libbpf 升级到1.1版本

Signed-off-by: wenlong_12 <wenlong12@huawei.com>

Signed-off-by: wenlong_12 <wenlong12@huawei.com>

.readthedocs.yaml

@@ -10,6 +10,11 @@ sphinx:
   builder: html
   configuration: docs/conf.py
 
+formats:
+  - htmlzip
+  - pdf
+  - epub
+
 # Optionally set the version of Python and requirements required to build your docs
 python:
    version: 3.7

BPF-CHECKPOINT-COMMIT

@@ -1 +1 @@
-fe68195daf34d5dddacd3f93dd3eafc4beca3a0e
+54c3f1a81421f85e60ae2eaae7be3727a09916ee

BUILD.gn

@@ -86,8 +86,6 @@ ohos_shared_library("libbpf") {
     "./src/str_error.h",
     "./src/strset.c",
     "./src/strset.h",
-    "./src/xsk.c",
-    "./src/xsk.h",
   ]
   configs = [ ":libbpf_config" ]
   public_configs = [ ":libbpf_public_config" ]

CHECKPOINT-COMMIT

@@ -1 +1 @@
-dc37dc617fabfb1c3a16d49f5d8cc20e9e3608ca
+7b43df6c6ec38c9097420902a1c8165c4b25bf70

LICENSE.BSD-2-Clause

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

README.md

@@ -1,17 +1,33 @@
-This is a mirror of [bpf-next Linux source
-tree](https://kernel.googlesource.com/pub/scm/linux/kernel/git/bpf/bpf-next)'s
-`tools/lib/bpf` directory plus its supporting header files.
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="assets/libbpf-logo-sideways-darkbg.png" width="40%">
+  <img src="assets/libbpf-logo-sideways.png" width="40%">
+</picture>
 
-All the gory details of syncing can be found in `scripts/sync-kernel.sh`
-script.
+libbpf
+[![Github Actions Builds & Tests](https://github.com/libbpf/libbpf/actions/workflows/test.yml/badge.svg)](https://github.com/libbpf/libbpf/actions/workflows/test.yml)
+[![Coverity](https://img.shields.io/coverity/scan/18195.svg)](https://scan.coverity.com/projects/libbpf)
+[![CodeQL](https://github.com/libbpf/libbpf/workflows/CodeQL/badge.svg?branch=master)](https://github.com/libbpf/libbpf/actions?query=workflow%3ACodeQL+branch%3Amaster)
+[![OSS-Fuzz Status](https://oss-fuzz-build-logs.storage.googleapis.com/badges/libbpf.svg)](https://oss-fuzz-build-logs.storage.googleapis.com/index.html#libbpf)
+[![Read the Docs](https://readthedocs.org/projects/libbpf/badge/?version=latest)](https://libbpf.readthedocs.io/en/latest/)
+======
 
-Some header files in this repo (`include/linux/*.h`) are reduced versions of
-their counterpart files at
-[bpf-next](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/)'s
-`tools/include/linux/*.h` to make compilation successful.
+**This is the official home of the libbpf library.**
 
-BPF/libbpf usage and questions
-==============================
+*Please use this Github repository for building and packaging libbpf
+and when using it in your projects through Git submodule.*
+
+Libbpf *authoritative source code* is developed as part of [bpf-next Linux source
+tree](https://kernel.googlesource.com/pub/scm/linux/kernel/git/bpf/bpf-next) under
+`tools/lib/bpf` subdirectory and is periodically synced to Github. As such, all the
+libbpf changes should be sent to [BPF mailing list](http://vger.kernel.org/vger-lists.html#bpf),
+please don't open PRs here unless you are changing Github-specific parts of libbpf
+(e.g., Github-specific Makefile).
+
+Libbpf and general BPF usage questions
+======================================
+
+Libbpf documentation can be found [here](https://libbpf.readthedocs.io/en/latest/api.html).
+It's an ongoing effort and has ways to go, but please take a look and consider contributing as well.
 
 Please check out [libbpf-bootstrap](https://github.com/libbpf/libbpf-bootstrap)
 and [the companion blog post](https://nakryiko.com/posts/libbpf-bootstrap/) for
@@ -36,12 +52,8 @@ to help you with whatever issue you have. This repository's PRs and issues
 should be opened only for dealing with issues pertaining to specific way this
 libbpf mirror repo is set up and organized.
 
