			/* if field offset isn't aligned according to field
+			 * type's alignment, then struct must be packed
+			 */
+			if (btf_member_bitfield_size(t, i) == 0 &&
+			    (m->offset % (8 * align)) != 0)
+				return 1;
 		}
 
+		/* if struct/union size isn't a multiple of its alignment,
+		 * then struct must be packed
+		 */
+		if ((t->size % max_align) != 0)
+			return 1;
+
 		return max_align;
 	}
 	default:
@@ -990,6 +1003,7 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
 	err = 0;
 
 	if (!btf_data) {
+		pr_warn("failed to find '%s' ELF section in %s\n", BTF_ELF_SEC, path);
 		err = -ENOENT;
 		goto done;
 	}
@@ -1559,15 +1573,15 @@ struct btf_pipe {
 static int btf_rewrite_str(__u32 *str_off, void *ctx)
 {
 	struct btf_pipe *p = ctx;
-	void *mapped_off;
+	long mapped_off;
 	int off, err;
 
 	if (!*str_off) /* nothing to do for empty strings */
 		return 0;
 
 	if (p->str_off_map &&
-	    hashmap__find(p->str_off_map, (void *)(long)*str_off, &mapped_off)) {
-		*str_off = (__u32)(long)mapped_off;
+	    hashmap__find(p->str_off_map, *str_off, &mapped_off)) {
+		*str_off = mapped_off;
 		return 0;
 	}
 
@@ -1579,7 +1593,7 @@ static int btf_rewrite_str(__u32 *str_off, void *ctx)
 	 * performing expensive string comparisons.
 	 */
 	if (p->str_off_map) {
-		err = hashmap__append(p->str_off_map, (void *)(long)*str_off, (void *)(long)off);
+		err = hashmap__append(p->str_off_map, *str_off, off);
 		if (err)
 			return err;
 	}
@@ -1630,8 +1644,8 @@ static int btf_rewrite_type_ids(__u32 *type_id, void *ctx)
 	return 0;
 }
 
-static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx);
-static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx);
+static size_t btf_dedup_identity_hash_fn(long key, void *ctx);
+static bool btf_dedup_equal_fn(long k1, long k2, void *ctx);
 
 int btf__add_btf(struct btf *btf, const struct btf *src_btf)
 {
@@ -1724,7 +1738,8 @@ err_out:
 	memset(btf->strs_data + old_strs_len, 0, btf->hdr->str_len - old_strs_len);
 
 	/* and now restore original strings section size; types data size
-	 * wasn't modified, so doesn't need restoring, see big comment above */
+	 * wasn't modified, so doesn't need restoring, see big comment above
+	 */
 	btf->hdr->str_len = old_strs_len;
 
 	hashmap__free(p.str_off_map);
@@ -2329,7 +2344,7 @@ int btf__add_restrict(struct btf *btf, int ref_type_id)
  */
 int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id)
 {
-	if (!value|| !value[0])
+	if (!value || !value[0])
 		return libbpf_err(-EINVAL);
 
 	return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id);
@@ -2881,6 +2896,7 @@ static int btf_dedup_strings(struct btf_dedup *d);
 static int btf_dedup_prim_types(struct btf_dedup *d);
 static int btf_dedup_struct_types(struct btf_dedup *d);
 static int btf_dedup_ref_types(struct btf_dedup *d);
+static int btf_dedup_resolve_fwds(struct btf_dedup *d);
 static int btf_dedup_compact_types(struct btf_dedup *d);
 static int btf_dedup_remap_types(struct btf_dedup *d);
 
@@ -2988,15 +3004,16 @@ static int btf_dedup_remap_types(struct btf_dedup *d);
  * Algorithm summary
  * =================
  *
- * Algorithm completes its work in 6 separate passes:
+ * Algorithm completes its work in 7 separate passes:
  *
  * 1. Strings deduplication.
  * 2. Primitive types deduplication (int, enum, fwd).
  * 3. Struct/union types deduplication.
- * 4. Reference types deduplication (pointers, typedefs, arrays, funcs, func
+ * 4. Resolve unambiguous forward declarations.
+ * 5. Reference types deduplication (pointers, typedefs, arrays, funcs, func
  *    protos, and const/volatile/restrict modifiers).
- * 5. Types compaction.
- * 6. Types remapping.
+ * 6. Types compaction.
+ * 7. Types remapping.
  *
  * Algorithm determines canonical type descriptor, which is a single
  * representative type for each truly unique type. This canonical type is the
@@ -3060,6 +3077,11 @@ int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts)
 		pr_debug("btf_dedup_struct_types failed:%d\n", err);
 		goto done;
 	}
+	err = btf_dedup_resolve_fwds(d);
+	if (err < 0) {
+		pr_debug("btf_dedup_resolve_fwds failed:%d\n", err);
+		goto done;
+	}
 	err = btf_dedup_ref_types(d);
 	if (err < 0) {
 		pr_debug("btf_dedup_ref_types failed:%d\n", err);
@@ -3126,12 +3148,11 @@ static long hash_combine(long h, long value)
 }
 
 #define for_each_dedup_cand(d, node, hash) \
-	hashmap__for_each_key_entry(d->dedup_table, node, (void *)hash)
+	hashmap__for_each_key_entry(d->dedup_table, node, hash)
 
 static int btf_dedup_table_add(struct btf_dedup *d, long hash, __u32 type_id)
 {
-	return hashmap__append(d->dedup_table,
-			       (void *)hash, (void *)(long)type_id);
+	return hashmap__append(d->dedup_table, hash, type_id);
 }
 
 static int btf_dedup_hypot_map_add(struct btf_dedup *d,
@@ -3178,17 +3199,17 @@ static void btf_dedup_free(struct btf_dedup *d)
 	free(d);
 }
 
-static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx)
+static size_t btf_dedup_identity_hash_fn(long key, void *ctx)
 {
-	return (size_t)key;
+	return key;
 }
 
-static size_t btf_dedup_collision_hash_fn(const void *key, void *ctx)
+static size_t btf_dedup_collision_hash_fn(long key, void *ctx)
 {
 	return 0;
 }
 
-static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx)
+static bool btf_dedup_equal_fn(long k1, long k2, void *ctx)
 {
 	return k1 == k2;
 }
@@ -3404,23 +3425,17 @@ static long btf_hash_enum(struct btf_type *t)
 {
 	long h;
 
-	/* don't hash vlen and enum members to support enum fwd resolving */
+	/* don't hash vlen, enum members and size to support enum fwd resolving */
 	h = hash_combine(0, t->name_off);
-	h = hash_combine(h, t->info & ~0xffff);
-	h = hash_combine(h, t->size);
 	return h;
 }
 
-/* Check structural equality of two ENUMs. */
-static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2)
+static bool btf_equal_enum_members(struct btf_type *t1, struct btf_type *t2)
 {
 	const struct btf_enum *m1, *m2;
 	__u16 vlen;
 	int i;
 
-	if (!btf_equal_common(t1, t2))
-		return false;
-
 	vlen = btf_vlen(t1);
 	m1 = btf_enum(t1);
 	m2 = btf_enum(t2);
@@ -3433,15 +3448,12 @@ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2)
 	return true;
 }
 
-static bool btf_equal_enum64(struct btf_type *t1, struct btf_type *t2)
+static bool btf_equal_enum64_members(struct btf_type *t1, struct btf_type *t2)
 {
 	const struct btf_enum64 *m1, *m2;
 	__u16 vlen;
 	int i;
 
-	if (!btf_equal_common(t1, t2))
-		return false;
-
 	vlen = btf_vlen(t1);
 	m1 = btf_enum64(t1);
 	m2 = btf_enum64(t2);
@@ -3455,6 +3467,19 @@ static bool btf_equal_enum64(struct btf_type *t1, struct btf_type *t2)
 	return true;
 }
 
+/* Check structural equality of two ENUMs or ENUM64s. */
+static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2)
+{
+	if (!btf_equal_common(t1, t2))
+		return false;
+
+	/* t1 & t2 kinds are identical because of btf_equal_common */
+	if (btf_kind(t1) == BTF_KIND_ENUM)
+		return btf_equal_enum_members(t1, t2);
+	else
+		return btf_equal_enum64_members(t1, t2);
+}
+
 static inline bool btf_is_enum_fwd(struct btf_type *t)
 {
 	return btf_is_any_enum(t) && btf_vlen(t) == 0;
@@ -3464,21 +3489,14 @@ static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2)
 {
 	if (!btf_is_enum_fwd(t1) && !btf_is_enum_fwd(t2))
 		return btf_equal_enum(t1, t2);
-	/* ignore vlen when comparing */
+	/* At this point either t1 or t2 or both are forward declarations, thus:
+	 * - skip comparing vlen because it is zero for forward declarations;
+	 * - skip comparing size to allow enum forward declarations
+	 *   to be compatible with enum64 full declarations;
+	 * - skip comparing kind for the same reason.
+	 */
 	return t1->name_off == t2->name_off &&
-	       (t1->info & ~0xffff) == (t2->info & ~0xffff) &&
-	       t1->size == t2->size;
-}
-
-static bool btf_compat_enum64(struct btf_type *t1, struct btf_type *t2)
-{
-	if (!btf_is_enum_fwd(t1) && !btf_is_enum_fwd(t2))
-		return btf_equal_enum64(t1, t2);
-
-	/* ignore vlen when comparing */
-	return t1->name_off == t2->name_off &&
-	       (t1->info & ~0xffff) == (t2->info & ~0xffff) &&
-	       t1->size == t2->size;
+	       btf_is_any_enum(t1) && btf_is_any_enum(t2);
 }
 
