Merge branch 'libbpf:master' into master

Update checked in vmlinux.h for 5.5 kernel tests.

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

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

@@ -18,9 +18,10 @@ runs:
   steps:
     - shell: bash
       run: |
-        echo "::group::Setup Env"
+        source $GITHUB_ACTION_PATH/../../../ci/vmtest/helpers.sh
+        foldable start "Setup Env"
         sudo apt-get install -y qemu-kvm zstd binutils-dev elfutils libcap-dev libelf-dev libdw-dev python3-docutils
-        echo "::endgroup::"
+        foldable end
     - shell: bash
       run: |
         export KERNEL=${{ inputs.kernel }}

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

@@ -6,9 +6,9 @@ THISDIR="$(cd $(dirname $0) && pwd)"
 
 source ${THISDIR}/helpers.sh
 
-travis_fold start prepare_selftests "Building selftests"
+foldable start prepare_selftests "Building selftests"
 
-LLVM_VER=15
+LLVM_VER=16
 LIBBPF_PATH="${REPO_ROOT}"
 
 PREPARE_SELFTESTS_SCRIPT=${THISDIR}/prepare_selftests-${KERNEL}.sh
@@ -39,4 +39,4 @@ cd ${LIBBPF_PATH}
 rm selftests/bpf/.gitignore
 git add selftests
 
-travis_fold end prepare_selftests
+foldable end prepare_selftests

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

@@ -1,26 +1,18 @@
 # $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 [ $1 = "start" ]; then
+    line="::group::$2"
     if [ ! -z "${3:-}" ]; then
-      echo -e "${YELLOW}$3${NOCOLOR}"
+      line="$line - ${YELLOW}$3${NOCOLOR}"
     fi
-    echo
   else
-    if [ $1 = "start" ]; then
-      line="::group::$2"
-      if [ ! -z "${3:-}" ]; then
-        line="$line - ${YELLOW}$3${NOCOLOR}"
-      fi
-    else
-      line="::endgroup::"
-    fi
-    echo -e "$line"
+    line="::endgroup::"
   fi
+  echo -e "$line"
 }
 
 __print() {

.github/actions/vmtest/action.yml

@@ -16,7 +16,7 @@ inputs:
 runs:
   using: "composite"
   steps:
-    # setup envinronment
+    # setup environment
     - name: Setup environment
       uses: libbpf/ci/setup-build-env@master
       with:
@@ -41,23 +41,26 @@ runs:
     - name: Prepare to build BPF selftests
       shell: bash
       run: |
-        echo "::group::Prepare buidling selftest"
+        source $GITHUB_ACTION_PATH/../../../ci/vmtest/helpers.sh
+        foldable start "Prepare building selftest"
         cd .kernel
-        cp ${{ github.workspace }}/travis-ci/vmtest/configs/config-latest.${{ inputs.arch }} .config
+        cat tools/testing/selftests/bpf/config \
+            tools/testing/selftests/bpf/config.${{ inputs.arch }} > .config
         make olddefconfig && make prepare
         cd -
-        echo "::endgroup::"
+        foldable end
     # 2. if kernel == LATEST, build kernel image from tree
     - name: Build kernel image
       if: ${{ inputs.kernel == 'LATEST' }}
       shell: bash
       run: |
-        echo "::group::Build Kernel Image"
+        source $GITHUB_ACTION_PATH/../../../ci/vmtest/helpers.sh
+        foldable start "Build Kernel Image"
         cd .kernel
         make -j $((4*$(nproc))) all > /dev/null
         cp vmlinux ${{ github.workspace }}
         cd -
-        echo "::endgroup::"
+        foldable end
     # else, just download prebuilt kernel image
     - name: Download prebuilt kernel
       if: ${{ inputs.kernel != 'LATEST' }}
@@ -75,13 +78,19 @@ runs:
     - name: prepare rootfs
       uses: libbpf/ci/prepare-rootfs@master
       with:
-        kernel: ${{ inputs.kernel }}
         project-name: 'libbpf'
         arch: ${{ inputs.arch }}
+        kernel: ${{ inputs.kernel }}
+        kernel-root: '.kernel'
+        image-output: '/tmp/root.img'
     # 5. run selftest in QEMU
     - name: Run selftests
+      env:
+        KERNEL: ${{ inputs.kernel }}
+        REPO_ROOT: ${{ github.workspace }}
       uses: libbpf/ci/run-qemu@master
       with:
+        arch: ${{ inputs.arch }}
         img: '/tmp/root.img'
         vmlinuz: 'vmlinuz'
-        arch: ${{ inputs.arch }}
+        kernel-root: '.kernel'

.github/workflows/build.yml

@@ -32,7 +32,7 @@ jobs:
           - name: gcc-10 ASan+UBSan
             target: RUN_GCC10_ASAN
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
         name: Checkout
       - uses: ./.github/actions/setup
         name: Setup
@@ -53,7 +53,7 @@ jobs:
           - arch: s390x
           - arch: x86
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
         name: Checkout
       - uses: ./.github/actions/setup
         name: Pre-Setup

.github/workflows/coverity.yml

@@ -11,16 +11,17 @@ jobs:
     if: github.repository == 'libbpf/libbpf'
     name: Coverity
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - uses: ./.github/actions/setup
       - name: Run coverity
         run: |
-          echo ::group::Setup CI env
+          source "${GITHUB_WORKSPACE}"/ci/vmtest/helpers.sh
+          foldable start "Setup CI env"
           source /tmp/ci_setup
           export COVERITY_SCAN_NOTIFICATION_EMAIL="${AUTHOR_EMAIL}"
           export COVERITY_SCAN_BRANCH_PATTERN=${GITHUB_REF##refs/*/}
           export TRAVIS_BRANCH=${COVERITY_SCAN_BRANCH_PATTERN}
-          echo ::endgroup::
+          foldable end
           scripts/coverity.sh
         env:
           COVERITY_SCAN_TOKEN: ${{ secrets.COVERITY_SCAN_TOKEN }}

.github/workflows/ondemand.yml

@@ -25,7 +25,7 @@ jobs:
     runs-on: ubuntu-latest
     name: vmtest with customized pahole/Kernel
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - uses: ./.github/actions/setup
       - uses: ./.github/actions/vmtest
         with:

.github/workflows/pahole.yml

@@ -12,7 +12,7 @@ jobs:
     env:
       STAGING: tmp.master
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - uses: ./.github/actions/setup
       - uses: ./.github/actions/vmtest
         with:

.github/workflows/test.yml

@@ -31,7 +31,7 @@ jobs:
             runs_on: z15
             arch: 's390x'
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
         name: Checkout
       - uses: ./.github/actions/setup
         name: Setup

BPF-CHECKPOINT-COMMIT

@@ -1 +1 @@
-d28b25a62a47a8c8aa19bd543863aab6717e68c9
+60240bc26114543fcbfcd8a28466e67e77b20388

CHECKPOINT-COMMIT

@@ -1 +1 @@
-b0d93b44641a83c28014ca38001e85bf6dc8501e
+87dbdc230d162bf9ee1ac77c8ade178b6b1e199e

README.md

@@ -1,17 +1,32 @@
-This is a mirror of [bpf-next Linux source
-tree](https://kernel.googlesource.com/pub/scm/linux/kernel/git/bpf/bpf-next)'s
-`tools/lib/bpf` directory plus its supporting header files.
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="assets/libbpf-logo-sideways-darkbg.png" width="40%">
+  <img src="assets/libbpf-logo-sideways.png" width="40%">
+</picture>
 
-All the gory details of syncing can be found in `scripts/sync-kernel.sh`
-script.
+libbpf
+[![Github Actions Builds & Tests](https://github.com/libbpf/libbpf/actions/workflows/test.yml/badge.svg)](https://github.com/libbpf/libbpf/actions/workflows/test.yml)
+[![Total alerts](https://img.shields.io/lgtm/alerts/g/libbpf/libbpf.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/libbpf/libbpf/alerts/)
+[![Coverity](https://img.shields.io/coverity/scan/18195.svg)](https://scan.coverity.com/projects/libbpf)
+[![OSS-Fuzz Status](https://oss-fuzz-build-logs.storage.googleapis.com/badges/libbpf.svg)](https://oss-fuzz-build-logs.storage.googleapis.com/index.html#libbpf)
+======
 
-Some header files in this repo (`include/linux/*.h`) are reduced versions of
-their counterpart files at
-[bpf-next](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/)'s
-`tools/include/linux/*.h` to make compilation successful.
+**This is the official home of the libbpf library.**
 
-BPF/libbpf usage and questions
-==============================
+*Please use this Github repository for building and packaging libbpf
+and when using it in your projects through Git submodule.*
+
+Libbpf *authoritative source code* is developed as part of [bpf-next Linux source
+tree](https://kernel.googlesource.com/pub/scm/linux/kernel/git/bpf/bpf-next) under
+`tools/lib/bpf` subdirectory and is periodically synced to Github. As such, all the
+libbpf changes should be sent to [BPF mailing list](http://vger.kernel.org/vger-lists.html#bpf),
+please don't open PRs here unless you are changing Github-specific parts of libbpf
+(e.g., Github-specific Makefile).
+
+Libbpf and general BPF usage questions
+======================================
+
+Libbpf documentation can be found [here](https://libbpf.readthedocs.io/en/latest/api.html).
+It's an ongoing effort and has ways to go, but please take a look and consider contributing as well.
 
 Please check out [libbpf-bootstrap](https://github.com/libbpf/libbpf-bootstrap)
 and [the companion blog post](https://nakryiko.com/posts/libbpf-bootstrap/) for
@@ -36,12 +51,8 @@ to help you with whatever issue you have. This repository's PRs and issues
 should be opened only for dealing with issues pertaining to specific way this
 libbpf mirror repo is set up and organized.
 
