Merge branch 'libbpf:master' into master

Syncing latest libbpf commits from kernel repository.
Baseline bpf-next commit:   227a0713b319e7a8605312dee1c97c97a719a9fc
Checkpoint bpf-next commit: dc37dc617fabfb1c3a16d49f5d8cc20e9e3608ca
Baseline bpf commit:        77b1b8b43ec3c060ecf7e926a92b0f8772171046
Checkpoint bpf commit:      fe68195daf34d5dddacd3f93dd3eafc4beca3a0e

Andrii Nakryiko (1):
  libbpf: Fix compilation warning due to mismatched printf format

Dan Carpenter (1):
  libbpf: Fix signedness bug in btf_dump_array_data()

Hengqi Chen (1):
  libbpf: Add BPF_KPROBE_SYSCALL macro

Ilya Leoshkevich (7):
  libbpf: Add PT_REGS_SYSCALL_REGS macro
  libbpf: Fix accessing syscall arguments on powerpc
  libbpf: Fix riscv register names
  libbpf: Fix accessing syscall arguments on riscv
  libbpf: Allow overriding PT_REGS_PARM1{_CORE}_SYSCALL
  libbpf: Fix accessing the first syscall argument on arm64
  libbpf: Fix accessing the first syscall argument on s390

Mauricio Vásquez (1):
  libbpf: Remove mode check in libbpf_set_strict_mode()

 src/bpf_tracing.h | 85 +++++++++++++++++++++++++++++++++++++++++------
 src/btf_dump.c    |  6 ++--
 src/libbpf.c      |  8 -----
 3 files changed, 79 insertions(+), 20 deletions(-)

--
2.30.2

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

@@ -0,0 +1,30 @@
+name: 'build-selftests'
+description: 'Build BPF selftests'
+inputs:
+  repo-path:
+    description: 'where is the source code'
+    required: true
+  kernel:
+    description: 'kernel version or LATEST'
+    required: true
+    default: 'LATEST'
+  vmlinux:
+    description: 'where is vmlinux file'
+    required: true
+    default: '${{ github.workspace }}/vmlinux'
+
+runs:
+  using: "composite"
+  steps:
+    - shell: bash
+      run: |
+        echo "::group::Setup Env"
+        sudo apt-get install -y qemu-kvm zstd binutils-dev elfutils libcap-dev libelf-dev libdw-dev python3-docutils
+        echo "::endgroup::"
+    - shell: bash
+      run: |
+        export KERNEL=${{ inputs.kernel }}
+        export REPO_ROOT="${{ github.workspace }}"
+        export REPO_PATH="${{ inputs.repo-path }}"
+        export VMLINUX_BTF="${{ inputs.vmlinux }}"
+        ${{ github.action_path }}/build_selftests.sh

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

@@ -2,16 +2,16 @@
 
 set -euo pipefail
 
-source $(cd $(dirname $0) && pwd)/helpers.sh
+THISDIR="$(cd $(dirname $0) && pwd)"
+
+source ${THISDIR}/helpers.sh
 
 travis_fold start prepare_selftests "Building selftests"
 
-sudo apt-get -y install python3-docutils # for rst2man
-
-LLVM_VER=14
+LLVM_VER=15
 LIBBPF_PATH="${REPO_ROOT}"
 
-PREPARE_SELFTESTS_SCRIPT=${VMTEST_ROOT}/prepare_selftests-${KERNEL}.sh
+PREPARE_SELFTESTS_SCRIPT=${THISDIR}/prepare_selftests-${KERNEL}.sh
 if [ -f "${PREPARE_SELFTESTS_SCRIPT}" ]; then
 	(cd "${REPO_ROOT}/${REPO_PATH}/tools/testing/selftests/bpf" && ${PREPARE_SELFTESTS_SCRIPT})
 fi
@@ -19,9 +19,10 @@ fi
 if [[ "${KERNEL}" = 'LATEST' ]]; then
 	VMLINUX_H=
 else
-	VMLINUX_H=${VMTEST_ROOT}/vmlinux.h
+	VMLINUX_H=${THISDIR}/vmlinux.h
 fi
 
+cd ${REPO_ROOT}/${REPO_PATH}
 make \
 	CLANG=clang-${LLVM_VER} \
 	LLC=llc-${LLVM_VER} \
@@ -29,7 +30,8 @@ make \
 	VMLINUX_BTF="${VMLINUX_BTF}" \
 	VMLINUX_H=${VMLINUX_H} \
 	-C "${REPO_ROOT}/${REPO_PATH}/tools/testing/selftests/bpf" \
-	-j $((4*$(nproc))) >/dev/null
+	-j $((4*$(nproc))) > /dev/null
+cd -
 mkdir ${LIBBPF_PATH}/selftests
 cp -R "${REPO_ROOT}/${REPO_PATH}/tools/testing/selftests/bpf" \
 	${LIBBPF_PATH}/selftests
@@ -37,6 +39,4 @@ cd ${LIBBPF_PATH}
 rm selftests/bpf/.gitignore
 git add selftests
 
-git add "${VMTEST_ROOT}"/configs/blacklist/BLACKLIST-* "${VMTEST_ROOT}"/configs/whitelist/WHITELIST-*
-
 travis_fold end prepare_selftests

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

@@ -0,0 +1,44 @@
+# $1 - start or end
+# $2 - fold identifier, no spaces
+# $3 - fold section description
+travis_fold() {
+  local YELLOW='\033[1;33m'
+  local NOCOLOR='\033[0m'
+  if [ -z ${GITHUB_WORKFLOW+x} ]; then
+    echo travis_fold:$1:$2
+    if [ ! -z "${3:-}" ]; then
+      echo -e "${YELLOW}$3${NOCOLOR}"
+    fi
+    echo
+  else
+    if [ $1 = "start" ]; then
+      line="::group::$2"
+      if [ ! -z "${3:-}" ]; then
+        line="$line - ${YELLOW}$3${NOCOLOR}"
+      fi
+    else
+      line="::endgroup::"
+    fi
+    echo -e "$line"
+  fi
+}
+
+__print() {
+  local TITLE=""
+  if [[ -n $2 ]]; then
+      TITLE=" title=$2"
+  fi
+  echo "::$1${TITLE}::$3"
+}
+
+# $1 - title
+# $2 - message
+print_error() {
+  __print error $1 $2
+}
+
+# $1 - title
+# $2 - message
+print_notice() {
+  __print notice $1 $2
+}

.github/actions/vmtest/action.yml

@@ -5,31 +5,83 @@ inputs:
     description: 'kernel version or LATEST'
     required: true
     default: 'LATEST'
-  kernel-rev:
-    description: 'CHECKPOINT or rev/tag/branch'
+  arch:
+    description: 'what arch to test'
     required: true
-    default: 'CHECKPOINT'
-  kernel-origin:
-    description: 'kernel repo'
-    required: true
-    default: 'https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git'
+    default: 'x86_64'
   pahole:
-    description: 'pahole rev/tag/branch'
+    description: 'pahole rev or master'
     required: true
     default: 'master'
-  pahole-origin:
-    description: 'pahole repo'
-    required: true
-    default: 'https://git.kernel.org/pub/scm/devel/pahole/pahole.git'
 runs:
   using: "composite"
   steps:
-    - run: |
-        source /tmp/ci_setup
-        export KERNEL=${{ inputs.kernel }}
-        export KERNEL_BRANCH=${{ inputs.kernel-rev }}
-        export KERNEL_ORIGIN=${{ inputs.kernel-origin }}
-        export PAHOLE_BRANCH=${{ inputs.pahole }}
-        export PAHOLE_ORIGIN=${{ inputs.pahole-origin }}
-        $CI_ROOT/vmtest/run_vmtest.sh
+    # setup envinronment
+    - name: Setup environment
+      uses: libbpf/ci/setup-build-env@master
+      with:
+        pahole: ${{ inputs.pahole }}
+    # 1. download CHECKPOINT kernel source
+    - name: Get checkpoint commit
       shell: bash
+      run: |
+        cat CHECKPOINT-COMMIT
+        echo "CHECKPOINT=$(cat CHECKPOINT-COMMIT)" >> $GITHUB_ENV
+    - name: Get kernel source at checkpoint
+      uses: libbpf/ci/get-linux-source@master
+      with:
+        repo: 'https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git'
+        rev: ${{ env.CHECKPOINT }}
+        dest: '${{ github.workspace }}/.kernel'
+    - name: Patch kernel source
+      uses: libbpf/ci/patch-kernel@master
+      with:
+        patches-root: '${{ github.workspace }}/travis-ci/diffs'
+        repo-root: '.kernel'
+    - name: Prepare to build BPF selftests
+      shell: bash
+      run: |
+        echo "::group::Prepare buidling selftest"
+        cd .kernel
+        cp ${{ github.workspace }}/travis-ci/vmtest/configs/config-latest.${{ inputs.arch }} .config
+        make olddefconfig && make prepare
+        cd -
+        echo "::endgroup::"
+    # 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"
+        cd .kernel
+        make -j $((4*$(nproc))) all > /dev/null
+        cp vmlinux ${{ github.workspace }}
+        cd -
+        echo "::endgroup::"
+    # else, just download prebuilt kernel image
+    - name: Download prebuilt kernel
+      if: ${{ inputs.kernel != 'LATEST' }}
+      uses: libbpf/ci/download-vmlinux@master
+      with:
+        kernel: ${{ inputs.kernel }}
+        arch: ${{ inputs.arch }}
+    # 3. build selftests
+    - name: Build BPF selftests
+      uses: ./.github/actions/build-selftests
+      with:
+        repo-path: '.kernel'
+        kernel: ${{ inputs.kernel }}
+    # 4. prepare rootfs
+    - name: prepare rootfs
+      uses: libbpf/ci/prepare-rootfs@master
+      with:
+        kernel: ${{ inputs.kernel }}
+        project-name: 'libbpf'
+        arch: ${{ inputs.arch }}
+    # 5. run selftest in QEMU
+    - name: Run selftests
+      uses: libbpf/ci/run-qemu@master
+      with:
+        img: '/tmp/root.img'
+        vmlinuz: 'vmlinuz'
+        arch: ${{ inputs.arch }}

.github/workflows/build.yml

@@ -0,0 +1,81 @@
+name: libbpf-build
+
+on:
+  pull_request:
+  push:
+  schedule:
+    - cron:  '0 18 * * *'
+
+concurrency:
+  group: ci-build-${{ github.head_ref }}
+  cancel-in-progress: true
+
+jobs:
+
+  debian:
+    runs-on: ubuntu-latest
+    name: Debian Build (${{ matrix.name }})
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - name: default
+            target: RUN
+          - name: ASan+UBSan
+            target: RUN_ASAN
+          - name: clang
+            target: RUN_CLANG
+          - name: clang ASan+UBSan
+            target: RUN_CLANG_ASAN
+          - name: gcc-10
+            target: RUN_GCC10
+          - name: gcc-10 ASan+UBSan
+            target: RUN_GCC10_ASAN
+    steps:
+      - uses: actions/checkout@v2
+        name: Checkout
+      - uses: ./.github/actions/setup
+        name: Setup
+      - uses: ./.github/actions/debian
+        name: Build
+        with:
+          target: ${{ matrix.target }}
+
+  ubuntu:
+    runs-on: ubuntu-latest
+    name: Ubuntu Focal Build (${{ matrix.arch }})
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - arch: aarch64
+          - arch: ppc64le
+          - arch: s390x
+          - arch: x86
+    steps:
+      - uses: actions/checkout@v2
+        name: Checkout
+      - uses: ./.github/actions/setup
+        name: Pre-Setup
+      - run: source /tmp/ci_setup && sudo -E $CI_ROOT/managers/ubuntu.sh
+        if: matrix.arch == 'x86'
+        name: Setup
+      - uses: uraimo/run-on-arch-action@v2.0.5
+        name: Build in docker
+        if: matrix.arch != 'x86'
+        with:
+          distro:
+            ubuntu20.04
+          arch:
+            ${{ matrix.arch }}
+          setup:
+            cp /tmp/ci_setup $GITHUB_WORKSPACE
+          dockerRunArgs: |
+            --volume "${GITHUB_WORKSPACE}:${GITHUB_WORKSPACE}"
+          shell: /bin/bash
+          install: |
+            export DEBIAN_FRONTEND=noninteractive
+            export TZ="America/Los_Angeles"
+            apt-get update -y
+            apt-get install -y tzdata build-essential sudo
+          run: source ${GITHUB_WORKSPACE}/ci_setup && $CI_ROOT/managers/ubuntu.sh