 /*
@@ -3753,7 +3771,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 	case BTF_KIND_INT:
 		h = btf_hash_int_decl_tag(t);
 		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
+			cand_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_int_tag(t, cand)) {
 				new_id = cand_id;
@@ -3763,9 +3781,10 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 		break;
 
 	case BTF_KIND_ENUM:
+	case BTF_KIND_ENUM64:
 		h = btf_hash_enum(t);
 		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
+			cand_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_enum(t, cand)) {
 				new_id = cand_id;
@@ -3783,32 +3802,11 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 		}
 		break;
 
-	case BTF_KIND_ENUM64:
-		h = btf_hash_enum(t);
-		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
-			cand = btf_type_by_id(d->btf, cand_id);
-			if (btf_equal_enum64(t, cand)) {
-				new_id = cand_id;
-				break;
-			}
-			if (btf_compat_enum64(t, cand)) {
-				if (btf_is_enum_fwd(t)) {
-					/* resolve fwd to full enum */
-					new_id = cand_id;
-					break;
-				}
-				/* resolve canonical enum fwd to full enum */
-				d->map[cand_id] = type_id;
-			}
-		}
-		break;
-
 	case BTF_KIND_FWD:
 	case BTF_KIND_FLOAT:
 		h = btf_hash_common(t);
 		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
+			cand_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_common(t, cand)) {
 				new_id = cand_id;
@@ -3887,14 +3885,14 @@ static inline __u16 btf_fwd_kind(struct btf_type *t)
 }
 
 /* Check if given two types are identical ARRAY definitions */
-static int btf_dedup_identical_arrays(struct btf_dedup *d, __u32 id1, __u32 id2)
+static bool btf_dedup_identical_arrays(struct btf_dedup *d, __u32 id1, __u32 id2)
 {
 	struct btf_type *t1, *t2;
 
 	t1 = btf_type_by_id(d->btf, id1);
 	t2 = btf_type_by_id(d->btf, id2);
 	if (!btf_is_array(t1) || !btf_is_array(t2))
-		return 0;
+		return false;
 
 	return btf_equal_array(t1, t2);
 }
@@ -3918,7 +3916,9 @@ static bool btf_dedup_identical_structs(struct btf_dedup *d, __u32 id1, __u32 id
 	m1 = btf_members(t1);
 	m2 = btf_members(t2);
 	for (i = 0, n = btf_vlen(t1); i < n; i++, m1++, m2++) {
-		if (m1->type != m2->type)
+		if (m1->type != m2->type &&
+		    !btf_dedup_identical_arrays(d, m1->type, m2->type) &&
+		    !btf_dedup_identical_structs(d, m1->type, m2->type))
 			return false;
 	}
 	return true;
@@ -4097,10 +4097,8 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 		return btf_equal_int_tag(cand_type, canon_type);
 
 	case BTF_KIND_ENUM:
-		return btf_compat_enum(cand_type, canon_type);
-
 	case BTF_KIND_ENUM64:
-		return btf_compat_enum64(cand_type, canon_type);
+		return btf_compat_enum(cand_type, canon_type);
 
 	case BTF_KIND_FWD:
 	case BTF_KIND_FLOAT:
@@ -4311,7 +4309,7 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
 
 	h = btf_hash_struct(t);
 	for_each_dedup_cand(d, hash_entry, h) {
-		__u32 cand_id = (__u32)(long)hash_entry->value;
+		__u32 cand_id = hash_entry->value;
 		int eq;
 
 		/*
@@ -4416,7 +4414,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 
 		h = btf_hash_common(t);
 		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
+			cand_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_common(t, cand)) {
 				new_id = cand_id;
@@ -4433,7 +4431,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 
 		h = btf_hash_int_decl_tag(t);
 		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
+			cand_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_int_tag(t, cand)) {
 				new_id = cand_id;
@@ -4457,7 +4455,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 
 		h = btf_hash_array(t);
 		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
+			cand_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_array(t, cand)) {
 				new_id = cand_id;
@@ -4489,7 +4487,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 
 		h = btf_hash_fnproto(t);
 		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
+			cand_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_fnproto(t, cand)) {
 				new_id = cand_id;
@@ -4525,6 +4523,134 @@ static int btf_dedup_ref_types(struct btf_dedup *d)
 	return 0;
 }
 
+/*
+ * Collect a map from type names to type ids for all canonical structs
+ * and unions. If the same name is shared by several canonical types
+ * use a special value 0 to indicate this fact.
+ */
+static int btf_dedup_fill_unique_names_map(struct btf_dedup *d, struct hashmap *names_map)
+{
+	__u32 nr_types = btf__type_cnt(d->btf);
+	struct btf_type *t;
+	__u32 type_id;
+	__u16 kind;
+	int err;
+
+	/*
+	 * Iterate over base and split module ids in order to get all
+	 * available structs in the map.
+	 */
+	for (type_id = 1; type_id < nr_types; ++type_id) {
+		t = btf_type_by_id(d->btf, type_id);
+		kind = btf_kind(t);
+
+		if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION)
+			continue;
+
+		/* Skip non-canonical types */
+		if (type_id != d->map[type_id])
+			continue;
+
+		err = hashmap__add(names_map, t->name_off, type_id);
+		if (err == -EEXIST)
+			err = hashmap__set(names_map, t->name_off, 0, NULL, NULL);
+
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int btf_dedup_resolve_fwd(struct btf_dedup *d, struct hashmap *names_map, __u32 type_id)
+{
+	struct btf_type *t = btf_type_by_id(d->btf, type_id);
+	enum btf_fwd_kind fwd_kind = btf_kflag(t);
+	__u16 cand_kind, kind = btf_kind(t);
+	struct btf_type *cand_t;
+	uintptr_t cand_id;
+
+	if (kind != BTF_KIND_FWD)
+		return 0;
+
+	/* Skip if this FWD already has a mapping */
+	if (type_id != d->map[type_id])
+		return 0;
+
+	if (!hashmap__find(names_map, t->name_off, &cand_id))
+		return 0;
+
+	/* Zero is a special value indicating that name is not unique */
+	if (!cand_id)
+		return 0;
+
+	cand_t = btf_type_by_id(d->btf, cand_id);
+	cand_kind = btf_kind(cand_t);
+	if ((cand_kind == BTF_KIND_STRUCT && fwd_kind != BTF_FWD_STRUCT) ||
+	    (cand_kind == BTF_KIND_UNION && fwd_kind != BTF_FWD_UNION))
+		return 0;
+
+	d->map[type_id] = cand_id;
+
+	return 0;
+}
+
+/*
+ * Resolve unambiguous forward declarations.
+ *
+ * The lion's share of all FWD declarations is resolved during
+ * `btf_dedup_struct_types` phase when different type graphs are
+ * compared against each other. However, if in some compilation unit a
+ * FWD declaration is not a part of a type graph compared against
+ * another type graph that declaration's canonical type would not be
+ * changed. Example:
+ *
+ * CU #1:
+ *
+ * struct foo;
+ * struct foo *some_global;
+ *
+ * CU #2:
+ *
+ * struct foo { int u; };
+ * struct foo *another_global;
+ *
+ * After `btf_dedup_struct_types` the BTF looks as follows:
+ *
+ * [1] STRUCT 'foo' size=4 vlen=1 ...
+ * [2] INT 'int' size=4 ...
+ * [3] PTR '(anon)' type_id=1
+ * [4] FWD 'foo' fwd_kind=struct
+ * [5] PTR '(anon)' type_id=4
+ *
+ * This pass assumes that such FWD declarations should be mapped to
+ * structs or unions with identical name in case if the name is not
+ * ambiguous.
+ */
+static int btf_dedup_resolve_fwds(struct btf_dedup *d)
+{
+	int i, err;
+	struct hashmap *names_map;
+
+	names_map = hashmap__new(btf_dedup_identity_hash_fn, btf_dedup_equal_fn, NULL);
+	if (IS_ERR(names_map))
+		return PTR_ERR(names_map);
+
+	err = btf_dedup_fill_unique_names_map(d, names_map);
+	if (err < 0)
+		goto exit;
+
+	for (i = 0; i < d->btf->nr_types; i++) {
+		err = btf_dedup_resolve_fwd(d, names_map, d->btf->start_id + i);
+		if (err < 0)
+			break;
+	}
+
+exit:
+	hashmap__free(names_map);
+	return err;
+}
+
 /*
  * Compact types.
  *

src/btf_dump.c

@@ -13,6 +13,7 @@
 #include <ctype.h>
 #include <endian.h>
 #include <errno.h>
+#include <limits.h>
 #include <linux/err.h>
 #include <linux/btf.h>
 #include <linux/kernel.h>
@@ -117,14 +118,14 @@ struct btf_dump {
 	struct btf_dump_data *typed_dump;
 };
 
-static size_t str_hash_fn(const void *key, void *ctx)
+static size_t str_hash_fn(long key, void *ctx)
 {
-	return str_hash(key);
+	return str_hash((void *)key);
 }
 
-static bool str_equal_fn(const void *a, const void *b, void *ctx)
+static bool str_equal_fn(long a, long b, void *ctx)
 {
-	return strcmp(a, b) == 0;
+	return strcmp((void *)a, (void *)b) == 0;
 }
 
 static const char *btf_name_of(const struct btf_dump *d, __u32 name_off)
@@ -219,6 +220,17 @@ static int btf_dump_resize(struct btf_dump *d)
 	return 0;
 }
 