-Build
-[![Github Actions Builds & Tests](https://github.com/libbpf/libbpf/actions/workflows/test.yml/badge.svg)](https://github.com/libbpf/libbpf/actions/workflows/test.yml)
-[![Total alerts](https://img.shields.io/lgtm/alerts/g/libbpf/libbpf.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/libbpf/libbpf/alerts/)
-[![Coverity](https://img.shields.io/coverity/scan/18195.svg)](https://scan.coverity.com/projects/libbpf)
-[![OSS-Fuzz Status](https://oss-fuzz-build-logs.storage.googleapis.com/badges/libbpf.svg)](https://oss-fuzz-build-logs.storage.googleapis.com/index.html#libbpf)
-=====
+Building libbpf
+===============
 libelf is an internal dependency of libbpf and thus it is required to link
 against and must be installed on the system for applications to work.
 pkg-config is used by default to find libelf, and the program called can be
@@ -156,6 +167,18 @@ Package dependencies of libbpf, package names may vary across distros:
 
 [![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

@@ -76,7 +76,7 @@ for phase in "${PHASES[@]}"; do
             info "install"
             docker_exec make -j$((4*$(nproc))) -C src OBJDIR=../build DESTDIR=../install install
             info "link binary"
-            docker_exec bash -c "EXTRA_CFLAGS=\"${EXTRA_CFLAGS}\" EXTRA_LDFLAGS=\"${EXTRA_LDFLAGS}\" ./travis-ci/managers/test_compile.sh"
+            docker_exec bash -c "EXTRA_CFLAGS=\"${EXTRA_CFLAGS}\" EXTRA_LDFLAGS=\"${EXTRA_LDFLAGS}\" ./ci/managers/test_compile.sh"
             ;;
         CLEANUP)
             info "Cleanup phase"