.github/workflows/test.yml

@@ -20,12 +20,16 @@ jobs:
         include:
           - kernel: 'LATEST'
             runs_on: ubuntu-latest
-          - kernel: 'LATEST'
-            runs_on: z15
+            arch: 'x86_64'
           - kernel: '5.5.0'
             runs_on: ubuntu-latest
+            arch: 'x86_64'
           - kernel: '4.9.0'
             runs_on: ubuntu-latest
+            arch: 'x86_64'
+          - kernel: 'LATEST'
+            runs_on: z15
+            arch: 's390x'
     steps:
       - uses: actions/checkout@v2
         name: Checkout
@@ -35,71 +39,4 @@ jobs:
         name: vmtest
         with:
           kernel: ${{ matrix.kernel }}
-
-  debian:
-    runs-on: ubuntu-latest
-    name: Debian Build (${{ matrix.name }})
-    strategy:
-      fail-fast: false
-      matrix:
-        include:
-          - name: default
-            target: RUN
-          - name: ASan+UBSan
-            target: RUN_ASAN
-          - name: clang
-            target: RUN_CLANG
-          - name: clang ASan+UBSan
-            target: RUN_CLANG_ASAN
-          - name: gcc-10
-            target: RUN_GCC10
-          - name: gcc-10 ASan+UBSan
-            target: RUN_GCC10_ASAN
-    steps:
-      - uses: actions/checkout@v2
-        name: Checkout
-      - uses: ./.github/actions/setup
-        name: Setup
-      - uses: ./.github/actions/debian
-        name: Build
-        with:
-          target: ${{ matrix.target }}
-
-  ubuntu:
-    runs-on: ubuntu-latest
-    name: Ubuntu Focal Build (${{ matrix.arch }})
-    strategy:
-      fail-fast: false
-      matrix:
-        include:
-          - arch: aarch64
-          - arch: ppc64le
-          - arch: s390x
-          - arch: x86
-    steps:
-      - uses: actions/checkout@v2
-        name: Checkout
-      - uses: ./.github/actions/setup
-        name: Pre-Setup
-      - run: source /tmp/ci_setup && sudo -E $CI_ROOT/managers/ubuntu.sh
-        if: matrix.arch == 'x86'
-        name: Setup
-      - uses: uraimo/run-on-arch-action@v2.0.5
-        name: Build in docker
-        if: matrix.arch != 'x86'
-        with:
-          distro:
-            ubuntu20.04
-          arch:
-            ${{ matrix.arch }}
-          setup:
-            cp /tmp/ci_setup $GITHUB_WORKSPACE
-          dockerRunArgs: |
-              --volume "${GITHUB_WORKSPACE}:${GITHUB_WORKSPACE}"
-          shell: /bin/bash
-          install: |
-              export DEBIAN_FRONTEND=noninteractive
-              export TZ="America/Los_Angeles"
-              apt-get update -y
-              apt-get install -y tzdata build-essential sudo
-          run: source ${GITHUB_WORKSPACE}/ci_setup && $CI_ROOT/managers/ubuntu.sh
+          arch: ${{ matrix.arch }}

BPF-CHECKPOINT-COMMIT

@@ -1 +1 @@
-c0d95d3380ee099d735e08618c0d599e72f6c8b0
+fe68195daf34d5dddacd3f93dd3eafc4beca3a0e

CHECKPOINT-COMMIT

@@ -1 +1 @@
-43174f0d4597325cb91f1f1f55263eb6e6101036
+dc37dc617fabfb1c3a16d49f5d8cc20e9e3608ca

README.md

@@ -81,7 +81,7 @@ Distributions packaging libbpf from this mirror:
   - [Gentoo](https://packages.gentoo.org/packages/dev-libs/libbpf)
   - [Debian](https://packages.debian.org/source/sid/libbpf)
   - [Arch](https://www.archlinux.org/packages/extra/x86_64/libbpf/)
-  - [Ubuntu](https://packages.ubuntu.com/source/groovy/libbpf)
+  - [Ubuntu](https://packages.ubuntu.com/source/impish/libbpf)
   - [Alpine](https://pkgs.alpinelinux.org/packages?name=libbpf)
 
 Benefits of packaging from the mirror over packaging from kernel sources:

docs/api.rst

@@ -6,7 +6,49 @@
 
 
 LIBBPF API
-==================
+==========
+
+Error Handling
+--------------
+
+When libbpf is used in "libbpf 1.0 mode", API functions can return errors in one of two ways.
+
+You can set "libbpf 1.0" mode with the following line:
+
+.. code-block::
+
+    libbpf_set_strict_mode(LIBBPF_STRICT_DIRECT_ERRS | LIBBPF_STRICT_CLEAN_PTRS);
+
+If the function returns an error code directly, it uses 0 to indicate success
+and a negative error code to indicate what caused the error. In this case the
+error code should be checked directly from the return, you do not need to check
+errno.
+
+For example:
+
+.. code-block::
+
+    err = some_libbpf_api_with_error_return(...);
+    if (err < 0) {
+        /* Handle error accordingly */
+    }
+
+If the function returns a pointer, it will return NULL to indicate there was
+an error. In this case errno should be checked for the error code.
+
+For example:
+
+.. code-block::
+
+    ptr = some_libbpf_api_returning_ptr();
+    if (!ptr) {
+        /* note no minus sign for EINVAL and E2BIG below */
+        if (errno == EINVAL) {
+           /* handle EINVAL error */
+        } else if (errno == E2BIG) {
+           /* handle E2BIG error */
+        }
+    }
 
 libbpf.h
 --------

fuzz/bpf-object-fuzzer.c

@@ -0,0 +1,23 @@
+#include "libbpf.h"
+
+static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args)
+{
+	return 0;
+}
+
+int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
+	struct bpf_object *obj = NULL;
+	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts);
+	int err;
+
+	libbpf_set_print(libbpf_print_fn);
+
+	opts.object_name = "fuzz-object";
+	obj = bpf_object__open_mem(data, size, &opts);
+	err = libbpf_get_error(obj);
+	if (err)
+		return 0;
+
+	bpf_object__close(obj);
+	return 0;
+}

include/linux/types.h

@@ -7,6 +7,8 @@
 #include <stddef.h>
 #include <stdint.h>
 
+#include <linux/stddef.h>
+
 #include <asm/types.h>
 #include <asm/posix_types.h>
 

include/uapi/linux/bpf.h

@@ -330,6 +330,8 @@ union bpf_iter_link_info {
  *			*ctx_out*, *data_in* and *data_out* must be NULL.
  *			*repeat* must be zero.
  *
+ *		BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN.
+ *
  *	Return
  *		Returns zero on success. On error, -1 is returned and *errno*
  *		is set appropriately.
@@ -1111,6 +1113,11 @@ enum bpf_link_type {
  */
 #define BPF_F_SLEEPABLE		(1U << 4)
 
+/* If BPF_F_XDP_HAS_FRAGS is used in BPF_PROG_LOAD command, the loaded program
+ * fully support xdp frags.
+ */
+#define BPF_F_XDP_HAS_FRAGS	(1U << 5)
+
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * the following extensions:
  *
@@ -1342,8 +1349,10 @@ union bpf_attr {
 			/* or valid module BTF object fd or 0 to attach to vmlinux */
 			__u32		attach_btf_obj_fd;
 		};
-		__u32		:32;		/* pad */
+		__u32		core_relo_cnt;	/* number of bpf_core_relo */
 		__aligned_u64	fd_array;	/* array of FDs */
+		__aligned_u64	core_relos;
+		__u32		core_relo_rec_size; /* sizeof(struct bpf_core_relo) */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -1773,6 +1782,8 @@ union bpf_attr {
  * 		0 on success, or a negative error in case of failure.
  *
  * u64 bpf_get_current_pid_tgid(void)
+ * 	Description
+ * 		Get the current pid and tgid.
  * 	Return
  * 		A 64-bit integer containing the current tgid and pid, and
  * 		created as such:
@@ -1780,6 +1791,8 @@ union bpf_attr {
  * 		*current_task*\ **->pid**.
  *
  * u64 bpf_get_current_uid_gid(void)
+ * 	Description
+ * 		Get the current uid and gid.
  * 	Return
  * 		A 64-bit integer containing the current GID and UID, and
  * 		created as such: *current_gid* **<< 32 \|** *current_uid*.
@@ -2254,6 +2267,8 @@ union bpf_attr {
  * 		The 32-bit hash.
  *
  * u64 bpf_get_current_task(void)
+ * 	Description
+ * 		Get the current task.
  * 	Return
  * 		A pointer to the current task struct.
  *
@@ -2367,6 +2382,8 @@ union bpf_attr {
  * 		indicate that the hash is outdated and to trigger a
  * 		recalculation the next time the kernel tries to access this
  * 		hash or when the **bpf_get_hash_recalc**\ () helper is called.
+ * 	Return
+ * 		void.
  *
  * long bpf_get_numa_node_id(void)
  * 	Description
@@ -2464,6 +2481,8 @@ union bpf_attr {
  * 		A 8-byte long unique number or 0 if *sk* is NULL.
  *
  * u32 bpf_get_socket_uid(struct sk_buff *skb)
+ * 	Description
+ * 		Get the owner UID of the socked associated to *skb*.
  * 	Return
  * 		The owner UID of the socket associated to *skb*. If the socket
  * 		is **NULL**, or if it is not a full socket (i.e. if it is a
@@ -3238,6 +3257,9 @@ union bpf_attr {
  * 		The id is returned or 0 in case the id could not be retrieved.
  *
  * u64 bpf_get_current_cgroup_id(void)
+ * 	Description
+ * 		Get the current cgroup id based on the cgroup within which
+ * 		the current task is running.
  * 	Return
  * 		A 64-bit integer containing the current cgroup id based
  * 		on the cgroup within which the current task is running.
@@ -4957,6 +4979,113 @@ union bpf_attr {
  *		**-ENOENT** if *task->mm* is NULL, or no vma contains *addr*.
  *		**-EBUSY** if failed to try lock mmap_lock.
  *		**-EINVAL** for invalid **flags**.
+ *
+ * long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags)
+ *	Description
+ *		For **nr_loops**, call **callback_fn** function
+ *		with **callback_ctx** as the context parameter.
+ *		The **callback_fn** should be a static function and
+ *		the **callback_ctx** should be a pointer to the stack.
+ *		The **flags** is used to control certain aspects of the helper.
+ *		Currently, the **flags** must be 0. Currently, nr_loops is
+ *		limited to 1 << 23 (~8 million) loops.
+ *
+ *		long (\*callback_fn)(u32 index, void \*ctx);
+ *
+ *		where **index** is the current index in the loop. The index
+ *		is zero-indexed.
+ *
+ *		If **callback_fn** returns 0, the helper will continue to the next
+ *		loop. If return value is 1, the helper will skip the rest of
+ *		the loops and return. Other return values are not used now,
+ *		and will be rejected by the verifier.
+ *
+ *	Return
+ *		The number of loops performed, **-EINVAL** for invalid **flags**,
+ *		**-E2BIG** if **nr_loops** exceeds the maximum number of loops.
+ *
+ * long bpf_strncmp(const char *s1, u32 s1_sz, const char *s2)
+ *	Description
+ *		Do strncmp() between **s1** and **s2**. **s1** doesn't need
+ *		to be null-terminated and **s1_sz** is the maximum storage
+ *		size of **s1**. **s2** must be a read-only string.
+ *	Return
+ *		An integer less than, equal to, or greater than zero
+ *		if the first **s1_sz** bytes of **s1** is found to be
+ *		less than, to match, or be greater than **s2**.
+ *
+ * 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)
+ *		returned in **value**.
+ *
+ *	Return
+ *		0 on success.
+ *		**-EINVAL** if n >= arguments count of traced function.
+ *
+ * long bpf_get_func_ret(void *ctx, u64 *value)
+ *	Description
+ *		Get return value of the traced function (for tracing programs)
+ *		in **value**.
+ *
+ *	Return
+ *		0 on success.
+ *		**-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN.
+ *
+ * long bpf_get_func_arg_cnt(void *ctx)
+ *	Description
+ *		Get number of arguments of the traced function (for tracing programs).
+ *
+ *	Return
+ *		The number of arguments of the traced function.
+ *
+ * int bpf_get_retval(void)
+ *	Description
+ *		Get the syscall's return value that will be returned to userspace.
+ *
+ *		This helper is currently supported by cgroup programs only.
+ *	Return
+ *		The syscall's return value.
+ *
+ * int bpf_set_retval(int retval)
+ *	Description
+ *		Set the syscall's return value that will be returned to userspace.
+ *
+ *		This helper is currently supported by cgroup programs only.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md)
+ *	Description
+ *		Get the total size of a given xdp buff (linear and paged area)
+ *	Return
+ *		The total size of a given xdp buffer.
+ *
+ * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len)
+ *	Description
+ *		This helper is provided as an easy way to load data from a
+ *		xdp buffer. It can be used to load *len* bytes from *offset* from
+ *		the frame associated to *xdp_md*, into the buffer pointed by
+ *		*buf*.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len)
+ *	Description
+ *		Store *len* bytes from buffer *buf* into the frame
+ *		associated to *xdp_md*, at *offset*.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * long bpf_copy_from_user_task(void *dst, u32 size, const void *user_ptr, struct task_struct *tsk, u64 flags)
+ *	Description
+ *		Read *size* bytes from user space address *user_ptr* in *tsk*'s
+ *		address space, and stores the data in *dst*. *flags* is not
+ *		used yet and is provided for future extensibility. This helper
+ *		can only be used by sleepable programs.
+ *	Return
+ *		0 on success, or a negative error in case of failure. On error
+ *		*dst* buffer is zeroed out.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5140,6 +5269,17 @@ union bpf_attr {
 	FN(skc_to_unix_sock),		\
 	FN(kallsyms_lookup_name),	\
 	FN(find_vma),			\
+	FN(loop),			\
+	FN(strncmp),			\
+	FN(get_func_arg),		\
+	FN(get_func_ret),		\
+	FN(get_func_arg_cnt),		\
+	FN(get_retval),			\
+	FN(set_retval),			\
+	FN(xdp_get_buff_len),		\
+	FN(xdp_load_bytes),		\
+	FN(xdp_store_bytes),		\
+	FN(copy_from_user_task),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -5434,7 +5574,8 @@ struct bpf_sock {
 	__u32 src_ip4;
 	__u32 src_ip6[4];
 	__u32 src_port;		/* host byte order */
-	__u32 dst_port;		/* network byte order */
+	__be16 dst_port;	/* network byte order */
+	__u16 :16;		/* zero padding */
 	__u32 dst_ip4;
 	__u32 dst_ip6[4];
 	__u32 state;
@@ -6349,4 +6490,78 @@ enum {
 	BTF_F_ZERO	=	(1ULL << 3),
 };
 