+static void btf_dump_free_names(struct hashmap *map)
+{
+	size_t bkt;
+	struct hashmap_entry *cur;
+
+	hashmap__for_each_entry(map, cur, bkt)
+		free((void *)cur->pkey);
+
+	hashmap__free(map);
+}
+
 void btf_dump__free(struct btf_dump *d)
 {
 	int i;
@@ -237,8 +249,8 @@ void btf_dump__free(struct btf_dump *d)
 	free(d->cached_names);
 	free(d->emit_queue);
 	free(d->decl_stack);
-	hashmap__free(d->type_names);
-	hashmap__free(d->ident_names);
+	btf_dump_free_names(d->type_names);
+	btf_dump_free_names(d->ident_names);
 
 	free(d);
 }
@@ -822,14 +834,9 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id,
 				 const struct btf_type *t)
 {
 	const struct btf_member *m;
-	int align, i, bit_sz;
+	int max_align = 1, align, i, bit_sz;
 	__u16 vlen;
 
-	align = btf__align_of(btf, id);
-	/* size of a non-packed struct has to be a multiple of its alignment*/
-	if (align && t->size % align)
-		return true;
-
 	m = btf_members(t);
 	vlen = btf_vlen(t);
 	/* all non-bitfield fields have to be naturally aligned */
@@ -838,8 +845,11 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id,
 		bit_sz = btf_member_bitfield_size(t, i);
 		if (align && bit_sz == 0 && m->offset % (8 * align) != 0)
 			return true;
+		max_align = max(align, max_align);
 	}
-
+	/* size of a non-packed struct has to be a multiple of its alignment */
+	if (t->size % max_align != 0)
+		return true;
 	/*
 	 * if original struct was marked as packed, but its layout is
 	 * naturally aligned, we'll detect that it's not packed
@@ -847,44 +857,97 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id,
 	return false;
 }
 
-static int chip_away_bits(int total, int at_most)
-{
-	return total % at_most ? : at_most;
-}
-
 static void btf_dump_emit_bit_padding(const struct btf_dump *d,
-				      int cur_off, int m_off, int m_bit_sz,
-				      int align, int lvl)
+				      int cur_off, int next_off, int next_align,
+				      bool in_bitfield, int lvl)
 {
-	int off_diff = m_off - cur_off;
-	int ptr_bits = d->ptr_sz * 8;
+	const struct {
+		const char *name;
+		int bits;
+	} pads[] = {
+		{"long", d->ptr_sz * 8}, {"int", 32}, {"short", 16}, {"char", 8}
+	};
+	int new_off, pad_bits, bits, i;
+	const char *pad_type;
 
-	if (off_diff <= 0)
-		/* no gap */
-		return;
-	if (m_bit_sz == 0 && off_diff < align * 8)
-		/* natural padding will take care of a gap */
-		return;
+	if (cur_off >= next_off)
+		return; /* no gap */
 
-	while (off_diff > 0) {
-		const char *pad_type;
-		int pad_bits;
+	/* For filling out padding we want to take advantage of
+	 * natural alignment rules to minimize unnecessary explicit
+	 * padding. First, we find the largest type (among long, int,
+	 * short, or char) that can be used to force naturally aligned
+	 * boundary. Once determined, we'll use such type to fill in
+	 * the remaining padding gap. In some cases we can rely on
+	 * compiler filling some gaps, but sometimes we need to force
+	 * alignment to close natural alignment with markers like
+	 * `long: 0` (this is always the case for bitfields).  Note
+	 * that even if struct itself has, let's say 4-byte alignment
+	 * (i.e., it only uses up to int-aligned types), using `long:
+	 * X;` explicit padding doesn't actually change struct's
+	 * overall alignment requirements, but compiler does take into
+	 * account that type's (long, in this example) natural
+	 * alignment requirements when adding implicit padding. We use
+	 * this fact heavily and don't worry about ruining correct
+	 * struct alignment requirement.
+	 */
+	for (i = 0; i < ARRAY_SIZE(pads); i++) {
+		pad_bits = pads[i].bits;
+		pad_type = pads[i].name;
 
-		if (ptr_bits > 32 && off_diff > 32) {
-			pad_type = "long";
-			pad_bits = chip_away_bits(off_diff, ptr_bits);
-		} else if (off_diff > 16) {
-			pad_type = "int";
-			pad_bits = chip_away_bits(off_diff, 32);
-		} else if (off_diff > 8) {
-			pad_type = "short";
-			pad_bits = chip_away_bits(off_diff, 16);
-		} else {
-			pad_type = "char";
-			pad_bits = chip_away_bits(off_diff, 8);
+		new_off = roundup(cur_off, pad_bits);
+		if (new_off <= next_off)
+			break;
+	}
+
+	if (new_off > cur_off && new_off <= next_off) {
+		/* We need explicit `<type>: 0` aligning mark if next
+		 * field is right on alignment offset and its
+		 * alignment requirement is less strict than <type>'s
+		 * alignment (so compiler won't naturally align to the
+		 * offset we expect), or if subsequent `<type>: X`,
+		 * will actually completely fit in the remaining hole,
+		 * making compiler basically ignore `<type>: X`
+		 * completely.
+		 */
+		if (in_bitfield ||
+		    (new_off == next_off && roundup(cur_off, next_align * 8) != new_off) ||
+		    (new_off != next_off && next_off - new_off <= new_off - cur_off))
+			/* but for bitfields we'll emit explicit bit count */
+			btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type,
+					in_bitfield ? new_off - cur_off : 0);
+		cur_off = new_off;
+	}
+
+	/* Now we know we start at naturally aligned offset for a chosen
+	 * padding type (long, int, short, or char), and so the rest is just
+	 * a straightforward filling of remaining padding gap with full
+	 * `<type>: sizeof(<type>);` markers, except for the last one, which
+	 * might need smaller than sizeof(<type>) padding.
+	 */
+	while (cur_off != next_off) {
+		bits = min(next_off - cur_off, pad_bits);
+		if (bits == pad_bits) {
+			btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, pad_bits);
+			cur_off += bits;
+			continue;
+		}
+		/* For the remainder padding that doesn't cover entire
+		 * pad_type bit length, we pick the smallest necessary type.
+		 * This is pure aesthetics, we could have just used `long`,
+		 * but having smallest necessary one communicates better the
+		 * scale of the padding gap.
+		 */
+		for (i = ARRAY_SIZE(pads) - 1; i >= 0; i--) {
+			pad_type = pads[i].name;
+			pad_bits = pads[i].bits;
+			if (pad_bits < bits)
+				continue;
+
+			btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, bits);
+			cur_off += bits;
+			break;
 		}
-		btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, pad_bits);
-		off_diff -= pad_bits;
 	}
 }
 
@@ -904,9 +967,11 @@ static void btf_dump_emit_struct_def(struct btf_dump *d,
 {
 	const struct btf_member *m = btf_members(t);
 	bool is_struct = btf_is_struct(t);
-	int align, i, packed, off = 0;
+	bool packed, prev_bitfield = false;
+	int align, i, off = 0;
 	__u16 vlen = btf_vlen(t);
 
+	align = btf__align_of(d->btf, id);
 	packed = is_struct ? btf_is_struct_packed(d->btf, id, t) : 0;
 
 	btf_dump_printf(d, "%s%s%s {",
@@ -916,37 +981,47 @@ static void btf_dump_emit_struct_def(struct btf_dump *d,
 
 	for (i = 0; i < vlen; i++, m++) {
 		const char *fname;
-		int m_off, m_sz;
+		int m_off, m_sz, m_align;
+		bool in_bitfield;
 
 		fname = btf_name_of(d, m->name_off);
 		m_sz = btf_member_bitfield_size(t, i);
 		m_off = btf_member_bit_offset(t, i);
-		align = packed ? 1 : btf__align_of(d->btf, m->type);
+		m_align = packed ? 1 : btf__align_of(d->btf, m->type);
 
-		btf_dump_emit_bit_padding(d, off, m_off, m_sz, align, lvl + 1);
+		in_bitfield = prev_bitfield && m_sz != 0;
+
+		btf_dump_emit_bit_padding(d, off, m_off, m_align, in_bitfield, lvl + 1);
 		btf_dump_printf(d, "\n%s", pfx(lvl + 1));
 		btf_dump_emit_type_decl(d, m->type, fname, lvl + 1);
 
 		if (m_sz) {
 			btf_dump_printf(d, ": %d", m_sz);
 			off = m_off + m_sz;
+			prev_bitfield = true;
 		} else {
 			m_sz = max((__s64)0, btf__resolve_size(d->btf, m->type));
 			off = m_off + m_sz * 8;
+			prev_bitfield = false;
 		}
+
 		btf_dump_printf(d, ";");
 	}
 
 	/* pad at the end, if necessary */
-	if (is_struct) {
-		align = packed ? 1 : btf__align_of(d->btf, id);
-		btf_dump_emit_bit_padding(d, off, t->size * 8, 0, align,
-					  lvl + 1);
-	}
+	if (is_struct)
+		btf_dump_emit_bit_padding(d, off, t->size * 8, align, false, lvl + 1);
 