-Build
-[![Github Actions Builds & Tests](https://github.com/libbpf/libbpf/actions/workflows/test.yml/badge.svg)](https://github.com/libbpf/libbpf/actions/workflows/test.yml)
-[![Total alerts](https://img.shields.io/lgtm/alerts/g/libbpf/libbpf.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/libbpf/libbpf/alerts/)
-[![Coverity](https://img.shields.io/coverity/scan/18195.svg)](https://scan.coverity.com/projects/libbpf)
-[![OSS-Fuzz Status](https://oss-fuzz-build-logs.storage.googleapis.com/badges/libbpf.svg)](https://oss-fuzz-build-logs.storage.googleapis.com/index.html#libbpf)
-=====
+Building libbpf
+===============
 libelf is an internal dependency of libbpf and thus it is required to link
 against and must be installed on the system for applications to work.
 pkg-config is used by default to find libelf, and the program called can be
@@ -73,34 +85,6 @@ $ cd src
 $ PKG_CONFIG_PATH=/build/root/lib64/pkgconfig DESTDIR=/build/root make install
 ```
 
-Distributions
-=============
-
-Distributions packaging libbpf from this mirror:
-  - [Fedora](https://src.fedoraproject.org/rpms/libbpf)
-  - [Gentoo](https://packages.gentoo.org/packages/dev-libs/libbpf)
-  - [Debian](https://packages.debian.org/source/sid/libbpf)
-  - [Arch](https://www.archlinux.org/packages/extra/x86_64/libbpf/)
-  - [Ubuntu](https://packages.ubuntu.com/source/impish/libbpf)
-  - [Alpine](https://pkgs.alpinelinux.org/packages?name=libbpf)
-
-Benefits of packaging from the mirror over packaging from kernel sources:
-  - Consistent versioning across distributions.
-  - No ties to any specific kernel, transparent handling of older kernels.
-    Libbpf is designed to be kernel-agnostic and work across multitude of
-    kernel versions. It has built-in mechanisms to gracefully handle older
-    kernels, that are missing some of the features, by working around or
-    gracefully degrading functionality. Thus libbpf is not tied to a specific
-    kernel version and can/should be packaged and versioned independently.
-  - Continuous integration testing via
-    [TravisCI](https://travis-ci.org/libbpf/libbpf).
-  - Static code analysis via [LGTM](https://lgtm.com/projects/g/libbpf/libbpf)
-    and [Coverity](https://scan.coverity.com/projects/libbpf).
-
-Package dependencies of libbpf, package names may vary across distros:
-  - zlib
-  - libelf
-
 BPF CO-RE (Compile Once – Run Everywhere)
 =========================================
 
@@ -154,6 +138,48 @@ use it:
   converting some more to both contribute to the BPF community and gain some
   more experience with it.
 
+Distributions
+=============
+
+Distributions packaging libbpf from this mirror:
+  - [Fedora](https://src.fedoraproject.org/rpms/libbpf)
+  - [Gentoo](https://packages.gentoo.org/packages/dev-libs/libbpf)
+  - [Debian](https://packages.debian.org/source/sid/libbpf)
+  - [Arch](https://archlinux.org/packages/core/x86_64/libbpf/)
+  - [Ubuntu](https://packages.ubuntu.com/source/impish/libbpf)
+  - [Alpine](https://pkgs.alpinelinux.org/packages?name=libbpf)
+
+Benefits of packaging from the mirror over packaging from kernel sources:
+  - Consistent versioning across distributions.
+  - No ties to any specific kernel, transparent handling of older kernels.
+    Libbpf is designed to be kernel-agnostic and work across multitude of
+    kernel versions. It has built-in mechanisms to gracefully handle older
+    kernels, that are missing some of the features, by working around or
+    gracefully degrading functionality. Thus libbpf is not tied to a specific
+    kernel version and can/should be packaged and versioned independently.
+  - Continuous integration testing via
+    [GitHub Actions](https://github.com/libbpf/libbpf/actions).
+  - Static code analysis via [LGTM](https://lgtm.com/projects/g/libbpf/libbpf)
+    and [Coverity](https://scan.coverity.com/projects/libbpf).
+
+Package dependencies of libbpf, package names may vary across distros:
+  - zlib
+  - libelf
+
+[![libbpf distro packaging status](https://repology.org/badge/vertical-allrepos/libbpf.svg)](https://repology.org/project/libbpf/versions)
+
+
+bpf-next to Github sync
+=======================
+
+All the gory details of syncing can be found in `scripts/sync-kernel.sh`
+script.
+
+Some header files in this repo (`include/linux/*.h`) are reduced versions of
+their counterpart files at
+[bpf-next](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/)'s
+`tools/include/linux/*.h` to make compilation successful.
+
 License
 =======
 

ci/managers/debian.sh

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

ci/managers/test_compile.sh

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

ci/managers/ubuntu.sh

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

ci/vmtest/configs/ALLOWLIST-5.5.0

@@ -1,4 +1,4 @@
-attach_probe
+# attach_probe
 autoload
 bpf_verif_scale
 cgroup_attach_autodetach
@@ -10,7 +10,6 @@ core_reloc
 core_retro
 cpu_mask
 endian
-fexit_stress
 get_branch_snapshot
 get_stackid_cannot_attach
 global_data
@@ -43,13 +42,13 @@ spinlock
 stacktrace_map
 stacktrace_map_raw_tp
 static_linked
-subprogs
 task_fd_query_rawtp
 task_fd_query_tp
 tc_bpf
 tcp_estats
 tcp_rtt
 tp_attach_query
+usdt/urand_pid_attach
 xdp
 xdp_info
 xdp_noinline

ci/vmtest/configs/DENYLIST-5.5.0

@@ -1,5 +1,5 @@
 # This file is not used and is there for historic purposes only.
-# See WHITELIST-5.5.0 instead.
+# See ALLOWLIST-5.5.0 instead.
 
 # PERMANENTLY DISABLED
 align			# verifier output format changed
@@ -71,6 +71,7 @@ sk_lookup		# v5.9+
 sk_storage_tracing	# missing bpf_sk_storage_get() helper
 skb_ctx			# ctx_{size, }_{in, out} in BPF_PROG_TEST_RUN is missing
 skb_helpers		# helpers added in 5.8+
+skeleton		# creates too big ARRAY map
 snprintf		# v5.13+
 snprintf_btf		# v5.10+
 sock_fields		# v5.10+

ci/vmtest/configs/DENYLIST-latest.s390x

@@ -0,0 +1,3 @@
+# TEMPORARY
+usdt/basic                               # failing verifier due to bounds check after LLVM update
+usdt/multispec                           # same as above

ci/vmtest/helpers.sh

@@ -1,16 +1,11 @@
+# shellcheck shell=bash
+
 # $1 - start or end
 # $2 - fold identifier, no spaces
 # $3 - fold section description
-travis_fold() {
+foldable() {
   local YELLOW='\033[1;33m'
   local NOCOLOR='\033[0m'
-  if [ -z ${GITHUB_WORKFLOW+x} ]; then
-    echo travis_fold:$1:$2
-    if [ ! -z "${3:-}" ]; then
-      echo -e "${YELLOW}$3${NOCOLOR}"
-    fi
-    echo
-  else
   if [ $1 = "start" ]; then
     line="::group::$2"
     if [ ! -z "${3:-}" ]; then
@@ -20,7 +15,6 @@ travis_fold() {
     line="::endgroup::"
   fi
   echo -e "$line"
-  fi
 }
 
 __print() {

ci/vmtest/run_selftests.sh

@@ -0,0 +1,87 @@
+#!/bin/bash
+
+set -euo pipefail
+
+source $(cd $(dirname $0) && pwd)/helpers.sh
+
+ARCH=$(uname -m)
+
+STATUS_FILE=/exitstatus
+
+read_lists() {
+	(for path in "$@"; do
+		if [[ -s "$path" ]]; then
+			cat "$path"
+		fi;
+	done) | cut -d'#' -f1 | tr -s ' \t\n' ','
+}
+
+test_progs() {
+	if [[ "${KERNEL}" != '4.9.0' ]]; then
+		foldable start test_progs "Testing test_progs"
+		# "&& true" does not change the return code (it is not executed
+		# if the Python script fails), but it prevents exiting on a
+		# failure due to the "set -e".
+		./test_progs ${DENYLIST:+-d$DENYLIST} ${ALLOWLIST:+-a$ALLOWLIST} && true
+		echo "test_progs:$?" >> "${STATUS_FILE}"
+		foldable end test_progs
+	fi
+}
+
+test_progs_no_alu32() {
+	foldable start test_progs-no_alu32 "Testing test_progs-no_alu32"
+	./test_progs-no_alu32 ${DENYLIST:+-d$DENYLIST} ${ALLOWLIST:+-a$ALLOWLIST} && true
+	echo "test_progs-no_alu32:$?" >> "${STATUS_FILE}"
+	foldable end test_progs-no_alu32
+}
+
+test_maps() {
+	if [[ "${KERNEL}" == 'latest' ]]; then
+		foldable start test_maps "Testing test_maps"
+		./test_maps && true
+		echo "test_maps:$?" >> "${STATUS_FILE}"
+		foldable end test_maps
+	fi
+}
+
+test_verifier() {
+	if [[ "${KERNEL}" == 'latest' ]]; then
+		foldable start test_verifier "Testing test_verifier"
+		./test_verifier && true
+		echo "test_verifier:$?" >> "${STATUS_FILE}"
+		foldable end test_verifier
+	fi
+}
+
+foldable end vm_init
+
+configs_path=/${PROJECT_NAME}/selftests/bpf
+local_configs_path=${PROJECT_NAME}/vmtest/configs
+DENYLIST=$(read_lists \
+	"$configs_path/DENYLIST" \
+	"$configs_path/DENYLIST.${ARCH}" \
+	"$local_configs_path/DENYLIST-${KERNEL}" \
+	"$local_configs_path/DENYLIST-${KERNEL}.${ARCH}" \
+)
+ALLOWLIST=$(read_lists \
+	"$configs_path/ALLOWLIST" \
+	"$configs_path/ALLOWLIST.${ARCH}" \
+	"$local_configs_path/ALLOWLIST-${KERNEL}" \
+	"$local_configs_path/ALLOWLIST-${KERNEL}.${ARCH}" \
+)
+
+echo "DENYLIST: ${DENYLIST}"
+echo "ALLOWLIST: ${ALLOWLIST}"
+
+cd ${PROJECT_NAME}/selftests/bpf
+
+if [ $# -eq 0 ]; then
+	test_progs
+	test_progs_no_alu32
+	# test_maps
+	test_verifier
+else
+	for test_name in "$@"; do
+		"${test_name}"
+	done
+fi

docs/index.rst

@@ -1,19 +1,21 @@
 .. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 
+.. _libbpf:
+
 libbpf
 ======
 
 .. toctree::
    :maxdepth: 1
 
+   API Documentation <https://libbpf.readthedocs.io/en/latest/api.html>
+   program_types
    libbpf_naming_convention
    libbpf_build
 
 This is documentation for libbpf, a userspace library for loading and
 interacting with bpf programs.
 
-For API documentation see the `versioned API documentation site <https://libbpf.readthedocs.io/en/latest/api.html>`_.
-
 All general BPF questions, including kernel functionality, libbpf APIs and
 their application, should be sent to bpf@vger.kernel.org mailing list.
 You can `subscribe <http://vger.kernel.org/vger-lists.html#bpf>`_ to the

docs/libbpf_naming_convention.rst

@@ -9,8 +9,8 @@ described here. It's recommended to follow these conventions whenever a
 new function or type is added to keep libbpf API clean and consistent.
 
 All types and functions provided by libbpf API should have one of the
-following prefixes: ``bpf_``, ``btf_``, ``libbpf_``, ``xsk_``,
-``btf_dump_``, ``ring_buffer_``, ``perf_buffer_``.
+following prefixes: ``bpf_``, ``btf_``, ``libbpf_``, ``btf_dump_``,
+``ring_buffer_``, ``perf_buffer_``.
 
 System call wrappers
 --------------------
@@ -59,15 +59,6 @@ Auxiliary functions and types that don't fit well in any of categories
 described above should have ``libbpf_`` prefix, e.g.
 ``libbpf_get_error`` or ``libbpf_prog_type_by_name``.
 
-AF_XDP functions
--------------------
-
-AF_XDP functions should have an ``xsk_`` prefix, e.g.
-``xsk_umem__get_data`` or ``xsk_umem__create``. The interface consists
-of both low-level ring access functions and high-level configuration
-functions. These can be mixed and matched. Note that these functions
-are not reentrant for performance reasons.
-
 ABI
 ---
 

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/btf.h

@@ -33,13 +33,13 @@ struct btf_type {
 	/* "info" bits arrangement
 	 * bits  0-15: vlen (e.g. # of struct's members)
 	 * bits 16-23: unused
-	 * bits 24-27: kind (e.g. int, ptr, array...etc)
-	 * bits 28-30: unused
+	 * bits 24-28: kind (e.g. int, ptr, array...etc)
+	 * bits 29-30: unused
 	 * bit     31: kind_flag, currently used by
-	 *             struct, union and fwd
+	 *             struct, union, enum, fwd and enum64
 	 */
 	__u32 info;
-	/* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC.
+	/* "size" is used by INT, ENUM, STRUCT, UNION, DATASEC and ENUM64.
 	 * "size" tells the size of the type it is describing.
 	 *
 	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
@@ -63,7 +63,7 @@ enum {
 	BTF_KIND_ARRAY		= 3,	/* Array	*/
 	BTF_KIND_STRUCT		= 4,	/* Struct	*/
 	BTF_KIND_UNION		= 5,	/* Union	*/
-	BTF_KIND_ENUM		= 6,	/* Enumeration	*/
+	BTF_KIND_ENUM		= 6,	/* Enumeration up to 32-bit values */
 	BTF_KIND_FWD		= 7,	/* Forward	*/
 	BTF_KIND_TYPEDEF	= 8,	/* Typedef	*/
 	BTF_KIND_VOLATILE	= 9,	/* Volatile	*/
@@ -76,6 +76,7 @@ enum {
 	BTF_KIND_FLOAT		= 16,	/* Floating point	*/
 	BTF_KIND_DECL_TAG	= 17,	/* Decl Tag */
 	BTF_KIND_TYPE_TAG	= 18,	/* Type Tag */
+	BTF_KIND_ENUM64		= 19,	/* Enumeration up to 64-bit values */
 
 	NR_BTF_KINDS,
 	BTF_KIND_MAX		= NR_BTF_KINDS - 1,
@@ -186,4 +187,14 @@ struct btf_decl_tag {
        __s32   component_idx;
 };
 
+/* BTF_KIND_ENUM64 is followed by multiple "struct btf_enum64".
+ * The exact number of btf_enum64 is stored in the vlen (of the
+ * info in "struct btf_type").
+ */
+struct btf_enum64 {
+	__u32	name_off;
+	__u32	val_lo32;
+	__u32	val_hi32;
+};
+
 #endif /* _UAPI__LINUX_BTF_H__ */

include/uapi/linux/fcntl.h

@@ -0,0 +1,114 @@
+/* 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

@@ -348,6 +348,8 @@ enum {
 	IFLA_PARENT_DEV_NAME,
 	IFLA_PARENT_DEV_BUS_NAME,
 	IFLA_GRO_MAX_SIZE,
+	IFLA_TSO_MAX_SIZE,
+	IFLA_TSO_MAX_SEGS,
 
 	__IFLA_MAX
 };
@@ -671,6 +673,7 @@ enum {
 	IFLA_XFRM_UNSPEC,
 	IFLA_XFRM_LINK,
 	IFLA_XFRM_IF_ID,
+	IFLA_XFRM_COLLECT_METADATA,
 	__IFLA_XFRM_MAX
 };
 
@@ -860,6 +863,7 @@ enum {
 	IFLA_BOND_PEER_NOTIF_DELAY,
 	IFLA_BOND_AD_LACP_ACTIVE,
 	IFLA_BOND_MISSED_MAX,
+	IFLA_BOND_NS_IP6_TARGET,
 	__IFLA_BOND_MAX,
 };
 
@@ -887,6 +891,7 @@ enum {
 	IFLA_BOND_SLAVE_AD_AGGREGATOR_ID,
 	IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE,
 	IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE,
+	IFLA_BOND_SLAVE_PRIO,
 	__IFLA_BOND_SLAVE_MAX,
 };
 

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,
 };
 
@@ -251,9 +253,50 @@ enum {
 	PERF_BR_SYSRET		= 8,	/* syscall return */
 	PERF_BR_COND_CALL	= 9,	/* conditional function call */
 	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|\
@@ -299,6 +342,7 @@ enum {
  *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
  *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
  *	  { u64		id;           } && PERF_FORMAT_ID
+ *	  { u64		lost;         } && PERF_FORMAT_LOST
  *	} && !PERF_FORMAT_GROUP
  *
  *	{ u64		nr;
@@ -306,6 +350,7 @@ enum {
  *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
  *	  { u64		value;
  *	    { u64	id;           } && PERF_FORMAT_ID
+ *	    { u64	lost;         } && PERF_FORMAT_LOST
  *	  }		cntr[nr];
  *	} && PERF_FORMAT_GROUP
  * };
@@ -315,8 +360,9 @@ enum perf_event_read_format {
 	PERF_FORMAT_TOTAL_TIME_RUNNING		= 1U << 1,
 	PERF_FORMAT_ID				= 1U << 2,
 	PERF_FORMAT_GROUP			= 1U << 3,
+	PERF_FORMAT_LOST			= 1U << 4,
 
-	PERF_FORMAT_MAX = 1U << 4,		/* non-ABI */
+	PERF_FORMAT_MAX = 1U << 5,		/* non-ABI */
 };
 
 #define PERF_ATTR_SIZE_VER0	64	/* sizeof first published struct */
@@ -465,6 +511,8 @@ struct perf_event_attr {
 	/*
 	 * User provided data if sigtrap=1, passed back to user via
 	 * siginfo_t::si_perf_data, e.g. to permit user to identify the event.
+	 * Note, siginfo_t::si_perf_data is long-sized, and sig_data will be
+	 * truncated accordingly on 32 bit architectures.
 	 */
 	__u64	sig_data;
 };
@@ -487,7 +535,7 @@ struct perf_event_query_bpf {
 	/*
 	 * User provided buffer to store program ids
 	 */
-	__u32	ids[0];
+	__u32	ids[];
 };
 
 /*
@@ -1288,7 +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 */
@@ -1306,7 +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 */
@@ -1356,6 +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;
@@ -1366,7 +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 {

include/uapi/linux/pkt_cls.h

@@ -180,7 +180,7 @@ struct tc_u32_sel {
 
 	short			hoff;
 	__be32			hmask;
-	struct tc_u32_key	keys[0];
+	struct tc_u32_key	keys[];
 };
 
 struct tc_u32_mark {
@@ -192,7 +192,7 @@ struct tc_u32_mark {
 struct tc_u32_pcnt {
 	__u64 rcnt;
 	__u64 rhit;
-	__u64 kcnts[0];
+	__u64 kcnts[];
 };
 
 /* Flags */

scripts/build-fuzzers.sh

@@ -17,6 +17,24 @@ mkdir -p "$OUT"
 
 export LIB_FUZZING_ENGINE=${LIB_FUZZING_ENGINE:--fsanitize=fuzzer}
 
+# libelf is compiled with _FORTIFY_SOURCE by default and it
+# isn't compatible with MSan. It was borrowed
+# from https://github.com/google/oss-fuzz/pull/7422
+if [[ "$SANITIZER" == memory ]]; then
+    CFLAGS+=" -U_FORTIFY_SOURCE"
+    CXXFLAGS+=" -U_FORTIFY_SOURCE"
+fi
+
+# The alignment check is turned off by default on OSS-Fuzz/CFLite so it should be
+# turned on explicitly there. It was borrowed from
+# https://github.com/google/oss-fuzz/pull/7092
+if [[ "$SANITIZER" == undefined ]]; then
+    additional_ubsan_checks=alignment
+    UBSAN_FLAGS="-fsanitize=$additional_ubsan_checks -fno-sanitize-recover=$additional_ubsan_checks"
+    CFLAGS+=" $UBSAN_FLAGS"
+    CXXFLAGS+=" $UBSAN_FLAGS"
+fi
+
 # Ideally libbelf should be built using release tarballs available
 # at https://sourceware.org/elfutils/ftp/. Unfortunately sometimes they
 # fail to compile (for example, elfutils-0.185 fails to compile with LDFLAGS enabled
@@ -26,7 +44,7 @@ rm -rf elfutils
 git clone git://sourceware.org/git/elfutils.git
 (
 cd elfutils
-git checkout 983e86fd89e8bf02f2d27ba5dce5bf078af4ceda
+git checkout e9f3045caa5c4498f371383e5519151942d48b6d
 git log --oneline -1
 
 # ASan isn't compatible with -Wl,--no-undefined: https://github.com/google/sanitizers/issues/380
@@ -36,6 +54,11 @@ find -name Makefile.am | xargs sed -i 's/,--no-undefined//'
 # https://clang.llvm.org/docs/AddressSanitizer.html#usage
 sed -i 's/^\(ZDEFS_LDFLAGS=\).*/\1/' configure.ac
 
+if [[ "$SANITIZER" == undefined ]]; then
+    # That's basicaly what --enable-sanitize-undefined does to turn off unaligned access
+    # elfutils heavily relies on on i386/x86_64 but without changing compiler flags along the way
+    sed -i 's/\(check_undefined_val\)=[0-9]/\1=1/' configure.ac
+fi
 
 autoreconf -i -f
 if ! ./configure --enable-maintainer-mode --disable-debuginfod --disable-libdebuginfod \

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

@@ -8,10 +8,24 @@ else
 	msg = @printf '  %-8s %s%s\n' "$(1)" "$(2)" "$(if $(3), $(3))";
 endif
 
-LIBBPF_VERSION := $(shell \
-	grep -oE '^LIBBPF_([0-9.]+)' libbpf.map | \
-	sort -rV | head -n1 | cut -d'_' -f2)
-LIBBPF_MAJOR_VERSION := $(firstword $(subst ., ,$(LIBBPF_VERSION)))
+LIBBPF_MAJOR_VERSION := 1
+LIBBPF_MINOR_VERSION := 1
+LIBBPF_PATCH_VERSION := 0
+LIBBPF_VERSION := $(LIBBPF_MAJOR_VERSION).$(LIBBPF_MINOR_VERSION).$(LIBBPF_PATCH_VERSION)
+LIBBPF_MAJMIN_VERSION := $(LIBBPF_MAJOR_VERSION).$(LIBBPF_MINOR_VERSION).0
+LIBBPF_MAP_VERSION := $(shell grep -oE '^LIBBPF_([0-9.]+)' libbpf.map | sort -rV | head -n1 | cut -d'_' -f2)
+ifneq ($(LIBBPF_MAJMIN_VERSION), $(LIBBPF_MAP_VERSION))
+$(error Libbpf release ($(LIBBPF_VERSION)) and map ($(LIBBPF_MAP_VERSION)) versions are out of sync!)
+endif
+
+define allow-override
+  $(if $(or $(findstring environment,$(origin $(1))),\
+            $(findstring command line,$(origin $(1)))),,\
+    $(eval $(1) = $(2)))
+endef
+
+$(call allow-override,CC,$(CROSS_COMPILE)cc)
+$(call allow-override,LD,$(CROSS_COMPILE)ld)
 
 TOPDIR = ..
 
@@ -21,8 +35,9 @@ ALL_CFLAGS := $(INCLUDES)
 SHARED_CFLAGS += -fPIC -fvisibility=hidden -DSHARED
 
 CFLAGS ?= -g -O2 -Werror -Wall -std=gnu89
-ALL_CFLAGS += $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
-ALL_LDFLAGS += $(LDFLAGS)
+ALL_CFLAGS += $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 $(EXTRA_CFLAGS)
+ALL_LDFLAGS += $(LDFLAGS) $(EXTRA_LDFLAGS)
+
 ifdef NO_PKG_CONFIG
 	ALL_LDFLAGS += -lelf -lz
 else
@@ -35,9 +50,9 @@ OBJDIR ?= .
 SHARED_OBJDIR := $(OBJDIR)/sharedobjs
 STATIC_OBJDIR := $(OBJDIR)/staticobjs
 OBJS := bpf.o btf.o libbpf.o libbpf_errno.o netlink.o \
-	nlattr.o str_error.o libbpf_probes.o bpf_prog_linfo.o xsk.o \
+	nlattr.o str_error.o libbpf_probes.o bpf_prog_linfo.o \
 	btf_dump.o hashmap.o ringbuf.o strset.o linker.o gen_loader.o \
-	relo_core.o
+	relo_core.o usdt.o
 SHARED_OBJS := $(addprefix $(SHARED_OBJDIR)/,$(OBJS))
 STATIC_OBJS := $(addprefix $(STATIC_OBJDIR)/,$(OBJS))
 
@@ -49,9 +64,10 @@ ifndef BUILD_STATIC_ONLY
 	VERSION_SCRIPT := libbpf.map
 endif
 
-HEADERS := bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h xsk.h \
+HEADERS := bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h \
 	   bpf_helpers.h bpf_helper_defs.h bpf_tracing.h \
-	   bpf_endian.h bpf_core_read.h skel_internal.h libbpf_version.h
+	   bpf_endian.h bpf_core_read.h skel_internal.h libbpf_version.h \
+	   usdt.bpf.h
 UAPI_HEADERS := $(addprefix $(TOPDIR)/include/uapi/linux/,\
 			    bpf.h bpf_common.h btf.h)
 
@@ -61,7 +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
@@ -99,7 +116,7 @@ $(OBJDIR)/libbpf.so.$(LIBBPF_VERSION): $(SHARED_OBJS)
 		  -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \
 		  $^ $(ALL_LDFLAGS) -o $@
 
-$(OBJDIR)/libbpf.pc:
+$(OBJDIR)/libbpf.pc: force
 	$(Q)sed -e "s|@PREFIX@|$(PREFIX)|" \
 		-e "s|@LIBDIR@|$(LIBDIR_PC)|" \
 		-e "s|@VERSION@|$(LIBBPF_VERSION)|" \
@@ -152,7 +169,7 @@ clean:
 	$(call msg,CLEAN)
 	$(Q)rm -rf *.o *.a *.so *.so.* *.pc $(SHARED_OBJDIR) $(STATIC_OBJDIR)
 
-.PHONY: cscope tags
+.PHONY: cscope tags force
 cscope:
 	$(call msg,CSCOPE)
 	$(Q)ls *.c *.h > cscope.files
@@ -162,3 +179,5 @@ tags:
 	$(call msg,CTAGS)
 	$(Q)rm -f TAGS tags
 	$(Q)ls *.c *.h | xargs $(TAGS_PROG) -a
+
+force:

src/bpf.h

@@ -61,48 +61,6 @@ LIBBPF_API int bpf_map_create(enum bpf_map_type map_type,
 			      __u32 max_entries,
 			      const struct bpf_map_create_opts *opts);
 
-struct bpf_create_map_attr {
-	const char *name;
-	enum bpf_map_type map_type;
-	__u32 map_flags;
-	__u32 key_size;
-	__u32 value_size;
-	__u32 max_entries;
-	__u32 numa_node;
-	__u32 btf_fd;
-	__u32 btf_key_type_id;
-	__u32 btf_value_type_id;
-	__u32 map_ifindex;
-	union {
-		__u32 inner_map_fd;
-		__u32 btf_vmlinux_value_type_id;
-	};
-};
-
-LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
-LIBBPF_API int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr);
-LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
-LIBBPF_API int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
-				   int key_size, int value_size,
-				   int max_entries, __u32 map_flags, int node);
-LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
-LIBBPF_API int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
-				   int key_size, int value_size,
-				   int max_entries, __u32 map_flags);
-LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
-LIBBPF_API int bpf_create_map(enum bpf_map_type map_type, int key_size,
-			      int value_size, int max_entries, __u32 map_flags);
-LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
-LIBBPF_API int bpf_create_map_in_map_node(enum bpf_map_type map_type,
-					  const char *name, int key_size,
-					  int inner_map_fd, int max_entries,
-					  __u32 map_flags, int node);
-LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
-LIBBPF_API int bpf_create_map_in_map(enum bpf_map_type map_type,
-				     const char *name, int key_size,
-				     int inner_map_fd, int max_entries,
-				     __u32 map_flags);
-
 struct bpf_prog_load_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */
 
@@ -145,54 +103,6 @@ LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type,
 			     const char *prog_name, const char *license,
 			     const struct bpf_insn *insns, size_t insn_cnt,
 			     const struct bpf_prog_load_opts *opts);
-/* this "specialization" should go away in libbpf 1.0 */
-LIBBPF_API int bpf_prog_load_v0_6_0(enum bpf_prog_type prog_type,
-				    const char *prog_name, const char *license,
-				    const struct bpf_insn *insns, size_t insn_cnt,
-				    const struct bpf_prog_load_opts *opts);
-
-/* This is an elaborate way to not conflict with deprecated bpf_prog_load()
- * API, defined in libbpf.h. Once we hit libbpf 1.0, all this will be gone.
- * With this approach, if someone is calling bpf_prog_load() with
- * 4 arguments, they will use the deprecated API, which keeps backwards
- * compatibility (both source code and binary). If bpf_prog_load() is called
- * with 6 arguments, though, it gets redirected to __bpf_prog_load.
- * So looking forward to libbpf 1.0 when this hack will be gone and
- * __bpf_prog_load() will be called just bpf_prog_load().
- */
-#ifndef bpf_prog_load
-#define bpf_prog_load(...) ___libbpf_overload(___bpf_prog_load, __VA_ARGS__)
-#define ___bpf_prog_load4(file, type, pobj, prog_fd) \
-	bpf_prog_load_deprecated(file, type, pobj, prog_fd)
-#define ___bpf_prog_load6(prog_type, prog_name, license, insns, insn_cnt, opts) \
-	bpf_prog_load(prog_type, prog_name, license, insns, insn_cnt, opts)
-#endif /* bpf_prog_load */
-
-struct bpf_load_program_attr {
-	enum bpf_prog_type prog_type;
-	enum bpf_attach_type expected_attach_type;
-	const char *name;
-	const struct bpf_insn *insns;
-	size_t insns_cnt;
-	const char *license;
-	union {
-		__u32 kern_version;
-		__u32 attach_prog_fd;
-	};
-	union {
-		__u32 prog_ifindex;
-		__u32 attach_btf_id;
-	};
-	__u32 prog_btf_fd;
-	__u32 func_info_rec_size;
-	const void *func_info;
-	__u32 func_info_cnt;
-	__u32 line_info_rec_size;
-	const void *line_info;
-	__u32 line_info_cnt;
-	__u32 log_level;
-	__u32 prog_flags;
-};
 
 /* Flags to direct loading requirements */
 #define MAPS_RELAX_COMPAT	0x01
@@ -200,22 +110,6 @@ struct bpf_load_program_attr {
 /* Recommended log buffer size */
 #define BPF_LOG_BUF_SIZE (UINT32_MAX >> 8) /* verifier maximum in kernels <= 5.1 */
 
-LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_load() instead")
-LIBBPF_API int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
-				      char *log_buf, size_t log_buf_sz);
-LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_load() instead")
-LIBBPF_API int bpf_load_program(enum bpf_prog_type type,
-				const struct bpf_insn *insns, size_t insns_cnt,
-				const char *license, __u32 kern_version,
-				char *log_buf, size_t log_buf_sz);
-LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_load() instead")
-LIBBPF_API int bpf_verify_program(enum bpf_prog_type type,
-				  const struct bpf_insn *insns,
-				  size_t insns_cnt, __u32 prog_flags,
-				  const char *license, __u32 kern_version,
-				  char *log_buf, size_t log_buf_sz,
-				  int log_level);
-
 struct bpf_btf_load_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */
 
@@ -229,10 +123,6 @@ struct bpf_btf_load_opts {
 LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size,
 			    const struct bpf_btf_load_opts *opts);
 
-LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_btf_load() instead")
-LIBBPF_API int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf,
-			    __u32 log_buf_size, bool do_log);
-
 LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value,
 				   __u64 flags);
 
@@ -244,6 +134,7 @@ LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key,
 LIBBPF_API int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key,
 						    void *value, __u64 flags);
 LIBBPF_API int bpf_map_delete_elem(int fd, const void *key);
+LIBBPF_API int bpf_map_delete_elem_flags(int fd, const void *key, __u64 flags);
 LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key);
 LIBBPF_API int bpf_map_freeze(int fd);
 
@@ -379,8 +270,19 @@ LIBBPF_API int bpf_map_update_batch(int fd, const void *keys, const void *values
 				    __u32 *count,
 				    const struct bpf_map_batch_opts *opts);
 
+struct bpf_obj_get_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+
+	__u32 file_flags;
+
+	size_t :0;
+};
+#define bpf_obj_get_opts__last_field file_flags
+
 LIBBPF_API int bpf_obj_pin(int fd, const char *pathname);
 LIBBPF_API int bpf_obj_get(const char *pathname);
+LIBBPF_API int bpf_obj_get_opts(const char *pathname,
+				const struct bpf_obj_get_opts *opts);
 
 struct bpf_prog_attach_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */
@@ -394,10 +296,6 @@ LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd,
 LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int attachable_fd,
 				     enum bpf_attach_type type,
 				     const struct bpf_prog_attach_opts *opts);
-LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_prog_attach_opts() instead")
-LIBBPF_API int bpf_prog_attach_xattr(int prog_fd, int attachable_fd,
-				     enum bpf_attach_type type,
-				     const struct bpf_prog_attach_opts *opts);
 LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
 LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd,
 				enum bpf_attach_type type);
@@ -413,10 +311,20 @@ struct bpf_link_create_opts {
 		struct {
 			__u64 bpf_cookie;
 		} perf_event;
+		struct {
+			__u32 flags;
+			__u32 cnt;
+			const char **syms;
+			const unsigned long *addrs;
+			const __u64 *cookies;
+		} kprobe_multi;
+		struct {
+			__u64 cookie;
+		} tracing;
 	};
 	size_t :0;
 };
-#define bpf_link_create_opts__last_field perf_event
+#define bpf_link_create_opts__last_field kprobe_multi.cookies
 
 LIBBPF_API int bpf_link_create(int prog_fd, int target_fd,
 			       enum bpf_attach_type attach_type,
@@ -453,36 +361,63 @@ struct bpf_prog_test_run_attr {
 			     * out: length of cxt_out */
 };
 
-LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_test_run_opts() instead")
-LIBBPF_API int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr);
-
-/*
- * bpf_prog_test_run does not check that data_out is large enough. Consider
- * using bpf_prog_test_run_opts instead.
- */
-LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_test_run_opts() instead")
-LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data,
-				 __u32 size, void *data_out, __u32 *size_out,
-				 __u32 *retval, __u32 *duration);
 LIBBPF_API int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id);
 LIBBPF_API int bpf_map_get_next_id(__u32 start_id, __u32 *next_id);
 LIBBPF_API int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id);
 LIBBPF_API int bpf_link_get_next_id(__u32 start_id, __u32 *next_id);
+
+struct bpf_get_fd_by_id_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u32 open_flags; /* permissions requested for the operation on fd */
+	size_t :0;
+};
+#define bpf_get_fd_by_id_opts__last_field open_flags
+
 LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_prog_get_fd_by_id_opts(__u32 id,
+				const struct bpf_get_fd_by_id_opts *opts);
 LIBBPF_API int bpf_map_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_map_get_fd_by_id_opts(__u32 id,
+				const struct bpf_get_fd_by_id_opts *opts);
 LIBBPF_API int bpf_btf_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_btf_get_fd_by_id_opts(__u32 id,
+				const struct bpf_get_fd_by_id_opts *opts);
 LIBBPF_API int bpf_link_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_link_get_fd_by_id_opts(__u32 id,
+				const struct bpf_get_fd_by_id_opts *opts);
 LIBBPF_API int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len);
+
+struct bpf_prog_query_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u32 query_flags;
+	__u32 attach_flags; /* output argument */
+	__u32 *prog_ids;
+	__u32 prog_cnt; /* input+output argument */
+	__u32 *prog_attach_flags;
+};
+#define bpf_prog_query_opts__last_field prog_attach_flags
+
+LIBBPF_API int bpf_prog_query_opts(int target_fd,
+				   enum bpf_attach_type type,
+				   struct bpf_prog_query_opts *opts);
 LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type,
 			      __u32 query_flags, __u32 *attach_flags,
 			      __u32 *prog_ids, __u32 *prog_cnt);
+
 LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd);
 LIBBPF_API int bpf_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 */
@@ -512,8 +447,9 @@ struct bpf_test_run_opts {
 	__u32 duration;      /* out: average per repetition in ns */
 	__u32 flags;
 	__u32 cpu;
+	__u32 batch_size;
 };
-#define bpf_test_run_opts__last_field cpu
+#define bpf_test_run_opts__last_field batch_size
 
 LIBBPF_API int bpf_prog_test_run_opts(int prog_fd,
 				      struct bpf_test_run_opts *opts);

src/bpf_core_read.h

@@ -29,6 +29,7 @@ enum bpf_type_id_kind {
 enum bpf_type_info_kind {
 	BPF_TYPE_EXISTS = 0,		/* type existence in target kernel */
 	BPF_TYPE_SIZE = 1,		/* type size in target kernel */
+	BPF_TYPE_MATCHES = 2,		/* type match in target kernel */
 };
 
 /* second argument to __builtin_preserve_enum_value() built-in */
@@ -110,21 +111,50 @@ enum bpf_enum_value_kind {
 	val;								      \
 })
 
+#define ___bpf_field_ref1(field)	(field)
+#define ___bpf_field_ref2(type, field)	(((typeof(type) *)0)->field)
+#define ___bpf_field_ref(args...)					    \
+	___bpf_apply(___bpf_field_ref, ___bpf_narg(args))(args)
+
 /*
  * Convenience macro to check that field actually exists in target kernel's.
  * Returns:
  *    1, if matching field is present in target kernel;
  *    0, if no matching field found.
+ *
+ * Supports two forms:
+ *   - field reference through variable access:
+ *     bpf_core_field_exists(p->my_field);
+ *   - field reference through type and field names:
+ *     bpf_core_field_exists(struct my_type, my_field).
  */
-#define bpf_core_field_exists(field)					    \
-	__builtin_preserve_field_info(field, BPF_FIELD_EXISTS)
+#define bpf_core_field_exists(field...)					    \
+	__builtin_preserve_field_info(___bpf_field_ref(field), BPF_FIELD_EXISTS)
 
 /*
  * Convenience macro to get the byte size of a field. Works for integers,
  * struct/unions, pointers, arrays, and enums.
+ *
+ * Supports two forms:
+ *   - field reference through variable access:
+ *     bpf_core_field_size(p->my_field);
+ *   - field reference through type and field names:
+ *     bpf_core_field_size(struct my_type, my_field).
  */
-#define bpf_core_field_size(field)					    \
-	__builtin_preserve_field_info(field, BPF_FIELD_BYTE_SIZE)
+#define bpf_core_field_size(field...)					    \
+	__builtin_preserve_field_info(___bpf_field_ref(field), BPF_FIELD_BYTE_SIZE)
+
+/*
+ * Convenience macro to get field's byte offset.
+ *
+ * Supports two forms:
+ *   - field reference through variable access:
+ *     bpf_core_field_offset(p->my_field);
+ *   - field reference through type and field names:
+ *     bpf_core_field_offset(struct my_type, my_field).
+ */
+#define bpf_core_field_offset(field...)					    \
+	__builtin_preserve_field_info(___bpf_field_ref(field), BPF_FIELD_BYTE_OFFSET)
 
 /*
  * Convenience macro to get BTF type ID of a specified type, using a local BTF
@@ -154,6 +184,16 @@ enum bpf_enum_value_kind {
 #define bpf_core_type_exists(type)					    \
 	__builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_EXISTS)
 
+/*
+ * Convenience macro to check that provided named type
+ * (struct/union/enum/typedef) "matches" that in a target kernel.
+ * Returns:
+ *    1, if the type matches in the target kernel's BTF;
+ *    0, if the type does not match any in the target kernel
+ */
+#define bpf_core_type_matches(type)					    \
+	__builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_MATCHES)
+
 /*
  * Convenience macro to get the byte size of a provided named type
  * (struct/union/enum/typedef) in a target kernel.

src/bpf_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;
@@ -38,6 +39,10 @@ struct inode;
 struct socket;
 struct file;
 struct bpf_timer;
+struct mptcp_sock;
+struct bpf_dynptr;
+struct iphdr;
+struct ipv6hdr;
 
 /*
  * bpf_map_lookup_elem
@@ -532,6 +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:
  *
@@ -961,8 +969,8 @@ static long (*bpf_probe_write_user)(void *dst, const void *src, __u32 len) = (vo
  * Returns
  * 	The return value depends on the result of the test, and can be:
  *
- * 	* 0, if current task belongs to the cgroup2.
- * 	* 1, if current task does not belong to the cgroup2.
+ * 	* 1, if current task belongs to the cgroup2.
+ * 	* 0, if current task does not belong to the cgroup2.
  * 	* A negative error code, if an error occurred.
  */
 static long (*bpf_current_task_under_cgroup)(void *map, __u32 index) = (void *) 37;
@@ -1001,7 +1009,8 @@ static long (*bpf_skb_change_tail)(struct __sk_buff *skb, __u32 len, __u64 flags
  * 	Pull in non-linear data in case the *skb* is non-linear and not
  * 	all of *len* are part of the linear section. Make *len* bytes
  * 	from *skb* readable and writable. If a zero value is passed for
- * 	*len*, then the whole length of the *skb* is pulled.
+ * 	*len*, then all bytes in the linear part of *skb* will be made
+ * 	readable and writable.
  *
  * 	This helper is only needed for reading and writing with direct
  * 	packet access.
@@ -1204,14 +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.
@@ -1234,10 +1248,12 @@ static long (*bpf_setsockopt)(void *bpf_socket, int level, int optname, void *op
  * 	There are two supported modes at this time:
  *
  * 	* **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
- * 	  (room space is added or removed below the layer 2 header).
+ * 	  (room space is added or removed between the layer 2 and
+ * 	  layer 3 headers).
  *
  * 	* **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
- * 	  (room space is added or removed below the layer 3 header).
+ * 	  (room space is added or removed between the layer 3 and
+ * 	  layer 4 headers).
  *
  * 	The following flags are supported at this time:
  *
@@ -1299,7 +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
@@ -1458,12 +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.
@@ -1737,8 +1751,18 @@ static long (*bpf_skb_get_xfrm_state)(struct __sk_buff *skb, __u32 index, struct
  * 	**BPF_F_USER_STACK**
  * 		Collect a user space stack instead of a kernel stack.
  * 	**BPF_F_USER_BUILD_ID**
- * 		Collect buildid+offset instead of ips for user stack,
- * 		only valid if **BPF_F_USER_STACK** is also specified.
+ * 		Collect (build_id, file_offset) instead of ips for user
+ * 		stack, only valid if **BPF_F_USER_STACK** is also
+ * 		specified.
+ *
+ * 		*file_offset* is an offset relative to the beginning
+ * 		of the executable or shared object file backing the vma
+ * 		which the *ip* falls in. It is *not* an offset relative
+ * 		to that object's base address. Accordingly, it must be
+ * 		adjusted by adding (sh_addr - sh_offset), where
+ * 		sh_{addr,offset} correspond to the executable section
+ * 		containing *file_offset* in the object, for comparisons
+ * 		to symbols' st_value to be valid.
  *
  * 	**bpf_get_stack**\ () can collect up to
  * 	**PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
@@ -1752,8 +1776,8 @@ static long (*bpf_skb_get_xfrm_state)(struct __sk_buff *skb, __u32 index, struct
  * 		# sysctl kernel.perf_event_max_stack=<new value>
  *
  * Returns
- * 	A non-negative value equal to or less than *size* on success,
- * 	or a negative error in case of failure.
+ * 	The non-negative copied *buf* length equal to or less than
+ * 	*size* on success, or a negative error in case of failure.
  */
 static long (*bpf_get_stack)(void *ctx, void *buf, __u32 size, __u64 flags) = (void *) 67;
 
@@ -2461,10 +2485,11 @@ static struct bpf_sock *(*bpf_skc_lookup_tcp)(void *ctx, struct bpf_sock_tuple *
  *
  * 	*iph* points to the start of the IPv4 or IPv6 header, while
  * 	*iph_len* contains **sizeof**\ (**struct iphdr**) or
- * 	**sizeof**\ (**struct ip6hdr**).
+ * 	**sizeof**\ (**struct ipv6hdr**).
  *
  * 	*th* points to the start of the TCP header, while *th_len*
- * 	contains **sizeof**\ (**struct tcphdr**).
+ * 	contains the length of the TCP header (at least
+ * 	**sizeof**\ (**struct tcphdr**)).
  *
  * Returns
  * 	0 if *iph* and *th* are a valid SYN cookie ACK, or a negative
@@ -2687,10 +2712,11 @@ static long (*bpf_send_signal)(__u32 sig) = (void *) 109;
  *
  * 	*iph* points to the start of the IPv4 or IPv6 header, while
  * 	*iph_len* contains **sizeof**\ (**struct iphdr**) or
- * 	**sizeof**\ (**struct ip6hdr**).
+ * 	**sizeof**\ (**struct ipv6hdr**).
  *
  * 	*th* points to the start of the TCP header, while *th_len*
- * 	contains the length of the TCP header.
+ * 	contains the length of the TCP header with options (at least
+ * 	**sizeof**\ (**struct tcphdr**)).
  *
  * Returns
  * 	On success, lower 32 bits hold the generated SYN cookie in
@@ -3305,8 +3331,8 @@ static struct udp6_sock *(*bpf_skc_to_udp6_sock)(void *sk) = (void *) 140;
  * 		# sysctl kernel.perf_event_max_stack=<new value>
  *
  * Returns
- * 	A non-negative value equal to or less than *size* on success,
- * 	or a negative error in case of failure.
+ * 	The non-negative copied *buf* length equal to or less than
+ * 	*size* on success, or a negative error in case of failure.
  */
 static long (*bpf_get_task_stack)(struct task_struct *task, void *buf, __u32 size, __u64 flags) = (void *) 141;
 
@@ -3407,7 +3433,7 @@ static long (*bpf_load_hdr_opt)(struct bpf_sock_ops *skops, void *searchby_res,
  *
  * 	**-EEXIST** if the option already exists.
  *
- * 	**-EFAULT** on failrue to parse the existing header options.
+ * 	**-EFAULT** on failure to parse the existing header options.
  *
  * 	**-EPERM** if the helper cannot be used under the current
  * 	*skops*\ **->op**.
@@ -3667,7 +3693,7 @@ static long (*bpf_redirect_peer)(__u32 ifindex, __u64 flags) = (void *) 155;
  * 	a *map* with *task* as the **key**.  From this
  * 	perspective,  the usage is not much different from
  * 	**bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this
- * 	helper enforces the key must be an task_struct and the map must also
+ * 	helper enforces the key must be a task_struct and the map must also
  * 	be a **BPF_MAP_TYPE_TASK_STORAGE**.
  *
  * 	Underneath, the value is stored locally at *task* instead of
@@ -3745,7 +3771,7 @@ static __u64 (*bpf_ktime_get_coarse_ns)(void) = (void *) 160;
 /*
  * bpf_ima_inode_hash
  *
- * 	Returns the stored IMA hash of the *inode* (if it's avaialable).
+ * 	Returns the stored IMA hash of the *inode* (if it's available).
  * 	If the hash is larger than *size*, then only *size*
  * 	bytes will be copied to *dst*
  *
@@ -3777,12 +3803,12 @@ static struct socket *(*bpf_sock_from_file)(struct file *file) = (void *) 162;
  *
  * 	The argument *len_diff* can be used for querying with a planned
  * 	size change. This allows to check MTU prior to changing packet
- * 	ctx. Providing an *len_diff* adjustment that is larger than the
+ * 	ctx. Providing a *len_diff* adjustment that is larger than the
  * 	actual packet size (resulting in negative packet size) will in
- * 	principle not exceed the MTU, why it is not considered a
- * 	failure.  Other BPF-helpers are needed for performing the
- * 	planned size change, why the responsability for catch a negative
- * 	packet size belong in those helpers.
+ * 	principle not exceed the MTU, which is why it is not considered
+ * 	a failure.  Other BPF helpers are needed for performing the
+ * 	planned size change; therefore the responsibility for catching
+ * 	a negative packet size belongs in those helpers.
  *
  * 	Specifying *ifindex* zero means the MTU check is performed
  * 	against the current net device.  This is practical if this isn't
@@ -4021,6 +4047,7 @@ static long (*bpf_timer_cancel)(struct bpf_timer *timer) = (void *) 172;
  *
  * Returns
  * 	Address of the traced function.
+ * 	0 for kprobes placed within the function (not at the entry).
  */
 static __u64 (*bpf_get_func_ip)(void *ctx) = (void *) 173;
 
@@ -4189,13 +4216,13 @@ static long (*bpf_strncmp)(const char *s1, __u32 s1_sz, const char *s2) = (void
 /*
  * bpf_get_func_arg
  *
- * 	Get **n**-th argument (zero based) of the traced function (for tracing programs)
+ * 	Get **n**-th argument register (zero based) of the traced function (for tracing programs)
  * 	returned in **value**.
  *
  *
  * Returns
  * 	0 on success.
- * 	**-EINVAL** if n >= arguments count of traced function.
+ * 	**-EINVAL** if n >= argument register count of traced function.
  */
 static long (*bpf_get_func_arg)(void *ctx, __u32 n, __u64 *value) = (void *) 183;
 
@@ -4215,32 +4242,45 @@ static long (*bpf_get_func_ret)(void *ctx, __u64 *value) = (void *) 184;
 /*
  * bpf_get_func_arg_cnt
  *
- * 	Get number of arguments of the traced function (for tracing programs).
+ * 	Get number of registers of the traced function (for tracing programs) where
+ * 	function arguments are stored in these registers.
  *
  *
  * Returns
- * 	The number of arguments of the traced function.
+ * 	The number of argument registers of the traced function.
  */
 static long (*bpf_get_func_arg_cnt)(void *ctx) = (void *) 185;
 
 /*
  * bpf_get_retval
  *
- * 	Get the syscall's return value that will be returned to userspace.
+ * 	Get the BPF program's return value that will be returned to the upper layers.
  *
- * 	This helper is currently supported by cgroup programs only.
+ * 	This helper is currently supported by cgroup programs and only by the hooks
+ * 	where BPF program's return value is returned to the userspace via errno.
  *
  * Returns
- * 	The syscall's return value.
+ * 	The BPF program's return value.
  */
 static int (*bpf_get_retval)(void) = (void *) 186;
 
 /*
  * bpf_set_retval
  *
- * 	Set the syscall's return value that will be returned to userspace.
+ * 	Set the BPF program's return value that will be returned to the upper layers.
+ *
+ * 	This helper is currently supported by cgroup programs and only by the hooks
+ * 	where BPF program's return value is returned to the userspace via errno.
+ *
+ * 	Note that there is the following corner case where the program exports an error
+ * 	via bpf_set_retval but signals success via 'return 1':
+ *
+ * 		bpf_set_retval(-EPERM);
+ * 		return 1;
+ *
+ * 	In this case, the BPF program's return value will use helper's -EPERM. This
+ * 	still holds true for cgroup/bind{4,6} which supports extra 'return 3' success case.
  *
- * 	This helper is currently supported by cgroup programs only.
  *
  * Returns
  * 	0 on success, or a negative error in case of failure.
@@ -4295,4 +4335,384 @@ static long (*bpf_xdp_store_bytes)(struct xdp_md *xdp_md, __u32 offset, void *bu
  */
 static long (*bpf_copy_from_user_task)(void *dst, __u32 size, const void *user_ptr, struct task_struct *tsk, __u64 flags) = (void *) 191;
 
+/*
+ * bpf_skb_set_tstamp
+ *
+ * 	Change the __sk_buff->tstamp_type to *tstamp_type*
+ * 	and set *tstamp* to the __sk_buff->tstamp together.
+ *
+ * 	If there is no need to change the __sk_buff->tstamp_type,
+ * 	the tstamp value can be directly written to __sk_buff->tstamp
+ * 	instead.
+ *
+ * 	BPF_SKB_TSTAMP_DELIVERY_MONO is the only tstamp that
+ * 	will be kept during bpf_redirect_*().  A non zero
+ * 	*tstamp* must be used with the BPF_SKB_TSTAMP_DELIVERY_MONO
+ * 	*tstamp_type*.
+ *
+ * 	A BPF_SKB_TSTAMP_UNSPEC *tstamp_type* can only be used
+ * 	with a zero *tstamp*.
+ *
+ * 	Only IPv4 and IPv6 skb->protocol are supported.
+ *
+ * 	This function is most useful when it needs to set a
+ * 	mono delivery time to __sk_buff->tstamp and then
+ * 	bpf_redirect_*() to the egress of an iface.  For example,
+ * 	changing the (rcv) timestamp in __sk_buff->tstamp at
+ * 	ingress to a mono delivery time and then bpf_redirect_*()
+ * 	to sch_fq@phy-dev.
+ *
+ * Returns
+ * 	0 on success.
+ * 	**-EINVAL** for invalid input
+ * 	**-EOPNOTSUPP** for unsupported protocol
+ */
+static long (*bpf_skb_set_tstamp)(struct __sk_buff *skb, __u64 tstamp, __u32 tstamp_type) = (void *) 192;
+
+/*
+ * bpf_ima_file_hash
+ *
+ * 	Returns a calculated IMA hash of the *file*.
+ * 	If the hash is larger than *size*, then only *size*
+ * 	bytes will be copied to *dst*
+ *
+ * Returns
+ * 	The **hash_algo** is returned on success,
+ * 	**-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if
+ * 	invalid arguments are passed.
+ */
+static long (*bpf_ima_file_hash)(struct file *file, void *dst, __u32 size) = (void *) 193;
+
+/*
+ * bpf_kptr_xchg
+ *
+ * 	Exchange kptr at pointer *map_value* with *ptr*, and return the
+ * 	old value. *ptr* can be NULL, otherwise it must be a referenced
+ * 	pointer which will be released when this helper is called.
+ *
+ * Returns
+ * 	The old value of kptr (which can be NULL). The returned pointer
+ * 	if not NULL, is a reference which must be released using its
+ * 	corresponding release function, or moved into a BPF map before
+ * 	program exit.
+ */
+static void *(*bpf_kptr_xchg)(void *map_value, void *ptr) = (void *) 194;
+
+/*
+ * bpf_map_lookup_percpu_elem
+ *
+ * 	Perform a lookup in *percpu map* for an entry associated to
+ * 	*key* on *cpu*.
+ *
+ * Returns
+ * 	Map value associated to *key* on *cpu*, or **NULL** if no entry
+ * 	was found or *cpu* is invalid.
+ */
+static void *(*bpf_map_lookup_percpu_elem)(void *map, const void *key, __u32 cpu) = (void *) 195;
+
+/*
+ * bpf_skc_to_mptcp_sock
+ *
+ * 	Dynamically cast a *sk* pointer to a *mptcp_sock* pointer.
+ *
+ * Returns
+ * 	*sk* if casting is valid, or **NULL** otherwise.
+ */
+static struct mptcp_sock *(*bpf_skc_to_mptcp_sock)(void *sk) = (void *) 196;
+
+/*
+ * bpf_dynptr_from_mem
+ *
+ * 	Get a dynptr to local memory *data*.
+ *
+ * 	*data* must be a ptr to a map value.
+ * 	The maximum *size* supported is DYNPTR_MAX_SIZE.
+ * 	*flags* is currently unused.
+ *
+ * Returns
+ * 	0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE,
+ * 	-EINVAL if flags is not 0.
+ */
+static long (*bpf_dynptr_from_mem)(void *data, __u32 size, __u64 flags, struct bpf_dynptr *ptr) = (void *) 197;
+
+/*
+ * bpf_ringbuf_reserve_dynptr
+ *
+ * 	Reserve *size* bytes of payload in a ring buffer *ringbuf*
+ * 	through the dynptr interface. *flags* must be 0.
+ *
+ * 	Please note that a corresponding bpf_ringbuf_submit_dynptr or
+ * 	bpf_ringbuf_discard_dynptr must be called on *ptr*, even if the
+ * 	reservation fails. This is enforced by the verifier.
+ *
+ * Returns
+ * 	0 on success, or a negative error in case of failure.
+ */
+static long (*bpf_ringbuf_reserve_dynptr)(void *ringbuf, __u32 size, __u64 flags, struct bpf_dynptr *ptr) = (void *) 198;
+
+/*
+ * bpf_ringbuf_submit_dynptr
+ *
+ * 	Submit reserved ring buffer sample, pointed to by *data*,
+ * 	through the dynptr interface. This is a no-op if the dynptr is
+ * 	invalid/null.
+ *
+ * 	For more information on *flags*, please see
+ * 	'bpf_ringbuf_submit'.
+ *
+ * Returns
+ * 	Nothing. Always succeeds.
+ */
+static void (*bpf_ringbuf_submit_dynptr)(struct bpf_dynptr *ptr, __u64 flags) = (void *) 199;
+
+/*
+ * bpf_ringbuf_discard_dynptr
+ *
+ * 	Discard reserved ring buffer sample through the dynptr
+ * 	interface. This is a no-op if the dynptr is invalid/null.
+ *
+ * 	For more information on *flags*, please see
+ * 	'bpf_ringbuf_discard'.
+ *
+ * Returns
+ * 	Nothing. Always succeeds.
+ */
+static void (*bpf_ringbuf_discard_dynptr)(struct bpf_dynptr *ptr, __u64 flags) = (void *) 200;
+
+/*
+ * bpf_dynptr_read
+ *
+ * 	Read *len* bytes from *src* into *dst*, starting from *offset*
+ * 	into *src*.
+ * 	*flags* is currently unused.
+ *
+ * Returns
+ * 	0 on success, -E2BIG if *offset* + *len* exceeds the length
+ * 	of *src*'s data, -EINVAL if *src* is an invalid dynptr or if
+ * 	*flags* is not 0.
+ */
+static long (*bpf_dynptr_read)(void *dst, __u32 len, const struct bpf_dynptr *src, __u32 offset, __u64 flags) = (void *) 201;
+
+/*
+ * bpf_dynptr_write
+ *
+ * 	Write *len* bytes from *src* into *dst*, starting from *offset*
+ * 	into *dst*.
+ * 	*flags* is currently unused.
+ *
+ * Returns
+ * 	0 on success, -E2BIG if *offset* + *len* exceeds the length
+ * 	of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst*
+ * 	is a read-only dynptr or if *flags* is not 0.
+ */
+static long (*bpf_dynptr_write)(const struct bpf_dynptr *dst, __u32 offset, void *src, __u32 len, __u64 flags) = (void *) 202;
+
+/*
+ * bpf_dynptr_data
+ *
+ * 	Get a pointer to the underlying dynptr data.
+ *
+ * 	*len* must be a statically known value. The returned data slice
+ * 	is invalidated whenever the dynptr is invalidated.
+ *
+ * Returns
+ * 	Pointer to the underlying dynptr data, NULL if the dynptr is
+ * 	read-only, if the dynptr is invalid, or if the offset and length
+ * 	is out of bounds.
+ */
+static void *(*bpf_dynptr_data)(const struct bpf_dynptr *ptr, __u32 offset, __u32 len) = (void *) 203;
+
+/*
+ * bpf_tcp_raw_gen_syncookie_ipv4
+ *
+ * 	Try to issue a SYN cookie for the packet with corresponding
+ * 	IPv4/TCP headers, *iph* and *th*, without depending on a
+ * 	listening socket.
+ *
+ * 	*iph* points to the IPv4 header.
+ *
+ * 	*th* points to the start of the TCP header, while *th_len*
+ * 	contains the length of the TCP header (at least
+ * 	**sizeof**\ (**struct tcphdr**)).
+ *
+ * Returns
+ * 	On success, lower 32 bits hold the generated SYN cookie in
+ * 	followed by 16 bits which hold the MSS value for that cookie,
+ * 	and the top 16 bits are unused.
+ *
+ * 	On failure, the returned value is one of the following:
+ *
+ * 	**-EINVAL** if *th_len* is invalid.
+ */
+static __s64 (*bpf_tcp_raw_gen_syncookie_ipv4)(struct iphdr *iph, struct tcphdr *th, __u32 th_len) = (void *) 204;
+
+/*
+ * bpf_tcp_raw_gen_syncookie_ipv6
+ *
+ * 	Try to issue a SYN cookie for the packet with corresponding
+ * 	IPv6/TCP headers, *iph* and *th*, without depending on a
+ * 	listening socket.
+ *
+ * 	*iph* points to the IPv6 header.
+ *
+ * 	*th* points to the start of the TCP header, while *th_len*
+ * 	contains the length of the TCP header (at least
+ * 	**sizeof**\ (**struct tcphdr**)).
+ *
+ * Returns
+ * 	On success, lower 32 bits hold the generated SYN cookie in
+ * 	followed by 16 bits which hold the MSS value for that cookie,
+ * 	and the top 16 bits are unused.
+ *
+ * 	On failure, the returned value is one of the following:
+ *
+ * 	**-EINVAL** if *th_len* is invalid.
+ *
+ * 	**-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
+ */
+static __s64 (*bpf_tcp_raw_gen_syncookie_ipv6)(struct ipv6hdr *iph, struct tcphdr *th, __u32 th_len) = (void *) 205;
+
+/*
+ * bpf_tcp_raw_check_syncookie_ipv4
+ *
+ * 	Check whether *iph* and *th* contain a valid SYN cookie ACK
+ * 	without depending on a listening socket.
+ *
+ * 	*iph* points to the IPv4 header.
+ *
+ * 	*th* points to the TCP header.
+ *
+ * Returns
+ * 	0 if *iph* and *th* are a valid SYN cookie ACK.
+ *
+ * 	On failure, the returned value is one of the following:
+ *
+ * 	**-EACCES** if the SYN cookie is not valid.
+ */
+static long (*bpf_tcp_raw_check_syncookie_ipv4)(struct iphdr *iph, struct tcphdr *th) = (void *) 206;
+
+/*
+ * bpf_tcp_raw_check_syncookie_ipv6
+ *
+ * 	Check whether *iph* and *th* contain a valid SYN cookie ACK
+ * 	without depending on a listening socket.
+ *
+ * 	*iph* points to the IPv6 header.
+ *
+ * 	*th* points to the TCP header.
+ *
+ * Returns
+ * 	0 if *iph* and *th* are a valid SYN cookie ACK.
+ *
+ * 	On failure, the returned value is one of the following:
+ *
+ * 	**-EACCES** if the SYN cookie is not valid.
+ *
+ * 	**-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
+ */
+static long (*bpf_tcp_raw_check_syncookie_ipv6)(struct ipv6hdr *iph, struct tcphdr *th) = (void *) 207;
+
+/*
+ * bpf_ktime_get_tai_ns
+ *
+ * 	A nonsettable system-wide clock derived from wall-clock time but
+ * 	ignoring leap seconds.  This clock does not experience
+ * 	discontinuities and backwards jumps caused by NTP inserting leap
+ * 	seconds as CLOCK_REALTIME does.
+ *
+ * 	See: **clock_gettime**\ (**CLOCK_TAI**)
+ *
+ * Returns
+ * 	Current *ktime*.
+ */
+static __u64 (*bpf_ktime_get_tai_ns)(void) = (void *) 208;
+
+/*
+ * bpf_user_ringbuf_drain
+ *
+ * 	Drain samples from the specified user ring buffer, and invoke
+ * 	the provided callback for each such sample:
+ *
+ * 	long (\*callback_fn)(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
+ * 	BPF_MAX_USER_RINGBUF_SAMPLES samples. If the return value is 1,
+ * 	the helper will skip the rest of the samples and return. Other
+ * 	return values are not used now, and will be rejected by the