+/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value
+ * has to be adjusted by relocations. It is emitted by llvm and passed to
+ * libbpf and later to the kernel.
+ */
+enum bpf_core_relo_kind {
+	BPF_CORE_FIELD_BYTE_OFFSET = 0,      /* field byte offset */
+	BPF_CORE_FIELD_BYTE_SIZE = 1,        /* field size in bytes */
+	BPF_CORE_FIELD_EXISTS = 2,           /* field existence in target kernel */
+	BPF_CORE_FIELD_SIGNED = 3,           /* field signedness (0 - unsigned, 1 - signed) */
+	BPF_CORE_FIELD_LSHIFT_U64 = 4,       /* bitfield-specific left bitshift */
+	BPF_CORE_FIELD_RSHIFT_U64 = 5,       /* bitfield-specific right bitshift */
+	BPF_CORE_TYPE_ID_LOCAL = 6,          /* type ID in local BPF object */
+	BPF_CORE_TYPE_ID_TARGET = 7,         /* type ID in target kernel */
+	BPF_CORE_TYPE_EXISTS = 8,            /* type existence in target kernel */
+	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 */
+};
+
+/*
+ * "struct bpf_core_relo" is used to pass relocation data form LLVM to libbpf
+ * and from libbpf to the kernel.
+ *
+ * CO-RE relocation captures the following data:
+ * - insn_off - instruction offset (in bytes) within a BPF program that needs
+ *   its insn->imm field to be relocated with actual field info;
+ * - type_id - BTF type ID of the "root" (containing) entity of a relocatable
+ *   type or field;
+ * - access_str_off - offset into corresponding .BTF string section. String
+ *   interpretation depends on specific relocation kind:
+ *     - for field-based relocations, string encodes an accessed field using
+ *       a sequence of field and array indices, separated by colon (:). It's
+ *       conceptually very close to LLVM's getelementptr ([0]) instruction's
+ *       arguments for identifying offset to a field.
+ *     - for type-based relocations, strings is expected to be just "0";
+ *     - for enum value-based relocations, string contains an index of enum
+ *       value within its enum type;
+ * - kind - one of enum bpf_core_relo_kind;
+ *
+ * Example:
+ *   struct sample {
+ *       int a;
+ *       struct {
+ *           int b[10];
+ *       };
+ *   };
+ *
+ *   struct sample *s = ...;
+ *   int *x = &s->a;     // encoded as "0:0" (a is field #0)
+ *   int *y = &s->b[5];  // encoded as "0:1:0:5" (anon struct is field #1,
+ *                       // b is field #0 inside anon struct, accessing elem #5)
+ *   int *z = &s[10]->b; // encoded as "10:1" (ptr is used as an array)
+ *
+ * type_id for all relocs in this example will capture BTF type id of
+ * `struct sample`.
+ *
+ * Such relocation is emitted when using __builtin_preserve_access_index()
+ * Clang built-in, passing expression that captures field address, e.g.:
+ *
+ * bpf_probe_read(&dst, sizeof(dst),
+ *		  __builtin_preserve_access_index(&src->a.b.c));
+ *
+ * In this case Clang will emit field relocation recording necessary data to
+ * be able to find offset of embedded `a.b.c` field within `src` struct.
+ *
+ * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction
+ */
+struct bpf_core_relo {
+	__u32 insn_off;
+	__u32 type_id;
+	__u32 access_str_off;
+	enum bpf_core_relo_kind kind;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */

include/uapi/linux/if_link.h

@@ -7,24 +7,23 @@
 
 /* This struct should be in sync with struct rtnl_link_stats64 */
 struct rtnl_link_stats {
-	__u32	rx_packets;		/* total packets received	*/
-	__u32	tx_packets;		/* total packets transmitted	*/
-	__u32	rx_bytes;		/* total bytes received 	*/
-	__u32	tx_bytes;		/* total bytes transmitted	*/
-	__u32	rx_errors;		/* bad packets received		*/
-	__u32	tx_errors;		/* packet transmit problems	*/
-	__u32	rx_dropped;		/* no space in linux buffers	*/
-	__u32	tx_dropped;		/* no space available in linux	*/
-	__u32	multicast;		/* multicast packets received	*/
+	__u32	rx_packets;
+	__u32	tx_packets;
+	__u32	rx_bytes;
+	__u32	tx_bytes;
+	__u32	rx_errors;
+	__u32	tx_errors;
+	__u32	rx_dropped;
+	__u32	tx_dropped;
+	__u32	multicast;
 	__u32	collisions;
-
 	/* detailed rx_errors: */
 	__u32	rx_length_errors;
-	__u32	rx_over_errors;		/* receiver ring buff overflow	*/
-	__u32	rx_crc_errors;		/* recved pkt with crc error	*/
-	__u32	rx_frame_errors;	/* recv'd frame alignment error */
-	__u32	rx_fifo_errors;		/* recv'r fifo overrun		*/
-	__u32	rx_missed_errors;	/* receiver missed packet	*/
+	__u32	rx_over_errors;
+	__u32	rx_crc_errors;
+	__u32	rx_frame_errors;
+	__u32	rx_fifo_errors;
+	__u32	rx_missed_errors;
 
 	/* detailed tx_errors */
 	__u32	tx_aborted_errors;
@@ -37,29 +36,201 @@ struct rtnl_link_stats {
 	__u32	rx_compressed;
 	__u32	tx_compressed;
 
-	__u32	rx_nohandler;		/* dropped, no handler found	*/
+	__u32	rx_nohandler;
 };
 
-/* The main device statistics structure */
+/**
+ * struct rtnl_link_stats64 - The main device statistics structure.
+ *
+ * @rx_packets: Number of good packets received by the interface.
+ *   For hardware interfaces counts all good packets received from the device
+ *   by the host, including packets which host had to drop at various stages
+ *   of processing (even in the driver).
+ *
+ * @tx_packets: Number of packets successfully transmitted.
+ *   For hardware interfaces counts packets which host was able to successfully
+ *   hand over to the device, which does not necessarily mean that packets
+ *   had been successfully transmitted out of the device, only that device
+ *   acknowledged it copied them out of host memory.
+ *
+ * @rx_bytes: Number of good received bytes, corresponding to @rx_packets.
+ *
+ *   For IEEE 802.3 devices should count the length of Ethernet Frames
+ *   excluding the FCS.
+ *
+ * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets.
+ *
+ *   For IEEE 802.3 devices should count the length of Ethernet Frames
+ *   excluding the FCS.
+ *
+ * @rx_errors: Total number of bad packets received on this network device.
+ *   This counter must include events counted by @rx_length_errors,
+ *   @rx_crc_errors, @rx_frame_errors and other errors not otherwise
+ *   counted.
+ *
+ * @tx_errors: Total number of transmit problems.
+ *   This counter must include events counter by @tx_aborted_errors,
+ *   @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors,
+ *   @tx_window_errors and other errors not otherwise counted.
+ *
+ * @rx_dropped: Number of packets received but not processed,
+ *   e.g. due to lack of resources or unsupported protocol.
+ *   For hardware interfaces this counter may include packets discarded
+ *   due to L2 address filtering but should not include packets dropped
+ *   by the device due to buffer exhaustion which are counted separately in
+ *   @rx_missed_errors (since procfs folds those two counters together).
+ *
+ * @tx_dropped: Number of packets dropped on their way to transmission,
+ *   e.g. due to lack of resources.
+ *
+ * @multicast: Multicast packets received.
+ *   For hardware interfaces this statistic is commonly calculated
+ *   at the device level (unlike @rx_packets) and therefore may include
+ *   packets which did not reach the host.
+ *
+ *   For IEEE 802.3 devices this counter may be equivalent to:
+ *
+ *    - 30.3.1.1.21 aMulticastFramesReceivedOK
+ *
+ * @collisions: Number of collisions during packet transmissions.
+ *
+ * @rx_length_errors: Number of packets dropped due to invalid length.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter should be equivalent to a sum
+ *   of the following attributes:
+ *
+ *    - 30.3.1.1.23 aInRangeLengthErrors
+ *    - 30.3.1.1.24 aOutOfRangeLengthField
+ *    - 30.3.1.1.25 aFrameTooLongErrors
+ *
+ * @rx_over_errors: Receiver FIFO overflow event counter.
+ *
+ *   Historically the count of overflow events. Such events may be
+ *   reported in the receive descriptors or via interrupts, and may
+ *   not correspond one-to-one with dropped packets.
+ *
+ *   The recommended interpretation for high speed interfaces is -
+ *   number of packets dropped because they did not fit into buffers
+ *   provided by the host, e.g. packets larger than MTU or next buffer
+ *   in the ring was not available for a scatter transfer.
+ *
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   This statistics was historically used interchangeably with
+ *   @rx_fifo_errors.
+ *
+ *   This statistic corresponds to hardware events and is not commonly used
+ *   on software devices.
+ *
+ * @rx_crc_errors: Number of packets received with a CRC error.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.6 aFrameCheckSequenceErrors
+ *
+ * @rx_frame_errors: Receiver frame alignment errors.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter should be equivalent to:
+ *
+ *    - 30.3.1.1.7 aAlignmentErrors
+ *
+ * @rx_fifo_errors: Receiver FIFO error counter.
+ *
+ *   Historically the count of overflow events. Those events may be
+ *   reported in the receive descriptors or via interrupts, and may
+ *   not correspond one-to-one with dropped packets.
+ *
+ *   This statistics was used interchangeably with @rx_over_errors.
+ *   Not recommended for use in drivers for high speed interfaces.
+ *
+ *   This statistic is used on software devices, e.g. to count software
+ *   packet queue overflow (can) or sequencing errors (GRE).
+ *
+ * @rx_missed_errors: Count of packets missed by the host.
+ *   Folded into the "drop" counter in `/proc/net/dev`.
+ *
+ *   Counts number of packets dropped by the device due to lack
+ *   of buffer space. This usually indicates that the host interface
+ *   is slower than the network interface, or host is not keeping up
+ *   with the receive packet rate.
+ *
+ *   This statistic corresponds to hardware events and is not used
+ *   on software devices.
+ *
+ * @tx_aborted_errors:
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *   For IEEE 802.3 devices capable of half-duplex operation this counter
+ *   must be equivalent to:
+ *
+ *    - 30.3.1.1.11 aFramesAbortedDueToXSColls
+ *
+ *   High speed interfaces may use this counter as a general device
+ *   discard counter.
+ *
+ * @tx_carrier_errors: Number of frame transmission errors due to loss
+ *   of carrier during transmission.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.13 aCarrierSenseErrors
+ *
+ * @tx_fifo_errors: Number of frame transmission errors due to device
+ *   FIFO underrun / underflow. This condition occurs when the device
+ *   begins transmission of a frame but is unable to deliver the
+ *   entire frame to the transmitter in time for transmission.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for
+ *   old half-duplex Ethernet.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices possibly equivalent to:
+ *
+ *    - 30.3.2.1.4 aSQETestErrors
+ *
+ * @tx_window_errors: Number of frame transmission errors due
+ *   to late collisions (for Ethernet - after the first 64B of transmission).
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.10 aLateCollisions
+ *
+ * @rx_compressed: Number of correctly received compressed packets.
+ *   This counters is only meaningful for interfaces which support
+ *   packet compression (e.g. CSLIP, PPP).
+ *
+ * @tx_compressed: Number of transmitted compressed packets.
+ *   This counters is only meaningful for interfaces which support
+ *   packet compression (e.g. CSLIP, PPP).
+ *
+ * @rx_nohandler: Number of packets received on the interface
+ *   but dropped by the networking stack because the device is
+ *   not designated to receive packets (e.g. backup link in a bond).
+ */
 struct rtnl_link_stats64 {
-	__u64	rx_packets;		/* total packets received	*/
-	__u64	tx_packets;		/* total packets transmitted	*/
-	__u64	rx_bytes;		/* total bytes received 	*/
-	__u64	tx_bytes;		/* total bytes transmitted	*/
-	__u64	rx_errors;		/* bad packets received		*/
-	__u64	tx_errors;		/* packet transmit problems	*/
-	__u64	rx_dropped;		/* no space in linux buffers	*/
-	__u64	tx_dropped;		/* no space available in linux	*/
-	__u64	multicast;		/* multicast packets received	*/
+	__u64	rx_packets;
+	__u64	tx_packets;
+	__u64	rx_bytes;
+	__u64	tx_bytes;
+	__u64	rx_errors;
+	__u64	tx_errors;
+	__u64	rx_dropped;
+	__u64	tx_dropped;
+	__u64	multicast;
 	__u64	collisions;
 