-	if (vlen)
+	/*
+	 * Keep `struct empty {}` on a single line,
+	 * only print newline when there are regular or padding fields.
+	 */
+	if (vlen || t->size) {
 		btf_dump_printf(d, "\n");
-	btf_dump_printf(d, "%s}", pfx(lvl));
+		btf_dump_printf(d, "%s}", pfx(lvl));
+	} else {
+		btf_dump_printf(d, "}");
+	}
 	if (packed)
 		btf_dump_printf(d, " __attribute__((packed))");
 }
@@ -1058,6 +1133,43 @@ static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id,
 	else
 		btf_dump_emit_enum64_val(d, t, lvl, vlen);
 	btf_dump_printf(d, "\n%s}", pfx(lvl));
+
+	/* special case enums with special sizes */
+	if (t->size == 1) {
+		/* one-byte enums can be forced with mode(byte) attribute */
+		btf_dump_printf(d, " __attribute__((mode(byte)))");
+	} else if (t->size == 8 && d->ptr_sz == 8) {
+		/* enum can be 8-byte sized if one of the enumerator values
+		 * doesn't fit in 32-bit integer, or by adding mode(word)
+		 * attribute (but probably only on 64-bit architectures); do
+		 * our best here to try to satisfy the contract without adding
+		 * unnecessary attributes
+		 */
+		bool needs_word_mode;
+
+		if (btf_is_enum(t)) {
+			/* enum can't represent 64-bit values, so we need word mode */
+			needs_word_mode = true;
+		} else {
+			/* enum64 needs mode(word) if none of its values has
+			 * non-zero upper 32-bits (which means that all values
+			 * fit in 32-bit integers and won't cause compiler to
+			 * bump enum to be 64-bit naturally
+			 */
+			int i;
+
+			needs_word_mode = true;
+			for (i = 0; i < vlen; i++) {
+				if (btf_enum64(t)[i].val_hi32 != 0) {
+					needs_word_mode = false;
+					break;
+				}
+			}
+		}
+		if (needs_word_mode)
+			btf_dump_printf(d, " __attribute__((mode(word)))");
+	}
+
 }
 
 static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id,
@@ -1520,11 +1632,22 @@ static void btf_dump_emit_type_cast(struct btf_dump *d, __u32 id,
 static size_t btf_dump_name_dups(struct btf_dump *d, struct hashmap *name_map,
 				 const char *orig_name)
 {
+	char *old_name, *new_name;
 	size_t dup_cnt = 0;
+	int err;
 
-	hashmap__find(name_map, orig_name, (void **)&dup_cnt);
+	new_name = strdup(orig_name);
+	if (!new_name)
+		return 1;
+
+	(void)hashmap__find(name_map, orig_name, &dup_cnt);
 	dup_cnt++;
-	hashmap__set(name_map, orig_name, (void *)dup_cnt, NULL, NULL);
+
+	err = hashmap__set(name_map, new_name, dup_cnt, &old_name, NULL);
+	if (err)
+		free(new_name);
+
+	free(old_name);
 
 	return dup_cnt;
 }
@@ -1963,7 +2086,7 @@ static int btf_dump_struct_data(struct btf_dump *d,
 {
 	const struct btf_member *m = btf_members(t);
 	__u16 n = btf_vlen(t);
-	int i, err;
+	int i, err = 0;
 
 	/* note that we increment depth before calling btf_dump_print() below;
 	 * this is intentional.  btf_dump_data_newline() will not print a

src/hashmap.c

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

src/hashmap.h

@@ -40,12 +40,32 @@ static inline size_t str_hash(const char *s)
 	return h;
 }
 
-typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx);
-typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx);
+typedef size_t (*hashmap_hash_fn)(long key, void *ctx);
+typedef bool (*hashmap_equal_fn)(long key1, long key2, void *ctx);
 
+/*
+ * Hashmap interface is polymorphic, keys and values could be either
+ * long-sized integers or pointers, this is achieved as follows:
+ * - interface functions that operate on keys and values are hidden
+ *   behind auxiliary macros, e.g. hashmap_insert <-> hashmap__insert;
+ * - these auxiliary macros cast the key and value parameters as
+ *   long or long *, so the user does not have to specify the casts explicitly;
+ * - for pointer parameters (e.g. old_key) the size of the pointed
+ *   type is verified by hashmap_cast_ptr using _Static_assert;
+ * - when iterating using hashmap__for_each_* forms
+ *   hasmap_entry->key should be used for integer keys and
+ *   hasmap_entry->pkey should be used for pointer keys,
+ *   same goes for values.
+ */
 struct hashmap_entry {
-	const void *key;
-	void *value;
+	union {
+		long key;
+		const void *pkey;
+	};
+	union {
+		long value;
+		void *pvalue;
+	};
 	struct hashmap_entry *next;
 };
 
@@ -102,6 +122,13 @@ enum hashmap_insert_strategy {
 	HASHMAP_APPEND,
 };
 
+#define hashmap_cast_ptr(p) ({								\
+	_Static_assert((__builtin_constant_p((p)) ? (p) == NULL : 0) ||			\
+				sizeof(*(p)) == sizeof(long),				\
+		       #p " pointee should be a long-sized integer or a pointer");	\
+	(long *)(p);									\
+})
+
 /*
  * hashmap__insert() adds key/value entry w/ various semantics, depending on
  * provided strategy value. If a given key/value pair replaced already
@@ -109,42 +136,38 @@ enum hashmap_insert_strategy {
  * through old_key and old_value to allow calling code do proper memory
  * management.
  */
-int hashmap__insert(struct hashmap *map, const void *key, void *value,
-		    enum hashmap_insert_strategy strategy,
-		    const void **old_key, void **old_value);
+int hashmap_insert(struct hashmap *map, long key, long value,
+		   enum hashmap_insert_strategy strategy,
+		   long *old_key, long *old_value);
 
-static inline int hashmap__add(struct hashmap *map,
-			       const void *key, void *value)
-{
-	return hashmap__insert(map, key, value, HASHMAP_ADD, NULL, NULL);
-}
+#define hashmap__insert(map, key, value, strategy, old_key, old_value) \
+	hashmap_insert((map), (long)(key), (long)(value), (strategy),  \
+		       hashmap_cast_ptr(old_key),		       \
+		       hashmap_cast_ptr(old_value))
 
-static inline int hashmap__set(struct hashmap *map,
-			       const void *key, void *value,
-			       const void **old_key, void **old_value)
-{
-	return hashmap__insert(map, key, value, HASHMAP_SET,
-			       old_key, old_value);
-}
+#define hashmap__add(map, key, value) \
+	hashmap__insert((map), (key), (value), HASHMAP_ADD, NULL, NULL)
 
-static inline int hashmap__update(struct hashmap *map,
-				  const void *key, void *value,
-				  const void **old_key, void **old_value)
-{
-	return hashmap__insert(map, key, value, HASHMAP_UPDATE,
-			       old_key, old_value);
-}
+#define hashmap__set(map, key, value, old_key, old_value) \
+	hashmap__insert((map), (key), (value), HASHMAP_SET, (old_key), (old_value))
 
-static inline int hashmap__append(struct hashmap *map,
-				  const void *key, void *value)
-{
-	return hashmap__insert(map, key, value, HASHMAP_APPEND, NULL, NULL);
-}
+#define hashmap__update(map, key, value, old_key, old_value) \
+	hashmap__insert((map), (key), (value), HASHMAP_UPDATE, (old_key), (old_value))
 
-bool hashmap__delete(struct hashmap *map, const void *key,
-		     const void **old_key, void **old_value);
+#define hashmap__append(map, key, value) \
+	hashmap__insert((map), (key), (value), HASHMAP_APPEND, NULL, NULL)
 
-bool hashmap__find(const struct hashmap *map, const void *key, void **value);
+bool hashmap_delete(struct hashmap *map, long key, long *old_key, long *old_value);
+
+#define hashmap__delete(map, key, old_key, old_value)		       \
+	hashmap_delete((map), (long)(key),			       \
+		       hashmap_cast_ptr(old_key),		       \
+		       hashmap_cast_ptr(old_value))
+
+bool hashmap_find(const struct hashmap *map, long key, long *value);
+
+#define hashmap__find(map, key, value) \
+	hashmap_find((map), (long)(key), hashmap_cast_ptr(value))
 
 /*
  * hashmap__for_each_entry - iterate over all entries in hashmap

src/libbpf.c

@@ -164,6 +164,7 @@ static const char * const map_type_name[] = {
 	[BPF_MAP_TYPE_TASK_STORAGE]		= "task_storage",
 	[BPF_MAP_TYPE_BLOOM_FILTER]		= "bloom_filter",
 	[BPF_MAP_TYPE_USER_RINGBUF]             = "user_ringbuf",
+	[BPF_MAP_TYPE_CGRP_STORAGE]		= "cgrp_storage",
 };
 
 static const char * const prog_type_name[] = {
@@ -346,7 +347,8 @@ enum sec_def_flags {
 	SEC_ATTACHABLE = 2,
 	SEC_ATTACHABLE_OPT = SEC_ATTACHABLE | SEC_EXP_ATTACH_OPT,
 	/* attachment target is specified through BTF ID in either kernel or
-	 * other BPF program's BTF object */
+	 * other BPF program's BTF object
+	 */
 	SEC_ATTACH_BTF = 4,
 	/* BPF program type allows sleeping/blocking in kernel */
 	SEC_SLEEPABLE = 8,
@@ -487,7 +489,7 @@ struct bpf_map {
 	char *name;
 	/* real_name is defined for special internal maps (.rodata*,
 	 * .data*, .bss, .kconfig) and preserves their original ELF section
-	 * name. This is important to be be able to find corresponding BTF
+	 * name. This is important to be able to find corresponding BTF
 	 * DATASEC information.
 	 */
 	char *real_name;
@@ -597,7 +599,7 @@ struct elf_state {
 	size_t shstrndx; /* section index for section name strings */
 	size_t strtabidx;
 	struct elf_sec_desc *secs;
-	int sec_cnt;
+	size_t sec_cnt;
 	int btf_maps_shndx;
 	__u32 btf_maps_sec_btf_id;
 	int text_shndx;
@@ -1408,6 +1410,10 @@ static int bpf_object__check_endianness(struct bpf_object *obj)
 static int
 bpf_object__init_license(struct bpf_object *obj, void *data, size_t size)
 {
+	if (!data) {
+		pr_warn("invalid license section in %s\n", obj->path);
+		return -LIBBPF_ERRNO__FORMAT;
+	}
 	/* libbpf_strlcpy() only copies first N - 1 bytes, so size + 1 won't
 	 * go over allowed ELF data section buffer
 	 */
@@ -1421,7 +1427,7 @@ bpf_object__init_kversion(struct bpf_object *obj, void *data, size_t size)
 {
 	__u32 kver;
 