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

@@ -36,6 +36,7 @@ $ sudo systemctl daemon-reload
 $ sudo tee /etc/actions-runner-libbpf
 repo=<owner>/<name>
 access_token=<ghp_***>
+runner_name=<hostname>
 ```
 
 Access token should have the repo scope, consult

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

@@ -24,7 +24,9 @@ RUN apt-get update && apt-get -y install \
         rsync \
         software-properties-common \
         sudo \
-        tree
+        tree \
+        iproute2 \
+        iputils-ping
 
 # amd64 dependencies.
 COPY --from=ld-prefix / /usr/x86_64-linux-gnu/
@@ -33,7 +35,7 @@ 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
+ARG version=2.296.0
 RUN useradd -m actions-runner
 RUN echo "actions-runner ALL=(ALL) NOPASSWD: ALL" >>/etc/sudoers
 RUN echo "Defaults env_keep += \"DEBIAN_FRONTEND\"" >>/etc/sudoers

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

@@ -7,7 +7,7 @@
 #
 # - repo=<owner>/<name>
 # - access_token=<ghp_***>
-#
+# - runner_name=<hostname>
 
 set -e -u
 
@@ -34,6 +34,7 @@ registration_token=$(jq --raw-output .token "$token_file")
     --url "https://github.com/$repo" \
     --token "$registration_token" \
     --labels z15 \
+    --name "$runner_name" \
     --ephemeral
 
 # Run one job.

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

ci/vmtest/helpers.sh

@@ -1,26 +1,18 @@
 # $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 [ $1 = "start" ]; then
+    line="::group::$2"
     if [ ! -z "${3:-}" ]; then
-      echo -e "${YELLOW}$3${NOCOLOR}"
+      line="$line - ${YELLOW}$3${NOCOLOR}"
     fi
-    echo
   else
-    if [ $1 = "start" ]; then
-      line="::group::$2"
-      if [ ! -z "${3:-}" ]; then
-        line="$line - ${YELLOW}$3${NOCOLOR}"
-      fi
-    else
-      line="::endgroup::"
-    fi
-    echo -e "$line"
+    line="::endgroup::"
   fi
+  echo -e "$line"
 }
 
 __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/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
 ---
 

include/uapi/linux/bpf.h

@@ -87,10 +87,29 @@ struct bpf_cgroup_storage_key {
 	__u32	attach_type;		/* program attach type (enum bpf_attach_type) */
 };
 
+enum bpf_cgroup_iter_order {
+	BPF_CGROUP_ITER_ORDER_UNSPEC = 0,
+	BPF_CGROUP_ITER_SELF_ONLY,		/* process only a single object. */
+	BPF_CGROUP_ITER_DESCENDANTS_PRE,	/* walk descendants in pre-order. */
+	BPF_CGROUP_ITER_DESCENDANTS_POST,	/* walk descendants in post-order. */
+	BPF_CGROUP_ITER_ANCESTORS_UP,		/* walk ancestors upward. */
+};
+
 union bpf_iter_link_info {
 	struct {
 		__u32	map_fd;
 	} map;
+	struct {
+		enum bpf_cgroup_iter_order order;
+
+		/* At most one of cgroup_fd and cgroup_id can be non-zero. If
+		 * both are zero, the walk starts from the default cgroup v2
+		 * root. For walking v1 hierarchy, one should always explicitly
+		 * specify cgroup_fd.
+		 */
+		__u32	cgroup_fd;
+		__u64	cgroup_id;
+	} cgroup;
 };
 
 /* BPF syscall commands, see bpf(2) man-page for more details. */
@@ -909,6 +928,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_INODE_STORAGE,
 	BPF_MAP_TYPE_TASK_STORAGE,
 	BPF_MAP_TYPE_BLOOM_FILTER,
+	BPF_MAP_TYPE_USER_RINGBUF,
 };
 
 /* Note that tracing related programs such as
@@ -1233,7 +1253,7 @@ enum {
 
 /* Query effective (directly attached + inherited from ancestor cgroups)
  * programs that will be executed for events within a cgroup.
- * attach_flags with this flag are returned only for directly attached programs.
+ * attach_flags with this flag are always returned 0.
  */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 
@@ -1432,7 +1452,10 @@ union bpf_attr {
 		__u32		attach_flags;
 		__aligned_u64	prog_ids;
 		__u32		prog_cnt;
-		__aligned_u64	prog_attach_flags; /* output: per-program attach_flags */
+		/* output: per-program attach_flags.
+		 * not allowed to be set during effective query.
+		 */
+		__aligned_u64	prog_attach_flags;
 	} query;
 
 	struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */
@@ -2361,7 +2384,8 @@ union bpf_attr {
  * 		Pull in non-linear data in case the *skb* is non-linear and not
  * 		all of *len* are part of the linear section. Make *len* bytes
  * 		from *skb* readable and writable. If a zero value is passed for
- * 		*len*, then the whole length of the *skb* is pulled.
+ *		*len*, then all bytes in the linear part of *skb* will be made
+ *		readable and writable.
  *
  * 		This helper is only needed for reading and writing with direct
  * 		packet access.
@@ -2572,10 +2596,12 @@ union bpf_attr {
  *		There are two supported modes at this time:
  *
  *		* **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
- *		  (room space is added or removed below the layer 2 header).
+ * 		  (room space is added or removed between the layer 2 and
+ * 		  layer 3 headers).
  *
  * 		* **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
- * 		  (room space is added or removed below the layer 3 header).
+ * 		  (room space is added or removed between the layer 3 and
+ * 		  layer 4 headers).
  *
  *		The following flags are supported at this time:
  *
@@ -3007,8 +3033,18 @@ union bpf_attr {
  * 		**BPF_F_USER_STACK**
  * 			Collect a user space stack instead of a kernel stack.
  * 		**BPF_F_USER_BUILD_ID**
- * 			Collect buildid+offset instead of ips for user stack,
- * 			only valid if **BPF_F_USER_STACK** is also specified.
+ * 			Collect (build_id, file_offset) instead of ips for user
+ * 			stack, only valid if **BPF_F_USER_STACK** is also
+ * 			specified.
+ *
+ * 			*file_offset* is an offset relative to the beginning
+ * 			of the executable or shared object file backing the vma
+ * 			which the *ip* falls in. It is *not* an offset relative
+ * 			to that object's base address. Accordingly, it must be
+ * 			adjusted by adding (sh_addr - sh_offset), where
+ * 			sh_{addr,offset} correspond to the executable section
+ * 			containing *file_offset* in the object, for comparisons
+ * 			to symbols' st_value to be valid.
  *
  * 		**bpf_get_stack**\ () can collect up to
  * 		**PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
@@ -4424,7 +4460,7 @@ union bpf_attr {
  *
  *		**-EEXIST** if the option already exists.
  *
- *		**-EFAULT** on failrue to parse the existing header options.
+ *		**-EFAULT** on failure to parse the existing header options.
  *
  *		**-EPERM** if the helper cannot be used under the current
  *		*skops*\ **->op**.
@@ -4633,7 +4669,7 @@ union bpf_attr {
  *		a *map* with *task* as the **key**.  From this
  *		perspective,  the usage is not much different from
  *		**bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this
- *		helper enforces the key must be an task_struct and the map must also
+ *		helper enforces the key must be a task_struct and the map must also
  *		be a **BPF_MAP_TYPE_TASK_STORAGE**.
  *
  *		Underneath, the value is stored locally at *task* instead of
@@ -4691,7 +4727,7 @@ union bpf_attr {
  *
  * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size)
  *	Description
- *		Returns the stored IMA hash of the *inode* (if it's avaialable).
+ *		Returns the stored IMA hash of the *inode* (if it's available).
  *		If the hash is larger than *size*, then only *size*
  *		bytes will be copied to *dst*
  *	Return
@@ -4715,12 +4751,12 @@ union bpf_attr {
  *
  *		The argument *len_diff* can be used for querying with a planned
  *		size change. This allows to check MTU prior to changing packet
- *		ctx. Providing an *len_diff* adjustment that is larger than the
+ *		ctx. Providing a *len_diff* adjustment that is larger than the
  *		actual packet size (resulting in negative packet size) will in
- *		principle not exceed the MTU, why it is not considered a
- *		failure.  Other BPF-helpers are needed for performing the
- *		planned size change, why the responsability for catch a negative
- *		packet size belong in those helpers.
+ *		principle not exceed the MTU, which is why it is not considered
+ *		a failure.  Other BPF helpers are needed for performing the
+ *		planned size change; therefore the responsibility for catching
+ *		a negative packet size belongs in those helpers.
  *
  *		Specifying *ifindex* zero means the MTU check is performed
  *		against the current net device.  This is practical if this isn't
@@ -4918,6 +4954,7 @@ union bpf_attr {
  * 		Get address of the traced function (for tracing and kprobe programs).
  * 	Return
  * 		Address of the traced function.
+ * 		0 for kprobes placed within the function (not at the entry).
  *
  * u64 bpf_get_attach_cookie(void *ctx)
  * 	Description
@@ -5047,12 +5084,12 @@ union bpf_attr {
  *
  * long bpf_get_func_arg(void *ctx, u32 n, u64 *value)
  *	Description
- *		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**.
  *
  *	Return
  *		0 on success.
- *		**-EINVAL** if n >= arguments count of traced function.
+ *		**-EINVAL** if n >= argument register count of traced function.
  *
  * long bpf_get_func_ret(void *ctx, u64 *value)
  *	Description
@@ -5065,24 +5102,37 @@ union bpf_attr {
  *
  * long bpf_get_func_arg_cnt(void *ctx)
  *	Description
- *		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.
  *
  *	Return
- *		The number of arguments of the traced function.
+ *		The number of argument registers of the traced function.
  *
  * int bpf_get_retval(void)
  *	Description
- *		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.
  *	Return
- *		The syscall's return value.
+ *		The BPF program's return value.
  *
  * int bpf_set_retval(int retval)
  *	Description
- *		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.
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
@@ -5226,22 +5276,25 @@ union bpf_attr {
  *	Return
  *		Nothing. Always succeeds.
  *
- * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset)
+ * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset, u64 flags)
  *	Description
  *		Read *len* bytes from *src* into *dst*, starting from *offset*
  *		into *src*.
+ *		*flags* is currently unused.
  *	Return
  *		0 on success, -E2BIG if *offset* + *len* exceeds the length
- *		of *src*'s data, -EINVAL if *src* is an invalid dynptr.
+ *		of *src*'s data, -EINVAL if *src* is an invalid dynptr or if
+ *		*flags* is not 0.
  *
- * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len)
+ * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags)
  *	Description
  *		Write *len* bytes from *src* into *dst*, starting from *offset*
  *		into *dst*.
+ *		*flags* is currently unused.
  *	Return
  *		0 on success, -E2BIG if *offset* + *len* exceeds the length
  *		of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst*
- *		is a read-only dynptr.
+ *		is a read-only dynptr or if *flags* is not 0.
  *
  * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len)
  *	Description
@@ -5327,6 +5380,55 @@ union bpf_attr {
  *		**-EACCES** if the SYN cookie is not valid.
  *
  *		**-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
+ *
+ * u64 bpf_ktime_get_tai_ns(void)
+ *	Description