+ * 	verifier.
+ *
+ * Returns
+ * 	The number of drained samples if no error was encountered while
+ * 	draining samples, or 0 if no samples were present in the ring
+ * 	buffer. If a user-space producer was epoll-waiting on this map,
+ * 	and at least one sample was drained, they will receive an event
+ * 	notification notifying them of available space in the ring
+ * 	buffer. If the BPF_RB_NO_WAKEUP flag is passed to this
+ * 	function, no wakeup notification will be sent. If the
+ * 	BPF_RB_FORCE_WAKEUP flag is passed, a wakeup notification will
+ * 	be sent even if no sample was drained.
+ *
+ * 	On failure, the returned value is one of the following:
+ *
+ * 	**-EBUSY** if the ring buffer is contended, and another calling
+ * 	context was concurrently draining the ring buffer.
+ *
+ * 	**-EINVAL** if user-space is not properly tracking the ring
+ * 	buffer due to the producer position not being aligned to 8
+ * 	bytes, a sample not being aligned to 8 bytes, or the producer
+ * 	position not matching the advertised length of a sample.
+ *
+ * 	**-E2BIG** if user-space has tried to publish a sample which is
+ * 	larger than the size of the ring buffer, or which cannot fit
+ * 	within a struct bpf_dynptr.
+ */
+static long (*bpf_user_ringbuf_drain)(void *map, void *callback_fn, void *ctx, __u64 flags) = (void *) 209;
+
+/*
+ * 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/bpf_helpers.h

@@ -22,12 +22,25 @@
  * To allow use of SEC() with externs (e.g., for extern .maps declarations),
  * make sure __attribute__((unused)) doesn't trigger compilation warning.
  */
+#if __GNUC__ && !__clang__
+
+/*
+ * Pragma macros are broken on GCC
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=55578
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90400
+ */
+#define SEC(name) __attribute__((section(name), used))
+
+#else
+
 #define SEC(name) \
 	_Pragma("GCC diagnostic push")					    \
 	_Pragma("GCC diagnostic ignored \"-Wignored-attributes\"")	    \
 	__attribute__((section(name), used))				    \
 	_Pragma("GCC diagnostic pop")					    \
 
+#endif
+
 /* Avoid 'linux/stddef.h' definition of '__always_inline'. */
 #undef __always_inline
 #define __always_inline inline __attribute__((always_inline))
@@ -75,6 +88,30 @@
 	})
 #endif
 
+/*
+ * Compiler (optimization) barrier.
+ */
+#ifndef barrier
+#define barrier() asm volatile("" ::: "memory")
+#endif
+
+/* Variable-specific compiler (optimization) barrier. It's a no-op which makes
+ * compiler believe that there is some black box modification of a given
+ * variable and thus prevents compiler from making extra assumption about its
+ * value and potential simplifications and optimizations on this variable.
+ *
+ * E.g., compiler might often delay or even omit 32-bit to 64-bit casting of
+ * a variable, making some code patterns unverifiable. Putting barrier_var()
+ * in place will ensure that cast is performed before the barrier_var()
+ * invocation, because compiler has to pessimistically assume that embedded
+ * asm section might perform some extra operations on that variable.
+ *
+ * This is a variable-specific variant of more global barrier().
+ */
+#ifndef barrier_var
+#define barrier_var(var) asm volatile("" : "=r"(var) : "0"(var))
+#endif
+
 /*
  * Helper macro to throw a compilation error if __bpf_unreachable() gets
  * built into the resulting code. This works given BPF back end does not
@@ -123,18 +160,6 @@ bpf_tail_call_static(void *ctx, const void *map, const __u32 slot)
 }
 #endif
 
-/*
- * Helper structure used by eBPF C program
- * to describe BPF map attributes to libbpf loader
- */
-struct bpf_map_def {
-	unsigned int type;
-	unsigned int key_size;
-	unsigned int value_size;
-	unsigned int max_entries;
-	unsigned int map_flags;
-} __attribute__((deprecated("use BTF-defined maps in .maps section")));
-
 enum libbpf_pin_type {
 	LIBBPF_PIN_NONE,
 	/* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */
@@ -149,6 +174,8 @@ enum libbpf_tristate {
 
 #define __kconfig __attribute__((section(".kconfig")))
 #define __ksym __attribute__((section(".ksyms")))
+#define __kptr __attribute__((btf_type_tag("kptr")))
+#define __kptr_ref __attribute__((btf_type_tag("kptr_ref")))
 
 #ifndef ___bpf_concat
 #define ___bpf_concat(a, b) a ## b

src/bpf_tracing.h

@@ -2,6 +2,8 @@
 #ifndef __BPF_TRACING_H__
 #define __BPF_TRACING_H__
 
+#include "bpf_helpers.h"
+
 /* Scan the ARCH passed in from ARCH env variable (see Makefile) */
 #if defined(__TARGET_ARCH_x86)
 	#define bpf_target_x86
@@ -27,6 +29,9 @@
 #elif defined(__TARGET_ARCH_riscv)
 	#define bpf_target_riscv
 	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_arc)
+	#define bpf_target_arc
+	#define bpf_target_defined
 #else
 
 /* Fall back to what the compiler says */
@@ -54,6 +59,9 @@
 #elif defined(__riscv) && __riscv_xlen == 64
 	#define bpf_target_riscv
 	#define bpf_target_defined
+#elif defined(__arc__)
+	#define bpf_target_arc
+	#define bpf_target_defined
 #endif /* no compiler target */
 
 #endif
@@ -134,7 +142,7 @@ struct pt_regs___s390 {
 #define __PT_RC_REG gprs[2]
 #define __PT_SP_REG gprs[15]
 #define __PT_IP_REG psw.addr
-#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma("GCC error \"use PT_REGS_PARM1_CORE_SYSCALL() instead\""); 0l; })
+#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x)
 #define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___s390 *)(x), orig_gpr2)
 
 #elif defined(bpf_target_arm)
@@ -169,7 +177,7 @@ struct pt_regs___arm64 {
 #define __PT_RC_REG regs[0]
 #define __PT_SP_REG sp
 #define __PT_IP_REG pc
-#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma("GCC error \"use PT_REGS_PARM1_CORE_SYSCALL() instead\""); 0l; })
+#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x)
 #define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___arm64 *)(x), orig_x0)
 
 #elif defined(bpf_target_mips)
@@ -229,12 +237,29 @@ struct pt_regs___arm64 {
 #define __PT_PARM6_REG a5
 #define __PT_RET_REG ra
 #define __PT_FP_REG s0
-#define __PT_RC_REG a5
+#define __PT_RC_REG a0
 #define __PT_SP_REG sp
 #define __PT_IP_REG pc
 /* riscv does not select ARCH_HAS_SYSCALL_WRAPPER. */
 #define PT_REGS_SYSCALL_REGS(ctx) ctx
 
+#elif defined(bpf_target_arc)
+
+/* arc provides struct user_pt_regs instead of struct pt_regs to userspace */
+#define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x))
+#define __PT_PARM1_REG scratch.r0
+#define __PT_PARM2_REG scratch.r1
+#define __PT_PARM3_REG scratch.r2
+#define __PT_PARM4_REG scratch.r3
+#define __PT_PARM5_REG scratch.r4
+#define __PT_RET_REG scratch.blink
+#define __PT_FP_REG __unsupported__
+#define __PT_RC_REG scratch.r0
+#define __PT_SP_REG scratch.sp
+#define __PT_IP_REG scratch.ret
+/* arc does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx
+
 #endif
 
 #if defined(bpf_target_defined)
@@ -405,7 +430,7 @@ struct pt_regs;
  */
 #define BPF_PROG(name, args...)						    \
 name(unsigned long long *ctx);						    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(unsigned long long *ctx, ##args);				    \
 typeof(name(0)) name(unsigned long long *ctx)				    \
 {									    \
@@ -414,9 +439,116 @@ typeof(name(0)) name(unsigned long long *ctx)				    \
 	return ____##name(___bpf_ctx_cast(args));			    \
 	_Pragma("GCC diagnostic pop")					    \
 }									    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(unsigned long long *ctx, ##args)
 
+#ifndef ___bpf_nth2
+#define ___bpf_nth2(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _13,	\
+		    _14, _15, _16, _17, _18, _19, _20, _21, _22, _23, _24, N, ...) N
+#endif
+#ifndef ___bpf_narg2
+#define ___bpf_narg2(...)	\
+	___bpf_nth2(_, ##__VA_ARGS__, 12, 12, 11, 11, 10, 10, 9, 9, 8, 8, 7, 7,	\
+		    6, 6, 5, 5, 4, 4, 3, 3, 2, 2, 1, 1, 0)
+#endif
+
+#define ___bpf_treg_cnt(t) \
+	__builtin_choose_expr(sizeof(t) == 1, 1,	\
+	__builtin_choose_expr(sizeof(t) == 2, 1,	\
+	__builtin_choose_expr(sizeof(t) == 4, 1,	\
+	__builtin_choose_expr(sizeof(t) == 8, 1,	\
+	__builtin_choose_expr(sizeof(t) == 16, 2,	\
+			      (void)0)))))
+
+#define ___bpf_reg_cnt0()		(0)
+#define ___bpf_reg_cnt1(t, x)		(___bpf_reg_cnt0() + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt2(t, x, args...)	(___bpf_reg_cnt1(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt3(t, x, args...)	(___bpf_reg_cnt2(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt4(t, x, args...)	(___bpf_reg_cnt3(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt5(t, x, args...)	(___bpf_reg_cnt4(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt6(t, x, args...)	(___bpf_reg_cnt5(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt7(t, x, args...)	(___bpf_reg_cnt6(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt8(t, x, args...)	(___bpf_reg_cnt7(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt9(t, x, args...)	(___bpf_reg_cnt8(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt10(t, x, args...)	(___bpf_reg_cnt9(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt11(t, x, args...)	(___bpf_reg_cnt10(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt12(t, x, args...)	(___bpf_reg_cnt11(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt(args...)	 ___bpf_apply(___bpf_reg_cnt, ___bpf_narg2(args))(args)
+
+#define ___bpf_union_arg(t, x, n) \
+	__builtin_choose_expr(sizeof(t) == 1, ({ union { __u8 z[1]; t x; } ___t = { .z = {ctx[n]}}; ___t.x; }), \
+	__builtin_choose_expr(sizeof(t) == 2, ({ union { __u16 z[1]; t x; } ___t = { .z = {ctx[n]} }; ___t.x; }), \
+	__builtin_choose_expr(sizeof(t) == 4, ({ union { __u32 z[1]; t x; } ___t = { .z = {ctx[n]} }; ___t.x; }), \
+	__builtin_choose_expr(sizeof(t) == 8, ({ union { __u64 z[1]; t x; } ___t = {.z = {ctx[n]} }; ___t.x; }), \
+	__builtin_choose_expr(sizeof(t) == 16, ({ union { __u64 z[2]; t x; } ___t = {.z = {ctx[n], ctx[n + 1]} }; ___t.x; }), \
+			      (void)0)))))
+
+#define ___bpf_ctx_arg0(n, args...)
+#define ___bpf_ctx_arg1(n, t, x)		, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt1(t, x))
+#define ___bpf_ctx_arg2(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt2(t, x, args)) ___bpf_ctx_arg1(n, args)
+#define ___bpf_ctx_arg3(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt3(t, x, args)) ___bpf_ctx_arg2(n, args)
+#define ___bpf_ctx_arg4(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt4(t, x, args)) ___bpf_ctx_arg3(n, args)
+#define ___bpf_ctx_arg5(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt5(t, x, args)) ___bpf_ctx_arg4(n, args)
+#define ___bpf_ctx_arg6(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt6(t, x, args)) ___bpf_ctx_arg5(n, args)
+#define ___bpf_ctx_arg7(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt7(t, x, args)) ___bpf_ctx_arg6(n, args)
+#define ___bpf_ctx_arg8(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt8(t, x, args)) ___bpf_ctx_arg7(n, args)
+#define ___bpf_ctx_arg9(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt9(t, x, args)) ___bpf_ctx_arg8(n, args)
+#define ___bpf_ctx_arg10(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt10(t, x, args)) ___bpf_ctx_arg9(n, args)
+#define ___bpf_ctx_arg11(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt11(t, x, args)) ___bpf_ctx_arg10(n, args)
+#define ___bpf_ctx_arg12(n, t, x, args...)	, ___bpf_union_arg(t, x, n - ___bpf_reg_cnt12(t, x, args)) ___bpf_ctx_arg11(n, args)
+#define ___bpf_ctx_arg(args...)	___bpf_apply(___bpf_ctx_arg, ___bpf_narg2(args))(___bpf_reg_cnt(args), args)
+
+#define ___bpf_ctx_decl0()
+#define ___bpf_ctx_decl1(t, x)			, t x
+#define ___bpf_ctx_decl2(t, x, args...)		, t x ___bpf_ctx_decl1(args)
+#define ___bpf_ctx_decl3(t, x, args...)		, t x ___bpf_ctx_decl2(args)
+#define ___bpf_ctx_decl4(t, x, args...)		, t x ___bpf_ctx_decl3(args)
+#define ___bpf_ctx_decl5(t, x, args...)		, t x ___bpf_ctx_decl4(args)
+#define ___bpf_ctx_decl6(t, x, args...)		, t x ___bpf_ctx_decl5(args)
+#define ___bpf_ctx_decl7(t, x, args...)		, t x ___bpf_ctx_decl6(args)
+#define ___bpf_ctx_decl8(t, x, args...)		, t x ___bpf_ctx_decl7(args)
+#define ___bpf_ctx_decl9(t, x, args...)		, t x ___bpf_ctx_decl8(args)
+#define ___bpf_ctx_decl10(t, x, args...)	, t x ___bpf_ctx_decl9(args)
+#define ___bpf_ctx_decl11(t, x, args...)	, t x ___bpf_ctx_decl10(args)
+#define ___bpf_ctx_decl12(t, x, args...)	, t x ___bpf_ctx_decl11(args)
+#define ___bpf_ctx_decl(args...)	___bpf_apply(___bpf_ctx_decl, ___bpf_narg2(args))(args)
+
+/*
+ * BPF_PROG2 is an enhanced version of BPF_PROG in order to handle struct
+ * arguments. Since each struct argument might take one or two u64 values
+ * in the trampoline stack, argument type size is needed to place proper number
+ * of u64 values for each argument. Therefore, BPF_PROG2 has different
+ * syntax from BPF_PROG. For example, for the following BPF_PROG syntax:
+ *
+ *   int BPF_PROG(test2, int a, int b) { ... }
+ *
+ * the corresponding BPF_PROG2 syntax is:
+ *
+ *   int BPF_PROG2(test2, int, a, int, b) { ... }
+ *
+ * where type and the corresponding argument name are separated by comma.
+ *
+ * Use BPF_PROG2 macro if one of the arguments might be a struct/union larger
+ * than 8 bytes:
+ *
+ *   int BPF_PROG2(test_struct_arg, struct bpf_testmod_struct_arg_1, a, int, b,
+ *		   int, c, int, d, struct bpf_testmod_struct_arg_2, e, int, ret)
+ *   {
+ *        // access a, b, c, d, e, and ret directly
+ *        ...
+ *   }
+ */
+#define BPF_PROG2(name, args...)						\
+name(unsigned long long *ctx);							\
+static __always_inline typeof(name(0))						\
+____##name(unsigned long long *ctx ___bpf_ctx_decl(args));			\
+typeof(name(0)) name(unsigned long long *ctx)					\
+{										\
+	return ____##name(ctx ___bpf_ctx_arg(args));				\
+}										\
+static __always_inline typeof(name(0))						\
+____##name(unsigned long long *ctx ___bpf_ctx_decl(args))
+
 struct pt_regs;
 
 #define ___bpf_kprobe_args0()           ctx
@@ -440,7 +572,7 @@ struct pt_regs;
  */
 #define BPF_KPROBE(name, args...)					    \
 name(struct pt_regs *ctx);						    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(struct pt_regs *ctx, ##args);				    \
 typeof(name(0)) name(struct pt_regs *ctx)				    \
 {									    \
@@ -449,7 +581,7 @@ typeof(name(0)) name(struct pt_regs *ctx)				    \
 	return ____##name(___bpf_kprobe_args(args));			    \
 	_Pragma("GCC diagnostic pop")					    \
 }									    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(struct pt_regs *ctx, ##args)
 
 #define ___bpf_kretprobe_args0()       ctx
@@ -464,7 +596,7 @@ ____##name(struct pt_regs *ctx, ##args)
  */
 #define BPF_KRETPROBE(name, args...)					    \
 name(struct pt_regs *ctx);						    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(struct pt_regs *ctx, ##args);				    \
 typeof(name(0)) name(struct pt_regs *ctx)				    \
 {									    \
@@ -475,16 +607,26 @@ typeof(name(0)) name(struct pt_regs *ctx)				    \
 }									    \
 static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
 
+/* If kernel has CONFIG_ARCH_HAS_SYSCALL_WRAPPER, read pt_regs directly */
 #define ___bpf_syscall_args0()           ctx
-#define ___bpf_syscall_args1(x)          ___bpf_syscall_args0(), (void *)PT_REGS_PARM1_CORE_SYSCALL(regs)
-#define ___bpf_syscall_args2(x, args...) ___bpf_syscall_args1(args), (void *)PT_REGS_PARM2_CORE_SYSCALL(regs)
-#define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (void *)PT_REGS_PARM3_CORE_SYSCALL(regs)
-#define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (void *)PT_REGS_PARM4_CORE_SYSCALL(regs)
-#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (void *)PT_REGS_PARM5_CORE_SYSCALL(regs)
+#define ___bpf_syscall_args1(x)          ___bpf_syscall_args0(), (void *)PT_REGS_PARM1_SYSCALL(regs)
+#define ___bpf_syscall_args2(x, args...) ___bpf_syscall_args1(args), (void *)PT_REGS_PARM2_SYSCALL(regs)
+#define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (void *)PT_REGS_PARM3_SYSCALL(regs)
+#define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (void *)PT_REGS_PARM4_SYSCALL(regs)
+#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (void *)PT_REGS_PARM5_SYSCALL(regs)
 #define ___bpf_syscall_args(args...)     ___bpf_apply(___bpf_syscall_args, ___bpf_narg(args))(args)
 
+/* If kernel doesn't have CONFIG_ARCH_HAS_SYSCALL_WRAPPER, we have to BPF_CORE_READ from pt_regs */
+#define ___bpf_syswrap_args0()           ctx
+#define ___bpf_syswrap_args1(x)          ___bpf_syswrap_args0(), (void *)PT_REGS_PARM1_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args2(x, args...) ___bpf_syswrap_args1(args), (void *)PT_REGS_PARM2_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args3(x, args...) ___bpf_syswrap_args2(args), (void *)PT_REGS_PARM3_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args4(x, args...) ___bpf_syswrap_args3(args), (void *)PT_REGS_PARM4_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args5(x, args...) ___bpf_syswrap_args4(args), (void *)PT_REGS_PARM5_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args(args...)     ___bpf_apply(___bpf_syswrap_args, ___bpf_narg(args))(args)
+
 /*
- * BPF_KPROBE_SYSCALL is a variant of BPF_KPROBE, which is intended for
+ * BPF_KSYSCALL is a variant of BPF_KPROBE, which is intended for
  * tracing syscall functions, like __x64_sys_close. It hides the underlying
  * platform-specific low-level way of getting syscall input arguments from
  * struct pt_regs, and provides a familiar typed and named function arguments
@@ -493,21 +635,41 @@ static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
  * Original struct pt_regs * context is preserved as 'ctx' argument. This might
  * be necessary when using BPF helpers like bpf_perf_event_output().
  *
- * This macro relies on BPF CO-RE support.
+ * At the moment BPF_KSYSCALL does not transparently handle all the calling
+ * convention quirks for the following syscalls:
+ *
+ * - mmap(): __ARCH_WANT_SYS_OLD_MMAP.
+ * - clone(): CONFIG_CLONE_BACKWARDS, CONFIG_CLONE_BACKWARDS2 and
+ *            CONFIG_CLONE_BACKWARDS3.
+ * - socket-related syscalls: __ARCH_WANT_SYS_SOCKETCALL.
+ * - compat syscalls.
+ *
+ * This may or may not change in the future. User needs to take extra measures
+ * to handle such quirks explicitly, if necessary.
+ *
+ * This macro relies on BPF CO-RE support and virtual __kconfig externs.
  */
-#define BPF_KPROBE_SYSCALL(name, args...)				    \
+#define BPF_KSYSCALL(name, args...)					    \
 name(struct pt_regs *ctx);						    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+extern _Bool LINUX_HAS_SYSCALL_WRAPPER __kconfig;			    \
+static __always_inline typeof(name(0))					    \
 ____##name(struct pt_regs *ctx, ##args);				    \
 typeof(name(0)) name(struct pt_regs *ctx)				    \
 {									    \
-	struct pt_regs *regs = PT_REGS_SYSCALL_REGS(ctx);		    \
+	struct pt_regs *regs = LINUX_HAS_SYSCALL_WRAPPER		    \
+			       ? (struct pt_regs *)PT_REGS_PARM1(ctx)	    \
+			       : ctx;					    \
 	_Pragma("GCC diagnostic push")					    \
 	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")		    \
+	if (LINUX_HAS_SYSCALL_WRAPPER)					    \
+		return ____##name(___bpf_syswrap_args(args));		    \
+	else								    \
 		return ____##name(___bpf_syscall_args(args));		    \
 	_Pragma("GCC diagnostic pop")					    \
 }									    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(struct pt_regs *ctx, ##args)
 
+#define BPF_KPROBE_SYSCALL BPF_KSYSCALL
+
 #endif

src/btf.h

@@ -116,24 +116,15 @@ LIBBPF_API struct btf *btf__parse_raw_split(const char *path, struct btf *base_b
 
 LIBBPF_API struct btf *btf__load_vmlinux_btf(void);
 LIBBPF_API struct btf *btf__load_module_btf(const char *module_name, struct btf *vmlinux_btf);
-LIBBPF_API struct btf *libbpf_find_kernel_btf(void);
 
 LIBBPF_API struct btf *btf__load_from_kernel_by_id(__u32 id);
 LIBBPF_API struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf);
-LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_from_kernel_by_id instead")
-LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf);
 
-LIBBPF_DEPRECATED_SINCE(0, 6, "intended for internal libbpf use only")
-LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf);
-LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_into_kernel instead")
-LIBBPF_API int btf__load(struct btf *btf);
 LIBBPF_API int btf__load_into_kernel(struct btf *btf);
 LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
 				   const char *type_name);
 LIBBPF_API __s32 btf__find_by_name_kind(const struct btf *btf,
 					const char *type_name, __u32 kind);
-LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__type_cnt() instead; note that btf__get_nr_types() == btf__type_cnt() - 1")
-LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf);
 LIBBPF_API __u32 btf__type_cnt(const struct btf *btf);
 LIBBPF_API const struct btf *btf__base_btf(const struct btf *btf);
 LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf,
@@ -150,29 +141,10 @@ LIBBPF_API void btf__set_fd(struct btf *btf, int fd);
 LIBBPF_API const void *btf__raw_data(const struct btf *btf, __u32 *size);
 LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
 LIBBPF_API const char *btf__str_by_offset(const struct btf *btf, __u32 offset);
-LIBBPF_DEPRECATED_SINCE(0, 7, "this API is not necessary when BTF-defined maps are used")
-LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
-				    __u32 expected_key_size,
-				    __u32 expected_value_size,
-				    __u32 *key_type_id, __u32 *value_type_id);
 
 LIBBPF_API struct btf_ext *btf_ext__new(const __u8 *data, __u32 size);
 LIBBPF_API void btf_ext__free(struct btf_ext *btf_ext);
 LIBBPF_API const void *btf_ext__raw_data(const struct btf_ext *btf_ext, __u32 *size);
-LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_func_info was never meant as a public API and has wrong assumptions embedded in it; it will be removed in the future libbpf versions")
-int btf_ext__reloc_func_info(const struct btf *btf,
-			     const struct btf_ext *btf_ext,
-			     const char *sec_name, __u32 insns_cnt,
-			     void **func_info, __u32 *cnt);
-LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_line_info was never meant as a public API and has wrong assumptions embedded in it; it will be removed in the future libbpf versions")
-int btf_ext__reloc_line_info(const struct btf *btf,
-			     const struct btf_ext *btf_ext,
-			     const char *sec_name, __u32 insns_cnt,
-			     void **line_info, __u32 *cnt);
-LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_func_info is deprecated; write custom func_info parsing to fetch rec_size")
-__u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext);
-LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_line_info is deprecated; write custom line_info parsing to fetch rec_size")
-__u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext);
 
 LIBBPF_API int btf__find_str(struct btf *btf, const char *s);
 LIBBPF_API int btf__add_str(struct btf *btf, const char *s);
@@ -215,6 +187,8 @@ LIBBPF_API int btf__add_field(struct btf *btf, const char *name, int field_type_
 /* enum construction APIs */
 LIBBPF_API int btf__add_enum(struct btf *btf, const char *name, __u32 bytes_sz);
 LIBBPF_API int btf__add_enum_value(struct btf *btf, const char *name, __s64 value);
+LIBBPF_API int btf__add_enum64(struct btf *btf, const char *name, __u32 bytes_sz, bool is_signed);
+LIBBPF_API int btf__add_enum64_value(struct btf *btf, const char *name, __u64 value);
 
 enum btf_fwd_kind {
 	BTF_FWD_STRUCT = 0,
@@ -257,22 +231,12 @@ struct btf_dedup_opts {
 
 LIBBPF_API int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts);
 
-LIBBPF_API int btf__dedup_v0_6_0(struct btf *btf, const struct btf_dedup_opts *opts);
-
-LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__dedup() instead")
-LIBBPF_API int btf__dedup_deprecated(struct btf *btf, struct btf_ext *btf_ext, const void *opts);
-#define btf__dedup(...) ___libbpf_overload(___btf_dedup, __VA_ARGS__)
-#define ___btf_dedup3(btf, btf_ext, opts) btf__dedup_deprecated(btf, btf_ext, opts)
-#define ___btf_dedup2(btf, opts) btf__dedup(btf, opts)
-
 struct btf_dump;
 
 struct btf_dump_opts {
-	union {
 	size_t sz;
-		void *ctx; /* DEPRECATED: will be gone in v1.0 */
-	};
 };
+#define btf_dump_opts__last_field sz
 
 typedef void (*btf_dump_printf_fn_t)(void *ctx, const char *fmt, va_list args);
 
@@ -281,51 +245,6 @@ LIBBPF_API struct btf_dump *btf_dump__new(const struct btf *btf,
 					  void *ctx,
 					  const struct btf_dump_opts *opts);
 
-LIBBPF_API struct btf_dump *btf_dump__new_v0_6_0(const struct btf *btf,
-						 btf_dump_printf_fn_t printf_fn,
-						 void *ctx,
-						 const struct btf_dump_opts *opts);
-
-LIBBPF_API struct btf_dump *btf_dump__new_deprecated(const struct btf *btf,
-						     const struct btf_ext *btf_ext,
-						     const struct btf_dump_opts *opts,
-						     btf_dump_printf_fn_t printf_fn);
-
-/* Choose either btf_dump__new() or btf_dump__new_deprecated() based on the
- * type of 4th argument. If it's btf_dump's print callback, use deprecated
- * API; otherwise, choose the new btf_dump__new(). ___libbpf_override()
- * doesn't work here because both variants have 4 input arguments.
- *
- * (void *) casts are necessary to avoid compilation warnings about type
- * mismatches, because even though __builtin_choose_expr() only ever evaluates
- * one side the other side still has to satisfy type constraints (this is
- * compiler implementation limitation which might be lifted eventually,
- * according to the documentation). So passing struct btf_ext in place of
- * btf_dump_printf_fn_t would be generating compilation warning.  Casting to
- * void * avoids this issue.
- *
- * Also, two type compatibility checks for a function and function pointer are
- * required because passing function reference into btf_dump__new() as
- * btf_dump__new(..., my_callback, ...) and as btf_dump__new(...,
- * &my_callback, ...) (not explicit ampersand in the latter case) actually
- * differs as far as __builtin_types_compatible_p() is concerned. Thus two
- * checks are combined to detect callback argument.
- *
- * The rest works just like in case of ___libbpf_override() usage with symbol
- * versioning.
- *
- * C++ compilers don't support __builtin_types_compatible_p(), so at least
- * don't screw up compilation for them and let C++ users pick btf_dump__new
- * vs btf_dump__new_deprecated explicitly.
- */
-#ifndef __cplusplus
-#define btf_dump__new(a1, a2, a3, a4) __builtin_choose_expr(				\
-	__builtin_types_compatible_p(typeof(a4), btf_dump_printf_fn_t) ||		\
-	__builtin_types_compatible_p(typeof(a4), void(void *, const char *, va_list)),	\
-	btf_dump__new_deprecated((void *)a1, (void *)a2, (void *)a3, (void *)a4),	\
-	btf_dump__new((void *)a1, (void *)a2, (void *)a3, (void *)a4))
-#endif
-
 LIBBPF_API void btf_dump__free(struct btf_dump *d);
 
 LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id);
@@ -393,9 +312,10 @@ btf_dump__dump_type_data(struct btf_dump *d, __u32 id,
 #ifndef BTF_KIND_FLOAT
 #define BTF_KIND_FLOAT		16	/* Floating point	*/
 #endif
-/* The kernel header switched to enums, so these two were never #defined */
+/* The kernel header switched to enums, so the following were never #defined */
 #define BTF_KIND_DECL_TAG	17	/* Decl Tag */
 #define BTF_KIND_TYPE_TAG	18	/* Type Tag */
+#define BTF_KIND_ENUM64		19	/* Enum for up-to 64bit values */
 
 static inline __u16 btf_kind(const struct btf_type *t)
 {
@@ -454,6 +374,11 @@ static inline bool btf_is_enum(const struct btf_type *t)
 	return btf_kind(t) == BTF_KIND_ENUM;
 }
 
+static inline bool btf_is_enum64(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_ENUM64;
+}
+