-	if (size != sizeof(kver)) {
+	if (!data || size != sizeof(kver)) {
 		pr_warn("invalid kver section in %s\n", obj->path);
 		return -LIBBPF_ERRNO__FORMAT;
 	}
@@ -1457,15 +1463,12 @@ static int find_elf_sec_sz(const struct bpf_object *obj, const char *name, __u32
 	return -ENOENT;
 }
 
-static int find_elf_var_offset(const struct bpf_object *obj, const char *name, __u32 *off)
+static Elf64_Sym *find_elf_var_sym(const struct bpf_object *obj, const char *name)
 {
 	Elf_Data *symbols = obj->efile.symbols;
 	const char *sname;
 	size_t si;
 
-	if (!name || !off)
-		return -EINVAL;
-
 	for (si = 0; si < symbols->d_size / sizeof(Elf64_Sym); si++) {
 		Elf64_Sym *sym = elf_sym_by_idx(obj, si);
 
@@ -1479,15 +1482,13 @@ static int find_elf_var_offset(const struct bpf_object *obj, const char *name, _
 		sname = elf_sym_str(obj, sym->st_name);
 		if (!sname) {
 			pr_warn("failed to get sym name string for var %s\n", name);
-			return -EIO;
-		}
-		if (strcmp(name, sname) == 0) {
-			*off = sym->st_value;
-			return 0;
+			return ERR_PTR(-EIO);
 		}
+		if (strcmp(name, sname) == 0)
+			return sym;
 	}
 
-	return -ENOENT;
+	return ERR_PTR(-ENOENT);
 }
 
 static struct bpf_map *bpf_object__add_map(struct bpf_object *obj)
@@ -1578,7 +1579,38 @@ static char *internal_map_name(struct bpf_object *obj, const char *real_name)
 }
 
 static int
-bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map);
+map_fill_btf_type_info(struct bpf_object *obj, struct bpf_map *map);
+
+/* Internal BPF map is mmap()'able only if at least one of corresponding
+ * DATASEC's VARs are to be exposed through BPF skeleton. I.e., it's a GLOBAL
+ * variable and it's not marked as __hidden (which turns it into, effectively,
+ * a STATIC variable).
+ */
+static bool map_is_mmapable(struct bpf_object *obj, struct bpf_map *map)
+{
+	const struct btf_type *t, *vt;
+	struct btf_var_secinfo *vsi;
+	int i, n;
+
+	if (!map->btf_value_type_id)
+		return false;
+
+	t = btf__type_by_id(obj->btf, map->btf_value_type_id);
+	if (!btf_is_datasec(t))
+		return false;
+
+	vsi = btf_var_secinfos(t);
+	for (i = 0, n = btf_vlen(t); i < n; i++, vsi++) {
+		vt = btf__type_by_id(obj->btf, vsi->type);
+		if (!btf_is_var(vt))
+			continue;
+
+		if (btf_var(vt)->linkage != BTF_VAR_STATIC)
+			return true;
+	}
+
+	return false;
+}
 
 static int
 bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
@@ -1610,7 +1642,12 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 	def->max_entries = 1;
 	def->map_flags = type == LIBBPF_MAP_RODATA || type == LIBBPF_MAP_KCONFIG
 			 ? BPF_F_RDONLY_PROG : 0;
-	def->map_flags |= BPF_F_MMAPABLE;
+
+	/* failures are fine because of maps like .rodata.str1.1 */
+	(void) map_fill_btf_type_info(obj, map);
+
+	if (map_is_mmapable(obj, map))
+		def->map_flags |= BPF_F_MMAPABLE;
 
 	pr_debug("map '%s' (global data): at sec_idx %d, offset %zu, flags %x.\n",
 		 map->name, map->sec_idx, map->sec_offset, def->map_flags);
@@ -1627,9 +1664,6 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 		return err;
 	}
 
-	/* failures are fine because of maps like .rodata.str1.1 */
-	(void) bpf_map_find_btf_info(obj, map);
-
 	if (data)
 		memcpy(map->mmaped, data, data_sz);
 
@@ -1830,12 +1864,20 @@ static int set_kcfg_value_num(struct extern_desc *ext, void *ext_val,
 		return -ERANGE;
 	}
 	switch (ext->kcfg.sz) {
-		case 1: *(__u8 *)ext_val = value; break;
-		case 2: *(__u16 *)ext_val = value; break;
-		case 4: *(__u32 *)ext_val = value; break;
-		case 8: *(__u64 *)ext_val = value; break;
-		default:
-			return -EINVAL;
+	case 1:
+		*(__u8 *)ext_val = value;
+		break;
+	case 2:
+		*(__u16 *)ext_val = value;
+		break;
+	case 4:
+		*(__u32 *)ext_val = value;
+		break;
+	case 8:
+		*(__u64 *)ext_val = value;
+		break;
+	default:
+		return -EINVAL;
 	}
 	ext->is_set = true;
 	return 0;
@@ -2541,7 +2583,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 		fill_map_from_def(map->inner_map, &inner_def);
 	}
 
-	err = bpf_map_find_btf_info(obj, map);
+	err = map_fill_btf_type_info(obj, map);
 	if (err)
 		return err;
 
@@ -2737,7 +2779,7 @@ static int bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf)
 				m->type = enum64_placeholder_id;
 				m->offset = 0;
 			}
-                }
+		}
 	}
 
 	return 0;
@@ -2846,57 +2888,89 @@ static int compare_vsi_off(const void *_a, const void *_b)
 static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf,
 			     struct btf_type *t)
 {
-	__u32 size = 0, off = 0, i, vars = btf_vlen(t);
-	const char *name = btf__name_by_offset(btf, t->name_off);
-	const struct btf_type *t_var;
+	__u32 size = 0, i, vars = btf_vlen(t);
+	const char *sec_name = btf__name_by_offset(btf, t->name_off);
 	struct btf_var_secinfo *vsi;
-	const struct btf_var *var;
-	int ret;
+	bool fixup_offsets = false;
+	int err;
 
-	if (!name) {
+	if (!sec_name) {
 		pr_debug("No name found in string section for DATASEC kind.\n");
 		return -ENOENT;
 	}
 
-	/* .extern datasec size and var offsets were set correctly during
-	 * extern collection step, so just skip straight to sorting variables
+	/* Extern-backing datasecs (.ksyms, .kconfig) have their size and
+	 * variable offsets set at the previous step. Further, not every
+	 * extern BTF VAR has corresponding ELF symbol preserved, so we skip
+	 * all fixups altogether for such sections and go straight to sorting
+	 * VARs within their DATASEC.
 	 */
-	if (t->size)
+	if (strcmp(sec_name, KCONFIG_SEC) == 0 || strcmp(sec_name, KSYMS_SEC) == 0)
 		goto sort_vars;
 
-	ret = find_elf_sec_sz(obj, name, &size);
-	if (ret || !size) {
-		pr_debug("Invalid size for section %s: %u bytes\n", name, size);
-		return -ENOENT;
+	/* Clang leaves DATASEC size and VAR offsets as zeroes, so we need to
+	 * fix this up. But BPF static linker already fixes this up and fills
+	 * all the sizes and offsets during static linking. So this step has
+	 * to be optional. But the STV_HIDDEN handling is non-optional for any
+	 * non-extern DATASEC, so the variable fixup loop below handles both
+	 * functions at the same time, paying the cost of BTF VAR <-> ELF
+	 * symbol matching just once.
+	 */
+	if (t->size == 0) {
+		err = find_elf_sec_sz(obj, sec_name, &size);
+		if (err || !size) {
+			pr_debug("sec '%s': failed to determine size from ELF: size %u, err %d\n",
+				 sec_name, size, err);
+			return -ENOENT;
+		}
+
+		t->size = size;
+		fixup_offsets = true;
 	}
 
-	t->size = size;
-
 	for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) {
+		const struct btf_type *t_var;
+		struct btf_var *var;
+		const char *var_name;
+		Elf64_Sym *sym;
+
 		t_var = btf__type_by_id(btf, vsi->type);
 		if (!t_var || !btf_is_var(t_var)) {
-			pr_debug("Non-VAR type seen in section %s\n", name);
+			pr_debug("sec '%s': unexpected non-VAR type found\n", sec_name);
 			return -EINVAL;
 		}
 
 		var = btf_var(t_var);
-		if (var->linkage == BTF_VAR_STATIC)
+		if (var->linkage == BTF_VAR_STATIC || var->linkage == BTF_VAR_GLOBAL_EXTERN)
 			continue;
 