+ *		A nonsettable system-wide clock derived from wall-clock time but
+ *		ignoring leap seconds.  This clock does not experience
+ *		discontinuities and backwards jumps caused by NTP inserting leap
+ *		seconds as CLOCK_REALTIME does.
+ *
+ *		See: **clock_gettime**\ (**CLOCK_TAI**)
+ *	Return
+ *		Current *ktime*.
+ *
+ * long bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void *ctx, u64 flags)
+ *	Description
+ *		Drain samples from the specified user ring buffer, and invoke
+ *		the provided callback for each such sample:
+ *
+ *		long (\*callback_fn)(struct bpf_dynptr \*dynptr, void \*ctx);
+ *
+ *		If **callback_fn** returns 0, the helper will continue to try
+ *		and drain the next sample, up to a maximum of
+ *		BPF_MAX_USER_RINGBUF_SAMPLES samples. If the return value is 1,
+ *		the helper will skip the rest of the samples and return. Other
+ *		return values are not used now, and will be rejected by the
+ *		verifier.
+ *	Return
+ *		The number of drained samples if no error was encountered while
+ *		draining samples, or 0 if no samples were present in the ring
+ *		buffer. If a user-space producer was epoll-waiting on this map,
+ *		and at least one sample was drained, they will receive an event
+ *		notification notifying them of available space in the ring
+ *		buffer. If the BPF_RB_NO_WAKEUP flag is passed to this
+ *		function, no wakeup notification will be sent. If the
+ *		BPF_RB_FORCE_WAKEUP flag is passed, a wakeup notification will
+ *		be sent even if no sample was drained.
+ *
+ *		On failure, the returned value is one of the following:
+ *
+ *		**-EBUSY** if the ring buffer is contended, and another calling
+ *		context was concurrently draining the ring buffer.
+ *
+ *		**-EINVAL** if user-space is not properly tracking the ring
+ *		buffer due to the producer position not being aligned to 8
+ *		bytes, a sample not being aligned to 8 bytes, or the producer
+ *		position not matching the advertised length of a sample.
+ *
+ *		**-E2BIG** if user-space has tried to publish a sample which is
+ *		larger than the size of the ring buffer, or which cannot fit
+ *		within a struct bpf_dynptr.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5537,6 +5639,8 @@ union bpf_attr {
 	FN(tcp_raw_gen_syncookie_ipv6),	\
 	FN(tcp_raw_check_syncookie_ipv4),	\
 	FN(tcp_raw_check_syncookie_ipv6),	\
+	FN(ktime_get_tai_ns),		\
+	FN(user_ringbuf_drain),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -5599,6 +5703,11 @@ enum {
 	BPF_F_SEQ_NUMBER		= (1ULL << 3),
 };
 
+/* BPF_FUNC_skb_get_tunnel_key flags. */
+enum {
+	BPF_F_TUNINFO_FLAGS		= (1ULL << 4),
+};
+
 /* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
  * BPF_FUNC_perf_event_read_value flags.
  */
@@ -5788,7 +5897,10 @@ struct bpf_tunnel_key {
 	};
 	__u8 tunnel_tos;
 	__u8 tunnel_ttl;
-	__u16 tunnel_ext;	/* Padding, future use. */
+	union {
+		__u16 tunnel_ext;	/* compat */
+		__be16 tunnel_flags;
+	};
 	__u32 tunnel_label;
 	union {
 		__u32 local_ipv4;
@@ -5832,6 +5944,11 @@ enum bpf_ret_code {
 	 *    represented by BPF_REDIRECT above).
 	 */
 	BPF_LWT_REROUTE = 128,
+	/* BPF_FLOW_DISSECTOR_CONTINUE: used by BPF_PROG_TYPE_FLOW_DISSECTOR
+	 *   to indicate that no custom dissection was performed, and
+	 *   fallback to standard dissector is requested.
+	 */
+	BPF_FLOW_DISSECTOR_CONTINUE = 129,
 };
 
 struct bpf_sock {
@@ -6130,11 +6247,22 @@ struct bpf_link_info {
 		struct {
 			__aligned_u64 target_name; /* in/out: target_name buffer ptr */
 			__u32 target_name_len;	   /* in/out: target_name buffer len */
+
+			/* If the iter specific field is 32 bits, it can be put
+			 * in the first or second union. Otherwise it should be
+			 * put in the second union.
+			 */
 			union {
 				struct {
 					__u32 map_id;
 				} map;
 			};
+			union {
+				struct {
+					__u64 cgroup_id;
+					__u32 order;
+				} cgroup;
+			};
 		} iter;
 		struct  {
 			__u32 netns_ino;
@@ -6786,6 +6914,7 @@ enum bpf_core_relo_kind {
 	BPF_CORE_TYPE_SIZE = 9,              /* type size in bytes */
 	BPF_CORE_ENUMVAL_EXISTS = 10,        /* enum value existence in target kernel */
 	BPF_CORE_ENUMVAL_VALUE = 11,         /* enum value integer value */
+	BPF_CORE_TYPE_MATCHES = 12,          /* type match in target kernel */
 };
 
 /*

include/uapi/linux/if_link.h

@@ -890,6 +890,7 @@ enum {
 	IFLA_BOND_SLAVE_AD_AGGREGATOR_ID,
 	IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE,
 	IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE,
+	IFLA_BOND_SLAVE_PRIO,
 	__IFLA_BOND_SLAVE_MAX,
 };
 

include/uapi/linux/perf_event.h

@@ -301,6 +301,7 @@ 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;
@@ -308,6 +309,7 @@ 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
  * };
@@ -317,8 +319,9 @@ 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 */
@@ -491,7 +494,7 @@ struct perf_event_query_bpf {
 	/*
 	 * User provided buffer to store program ids
 	 */
-	__u32	ids[0];
+	__u32	ids[];
 };
 
 /*

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 */

src/Makefile

@@ -9,7 +9,7 @@ else
 endif
 
 LIBBPF_MAJOR_VERSION := 1
-LIBBPF_MINOR_VERSION := 0
+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

src/bpf.c

@@ -84,9 +84,7 @@ static inline int sys_bpf_fd(enum bpf_cmd cmd, union bpf_attr *attr,
 	return ensure_good_fd(fd);
 }
 
-#define PROG_LOAD_ATTEMPTS 5
-
-static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts)
+int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts)
 {
 	int fd;
 
@@ -107,7 +105,7 @@ static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int
  */
 int probe_memcg_account(void)
 {
-	const size_t prog_load_attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd);
+	const size_t attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd);
 	struct bpf_insn insns[] = {
 		BPF_EMIT_CALL(BPF_FUNC_ktime_get_coarse_ns),
 		BPF_EXIT_INSN(),
@@ -117,13 +115,13 @@ int probe_memcg_account(void)
 	int prog_fd;
 
 	/* attempt loading freplace trying to use custom BTF */
-	memset(&attr, 0, prog_load_attr_sz);
+	memset(&attr, 0, attr_sz);
 	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
 	attr.insns = ptr_to_u64(insns);
 	attr.insn_cnt = insn_cnt;
 	attr.license = ptr_to_u64("GPL");
 
-	prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, prog_load_attr_sz);
+	prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, attr_sz);
 	if (prog_fd >= 0) {
 		close(prog_fd);
 		return 1;
@@ -183,7 +181,7 @@ int bpf_map_create(enum bpf_map_type map_type,
 		return libbpf_err(-EINVAL);
 
 	attr.map_type = map_type;
-	if (map_name)
+	if (map_name && kernel_supports(NULL, FEAT_PROG_NAME))
 		libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name));
 	attr.key_size = key_size;
 	attr.value_size = value_size;
@@ -234,6 +232,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 		  const struct bpf_insn *insns, size_t insn_cnt,
 		  const struct bpf_prog_load_opts *opts)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, fd_array);
 	void *finfo = NULL, *linfo = NULL;
 	const char *func_info, *line_info;
 	__u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd;
@@ -253,7 +252,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 	if (attempts == 0)
 		attempts = PROG_LOAD_ATTEMPTS;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 
 	attr.prog_type = prog_type;
 	attr.expected_attach_type = OPTS_GET(opts, expected_attach_type, 0);
@@ -263,7 +262,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 	attr.prog_ifindex = OPTS_GET(opts, prog_ifindex, 0);
 	attr.kern_version = OPTS_GET(opts, kern_version, 0);
 
-	if (prog_name)
+	if (prog_name && kernel_supports(NULL, FEAT_PROG_NAME))
 		libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
 	attr.license = ptr_to_u64(license);
 
@@ -316,7 +315,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 		attr.log_level = log_level;
 	}
 
-	fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts);
+	fd = sys_bpf_prog_load(&attr, attr_sz, attempts);
 	if (fd >= 0)
 		return fd;
 
@@ -356,7 +355,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 			break;
 		}
 
-		fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts);
+		fd = sys_bpf_prog_load(&attr, attr_sz, attempts);
 		if (fd >= 0)
 			goto done;
 	}
@@ -370,7 +369,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 		attr.log_size = log_size;
 		attr.log_level = 1;
 
-		fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts);
+		fd = sys_bpf_prog_load(&attr, attr_sz, attempts);
 	}
 done:
 	/* free() doesn't affect errno, so we don't need to restore it */
@@ -382,127 +381,136 @@ done:
 int bpf_map_update_elem(int fd, const void *key, const void *value,
 			__u64 flags)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
 	attr.flags = flags;
 
-	ret = sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_map_lookup_elem(int fd, const void *key, void *value)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
 
-	ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, __u64 flags)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
 	attr.flags = flags;
 
-	ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
 
-	ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key, void *value, __u64 flags)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
 	attr.flags = flags;
 
-	ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_map_delete_elem(int fd, const void *key)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 
-	ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_map_delete_elem_flags(int fd, const void *key, __u64 flags)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.flags = flags;
 
-	ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_map_get_next_key(int fd, const void *key, void *next_key)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, next_key);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.next_key = ptr_to_u64(next_key);
 
-	ret = sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_map_freeze(int fd)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, map_fd);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.map_fd = fd;
 
-	ret = sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_FREEZE, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
@@ -511,13 +519,14 @@ static int bpf_map_batch_common(int cmd, int fd, void  *in_batch,
 				__u32 *count,
 				const struct bpf_map_batch_opts *opts)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, batch);
 	union bpf_attr attr;
 	int ret;
 
 	if (!OPTS_VALID(opts, bpf_map_batch_opts))
 		return libbpf_err(-EINVAL);
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.batch.map_fd = fd;
 	attr.batch.in_batch = ptr_to_u64(in_batch);
 	attr.batch.out_batch = ptr_to_u64(out_batch);
@@ -527,7 +536,7 @@ static int bpf_map_batch_common(int cmd, int fd, void  *in_batch,
 	attr.batch.elem_flags  = OPTS_GET(opts, elem_flags, 0);
 	attr.batch.flags = OPTS_GET(opts, flags, 0);
 
-	ret = sys_bpf(cmd, &attr, sizeof(attr));