 	/* detailed rx_errors: */
 	__u64	rx_length_errors;
-	__u64	rx_over_errors;		/* receiver ring buff overflow	*/
-	__u64	rx_crc_errors;		/* recved pkt with crc error	*/
-	__u64	rx_frame_errors;	/* recv'd frame alignment error */
-	__u64	rx_fifo_errors;		/* recv'r fifo overrun		*/
-	__u64	rx_missed_errors;	/* receiver missed packet	*/
+	__u64	rx_over_errors;
+	__u64	rx_crc_errors;
+	__u64	rx_frame_errors;
+	__u64	rx_fifo_errors;
+	__u64	rx_missed_errors;
 
 	/* detailed tx_errors */
 	__u64	tx_aborted_errors;
@@ -71,8 +242,7 @@ struct rtnl_link_stats64 {
 	/* for cslip etc */
 	__u64	rx_compressed;
 	__u64	tx_compressed;
-
-	__u64	rx_nohandler;		/* dropped, no handler found	*/
+	__u64	rx_nohandler;
 };
 
 /* The struct should be in sync with struct ifmap */
@@ -170,12 +340,30 @@ enum {
 	IFLA_PROP_LIST,
 	IFLA_ALT_IFNAME, /* Alternative ifname */
 	IFLA_PERM_ADDRESS,
+	IFLA_PROTO_DOWN_REASON,
+
+	/* device (sysfs) name as parent, used instead
+	 * of IFLA_LINK where there's no parent netdev
+	 */
+	IFLA_PARENT_DEV_NAME,
+	IFLA_PARENT_DEV_BUS_NAME,
+	IFLA_GRO_MAX_SIZE,
+
 	__IFLA_MAX
 };
 
 
 #define IFLA_MAX (__IFLA_MAX - 1)
 
+enum {
+	IFLA_PROTO_DOWN_REASON_UNSPEC,
+	IFLA_PROTO_DOWN_REASON_MASK,	/* u32, mask for reason bits */
+	IFLA_PROTO_DOWN_REASON_VALUE,   /* u32, reason bit value */
+
+	__IFLA_PROTO_DOWN_REASON_CNT,
+	IFLA_PROTO_DOWN_REASON_MAX = __IFLA_PROTO_DOWN_REASON_CNT - 1
+};
+
 /* backwards compatibility for userspace */
 #ifndef __KERNEL__
 #define IFLA_RTA(r)  ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg))))
@@ -293,6 +481,7 @@ enum {
 	IFLA_BR_MCAST_MLD_VERSION,
 	IFLA_BR_VLAN_STATS_PER_PORT,
 	IFLA_BR_MULTI_BOOLOPT,
+	IFLA_BR_MCAST_QUERIER_STATE,
 	__IFLA_BR_MAX,
 };
 
@@ -346,6 +535,8 @@ enum {
 	IFLA_BRPORT_BACKUP_PORT,
 	IFLA_BRPORT_MRP_RING_OPEN,
 	IFLA_BRPORT_MRP_IN_OPEN,
+	IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT,
+	IFLA_BRPORT_MCAST_EHT_HOSTS_CNT,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -433,6 +624,7 @@ enum macvlan_macaddr_mode {
 };
 
 #define MACVLAN_FLAG_NOPROMISC	1
+#define MACVLAN_FLAG_NODST	2 /* skip dst macvlan if matching src macvlan */
 
 /* VRF section */
 enum {
@@ -597,6 +789,18 @@ enum ifla_geneve_df {
 	GENEVE_DF_MAX = __GENEVE_DF_END - 1,
 };
 
+/* Bareudp section  */
+enum {
+	IFLA_BAREUDP_UNSPEC,
+	IFLA_BAREUDP_PORT,
+	IFLA_BAREUDP_ETHERTYPE,
+	IFLA_BAREUDP_SRCPORT_MIN,
+	IFLA_BAREUDP_MULTIPROTO_MODE,
+	__IFLA_BAREUDP_MAX
+};
+
+#define IFLA_BAREUDP_MAX (__IFLA_BAREUDP_MAX - 1)
+
 /* PPP section */
 enum {
 	IFLA_PPP_UNSPEC,
@@ -655,6 +859,7 @@ enum {
 	IFLA_BOND_TLB_DYNAMIC_LB,
 	IFLA_BOND_PEER_NOTIF_DELAY,
 	IFLA_BOND_AD_LACP_ACTIVE,
+	IFLA_BOND_MISSED_MAX,
 	__IFLA_BOND_MAX,
 };
 
@@ -899,7 +1104,14 @@ enum {
 #define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1)
 
 
-/* HSR section */
+/* HSR/PRP section, both uses same interface */
+
+/* Different redundancy protocols for hsr device */
+enum {
+	HSR_PROTOCOL_HSR,
+	HSR_PROTOCOL_PRP,
+	HSR_PROTOCOL_MAX,
+};
 
 enum {
 	IFLA_HSR_UNSPEC,
@@ -909,6 +1121,9 @@ enum {
 	IFLA_HSR_SUPERVISION_ADDR,	/* Supervision frame multicast addr */
 	IFLA_HSR_SEQ_NR,
 	IFLA_HSR_VERSION,		/* HSR version */
+	IFLA_HSR_PROTOCOL,		/* Indicate different protocol than
+					 * HSR. For example PRP.
+					 */
 	__IFLA_HSR_MAX,
 };
 
@@ -1033,6 +1248,8 @@ enum {
 #define RMNET_FLAGS_INGRESS_MAP_COMMANDS          (1U << 1)
 #define RMNET_FLAGS_INGRESS_MAP_CKSUMV4           (1U << 2)
 #define RMNET_FLAGS_EGRESS_MAP_CKSUMV4            (1U << 3)
+#define RMNET_FLAGS_INGRESS_MAP_CKSUMV5           (1U << 4)
+#define RMNET_FLAGS_EGRESS_MAP_CKSUMV5            (1U << 5)
 
 enum {
 	IFLA_RMNET_UNSPEC,
@@ -1048,4 +1265,14 @@ struct ifla_rmnet_flags {
 	__u32	mask;
 };
 
+/* MCTP section */
+
+enum {
+	IFLA_MCTP_UNSPEC,
+	IFLA_MCTP_NET,
+	__IFLA_MCTP_MAX,
+};
+
+#define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1)
+
 #endif /* _UAPI_LINUX_IF_LINK_H */

scripts/build-fuzzers.sh

@@ -0,0 +1,58 @@
+#!/bin/bash
+set -eux
+
+SANITIZER=${SANITIZER:-address}
+flags="-O1 -fno-omit-frame-pointer -g -DFUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION -fsanitize=$SANITIZER -fsanitize=fuzzer-no-link"
+
+export CC=${CC:-clang}
+export CFLAGS=${CFLAGS:-$flags}
+
+export CXX=${CXX:-clang++}
+export CXXFLAGS=${CXXFLAGS:-$flags}
+
+cd "$(dirname -- "$0")/.."
+
+export OUT=${OUT:-"$(pwd)/out"}
+mkdir -p "$OUT"
+
+export LIB_FUZZING_ENGINE=${LIB_FUZZING_ENGINE:--fsanitize=fuzzer}
+
+# Ideally libbelf should be built using release tarballs available
+# at https://sourceware.org/elfutils/ftp/. Unfortunately sometimes they
+# fail to compile (for example, elfutils-0.185 fails to compile with LDFLAGS enabled
+# due to https://bugs.gentoo.org/794601) so let's just point the script to
+# commits referring to versions of libelf that actually can be built
+rm -rf elfutils
+git clone git://sourceware.org/git/elfutils.git
+(
+cd elfutils
+git checkout 983e86fd89e8bf02f2d27ba5dce5bf078af4ceda
+git log --oneline -1
+
+# ASan isn't compatible with -Wl,--no-undefined: https://github.com/google/sanitizers/issues/380
+find -name Makefile.am | xargs sed -i 's/,--no-undefined//'
+
+# ASan isn't compatible with -Wl,-z,defs either:
+# https://clang.llvm.org/docs/AddressSanitizer.html#usage
+sed -i 's/^\(ZDEFS_LDFLAGS=\).*/\1/' configure.ac
+
+
+autoreconf -i -f
+if ! ./configure --enable-maintainer-mode --disable-debuginfod --disable-libdebuginfod \
+	    CC="$CC" CFLAGS="-Wno-error $CFLAGS" CXX="$CXX" CXXFLAGS="-Wno-error $CXXFLAGS" LDFLAGS="$CFLAGS"; then
+    cat config.log
+    exit 1
+fi
+
+make -C config -j$(nproc) V=1
+make -C lib -j$(nproc) V=1
+make -C libelf -j$(nproc) V=1
+)
+
+make -C src BUILD_STATIC_ONLY=y V=1 clean
+make -C src -j$(nproc) CFLAGS="-I$(pwd)/elfutils/libelf $CFLAGS" BUILD_STATIC_ONLY=y V=1
+
+$CC $CFLAGS -Isrc -Iinclude -Iinclude/uapi -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64  -c fuzz/bpf-object-fuzzer.c -o bpf-object-fuzzer.o
+$CXX $CXXFLAGS $LIB_FUZZING_ENGINE bpf-object-fuzzer.o src/libbpf.a "$(pwd)/elfutils/libelf/libelf.a" -l:libz.a -o "$OUT/bpf-object-fuzzer"
+
+cp fuzz/bpf-object-fuzzer_seed_corpus.zip "$OUT"

scripts/sync-kernel.sh

@@ -47,6 +47,7 @@ PATH_MAP=(									\
 	[tools/include/uapi/linux/netlink.h]=include/uapi/linux/netlink.h	\
 	[tools/include/uapi/linux/pkt_cls.h]=include/uapi/linux/pkt_cls.h	\
 	[tools/include/uapi/linux/pkt_sched.h]=include/uapi/linux/pkt_sched.h	\
+	[include/uapi/linux/perf_event.h]=include/uapi/linux/perf_event.h	\
 	[Documentation/bpf/libbpf]=docs						\
 )
 