-		name = btf__name_by_offset(btf, t_var->name_off);
-		if (!name) {
-			pr_debug("No name found in string section for VAR kind\n");
+		var_name = btf__name_by_offset(btf, t_var->name_off);
+		if (!var_name) {
+			pr_debug("sec '%s': failed to find name of DATASEC's member #%d\n",
+				 sec_name, i);
 			return -ENOENT;
 		}
 
-		ret = find_elf_var_offset(obj, name, &off);
-		if (ret) {
-			pr_debug("No offset found in symbol table for VAR %s\n",
-				 name);
+		sym = find_elf_var_sym(obj, var_name);
+		if (IS_ERR(sym)) {
+			pr_debug("sec '%s': failed to find ELF symbol for VAR '%s'\n",
+				 sec_name, var_name);
 			return -ENOENT;
 		}
 
-		vsi->offset = off;
+		if (fixup_offsets)
+			vsi->offset = sym->st_value;
+
+		/* if variable is a global/weak symbol, but has restricted
+		 * (STV_HIDDEN or STV_INTERNAL) visibility, mark its BTF VAR
+		 * as static. This follows similar logic for functions (BPF
+		 * subprogs) and influences libbpf's further decisions about
+		 * whether to make global data BPF array maps as
+		 * BPF_F_MMAPABLE.
+		 */
+		if (ELF64_ST_VISIBILITY(sym->st_other) == STV_HIDDEN
+		    || ELF64_ST_VISIBILITY(sym->st_other) == STV_INTERNAL)
+			var->linkage = BTF_VAR_STATIC;
 	}
 
 sort_vars:
@@ -2904,13 +2978,16 @@ sort_vars:
 	return 0;
 }
 
-static int btf_finalize_data(struct bpf_object *obj, struct btf *btf)
+static int bpf_object_fixup_btf(struct bpf_object *obj)
 {
-	int err = 0;
-	__u32 i, n = btf__type_cnt(btf);
+	int i, n, err = 0;
 
+	if (!obj->btf)
+		return 0;
+
+	n = btf__type_cnt(obj->btf);
 	for (i = 1; i < n; i++) {
-		struct btf_type *t = btf_type_by_id(btf, i);
+		struct btf_type *t = btf_type_by_id(obj->btf, i);
 
 		/* Loader needs to fix up some of the things compiler
 		 * couldn't get its hands on while emitting BTF. This
@@ -2918,28 +2995,12 @@ static int btf_finalize_data(struct bpf_object *obj, struct btf *btf)
 		 * the info from the ELF itself for this purpose.
 		 */
 		if (btf_is_datasec(t)) {
-			err = btf_fixup_datasec(obj, btf, t);
+			err = btf_fixup_datasec(obj, obj->btf, t);
 			if (err)
-				break;
+				return err;
 		}
 	}
 
-	return libbpf_err(err);
-}
-
-static int bpf_object__finalize_btf(struct bpf_object *obj)
-{
-	int err;
-
-	if (!obj->btf)
-		return 0;
-
-	err = btf_finalize_data(obj, obj->btf);
-	if (err) {
-		pr_warn("Error finalizing %s: %d.\n", BTF_ELF_SEC, err);
-		return err;
-	}
-
 	return 0;
 }
 
@@ -3312,10 +3373,15 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 	Elf64_Shdr *sh;
 
 	/* ELF section indices are 0-based, but sec #0 is special "invalid"
-	 * section. e_shnum does include sec #0, so e_shnum is the necessary
-	 * size of an array to keep all the sections.
+	 * section. Since section count retrieved by elf_getshdrnum() does
+	 * include sec #0, it is already the necessary size of an array to keep
+	 * all the sections.
 	 */
-	obj->efile.sec_cnt = obj->efile.ehdr->e_shnum;
+	if (elf_getshdrnum(obj->efile.elf, &obj->efile.sec_cnt)) {
+		pr_warn("elf: failed to get the number of sections for %s: %s\n",
+			obj->path, elf_errmsg(-1));
+		return -LIBBPF_ERRNO__FORMAT;
+	}
 	obj->efile.secs = calloc(obj->efile.sec_cnt, sizeof(*obj->efile.secs));
 	if (!obj->efile.secs)
 		return -ENOMEM;
@@ -3445,7 +3511,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 			sec_desc->sec_type = SEC_RELO;
 			sec_desc->shdr = sh;
 			sec_desc->data = data;
-		} else if (sh->sh_type == SHT_NOBITS && strcmp(name, BSS_SEC) == 0) {
+		} else if (sh->sh_type == SHT_NOBITS && (strcmp(name, BSS_SEC) == 0 ||
+							 str_has_pfx(name, BSS_SEC "."))) {
 			sec_desc->sec_type = SEC_BSS;
 			sec_desc->shdr = sh;
 			sec_desc->data = data;
@@ -3461,7 +3528,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 	}
 
 	/* sort BPF programs by section name and in-section instruction offset
-	 * for faster search */
+	 * for faster search
+	 */
 	if (obj->nr_programs)
 		qsort(obj->programs, obj->nr_programs, sizeof(*obj->programs), cmp_progs);
 
@@ -3760,7 +3828,7 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
 				return -EINVAL;
 			}
 			ext->kcfg.type = find_kcfg_type(obj->btf, t->type,
-						        &ext->kcfg.is_signed);
+							&ext->kcfg.is_signed);
 			if (ext->kcfg.type == KCFG_UNKNOWN) {
 				pr_warn("extern (kcfg) '%s': type is unsupported\n", ext_name);
 				return -ENOTSUP;
@@ -4106,6 +4174,9 @@ static struct bpf_program *find_prog_by_sec_insn(const struct bpf_object *obj,
 	int l = 0, r = obj->nr_programs - 1, m;
 	struct bpf_program *prog;
 
+	if (!obj->nr_programs)
+		return NULL;
+
 	while (l < r) {
 		m = l + (r - l + 1) / 2;
 		prog = &obj->programs[m];
@@ -4223,7 +4294,7 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, Elf64_Shdr *shdr, Elf_Dat
 	return 0;
 }
 
-static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map)
+static int map_fill_btf_type_info(struct bpf_object *obj, struct bpf_map *map)
 {
 	int id;
 
@@ -4905,9 +4976,9 @@ bpf_object__reuse_map(struct bpf_map *map)
 
 	err = bpf_map__reuse_fd(map, pin_fd);
 	close(pin_fd);
-	if (err) {
+	if (err)
 		return err;
-	}
+
 	map->pinned = true;
 	pr_debug("reused pinned map at '%s'\n", map->pin_path);
 
@@ -5425,7 +5496,7 @@ static int load_module_btfs(struct bpf_object *obj)
 		}
 
 		err = libbpf_ensure_mem((void **)&obj->btf_modules, &obj->btf_module_cap,
-				        sizeof(*obj->btf_modules), obj->btf_module_cnt + 1);
+					sizeof(*obj->btf_modules), obj->btf_module_cnt + 1);
 		if (err)
 			goto err_out;
 
@@ -5541,21 +5612,16 @@ int bpf_core_types_match(const struct btf *local_btf, __u32 local_id,
 	return __bpf_core_types_match(local_btf, local_id, targ_btf, targ_id, false, 32);
 }
 
-static size_t bpf_core_hash_fn(const void *key, void *ctx)
+static size_t bpf_core_hash_fn(const long key, void *ctx)
 {
-	return (size_t)key;
+	return key;
 }
 
-static bool bpf_core_equal_fn(const void *k1, const void *k2, void *ctx)
+static bool bpf_core_equal_fn(const long k1, const long k2, void *ctx)
 {
 	return k1 == k2;
 }
 
-static void *u32_as_hash_key(__u32 x)
-{
-	return (void *)(uintptr_t)x;
-}
-
 static int record_relo_core(struct bpf_program *prog,
 			    const struct bpf_core_relo *core_relo, int insn_idx)
 {
@@ -5598,7 +5664,6 @@ static int bpf_core_resolve_relo(struct bpf_program *prog,
 				 struct bpf_core_relo_res *targ_res)
 {
 	struct bpf_core_spec specs_scratch[3] = {};
-	const void *type_key = u32_as_hash_key(relo->type_id);
 	struct bpf_core_cand_list *cands = NULL;
 	const char *prog_name = prog->name;
 	const struct btf_type *local_type;
@@ -5615,7 +5680,7 @@ static int bpf_core_resolve_relo(struct bpf_program *prog,
 		return -EINVAL;
 
 	if (relo->kind != BPF_CORE_TYPE_ID_LOCAL &&
-	    !hashmap__find(cand_cache, type_key, (void **)&cands)) {
+	    !hashmap__find(cand_cache, local_id, &cands)) {
 		cands = bpf_core_find_cands(prog->obj, local_btf, local_id);
 		if (IS_ERR(cands)) {
 			pr_warn("prog '%s': relo #%d: target candidate search failed for [%d] %s %s: %ld\n",
@@ -5623,7 +5688,7 @@ static int bpf_core_resolve_relo(struct bpf_program *prog,
 				local_name, PTR_ERR(cands));
 			return PTR_ERR(cands);
 		}
-		err = hashmap__set(cand_cache, type_key, cands, NULL, NULL);
+		err = hashmap__set(cand_cache, local_id, cands, NULL, NULL);
 		if (err) {
 			bpf_core_free_cands(cands);
 			return err;
@@ -5746,7 +5811,7 @@ out:
 