+	ret = sys_bpf(cmd, &attr, attr_sz);
 	*count = attr.batch.count;
 
 	return libbpf_err_errno(ret);
@@ -566,26 +575,37 @@ int bpf_map_update_batch(int fd, const void *keys, const void *values, __u32 *co
 
 int bpf_obj_pin(int fd, const char *pathname)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, file_flags);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.pathname = ptr_to_u64((void *)pathname);
 	attr.bpf_fd = fd;
 
-	ret = sys_bpf(BPF_OBJ_PIN, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_OBJ_PIN, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_obj_get(const char *pathname)
 {
+	return bpf_obj_get_opts(pathname, NULL);
+}
+
+int bpf_obj_get_opts(const char *pathname, const struct bpf_obj_get_opts *opts)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, file_flags);
 	union bpf_attr attr;
 	int fd;
 
-	memset(&attr, 0, sizeof(attr));
-	attr.pathname = ptr_to_u64((void *)pathname);
+	if (!OPTS_VALID(opts, bpf_obj_get_opts))
+		return libbpf_err(-EINVAL);
 
-	fd = sys_bpf_fd(BPF_OBJ_GET, &attr, sizeof(attr));
+	memset(&attr, 0, attr_sz);
+	attr.pathname = ptr_to_u64((void *)pathname);
+	attr.file_flags = OPTS_GET(opts, file_flags, 0);
+
+	fd = sys_bpf_fd(BPF_OBJ_GET, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
@@ -603,52 +623,50 @@ int bpf_prog_attach_opts(int prog_fd, int target_fd,
 			  enum bpf_attach_type type,
 			  const struct bpf_prog_attach_opts *opts)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd);
 	union bpf_attr attr;
 	int ret;
 
 	if (!OPTS_VALID(opts, bpf_prog_attach_opts))
 		return libbpf_err(-EINVAL);
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.target_fd	   = target_fd;
 	attr.attach_bpf_fd = prog_fd;
 	attr.attach_type   = type;
 	attr.attach_flags  = OPTS_GET(opts, flags, 0);
 	attr.replace_bpf_fd = OPTS_GET(opts, replace_prog_fd, 0);
 
-	ret = sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_PROG_ATTACH, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
-__attribute__((alias("bpf_prog_attach_opts")))
-int bpf_prog_attach_xattr(int prog_fd, int target_fd,
-			  enum bpf_attach_type type,
-			  const struct bpf_prog_attach_opts *opts);
-
 int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.target_fd	 = target_fd;
 	attr.attach_type = type;
 
-	ret = sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_PROG_DETACH, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.target_fd	 = target_fd;
 	attr.attach_bpf_fd = prog_fd;
 	attr.attach_type = type;
 
-	ret = sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_PROG_DETACH, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
@@ -656,6 +674,7 @@ int bpf_link_create(int prog_fd, int target_fd,
 		    enum bpf_attach_type attach_type,
 		    const struct bpf_link_create_opts *opts)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, link_create);
 	__u32 target_btf_id, iter_info_len;
 	union bpf_attr attr;
 	int fd, err;
@@ -674,7 +693,7 @@ int bpf_link_create(int prog_fd, int target_fd,
 			return libbpf_err(-EINVAL);
 	}
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.link_create.prog_fd = prog_fd;
 	attr.link_create.target_fd = target_fd;
 	attr.link_create.attach_type = attach_type;
@@ -718,7 +737,7 @@ int bpf_link_create(int prog_fd, int target_fd,
 		break;
 	}
 proceed:
-	fd = sys_bpf_fd(BPF_LINK_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_LINK_CREATE, &attr, attr_sz);
 	if (fd >= 0)
 		return fd;
 	/* we'll get EINVAL if LINK_CREATE doesn't support attaching fentry
@@ -754,44 +773,47 @@ proceed:
 
 int bpf_link_detach(int link_fd)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, link_detach);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.link_detach.link_fd = link_fd;
 
-	ret = sys_bpf(BPF_LINK_DETACH, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_LINK_DETACH, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_link_update(int link_fd, int new_prog_fd,
 		    const struct bpf_link_update_opts *opts)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, link_update);
 	union bpf_attr attr;
 	int ret;
 
 	if (!OPTS_VALID(opts, bpf_link_update_opts))
 		return libbpf_err(-EINVAL);
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.link_update.link_fd = link_fd;
 	attr.link_update.new_prog_fd = new_prog_fd;
 	attr.link_update.flags = OPTS_GET(opts, flags, 0);
 	attr.link_update.old_prog_fd = OPTS_GET(opts, old_prog_fd, 0);
 
-	ret = sys_bpf(BPF_LINK_UPDATE, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_LINK_UPDATE, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_iter_create(int link_fd)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, iter_create);
 	union bpf_attr attr;
 	int fd;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.iter_create.link_fd = link_fd;
 
-	fd = sys_bpf_fd(BPF_ITER_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_ITER_CREATE, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
@@ -799,13 +821,14 @@ int bpf_prog_query_opts(int target_fd,
 			enum bpf_attach_type type,
 			struct bpf_prog_query_opts *opts)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, query);
 	union bpf_attr attr;
 	int ret;
 
 	if (!OPTS_VALID(opts, bpf_prog_query_opts))
 		return libbpf_err(-EINVAL);
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 
 	attr.query.target_fd	= target_fd;
 	attr.query.attach_type	= type;
@@ -814,7 +837,7 @@ int bpf_prog_query_opts(int target_fd,
 	attr.query.prog_ids	= ptr_to_u64(OPTS_GET(opts, prog_ids, NULL));
 	attr.query.prog_attach_flags = ptr_to_u64(OPTS_GET(opts, prog_attach_flags, NULL));
 
-	ret = sys_bpf(BPF_PROG_QUERY, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_PROG_QUERY, &attr, attr_sz);
 
 	OPTS_SET(opts, attach_flags, attr.query.attach_flags);
 	OPTS_SET(opts, prog_cnt, attr.query.prog_cnt);
@@ -843,13 +866,14 @@ int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
 
 int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, test);
 	union bpf_attr attr;
 	int ret;
 
 	if (!OPTS_VALID(opts, bpf_test_run_opts))
 		return libbpf_err(-EINVAL);
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.test.prog_fd = prog_fd;
 	attr.test.batch_size = OPTS_GET(opts, batch_size, 0);
 	attr.test.cpu = OPTS_GET(opts, cpu, 0);
@@ -865,7 +889,7 @@ int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts)
 	attr.test.data_in = ptr_to_u64(OPTS_GET(opts, data_in, NULL));
 	attr.test.data_out = ptr_to_u64(OPTS_GET(opts, data_out, NULL));
 
-	ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, attr_sz);
 
 	OPTS_SET(opts, data_size_out, attr.test.data_size_out);
 	OPTS_SET(opts, ctx_size_out, attr.test.ctx_size_out);
@@ -877,13 +901,14 @@ int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts)
 
 static int bpf_obj_get_next_id(__u32 start_id, __u32 *next_id, int cmd)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, open_flags);
 	union bpf_attr attr;
 	int err;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.start_id = start_id;
 
-	err = sys_bpf(cmd, &attr, sizeof(attr));
+	err = sys_bpf(cmd, &attr, attr_sz);
 	if (!err)
 		*next_id = attr.next_id;
 
@@ -912,80 +937,84 @@ int bpf_link_get_next_id(__u32 start_id, __u32 *next_id)
 
 int bpf_prog_get_fd_by_id(__u32 id)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, open_flags);
 	union bpf_attr attr;
 	int fd;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.prog_id = id;
 
-	fd = sys_bpf_fd(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_PROG_GET_FD_BY_ID, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
 int bpf_map_get_fd_by_id(__u32 id)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, open_flags);
 	union bpf_attr attr;
 	int fd;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.map_id = id;
 
-	fd = sys_bpf_fd(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_MAP_GET_FD_BY_ID, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
 int bpf_btf_get_fd_by_id(__u32 id)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, open_flags);
 	union bpf_attr attr;
 	int fd;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.btf_id = id;
 
-	fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
 int bpf_link_get_fd_by_id(__u32 id)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, open_flags);
 	union bpf_attr attr;
 	int fd;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.link_id = id;
 
-	fd = sys_bpf_fd(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_LINK_GET_FD_BY_ID, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
 int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, info);
 	union bpf_attr attr;
 	int err;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.info.bpf_fd = bpf_fd;
 	attr.info.info_len = *info_len;
 	attr.info.info = ptr_to_u64(info);
 
-	err = sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, sizeof(attr));
-
+	err = sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, attr_sz);
 	if (!err)
 		*info_len = attr.info.info_len;
-
 	return libbpf_err_errno(err);
 }
 
 int bpf_raw_tracepoint_open(const char *name, int prog_fd)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint);
 	union bpf_attr attr;
 	int fd;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.raw_tracepoint.name = ptr_to_u64(name);
 	attr.raw_tracepoint.prog_fd = prog_fd;
 
-	fd = sys_bpf_fd(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_RAW_TRACEPOINT_OPEN, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
@@ -1041,16 +1070,18 @@ 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)
 {
-	union bpf_attr attr = {};
+	const size_t attr_sz = offsetofend(union bpf_attr, task_fd_query);
+	union bpf_attr attr;
 	int err;
 
+	memset(&attr, 0, attr_sz);
 	attr.task_fd_query.pid = pid;
 	attr.task_fd_query.fd = fd;
 	attr.task_fd_query.flags = flags;
 	attr.task_fd_query.buf = ptr_to_u64(buf);
 	attr.task_fd_query.buf_len = *buf_len;
 
-	err = sys_bpf(BPF_TASK_FD_QUERY, &attr, sizeof(attr));
+	err = sys_bpf(BPF_TASK_FD_QUERY, &attr, attr_sz);
 
 	*buf_len = attr.task_fd_query.buf_len;
 	*prog_id = attr.task_fd_query.prog_id;
@@ -1063,30 +1094,32 @@ int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len,
 
 int bpf_enable_stats(enum bpf_stats_type type)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, enable_stats);
 	union bpf_attr attr;
 	int fd;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.enable_stats.type = type;
 
-	fd = sys_bpf_fd(BPF_ENABLE_STATS, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_ENABLE_STATS, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
 int bpf_prog_bind_map(int prog_fd, int map_fd,
 		      const struct bpf_prog_bind_opts *opts)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, prog_bind_map);
 	union bpf_attr attr;
 	int ret;
 
 	if (!OPTS_VALID(opts, bpf_prog_bind_opts))
 		return libbpf_err(-EINVAL);
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.prog_bind_map.prog_fd = prog_fd;
 	attr.prog_bind_map.map_fd = map_fd;
 	attr.prog_bind_map.flags = OPTS_GET(opts, flags, 0);
 