@@ -264,7 +265,7 @@ git checkout -b ${LIBBPF_SYNC_TAG}
 
 for patch in $(ls -1 ${TMP_DIR}/patches | tail -n +2); do
 	if ! git am -3 --committer-date-is-author-date "${TMP_DIR}/patches/${patch}"; then
-		if ! git apply -3 "${TMP_DIR}/patches/${patch}"; then
+		if ! patch -p1 --merge < "${TMP_DIR}/patches/${patch}"; then
 			read -p "Applying ${TMP_DIR}/patches/${patch} failed, please resolve manually and press <return> to proceed..."
 		fi
 		git am --continue

src/bpf.c

@@ -28,7 +28,9 @@
 #include <asm/unistd.h>
 #include <errno.h>
 #include <linux/bpf.h>
+#include <linux/filter.h>
 #include <limits.h>
+#include <sys/resource.h>
 #include "bpf.h"
 #include "libbpf.h"
 #include "libbpf_internal.h"
@@ -94,6 +96,77 @@ static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int
 	return fd;
 }
 
+/* Probe whether kernel switched from memlock-based (RLIMIT_MEMLOCK) to
+ * memcg-based memory accounting for BPF maps and progs. This was done in [0].
+ * We use the support for bpf_ktime_get_coarse_ns() helper, which was added in
+ * the same 5.11 Linux release ([1]), to detect memcg-based accounting for BPF.
+ *
+ *   [0] https://lore.kernel.org/bpf/20201201215900.3569844-1-guro@fb.com/
+ *   [1] d05512618056 ("bpf: Add bpf_ktime_get_coarse_ns helper")
+ */
+int probe_memcg_account(void)
+{
+	const size_t prog_load_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(),
+	};
+	size_t insn_cnt = sizeof(insns) / sizeof(insns[0]);
+	union bpf_attr attr;
+	int prog_fd;
+
+	/* attempt loading freplace trying to use custom BTF */
+	memset(&attr, 0, prog_load_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);
+	if (prog_fd >= 0) {
+		close(prog_fd);
+		return 1;
+	}
+	return 0;
+}
+
+static bool memlock_bumped;
+static rlim_t memlock_rlim = RLIM_INFINITY;
+
+int libbpf_set_memlock_rlim(size_t memlock_bytes)
+{
+	if (memlock_bumped)
+		return libbpf_err(-EBUSY);
+
+	memlock_rlim = memlock_bytes;
+	return 0;
+}
+
+int bump_rlimit_memlock(void)
+{
+	struct rlimit rlim;
+
+	/* this the default in libbpf 1.0, but for now user has to opt-in explicitly */
+	if (!(libbpf_mode & LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK))
+		return 0;
+
+	/* if kernel supports memcg-based accounting, skip bumping RLIMIT_MEMLOCK */
+	if (memlock_bumped || kernel_supports(NULL, FEAT_MEMCG_ACCOUNT))
+		return 0;
+
+	memlock_bumped = true;
+
+	/* zero memlock_rlim_max disables auto-bumping RLIMIT_MEMLOCK */
+	if (memlock_rlim == 0)
+		return 0;
+
+	rlim.rlim_cur = rlim.rlim_max = memlock_rlim;
+	if (setrlimit(RLIMIT_MEMLOCK, &rlim))
+		return -errno;
+
+	return 0;
+}
+
 int bpf_map_create(enum bpf_map_type map_type,
 		   const char *map_name,
 		   __u32 key_size,
@@ -105,6 +178,8 @@ int bpf_map_create(enum bpf_map_type map_type,
 	union bpf_attr attr;
 	int fd;
 
+	bump_rlimit_memlock();
+
 	memset(&attr, 0, attr_sz);
 
 	if (!OPTS_VALID(opts, bpf_map_create_opts))
@@ -112,7 +187,7 @@ int bpf_map_create(enum bpf_map_type map_type,
 
 	attr.map_type = map_type;
 	if (map_name)
-		strncat(attr.map_name, map_name, sizeof(attr.map_name) - 1);
+		libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name));
 	attr.key_size = key_size;
 	attr.value_size = value_size;
 	attr.max_entries = max_entries;
@@ -251,6 +326,8 @@ int bpf_prog_load_v0_6_0(enum bpf_prog_type prog_type,
 	union bpf_attr attr;
 	char *log_buf;
 
+	bump_rlimit_memlock();
+
 	if (!OPTS_VALID(opts, bpf_prog_load_opts))
 		return libbpf_err(-EINVAL);
 
@@ -271,7 +348,7 @@ int bpf_prog_load_v0_6_0(enum bpf_prog_type prog_type,
 	attr.kern_version = OPTS_GET(opts, kern_version, 0);
 
 	if (prog_name)
-		strncat(attr.prog_name, prog_name, sizeof(attr.prog_name) - 1);
+		libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
 	attr.license = ptr_to_u64(license);
 
 	if (insn_cnt > UINT_MAX)
@@ -303,10 +380,6 @@ int bpf_prog_load_v0_6_0(enum bpf_prog_type prog_type,
 	if (log_level && !log_buf)
 		return libbpf_err(-EINVAL);
 
-	attr.log_level = log_level;
-	attr.log_buf = ptr_to_u64(log_buf);
-	attr.log_size = log_size;
-
 	func_info_rec_size = OPTS_GET(opts, func_info_rec_size, 0);
 	func_info = OPTS_GET(opts, func_info, NULL);
 	attr.func_info_rec_size = func_info_rec_size;
@@ -321,6 +394,12 @@ int bpf_prog_load_v0_6_0(enum bpf_prog_type prog_type,
 
 	attr.fd_array = ptr_to_u64(OPTS_GET(opts, fd_array, NULL));
 
+	if (log_level) {
+		attr.log_buf = ptr_to_u64(log_buf);
+		attr.log_size = log_size;
+		attr.log_level = log_level;
+	}
+
 	fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts);
 	if (fd >= 0)
 		return fd;
@@ -366,16 +445,17 @@ int bpf_prog_load_v0_6_0(enum bpf_prog_type prog_type,
 			goto done;
 	}
 
-	if (log_level || !log_buf)
-		goto done;
+	if (log_level == 0 && log_buf) {
+		/* log_level == 0 with non-NULL log_buf requires retrying on error
+		 * with log_level == 1 and log_buf/log_buf_size set, to get details of
+		 * failure
+		 */
+		attr.log_buf = ptr_to_u64(log_buf);
+		attr.log_size = log_size;
+		attr.log_level = 1;
 
-	/* Try again with log */
-	log_buf[0] = 0;
-	attr.log_buf = ptr_to_u64(log_buf);
-	attr.log_size = log_size;
-	attr.log_level = 1;
-
-	fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts);
+		fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts);
+	}
 done:
 	/* free() doesn't affect errno, so we don't need to restore it */
 	free(finfo);
@@ -453,6 +533,8 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 	union bpf_attr attr;
 	int fd;
 
+	bump_rlimit_memlock();
+
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = type;
 	attr.insn_cnt = (__u32)insns_cnt;
@@ -609,11 +691,11 @@ static int bpf_map_batch_common(int cmd, int fd, void  *in_batch,
 	return libbpf_err_errno(ret);
 }
 
-int bpf_map_delete_batch(int fd, void *keys, __u32 *count,
+int bpf_map_delete_batch(int fd, const void *keys, __u32 *count,
 			 const struct bpf_map_batch_opts *opts)
 {
 	return bpf_map_batch_common(BPF_MAP_DELETE_BATCH, fd, NULL,
-				    NULL, keys, NULL, count, opts);
+				    NULL, (void *)keys, NULL, count, opts);
 }
 
 int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, void *keys,
@@ -633,11 +715,11 @@ int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, void *out_batch,
 				    count, opts);
 }
 
-int bpf_map_update_batch(int fd, void *keys, void *values, __u32 *count,
+int bpf_map_update_batch(int fd, const void *keys, const void *values, __u32 *count,
 			 const struct bpf_map_batch_opts *opts)
 {
 	return bpf_map_batch_common(BPF_MAP_UPDATE_BATCH, fd, NULL, NULL,
-				    keys, values, count, opts);
+				    (void *)keys, (void *)values, count, opts);
 }
 
 int bpf_obj_pin(int fd, const char *pathname)
@@ -672,10 +754,10 @@ int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
 		.flags = flags,
 	);
 
-	return bpf_prog_attach_xattr(prog_fd, target_fd, type, &opts);
+	return bpf_prog_attach_opts(prog_fd, target_fd, type, &opts);
 }
 
-int bpf_prog_attach_xattr(int prog_fd, int target_fd,
+int bpf_prog_attach_opts(int prog_fd, int target_fd,
 			  enum bpf_attach_type type,
 			  const struct bpf_prog_attach_opts *opts)
 {
@@ -696,6 +778,11 @@ int bpf_prog_attach_xattr(int prog_fd, int target_fd,
 	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)
 {
 	union bpf_attr attr;
@@ -1044,24 +1131,67 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd)
 	return libbpf_err_errno(fd);
 }
 
-int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
-		 bool do_log)
+int bpf_btf_load(const void *btf_data, size_t btf_size, const struct bpf_btf_load_opts *opts)
 {
-	union bpf_attr attr = {};
+	const size_t attr_sz = offsetofend(union bpf_attr, btf_log_level);
+	union bpf_attr attr;
+	char *log_buf;
+	size_t log_size;
+	__u32 log_level;
 	int fd;
 
-	attr.btf = ptr_to_u64(btf);
+	bump_rlimit_memlock();
+
+	memset(&attr, 0, attr_sz);
+
+	if (!OPTS_VALID(opts, bpf_btf_load_opts))
+		return libbpf_err(-EINVAL);
+
+	log_buf = OPTS_GET(opts, log_buf, NULL);
+	log_size = OPTS_GET(opts, log_size, 0);
+	log_level = OPTS_GET(opts, log_level, 0);
+
+	if (log_size > UINT_MAX)
+		return libbpf_err(-EINVAL);
+	if (log_size && !log_buf)
+		return libbpf_err(-EINVAL);
+
+	attr.btf = ptr_to_u64(btf_data);
 	attr.btf_size = btf_size;
+	/* log_level == 0 and log_buf != NULL means "try loading without
+	 * log_buf, but retry with log_buf and log_level=1 on error", which is
+	 * consistent across low-level and high-level BTF and program loading
+	 * APIs within libbpf and provides a sensible behavior in practice
+	 */
+	if (log_level) {
+		attr.btf_log_buf = ptr_to_u64(log_buf);
+		attr.btf_log_size = (__u32)log_size;
+		attr.btf_log_level = log_level;
+	}
+
+	fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, attr_sz);
+	if (fd < 0 && log_buf && log_level == 0) {
+		attr.btf_log_buf = ptr_to_u64(log_buf);
+		attr.btf_log_size = (__u32)log_size;
+		attr.btf_log_level = 1;
+		fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, attr_sz);
+	}
+	return libbpf_err_errno(fd);
+}
+
+int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size, bool do_log)
+{
+	LIBBPF_OPTS(bpf_btf_load_opts, opts);
+	int fd;
 
 retry:
 	if (do_log && log_buf && log_buf_size) {
-		attr.btf_log_level = 1;
-		attr.btf_log_size = log_buf_size;
-		attr.btf_log_buf = ptr_to_u64(log_buf);
+		opts.log_buf = log_buf;
+		opts.log_size = log_buf_size;
+		opts.log_level = 1;
 	}
 