 static inline bool btf_is_fwd(const struct btf_type *t)
 {
 	return btf_kind(t) == BTF_KIND_FWD;
@@ -524,6 +449,18 @@ static inline bool btf_is_type_tag(const struct btf_type *t)
 	return btf_kind(t) == BTF_KIND_TYPE_TAG;
 }
 
+static inline bool btf_is_any_enum(const struct btf_type *t)
+{
+	return btf_is_enum(t) || btf_is_enum64(t);
+}
+
+static inline bool btf_kind_core_compat(const struct btf_type *t1,
+					const struct btf_type *t2)
+{
+	return btf_kind(t1) == btf_kind(t2) ||
+	       (btf_is_any_enum(t1) && btf_is_any_enum(t2));
+}
+
 static inline __u8 btf_int_encoding(const struct btf_type *t)
 {
 	return BTF_INT_ENCODING(*(__u32 *)(t + 1));
@@ -549,6 +486,39 @@ static inline struct btf_enum *btf_enum(const struct btf_type *t)
 	return (struct btf_enum *)(t + 1);
 }
 
+struct btf_enum64;
+
+static inline struct btf_enum64 *btf_enum64(const struct btf_type *t)
+{
+	return (struct btf_enum64 *)(t + 1);
+}
+
+static inline __u64 btf_enum64_value(const struct btf_enum64 *e)
+{
+	/* struct btf_enum64 is introduced in Linux 6.0, which is very
+	 * bleeding-edge. Here we are avoiding relying on struct btf_enum64
+	 * definition coming from kernel UAPI headers to support wider range
+	 * of system-wide kernel headers.
+	 *
+	 * Given this header can be also included from C++ applications, that
+	 * further restricts C tricks we can use (like using compatible
+	 * anonymous struct). So just treat struct btf_enum64 as
+	 * a three-element array of u32 and access second (lo32) and third
+	 * (hi32) elements directly.
+	 *
+	 * For reference, here is a struct btf_enum64 definition:
+	 *
+	 * const struct btf_enum64 {
+	 *	__u32	name_off;
+	 *	__u32	val_lo32;
+	 *	__u32	val_hi32;
+	 * };
+	 */
+	const __u32 *e64 = (const __u32 *)e;
+
+	return ((__u64)e64[2] << 32) | e64[1];
+}
+
 static inline struct btf_member *btf_members(const struct btf_type *t)
 {
 	return (struct btf_member *)(t + 1);

src/btf_dump.c

@@ -13,6 +13,7 @@
 #include <ctype.h>
 #include <endian.h>
 #include <errno.h>
+#include <limits.h>
 #include <linux/err.h>
 #include <linux/btf.h>
 #include <linux/kernel.h>
@@ -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)
@@ -144,8 +145,7 @@ static void btf_dump_printf(const struct btf_dump *d, const char *fmt, ...)
 static int btf_dump_mark_referenced(struct btf_dump *d);
 static int btf_dump_resize(struct btf_dump *d);
 
-DEFAULT_VERSION(btf_dump__new_v0_6_0, btf_dump__new, LIBBPF_0.6.0)
-struct btf_dump *btf_dump__new_v0_6_0(const struct btf *btf,
+struct btf_dump *btf_dump__new(const struct btf *btf,
 			       btf_dump_printf_fn_t printf_fn,
 			       void *ctx,
 			       const struct btf_dump_opts *opts)
@@ -153,6 +153,9 @@ struct btf_dump *btf_dump__new_v0_6_0(const struct btf *btf,
 	struct btf_dump *d;
 	int err;
 
+	if (!OPTS_VALID(opts, btf_dump_opts))
+		return libbpf_err_ptr(-EINVAL);
+
 	if (!printf_fn)
 		return libbpf_err_ptr(-EINVAL);
 
@@ -188,17 +191,6 @@ err:
 	return libbpf_err_ptr(err);
 }
 
-COMPAT_VERSION(btf_dump__new_deprecated, btf_dump__new, LIBBPF_0.0.4)
-struct btf_dump *btf_dump__new_deprecated(const struct btf *btf,
-					  const struct btf_ext *btf_ext,
-					  const struct btf_dump_opts *opts,
-					  btf_dump_printf_fn_t printf_fn)
-{
-	if (!printf_fn)
-		return libbpf_err_ptr(-EINVAL);
-	return btf_dump__new_v0_6_0(btf, printf_fn, opts ? opts->ctx : NULL, opts);
-}
-
 static int btf_dump_resize(struct btf_dump *d)
 {
 	int err, last_id = btf__type_cnt(d->btf) - 1;
@@ -228,6 +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;
@@ -246,8 +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);
 }
@@ -318,6 +321,7 @@ static int btf_dump_mark_referenced(struct btf_dump *d)
 		switch (btf_kind(t)) {
 		case BTF_KIND_INT:
 		case BTF_KIND_ENUM:
+		case BTF_KIND_ENUM64:
 		case BTF_KIND_FWD:
 		case BTF_KIND_FLOAT:
 			break;
@@ -538,6 +542,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 		return 1;
 	}
 	case BTF_KIND_ENUM:
+	case BTF_KIND_ENUM64:
 	case BTF_KIND_FWD:
 		/*
 		 * non-anonymous or non-referenced enums are top-level
@@ -739,6 +744,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
 		tstate->emit_state = EMITTED;
 		break;
 	case BTF_KIND_ENUM:
+	case BTF_KIND_ENUM64:
 		if (top_level_def) {
 			btf_dump_emit_enum_def(d, id, t, 0);
 			btf_dump_printf(d, ";\n\n");
@@ -828,14 +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 */
@@ -844,8 +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
@@ -853,44 +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;
-
-	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;
-
-	while (off_diff > 0) {
+	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;
-		int pad_bits;
 
-		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);
+	if (cur_off >= next_off)
+		return; /* no gap */
+
+	/* 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;
+
+		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);
-		off_diff -= 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;
+		}
 	}
 }
 
@@ -910,9 +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 {",
@@ -922,37 +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));
+	} else {
+		btf_dump_printf(d, "}");
+	}
 	if (packed)
 		btf_dump_printf(d, " __attribute__((packed))");
 }
@@ -989,39 +1058,119 @@ static void btf_dump_emit_enum_fwd(struct btf_dump *d, __u32 id,
 	btf_dump_printf(d, "enum %s", btf_dump_type_name(d, id));
 }
 
-static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id,
+static void btf_dump_emit_enum32_val(struct btf_dump *d,
 				     const struct btf_type *t,
-				   int lvl)
+				     int lvl, __u16 vlen)
 {
 	const struct btf_enum *v = btf_enum(t);
-	__u16 vlen = btf_vlen(t);
+	bool is_signed = btf_kflag(t);
+	const char *fmt_str;
 	const char *name;
 	size_t dup_cnt;
 	int i;
 
-	btf_dump_printf(d, "enum%s%s",
-			t->name_off ? " " : "",
-			btf_dump_type_name(d, id));
-
-	if (vlen) {
-		btf_dump_printf(d, " {");
 	for (i = 0; i < vlen; i++, v++) {
 		name = btf_name_of(d, v->name_off);
 		/* enumerators share namespace with typedef idents */
 		dup_cnt = btf_dump_name_dups(d, d->ident_names, name);
 		if (dup_cnt > 1) {
-				btf_dump_printf(d, "\n%s%s___%zu = %u,",
-						pfx(lvl + 1), name, dup_cnt,
-						(__u32)v->val);
+			fmt_str = is_signed ? "\n%s%s___%zd = %d," : "\n%s%s___%zd = %u,";
+			btf_dump_printf(d, fmt_str, pfx(lvl + 1), name, dup_cnt, v->val);
 		} else {
-				btf_dump_printf(d, "\n%s%s = %u,",
+			fmt_str = is_signed ? "\n%s%s = %d," : "\n%s%s = %u,";
+			btf_dump_printf(d, fmt_str, pfx(lvl + 1), name, v->val);
+		}
+	}
+}
+
+static void btf_dump_emit_enum64_val(struct btf_dump *d,
+				     const struct btf_type *t,
+				     int lvl, __u16 vlen)
+{
+	const struct btf_enum64 *v = btf_enum64(t);
+	bool is_signed = btf_kflag(t);
+	const char *fmt_str;
+	const char *name;
+	size_t dup_cnt;
+	__u64 val;
+	int i;
+
+	for (i = 0; i < vlen; i++, v++) {
+		name = btf_name_of(d, v->name_off);
+		dup_cnt = btf_dump_name_dups(d, d->ident_names, name);
+		val = btf_enum64_value(v);
+		if (dup_cnt > 1) {
+			fmt_str = is_signed ? "\n%s%s___%zd = %lldLL,"
+					    : "\n%s%s___%zd = %lluULL,";
+			btf_dump_printf(d, fmt_str,
+					pfx(lvl + 1), name, dup_cnt,
+					(unsigned long long)val);
+		} else {
+			fmt_str = is_signed ? "\n%s%s = %lldLL,"
+					    : "\n%s%s = %lluULL,";
+			btf_dump_printf(d, fmt_str,
 					pfx(lvl + 1), name,
-						(__u32)v->val);
+					(unsigned long long)val);
 		}
 	}
+}
+static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id,
+				   const struct btf_type *t,
+				   int lvl)
+{
+	__u16 vlen = btf_vlen(t);
+
+	btf_dump_printf(d, "enum%s%s",
+			t->name_off ? " " : "",
+			btf_dump_type_name(d, id));
+
+	if (!vlen)
+		return;
+
+	btf_dump_printf(d, " {");
+	if (btf_is_enum(t))
+		btf_dump_emit_enum32_val(d, t, lvl, vlen);
+	else
+		btf_dump_emit_enum64_val(d, t, lvl, vlen);
 	btf_dump_printf(d, "\n%s}", pfx(lvl));
+
+	/* special case enums with special sizes */
+	if (t->size == 1) {
+		/* one-byte enums can be forced with mode(byte) attribute */
+		btf_dump_printf(d, " __attribute__((mode(byte)))");
+	} else if (t->size == 8 && d->ptr_sz == 8) {
+		/* enum can be 8-byte sized if one of the enumerator values
+		 * doesn't fit in 32-bit integer, or by adding mode(word)
+		 * attribute (but probably only on 64-bit architectures); do
+		 * our best here to try to satisfy the contract without adding
+		 * unnecessary attributes
+		 */
+		bool needs_word_mode;
+
+		if (btf_is_enum(t)) {
+			/* enum can't represent 64-bit values, so we need word mode */
+			needs_word_mode = true;
+		} else {
+			/* enum64 needs mode(word) if none of its values has
+			 * non-zero upper 32-bits (which means that all values
+			 * fit in 32-bit integers and won't cause compiler to
+			 * bump enum to be 64-bit naturally
+			 */
+			int i;
+
+			needs_word_mode = true;
+			for (i = 0; i < vlen; i++) {
+				if (btf_enum64(t)[i].val_hi32 != 0) {
+					needs_word_mode = false;
+					break;
 				}
 			}
+		}
+		if (needs_word_mode)
+			btf_dump_printf(d, " __attribute__((mode(word)))");
+	}
+
+}
 
 static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id,
 				  const struct btf_type *t)
@@ -1178,6 +1327,7 @@ skip_mod:
 			break;
 		case BTF_KIND_INT:
 		case BTF_KIND_ENUM:
+		case BTF_KIND_ENUM64:
 		case BTF_KIND_FWD:
 		case BTF_KIND_STRUCT:
 		case BTF_KIND_UNION:
@@ -1312,6 +1462,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 				btf_dump_emit_struct_fwd(d, id, t);
 			break;
 		case BTF_KIND_ENUM:
+		case BTF_KIND_ENUM64:
 			btf_dump_emit_mods(d, decls);
 			/* inline anonymous enum */
 			if (t->name_off == 0 && !d->skip_anon_defs)
@@ -1481,11 +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;
 }
@@ -1505,6 +1667,11 @@ static const char *btf_dump_resolve_name(struct btf_dump *d, __u32 id,
 	if (s->name_resolved)
 		return *cached_name ? *cached_name : orig_name;
 
+	if (btf_is_fwd(t) || (btf_is_enum(t) && btf_vlen(t) == 0)) {
+		s->name_resolved = 1;
+		return orig_name;
+	}
+
 	dup_cnt = btf_dump_name_dups(d, name_map, orig_name);
 	if (dup_cnt > 1) {
 		const size_t max_len = 256;
@@ -1919,7 +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
@@ -1983,7 +2150,8 @@ static int btf_dump_get_enum_value(struct btf_dump *d,
 				   __u32 id,
 				   __s64 *value)
 {
-	/* handle unaligned enum value */
+	bool is_signed = btf_kflag(t);
+
 	if (!ptr_is_aligned(d->btf, id, data)) {
 		__u64 val;
 		int err;
@@ -2000,13 +2168,13 @@ static int btf_dump_get_enum_value(struct btf_dump *d,
 		*value = *(__s64 *)data;
 		return 0;
 	case 4:
-		*value = *(__s32 *)data;
+		*value = is_signed ? (__s64)*(__s32 *)data : *(__u32 *)data;
 		return 0;
 	case 2:
-		*value = *(__s16 *)data;
+		*value = is_signed ? *(__s16 *)data : *(__u16 *)data;
 		return 0;
 	case 1:
-		*value = *(__s8 *)data;
+		*value = is_signed ? *(__s8 *)data : *(__u8 *)data;
 		return 0;
 	default:
 		pr_warn("unexpected size %d for enum, id:[%u]\n", t->size, id);
@@ -2019,7 +2187,7 @@ static int btf_dump_enum_data(struct btf_dump *d,
 			      __u32 id,
 			      const void *data)
 {
-	const struct btf_enum *e;
+	bool is_signed;
 	__s64 value;
 	int i, err;
 
@@ -2027,6 +2195,10 @@ static int btf_dump_enum_data(struct btf_dump *d,
 	if (err)
 		return err;
 
+	is_signed = btf_kflag(t);
+	if (btf_is_enum(t)) {
+		const struct btf_enum *e;
+
 		for (i = 0, e = btf_enum(t); i < btf_vlen(t); i++, e++) {
 			if (value != e->val)
 				continue;
@@ -2034,7 +2206,20 @@ static int btf_dump_enum_data(struct btf_dump *d,
 			return 0;
 		}
 
-	btf_dump_type_values(d, "%d", value);
+		btf_dump_type_values(d, is_signed ? "%d" : "%u", value);
+	} else {
+		const struct btf_enum64 *e;
+
+		for (i = 0, e = btf_enum64(t); i < btf_vlen(t); i++, e++) {
+			if (value != btf_enum64_value(e))
+				continue;
+			btf_dump_type_values(d, "%s", btf_name_of(d, e->name_off));
+			return 0;
+		}
+
+		btf_dump_type_values(d, is_signed ? "%lldLL" : "%lluULL",
+				     (unsigned long long)value);
+	}
 	return 0;
 }
 
@@ -2094,6 +2279,7 @@ static int btf_dump_type_data_check_overflow(struct btf_dump *d,
 	case BTF_KIND_FLOAT:
 	case BTF_KIND_PTR:
 	case BTF_KIND_ENUM:
+	case BTF_KIND_ENUM64:
 		if (data + bits_offset / 8 + size > d->typed_dump->data_end)
 			return -E2BIG;
 		break;
@@ -2198,6 +2384,7 @@ static int btf_dump_type_data_check_zero(struct btf_dump *d,
 		return -ENODATA;
 	}
 	case BTF_KIND_ENUM:
+	case BTF_KIND_ENUM64:
 		err = btf_dump_get_enum_value(d, t, data, id, &value);
 		if (err)
 			return err;
@@ -2270,6 +2457,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d,
 		err = btf_dump_struct_data(d, t, id, data);
 		break;
 	case BTF_KIND_ENUM:
+	case BTF_KIND_ENUM64:
 		/* handle bitfield and int enum values */
 		if (bit_sz) {
 			__u64 print_num;
@@ -2320,7 +2508,7 @@ int btf_dump__dump_type_data(struct btf_dump *d, __u32 id,
 	d->typed_dump->indent_lvl = OPTS_GET(opts, indent_level, 0);
 
 	/* default indent string is a tab */
-	if (!opts->indent_str)
+	if (!OPTS_GET(opts, indent_str, NULL))
 		d->typed_dump->indent_str[0] = '\t';
 	else
 		libbpf_strlcpy(d->typed_dump->indent_str, opts->indent_str,

src/gen_loader.c

@@ -533,7 +533,7 @@ void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *attach_name,
 	gen->attach_kind = kind;
 	ret = snprintf(gen->attach_target, sizeof(gen->attach_target), "%s%s",
 		       prefix, attach_name);
-	if (ret == sizeof(gen->attach_target))
+	if (ret >= sizeof(gen->attach_target))
 		gen->error = -ENOSPC;
 }
 
@@ -1043,18 +1043,27 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue,
 	value = add_data(gen, pvalue, value_size);
 	key = add_data(gen, &zero, sizeof(zero));
 
-	/* if (map_desc[map_idx].initial_value)
-	 *    copy_from_user(value, initial_value, value_size);
+	/* if (map_desc[map_idx].initial_value) {
+	 *    if (ctx->flags & BPF_SKEL_KERNEL)
+	 *        bpf_probe_read_kernel(value, value_size, initial_value);
+	 *    else
+	 *        bpf_copy_from_user(value, value_size, initial_value);
+	 * }
 	 */
 	emit(gen, BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_6,
 			      sizeof(struct bpf_loader_ctx) +
 			      sizeof(struct bpf_map_desc) * map_idx +
 			      offsetof(struct bpf_map_desc, initial_value)));
-	emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0, 4));
+	emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0, 8));
 	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
 					 0, 0, 0, value));
 	emit(gen, BPF_MOV64_IMM(BPF_REG_2, value_size));
+	emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6,
+			      offsetof(struct bpf_loader_ctx, flags)));
+	emit(gen, BPF_JMP_IMM(BPF_JSET, BPF_REG_0, BPF_SKEL_KERNEL, 2));
 	emit(gen, BPF_EMIT_CALL(BPF_FUNC_copy_from_user));
+	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 1));
+	emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel));
 
 	map_update_attr = add_data(gen, &attr, attr_size);
 	move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4,

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,
+int hashmap_insert(struct hashmap *map, long key, long value,
 		   enum hashmap_insert_strategy strategy,
-		    const void **old_key, void **old_value)
+		   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,
+int hashmap_insert(struct hashmap *map, long key, long value,
 		   enum hashmap_insert_strategy strategy,
-		    const void **old_key, void **old_value);
+		   long *old_key, long *old_value);
 
-static inline int hashmap__add(struct hashmap *map,
-			       const void *key, void *value)
-{
-	return hashmap__insert(map, key, value, HASHMAP_ADD, NULL, NULL);
-}
+#define hashmap__insert(map, key, value, strategy, old_key, old_value) \
+	hashmap_insert((map), (long)(key), (long)(value), (strategy),  \
+		       hashmap_cast_ptr(old_key),		       \
+		       hashmap_cast_ptr(old_value))
 
-static inline int hashmap__set(struct hashmap *map,
-			       const void *key, void *value,
-			       const void **old_key, void **old_value)
-{
-	return hashmap__insert(map, key, value, HASHMAP_SET,
-			       old_key, old_value);
-}
+#define hashmap__add(map, key, value) \
+	hashmap__insert((map), (key), (value), HASHMAP_ADD, NULL, NULL)
 
-static inline int hashmap__update(struct hashmap *map,
-				  const void *key, void *value,
-				  const void **old_key, void **old_value)
-{
-	return hashmap__insert(map, key, value, HASHMAP_UPDATE,
-			       old_key, old_value);
-}
+#define hashmap__set(map, key, value, old_key, old_value) \
+	hashmap__insert((map), (key), (value), HASHMAP_SET, (old_key), (old_value))
 
-static inline int hashmap__append(struct hashmap *map,
-				  const void *key, void *value)
-{
-	return hashmap__insert(map, key, value, HASHMAP_APPEND, NULL, NULL);
-}
+#define hashmap__update(map, key, value, old_key, old_value) \
+	hashmap__insert((map), (key), (value), HASHMAP_UPDATE, (old_key), (old_value))
 
-bool hashmap__delete(struct hashmap *map, const void *key,
-		     const void **old_key, void **old_value);
+#define hashmap__append(map, key, value) \
+	hashmap__insert((map), (key), (value), HASHMAP_APPEND, NULL, NULL)
 
-bool hashmap__find(const struct hashmap *map, const void *key, void **value);
+bool hashmap_delete(struct hashmap *map, long key, long *old_key, long *old_value);
+
+#define hashmap__delete(map, key, old_key, old_value)		       \
+	hashmap_delete((map), (long)(key),			       \
+		       hashmap_cast_ptr(old_key),		       \
+		       hashmap_cast_ptr(old_value))
+
+bool hashmap_find(const struct hashmap *map, long key, long *value);
+
+#define hashmap__find(map, key, value) \
+	hashmap_find((map), (long)(key), hashmap_cast_ptr(value))
 
 /*
  * hashmap__for_each_entry - iterate over all entries in hashmap

src/libbpf.map

@@ -1,29 +1,14 @@
 LIBBPF_0.0.1 {
 	global:
 		bpf_btf_get_fd_by_id;
-		bpf_create_map;
-		bpf_create_map_in_map;
-		bpf_create_map_in_map_node;
-		bpf_create_map_name;
-		bpf_create_map_node;
-		bpf_create_map_xattr;
-		bpf_load_btf;
-		bpf_load_program;
-		bpf_load_program_xattr;
 		bpf_map__btf_key_type_id;
 		bpf_map__btf_value_type_id;
-		bpf_map__def;
 		bpf_map__fd;
-		bpf_map__is_offload_neutral;
 		bpf_map__name;
-		bpf_map__next;
 		bpf_map__pin;
-		bpf_map__prev;
-		bpf_map__priv;
 		bpf_map__reuse_fd;
 		bpf_map__set_ifindex;
 		bpf_map__set_inner_map_fd;
-		bpf_map__set_priv;
 		bpf_map__unpin;
 		bpf_map_delete_elem;
 		bpf_map_get_fd_by_id;
@@ -38,79 +23,37 @@ LIBBPF_0.0.1 {
 		bpf_object__btf_fd;
 		bpf_object__close;
 		bpf_object__find_map_by_name;
-		bpf_object__find_map_by_offset;
-		bpf_object__find_program_by_title;
 		bpf_object__kversion;
 		bpf_object__load;
 		bpf_object__name;
-		bpf_object__next;
 		bpf_object__open;
-		bpf_object__open_buffer;
-		bpf_object__open_xattr;
 		bpf_object__pin;
 		bpf_object__pin_maps;
 		bpf_object__pin_programs;
-		bpf_object__priv;
-		bpf_object__set_priv;
-		bpf_object__unload;
 		bpf_object__unpin_maps;
 		bpf_object__unpin_programs;
-		bpf_perf_event_read_simple;
 		bpf_prog_attach;
 		bpf_prog_detach;
 		bpf_prog_detach2;
 		bpf_prog_get_fd_by_id;
 		bpf_prog_get_next_id;
-		bpf_prog_load;
-		bpf_prog_load_xattr;
 		bpf_prog_query;
-		bpf_prog_test_run;
-		bpf_prog_test_run_xattr;
 		bpf_program__fd;
-		bpf_program__is_kprobe;
-		bpf_program__is_perf_event;
-		bpf_program__is_raw_tracepoint;
-		bpf_program__is_sched_act;
-		bpf_program__is_sched_cls;
-		bpf_program__is_socket_filter;
-		bpf_program__is_tracepoint;
-		bpf_program__is_xdp;
-		bpf_program__load;
-		bpf_program__next;
-		bpf_program__nth_fd;
 		bpf_program__pin;
-		bpf_program__pin_instance;
-		bpf_program__prev;
-		bpf_program__priv;
 		bpf_program__set_expected_attach_type;
 		bpf_program__set_ifindex;
-		bpf_program__set_kprobe;
-		bpf_program__set_perf_event;
-		bpf_program__set_prep;
-		bpf_program__set_priv;
-		bpf_program__set_raw_tracepoint;
-		bpf_program__set_sched_act;
-		bpf_program__set_sched_cls;
-		bpf_program__set_socket_filter;
-		bpf_program__set_tracepoint;
 		bpf_program__set_type;
-		bpf_program__set_xdp;
-		bpf_program__title;
 		bpf_program__unload;
 		bpf_program__unpin;
-		bpf_program__unpin_instance;
 		bpf_prog_linfo__free;
 		bpf_prog_linfo__new;
 		bpf_prog_linfo__lfind_addr_func;
 		bpf_prog_linfo__lfind;
 		bpf_raw_tracepoint_open;
-		bpf_set_link_xdp_fd;
 		bpf_task_fd_query;
-		bpf_verify_program;
 		btf__fd;
 		btf__find_by_name;
 		btf__free;
-		btf__get_from_id;
 		btf__name_by_offset;
 		btf__new;
 		btf__resolve_size;
@@ -127,48 +70,24 @@ LIBBPF_0.0.1 {
 
 LIBBPF_0.0.2 {
 	global:
-		bpf_probe_helper;
-		bpf_probe_map_type;
-		bpf_probe_prog_type;
-		bpf_map__resize;
 		bpf_map_lookup_elem_flags;
 		bpf_object__btf;
 		bpf_object__find_map_fd_by_name;
-		bpf_get_link_xdp_id;
-		btf__dedup;
-		btf__get_map_kv_tids;
-		btf__get_nr_types;
 		btf__get_raw_data;
-		btf__load;
 		btf_ext__free;
-		btf_ext__func_info_rec_size;
 		btf_ext__get_raw_data;
-		btf_ext__line_info_rec_size;
 		btf_ext__new;
-		btf_ext__reloc_func_info;
-		btf_ext__reloc_line_info;
-		xsk_umem__create;
-		xsk_socket__create;
-		xsk_umem__delete;
-		xsk_socket__delete;
-		xsk_umem__fd;
-		xsk_socket__fd;
-		bpf_program__get_prog_info_linear;
-		bpf_program__bpil_addr_to_offs;
-		bpf_program__bpil_offs_to_addr;
 } LIBBPF_0.0.1;
 
 LIBBPF_0.0.3 {
 	global:
 		bpf_map__is_internal;
 		bpf_map_freeze;
-		btf__finalize_data;
 } LIBBPF_0.0.2;
 
 LIBBPF_0.0.4 {
 	global:
 		bpf_link__destroy;
-		bpf_object__load_xattr;
 		bpf_program__attach_kprobe;
 		bpf_program__attach_perf_event;
 		bpf_program__attach_raw_tracepoint;
@@ -176,14 +95,10 @@ LIBBPF_0.0.4 {
 		bpf_program__attach_uprobe;
 		btf_dump__dump_type;
 		btf_dump__free;
-		btf_dump__new;
 		btf__parse_elf;
 		libbpf_num_possible_cpus;
 		perf_buffer__free;
-		perf_buffer__new;
-		perf_buffer__new_raw;
 		perf_buffer__poll;
-		xsk_umem__create;
 } LIBBPF_0.0.3;
 
 LIBBPF_0.0.5 {
@@ -193,7 +108,6 @@ LIBBPF_0.0.5 {
 
 LIBBPF_0.0.6 {
 	global:
-		bpf_get_link_xdp_info;
 		bpf_map__get_pin_path;
 		bpf_map__is_pinned;
 		bpf_map__set_pin_path;
@@ -202,9 +116,6 @@ LIBBPF_0.0.6 {
 		bpf_program__attach_trace;
 		bpf_program__get_expected_attach_type;
 		bpf_program__get_type;
-		bpf_program__is_tracing;
-		bpf_program__set_tracing;
-		bpf_program__size;
 		btf__find_by_name_kind;
 		libbpf_find_vmlinux_btf_id;
 } LIBBPF_0.0.5;
@@ -224,14 +135,8 @@ LIBBPF_0.0.7 {
 		bpf_object__detach_skeleton;
 		bpf_object__load_skeleton;
 		bpf_object__open_skeleton;
-		bpf_probe_large_insn_limit;
-		bpf_prog_attach_xattr;
 		bpf_program__attach;
 		bpf_program__name;
-		bpf_program__is_extension;
-		bpf_program__is_struct_ops;
-		bpf_program__set_extension;
-		bpf_program__set_struct_ops;
 		btf__align_of;
 		libbpf_find_kernel_btf;
 } LIBBPF_0.0.6;
@@ -250,10 +155,7 @@ LIBBPF_0.0.8 {
 		bpf_prog_attach_opts;
 		bpf_program__attach_cgroup;
 		bpf_program__attach_lsm;
-		bpf_program__is_lsm;
 		bpf_program__set_attach_target;
-		bpf_program__set_lsm;
-		bpf_set_link_xdp_fd_opts;
 } LIBBPF_0.0.7;
 
 LIBBPF_0.0.9 {
@@ -291,9 +193,7 @@ LIBBPF_0.1.0 {
 		bpf_map__value_size;
 		bpf_program__attach_xdp;
 		bpf_program__autoload;
-		bpf_program__is_sk_lookup;
 		bpf_program__set_autoload;
-		bpf_program__set_sk_lookup;
 		btf__parse;
 		btf__parse_raw;
 		btf__pointer_size;
@@ -336,7 +236,6 @@ LIBBPF_0.2.0 {
 		perf_buffer__buffer_fd;
 		perf_buffer__epoll_fd;
 		perf_buffer__consume_buffer;
-		xsk_socket__create_shared;
 } LIBBPF_0.1.0;
 
 LIBBPF_0.3.0 {
@@ -348,8 +247,6 @@ LIBBPF_0.3.0 {
 		btf__new_empty_split;
 		btf__new_split;
 		ring_buffer__epoll_fd;
-		xsk_setup_xdp_prog;
-		xsk_socket__update_xskmap;
 } LIBBPF_0.2.0;
 
 LIBBPF_0.4.0 {
@@ -397,7 +294,6 @@ LIBBPF_0.6.0 {
 		bpf_object__next_program;
 		bpf_object__prev_map;
 		bpf_object__prev_program;
-		bpf_prog_load_deprecated;
 		bpf_prog_load;
 		bpf_program__flags;
 		bpf_program__insn_cnt;
@@ -407,18 +303,14 @@ LIBBPF_0.6.0 {
 		btf__add_decl_tag;
 		btf__add_type_tag;
 		btf__dedup;
-		btf__dedup_deprecated;
 		btf__raw_data;
 		btf__type_cnt;
 		btf_dump__new;
-		btf_dump__new_deprecated;
 		libbpf_major_version;
 		libbpf_minor_version;
 		libbpf_version_string;
 		perf_buffer__new;
-		perf_buffer__new_deprecated;
 		perf_buffer__new_raw;
-		perf_buffer__new_raw_deprecated;
 } LIBBPF_0.5.0;
 
 LIBBPF_0.7.0 {
@@ -434,8 +326,59 @@ LIBBPF_0.7.0 {
 		bpf_xdp_detach;
 		bpf_xdp_query;
 		bpf_xdp_query_id;
+		btf_ext__raw_data;
 		libbpf_probe_bpf_helper;
 		libbpf_probe_bpf_map_type;
 		libbpf_probe_bpf_prog_type;
-		libbpf_set_memlock_rlim_max;
+		libbpf_set_memlock_rlim;
 } LIBBPF_0.6.0;
+
+LIBBPF_0.8.0 {
+	global:
+		bpf_map__autocreate;
+		bpf_map__get_next_key;
+		bpf_map__delete_elem;
+		bpf_map__lookup_and_delete_elem;
+		bpf_map__lookup_elem;
+		bpf_map__set_autocreate;
+		bpf_map__update_elem;
+		bpf_map_delete_elem_flags;
+		bpf_object__destroy_subskeleton;
+		bpf_object__open_subskeleton;
+		bpf_program__attach_kprobe_multi_opts;
+		bpf_program__attach_trace_opts;
+		bpf_program__attach_usdt;
+		bpf_program__set_insns;
+		libbpf_register_prog_handler;
+		libbpf_unregister_prog_handler;
+} LIBBPF_0.7.0;
+
+LIBBPF_1.0.0 {
+	global:
+		bpf_obj_get_opts;
+		bpf_prog_query_opts;
+		bpf_program__attach_ksyscall;
+		bpf_program__autoattach;
+		bpf_program__set_autoattach;
+		btf__add_enum64;
+		btf__add_enum64_value;
+		libbpf_bpf_attach_type_str;
+		libbpf_bpf_link_type_str;
+		libbpf_bpf_map_type_str;
+		libbpf_bpf_prog_type_str;
+		perf_buffer__buffer;
+} LIBBPF_0.8.0;
+
+LIBBPF_1.1.0 {
+	global:
+		bpf_btf_get_fd_by_id_opts;
+		bpf_link_get_fd_by_id_opts;
+		bpf_map_get_fd_by_id_opts;
+		bpf_prog_get_fd_by_id_opts;
+		user_ring_buffer__discard;
+		user_ring_buffer__free;
+		user_ring_buffer__new;
+		user_ring_buffer__reserve;
+		user_ring_buffer__reserve_blocking;
+		user_ring_buffer__submit;
+} LIBBPF_1.0.0;

src/libbpf_common.h

@@ -30,20 +30,10 @@
 /* Add checks for other versions below when planning deprecation of API symbols
  * with the LIBBPF_DEPRECATED_SINCE macro.
  */
-#if __LIBBPF_CURRENT_VERSION_GEQ(0, 6)
-#define __LIBBPF_MARK_DEPRECATED_0_6(X) X
+#if __LIBBPF_CURRENT_VERSION_GEQ(1, 0)
+#define __LIBBPF_MARK_DEPRECATED_1_0(X) X
 #else
-#define __LIBBPF_MARK_DEPRECATED_0_6(X)
-#endif
-#if __LIBBPF_CURRENT_VERSION_GEQ(0, 7)
-#define __LIBBPF_MARK_DEPRECATED_0_7(X) X
-#else
-#define __LIBBPF_MARK_DEPRECATED_0_7(X)
-#endif
-#if __LIBBPF_CURRENT_VERSION_GEQ(0, 8)
-#define __LIBBPF_MARK_DEPRECATED_0_8(X) X
-#else
-#define __LIBBPF_MARK_DEPRECATED_0_8(X)
+#define __LIBBPF_MARK_DEPRECATED_1_0(X)
 #endif
 
 /* This set of internal macros allows to do "function overloading" based on

src/libbpf_errno.c

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

src/libbpf_internal.h

@@ -15,7 +15,6 @@
 #include <linux/err.h>
 #include <fcntl.h>
 #include <unistd.h>
-#include "libbpf_legacy.h"
 #include "relo_core.h"
 
 /* make sure libbpf doesn't use kernel-only integer typedefs */
@@ -103,6 +102,17 @@
 #define str_has_pfx(str, pfx) \
 	(strncmp(str, pfx, __builtin_constant_p(pfx) ? sizeof(pfx) - 1 : strlen(pfx)) == 0)
 
+/* suffix check */
+static inline bool str_has_sfx(const char *str, const char *sfx)
+{
+	size_t str_len = strlen(str);
+	size_t sfx_len = strlen(sfx);
+
+	if (sfx_len > str_len)
+		return false;
+	return strcmp(str + str_len - sfx_len, sfx) == 0;
+}
+
 /* Symbol versioning is different between static and shared library.
  * Properly versioned symbols are needed for shared library, but
  * only the symbol of the new version is needed for static library.
@@ -148,6 +158,15 @@ do {				\