-	ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }

src/bpf.h

@@ -270,8 +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 */

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 */
@@ -183,6 +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

@@ -1005,7 +1005,8 @@ static long (*bpf_skb_change_tail)(struct __sk_buff *skb, __u32 len, __u64 flags
  * 	Pull in non-linear data in case the *skb* is non-linear and not
  * 	all of *len* are part of the linear section. Make *len* bytes
  * 	from *skb* readable and writable. If a zero value is passed for
- * 	*len*, then the whole length of the *skb* is pulled.
+ * 	*len*, then all bytes in the linear part of *skb* will be made
+ * 	readable and writable.
  *
  * 	This helper is only needed for reading and writing with direct
  * 	packet access.
@@ -1238,10 +1239,12 @@ static long (*bpf_setsockopt)(void *bpf_socket, int level, int optname, void *op
  * 	There are two supported modes at this time:
  *
  * 	* **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
- * 	  (room space is added or removed below the layer 2 header).
+ * 	  (room space is added or removed between the layer 2 and
+ * 	  layer 3 headers).
  *
  * 	* **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
- * 	  (room space is added or removed below the layer 3 header).
+ * 	  (room space is added or removed between the layer 3 and
+ * 	  layer 4 headers).
  *
  * 	The following flags are supported at this time:
  *
@@ -1741,8 +1744,18 @@ static long (*bpf_skb_get_xfrm_state)(struct __sk_buff *skb, __u32 index, struct
  * 	**BPF_F_USER_STACK**
  * 		Collect a user space stack instead of a kernel stack.
  * 	**BPF_F_USER_BUILD_ID**
- * 		Collect buildid+offset instead of ips for user stack,
- * 		only valid if **BPF_F_USER_STACK** is also specified.
+ * 		Collect (build_id, file_offset) instead of ips for user
+ * 		stack, only valid if **BPF_F_USER_STACK** is also
+ * 		specified.
+ *
+ * 		*file_offset* is an offset relative to the beginning
+ * 		of the executable or shared object file backing the vma
+ * 		which the *ip* falls in. It is *not* an offset relative
+ * 		to that object's base address. Accordingly, it must be
+ * 		adjusted by adding (sh_addr - sh_offset), where
+ * 		sh_{addr,offset} correspond to the executable section
+ * 		containing *file_offset* in the object, for comparisons
+ * 		to symbols' st_value to be valid.
  *
  * 	**bpf_get_stack**\ () can collect up to
  * 	**PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
@@ -3413,7 +3426,7 @@ static long (*bpf_load_hdr_opt)(struct bpf_sock_ops *skops, void *searchby_res,
  *
  * 	**-EEXIST** if the option already exists.
  *
- * 	**-EFAULT** on failrue to parse the existing header options.
+ * 	**-EFAULT** on failure to parse the existing header options.
  *
  * 	**-EPERM** if the helper cannot be used under the current
  * 	*skops*\ **->op**.
@@ -3673,7 +3686,7 @@ static long (*bpf_redirect_peer)(__u32 ifindex, __u64 flags) = (void *) 155;
  * 	a *map* with *task* as the **key**.  From this
  * 	perspective,  the usage is not much different from
  * 	**bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this
- * 	helper enforces the key must be an task_struct and the map must also
+ * 	helper enforces the key must be a task_struct and the map must also
  * 	be a **BPF_MAP_TYPE_TASK_STORAGE**.
  *
  * 	Underneath, the value is stored locally at *task* instead of
@@ -3751,7 +3764,7 @@ static __u64 (*bpf_ktime_get_coarse_ns)(void) = (void *) 160;
 /*
  * bpf_ima_inode_hash
  *
- * 	Returns the stored IMA hash of the *inode* (if it's avaialable).
+ * 	Returns the stored IMA hash of the *inode* (if it's available).
  * 	If the hash is larger than *size*, then only *size*
  * 	bytes will be copied to *dst*
  *
@@ -3783,12 +3796,12 @@ static struct socket *(*bpf_sock_from_file)(struct file *file) = (void *) 162;
  *
  * 	The argument *len_diff* can be used for querying with a planned
  * 	size change. This allows to check MTU prior to changing packet
- * 	ctx. Providing an *len_diff* adjustment that is larger than the
+ * 	ctx. Providing a *len_diff* adjustment that is larger than the
  * 	actual packet size (resulting in negative packet size) will in
- * 	principle not exceed the MTU, why it is not considered a
- * 	failure.  Other BPF-helpers are needed for performing the
- * 	planned size change, why the responsability for catch a negative
- * 	packet size belong in those helpers.
+ * 	principle not exceed the MTU, which is why it is not considered
+ * 	a failure.  Other BPF helpers are needed for performing the
+ * 	planned size change; therefore the responsibility for catching
+ * 	a negative packet size belongs in those helpers.
  *
  * 	Specifying *ifindex* zero means the MTU check is performed
  * 	against the current net device.  This is practical if this isn't
@@ -4027,6 +4040,7 @@ static long (*bpf_timer_cancel)(struct bpf_timer *timer) = (void *) 172;
  *
  * Returns
  * 	Address of the traced function.
+ * 	0 for kprobes placed within the function (not at the entry).
  */
 static __u64 (*bpf_get_func_ip)(void *ctx) = (void *) 173;
 
@@ -4195,13 +4209,13 @@ 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;
 
@@ -4221,32 +4235,45 @@ 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.
@@ -4450,25 +4477,28 @@ static void (*bpf_ringbuf_discard_dynptr)(struct bpf_dynptr *ptr, __u64 flags) =
  *
  * 	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.
+ * 	of *src*'s data, -EINVAL if *src* is an invalid dynptr or if
+ * 	*flags* is not 0.
  */
-static long (*bpf_dynptr_read)(void *dst, __u32 len, struct bpf_dynptr *src, __u32 offset) = (void *) 201;
+static long (*bpf_dynptr_read)(void *dst, __u32 len, struct bpf_dynptr *src, __u32 offset, __u64 flags) = (void *) 201;
 
 /*
  * bpf_dynptr_write
  *
  * 	Write *len* bytes from *src* into *dst*, starting from *offset*
  * 	into *dst*.
+ * 	*flags* is currently unused.
  *
  * Returns
  * 	0 on success, -E2BIG if *offset* + *len* exceeds the length
  * 	of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst*
- * 	is a read-only dynptr.
+ * 	is a read-only dynptr or if *flags* is not 0.
  */
-static long (*bpf_dynptr_write)(struct bpf_dynptr *dst, __u32 offset, void *src, __u32 len) = (void *) 202;
+static long (*bpf_dynptr_write)(struct bpf_dynptr *dst, __u32 offset, void *src, __u32 len, __u64 flags) = (void *) 202;
 
 /*
  * bpf_dynptr_data
@@ -4575,4 +4605,61 @@ static long (*bpf_tcp_raw_check_syncookie_ipv4)(struct iphdr *iph, struct tcphdr
  */
 static long (*bpf_tcp_raw_check_syncookie_ipv6)(struct ipv6hdr *iph, struct tcphdr *th) = (void *) 207;
 
+/*
+ * bpf_ktime_get_tai_ns
+ *
+ * 	A nonsettable system-wide clock derived from wall-clock time but
+ * 	ignoring leap seconds.  This clock does not experience
+ * 	discontinuities and backwards jumps caused by NTP inserting leap
+ * 	seconds as CLOCK_REALTIME does.
+ *
+ * 	See: **clock_gettime**\ (**CLOCK_TAI**)
+ *
+ * Returns
+ * 	Current *ktime*.
+ */
+static __u64 (*bpf_ktime_get_tai_ns)(void) = (void *) 208;
+
+/*
+ * bpf_user_ringbuf_drain
+ *
+ * 	Drain samples from the specified user ring buffer, and invoke
+ * 	the provided callback for each such sample:
+ *
+ * 	long (\*callback_fn)(struct bpf_dynptr \*dynptr, void \*ctx);
+ *
+ * 	If **callback_fn** returns 0, the helper will continue to try
+ * 	and drain the next sample, up to a maximum of
+ * 	BPF_MAX_USER_RINGBUF_SAMPLES samples. If the return value is 1,
+ * 	the helper will skip the rest of the samples and return. Other
+ * 	return values are not used now, and will be rejected by the
+ * 	verifier.
+ *
+ * Returns
+ * 	The number of drained samples if no error was encountered while
+ * 	draining samples, or 0 if no samples were present in the ring
+ * 	buffer. If a user-space producer was epoll-waiting on this map,
+ * 	and at least one sample was drained, they will receive an event
+ * 	notification notifying them of available space in the ring
+ * 	buffer. If the BPF_RB_NO_WAKEUP flag is passed to this
+ * 	function, no wakeup notification will be sent. If the
+ * 	BPF_RB_FORCE_WAKEUP flag is passed, a wakeup notification will
+ * 	be sent even if no sample was drained.
+ *
+ * 	On failure, the returned value is one of the following:
+ *
+ * 	**-EBUSY** if the ring buffer is contended, and another calling
+ * 	context was concurrently draining the ring buffer.
+ *
+ * 	**-EINVAL** if user-space is not properly tracking the ring
+ * 	buffer due to the producer position not being aligned to 8
+ * 	bytes, a sample not being aligned to 8 bytes, or the producer
+ * 	position not matching the advertised length of a sample.
+ *
+ * 	**-E2BIG** if user-space has tried to publish a sample which is
+ * 	larger than the size of the ring buffer, or which cannot fit
+ * 	within a struct bpf_dynptr.
+ */
+static long (*bpf_user_ringbuf_drain)(void *map, void *callback_fn, void *ctx, __u64 flags) = (void *) 209;
+
 

src/bpf_helpers.h

@@ -22,12 +22,25 @@
  * To allow use of SEC() with externs (e.g., for extern .maps declarations),
  * make sure __attribute__((unused)) doesn't trigger compilation warning.
  */
+#if __GNUC__ && !__clang__
+
+/*
+ * Pragma macros are broken on GCC
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=55578
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90400
+ */
+#define SEC(name) __attribute__((section(name), used))
+
+#else
+
 #define SEC(name) \
 	_Pragma("GCC diagnostic push")					    \
 	_Pragma("GCC diagnostic ignored \"-Wignored-attributes\"")	    \
 	__attribute__((section(name), used))				    \
 	_Pragma("GCC diagnostic pop")					    \
 
+#endif
+
 /* Avoid 'linux/stddef.h' definition of '__always_inline'. */
 #undef __always_inline
 #define __always_inline inline __attribute__((always_inline))
@@ -147,18 +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) */

src/bpf_tracing.h

@@ -2,6 +2,8 @@
 #ifndef __BPF_TRACING_H__
 #define __BPF_TRACING_H__
 
+#include <bpf/bpf_helpers.h>
+
 /* Scan the ARCH passed in from ARCH env variable (see Makefile) */
 #if defined(__TARGET_ARCH_x86)
 	#define bpf_target_x86
@@ -140,7 +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)
@@ -174,7 +176,7 @@ 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)
@@ -233,7 +235,7 @@ struct pt_regs___arm64 {
 #define __PT_PARM5_REG a4
 #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. */
@@ -424,7 +426,7 @@ struct pt_regs;
  */
 #define BPF_PROG(name, args...)						    \
 name(unsigned long long *ctx);						    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(unsigned long long *ctx, ##args);				    \
 typeof(name(0)) name(unsigned long long *ctx)				    \
 {									    \
@@ -433,9 +435,116 @@ 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
@@ -458,7 +567,7 @@ struct pt_regs;
  */
 #define BPF_KPROBE(name, args...)					    \
 name(struct pt_regs *ctx);						    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(struct pt_regs *ctx, ##args);				    \