 	if (!IS_ERR_OR_NULL(cand_cache)) {
 		hashmap__for_each_entry(cand_cache, entry, i) {
-			bpf_core_free_cands(entry->value);
+			bpf_core_free_cands(entry->pvalue);
 		}
 		hashmap__free(cand_cache);
 	}
@@ -6183,7 +6248,8 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog,
 		 * prog; each main prog can have a different set of
 		 * subprograms appended (potentially in different order as
 		 * well), so position of any subprog can be different for
-		 * different main programs */
+		 * different main programs
+		 */
 		insn->imm = subprog->sub_insn_off - (prog->sub_insn_off + insn_idx) - 1;
 
 		pr_debug("prog '%s': insn #%zu relocated, imm %d points to subprog '%s' (now at %zu offset)\n",
@@ -7221,7 +7287,7 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf,
 	err = err ? : bpf_object__check_endianness(obj);
 	err = err ? : bpf_object__elf_collect(obj);
 	err = err ? : bpf_object__collect_externs(obj);
-	err = err ? : bpf_object__finalize_btf(obj);
+	err = err ? : bpf_object_fixup_btf(obj);
 	err = err ? : bpf_object__init_maps(obj, opts);
 	err = err ? : bpf_object_init_progs(obj, opts);
 	err = err ? : bpf_object__collect_relos(obj);
@@ -9837,7 +9903,7 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
 	char errmsg[STRERR_BUFSIZE];
 	int type, pfd;
 
-	if (ref_ctr_off >= (1ULL << PERF_UPROBE_REF_CTR_OFFSET_BITS))
+	if ((__u64)ref_ctr_off >= (1ULL << PERF_UPROBE_REF_CTR_OFFSET_BITS))
 		return -EINVAL;
 
 	memset(&attr, 0, attr_sz);
@@ -10941,7 +11007,7 @@ struct bpf_link *bpf_program__attach_usdt(const struct bpf_program *prog,
 
 	usdt_cookie = OPTS_GET(opts, usdt_cookie, 0);
 	link = usdt_manager_attach_usdt(obj->usdt_man, prog, pid, binary_path,
-				        usdt_provider, usdt_name, usdt_cookie);
+					usdt_provider, usdt_name, usdt_cookie);
 	err = libbpf_get_error(link);
 	if (err)
 		return libbpf_err_ptr(err);
@@ -11169,7 +11235,7 @@ static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf
 	}
 
 	*link = bpf_program__attach_raw_tracepoint(prog, tp_name);
-	return libbpf_get_error(link);
+	return libbpf_get_error(*link);
 }
 
 /* Common logic for all BPF program types that attach to a btf_id */
@@ -12250,7 +12316,7 @@ int bpf_object__open_subskeleton(struct bpf_object_subskeleton *s)
 	btf = bpf_object__btf(s->obj);
 	if (!btf) {
 		pr_warn("subskeletons require BTF at runtime (object %s)\n",
-		        bpf_object__name(s->obj));
+			bpf_object__name(s->obj));
 		return libbpf_err(-errno);
 	}
 

src/libbpf.map

@@ -367,10 +367,14 @@ LIBBPF_1.0.0 {
 		libbpf_bpf_map_type_str;
 		libbpf_bpf_prog_type_str;
 		perf_buffer__buffer;
-};
+} LIBBPF_0.8.0;
 
 LIBBPF_1.1.0 {
 	global:
+		bpf_btf_get_fd_by_id_opts;
+		bpf_link_get_fd_by_id_opts;
+		bpf_map_get_fd_by_id_opts;
+		bpf_prog_get_fd_by_id_opts;
 		user_ring_buffer__discard;
 		user_ring_buffer__free;
 		user_ring_buffer__new;

src/libbpf_errno.c

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

src/libbpf_probes.c

@@ -221,6 +221,7 @@ static int probe_map_create(enum bpf_map_type map_type)
 	case BPF_MAP_TYPE_SK_STORAGE:
 	case BPF_MAP_TYPE_INODE_STORAGE:
 	case BPF_MAP_TYPE_TASK_STORAGE:
+	case BPF_MAP_TYPE_CGRP_STORAGE:
 		btf_key_type_id = 1;
 		btf_value_type_id = 3;
 		value_size = 8;
@@ -234,7 +235,7 @@ static int probe_map_create(enum bpf_map_type map_type)
 	case BPF_MAP_TYPE_USER_RINGBUF:
 		key_size = 0;
 		value_size = 0;
-		max_entries = 4096;
+		max_entries = sysconf(_SC_PAGE_SIZE);
 		break;
 	case BPF_MAP_TYPE_STRUCT_OPS:
 		/* we'll get -ENOTSUPP for invalid BTF type ID for struct_ops */

src/nlattr.c

@@ -32,7 +32,7 @@ static struct nlattr *nla_next(const struct nlattr *nla, int *remaining)
 
 static int nla_ok(const struct nlattr *nla, int remaining)
 {
-	return remaining >= sizeof(*nla) &&
+	return remaining >= (int)sizeof(*nla) &&
 	       nla->nla_len >= sizeof(*nla) &&
 	       nla->nla_len <= remaining;
 }

src/ringbuf.c

@@ -77,6 +77,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 	__u32 len = sizeof(info);
 	struct epoll_event *e;
 	struct ring *r;
+	__u64 mmap_sz;
 	void *tmp;
 	int err;
 
@@ -115,8 +116,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 	r->mask = info.max_entries - 1;
 
 	/* Map writable consumer page */
-	tmp = mmap(NULL, rb->page_size, PROT_READ | PROT_WRITE, MAP_SHARED,
-		   map_fd, 0);
+	tmp = mmap(NULL, rb->page_size, PROT_READ | PROT_WRITE, MAP_SHARED, map_fd, 0);
 	if (tmp == MAP_FAILED) {
 		err = -errno;
 		pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %d\n",
@@ -128,9 +128,13 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 	/* Map read-only producer page and data pages. We map twice as big
 	 * data size to allow simple reading of samples that wrap around the
 	 * end of a ring buffer. See kernel implementation for details.
-	 * */
-	tmp = mmap(NULL, rb->page_size + 2 * info.max_entries, PROT_READ,
-		   MAP_SHARED, map_fd, rb->page_size);
+	 */
+	mmap_sz = rb->page_size + 2 * (__u64)info.max_entries;
+	if (mmap_sz != (__u64)(size_t)mmap_sz) {
+		pr_warn("ringbuf: ring buffer size (%u) is too big\n", info.max_entries);
+		return libbpf_err(-E2BIG);
+	}
+	tmp = mmap(NULL, (size_t)mmap_sz, PROT_READ, MAP_SHARED, map_fd, rb->page_size);
 	if (tmp == MAP_FAILED) {
 		err = -errno;
 		ringbuf_unmap_ring(rb, r);
@@ -220,7 +224,7 @@ static inline int roundup_len(__u32 len)
 	return (len + 7) / 8 * 8;
 }
 
-static int64_t ringbuf_process_ring(struct ring* r)
+static int64_t ringbuf_process_ring(struct ring *r)
 {
 	int *len_ptr, len, err;
 	/* 64-bit to avoid overflow in case of extreme application behavior */
@@ -348,6 +352,7 @@ static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd)
 {
 	struct bpf_map_info info;
 	__u32 len = sizeof(info);
+	__u64 mmap_sz;
 	void *tmp;
 	struct epoll_event *rb_epoll;
 	int err;
@@ -384,8 +389,13 @@ static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd)
 	 * simple reading and writing of samples that wrap around the end of
 	 * the buffer.  See the kernel implementation for details.
 	 */
-	tmp = mmap(NULL, rb->page_size + 2 * info.max_entries,
-		   PROT_READ | PROT_WRITE, MAP_SHARED, map_fd, rb->page_size);
+	mmap_sz = rb->page_size + 2 * (__u64)info.max_entries;
+	if (mmap_sz != (__u64)(size_t)mmap_sz) {
+		pr_warn("user ringbuf: ring buf size (%u) is too big\n", info.max_entries);
+		return -E2BIG;
+	}
+	tmp = mmap(NULL, (size_t)mmap_sz, PROT_READ | PROT_WRITE, MAP_SHARED,
+		   map_fd, rb->page_size);
 	if (tmp == MAP_FAILED) {
 		err = -errno;
 		pr_warn("user ringbuf: failed to mmap data pages for map fd=%d: %d\n",
@@ -476,6 +486,10 @@ void *user_ring_buffer__reserve(struct user_ring_buffer *rb, __u32 size)
 	__u64 cons_pos, prod_pos;
 	struct ringbuf_hdr *hdr;
 
+	/* The top two bits are used as special flags */
+	if (size & (BPF_RINGBUF_BUSY_BIT | BPF_RINGBUF_DISCARD_BIT))
+		return errno = E2BIG, NULL;
+
 	/* Synchronizes with smp_store_release() in __bpf_user_ringbuf_peek() in
 	 * the kernel.
 	 */

src/strset.c

@@ -19,19 +19,19 @@ struct strset {
 	struct hashmap *strs_hash;
 };
 