-	fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, sizeof(attr));
-
+	fd = bpf_btf_load(btf, btf_size, &opts);
 	if (fd < 0 && !do_log && log_buf && log_buf_size) {
 		do_log = true;
 		goto retry;

src/bpf.h

@@ -35,6 +35,8 @@
 extern "C" {
 #endif
 
+int libbpf_set_memlock_rlim(size_t memlock_bytes);
+
 struct bpf_map_create_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */
 
@@ -43,12 +45,12 @@ struct bpf_map_create_opts {
 	__u32 btf_value_type_id;
 	__u32 btf_vmlinux_value_type_id;
 
-	int inner_map_fd;
-	int map_flags;
+	__u32 inner_map_fd;
+	__u32 map_flags;
 	__u64 map_extra;
 
-	int numa_node;
-	int map_ifindex;
+	__u32 numa_node;
+	__u32 map_ifindex;
 };
 #define bpf_map_create_opts__last_field map_ifindex
 
@@ -195,8 +197,9 @@ struct bpf_load_program_attr {
 /* Flags to direct loading requirements */
 #define MAPS_RELAX_COMPAT	0x01
 
-/* Recommend log buffer size */
+/* Recommended log buffer size */
 #define BPF_LOG_BUF_SIZE (UINT32_MAX >> 8) /* verifier maximum in kernels <= 5.1 */
+
 LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_load() instead")
 LIBBPF_API int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 				      char *log_buf, size_t log_buf_sz);
@@ -213,6 +216,23 @@ LIBBPF_API int bpf_verify_program(enum bpf_prog_type type,
 				  char *log_buf, size_t log_buf_sz,
 				  int log_level);
 
+struct bpf_btf_load_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+
+	/* kernel log options */
+	char *log_buf;
+	__u32 log_level;
+	__u32 log_size;
+};
+#define bpf_btf_load_opts__last_field log_size
+
+LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size,
+			    const struct bpf_btf_load_opts *opts);
+
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_btf_load() instead")
+LIBBPF_API int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf,
+			    __u32 log_buf_size, bool do_log);
+
 LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value,
 				   __u64 flags);
 
@@ -234,17 +254,128 @@ struct bpf_map_batch_opts {
 };
 #define bpf_map_batch_opts__last_field flags
 
-LIBBPF_API int bpf_map_delete_batch(int fd, void *keys,
+
+/**
+ * @brief **bpf_map_delete_batch()** allows for batch deletion of multiple
+ * elements in a BPF map.
+ *
+ * @param fd BPF map file descriptor
+ * @param keys pointer to an array of *count* keys
+ * @param count input and output parameter; on input **count** represents the
+ * number of  elements in the map to delete in batch;
+ * on output if a non-EFAULT error is returned, **count** represents the number of deleted
+ * elements if the output **count** value is not equal to the input **count** value
+ * If EFAULT is returned, **count** should not be trusted to be correct.
+ * @param opts options for configuring the way the batch deletion works
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
+LIBBPF_API int bpf_map_delete_batch(int fd, const void *keys,
 				    __u32 *count,
 				    const struct bpf_map_batch_opts *opts);
+
+/**
+ * @brief **bpf_map_lookup_batch()** allows for batch lookup of BPF map elements.
+ *
+ * The parameter *in_batch* is the address of the first element in the batch to read.
+ * *out_batch* is an output parameter that should be passed as *in_batch* to subsequent
+ * calls to **bpf_map_lookup_batch()**. NULL can be passed for *in_batch* to indicate
+ * that the batched lookup starts from the beginning of the map.
+ *
+ * The *keys* and *values* are output parameters which must point to memory large enough to
+ * hold *count* items based on the key and value size of the map *map_fd*. The *keys*
+ * buffer must be of *key_size* * *count*. The *values* buffer must be of
+ * *value_size* * *count*.
+ *
+ * @param fd BPF map file descriptor
+ * @param in_batch address of the first element in batch to read, can pass NULL to
+ * indicate that the batched lookup starts from the beginning of the map.
+ * @param out_batch output parameter that should be passed to next call as *in_batch*
+ * @param keys pointer to an array large enough for *count* keys
+ * @param values pointer to an array large enough for *count* values
+ * @param count input and output parameter; on input it's the number of elements
+ * in the map to read in batch; on output it's the number of elements that were
+ * successfully read.
+ * If a non-EFAULT error is returned, count will be set as the number of elements
+ * that were read before the error occurred.
+ * If EFAULT is returned, **count** should not be trusted to be correct.
+ * @param opts options for configuring the way the batch lookup works
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
 LIBBPF_API int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch,
 				    void *keys, void *values, __u32 *count,
 				    const struct bpf_map_batch_opts *opts);
+
+/**
+ * @brief **bpf_map_lookup_and_delete_batch()** allows for batch lookup and deletion
+ * of BPF map elements where each element is deleted after being retrieved.
+ *
+ * @param fd BPF map file descriptor
+ * @param in_batch address of the first element in batch to read, can pass NULL to
+ * get address of the first element in *out_batch*
+ * @param out_batch output parameter that should be passed to next call as *in_batch*
+ * @param keys pointer to an array of *count* keys
+ * @param values pointer to an array large enough for *count* values
+ * @param count input and output parameter; on input it's the number of elements
+ * in the map to read and delete in batch; on output it represents the number of
+ * elements that were successfully read and deleted
+ * If a non-**EFAULT** error code is returned and if the output **count** value
+ * is not equal to the input **count** value, up to **count** elements may
+ * have been deleted.
+ * if **EFAULT** is returned up to *count* elements may have been deleted without
+ * being returned via the *keys* and *values* output parameters.
+ * @param opts options for configuring the way the batch lookup and delete works
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
 LIBBPF_API int bpf_map_lookup_and_delete_batch(int fd, void *in_batch,
 					void *out_batch, void *keys,
 					void *values, __u32 *count,
 					const struct bpf_map_batch_opts *opts);
-LIBBPF_API int bpf_map_update_batch(int fd, void *keys, void *values,
+
+/**
+ * @brief **bpf_map_update_batch()** updates multiple elements in a map
+ * by specifying keys and their corresponding values.
+ *
+ * The *keys* and *values* parameters must point to memory large enough
+ * to hold *count* items based on the key and value size of the map.
+ *
+ * The *opts* parameter can be used to control how *bpf_map_update_batch()*
+ * should handle keys that either do or do not already exist in the map.
+ * In particular the *flags* parameter of *bpf_map_batch_opts* can be
+ * one of the following:
+ *
+ * Note that *count* is an input and output parameter, where on output it
+ * represents how many elements were successfully updated. Also note that if
+ * **EFAULT** then *count* should not be trusted to be correct.
+ *
+ * **BPF_ANY**
+ *    Create new elements or update existing.
+ *
+ * **BPF_NOEXIST**
+ *    Create new elements only if they do not exist.
+ *
+ * **BPF_EXIST**
+ *    Update existing elements.
+ *
+ * **BPF_F_LOCK**
+ *    Update spin_lock-ed map elements. This must be
+ *    specified if the map value contains a spinlock.
+ *
+ * @param fd BPF map file descriptor
+ * @param keys pointer to an array of *count* keys
+ * @param values pointer to an array of *count* values
+ * @param count input and output parameter; on input it's the number of elements
+ * in the map to update in batch; on output if a non-EFAULT error is returned,
+ * **count** represents the number of updated elements if the output **count**
+ * value is not equal to the input **count** value.
+ * If EFAULT is returned, **count** should not be trusted to be correct.
+ * @param opts options for configuring the way the batch update works
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
+LIBBPF_API int bpf_map_update_batch(int fd, const void *keys, const void *values,
 				    __u32 *count,
 				    const struct bpf_map_batch_opts *opts);
 
@@ -260,6 +391,10 @@ struct bpf_prog_attach_opts {
 
 LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd,
 			       enum bpf_attach_type type, unsigned int flags);
+LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int attachable_fd,
+				     enum bpf_attach_type type,
+				     const struct bpf_prog_attach_opts *opts);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_prog_attach_opts() instead")
 LIBBPF_API int bpf_prog_attach_xattr(int prog_fd, int attachable_fd,
 				     enum bpf_attach_type type,
 				     const struct bpf_prog_attach_opts *opts);
@@ -318,12 +453,14 @@ struct bpf_prog_test_run_attr {
 			     * out: length of cxt_out */
 };
 
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_test_run_opts() instead")
 LIBBPF_API int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr);
 
 /*
  * bpf_prog_test_run does not check that data_out is large enough. Consider
- * using bpf_prog_test_run_xattr instead.
+ * using bpf_prog_test_run_opts instead.
  */
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_test_run_opts() instead")
 LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data,
 				 __u32 size, void *data_out, __u32 *size_out,
 				 __u32 *retval, __u32 *duration);
@@ -340,8 +477,6 @@ LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type,
 			      __u32 query_flags, __u32 *attach_flags,
 			      __u32 *prog_ids, __u32 *prog_cnt);
 LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd);
-LIBBPF_API int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf,
-			    __u32 log_buf_size, bool do_log);
 LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf,
 				 __u32 *buf_len, __u32 *prog_id, __u32 *fd_type,
 				 __u64 *probe_offset, __u64 *probe_addr);

src/bpf_gen_internal.h

@@ -39,6 +39,8 @@ struct bpf_gen {
 	int error;
 	struct ksym_relo_desc *relos;
 	int relo_cnt;
+	struct bpf_core_relo *core_relos;
+	int core_relo_cnt;
 	char attach_target[128];
 	int attach_kind;
 	struct ksym_desc *ksyms;
@@ -64,5 +66,7 @@ void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx);
 void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *name, enum bpf_attach_type type);
 void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak,
 			    bool is_typeless, int kind, int insn_idx);
+void bpf_gen__record_relo_core(struct bpf_gen *gen, const struct bpf_core_relo *core_relo);
+void bpf_gen__populate_outer_map(struct bpf_gen *gen, int outer_map_idx, int key, int inner_map_idx);
 
 #endif

src/bpf_helper_defs.h

@@ -352,6 +352,7 @@ static long (*bpf_clone_redirect)(struct __sk_buff *skb, __u32 ifindex, __u64 fl
 /*
  * bpf_get_current_pid_tgid
  *
+ * 	Get the current pid and tgid.
  *
  * Returns
  * 	A 64-bit integer containing the current tgid and pid, and
@@ -364,6 +365,7 @@ static __u64 (*bpf_get_current_pid_tgid)(void) = (void *) 14;
 /*
  * bpf_get_current_uid_gid
  *
+ * 	Get the current uid and gid.
  *
  * Returns
  * 	A 64-bit integer containing the current GID and UID, and
@@ -919,6 +921,7 @@ static __u32 (*bpf_get_hash_recalc)(struct __sk_buff *skb) = (void *) 34;
 /*
  * bpf_get_current_task
  *
+ * 	Get the current task.
  *
  * Returns
  * 	A pointer to the current task struct.
@@ -1057,6 +1060,8 @@ static __s64 (*bpf_csum_update)(struct __sk_buff *skb, __wsum csum) = (void *) 4
  * 	recalculation the next time the kernel tries to access this
  * 	hash or when the **bpf_get_hash_recalc**\ () helper is called.
  *
+ * Returns
+ * 	void.
  */
 static void (*bpf_set_hash_invalid)(struct __sk_buff *skb) = (void *) 41;
 
@@ -1156,6 +1161,7 @@ static __u64 (*bpf_get_socket_cookie)(void *ctx) = (void *) 46;
 /*
  * bpf_get_socket_uid
  *
+ * 	Get the owner UID of the socked associated to *skb*.
  *
  * Returns
  * 	The owner UID of the socket associated to *skb*. If the socket
@@ -2063,6 +2069,8 @@ static __u64 (*bpf_skb_cgroup_id)(struct __sk_buff *skb) = (void *) 79;
 /*
  * bpf_get_current_cgroup_id
  *
+ * 	Get the current cgroup id based on the cgroup within which
+ * 	the current task is running.
  *
  * Returns
  * 	A 64-bit integer containing the current cgroup id based
@@ -4136,4 +4144,155 @@ static long (*bpf_kallsyms_lookup_name)(const char *name, int name_sz, int flags
  */
 static long (*bpf_find_vma)(struct task_struct *task, __u64 addr, void *callback_fn, void *callback_ctx, __u64 flags) = (void *) 180;
 