 #ifndef __has_builtin
 #define __has_builtin(x) 0
 #endif
+
+struct bpf_link {
+	int (*detach)(struct bpf_link *link);
+	void (*dealloc)(struct bpf_link *link);
+	char *pin_path;		/* NULL, if not pinned */
+	int fd;			/* hook FD, -1 if not applicable */
+	bool disconnected;
+};
+
 /*
  * Re-implement glibc's reallocarray() for libbpf internal-only use.
  * reallocarray(), unfortunately, is not available in all versions of glibc,
@@ -329,6 +348,12 @@ enum kern_feature_id {
 	FEAT_BTF_TYPE_TAG,
 	/* memcg-based accounting for BPF maps and progs */
 	FEAT_MEMCG_ACCOUNT,
+	/* BPF cookie (bpf_get_attach_cookie() BPF helper) support */
+	FEAT_BPF_COOKIE,
+	/* BTF_KIND_ENUM64 support and BTF_KIND_ENUM kflag support */
+	FEAT_BTF_ENUM64,
+	/* Kernel uses syscall wrapper (CONFIG_ARCH_HAS_SYSCALL_WRAPPER) */
+	FEAT_SYSCALL_WRAPPER,
 	__FEAT_CNT,
 };
 
@@ -354,6 +379,13 @@ struct btf_ext_info {
 	void *info;
 	__u32 rec_size;
 	__u32 len;
+	/* optional (maintained internally by libbpf) mapping between .BTF.ext
+	 * section and corresponding ELF section. This is used to join
+	 * information like CO-RE relocation records with corresponding BPF
+	 * programs defined in ELF sections
+	 */
+	__u32 *sec_idxs;
+	int sec_cnt;
 };
 
 #define for_each_btf_ext_sec(seg, sec)					\
@@ -447,7 +479,10 @@ int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void
 __s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name,
 				 __u32 kind);
 
-extern enum libbpf_strict_mode libbpf_mode;
+typedef int (*kallsyms_cb_t)(unsigned long long sym_addr, char sym_type,
+			     const char *sym_name, void *ctx);
+
+int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *arg);
 
 /* handle direct returned errors */
 static inline int libbpf_err(int ret)
@@ -462,12 +497,8 @@ static inline int libbpf_err(int ret)
  */
 static inline int libbpf_err_errno(int ret)
 {
-	if (libbpf_mode & LIBBPF_STRICT_DIRECT_ERRS)
 	/* errno is already assumed to be set on error */
 	return ret < 0 ? -errno : ret;
-
-	/* legacy: on error return -1 directly and don't touch errno */
-	return ret;
 }
 
 /* handle error for pointer-returning APIs, err is assumed to be < 0 always */
@@ -475,12 +506,7 @@ static inline void *libbpf_err_ptr(int err)
 {
 	/* set errno on error, this doesn't break anything */
 	errno = -err;
-
-	if (libbpf_mode & LIBBPF_STRICT_CLEAN_PTRS)
 	return NULL;
-
-	/* legacy: encode err as ptr */
-	return ERR_PTR(err);
 }
 
 /* handle pointer-returning APIs' error handling */
@@ -490,11 +516,7 @@ static inline void *libbpf_ptr(void *ret)
 	if (IS_ERR(ret))
 		errno = -PTR_ERR(ret);
 
-	if (libbpf_mode & LIBBPF_STRICT_CLEAN_PTRS)
 	return IS_ERR(ret) ? NULL : ret;
-
-	/* legacy: pass-through original pointer */
-	return ret;
 }
 
 static inline bool str_is_empty(const char *s)
@@ -529,4 +551,29 @@ static inline int ensure_good_fd(int fd)
 	return fd;
 }
 
+/* The following two functions are exposed to bpftool */
+int bpf_core_add_cands(struct bpf_core_cand *local_cand,
+		       size_t local_essent_len,
+		       const struct btf *targ_btf,
+		       const char *targ_btf_name,
+		       int targ_start_id,
+		       struct bpf_core_cand_list *cands);
+void bpf_core_free_cands(struct bpf_core_cand_list *cands);
+
+struct usdt_manager *usdt_manager_new(struct bpf_object *obj);
+void usdt_manager_free(struct usdt_manager *man);
+struct bpf_link * usdt_manager_attach_usdt(struct usdt_manager *man,
+					   const struct bpf_program *prog,
+					   pid_t pid, const char *path,
+					   const char *usdt_provider, const char *usdt_name,
+					   __u64 usdt_cookie);
+
+static inline bool is_pow_of_2(size_t x)
+{
+	return x && (x & (x - 1)) == 0;
+}
+
+#define PROG_LOAD_ATTEMPTS 5
+int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts);
+
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */

src/libbpf_legacy.h

@@ -20,6 +20,11 @@
 extern "C" {
 #endif
 
+/* As of libbpf 1.0 libbpf_set_strict_mode() and enum libbpf_struct_mode have
+ * no effect. But they are left in libbpf_legacy.h so that applications that
+ * prepared for libbpf 1.0 before final release by using
+ * libbpf_set_strict_mode() still work with libbpf 1.0+ without any changes.
+ */
 enum libbpf_strict_mode {
 	/* Turn on all supported strict features of libbpf to simulate libbpf
 	 * v1.0 behavior.
@@ -54,6 +59,10 @@ enum libbpf_strict_mode {
 	 *
 	 * Note, in this mode the program pin path will be based on the
 	 * function name instead of section name.
+	 *
+	 * Additionally, routines in the .text section are always considered
+	 * sub-programs. Legacy behavior allows for a single routine in .text
+	 * to be a program.
 	 */
 	LIBBPF_STRICT_SEC_NAME = 0x04,
 	/*
@@ -67,8 +76,8 @@ enum libbpf_strict_mode {
 	 * first BPF program or map creation operation. This is done only if
 	 * kernel is too old to support memcg-based memory accounting for BPF
 	 * subsystem. By default, RLIMIT_MEMLOCK limit is set to RLIM_INFINITY,
-	 * but it can be overriden with libbpf_set_memlock_rlim_max() API.
-	 * Note that libbpf_set_memlock_rlim_max() needs to be called before
+	 * but it can be overriden with libbpf_set_memlock_rlim() API.
+	 * Note that libbpf_set_memlock_rlim() needs to be called before
 	 * the very first bpf_prog_load(), bpf_map_create() or bpf_object__load()
 	 * operation.
 	 */
@@ -84,6 +93,25 @@ enum libbpf_strict_mode {
 
 LIBBPF_API int libbpf_set_strict_mode(enum libbpf_strict_mode mode);
 
+/**
+ * @brief **libbpf_get_error()** extracts the error code from the passed
+ * pointer
+ * @param ptr pointer returned from libbpf API function
+ * @return error code; or 0 if no error occured
+ *
+ * Note, as of libbpf 1.0 this function is not necessary and not recommended
+ * to be used. Libbpf doesn't return error code embedded into the pointer
+ * itself. Instead, NULL is returned on error and error code is passed through
+ * thread-local errno variable. **libbpf_get_error()** is just returning -errno
+ * value if it receives NULL, which is correct only if errno hasn't been
+ * modified between libbpf API call and corresponding **libbpf_get_error()**
+ * call. Prefer to check return for NULL and use errno directly.
+ *
+ * This API is left in libbpf 1.0 to allow applications that were 1.0-ready
+ * before final libbpf 1.0 without needing to change them.
+ */
+LIBBPF_API long libbpf_get_error(const void *ptr);
+
 #define DECLARE_LIBBPF_OPTS LIBBPF_OPTS
 
 /* "Discouraged" APIs which don't follow consistent libbpf naming patterns.
@@ -97,6 +125,8 @@ struct bpf_map;
 struct btf;
 struct btf_ext;
 
+LIBBPF_API struct btf *libbpf_find_kernel_btf(void);
+
 LIBBPF_API enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog);
 LIBBPF_API enum bpf_attach_type bpf_program__get_expected_attach_type(const struct bpf_program *prog);
 LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map);

src/libbpf_probes.c

@@ -17,47 +17,14 @@
 #include "libbpf.h"
 #include "libbpf_internal.h"
 
-static bool grep(const char *buffer, const char *pattern)
-{
-	return !!strstr(buffer, pattern);
-}
-
-static int get_vendor_id(int ifindex)
-{
-	char ifname[IF_NAMESIZE], path[64], buf[8];
-	ssize_t len;
-	int fd;
-
-	if (!if_indextoname(ifindex, ifname))
-		return -1;
-
-	snprintf(path, sizeof(path), "/sys/class/net/%s/device/vendor", ifname);
-
-	fd = open(path, O_RDONLY | O_CLOEXEC);
-	if (fd < 0)
-		return -1;
-
-	len = read(fd, buf, sizeof(buf));
-	close(fd);
-	if (len < 0)
-		return -1;
-	if (len >= (ssize_t)sizeof(buf))
-		return -1;
-	buf[len] = '\0';
-
-	return strtol(buf, NULL, 0);
-}
-
 static int probe_prog_load(enum bpf_prog_type prog_type,
 			   const struct bpf_insn *insns, size_t insns_cnt,
-			   char *log_buf, size_t log_buf_sz,
-			   __u32 ifindex)
+			   char *log_buf, size_t log_buf_sz)
 {
 	LIBBPF_OPTS(bpf_prog_load_opts, opts,
 		.log_buf = log_buf,
 		.log_size = log_buf_sz,
 		.log_level = log_buf ? 1 : 0,
-		.prog_ifindex = ifindex,
 	);
 	int fd, err, exp_err = 0;
 	const char *exp_msg = NULL;
@@ -161,31 +128,10 @@ int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts)
 	if (opts)
 		return libbpf_err(-EINVAL);
 
-	ret = probe_prog_load(prog_type, insns, insn_cnt, NULL, 0, 0);
+	ret = probe_prog_load(prog_type, insns, insn_cnt, NULL, 0);
 	return libbpf_err(ret);
 }
 
-bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex)
-{
-	struct bpf_insn insns[2] = {
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN()
-	};
-
-	/* prefer libbpf_probe_bpf_prog_type() unless offload is requested */
-	if (ifindex == 0)
-		return libbpf_probe_bpf_prog_type(prog_type, NULL) == 1;
-
-	if (ifindex && prog_type == BPF_PROG_TYPE_SCHED_CLS)
-		/* nfp returns -EINVAL on exit(0) with TC offload */
-		insns[0].imm = 2;
-
-	errno = 0;
-	probe_prog_load(prog_type, insns, ARRAY_SIZE(insns), NULL, 0, ifindex);
-
-	return errno != EINVAL && errno != EOPNOTSUPP;
-}
-
 int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
 			 const char *str_sec, size_t str_len)
 {
@@ -242,14 +188,12 @@ static int load_local_storage_btf(void)
 				     strs, sizeof(strs));
 }
 
-static int probe_map_create(enum bpf_map_type map_type, __u32 ifindex)
+static int probe_map_create(enum bpf_map_type map_type)
 {
 	LIBBPF_OPTS(bpf_map_create_opts, opts);
 	int key_size, value_size, max_entries;
 	__u32 btf_key_type_id = 0, btf_value_type_id = 0;
-	int fd = -1, btf_fd = -1, fd_inner = -1, exp_err = 0, err;
-
-	opts.map_ifindex = ifindex;
+	int fd = -1, btf_fd = -1, fd_inner = -1, exp_err = 0, err = 0;
 
 	key_size	= sizeof(__u32);
 	value_size	= sizeof(__u32);
@@ -277,6 +221,7 @@ static int probe_map_create(enum bpf_map_type map_type, __u32 ifindex)
 	case BPF_MAP_TYPE_SK_STORAGE:
 	case BPF_MAP_TYPE_INODE_STORAGE:
 	case BPF_MAP_TYPE_TASK_STORAGE:
+	case BPF_MAP_TYPE_CGRP_STORAGE:
 		btf_key_type_id = 1;
 		btf_value_type_id = 3;
 		value_size = 8;
@@ -287,9 +232,10 @@ static int probe_map_create(enum bpf_map_type map_type, __u32 ifindex)
 			return btf_fd;
 		break;
 	case BPF_MAP_TYPE_RINGBUF:
+	case BPF_MAP_TYPE_USER_RINGBUF:
 		key_size = 0;
 		value_size = 0;
-		max_entries = 4096;
+		max_entries = sysconf(_SC_PAGE_SIZE);
 		break;
 	case BPF_MAP_TYPE_STRUCT_OPS:
 		/* we'll get -ENOTSUPP for invalid BTF type ID for struct_ops */
@@ -326,12 +272,6 @@ static int probe_map_create(enum bpf_map_type map_type, __u32 ifindex)
 
 	if (map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
 	    map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
-		/* TODO: probe for device, once libbpf has a function to create
-		 * map-in-map for offload
-		 */
-		if (ifindex)
-			goto cleanup;
-
 		fd_inner = bpf_map_create(BPF_MAP_TYPE_HASH, NULL,
 					  sizeof(__u32), sizeof(__u32), 1, NULL);
 		if (fd_inner < 0)
@@ -370,15 +310,10 @@ int libbpf_probe_bpf_map_type(enum bpf_map_type map_type, const void *opts)
 	if (opts)
 		return libbpf_err(-EINVAL);
 
-	ret = probe_map_create(map_type, 0);
+	ret = probe_map_create(map_type);
 	return libbpf_err(ret);
 }
 
-bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
-{
-	return probe_map_create(map_type, ifindex) == 1;
-}
-
 int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, enum bpf_func_id helper_id,
 			    const void *opts)
 {
@@ -407,7 +342,7 @@ int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, enum bpf_func_id helpe
 	}
 
 	buf[0] = '\0';
-	ret = probe_prog_load(prog_type, insns, insn_cnt, buf, sizeof(buf), 0);
+	ret = probe_prog_load(prog_type, insns, insn_cnt, buf, sizeof(buf));
 	if (ret < 0)
 		return libbpf_err(ret);
 
@@ -427,51 +362,3 @@ int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, enum bpf_func_id helpe
 		return 0;
 	return 1; /* assume supported */
 }
-
-bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type,
-		      __u32 ifindex)
-{
-	struct bpf_insn insns[2] = {
-		BPF_EMIT_CALL(id),
-		BPF_EXIT_INSN()
-	};
-	char buf[4096] = {};
-	bool res;
-
-	probe_prog_load(prog_type, insns, ARRAY_SIZE(insns), buf, sizeof(buf), ifindex);
-	res = !grep(buf, "invalid func ") && !grep(buf, "unknown func ");
-
-	if (ifindex) {
-		switch (get_vendor_id(ifindex)) {
-		case 0x19ee: /* Netronome specific */
-			res = res && !grep(buf, "not supported by FW") &&
-				!grep(buf, "unsupported function id");
-			break;
-		default:
-			break;
-		}
-	}
-
-	return res;
-}
-
-/*
- * Probe for availability of kernel commit (5.3):
- *
- * c04c0d2b968a ("bpf: increase complexity limit and maximum program size")
- */
-bool bpf_probe_large_insn_limit(__u32 ifindex)
-{
-	struct bpf_insn insns[BPF_MAXINSNS + 1];
-	int i;
-
-	for (i = 0; i < BPF_MAXINSNS; i++)
-		insns[i] = BPF_MOV64_IMM(BPF_REG_0, 1);
-	insns[BPF_MAXINSNS] = BPF_EXIT_INSN();
-
-	errno = 0;
-	probe_prog_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0,
-			ifindex);
-
-	return errno != E2BIG && errno != EINVAL;
-}

src/libbpf_version.h

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

src/linker.c

@@ -697,11 +697,6 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename,
 	return err;
 }
 
-static bool is_pow_of_2(size_t x)
-{
-	return x && (x & (x - 1)) == 0;
-}
-
 static int linker_sanity_check_elf(struct src_obj *obj)
 {
 	struct src_sec *sec;
@@ -1340,6 +1335,7 @@ recur:
 	case BTF_KIND_STRUCT:
 	case BTF_KIND_UNION:
 	case BTF_KIND_ENUM:
+	case BTF_KIND_ENUM64:
 	case BTF_KIND_FWD:
 	case BTF_KIND_FUNC:
 	case BTF_KIND_VAR:
@@ -1362,6 +1358,7 @@ recur:
 	case BTF_KIND_INT:
 	case BTF_KIND_FLOAT:
 	case BTF_KIND_ENUM:
+	case BTF_KIND_ENUM64:
 		/* ignore encoding for int and enum values for enum */
 		if (t1->size != t2->size) {
 			pr_warn("global '%s': incompatible %s '%s' size %u and %u\n",

src/netlink.c

@@ -27,6 +27,14 @@ typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);
 typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, libbpf_dump_nlmsg_t,
 			      void *cookie);
 
+struct xdp_link_info {
+	__u32 prog_id;
+	__u32 drv_prog_id;
+	__u32 hw_prog_id;
+	__u32 skb_prog_id;
+	__u8 attach_mode;
+};
+
 struct xdp_id_md {
 	int ifindex;
 	__u32 flags;
@@ -87,29 +95,75 @@ enum {
 	NL_DONE,
 };
 
+static int netlink_recvmsg(int sock, struct msghdr *mhdr, int flags)
+{
+	int len;
+
+	do {
+		len = recvmsg(sock, mhdr, flags);
+	} while (len < 0 && (errno == EINTR || errno == EAGAIN));
+
+	if (len < 0)
+		return -errno;
+	return len;
+}
+
+static int alloc_iov(struct iovec *iov, int len)
+{
+	void *nbuf;
+
+	nbuf = realloc(iov->iov_base, len);
+	if (!nbuf)
+		return -ENOMEM;
+
+	iov->iov_base = nbuf;
+	iov->iov_len = len;
+	return 0;
+}
+
 static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq,
 			       __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn,
 			       void *cookie)
 {
+	struct iovec iov = {};
+	struct msghdr mhdr = {
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+	};
 	bool multipart = true;
 	struct nlmsgerr *err;
 	struct nlmsghdr *nh;
-	char buf[4096];
 	int len, ret;
 
+	ret = alloc_iov(&iov, 4096);
+	if (ret)
+		goto done;
+
 	while (multipart) {
 start:
 		multipart = false;
-		len = recv(sock, buf, sizeof(buf), 0);
+		len = netlink_recvmsg(sock, &mhdr, MSG_PEEK | MSG_TRUNC);
 		if (len < 0) {
-			ret = -errno;
+			ret = len;
+			goto done;
+		}
+
+		if (len > iov.iov_len) {
+			ret = alloc_iov(&iov, len);
+			if (ret)
+				goto done;
+		}
+
+		len = netlink_recvmsg(sock, &mhdr, 0);
+		if (len < 0) {
+			ret = len;
 			goto done;
 		}
 
 		if (len == 0)
 			break;
 
-		for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
+		for (nh = (struct nlmsghdr *)iov.iov_base; NLMSG_OK(nh, len);
 		     nh = NLMSG_NEXT(nh, len)) {
 			if (nh->nlmsg_pid != nl_pid) {
 				ret = -LIBBPF_ERRNO__WRNGPID;
@@ -130,7 +184,8 @@ start:
 				libbpf_nla_dump_errormsg(nh);
 				goto done;
 			case NLMSG_DONE:
-				return 0;
+				ret = 0;
+				goto done;
 			default:
 				break;
 			}
@@ -142,15 +197,17 @@ start:
 				case NL_NEXT:
 					goto start;
 				case NL_DONE:
-					return 0;
+					ret = 0;
+					goto done;
 				default:
-					return ret;
+					goto done;
 				}
 			}
 		}
 	}
 	ret = 0;
 done:
+	free(iov.iov_base);
 	return ret;
 }
 
@@ -239,31 +296,6 @@ int bpf_xdp_detach(int ifindex, __u32 flags, const struct bpf_xdp_attach_opts *o
 	return bpf_xdp_attach(ifindex, -1, flags, opts);
 }
 
-int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags,
-			     const struct bpf_xdp_set_link_opts *opts)
-{
-	int old_fd = -1, ret;
-
-	if (!OPTS_VALID(opts, bpf_xdp_set_link_opts))
-		return libbpf_err(-EINVAL);
-
-	if (OPTS_HAS(opts, old_fd)) {
-		old_fd = OPTS_GET(opts, old_fd, -1);
-		flags |= XDP_FLAGS_REPLACE;
-	}
-
-	ret = __bpf_set_link_xdp_fd_replace(ifindex, fd, old_fd, flags);
-	return libbpf_err(ret);
-}
-
-int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
-{
-	int ret;
-
-	ret = __bpf_set_link_xdp_fd_replace(ifindex, fd, 0, flags);
-	return libbpf_err(ret);
-}
-
 static int __dump_link_nlmsg(struct nlmsghdr *nlh,
 			     libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie)
 {
@@ -364,30 +396,6 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
 	return 0;
 }
 
-int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
-			  size_t info_size, __u32 flags)
-{
-	LIBBPF_OPTS(bpf_xdp_query_opts, opts);
-	size_t sz;
-	int err;
-
-	if (!info_size)
-		return libbpf_err(-EINVAL);
-
-	err = bpf_xdp_query(ifindex, flags, &opts);
-	if (err)
-		return libbpf_err(err);
-
-	/* struct xdp_link_info field layout matches struct bpf_xdp_query_opts
-	 * layout after sz field
-	 */
-	sz = min(info_size, offsetofend(struct xdp_link_info, attach_mode));
-	memcpy(info, &opts.prog_id, sz);
-	memset((void *)info + sz, 0, info_size - sz);
-
-	return 0;
-}
-
 int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id)
 {
 	LIBBPF_OPTS(bpf_xdp_query_opts, opts);
@@ -414,11 +422,6 @@ int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id)
 }
 
 
-int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags)
-{
-	return bpf_xdp_query_id(ifindex, flags, prog_id);
-}
-
 typedef int (*qdisc_config_t)(struct libbpf_nla_req *req);
 
 static int clsact_config(struct libbpf_nla_req *req)
@@ -584,11 +587,12 @@ static int get_tc_info(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn,
 
 static int tc_add_fd_and_name(struct libbpf_nla_req *req, int fd)
 {
-	struct bpf_prog_info info = {};
+	struct bpf_prog_info info;
 	__u32 info_len = sizeof(info);
 	char name[256];
 	int len, ret;
 
+	memset(&info, 0, info_len);
 	ret = bpf_obj_get_info_by_fd(fd, &info, &info_len);
 	if (ret < 0)
 		return ret;

src/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/relo_core.c

@@ -95,6 +95,7 @@ static const char *core_relo_kind_str(enum bpf_core_relo_kind kind)
 	case BPF_CORE_TYPE_ID_LOCAL: return "local_type_id";
 	case BPF_CORE_TYPE_ID_TARGET: return "target_type_id";
 	case BPF_CORE_TYPE_EXISTS: return "type_exists";
+	case BPF_CORE_TYPE_MATCHES: return "type_matches";
 	case BPF_CORE_TYPE_SIZE: return "type_size";
 	case BPF_CORE_ENUMVAL_EXISTS: return "enumval_exists";
 	case BPF_CORE_ENUMVAL_VALUE: return "enumval_value";
@@ -123,6 +124,7 @@ static bool core_relo_is_type_based(enum bpf_core_relo_kind kind)
 	case BPF_CORE_TYPE_ID_LOCAL:
 	case BPF_CORE_TYPE_ID_TARGET:
 	case BPF_CORE_TYPE_EXISTS:
+	case BPF_CORE_TYPE_MATCHES:
 	case BPF_CORE_TYPE_SIZE:
 		return true;
 	default:
@@ -141,6 +143,86 @@ static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind)
 	}
 }
 
+int __bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id,
+				const struct btf *targ_btf, __u32 targ_id, int level)
+{
+	const struct btf_type *local_type, *targ_type;
+	int depth = 32; /* max recursion depth */
+
+	/* caller made sure that names match (ignoring flavor suffix) */
+	local_type = btf_type_by_id(local_btf, local_id);
+	targ_type = btf_type_by_id(targ_btf, targ_id);
+	if (!btf_kind_core_compat(local_type, targ_type))
+		return 0;
+
+recur:
+	depth--;
+	if (depth < 0)
+		return -EINVAL;
+
+	local_type = skip_mods_and_typedefs(local_btf, local_id, &local_id);
+	targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id);
+	if (!local_type || !targ_type)
+		return -EINVAL;
+
+	if (!btf_kind_core_compat(local_type, targ_type))
+		return 0;
+
+	switch (btf_kind(local_type)) {
+	case BTF_KIND_UNKN:
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION:
+	case BTF_KIND_ENUM:
+	case BTF_KIND_FWD:
+	case BTF_KIND_ENUM64:
+		return 1;
+	case BTF_KIND_INT:
+		/* just reject deprecated bitfield-like integers; all other
+		 * integers are by default compatible between each other
+		 */
+		return btf_int_offset(local_type) == 0 && btf_int_offset(targ_type) == 0;
+	case BTF_KIND_PTR:
+		local_id = local_type->type;
+		targ_id = targ_type->type;
+		goto recur;
+	case BTF_KIND_ARRAY:
+		local_id = btf_array(local_type)->type;
+		targ_id = btf_array(targ_type)->type;
+		goto recur;
+	case BTF_KIND_FUNC_PROTO: {
+		struct btf_param *local_p = btf_params(local_type);
+		struct btf_param *targ_p = btf_params(targ_type);
+		__u16 local_vlen = btf_vlen(local_type);
+		__u16 targ_vlen = btf_vlen(targ_type);
+		int i, err;
+
+		if (local_vlen != targ_vlen)
+			return 0;
+
+		for (i = 0; i < local_vlen; i++, local_p++, targ_p++) {
+			if (level <= 0)
+				return -EINVAL;
+
+			skip_mods_and_typedefs(local_btf, local_p->type, &local_id);
+			skip_mods_and_typedefs(targ_btf, targ_p->type, &targ_id);
+			err = __bpf_core_types_are_compat(local_btf, local_id, targ_btf, targ_id,
+							  level - 1);
+			if (err <= 0)
+				return err;
+		}
+
+		/* tail recurse for return type check */
+		skip_mods_and_typedefs(local_btf, local_type->type, &local_id);
+		skip_mods_and_typedefs(targ_btf, targ_type->type, &targ_id);
+		goto recur;
+	}
+	default:
+		pr_warn("unexpected kind %s relocated, local [%d], target [%d]\n",
+			btf_kind_str(local_type), local_id, targ_id);
+		return 0;
+	}
+}
+
 /*
  * Turn bpf_core_relo into a low- and high-level spec representation,
  * validating correctness along the way, as well as calculating resulting
@@ -167,40 +249,39 @@ static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind)
  * just a parsed access string representation): [0, 1, 2, 3].
  *
  * High-level spec will capture only 3 points:
- *   - intial zero-index access by pointer (&s->... is the same as &s[0]...);
+ *   - initial zero-index access by pointer (&s->... is the same as &s[0]...);
  *   - field 'a' access (corresponds to '2' in low-level spec);
  *   - array element #3 access (corresponds to '3' in low-level spec).
  *
- * Type-based relocations (TYPE_EXISTS/TYPE_SIZE,
+ * Type-based relocations (TYPE_EXISTS/TYPE_MATCHES/TYPE_SIZE,
  * TYPE_ID_LOCAL/TYPE_ID_TARGET) don't capture any field information. Their
  * spec and raw_spec are kept empty.
  *
  * Enum value-based relocations (ENUMVAL_EXISTS/ENUMVAL_VALUE) use access
  * string to specify enumerator's value index that need to be relocated.
  */
-static int bpf_core_parse_spec(const char *prog_name, const struct btf *btf,
-			       __u32 type_id,
-			       const char *spec_str,
-			       enum bpf_core_relo_kind relo_kind,
+int bpf_core_parse_spec(const char *prog_name, const struct btf *btf,
+			const struct bpf_core_relo *relo,
 			struct bpf_core_spec *spec)
 {
 	int access_idx, parsed_len, i;
 	struct bpf_core_accessor *acc;
 	const struct btf_type *t;
-	const char *name;
-	__u32 id;
+	const char *name, *spec_str;
+	__u32 id, name_off;
 	__s64 sz;
 
+	spec_str = btf__name_by_offset(btf, relo->access_str_off);
 	if (str_is_empty(spec_str) || *spec_str == ':')
 		return -EINVAL;
 
 	memset(spec, 0, sizeof(*spec));
 	spec->btf = btf;
-	spec->root_type_id = type_id;
-	spec->relo_kind = relo_kind;
+	spec->root_type_id = relo->type_id;
+	spec->relo_kind = relo->kind;
 
 	/* type-based relocations don't have a field access string */
-	if (core_relo_is_type_based(relo_kind)) {
+	if (core_relo_is_type_based(relo->kind)) {
 		if (strcmp(spec_str, "0"))
 			return -EINVAL;
 		return 0;
@@ -221,7 +302,7 @@ static int bpf_core_parse_spec(const char *prog_name, const struct btf *btf,
 	if (spec->raw_len == 0)
 		return -EINVAL;
 
-	t = skip_mods_and_typedefs(btf, type_id, &id);
+	t = skip_mods_and_typedefs(btf, relo->type_id, &id);
 	if (!t)
 		return -EINVAL;
 
@@ -231,16 +312,18 @@ static int bpf_core_parse_spec(const char *prog_name, const struct btf *btf,
 	acc->idx = access_idx;
 	spec->len++;
 
-	if (core_relo_is_enumval_based(relo_kind)) {
-		if (!btf_is_enum(t) || spec->raw_len > 1 || access_idx >= btf_vlen(t))
+	if (core_relo_is_enumval_based(relo->kind)) {
+		if (!btf_is_any_enum(t) || spec->raw_len > 1 || access_idx >= btf_vlen(t))
 			return -EINVAL;
 
 		/* record enumerator name in a first accessor */
-		acc->name = btf__name_by_offset(btf, btf_enum(t)[access_idx].name_off);
+		name_off = btf_is_enum(t) ? btf_enum(t)[access_idx].name_off
+					  : btf_enum64(t)[access_idx].name_off;
+		acc->name = btf__name_by_offset(btf, name_off);
 		return 0;
 	}
 
-	if (!core_relo_is_field_based(relo_kind))
+	if (!core_relo_is_field_based(relo->kind))
 		return -EINVAL;
 
 	sz = btf__resolve_size(btf, id);
@@ -301,7 +384,7 @@ static int bpf_core_parse_spec(const char *prog_name, const struct btf *btf,
 			spec->bit_offset += access_idx * sz * 8;
 		} else {
 			pr_warn("prog '%s': relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %s\n",
-				prog_name, type_id, spec_str, i, id, btf_kind_str(t));
+				prog_name, relo->type_id, spec_str, i, id, btf_kind_str(t));
 			return -EINVAL;
 		}
 	}
@@ -341,7 +424,7 @@ recur:
 
 	if (btf_is_composite(local_type) && btf_is_composite(targ_type))
 		return 1;
-	if (btf_kind(local_type) != btf_kind(targ_type))
+	if (!btf_kind_core_compat(local_type, targ_type))
 		return 0;
 
 	switch (btf_kind(local_type)) {
@@ -349,6 +432,7 @@ recur:
 	case BTF_KIND_FLOAT:
 		return 1;
 	case BTF_KIND_FWD:
+	case BTF_KIND_ENUM64:
 	case BTF_KIND_ENUM: {
 		const char *local_name, *targ_name;
 		size_t local_len, targ_len;
@@ -478,6 +562,7 @@ static int bpf_core_spec_match(struct bpf_core_spec *local_spec,
 	const struct bpf_core_accessor *local_acc;
 	struct bpf_core_accessor *targ_acc;
 	int i, sz, matched;
+	__u32 name_off;
 
 	memset(targ_spec, 0, sizeof(*targ_spec));
 	targ_spec->btf = targ_btf;
@@ -485,6 +570,11 @@ static int bpf_core_spec_match(struct bpf_core_spec *local_spec,
 	targ_spec->relo_kind = local_spec->relo_kind;
 
 	if (core_relo_is_type_based(local_spec->relo_kind)) {
+		if (local_spec->relo_kind == BPF_CORE_TYPE_MATCHES)
+			return bpf_core_types_match(local_spec->btf,
+						    local_spec->root_type_id,
+						    targ_btf, targ_id);
+		else
 			return bpf_core_types_are_compat(local_spec->btf,
 							 local_spec->root_type_id,
 							 targ_btf, targ_id);
@@ -495,18 +585,22 @@ static int bpf_core_spec_match(struct bpf_core_spec *local_spec,
 
 	if (core_relo_is_enumval_based(local_spec->relo_kind)) {
 		size_t local_essent_len, targ_essent_len;
-		const struct btf_enum *e;
 		const char *targ_name;
 
 		/* has to resolve to an enum */
 		targ_type = skip_mods_and_typedefs(targ_spec->btf, targ_id, &targ_id);
-		if (!btf_is_enum(targ_type))
+		if (!btf_is_any_enum(targ_type))
 			return 0;
 
 		local_essent_len = bpf_core_essential_name_len(local_acc->name);
 
-		for (i = 0, e = btf_enum(targ_type); i < btf_vlen(targ_type); i++, e++) {
-			targ_name = btf__name_by_offset(targ_spec->btf, e->name_off);
+		for (i = 0; i < btf_vlen(targ_type); i++) {
+			if (btf_is_enum(targ_type))
+				name_off = btf_enum(targ_type)[i].name_off;
+			else
+				name_off = btf_enum64(targ_type)[i].name_off;
+
+			targ_name = btf__name_by_offset(targ_spec->btf, name_off);
 			targ_essent_len = bpf_core_essential_name_len(targ_name);