-static size_t strset_hash_fn(const void *key, void *ctx)
+static size_t strset_hash_fn(long key, void *ctx)
 {
 	const struct strset *s = ctx;
-	const char *str = s->strs_data + (long)key;
+	const char *str = s->strs_data + key;
 
 	return str_hash(str);
 }
 
-static bool strset_equal_fn(const void *key1, const void *key2, void *ctx)
+static bool strset_equal_fn(long key1, long key2, void *ctx)
 {
 	const struct strset *s = ctx;
-	const char *str1 = s->strs_data + (long)key1;
-	const char *str2 = s->strs_data + (long)key2;
+	const char *str1 = s->strs_data + key1;
+	const char *str2 = s->strs_data + key2;
 
 	return strcmp(str1, str2) == 0;
 }
@@ -67,7 +67,7 @@ struct strset *strset__new(size_t max_data_sz, const char *init_data, size_t ini
 			/* hashmap__add() returns EEXIST if string with the same
 			 * content already is in the hash map
 			 */
-			err = hashmap__add(hash, (void *)off, (void *)off);
+			err = hashmap__add(hash, off, off);
 			if (err == -EEXIST)
 				continue; /* duplicate */
 			if (err)
@@ -127,7 +127,7 @@ int strset__find_str(struct strset *set, const char *s)
 	new_off = set->strs_data_len;
 	memcpy(p, s, len);
 
-	if (hashmap__find(set->strs_hash, (void *)new_off, (void **)&old_off))
+	if (hashmap__find(set->strs_hash, new_off, &old_off))
 		return old_off;
 
 	return -ENOENT;
@@ -165,8 +165,8 @@ int strset__add_str(struct strset *set, const char *s)
 	 * contents doesn't exist already (HASHMAP_ADD strategy). If such
 	 * string exists, we'll get its offset in old_off (that's old_key).
 	 */
-	err = hashmap__insert(set->strs_hash, (void *)new_off, (void *)new_off,
-			      HASHMAP_ADD, (const void **)&old_off, NULL);
+	err = hashmap__insert(set->strs_hash, new_off, new_off,
+			      HASHMAP_ADD, &old_off, NULL);
 	if (err == -EEXIST)
 		return old_off; /* duplicated string, return existing offset */
 	if (err)

src/usdt.c

@@ -873,31 +873,27 @@ static void bpf_link_usdt_dealloc(struct bpf_link *link)
 	free(usdt_link);
 }
 
-static size_t specs_hash_fn(const void *key, void *ctx)
+static size_t specs_hash_fn(long key, void *ctx)
 {
-	const char *s = key;
-
-	return str_hash(s);
+	return str_hash((char *)key);
 }
 
-static bool specs_equal_fn(const void *key1, const void *key2, void *ctx)
+static bool specs_equal_fn(long key1, long key2, void *ctx)
 {
-	const char *s1 = key1;
-	const char *s2 = key2;
-
-	return strcmp(s1, s2) == 0;
+	return strcmp((char *)key1, (char *)key2) == 0;
 }
 
 static int allocate_spec_id(struct usdt_manager *man, struct hashmap *specs_hash,
 			    struct bpf_link_usdt *link, struct usdt_target *target,
 			    int *spec_id, bool *is_new)
 {
-	void *tmp;
+	long tmp;
+	void *new_ids;
 	int err;
 
 	/* check if we already allocated spec ID for this spec string */
 	if (hashmap__find(specs_hash, target->spec_str, &tmp)) {
-		*spec_id = (long)tmp;
+		*spec_id = tmp;
 		*is_new = false;
 		return 0;
 	}
@@ -905,17 +901,17 @@ static int allocate_spec_id(struct usdt_manager *man, struct hashmap *specs_hash
 	/* otherwise it's a new ID that needs to be set up in specs map and
 	 * returned back to usdt_manager when USDT link is detached
 	 */
-	tmp = libbpf_reallocarray(link->spec_ids, link->spec_cnt + 1, sizeof(*link->spec_ids));
-	if (!tmp)
+	new_ids = libbpf_reallocarray(link->spec_ids, link->spec_cnt + 1, sizeof(*link->spec_ids));
+	if (!new_ids)
 		return -ENOMEM;
-	link->spec_ids = tmp;
+	link->spec_ids = new_ids;
 
 	/* get next free spec ID, giving preference to free list, if not empty */
 	if (man->free_spec_cnt) {
 		*spec_id = man->free_spec_ids[man->free_spec_cnt - 1];
 
 		/* cache spec ID for current spec string for future lookups */
-		err = hashmap__add(specs_hash, target->spec_str, (void *)(long)*spec_id);
+		err = hashmap__add(specs_hash, target->spec_str, *spec_id);
 		if (err)
 			 return err;
 
@@ -928,7 +924,7 @@ static int allocate_spec_id(struct usdt_manager *man, struct hashmap *specs_hash
 		*spec_id = man->next_free_spec_id;
 
 		/* cache spec ID for current spec string for future lookups */
-		err = hashmap__add(specs_hash, target->spec_str, (void *)(long)*spec_id);
+		err = hashmap__add(specs_hash, target->spec_str, *spec_id);
 		if (err)
 			 return err;
 
@@ -1225,26 +1221,32 @@ static int calc_pt_regs_off(const char *reg_name)
 
 static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
 {
-	char *reg_name = NULL;
+	char reg_name[16];
 	int arg_sz, len, reg_off;
 	long off;
 
-	if (sscanf(arg_str, " %d @ %ld ( %%%m[^)] ) %n", &arg_sz, &off, &reg_name, &len) == 3) {
+	if (sscanf(arg_str, " %d @ %ld ( %%%15[^)] ) %n", &arg_sz, &off, reg_name, &len) == 3) {
 		/* Memory dereference case, e.g., -4@-20(%rbp) */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = off;
 		reg_off = calc_pt_regs_off(reg_name);
-		free(reg_name);
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
-	} else if (sscanf(arg_str, " %d @ %%%ms %n", &arg_sz, &reg_name, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ ( %%%15[^)] ) %n", &arg_sz, reg_name, &len) == 2) {
+		/* Memory dereference case without offset, e.g., 8@(%rsp) */
+		arg->arg_type = USDT_ARG_REG_DEREF;
+		arg->val_off = 0;
+		reg_off = calc_pt_regs_off(reg_name);
+		if (reg_off < 0)
+			return reg_off;
+		arg->reg_off = reg_off;
+	} else if (sscanf(arg_str, " %d @ %%%15s %n", &arg_sz, reg_name, &len) == 2) {
 		/* Register read case, e.g., -4@%eax */
 		arg->arg_type = USDT_ARG_REG;
 		arg->val_off = 0;
 
 		reg_off = calc_pt_regs_off(reg_name);
-		free(reg_name);
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
@@ -1348,25 +1350,23 @@ static int calc_pt_regs_off(const char *reg_name)
 
 static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
 {
-	char *reg_name = NULL;
+	char reg_name[16];
 	int arg_sz, len, reg_off;
 	long off;
 
-	if (sscanf(arg_str, " %d @ \[ %m[a-z0-9], %ld ] %n", &arg_sz, &reg_name, &off, &len) == 3) {
+	if (sscanf(arg_str, " %d @ \[ %15[a-z0-9], %ld ] %n", &arg_sz, reg_name, &off, &len) == 3) {
 		/* Memory dereference case, e.g., -4@[sp, 96] */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = off;
 		reg_off = calc_pt_regs_off(reg_name);
-		free(reg_name);
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
-	} else if (sscanf(arg_str, " %d @ \[ %m[a-z0-9] ] %n", &arg_sz, &reg_name, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ \[ %15[a-z0-9] ] %n", &arg_sz, reg_name, &len) == 2) {
 		/* Memory dereference case, e.g., -4@[sp] */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = 0;
 		reg_off = calc_pt_regs_off(reg_name);
-		free(reg_name);
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
@@ -1375,12 +1375,11 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		arg->arg_type = USDT_ARG_CONST;
 		arg->val_off = off;
 		arg->reg_off = 0;
-	} else if (sscanf(arg_str, " %d @ %m[a-z0-9] %n", &arg_sz, &reg_name, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", &arg_sz, reg_name, &len) == 2) {
 		/* Register read case, e.g., -8@x4 */
 		arg->arg_type = USDT_ARG_REG;
 		arg->val_off = 0;
 		reg_off = calc_pt_regs_off(reg_name);
-		free(reg_name);
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
@@ -1459,16 +1458,15 @@ static int calc_pt_regs_off(const char *reg_name)
 
 static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
 {
-	char *reg_name = NULL;
+	char reg_name[16];
 	int arg_sz, len, reg_off;
 	long off;
 
-	if (sscanf(arg_str, " %d @ %ld ( %m[a-z0-9] ) %n", &arg_sz, &off, &reg_name, &len) == 3) {
+	if (sscanf(arg_str, " %d @ %ld ( %15[a-z0-9] ) %n", &arg_sz, &off, reg_name, &len) == 3) {
 		/* Memory dereference case, e.g., -8@-88(s0) */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = off;
 		reg_off = calc_pt_regs_off(reg_name);
-		free(reg_name);
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
@@ -1477,12 +1475,11 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		arg->arg_type = USDT_ARG_CONST;
 		arg->val_off = off;
 		arg->reg_off = 0;
-	} else if (sscanf(arg_str, " %d @ %m[a-z0-9] %n", &arg_sz, &reg_name, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", &arg_sz, reg_name, &len) == 2) {
 		/* Register read case, e.g., -8@a1 */
 		arg->arg_type = USDT_ARG_REG;
 		arg->val_off = 0;
 		reg_off = calc_pt_regs_off(reg_name);
-		free(reg_name);
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;

travis-ci

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