+/*
+ * bpf_loop
+ *
+ * 	For **nr_loops**, call **callback_fn** function
+ * 	with **callback_ctx** as the context parameter.
+ * 	The **callback_fn** should be a static function and
+ * 	the **callback_ctx** should be a pointer to the stack.
+ * 	The **flags** is used to control certain aspects of the helper.
+ * 	Currently, the **flags** must be 0. Currently, nr_loops is
+ * 	limited to 1 << 23 (~8 million) loops.
+ *
+ * 	long (\*callback_fn)(u32 index, void \*ctx);
+ *
+ * 	where **index** is the current index in the loop. The index
+ * 	is zero-indexed.
+ *
+ * 	If **callback_fn** returns 0, the helper will continue to the next
+ * 	loop. If return value is 1, the helper will skip the rest of
+ * 	the loops and return. Other return values are not used now,
+ * 	and will be rejected by the verifier.
+ *
+ *
+ * Returns
+ * 	The number of loops performed, **-EINVAL** for invalid **flags**,
+ * 	**-E2BIG** if **nr_loops** exceeds the maximum number of loops.
+ */
+static long (*bpf_loop)(__u32 nr_loops, void *callback_fn, void *callback_ctx, __u64 flags) = (void *) 181;
+
+/*
+ * bpf_strncmp
+ *
+ * 	Do strncmp() between **s1** and **s2**. **s1** doesn't need
+ * 	to be null-terminated and **s1_sz** is the maximum storage
+ * 	size of **s1**. **s2** must be a read-only string.
+ *
+ * Returns
+ * 	An integer less than, equal to, or greater than zero
+ * 	if the first **s1_sz** bytes of **s1** is found to be
+ * 	less than, to match, or be greater than **s2**.
+ */
+static long (*bpf_strncmp)(const char *s1, __u32 s1_sz, const char *s2) = (void *) 182;
+
+/*
+ * bpf_get_func_arg
+ *
+ * 	Get **n**-th argument (zero based) of the traced function (for tracing programs)
+ * 	returned in **value**.
+ *
+ *
+ * Returns
+ * 	0 on success.
+ * 	**-EINVAL** if n >= arguments count of traced function.
+ */
+static long (*bpf_get_func_arg)(void *ctx, __u32 n, __u64 *value) = (void *) 183;
+
+/*
+ * bpf_get_func_ret
+ *
+ * 	Get return value of the traced function (for tracing programs)
+ * 	in **value**.
+ *
+ *
+ * Returns
+ * 	0 on success.
+ * 	**-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN.
+ */
+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).
+ *
+ *
+ * Returns
+ * 	The number of arguments 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.
+ *
+ * 	This helper is currently supported by cgroup programs only.
+ *
+ * Returns
+ * 	The syscall'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.
+ *
+ * 	This helper is currently supported by cgroup programs only.
+ *
+ * Returns
+ * 	0 on success, or a negative error in case of failure.
+ */
+static int (*bpf_set_retval)(int retval) = (void *) 187;
+
+/*
+ * bpf_xdp_get_buff_len
+ *
+ * 	Get the total size of a given xdp buff (linear and paged area)
+ *
+ * Returns
+ * 	The total size of a given xdp buffer.
+ */
+static __u64 (*bpf_xdp_get_buff_len)(struct xdp_md *xdp_md) = (void *) 188;
+
+/*
+ * bpf_xdp_load_bytes
+ *
+ * 	This helper is provided as an easy way to load data from a
+ * 	xdp buffer. It can be used to load *len* bytes from *offset* from
+ * 	the frame associated to *xdp_md*, into the buffer pointed by
+ * 	*buf*.
+ *
+ * Returns
+ * 	0 on success, or a negative error in case of failure.
+ */
+static long (*bpf_xdp_load_bytes)(struct xdp_md *xdp_md, __u32 offset, void *buf, __u32 len) = (void *) 189;
+
+/*
+ * bpf_xdp_store_bytes
+ *
+ * 	Store *len* bytes from buffer *buf* into the frame
+ * 	associated to *xdp_md*, at *offset*.
+ *
+ * Returns
+ * 	0 on success, or a negative error in case of failure.
+ */
+static long (*bpf_xdp_store_bytes)(struct xdp_md *xdp_md, __u32 offset, void *buf, __u32 len) = (void *) 190;
+
+/*
+ * bpf_copy_from_user_task
+ *
+ * 	Read *size* bytes from user space address *user_ptr* in *tsk*'s
+ * 	address space, and stores the data in *dst*. *flags* is not
+ * 	used yet and is provided for future extensibility. This helper
+ * 	can only be used by sleepable programs.
+ *
+ * Returns
+ * 	0 on success, or a negative error in case of failure. On error
+ * 	*dst* buffer is zeroed out.
+ */
+static long (*bpf_copy_from_user_task)(void *dst, __u32 size, const void *user_ptr, struct task_struct *tsk, __u64 flags) = (void *) 191;
+
 

src/bpf_helpers.h

@@ -133,7 +133,7 @@ struct bpf_map_def {
 	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,

src/bpf_tracing.h

@@ -66,277 +66,246 @@
 
 #if defined(__KERNEL__) || defined(__VMLINUX_H__)
 
-#define PT_REGS_PARM1(x) ((x)->di)
-#define PT_REGS_PARM2(x) ((x)->si)
-#define PT_REGS_PARM3(x) ((x)->dx)
-#define PT_REGS_PARM4(x) ((x)->cx)
-#define PT_REGS_PARM5(x) ((x)->r8)
-#define PT_REGS_RET(x) ((x)->sp)
-#define PT_REGS_FP(x) ((x)->bp)
-#define PT_REGS_RC(x) ((x)->ax)
-#define PT_REGS_SP(x) ((x)->sp)
-#define PT_REGS_IP(x) ((x)->ip)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), di)
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), si)
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), dx)
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), cx)
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8)
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), sp)
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), bp)
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), ax)
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), ip)
+#define __PT_PARM1_REG di
+#define __PT_PARM2_REG si
+#define __PT_PARM3_REG dx
+#define __PT_PARM4_REG cx
+#define __PT_PARM5_REG r8
+#define __PT_RET_REG sp
+#define __PT_FP_REG bp
+#define __PT_RC_REG ax
+#define __PT_SP_REG sp
+#define __PT_IP_REG ip
+/* syscall uses r10 for PARM4 */
+#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10)
+#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10)
 
 #else
 
 #ifdef __i386__
+
+#define __PT_PARM1_REG eax
+#define __PT_PARM2_REG edx
+#define __PT_PARM3_REG ecx
 /* i386 kernel is built with -mregparm=3 */
-#define PT_REGS_PARM1(x) ((x)->eax)
-#define PT_REGS_PARM2(x) ((x)->edx)
-#define PT_REGS_PARM3(x) ((x)->ecx)
-#define PT_REGS_PARM4(x) 0
-#define PT_REGS_PARM5(x) 0
-#define PT_REGS_RET(x) ((x)->esp)
-#define PT_REGS_FP(x) ((x)->ebp)
-#define PT_REGS_RC(x) ((x)->eax)
-#define PT_REGS_SP(x) ((x)->esp)
-#define PT_REGS_IP(x) ((x)->eip)
+#define __PT_PARM4_REG __unsupported__
+#define __PT_PARM5_REG __unsupported__
+#define __PT_RET_REG esp
+#define __PT_FP_REG ebp
+#define __PT_RC_REG eax
+#define __PT_SP_REG esp
+#define __PT_IP_REG eip
 
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), eax)
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), edx)
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), ecx)
-#define PT_REGS_PARM4_CORE(x) 0
-#define PT_REGS_PARM5_CORE(x) 0
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), esp)
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), ebp)
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), eax)
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), esp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), eip)
+#else /* __i386__ */
 
-#else
+#define __PT_PARM1_REG rdi
+#define __PT_PARM2_REG rsi
+#define __PT_PARM3_REG rdx
+#define __PT_PARM4_REG rcx
+#define __PT_PARM5_REG r8
+#define __PT_RET_REG rsp
+#define __PT_FP_REG rbp
+#define __PT_RC_REG rax
+#define __PT_SP_REG rsp
+#define __PT_IP_REG rip
+/* syscall uses r10 for PARM4 */
+#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10)
+#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10)
 
-#define PT_REGS_PARM1(x) ((x)->rdi)
-#define PT_REGS_PARM2(x) ((x)->rsi)
-#define PT_REGS_PARM3(x) ((x)->rdx)
-#define PT_REGS_PARM4(x) ((x)->rcx)
-#define PT_REGS_PARM5(x) ((x)->r8)
-#define PT_REGS_RET(x) ((x)->rsp)
-#define PT_REGS_FP(x) ((x)->rbp)
-#define PT_REGS_RC(x) ((x)->rax)
-#define PT_REGS_SP(x) ((x)->rsp)
-#define PT_REGS_IP(x) ((x)->rip)
+#endif /* __i386__ */
 
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), rdi)
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), rsi)
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), rdx)
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), rcx)
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8)
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), rsp)
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), rbp)
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), rax)
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), rsp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), rip)
-
-#endif
-#endif
+#endif /* __KERNEL__ || __VMLINUX_H__ */
 
 #elif defined(bpf_target_s390)
 
-/* s390 provides user_pt_regs instead of struct pt_regs to userspace */
-struct pt_regs;
-#define PT_REGS_S390 const volatile user_pt_regs
-#define PT_REGS_PARM1(x) (((PT_REGS_S390 *)(x))->gprs[2])
-#define PT_REGS_PARM2(x) (((PT_REGS_S390 *)(x))->gprs[3])
-#define PT_REGS_PARM3(x) (((PT_REGS_S390 *)(x))->gprs[4])
-#define PT_REGS_PARM4(x) (((PT_REGS_S390 *)(x))->gprs[5])
-#define PT_REGS_PARM5(x) (((PT_REGS_S390 *)(x))->gprs[6])
-#define PT_REGS_RET(x) (((PT_REGS_S390 *)(x))->gprs[14])
-/* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_FP(x) (((PT_REGS_S390 *)(x))->gprs[11])
-#define PT_REGS_RC(x) (((PT_REGS_S390 *)(x))->gprs[2])
-#define PT_REGS_SP(x) (((PT_REGS_S390 *)(x))->gprs[15])
-#define PT_REGS_IP(x) (((PT_REGS_S390 *)(x))->psw.addr)
+struct pt_regs___s390 {
+	unsigned long orig_gpr2;
+};
 
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[3])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[4])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[5])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[6])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[14])
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[11])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[15])
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), psw.addr)
+/* s390 provides user_pt_regs instead of struct pt_regs to userspace */
+#define __PT_REGS_CAST(x) ((const user_pt_regs *)(x))
+#define __PT_PARM1_REG gprs[2]
+#define __PT_PARM2_REG gprs[3]
+#define __PT_PARM3_REG gprs[4]
+#define __PT_PARM4_REG gprs[5]
+#define __PT_PARM5_REG gprs[6]
+#define __PT_RET_REG grps[14]
+#define __PT_FP_REG gprs[11]	/* Works only with CONFIG_FRAME_POINTER */
+#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_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___s390 *)(x), orig_gpr2)
 
 #elif defined(bpf_target_arm)
 
-#define PT_REGS_PARM1(x) ((x)->uregs[0])
-#define PT_REGS_PARM2(x) ((x)->uregs[1])
-#define PT_REGS_PARM3(x) ((x)->uregs[2])
-#define PT_REGS_PARM4(x) ((x)->uregs[3])
-#define PT_REGS_PARM5(x) ((x)->uregs[4])
-#define PT_REGS_RET(x) ((x)->uregs[14])
-#define PT_REGS_FP(x) ((x)->uregs[11]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->uregs[0])
-#define PT_REGS_SP(x) ((x)->uregs[13])
-#define PT_REGS_IP(x) ((x)->uregs[12])
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), uregs[0])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), uregs[1])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), uregs[2])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), uregs[3])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), uregs[4])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), uregs[14])
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), uregs[11])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), uregs[0])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), uregs[13])
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), uregs[12])
+#define __PT_PARM1_REG uregs[0]
+#define __PT_PARM2_REG uregs[1]
+#define __PT_PARM3_REG uregs[2]
+#define __PT_PARM4_REG uregs[3]
+#define __PT_PARM5_REG uregs[4]
+#define __PT_RET_REG uregs[14]
+#define __PT_FP_REG uregs[11]	/* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG uregs[0]
+#define __PT_SP_REG uregs[13]
+#define __PT_IP_REG uregs[12]
 