 typeof(name(0)) name(struct pt_regs *ctx)				    \
 {									    \
@@ -467,7 +576,7 @@ 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
@@ -482,7 +591,7 @@ ____##name(struct pt_regs *ctx, ##args)
  */
 #define BPF_KRETPROBE(name, args...)					    \
 name(struct pt_regs *ctx);						    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(struct pt_regs *ctx, ##args);				    \
 typeof(name(0)) name(struct pt_regs *ctx)				    \
 {									    \
@@ -493,39 +602,69 @@ typeof(name(0)) name(struct pt_regs *ctx)				    \
 }									    \
 static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
 
+/* If kernel has CONFIG_ARCH_HAS_SYSCALL_WRAPPER, read pt_regs directly */
 #define ___bpf_syscall_args0()           ctx
-#define ___bpf_syscall_args1(x)          ___bpf_syscall_args0(), (void *)PT_REGS_PARM1_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
  * syntax and semantics of accessing syscall input parameters.
  *
- * Original struct pt_regs* context is preserved as 'ctx' argument. This might
+ * 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\"")		    \
-	return ____##name(___bpf_syscall_args(args));			    \
+	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.c

@@ -1225,8 +1225,6 @@ int btf__load_into_kernel(struct btf *btf)
 	return btf_load_into_kernel(btf, NULL, 0, 0);
 }
 
-int btf__load(struct btf *) __attribute__((alias("btf__load_into_kernel")));
-
 int btf__fd(const struct btf *btf)
 {
 	return btf->fd;
@@ -4644,20 +4642,17 @@ static int btf_dedup_remap_types(struct btf_dedup *d)
  */
 struct btf *btf__load_vmlinux_btf(void)
 {
-	struct {
-		const char *path_fmt;
-		bool raw_btf;
-	} locations[] = {
+	const char *locations[] = {
 		/* try canonical vmlinux BTF through sysfs first */
-		{ "/sys/kernel/btf/vmlinux", true /* raw BTF */ },
-		/* fall back to trying to find vmlinux ELF on disk otherwise */
-		{ "/boot/vmlinux-%1$s" },
-		{ "/lib/modules/%1$s/vmlinux-%1$s" },
-		{ "/lib/modules/%1$s/build/vmlinux" },
-		{ "/usr/lib/modules/%1$s/kernel/vmlinux" },
-		{ "/usr/lib/debug/boot/vmlinux-%1$s" },
-		{ "/usr/lib/debug/boot/vmlinux-%1$s.debug" },
-		{ "/usr/lib/debug/lib/modules/%1$s/vmlinux" },
+		"/sys/kernel/btf/vmlinux",
+		/* fall back to trying to find vmlinux on disk otherwise */
+		"/boot/vmlinux-%1$s",
+		"/lib/modules/%1$s/vmlinux-%1$s",
+		"/lib/modules/%1$s/build/vmlinux",
+		"/usr/lib/modules/%1$s/kernel/vmlinux",
+		"/usr/lib/debug/boot/vmlinux-%1$s",
+		"/usr/lib/debug/boot/vmlinux-%1$s.debug",
+		"/usr/lib/debug/lib/modules/%1$s/vmlinux",
 	};
 	char path[PATH_MAX + 1];
 	struct utsname buf;
@@ -4667,15 +4662,12 @@ struct btf *btf__load_vmlinux_btf(void)
 	uname(&buf);
 
 	for (i = 0; i < ARRAY_SIZE(locations); i++) {
-		snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release);
+		snprintf(path, PATH_MAX, locations[i], buf.release);
 
-		if (access(path, R_OK))
+		if (faccessat(AT_FDCWD, path, R_OK, AT_EACCESS))
 			continue;
 
-		if (locations[i].raw_btf)
-			btf = btf__parse_raw(path);
-		else
-			btf = btf__parse_elf(path, NULL);
+		btf = btf__parse(path, NULL);
 		err = libbpf_get_error(btf);
 		pr_debug("loading kernel BTF '%s': %d\n", path, err);
 		if (err)

src/btf.h

@@ -116,7 +116,6 @@ 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);
@@ -487,6 +486,8 @@ 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);
@@ -494,7 +495,28 @@ static inline struct btf_enum64 *btf_enum64(const struct btf_type *t)
 
 static inline __u64 btf_enum64_value(const struct btf_enum64 *e)
 {
-	return ((__u64)e->val_hi32 << 32) | e->val_lo32;
+	/* 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)

src/btf_dump.c

@@ -2045,7 +2045,7 @@ static int btf_dump_get_enum_value(struct btf_dump *d,
 		*value = *(__s64 *)data;
 		return 0;
 	case 4:
-		*value = is_signed ? *(__s32 *)data : *(__u32 *)data;
+		*value = is_signed ? (__s64)*(__s32 *)data : *(__u32 *)data;
 		return 0;
 	case 2:
 		*value = is_signed ? *(__s16 *)data : *(__u16 *)data;
@@ -2385,7 +2385,7 @@ 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;
 }
 

src/libbpf.h

@@ -118,7 +118,9 @@ struct bpf_object_open_opts {
 	 * auto-pinned to that path on load; defaults to "/sys/fs/bpf".
 	 */
 	const char *pin_root_path;
-	long :0;
+
+	__u32 :32; /* stub out now removed attach_prog_fd */
+
 	/* Additional kernel config content that augments and overrides
 	 * system Kconfig for CONFIG_xxx externs.
 	 */
@@ -260,6 +262,8 @@ LIBBPF_API const char *bpf_program__name(const struct bpf_program *prog);
 LIBBPF_API const char *bpf_program__section_name(const struct bpf_program *prog);
 LIBBPF_API bool bpf_program__autoload(const struct bpf_program *prog);
 LIBBPF_API int bpf_program__set_autoload(struct bpf_program *prog, bool autoload);
+LIBBPF_API bool bpf_program__autoattach(const struct bpf_program *prog);
+LIBBPF_API void bpf_program__set_autoattach(struct bpf_program *prog, bool autoattach);
 
 struct bpf_insn;
 
@@ -457,6 +461,52 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
 				      const char *pattern,
 				      const struct bpf_kprobe_multi_opts *opts);
 
+struct bpf_ksyscall_opts {
+	/* size of this struct, for forward/backward compatiblity */
+	size_t sz;
+	/* custom user-provided value fetchable through bpf_get_attach_cookie() */
+	__u64 bpf_cookie;
+	/* attach as return probe? */
+	bool retprobe;
+	size_t :0;
+};
+#define bpf_ksyscall_opts__last_field retprobe
+
+/**
+ * @brief **bpf_program__attach_ksyscall()** attaches a BPF program
+ * to kernel syscall handler of a specified syscall. Optionally it's possible
+ * to request to install retprobe that will be triggered at syscall exit. It's
+ * also possible to associate BPF cookie (though options).
+ *
+ * Libbpf automatically will determine correct full kernel function name,
+ * which depending on system architecture and kernel version/configuration
+ * could be of the form __<arch>_sys_<syscall> or __se_sys_<syscall>, and will
+ * attach specified program using kprobe/kretprobe mechanism.
+ *
+ * **bpf_program__attach_ksyscall()** is an API counterpart of declarative
+ * **SEC("ksyscall/<syscall>")** annotation of BPF programs.
+ *
+ * At the moment **SEC("ksyscall")** and **bpf_program__attach_ksyscall()** do
+ * not handle all the calling convention quirks for mmap(), clone() and compat
+ * syscalls. It also only attaches to "native" syscall interfaces. If host
+ * system supports compat syscalls or defines 32-bit syscalls in 64-bit
+ * kernel, such syscall interfaces won't be attached to by libbpf.
+ *
+ * These limitations may or may not change in the future. Therefore it is
+ * recommended to use SEC("kprobe") for these syscalls or if working with
+ * compat and 32-bit interfaces is required.
+ *
+ * @param prog BPF program to attach
+ * @param syscall_name Symbolic name of the syscall (e.g., "bpf")
+ * @param opts Additional options (see **struct bpf_ksyscall_opts**)
+ * @return Reference to the newly created BPF link; or NULL is returned on
+ * error, error code is stored in errno
+ */
+LIBBPF_API struct bpf_link *
+bpf_program__attach_ksyscall(const struct bpf_program *prog,
+			     const char *syscall_name,
+			     const struct bpf_ksyscall_opts *opts);
+
 struct bpf_uprobe_opts {
 	/* size of this struct, for forward/backward compatiblity */
 	size_t sz;
@@ -963,6 +1013,7 @@ LIBBPF_API int bpf_tc_query(const struct bpf_tc_hook *hook,
 
 /* Ring buffer APIs */
 struct ring_buffer;
+struct user_ring_buffer;
 
 typedef int (*ring_buffer_sample_fn)(void *ctx, void *data, size_t size);
 
@@ -982,6 +1033,112 @@ LIBBPF_API int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms);
 LIBBPF_API int ring_buffer__consume(struct ring_buffer *rb);
 LIBBPF_API int ring_buffer__epoll_fd(const struct ring_buffer *rb);
 
+struct user_ring_buffer_opts {
+	size_t sz; /* size of this struct, for forward/backward compatibility */
+};
+
+#define user_ring_buffer_opts__last_field sz
+
+/* @brief **user_ring_buffer__new()** creates a new instance of a user ring
+ * buffer.
+ *
+ * @param map_fd A file descriptor to a BPF_MAP_TYPE_USER_RINGBUF map.
+ * @param opts Options for how the ring buffer should be created.
+ * @return A user ring buffer on success; NULL and errno being set on a
+ * failure.
+ */
+LIBBPF_API struct user_ring_buffer *
+user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts);
+
+/* @brief **user_ring_buffer__reserve()** reserves a pointer to a sample in the
+ * user ring buffer.
+ * @param rb A pointer to a user ring buffer.
+ * @param size The size of the sample, in bytes.
+ * @return A pointer to an 8-byte aligned reserved region of the user ring
+ * buffer; NULL, and errno being set if a sample could not be reserved.
+ *
+ * This function is *not* thread safe, and callers must synchronize accessing
+ * this function if there are multiple producers.  If a size is requested that
+ * is larger than the size of the entire ring buffer, errno will be set to
+ * E2BIG and NULL is returned. If the ring buffer could accommodate the size,
+ * but currently does not have enough space, errno is set to ENOSPC and NULL is
+ * returned.
+ *
+ * After initializing the sample, callers must invoke
+ * **user_ring_buffer__submit()** to post the sample to the kernel. Otherwise,
+ * the sample must be freed with **user_ring_buffer__discard()**.
+ */
+LIBBPF_API void *user_ring_buffer__reserve(struct user_ring_buffer *rb, __u32 size);
+
+/* @brief **user_ring_buffer__reserve_blocking()** reserves a record in the
+ * ring buffer, possibly blocking for up to @timeout_ms until a sample becomes
+ * available.
+ * @param rb The user ring buffer.
+ * @param size The size of the sample, in bytes.
+ * @param timeout_ms The amount of time, in milliseconds, for which the caller
+ * should block when waiting for a sample. -1 causes the caller to block
+ * indefinitely.
+ * @return A pointer to an 8-byte aligned reserved region of the user ring
+ * buffer; NULL, and errno being set if a sample could not be reserved.
+ *
+ * This function is *not* thread safe, and callers must synchronize
+ * accessing this function if there are multiple producers
+ *
+ * If **timeout_ms** is -1, the function will block indefinitely until a sample
+ * becomes available. Otherwise, **timeout_ms** must be non-negative, or errno
+ * is set to EINVAL, and NULL is returned. If **timeout_ms** is 0, no blocking
+ * will occur and the function will return immediately after attempting to
+ * reserve a sample.
+ *
+ * If **size** is larger than the size of the entire ring buffer, errno is set
+ * to E2BIG and NULL is returned. If the ring buffer could accommodate
+ * **size**, but currently does not have enough space, the caller will block
+ * until at most **timeout_ms** has elapsed. If insufficient space is available
+ * at that time, errno is set to ENOSPC, and NULL is returned.
+ *
+ * The kernel guarantees that it will wake up this thread to check if