 			if (targ_essent_len != local_essent_len)
 				continue;
@@ -584,7 +678,7 @@ static int bpf_core_spec_match(struct bpf_core_spec *local_spec,
 static int bpf_core_calc_field_relo(const char *prog_name,
 				    const struct bpf_core_relo *relo,
 				    const struct bpf_core_spec *spec,
-				    __u32 *val, __u32 *field_sz, __u32 *type_id,
+				    __u64 *val, __u32 *field_sz, __u32 *type_id,
 				    bool *validate)
 {
 	const struct bpf_core_accessor *acc;
@@ -681,8 +775,7 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 		*val = byte_sz;
 		break;
 	case BPF_CORE_FIELD_SIGNED:
-		/* enums will be assumed unsigned */
-		*val = btf_is_enum(mt) ||
+		*val = (btf_is_any_enum(mt) && BTF_INFO_KFLAG(mt->info)) ||
 		       (btf_int_encoding(mt) & BTF_INT_SIGNED);
 		if (validate)
 			*validate = true; /* signedness is never ambiguous */
@@ -709,7 +802,7 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 
 static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo,
 				   const struct bpf_core_spec *spec,
-				   __u32 *val, bool *validate)
+				   __u64 *val, bool *validate)
 {
 	__s64 sz;
 
@@ -733,6 +826,7 @@ static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo,
 			*validate = false;
 		break;
 	case BPF_CORE_TYPE_EXISTS:
+	case BPF_CORE_TYPE_MATCHES:
 		*val = 1;
 		break;
 	case BPF_CORE_TYPE_SIZE:
@@ -752,10 +846,9 @@ static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo,
 
 static int bpf_core_calc_enumval_relo(const struct bpf_core_relo *relo,
 				      const struct bpf_core_spec *spec,
-				      __u32 *val)
+				      __u64 *val)
 {
 	const struct btf_type *t;
-	const struct btf_enum *e;
 
 	switch (relo->kind) {
 	case BPF_CORE_ENUMVAL_EXISTS:
@@ -765,8 +858,10 @@ static int bpf_core_calc_enumval_relo(const struct bpf_core_relo *relo,
 		if (!spec)
 			return -EUCLEAN; /* request instruction poisoning */
 		t = btf_type_by_id(spec->btf, spec->spec[0].type_id);
-		e = btf_enum(t) + spec->spec[0].idx;
-		*val = e->val;
+		if (btf_is_enum(t))
+			*val = btf_enum(t)[spec->spec[0].idx].val;
+		else
+			*val = btf_enum64_value(btf_enum64(t) + spec->spec[0].idx);
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -775,31 +870,6 @@ static int bpf_core_calc_enumval_relo(const struct bpf_core_relo *relo,
 	return 0;
 }
 
-struct bpf_core_relo_res
-{
-	/* expected value in the instruction, unless validate == false */
-	__u32 orig_val;
-	/* new value that needs to be patched up to */
-	__u32 new_val;
-	/* relocation unsuccessful, poison instruction, but don't fail load */
-	bool poison;
-	/* some relocations can't be validated against orig_val */
-	bool validate;
-	/* for field byte offset relocations or the forms:
-	 *     *(T *)(rX + <off>) = rY
-	 *     rX = *(T *)(rY + <off>),
-	 * we remember original and resolved field size to adjust direct
-	 * memory loads of pointers and integers; this is necessary for 32-bit
-	 * host kernel architectures, but also allows to automatically
-	 * relocate fields that were resized from, e.g., u32 to u64, etc.
-	 */
-	bool fail_memsz_adjust;
-	__u32 orig_sz;
-	__u32 orig_type_id;
-	__u32 new_sz;
-	__u32 new_type_id;
-};
-
 /* Calculate original and target relocation values, given local and target
  * specs and relocation kind. These values are calculated for each candidate.
  * If there are multiple candidates, resulting values should all be consistent
@@ -951,11 +1021,11 @@ static int insn_bytes_to_bpf_size(__u32 sz)
  * 5. *(T *)(rX + <off>) = rY, where T is one of {u8, u16, u32, u64};
  * 6. *(T *)(rX + <off>) = <imm>, where T is one of {u8, u16, u32, u64}.
  */
-static int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn,
+int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn,
 			int insn_idx, const struct bpf_core_relo *relo,
 			int relo_idx, const struct bpf_core_relo_res *res)
 {
-	__u32 orig_val, new_val;
+	__u64 orig_val, new_val;
 	__u8 class;
 
 	class = BPF_CLASS(insn->code);
@@ -980,28 +1050,30 @@ poison:
 		if (BPF_SRC(insn->code) != BPF_K)
 			return -EINVAL;
 		if (res->validate && insn->imm != orig_val) {
-			pr_warn("prog '%s': relo #%d: unexpected insn #%d (ALU/ALU64) value: got %u, exp %u -> %u\n",
+			pr_warn("prog '%s': relo #%d: unexpected insn #%d (ALU/ALU64) value: got %u, exp %llu -> %llu\n",
 				prog_name, relo_idx,
-				insn_idx, insn->imm, orig_val, new_val);
+				insn_idx, insn->imm, (unsigned long long)orig_val,
+				(unsigned long long)new_val);
 			return -EINVAL;
 		}
 		orig_val = insn->imm;
 		insn->imm = new_val;
-		pr_debug("prog '%s': relo #%d: patched insn #%d (ALU/ALU64) imm %u -> %u\n",
+		pr_debug("prog '%s': relo #%d: patched insn #%d (ALU/ALU64) imm %llu -> %llu\n",
 			 prog_name, relo_idx, insn_idx,
-			 orig_val, new_val);
+			 (unsigned long long)orig_val, (unsigned long long)new_val);
 		break;
 	case BPF_LDX:
 	case BPF_ST:
 	case BPF_STX:
 		if (res->validate && insn->off != orig_val) {
-			pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDX/ST/STX) value: got %u, exp %u -> %u\n",
-				prog_name, relo_idx, insn_idx, insn->off, orig_val, new_val);
+			pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDX/ST/STX) value: got %u, exp %llu -> %llu\n",
+				prog_name, relo_idx, insn_idx, insn->off, (unsigned long long)orig_val,
+				(unsigned long long)new_val);
 			return -EINVAL;
 		}
 		if (new_val > SHRT_MAX) {
-			pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) value too big: %u\n",
-				prog_name, relo_idx, insn_idx, new_val);
+			pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) value too big: %llu\n",
+				prog_name, relo_idx, insn_idx, (unsigned long long)new_val);
 			return -ERANGE;
 		}
 		if (res->fail_memsz_adjust) {
@@ -1013,8 +1085,9 @@ poison:
 
 		orig_val = insn->off;
 		insn->off = new_val;
-		pr_debug("prog '%s': relo #%d: patched insn #%d (LDX/ST/STX) off %u -> %u\n",
-			 prog_name, relo_idx, insn_idx, orig_val, new_val);
+		pr_debug("prog '%s': relo #%d: patched insn #%d (LDX/ST/STX) off %llu -> %llu\n",
+			 prog_name, relo_idx, insn_idx, (unsigned long long)orig_val,
+			 (unsigned long long)new_val);
 
 		if (res->new_sz != res->orig_sz) {
 			int insn_bytes_sz, insn_bpf_sz;
@@ -1050,20 +1123,20 @@ poison:
 			return -EINVAL;
 		}
 
-		imm = insn[0].imm + ((__u64)insn[1].imm << 32);
+		imm = (__u32)insn[0].imm | ((__u64)insn[1].imm << 32);
 		if (res->validate && imm != orig_val) {
-			pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDIMM64) value: got %llu, exp %u -> %u\n",
+			pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDIMM64) value: got %llu, exp %llu -> %llu\n",
 				prog_name, relo_idx,
 				insn_idx, (unsigned long long)imm,
-				orig_val, new_val);
+				(unsigned long long)orig_val, (unsigned long long)new_val);
 			return -EINVAL;
 		}
 
 		insn[0].imm = new_val;
-		insn[1].imm = 0; /* currently only 32-bit values are supported */
-		pr_debug("prog '%s': relo #%d: patched insn #%d (LDIMM64) imm64 %llu -> %u\n",
+		insn[1].imm = new_val >> 32;
+		pr_debug("prog '%s': relo #%d: patched insn #%d (LDIMM64) imm64 %llu -> %llu\n",
 			 prog_name, relo_idx, insn_idx,
-			 (unsigned long long)imm, new_val);
+			 (unsigned long long)imm, (unsigned long long)new_val);
 		break;
 	}
 	default:
@@ -1080,55 +1153,82 @@ poison:
  * [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>,
  * where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b
  */
-static void bpf_core_dump_spec(const char *prog_name, int level, const struct bpf_core_spec *spec)
+int bpf_core_format_spec(char *buf, size_t buf_sz, const struct bpf_core_spec *spec)
 {
 	const struct btf_type *t;
-	const struct btf_enum *e;
 	const char *s;
 	__u32 type_id;
-	int i;
+	int i, len = 0;
+
+#define append_buf(fmt, args...)				\
+	({							\
+		int r;						\
+		r = snprintf(buf, buf_sz, fmt, ##args);		\
+		len += r;					\
+		if (r >= buf_sz)				\
+			r = buf_sz;				\
+		buf += r;					\
+		buf_sz -= r;					\
+	})
 
 	type_id = spec->root_type_id;
 	t = btf_type_by_id(spec->btf, type_id);
 	s = btf__name_by_offset(spec->btf, t->name_off);
 
-	libbpf_print(level, "[%u] %s %s", type_id, btf_kind_str(t), str_is_empty(s) ? "<anon>" : s);
+	append_buf("<%s> [%u] %s %s",
+		   core_relo_kind_str(spec->relo_kind),
+		   type_id, btf_kind_str(t), str_is_empty(s) ? "<anon>" : s);
 
 	if (core_relo_is_type_based(spec->relo_kind))
-		return;
+		return len;
 
 	if (core_relo_is_enumval_based(spec->relo_kind)) {
 		t = skip_mods_and_typedefs(spec->btf, type_id, NULL);
+		if (btf_is_enum(t)) {
+			const struct btf_enum *e;
+			const char *fmt_str;
+
 			e = btf_enum(t) + spec->raw_spec[0];
 			s = btf__name_by_offset(spec->btf, e->name_off);
+			fmt_str = BTF_INFO_KFLAG(t->info) ? "::%s = %d" : "::%s = %u";
+			append_buf(fmt_str, s, e->val);
+		} else {
+			const struct btf_enum64 *e;
+			const char *fmt_str;
 
-		libbpf_print(level, "::%s = %u", s, e->val);
-		return;
+			e = btf_enum64(t) + spec->raw_spec[0];
+			s = btf__name_by_offset(spec->btf, e->name_off);
+			fmt_str = BTF_INFO_KFLAG(t->info) ? "::%s = %lld" : "::%s = %llu";
+			append_buf(fmt_str, s, (unsigned long long)btf_enum64_value(e));
+		}
+		return len;
 	}
 
 	if (core_relo_is_field_based(spec->relo_kind)) {
 		for (i = 0; i < spec->len; i++) {
 			if (spec->spec[i].name)
-				libbpf_print(level, ".%s", spec->spec[i].name);
+				append_buf(".%s", spec->spec[i].name);
 			else if (i > 0 || spec->spec[i].idx > 0)
-				libbpf_print(level, "[%u]", spec->spec[i].idx);
+				append_buf("[%u]", spec->spec[i].idx);
 		}
 
-		libbpf_print(level, " (");
+		append_buf(" (");
 		for (i = 0; i < spec->raw_len; i++)
-			libbpf_print(level, "%s%d", i == 0 ? "" : ":", spec->raw_spec[i]);
+			append_buf("%s%d", i == 0 ? "" : ":", spec->raw_spec[i]);
 
 		if (spec->bit_offset % 8)
-			libbpf_print(level, " @ offset %u.%u)",
-				     spec->bit_offset / 8, spec->bit_offset % 8);
+			append_buf(" @ offset %u.%u)", spec->bit_offset / 8, spec->bit_offset % 8);
 		else
-			libbpf_print(level, " @ offset %u)", spec->bit_offset / 8);
-		return;
+			append_buf(" @ offset %u)", spec->bit_offset / 8);
+		return len;
 	}
+
+	return len;
+#undef append_buf
 }
 
 /*
- * CO-RE relocate single instruction.
+ * Calculate CO-RE relocation target result.
  *
  * The outline and important points of the algorithm:
  * 1. For given local type, find corresponding candidate target types.
@@ -1159,11 +1259,11 @@ static void bpf_core_dump_spec(const char *prog_name, int level, const struct bp
  * 3. It is supported and expected that there might be multiple flavors
  *    matching the spec. As long as all the specs resolve to the same set of
  *    offsets across all candidates, there is no error. If there is any
- *    ambiguity, CO-RE relocation will fail. This is necessary to accomodate
- *    imprefection of BTF deduplication, which can cause slight duplication of
+ *    ambiguity, CO-RE relocation will fail. This is necessary to accommodate
+ *    imperfection of BTF deduplication, which can cause slight duplication of
  *    the same BTF type, if some directly or indirectly referenced (by
  *    pointer) type gets resolved to different actual types in different
- *    object files. If such situation occurs, deduplicated BTF will end up
+ *    object files. If such a situation occurs, deduplicated BTF will end up
  *    with two (or more) structurally identical types, which differ only in
  *    types they refer to through pointer. This should be OK in most cases and
  *    is not an error.
@@ -1177,22 +1277,22 @@ static void bpf_core_dump_spec(const char *prog_name, int level, const struct bp
  *    between multiple relocations for the same type ID and is updated as some
  *    of the candidates are pruned due to structural incompatibility.
  */
-int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
-			     int insn_idx,
+int bpf_core_calc_relo_insn(const char *prog_name,
 			    const struct bpf_core_relo *relo,
 			    int relo_idx,
 			    const struct btf *local_btf,
 			    struct bpf_core_cand_list *cands,
-			     struct bpf_core_spec *specs_scratch)
+			    struct bpf_core_spec *specs_scratch,
+			    struct bpf_core_relo_res *targ_res)
 {
 	struct bpf_core_spec *local_spec = &specs_scratch[0];
 	struct bpf_core_spec *cand_spec = &specs_scratch[1];
 	struct bpf_core_spec *targ_spec = &specs_scratch[2];
-	struct bpf_core_relo_res cand_res, targ_res;
+	struct bpf_core_relo_res cand_res;
 	const struct btf_type *local_type;
 	const char *local_name;
 	__u32 local_id;
-	const char *spec_str;
+	char spec_buf[256];
 	int i, j, err;
 
 	local_id = relo->type_id;
@@ -1201,38 +1301,34 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 	if (!local_name)
 		return -EINVAL;
 
-	spec_str = btf__name_by_offset(local_btf, relo->access_str_off);
-	if (str_is_empty(spec_str))
-		return -EINVAL;
-
-	err = bpf_core_parse_spec(prog_name, local_btf, local_id, spec_str,
-				  relo->kind, local_spec);
+	err = bpf_core_parse_spec(prog_name, local_btf, relo, local_spec);
 	if (err) {
+		const char *spec_str;
+
+		spec_str = btf__name_by_offset(local_btf, relo->access_str_off);
 		pr_warn("prog '%s': relo #%d: parsing [%d] %s %s + %s failed: %d\n",
 			prog_name, relo_idx, local_id, btf_kind_str(local_type),
 			str_is_empty(local_name) ? "<anon>" : local_name,
-			spec_str, err);
+			spec_str ?: "<?>", err);
 		return -EINVAL;
 	}
 
-	pr_debug("prog '%s': relo #%d: kind <%s> (%d), spec is ", prog_name,
-		 relo_idx, core_relo_kind_str(relo->kind), relo->kind);
-	bpf_core_dump_spec(prog_name, LIBBPF_DEBUG, local_spec);
-	libbpf_print(LIBBPF_DEBUG, "\n");
+	bpf_core_format_spec(spec_buf, sizeof(spec_buf), local_spec);
+	pr_debug("prog '%s': relo #%d: %s\n", prog_name, relo_idx, spec_buf);
 
 	/* TYPE_ID_LOCAL relo is special and doesn't need candidate search */
 	if (relo->kind == BPF_CORE_TYPE_ID_LOCAL) {
 		/* bpf_insn's imm value could get out of sync during linking */
-		memset(&targ_res, 0, sizeof(targ_res));
-		targ_res.validate = false;
-		targ_res.poison = false;
-		targ_res.orig_val = local_spec->root_type_id;
-		targ_res.new_val = local_spec->root_type_id;
-		goto patch_insn;
+		memset(targ_res, 0, sizeof(*targ_res));
+		targ_res->validate = false;
+		targ_res->poison = false;
+		targ_res->orig_val = local_spec->root_type_id;
+		targ_res->new_val = local_spec->root_type_id;
+		return 0;
 	}
 
 	/* libbpf doesn't support candidate search for anonymous types */
-	if (str_is_empty(spec_str)) {
+	if (str_is_empty(local_name)) {
 		pr_warn("prog '%s': relo #%d: <%s> (%d) relocation doesn't support anonymous types\n",
 			prog_name, relo_idx, core_relo_kind_str(relo->kind), relo->kind);
 		return -EOPNOTSUPP;
@@ -1242,17 +1338,15 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 		err = bpf_core_spec_match(local_spec, cands->cands[i].btf,
 					  cands->cands[i].id, cand_spec);
 		if (err < 0) {
-			pr_warn("prog '%s': relo #%d: error matching candidate #%d ",
-				prog_name, relo_idx, i);
-			bpf_core_dump_spec(prog_name, LIBBPF_WARN, cand_spec);
-			libbpf_print(LIBBPF_WARN, ": %d\n", err);
+			bpf_core_format_spec(spec_buf, sizeof(spec_buf), cand_spec);
+			pr_warn("prog '%s': relo #%d: error matching candidate #%d %s: %d\n ",
+				prog_name, relo_idx, i, spec_buf, err);
 			return err;
 		}
 
-		pr_debug("prog '%s': relo #%d: %s candidate #%d ", prog_name,
-			 relo_idx, err == 0 ? "non-matching" : "matching", i);
-		bpf_core_dump_spec(prog_name, LIBBPF_DEBUG, cand_spec);
-		libbpf_print(LIBBPF_DEBUG, "\n");
+		bpf_core_format_spec(spec_buf, sizeof(spec_buf), cand_spec);
+		pr_debug("prog '%s': relo #%d: %s candidate #%d %s\n", prog_name,
+			 relo_idx, err == 0 ? "non-matching" : "matching", i, spec_buf);
 
 		if (err == 0)
 			continue;
@@ -1262,7 +1356,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 			return err;
 
 		if (j == 0) {
-			targ_res = cand_res;
+			*targ_res = cand_res;
 			*targ_spec = *cand_spec;
 		} else if (cand_spec->bit_offset != targ_spec->bit_offset) {
 			/* if there are many field relo candidates, they
@@ -1272,15 +1366,18 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 				prog_name, relo_idx, cand_spec->bit_offset,
 				targ_spec->bit_offset);
 			return -EINVAL;
-		} else if (cand_res.poison != targ_res.poison || cand_res.new_val != targ_res.new_val) {
+		} else if (cand_res.poison != targ_res->poison ||
+			   cand_res.new_val != targ_res->new_val) {
 			/* all candidates should result in the same relocation
 			 * decision and value, otherwise it's dangerous to
 			 * proceed due to ambiguity
 			 */
-			pr_warn("prog '%s': relo #%d: relocation decision ambiguity: %s %u != %s %u\n",
+			pr_warn("prog '%s': relo #%d: relocation decision ambiguity: %s %llu != %s %llu\n",
 				prog_name, relo_idx,
-				cand_res.poison ? "failure" : "success", cand_res.new_val,
-				targ_res.poison ? "failure" : "success", targ_res.new_val);
+				cand_res.poison ? "failure" : "success",
+				(unsigned long long)cand_res.new_val,
+				targ_res->poison ? "failure" : "success",
+				(unsigned long long)targ_res->new_val);
 			return -EINVAL;
 		}
 
@@ -1314,19 +1411,280 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 			 prog_name, relo_idx);
 
 		/* calculate single target relo result explicitly */
-		err = bpf_core_calc_relo(prog_name, relo, relo_idx, local_spec, NULL, &targ_res);
+		err = bpf_core_calc_relo(prog_name, relo, relo_idx, local_spec, NULL, targ_res);
 		if (err)
 			return err;
 	}
 
-patch_insn:
-	/* bpf_core_patch_insn() should know how to handle missing targ_spec */
-	err = bpf_core_patch_insn(prog_name, insn, insn_idx, relo, relo_idx, &targ_res);
-	if (err) {
-		pr_warn("prog '%s': relo #%d: failed to patch insn #%u: %d\n",
-			prog_name, relo_idx, relo->insn_off / 8, err);
-		return -EINVAL;
-	}
-
 	return 0;
 }
+
+static bool bpf_core_names_match(const struct btf *local_btf, size_t local_name_off,
+				 const struct btf *targ_btf, size_t targ_name_off)
+{
+	const char *local_n, *targ_n;
+	size_t local_len, targ_len;
+
+	local_n = btf__name_by_offset(local_btf, local_name_off);
+	targ_n = btf__name_by_offset(targ_btf, targ_name_off);
+
+	if (str_is_empty(targ_n))
+		return str_is_empty(local_n);
+
+	targ_len = bpf_core_essential_name_len(targ_n);
+	local_len = bpf_core_essential_name_len(local_n);
+
+	return targ_len == local_len && strncmp(local_n, targ_n, local_len) == 0;
+}
+
+static int bpf_core_enums_match(const struct btf *local_btf, const struct btf_type *local_t,
+				const struct btf *targ_btf, const struct btf_type *targ_t)
+{
+	__u16 local_vlen = btf_vlen(local_t);
+	__u16 targ_vlen = btf_vlen(targ_t);
+	int i, j;
+
+	if (local_t->size != targ_t->size)
+		return 0;
+
+	if (local_vlen > targ_vlen)
+		return 0;
+
+	/* iterate over the local enum's variants and make sure each has
+	 * a symbolic name correspondent in the target
+	 */
+	for (i = 0; i < local_vlen; i++) {
+		bool matched = false;
+		__u32 local_n_off, targ_n_off;
+
+		local_n_off = btf_is_enum(local_t) ? btf_enum(local_t)[i].name_off :
+						     btf_enum64(local_t)[i].name_off;
+
+		for (j = 0; j < targ_vlen; j++) {
+			targ_n_off = btf_is_enum(targ_t) ? btf_enum(targ_t)[j].name_off :
+							   btf_enum64(targ_t)[j].name_off;
+
+			if (bpf_core_names_match(local_btf, local_n_off, targ_btf, targ_n_off)) {
+				matched = true;
+				break;
+			}
+		}
+
+		if (!matched)
+			return 0;
+	}
+	return 1;
+}
+
+static int bpf_core_composites_match(const struct btf *local_btf, const struct btf_type *local_t,
+				     const struct btf *targ_btf, const struct btf_type *targ_t,
+				     bool behind_ptr, int level)
+{
+	const struct btf_member *local_m = btf_members(local_t);
+	__u16 local_vlen = btf_vlen(local_t);
+	__u16 targ_vlen = btf_vlen(targ_t);
+	int i, j, err;
+
+	if (local_vlen > targ_vlen)
+		return 0;
+
+	/* check that all local members have a match in the target */
+	for (i = 0; i < local_vlen; i++, local_m++) {
+		const struct btf_member *targ_m = btf_members(targ_t);
+		bool matched = false;
+
+		for (j = 0; j < targ_vlen; j++, targ_m++) {
+			if (!bpf_core_names_match(local_btf, local_m->name_off,
+						  targ_btf, targ_m->name_off))
+				continue;
+
+			err = __bpf_core_types_match(local_btf, local_m->type, targ_btf,
+						     targ_m->type, behind_ptr, level - 1);
+			if (err < 0)
+				return err;
+			if (err > 0) {
+				matched = true;
+				break;
+			}
+		}
+
+		if (!matched)
+			return 0;
+	}
+	return 1;
+}
+
+/* Check that two types "match". This function assumes that root types were
+ * already checked for name match.
+ *
+ * The matching relation is defined as follows:
+ * - modifiers and typedefs are stripped (and, hence, effectively ignored)
+ * - generally speaking types need to be of same kind (struct vs. struct, union
+ *   vs. union, etc.)
+ *   - exceptions are struct/union behind a pointer which could also match a
+ *     forward declaration of a struct or union, respectively, and enum vs.
+ *     enum64 (see below)
+ * Then, depending on type:
+ * - integers:
+ *   - match if size and signedness match
+ * - arrays & pointers:
+ *   - target types are recursively matched
+ * - structs & unions:
+ *   - local members need to exist in target with the same name
+ *   - for each member we recursively check match unless it is already behind a
+ *     pointer, in which case we only check matching names and compatible kind
+ * - enums:
+ *   - local variants have to have a match in target by symbolic name (but not
+ *     numeric value)
+ *   - size has to match (but enum may match enum64 and vice versa)
+ * - function pointers:
+ *   - number and position of arguments in local type has to match target
+ *   - for each argument and the return value we recursively check match
+ */
+int __bpf_core_types_match(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf,
+			   __u32 targ_id, bool behind_ptr, int level)
+{
+	const struct btf_type *local_t, *targ_t;
+	int depth = 32; /* max recursion depth */
+	__u16 local_k, targ_k;
+
+	if (level <= 0)
+		return -EINVAL;
+
+	local_t = btf_type_by_id(local_btf, local_id);
+	targ_t = btf_type_by_id(targ_btf, targ_id);
+
+recur:
+	depth--;
+	if (depth < 0)
+		return -EINVAL;
+
+	local_t = skip_mods_and_typedefs(local_btf, local_id, &local_id);
+	targ_t = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id);
+	if (!local_t || !targ_t)
+		return -EINVAL;
+
+	/* While the name check happens after typedefs are skipped, root-level
+	 * typedefs would still be name-matched as that's the contract with
+	 * callers.
+	 */
+	if (!bpf_core_names_match(local_btf, local_t->name_off, targ_btf, targ_t->name_off))
+		return 0;
+
+	local_k = btf_kind(local_t);
+	targ_k = btf_kind(targ_t);
+
+	switch (local_k) {
+	case BTF_KIND_UNKN:
+		return local_k == targ_k;
+	case BTF_KIND_FWD: {
+		bool local_f = BTF_INFO_KFLAG(local_t->info);
+
+		if (behind_ptr) {
+			if (local_k == targ_k)
+				return local_f == BTF_INFO_KFLAG(targ_t->info);
+
+			/* for forward declarations kflag dictates whether the
+			 * target is a struct (0) or union (1)
+			 */
+			return (targ_k == BTF_KIND_STRUCT && !local_f) ||
+			       (targ_k == BTF_KIND_UNION && local_f);
+		} else {
+			if (local_k != targ_k)
+				return 0;
+
+			/* match if the forward declaration is for the same kind */
+			return local_f == BTF_INFO_KFLAG(targ_t->info);
+		}
+	}
+	case BTF_KIND_ENUM:
+	case BTF_KIND_ENUM64:
+		if (!btf_is_any_enum(targ_t))
+			return 0;
+
+		return bpf_core_enums_match(local_btf, local_t, targ_btf, targ_t);
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION:
+		if (behind_ptr) {
+			bool targ_f = BTF_INFO_KFLAG(targ_t->info);
+
+			if (local_k == targ_k)
+				return 1;
+
+			if (targ_k != BTF_KIND_FWD)
+				return 0;
+
+			return (local_k == BTF_KIND_UNION) == targ_f;
+		} else {
+			if (local_k != targ_k)
+				return 0;
+
+			return bpf_core_composites_match(local_btf, local_t, targ_btf, targ_t,
+							 behind_ptr, level);
+		}
+	case BTF_KIND_INT: {
+		__u8 local_sgn;
+		__u8 targ_sgn;
+
+		if (local_k != targ_k)
+			return 0;
+
+		local_sgn = btf_int_encoding(local_t) & BTF_INT_SIGNED;
+		targ_sgn = btf_int_encoding(targ_t) & BTF_INT_SIGNED;
+
+		return local_t->size == targ_t->size && local_sgn == targ_sgn;
+	}
+	case BTF_KIND_PTR:
+		if (local_k != targ_k)
+			return 0;
+
+		behind_ptr = true;
+
+		local_id = local_t->type;
+		targ_id = targ_t->type;
+		goto recur;
+	case BTF_KIND_ARRAY: {
+		const struct btf_array *local_array = btf_array(local_t);
+		const struct btf_array *targ_array = btf_array(targ_t);
+
+		if (local_k != targ_k)
+			return 0;
+
+		if (local_array->nelems != targ_array->nelems)
+			return 0;
+
+		local_id = local_array->type;
+		targ_id = targ_array->type;
+		goto recur;
+	}
+	case BTF_KIND_FUNC_PROTO: {
+		struct btf_param *local_p = btf_params(local_t);
+		struct btf_param *targ_p = btf_params(targ_t);
+		__u16 local_vlen = btf_vlen(local_t);
+		__u16 targ_vlen = btf_vlen(targ_t);
+		int i, err;
+
+		if (local_k != targ_k)
+			return 0;
+
+		if (local_vlen != targ_vlen)
+			return 0;
+
+		for (i = 0; i < local_vlen; i++, local_p++, targ_p++) {
+			err = __bpf_core_types_match(local_btf, local_p->type, targ_btf,
+						     targ_p->type, behind_ptr, level - 1);
+			if (err <= 0)
+				return err;
+		}
+
+		/* tail recurse for return type check */
+		local_id = local_t->type;
+		targ_id = targ_t->type;
+		goto recur;
+	}
+	default:
+		pr_warn("unexpected kind %s relocated, local [%d], target [%d]\n",
+			btf_kind_str(local_t), local_id, targ_id);
+		return 0;
+	}
+}

src/relo_core.h

@@ -44,14 +44,56 @@ struct bpf_core_spec {
 	__u32 bit_offset;
 };
 
-int bpf_core_apply_relo_insn(const char *prog_name,
-			     struct bpf_insn *insn, int insn_idx,
+struct bpf_core_relo_res {
+	/* expected value in the instruction, unless validate == false */
+	__u64 orig_val;
+	/* new value that needs to be patched up to */
+	__u64 new_val;
+	/* relocation unsuccessful, poison instruction, but don't fail load */
+	bool poison;
+	/* some relocations can't be validated against orig_val */
+	bool validate;
+	/* for field byte offset relocations or the forms:
+	 *     *(T *)(rX + <off>) = rY
+	 *     rX = *(T *)(rY + <off>),
+	 * we remember original and resolved field size to adjust direct
+	 * memory loads of pointers and integers; this is necessary for 32-bit
+	 * host kernel architectures, but also allows to automatically
+	 * relocate fields that were resized from, e.g., u32 to u64, etc.
+	 */
+	bool fail_memsz_adjust;
+	__u32 orig_sz;
+	__u32 orig_type_id;
+	__u32 new_sz;
+	__u32 new_type_id;
+};
+
+int __bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id,
+				const struct btf *targ_btf, __u32 targ_id, int level);
+int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id,
+			      const struct btf *targ_btf, __u32 targ_id);
+int __bpf_core_types_match(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf,
+			   __u32 targ_id, bool behind_ptr, int level);
+int bpf_core_types_match(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf,
+			 __u32 targ_id);
+
+size_t bpf_core_essential_name_len(const char *name);
+
+int bpf_core_calc_relo_insn(const char *prog_name,
 			    const struct bpf_core_relo *relo, int relo_idx,
 			    const struct btf *local_btf,
 			    struct bpf_core_cand_list *cands,
-			     struct bpf_core_spec *specs_scratch);
-int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id,
-			      const struct btf *targ_btf, __u32 targ_id);
+			    struct bpf_core_spec *specs_scratch,
+			    struct bpf_core_relo_res *targ_res);
+