+ * sufficient space is available in the ring buffer at least once per
+ * invocation of the **bpf_ringbuf_drain()** helper function, provided that at
+ * least one sample is consumed, and the BPF program did not invoke the
+ * function with BPF_RB_NO_WAKEUP. A wakeup may occur sooner than that, but the
+ * kernel does not guarantee this. If the helper function is invoked with
+ * BPF_RB_FORCE_WAKEUP, a wakeup event will be sent even if no sample is
+ * consumed.
+ *
+ * When a sample of size **size** is found within **timeout_ms**, a pointer to
+ * the sample is returned. After initializing the sample, callers must invoke
+ * **user_ring_buffer__submit()** to post the sample to the ring buffer.
+ * Otherwise, the sample must be freed with **user_ring_buffer__discard()**.
+ */
+LIBBPF_API void *user_ring_buffer__reserve_blocking(struct user_ring_buffer *rb,
+						    __u32 size,
+						    int timeout_ms);
+
+/* @brief **user_ring_buffer__submit()** submits a previously reserved sample
+ * into the ring buffer.
+ * @param rb The user ring buffer.
+ * @param sample A reserved sample.
+ *
+ * It is not necessary to synchronize amongst multiple producers when invoking
+ * this function.
+ */
+LIBBPF_API void user_ring_buffer__submit(struct user_ring_buffer *rb, void *sample);
+
+/* @brief **user_ring_buffer__discard()** discards a previously reserved sample.
+ * @param rb The user ring buffer.
+ * @param sample A reserved sample.
+ *
+ * It is not necessary to synchronize amongst multiple producers when invoking
+ * this function.
+ */
+LIBBPF_API void user_ring_buffer__discard(struct user_ring_buffer *rb, void *sample);
+
+/* @brief **user_ring_buffer__free()** frees a ring buffer that was previously
+ * created with **user_ring_buffer__new()**.
+ * @param rb The user ring buffer being freed.
+ */
+LIBBPF_API void user_ring_buffer__free(struct user_ring_buffer *rb);
+
 /* Perf buffer APIs */
 struct perf_buffer;
 
@@ -1053,6 +1210,22 @@ LIBBPF_API int perf_buffer__consume(struct perf_buffer *pb);
 LIBBPF_API int perf_buffer__consume_buffer(struct perf_buffer *pb, size_t buf_idx);
 LIBBPF_API size_t perf_buffer__buffer_cnt(const struct perf_buffer *pb);
 LIBBPF_API int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_idx);
+/**
+ * @brief **perf_buffer__buffer()** returns the per-cpu raw mmap()'ed underlying
+ * memory region of the ring buffer.
+ * This ring buffer can be used to implement a custom events consumer.
+ * The ring buffer starts with the *struct perf_event_mmap_page*, which
+ * holds the ring buffer managment fields, when accessing the header
+ * structure it's important to be SMP aware.
+ * You can refer to *perf_event_read_simple* for a simple example.
+ * @param pb the perf buffer structure
+ * @param buf_idx the buffer index to retreive
+ * @param buf (out) gets the base pointer of the mmap()'ed memory
+ * @param buf_size (out) gets the size of the mmap()'ed region
+ * @return 0 on success, negative error code for failure
+ */
+LIBBPF_API int perf_buffer__buffer(struct perf_buffer *pb, int buf_idx, void **buf,
+				   size_t *buf_size);
 
 struct bpf_prog_linfo;
 struct bpf_prog_info;

src/libbpf.map

@@ -355,11 +355,26 @@ LIBBPF_0.8.0 {
 
 LIBBPF_1.0.0 {
 	global:
+		bpf_obj_get_opts;
 		bpf_prog_query_opts;
+		bpf_program__attach_ksyscall;
+		bpf_program__autoattach;
+		bpf_program__set_autoattach;
 		btf__add_enum64;
 		btf__add_enum64_value;
 		libbpf_bpf_attach_type_str;
 		libbpf_bpf_link_type_str;
 		libbpf_bpf_map_type_str;
 		libbpf_bpf_prog_type_str;
+		perf_buffer__buffer;
 };
+
+LIBBPF_1.1.0 {
+	global:
+		user_ring_buffer__discard;
+		user_ring_buffer__free;
+		user_ring_buffer__new;
+		user_ring_buffer__reserve;
+		user_ring_buffer__reserve_blocking;
+		user_ring_buffer__submit;
+} LIBBPF_1.0.0;

src/libbpf_internal.h

@@ -108,9 +108,9 @@ 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 strcmp(str + str_len - sfx_len, sfx);
-	return false;
+	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.
@@ -352,6 +352,8 @@ enum kern_feature_id {
 	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,
 };
 
@@ -571,4 +573,7 @@ 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

@@ -125,6 +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

@@ -193,7 +193,7 @@ 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;
+	int fd = -1, btf_fd = -1, fd_inner = -1, exp_err = 0, err = 0;
 
 	key_size	= sizeof(__u32);
 	value_size	= sizeof(__u32);
@@ -231,6 +231,7 @@ static int probe_map_create(enum bpf_map_type map_type)
 			return btf_fd;
 		break;
 	case BPF_MAP_TYPE_RINGBUF:
+	case BPF_MAP_TYPE_USER_RINGBUF:
 		key_size = 0;
 		value_size = 0;
 		max_entries = 4096;

src/libbpf_version.h

@@ -4,6 +4,6 @@
 #define __LIBBPF_VERSION_H
 
 #define LIBBPF_MAJOR_VERSION 1
-#define LIBBPF_MINOR_VERSION 0
+#define LIBBPF_MINOR_VERSION 1
 
 #endif /* __LIBBPF_VERSION_H */

src/netlink.c

@@ -587,11 +587,12 @@ static int get_tc_info(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn,
 
 static int tc_add_fd_and_name(struct libbpf_nla_req *req, int fd)
 {
-	struct bpf_prog_info info = {};
+	struct bpf_prog_info info;
 	__u32 info_len = sizeof(info);
 	char name[256];
 	int len, ret;
 
+	memset(&info, 0, info_len);
 	ret = bpf_obj_get_info_by_fd(fd, &info, &info_len);
 	if (ret < 0)
 		return ret;

src/relo_core.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:
@@ -251,7 +253,7 @@ recur:
  *   - 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.
  *
@@ -568,9 +570,14 @@ 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)) {
-		return bpf_core_types_are_compat(local_spec->btf,
-						 local_spec->root_type_id,
-						 targ_btf, targ_id);
+		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);
 	}
 
 	local_acc = &local_spec->spec[0];
@@ -819,6 +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:
@@ -1410,3 +1418,273 @@ int bpf_core_calc_relo_insn(const char *prog_name,
 
 	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

@@ -72,6 +72,10 @@ 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);
 

src/ringbuf.c

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

src/skel_internal.h

@@ -66,13 +66,13 @@ struct bpf_load_and_run_opts {
 	const char *errstr;
 };
 
-long bpf_sys_bpf(__u32 cmd, void *attr, __u32 attr_size);
+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 bpf_sys_bpf(cmd, attr, size);
+	return kern_sys_bpf(cmd, attr, size);
 #else
 	return syscall(__NR_bpf, cmd, attr, size);
 #endif
@@ -251,6 +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);
@@ -285,6 +308,8 @@ static inline int skel_link_create(int prog_fd, int target_fd,
 
 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;
 
@@ -302,7 +327,7 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
 		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);
@@ -313,18 +338,18 @@ 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;
-	err = 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";
 		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) {

src/usdt.bpf.h

@@ -6,7 +6,6 @@
 #include <linux/errno.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-#include <bpf/bpf_core_read.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
@@ -30,14 +29,6 @@
 #ifndef BPF_USDT_MAX_IP_CNT
 #define BPF_USDT_MAX_IP_CNT (4 * BPF_USDT_MAX_SPEC_CNT)
 #endif
-/* We use BPF CO-RE to detect support for BPF cookie from BPF side. This is
- * the only dependency on CO-RE, so if it's undesirable, user can override
- * BPF_USDT_HAS_BPF_COOKIE to specify whether to BPF cookie is supported or not.
- */
-#ifndef BPF_USDT_HAS_BPF_COOKIE
-#define BPF_USDT_HAS_BPF_COOKIE \
-	bpf_core_enum_value_exists(enum bpf_func_id___usdt, BPF_FUNC_get_attach_cookie___usdt)
-#endif
 
 enum __bpf_usdt_arg_type {
 	BPF_USDT_ARG_CONST,
@@ -83,15 +74,12 @@ struct {
 	__type(value, __u32);
 } __bpf_usdt_ip_to_spec_id SEC(".maps") __weak;
 
-/* don't rely on user's BPF code to have latest definition of bpf_func_id */
-enum bpf_func_id___usdt {
-	BPF_FUNC_get_attach_cookie___usdt = 0xBAD, /* value doesn't matter */
-};
+extern const _Bool LINUX_HAS_BPF_COOKIE __kconfig;
 
 static __always_inline
 int __bpf_usdt_spec_id(struct pt_regs *ctx)
 {
-	if (!BPF_USDT_HAS_BPF_COOKIE) {
+	if (!LINUX_HAS_BPF_COOKIE) {
 		long ip = PT_REGS_IP(ctx);
 		int *spec_id_ptr;
 
@@ -244,7 +232,7 @@ long bpf_usdt_cookie(struct pt_regs *ctx)
  */
 #define BPF_USDT(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)				    \
 {									    \
@@ -253,7 +241,7 @@ typeof(name(0)) name(struct pt_regs *ctx)				    \
         return ____##name(___bpf_usdt_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)
 
 #endif /* __USDT_BPF_H__ */

src/usdt.c

@@ -282,7 +282,7 @@ struct usdt_manager *usdt_manager_new(struct bpf_object *obj)
 	 * If this is not supported, USDTs with semaphores will not be supported.
 	 * Added in: a6ca88b241d5 ("trace_uprobe: support reference counter in fd-based uprobe")
 	 */
-	man->has_sema_refcnt = access(ref_ctr_sysfs_path, F_OK) == 0;
+	man->has_sema_refcnt = faccessat(AT_FDCWD, ref_ctr_sysfs_path, F_OK, AT_EACCESS) == 0;
 
 	return man;
 }
@@ -652,11 +652,9 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char *
 		 *
 		 *   [0] https://sourceware.org/systemtap/wiki/UserSpaceProbeImplementation
 		 */
-		usdt_rel_ip = usdt_abs_ip = note.loc_addr;
-		if (base_addr) {
+		usdt_abs_ip = note.loc_addr;
+		if (base_addr)
 			usdt_abs_ip += base_addr - note.base_addr;
-			usdt_rel_ip += base_addr - note.base_addr;
-		}
 
 		/* When attaching uprobes (which is what USDTs basically are)
 		 * kernel expects file offset to be specified, not a relative

travis-ci

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

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

@@ -1,6 +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
-varlen

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

@@ -1,67 +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)
-mptcp
-kprobe_multi_test                        # relies on fentry
-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_lookup                                # endianness problem
-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_crash                              # 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)
-map_kptr                                 # failed to open_and_load program: -524 (trampoline)
-bpf_cookie                               # failed to open_and_load program: -524 (trampoline)
-xdp_do_redirect                          # prog_run_max_size unexpected error: -22 (errno 22)
-send_signal                              # intermittently fails to receive signal
-select_reuseport                         # intermittently fails on new s390x setup
-xdp_synproxy                             # JIT does not support calling kernel function                                (kfunc)
-unpriv_bpf_disabled                      # fentry

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