+int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn,
+			int insn_idx, const struct bpf_core_relo *relo,
+			int relo_idx, const struct bpf_core_relo_res *res);
+
+int bpf_core_parse_spec(const char *prog_name, const struct btf *btf,
+		        const struct bpf_core_relo *relo,
+		        struct bpf_core_spec *spec);
+
+int bpf_core_format_spec(char *buf, size_t buf_sz, const struct bpf_core_spec *spec);
 
-size_t bpf_core_essential_name_len(const char *name);
 #endif

src/ringbuf.c

@@ -16,6 +16,7 @@
 #include <asm/barrier.h>
 #include <sys/mman.h>
 #include <sys/epoll.h>
+#include <time.h>
 
 #include "libbpf.h"
 #include "libbpf_internal.h"
@@ -39,6 +40,23 @@ struct ring_buffer {
 	int ring_cnt;
 };
 
+struct user_ring_buffer {
+	struct epoll_event event;
+	unsigned long *consumer_pos;
+	unsigned long *producer_pos;
+	void *data;
+	unsigned long mask;
+	size_t page_size;
+	int map_fd;
+	int epoll_fd;
+};
+
+/* 8-byte ring buffer header structure */
+struct ringbuf_hdr {
+	__u32 len;
+	__u32 pad;
+};
+
 static void ringbuf_unmap_ring(struct ring_buffer *rb, struct ring *r)
 {
 	if (r->consumer_pos) {
@@ -59,6 +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;
 
@@ -97,8 +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",
@@ -110,9 +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);
@@ -300,3 +322,266 @@ int ring_buffer__epoll_fd(const struct ring_buffer *rb)
 {
 	return rb->epoll_fd;
 }
+
+static void user_ringbuf_unmap_ring(struct user_ring_buffer *rb)
+{
+	if (rb->consumer_pos) {
+		munmap(rb->consumer_pos, rb->page_size);
+		rb->consumer_pos = NULL;
+	}
+	if (rb->producer_pos) {
+		munmap(rb->producer_pos, rb->page_size + 2 * (rb->mask + 1));
+		rb->producer_pos = NULL;
+	}
+}
+
+void user_ring_buffer__free(struct user_ring_buffer *rb)
+{
+	if (!rb)
+		return;
+
+	user_ringbuf_unmap_ring(rb);
+
+	if (rb->epoll_fd >= 0)
+		close(rb->epoll_fd);
+
+	free(rb);
+}
+
+static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd)
+{
+	struct bpf_map_info info;
+	__u32 len = sizeof(info);
+	__u64 mmap_sz;
+	void *tmp;
+	struct epoll_event *rb_epoll;
+	int err;
+
+	memset(&info, 0, sizeof(info));
+
+	err = bpf_obj_get_info_by_fd(map_fd, &info, &len);
+	if (err) {
+		err = -errno;
+		pr_warn("user ringbuf: failed to get map info for fd=%d: %d\n", map_fd, err);
+		return err;
+	}
+
+	if (info.type != BPF_MAP_TYPE_USER_RINGBUF) {
+		pr_warn("user ringbuf: map fd=%d is not BPF_MAP_TYPE_USER_RINGBUF\n", map_fd);
+		return -EINVAL;
+	}
+
+	rb->map_fd = map_fd;
+	rb->mask = info.max_entries - 1;
+
+	/* Map read-only consumer page */
+	tmp = mmap(NULL, rb->page_size, PROT_READ, MAP_SHARED, map_fd, 0);
+	if (tmp == MAP_FAILED) {
+		err = -errno;
+		pr_warn("user ringbuf: failed to mmap consumer page for map fd=%d: %d\n",
+			map_fd, err);
+		return err;
+	}
+	rb->consumer_pos = tmp;
+
+	/* Map read-write the producer page and data pages. We map the data
+	 * region as twice the total size of the ring buffer to allow the
+	 * simple reading and writing of samples that wrap around the end of
+	 * the buffer.  See the kernel implementation for details.
+	 */
+	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",
+			map_fd, err);
+		return err;
+	}
+
+	rb->producer_pos = tmp;
+	rb->data = tmp + rb->page_size;
+
+	rb_epoll = &rb->event;
+	rb_epoll->events = EPOLLOUT;
+	if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, rb_epoll) < 0) {
+		err = -errno;
+		pr_warn("user ringbuf: failed to epoll add map fd=%d: %d\n", map_fd, err);
+		return err;
+	}
+
+	return 0;
+}
+
+struct user_ring_buffer *
+user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts)
+{
+	struct user_ring_buffer *rb;
+	int err;
+
+	if (!OPTS_VALID(opts, user_ring_buffer_opts))
+		return errno = EINVAL, NULL;
+
+	rb = calloc(1, sizeof(*rb));
+	if (!rb)
+		return errno = ENOMEM, NULL;
+
+	rb->page_size = getpagesize();
+
+	rb->epoll_fd = epoll_create1(EPOLL_CLOEXEC);
+	if (rb->epoll_fd < 0) {
+		err = -errno;
+		pr_warn("user ringbuf: failed to create epoll instance: %d\n", err);
+		goto err_out;
+	}
+
+	err = user_ringbuf_map(rb, map_fd);
+	if (err)
+		goto err_out;
+
+	return rb;
+
+err_out:
+	user_ring_buffer__free(rb);
+	return errno = -err, NULL;
+}
+
+static void user_ringbuf_commit(struct user_ring_buffer *rb, void *sample, bool discard)
+{
+	__u32 new_len;
+	struct ringbuf_hdr *hdr;
+	uintptr_t hdr_offset;
+
+	hdr_offset = rb->mask + 1 + (sample - rb->data) - BPF_RINGBUF_HDR_SZ;
+	hdr = rb->data + (hdr_offset & rb->mask);
+
+	new_len = hdr->len & ~BPF_RINGBUF_BUSY_BIT;
+	if (discard)
+		new_len |= BPF_RINGBUF_DISCARD_BIT;
+
+	/* Synchronizes with smp_load_acquire() in __bpf_user_ringbuf_peek() in
+	 * the kernel.
+	 */
+	__atomic_exchange_n(&hdr->len, new_len, __ATOMIC_ACQ_REL);
+}
+
+void user_ring_buffer__discard(struct user_ring_buffer *rb, void *sample)
+{
+	user_ringbuf_commit(rb, sample, true);
+}
+
+void user_ring_buffer__submit(struct user_ring_buffer *rb, void *sample)
+{
+	user_ringbuf_commit(rb, sample, false);
+}
+
+void *user_ring_buffer__reserve(struct user_ring_buffer *rb, __u32 size)
+{
+	__u32 avail_size, total_size, max_size;
+	/* 64-bit to avoid overflow in case of extreme application behavior */
+	__u64 cons_pos, prod_pos;
+	struct ringbuf_hdr *hdr;
+
+	/* 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.
+	 */
+	cons_pos = smp_load_acquire(rb->consumer_pos);
+	/* Synchronizes with smp_store_release() in user_ringbuf_commit() */
+	prod_pos = smp_load_acquire(rb->producer_pos);
+
+	max_size = rb->mask + 1;
+	avail_size = max_size - (prod_pos - cons_pos);
+	/* Round up total size to a multiple of 8. */
+	total_size = (size + BPF_RINGBUF_HDR_SZ + 7) / 8 * 8;
+
+	if (total_size > max_size)
+		return errno = E2BIG, NULL;
+
+	if (avail_size < total_size)
+		return errno = ENOSPC, NULL;
+
+	hdr = rb->data + (prod_pos & rb->mask);
+	hdr->len = size | BPF_RINGBUF_BUSY_BIT;
+	hdr->pad = 0;
+
+	/* Synchronizes with smp_load_acquire() in __bpf_user_ringbuf_peek() in
+	 * the kernel.
+	 */
+	smp_store_release(rb->producer_pos, prod_pos + total_size);
+
+	return (void *)rb->data + ((prod_pos + BPF_RINGBUF_HDR_SZ) & rb->mask);
+}
+
+static __u64 ns_elapsed_timespec(const struct timespec *start, const struct timespec *end)
+{
+	__u64 start_ns, end_ns, ns_per_s = 1000000000;
+
+	start_ns = (__u64)start->tv_sec * ns_per_s + start->tv_nsec;
+	end_ns = (__u64)end->tv_sec * ns_per_s + end->tv_nsec;
+
+	return end_ns - start_ns;
+}
+
+void *user_ring_buffer__reserve_blocking(struct user_ring_buffer *rb, __u32 size, int timeout_ms)
+{
+	void *sample;
+	int err, ms_remaining = timeout_ms;
+	struct timespec start;
+
+	if (timeout_ms < 0 && timeout_ms != -1)
+		return errno = EINVAL, NULL;
+
+	if (timeout_ms != -1) {
+		err = clock_gettime(CLOCK_MONOTONIC, &start);
+		if (err)
+			return NULL;
+	}
+
+	do {
+		int cnt, ms_elapsed;
+		struct timespec curr;
+		__u64 ns_per_ms = 1000000;
+
+		sample = user_ring_buffer__reserve(rb, size);
+		if (sample)
+			return sample;
+		else if (errno != ENOSPC)
+			return NULL;
+
+		/* The kernel guarantees at least one event notification
+		 * delivery whenever at least one sample is drained from the
+		 * ring buffer in an invocation to bpf_ringbuf_drain(). Other
+		 * additional events may be delivered at any time, but only one
+		 * event is guaranteed per bpf_ringbuf_drain() invocation,
+		 * provided that a sample is drained, and the BPF program did
+		 * not pass BPF_RB_NO_WAKEUP to bpf_ringbuf_drain(). If
+		 * BPF_RB_FORCE_WAKEUP is passed to bpf_ringbuf_drain(), a
+		 * wakeup event will be delivered even if no samples are
+		 * drained.
+		 */
+		cnt = epoll_wait(rb->epoll_fd, &rb->event, 1, ms_remaining);
+		if (cnt < 0)
+			return NULL;
+
+		if (timeout_ms == -1)
+			continue;
+
+		err = clock_gettime(CLOCK_MONOTONIC, &curr);
+		if (err)
+			return NULL;
+
+		ms_elapsed = ns_elapsed_timespec(&start, &curr) / ns_per_ms;
+		ms_remaining = timeout_ms - ms_elapsed;
+	} while (ms_remaining > 0);
+
+	/* Try one more time to reserve a sample after the specified timeout has elapsed. */
+	return user_ring_buffer__reserve(rb, size);
+}

src/skel_internal.h

@@ -3,9 +3,19 @@
 #ifndef __SKEL_INTERNAL_H
 #define __SKEL_INTERNAL_H
 
+#ifdef __KERNEL__
+#include <linux/fdtable.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/slab.h>
+#include <linux/bpf.h>
+#else
 #include <unistd.h>
 #include <sys/syscall.h>
 #include <sys/mman.h>
+#include <stdlib.h>
+#include "bpf.h"
+#endif
 
 #ifndef __NR_bpf
 # if defined(__mips__) && defined(_ABIO32)
@@ -25,24 +35,23 @@
  * requested during loader program generation.
  */
 struct bpf_map_desc {
-	union {
-		/* input for the loader prog */
-		struct {
-			__aligned_u64 initial_value;
-			__u32 max_entries;
-		};
 	/* output of the loader prog */
-		struct {
 	int map_fd;
-		};
-	};
+	/* input for the loader prog */
+	__u32 max_entries;
+	__aligned_u64 initial_value;
 };
 struct bpf_prog_desc {
 	int prog_fd;
 };
 
+enum {
+	BPF_SKEL_KERNEL = (1ULL << 0),
+};
+
 struct bpf_loader_ctx {
-	size_t sz;
+	__u32 sz;
+	__u32 flags;
 	__u32 log_level;
 	__u32 log_size;
 	__u64 log_buf;
@@ -57,12 +66,144 @@ struct bpf_load_and_run_opts {
 	const char *errstr;
 };
 
+long kern_sys_bpf(__u32 cmd, void *attr, __u32 attr_size);
+
 static inline int skel_sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
 			  unsigned int size)
 {
+#ifdef __KERNEL__
+	return kern_sys_bpf(cmd, attr, size);
+#else
 	return syscall(__NR_bpf, cmd, attr, size);
+#endif
 }
 
+#ifdef __KERNEL__
+static inline int close(int fd)
+{
+	return close_fd(fd);
+}
+
+static inline void *skel_alloc(size_t size)
+{
+	struct bpf_loader_ctx *ctx = kzalloc(size, GFP_KERNEL);
+
+	if (!ctx)
+		return NULL;
+	ctx->flags |= BPF_SKEL_KERNEL;
+	return ctx;
+}
+
+static inline void skel_free(const void *p)
+{
+	kfree(p);
+}
+
+/* skel->bss/rodata maps are populated the following way:
+ *
+ * For kernel use:
+ * skel_prep_map_data() allocates kernel memory that kernel module can directly access.
+ * Generated lskel stores the pointer in skel->rodata and in skel->maps.rodata.initial_value.
+ * The loader program will perform probe_read_kernel() from maps.rodata.initial_value.
+ * skel_finalize_map_data() sets skel->rodata to point to actual value in a bpf map and
+ * does maps.rodata.initial_value = ~0ULL to signal skel_free_map_data() that kvfree
+ * is not nessary.
+ *
+ * For user space:
+ * skel_prep_map_data() mmaps anon memory into skel->rodata that can be accessed directly.
+ * Generated lskel stores the pointer in skel->rodata and in skel->maps.rodata.initial_value.
+ * The loader program will perform copy_from_user() from maps.rodata.initial_value.
+ * skel_finalize_map_data() remaps bpf array map value from the kernel memory into
+ * skel->rodata address.
+ *
+ * The "bpftool gen skeleton -L" command generates lskel.h that is suitable for
+ * both kernel and user space. The generated loader program does
+ * either bpf_probe_read_kernel() or bpf_copy_from_user() from initial_value
+ * depending on bpf_loader_ctx->flags.
+ */
+static inline void skel_free_map_data(void *p, __u64 addr, size_t sz)
+{
+	if (addr != ~0ULL)
+		kvfree(p);
+	/* When addr == ~0ULL the 'p' points to
+	 * ((struct bpf_array *)map)->value. See skel_finalize_map_data.
+	 */
+}
+
+static inline void *skel_prep_map_data(const void *val, size_t mmap_sz, size_t val_sz)
+{
+	void *addr;
+
+	addr = kvmalloc(val_sz, GFP_KERNEL);
+	if (!addr)
+		return NULL;
+	memcpy(addr, val, val_sz);
+	return addr;
+}
+
+static inline void *skel_finalize_map_data(__u64 *init_val, size_t mmap_sz, int flags, int fd)
+{
+	struct bpf_map *map;
+	void *addr = NULL;
+
+	kvfree((void *) (long) *init_val);
+	*init_val = ~0ULL;
+
+	/* At this point bpf_load_and_run() finished without error and
+	 * 'fd' is a valid bpf map FD. All sanity checks below should succeed.
+	 */
+	map = bpf_map_get(fd);
+	if (IS_ERR(map))
+		return NULL;
+	if (map->map_type != BPF_MAP_TYPE_ARRAY)
+		goto out;
+	addr = ((struct bpf_array *)map)->value;
+	/* the addr stays valid, since FD is not closed */
+out:
+	bpf_map_put(map);
+	return addr;
+}
+
+#else
+
+static inline void *skel_alloc(size_t size)
+{
+	return calloc(1, size);
+}
+
+static inline void skel_free(void *p)
+{
+	free(p);
+}
+
+static inline void skel_free_map_data(void *p, __u64 addr, size_t sz)
+{
+	munmap(p, sz);
+}
+
+static inline void *skel_prep_map_data(const void *val, size_t mmap_sz, size_t val_sz)
+{
+	void *addr;
+
+	addr = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE,
+		    MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	if (addr == (void *) -1)
+		return NULL;
+	memcpy(addr, val, val_sz);
+	return addr;
+}
+
+static inline void *skel_finalize_map_data(__u64 *init_val, size_t mmap_sz, int flags, int fd)
+{
+	void *addr;
+
+	addr = mmap((void *) (long) *init_val, mmap_sz, flags, MAP_SHARED | MAP_FIXED, fd, 0);
+	if (addr == (void *) -1)
+		return NULL;
+	return addr;
+}
+#endif
+
 static inline int skel_closenz(int fd)
 {
 	if (fd > 0)
@@ -110,6 +251,29 @@ static inline int skel_map_update_elem(int fd, const void *key,
 	return skel_sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, attr_sz);
 }
 
+static inline int skel_map_delete_elem(int fd, const void *key)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_sz);
+	attr.map_fd = fd;
+	attr.key = (long)key;
+
+	return skel_sys_bpf(BPF_MAP_DELETE_ELEM, &attr, attr_sz);
+}
+
+static inline int skel_map_get_fd_by_id(__u32 id)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_sz);
+	attr.map_id = id;
+
+	return skel_sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, attr_sz);
+}
+
 static inline int skel_raw_tracepoint_open(const char *name, int prog_fd)
 {
 	const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint.prog_fd);
@@ -136,26 +300,34 @@ static inline int skel_link_create(int prog_fd, int target_fd,
 	return skel_sys_bpf(BPF_LINK_CREATE, &attr, attr_sz);
 }
 
+#ifdef __KERNEL__
+#define set_err
+#else
+#define set_err err = -errno
+#endif
+
 static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
 {
+	const size_t prog_load_attr_sz = offsetofend(union bpf_attr, fd_array);
+	const size_t test_run_attr_sz = offsetofend(union bpf_attr, test);
 	int map_fd = -1, prog_fd = -1, key = 0, err;
 	union bpf_attr attr;
 
-	map_fd = skel_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1);
+	err = map_fd = skel_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1);
 	if (map_fd < 0) {
 		opts->errstr = "failed to create loader map";
-		err = -errno;
+		set_err;
 		goto out;
 	}
 
 	err = skel_map_update_elem(map_fd, &key, opts->data, 0);
 	if (err < 0) {
 		opts->errstr = "failed to update loader map";
-		err = -errno;
+		set_err;
 		goto out;
 	}
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, prog_load_attr_sz);
 	attr.prog_type = BPF_PROG_TYPE_SYSCALL;
 	attr.insns = (long) opts->insns;
 	attr.insn_cnt = opts->insns_sz / sizeof(struct bpf_insn);
@@ -166,25 +338,27 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
 	attr.log_size = opts->ctx->log_size;
 	attr.log_buf = opts->ctx->log_buf;
 	attr.prog_flags = BPF_F_SLEEPABLE;
-	prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+	err = prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, prog_load_attr_sz);
 	if (prog_fd < 0) {
 		opts->errstr = "failed to load loader prog";
-		err = -errno;
+		set_err;
 		goto out;
 	}
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, test_run_attr_sz);
 	attr.test.prog_fd = prog_fd;
 	attr.test.ctx_in = (long) opts->ctx;
 	attr.test.ctx_size_in = opts->ctx->sz;
-	err = skel_sys_bpf(BPF_PROG_RUN, &attr, sizeof(attr));
+	err = skel_sys_bpf(BPF_PROG_RUN, &attr, test_run_attr_sz);
 	if (err < 0 || (int)attr.test.retval < 0) {
 		opts->errstr = "failed to execute loader prog";
 		if (err < 0) {
-			err = -errno;
+			set_err;
 		} else {
 			err = (int)attr.test.retval;
+#ifndef __KERNEL__
 			errno = -err;
+#endif
 		}
 		goto out;
 	}

src/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.bpf.h

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

src/xsk.h

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

travis-ci/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

travis-ci/managers/test_compile.sh

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

travis-ci/rootfs/mkrootfs_arch.sh

@@ -1,106 +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 "$PWD")"
-
-packages=(
-	busybox
-	# libbpf dependencies.
-	libelf
-	zlib
-	# selftests test_progs dependencies.
-	binutils
-	elfutils
-	glibc
-	iproute2
-	# selftests test_verifier dependencies.
-	libcap
-)
-
-pacstrap -C "$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"

travis-ci/rootfs/mkrootfs_debian.sh

@@ -1,40 +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.
-
-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,iproute2,libcap2,libelf1,strace,zlib1g
-debootstrap --include="$packages" --variant=minbase bullseye "$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/*
-
-# Save some more space by removing coreutils - the tests use busybox. Before
-# doing that, delete the buggy postrm script, which uses the rm command.
-rm -f "$root/var/lib/dpkg/info/coreutils.postrm"
-chroot "$root" dpkg --remove --force-remove-essential coreutils
-
-# 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"

travis-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"

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

@@ -1,74 +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 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.
-
-## Configuring the builder.
-
-### Install prerequisites.
-
-```
-$ sudo dnf install docker        # RHEL
-$ 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_***>
-```
-
-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.
-
-```
-$ 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
-```

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

@@ -1,50 +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
-
-# 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=2.285.0
-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"]

travis-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

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

@@ -1,40 +0,0 @@
-#!/bin/bash
-
-#
-# Ephemeral runner startup script.
-#
-# Expects the following environment variables:
-#
-# - repo=<owner>/<name>
-# - access_token=<ghp_***>
-#
-
-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 \
-    --ephemeral
-
-# Run one job.
-./run.sh

travis-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"

travis-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

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

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

travis-ci/vmtest/configs/blacklist/BLACKLIST-latest.s390x

@@ -1,56 +0,0 @@
-# TEMPORARY
-atomics                                  # attach(add): actual -524 <= expected 0                                      (trampoline)
-bpf_iter_setsockopt                      # JIT does not support calling kernel function                                (kfunc)
-bloom_filter_map                         # failed to find kernel BTF type ID of '__x64_sys_getpgid': -3                (?)
-bpf_tcp_ca                               # JIT does not support calling kernel function                                (kfunc)
-bpf_loop                                 # attaches to __x64_sys_nanosleep
-bpf_mod_race                             # BPF trampoline
-bpf_nf                                   # JIT does not support calling kernel function
-core_read_macros                         # unknown func bpf_probe_read#4                                               (overlapping)
-d_path                                   # failed to auto-attach program 'prog_stat': -524                             (trampoline)
-dummy_st_ops                             # test_run unexpected error: -524 (errno 524)                                 (trampoline)
-fentry_fexit                             # fentry attach failed: -524                                                  (trampoline)
-fentry_test                              # fentry_first_attach unexpected error: -524                                  (trampoline)
-fexit_bpf2bpf                            # freplace_attach_trace unexpected error: -524                                (trampoline)
-fexit_sleep                              # fexit_skel_load fexit skeleton failed                                       (trampoline)
-fexit_stress                             # fexit attach failed prog 0 failed: -524                                     (trampoline)
-fexit_test                               # fexit_first_attach unexpected error: -524                                   (trampoline)
-get_func_args_test	                 # trampoline
-get_func_ip_test                         # get_func_ip_test__attach unexpected error: -524                             (trampoline)
-get_stack_raw_tp                         # user_stack corrupted user stack                                             (no backchain userspace)
-kfree_skb                                # attach fentry unexpected error: -524                                        (trampoline)
-kfunc_call                               # 'bpf_prog_active': not found in kernel BTF                                  (?)
-ksyms_module                             # test_ksyms_module__open_and_load unexpected error: -9                       (?)
-ksyms_module_libbpf                      # JIT does not support calling kernel function                                (kfunc)
-ksyms_module_lskel                       # test_ksyms_module_lskel__open_and_load unexpected error: -9                 (?)
-modify_return                            # modify_return attach failed: -524                                           (trampoline)
-module_attach                            # skel_attach skeleton attach failed: -524                                    (trampoline)
-netcnt                                   # failed to load BPF skeleton 'netcnt_prog': -7                               (?)
-probe_user                               # check_kprobe_res wrong kprobe res from probe read                           (?)
-recursion                                # skel_attach unexpected error: -524                                          (trampoline)
-ringbuf                                  # skel_load skeleton load failed                                              (?)
-sk_assign                                # Can't read on server: Invalid argument                                      (?)
-sk_storage_tracing                       # test_sk_storage_tracing__attach unexpected error: -524                      (trampoline)
-skc_to_unix_sock                         # could not attach BPF object unexpected error: -524                          (trampoline)
-socket_cookie                            # prog_attach unexpected error: -524                                          (trampoline)
-stacktrace_build_id                      # compare_map_keys stackid_hmap vs. stackmap err -2 errno 2                   (?)
-tailcalls                                # tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls      (?)
-task_local_storage                       # failed to auto-attach program 'trace_exit_creds': -524                      (trampoline)
-test_bpffs                               # bpffs test  failed 255                                                      (iterator)
-test_bprm_opts                           # failed to auto-attach program 'secure_exec': -524                           (trampoline)
-test_ima                                 # failed to auto-attach program 'ima': -524                                   (trampoline)
-test_local_storage                       # failed to auto-attach program 'unlink_hook': -524                           (trampoline)
-test_lsm                                 # failed to find kernel BTF type ID of '__x64_sys_setdomainname': -3          (?)
-test_overhead                            # attach_fentry unexpected error: -524                                        (trampoline)
-test_profiler                            # unknown func bpf_probe_read_str#45                                          (overlapping)
-timer                                    # failed to auto-attach program 'test1': -524                                 (trampoline)
-timer_mim                                # failed to auto-attach program 'test1': -524                                 (trampoline)
-trace_ext                                # failed to auto-attach program 'test_pkt_md_access_new': -524                (trampoline)
-trace_printk                             # trace_printk__load unexpected error: -2 (errno 2)                           (?)
-trace_vprintk                            # trace_vprintk__open_and_load unexpected error: -9                           (?)
-trampoline_count                         # prog 'prog1': failed to attach: ERROR: strerror_r(-524)=22                  (trampoline)
-verif_stats                              # trace_vprintk__open_and_load unexpected error: -9                           (?)
-vmlinux                                  # failed to auto-attach program 'handle__fentry': -524                        (trampoline)
-xdp_adjust_tail                          # case-128 err 0 errno 28 retval 1 size 128 expect-size 3520                  (?)
-xdp_bonding                              # failed to auto-attach program 'trace_on_entry': -524                        (trampoline)
-xdp_bpf2bpf                              # failed to auto-attach program 'trace_on_entry': -524                        (trampoline)

travis-ci/vmtest/run_selftests.sh

@@ -1,63 +0,0 @@
-#!/bin/bash
-
-set -euo pipefail
-
-source $(cd $(dirname $0) && pwd)/helpers.sh
-
-ARCH=$(uname -m)
-
-STATUS_FILE=/exitstatus
-
-read_lists() {
-	(for path in "$@"; do
-		if [[ -s "$path" ]]; then
-			cat "$path"
-		fi;
-	done) | cut -d'#' -f1 | tr -s ' \t\n' ','
-}
-
-test_progs() {
-	if [[ "${KERNEL}" != '4.9.0' ]]; then
-		travis_fold start test_progs "Testing test_progs"
-		# "&& true" does not change the return code (it is not executed
-		# if the Python script fails), but it prevents exiting on a
-		# failure due to the "set -e".
-		./test_progs ${BLACKLIST:+-d$BLACKLIST} ${WHITELIST:+-a$WHITELIST} && true
-		echo "test_progs:$?" >> "${STATUS_FILE}"
-		travis_fold end test_progs
-	fi
-
-	travis_fold start test_progs-no_alu32 "Testing test_progs-no_alu32"
-	./test_progs-no_alu32 ${BLACKLIST:+-d$BLACKLIST} ${WHITELIST:+-a$WHITELIST} && true
-	echo "test_progs-no_alu32:$?" >> "${STATUS_FILE}"
-	travis_fold end test_progs-no_alu32
-}
-
-test_maps() {
-	travis_fold start test_maps "Testing test_maps"
-	./test_maps && true
-	echo "test_maps:$?" >> "${STATUS_FILE}"
-	travis_fold end test_maps
-}
-
-test_verifier() {
-	travis_fold start test_verifier "Testing test_verifier"
-	./test_verifier && true
-	echo "test_verifier:$?" >> "${STATUS_FILE}"
-	travis_fold end test_verifier
-}
-
-travis_fold end vm_init
-
-configs_path=${PROJECT_NAME}/vmtest/configs
-BLACKLIST=$(read_lists "$configs_path/blacklist/BLACKLIST-${KERNEL}" "$configs_path/blacklist/BLACKLIST-${KERNEL}.${ARCH}")
-WHITELIST=$(read_lists "$configs_path/whitelist/WHITELIST-${KERNEL}" "$configs_path/whitelist/WHITELIST-${KERNEL}.${ARCH}")
-
-cd ${PROJECT_NAME}/selftests/bpf
-
-test_progs
-
-if [[ "${KERNEL}" == 'latest' ]]; then
-	# test_maps
-	test_verifier
-fi