 #elif defined(bpf_target_arm64)
 
-/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
-struct pt_regs;
-#define PT_REGS_ARM64 const volatile struct user_pt_regs
-#define PT_REGS_PARM1(x) (((PT_REGS_ARM64 *)(x))->regs[0])
-#define PT_REGS_PARM2(x) (((PT_REGS_ARM64 *)(x))->regs[1])
-#define PT_REGS_PARM3(x) (((PT_REGS_ARM64 *)(x))->regs[2])
-#define PT_REGS_PARM4(x) (((PT_REGS_ARM64 *)(x))->regs[3])
-#define PT_REGS_PARM5(x) (((PT_REGS_ARM64 *)(x))->regs[4])
-#define PT_REGS_RET(x) (((PT_REGS_ARM64 *)(x))->regs[30])
-/* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_FP(x) (((PT_REGS_ARM64 *)(x))->regs[29])
-#define PT_REGS_RC(x) (((PT_REGS_ARM64 *)(x))->regs[0])
-#define PT_REGS_SP(x) (((PT_REGS_ARM64 *)(x))->sp)
-#define PT_REGS_IP(x) (((PT_REGS_ARM64 *)(x))->pc)
+struct pt_regs___arm64 {
+	unsigned long orig_x0;
+};
 
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[1])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[2])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[3])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[4])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[30])
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[29])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), sp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), pc)
+/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
+#define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x))
+#define __PT_PARM1_REG regs[0]
+#define __PT_PARM2_REG regs[1]
+#define __PT_PARM3_REG regs[2]
+#define __PT_PARM4_REG regs[3]
+#define __PT_PARM5_REG regs[4]
+#define __PT_RET_REG regs[30]
+#define __PT_FP_REG regs[29]	/* Works only with CONFIG_FRAME_POINTER */
+#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_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___arm64 *)(x), orig_x0)
 
 #elif defined(bpf_target_mips)
 
-#define PT_REGS_PARM1(x) ((x)->regs[4])
-#define PT_REGS_PARM2(x) ((x)->regs[5])
-#define PT_REGS_PARM3(x) ((x)->regs[6])
-#define PT_REGS_PARM4(x) ((x)->regs[7])
-#define PT_REGS_PARM5(x) ((x)->regs[8])
-#define PT_REGS_RET(x) ((x)->regs[31])
-#define PT_REGS_FP(x) ((x)->regs[30]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->regs[2])
-#define PT_REGS_SP(x) ((x)->regs[29])
-#define PT_REGS_IP(x) ((x)->cp0_epc)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), regs[4])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), regs[5])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), regs[6])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), regs[7])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), regs[8])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), regs[31])
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), regs[30])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), regs[2])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), regs[29])
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), cp0_epc)
+#define __PT_PARM1_REG regs[4]
+#define __PT_PARM2_REG regs[5]
+#define __PT_PARM3_REG regs[6]
+#define __PT_PARM4_REG regs[7]
+#define __PT_PARM5_REG regs[8]
+#define __PT_RET_REG regs[31]
+#define __PT_FP_REG regs[30]	/* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG regs[2]
+#define __PT_SP_REG regs[29]
+#define __PT_IP_REG cp0_epc
 
 #elif defined(bpf_target_powerpc)
 
-#define PT_REGS_PARM1(x) ((x)->gpr[3])
-#define PT_REGS_PARM2(x) ((x)->gpr[4])
-#define PT_REGS_PARM3(x) ((x)->gpr[5])
-#define PT_REGS_PARM4(x) ((x)->gpr[6])
-#define PT_REGS_PARM5(x) ((x)->gpr[7])
-#define PT_REGS_RC(x) ((x)->gpr[3])
-#define PT_REGS_SP(x) ((x)->sp)
-#define PT_REGS_IP(x) ((x)->nip)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), gpr[3])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), gpr[4])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), gpr[5])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), gpr[6])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), gpr[7])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), gpr[3])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), nip)
+#define __PT_PARM1_REG gpr[3]
+#define __PT_PARM2_REG gpr[4]
+#define __PT_PARM3_REG gpr[5]
+#define __PT_PARM4_REG gpr[6]
+#define __PT_PARM5_REG gpr[7]
+#define __PT_RET_REG regs[31]
+#define __PT_FP_REG __unsupported__
+#define __PT_RC_REG gpr[3]
+#define __PT_SP_REG sp
+#define __PT_IP_REG nip
+/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx
 
 #elif defined(bpf_target_sparc)
 
-#define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0])
-#define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1])
-#define PT_REGS_PARM3(x) ((x)->u_regs[UREG_I2])
-#define PT_REGS_PARM4(x) ((x)->u_regs[UREG_I3])
-#define PT_REGS_PARM5(x) ((x)->u_regs[UREG_I4])
-#define PT_REGS_RET(x) ((x)->u_regs[UREG_I7])
-#define PT_REGS_RC(x) ((x)->u_regs[UREG_I0])
-#define PT_REGS_SP(x) ((x)->u_regs[UREG_FP])
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I1])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I2])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I3])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I4])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I7])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), u_regs[UREG_FP])
-
+#define __PT_PARM1_REG u_regs[UREG_I0]
+#define __PT_PARM2_REG u_regs[UREG_I1]
+#define __PT_PARM3_REG u_regs[UREG_I2]
+#define __PT_PARM4_REG u_regs[UREG_I3]
+#define __PT_PARM5_REG u_regs[UREG_I4]
+#define __PT_RET_REG u_regs[UREG_I7]
+#define __PT_FP_REG __unsupported__
+#define __PT_RC_REG u_regs[UREG_I0]
+#define __PT_SP_REG u_regs[UREG_FP]
 /* Should this also be a bpf_target check for the sparc case? */
 #if defined(__arch64__)
-#define PT_REGS_IP(x) ((x)->tpc)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), tpc)
+#define __PT_IP_REG tpc
 #else
-#define PT_REGS_IP(x) ((x)->pc)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), pc)
+#define __PT_IP_REG pc
 #endif
 
 #elif defined(bpf_target_riscv)
 
-struct pt_regs;
-#define PT_REGS_RV const volatile struct user_regs_struct
-#define PT_REGS_PARM1(x) (((PT_REGS_RV *)(x))->a0)
-#define PT_REGS_PARM2(x) (((PT_REGS_RV *)(x))->a1)
-#define PT_REGS_PARM3(x) (((PT_REGS_RV *)(x))->a2)
-#define PT_REGS_PARM4(x) (((PT_REGS_RV *)(x))->a3)
-#define PT_REGS_PARM5(x) (((PT_REGS_RV *)(x))->a4)
-#define PT_REGS_RET(x) (((PT_REGS_RV *)(x))->ra)
-#define PT_REGS_FP(x) (((PT_REGS_RV *)(x))->s5)
-#define PT_REGS_RC(x) (((PT_REGS_RV *)(x))->a5)
-#define PT_REGS_SP(x) (((PT_REGS_RV *)(x))->sp)
-#define PT_REGS_IP(x) (((PT_REGS_RV *)(x))->epc)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a0)
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a1)
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a2)
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a3)
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a4)
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), ra)
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), fp)
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a5)
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), sp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), epc)
+#define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x))
+#define __PT_PARM1_REG a0
+#define __PT_PARM2_REG a1
+#define __PT_PARM3_REG a2
+#define __PT_PARM4_REG a3
+#define __PT_PARM5_REG a4
+#define __PT_RET_REG ra
+#define __PT_FP_REG s0
+#define __PT_RC_REG a5
+#define __PT_SP_REG sp
+#define __PT_IP_REG pc
+/* riscv does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx
 
 #endif
 
+#if defined(bpf_target_defined)
+
+struct pt_regs;
+
+/* allow some architecutres to override `struct pt_regs` */
+#ifndef __PT_REGS_CAST
+#define __PT_REGS_CAST(x) (x)
+#endif
+
+#define PT_REGS_PARM1(x) (__PT_REGS_CAST(x)->__PT_PARM1_REG)
+#define PT_REGS_PARM2(x) (__PT_REGS_CAST(x)->__PT_PARM2_REG)
+#define PT_REGS_PARM3(x) (__PT_REGS_CAST(x)->__PT_PARM3_REG)
+#define PT_REGS_PARM4(x) (__PT_REGS_CAST(x)->__PT_PARM4_REG)
+#define PT_REGS_PARM5(x) (__PT_REGS_CAST(x)->__PT_PARM5_REG)
+#define PT_REGS_RET(x) (__PT_REGS_CAST(x)->__PT_RET_REG)
+#define PT_REGS_FP(x) (__PT_REGS_CAST(x)->__PT_FP_REG)
+#define PT_REGS_RC(x) (__PT_REGS_CAST(x)->__PT_RC_REG)
+#define PT_REGS_SP(x) (__PT_REGS_CAST(x)->__PT_SP_REG)
+#define PT_REGS_IP(x) (__PT_REGS_CAST(x)->__PT_IP_REG)
+
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM1_REG)
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM2_REG)
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM3_REG)
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM4_REG)
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM5_REG)
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RET_REG)
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_FP_REG)
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RC_REG)
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_SP_REG)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_IP_REG)
+
 #if defined(bpf_target_powerpc)
+
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = (ctx)->link; })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
+
 #elif defined(bpf_target_sparc)
+
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = PT_REGS_RET(ctx); })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
-#elif defined(bpf_target_defined)
+
+#else
+
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)					    \
 	({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); })
 #define BPF_KRETPROBE_READ_RET_IP(ip, ctx)				    \
-	({ bpf_probe_read_kernel(&(ip), sizeof(ip),			    \
-			  (void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
+	({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
+
 #endif
 
-#if !defined(bpf_target_defined)
+#ifndef PT_REGS_PARM1_SYSCALL
+#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1(x)
+#endif
+#define PT_REGS_PARM2_SYSCALL(x) PT_REGS_PARM2(x)
+#define PT_REGS_PARM3_SYSCALL(x) PT_REGS_PARM3(x)
+#ifndef PT_REGS_PARM4_SYSCALL
+#define PT_REGS_PARM4_SYSCALL(x) PT_REGS_PARM4(x)
+#endif
+#define PT_REGS_PARM5_SYSCALL(x) PT_REGS_PARM5(x)
+
+#ifndef PT_REGS_PARM1_CORE_SYSCALL
+#define PT_REGS_PARM1_CORE_SYSCALL(x) PT_REGS_PARM1_CORE(x)
+#endif
+#define PT_REGS_PARM2_CORE_SYSCALL(x) PT_REGS_PARM2_CORE(x)
+#define PT_REGS_PARM3_CORE_SYSCALL(x) PT_REGS_PARM3_CORE(x)
+#ifndef PT_REGS_PARM4_CORE_SYSCALL
+#define PT_REGS_PARM4_CORE_SYSCALL(x) PT_REGS_PARM4_CORE(x)
+#endif
+#define PT_REGS_PARM5_CORE_SYSCALL(x) PT_REGS_PARM5_CORE(x)
+
+#else /* defined(bpf_target_defined) */
 
 #define PT_REGS_PARM1(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define PT_REGS_PARM2(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
@@ -363,7 +332,29 @@ struct pt_regs;
 #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define BPF_KRETPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 
-#endif /* !defined(bpf_target_defined) */
+#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM2_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM3_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM4_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM5_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+
+#define PT_REGS_PARM1_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM2_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM3_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM4_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM5_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+
+#endif /* defined(bpf_target_defined) */
+
+/*
+ * When invoked from a syscall handler kprobe, returns a pointer to a
+ * struct pt_regs containing syscall arguments and suitable for passing to
+ * PT_REGS_PARMn_SYSCALL() and PT_REGS_PARMn_CORE_SYSCALL().
+ */
+#ifndef PT_REGS_SYSCALL_REGS
+/* By default, assume that the arch selects ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ((struct pt_regs *)PT_REGS_PARM1(ctx))
+#endif
 
 #ifndef ___bpf_concat
 #define ___bpf_concat(a, b) a ## b
@@ -375,25 +366,23 @@ struct pt_regs;
 #define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N
 #endif
 #ifndef ___bpf_narg
-#define ___bpf_narg(...) \
-	___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+#define ___bpf_narg(...) ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
 #endif
 
-#define ___bpf_ctx_cast0() ctx
-#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0]
-#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1]
-#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2]
-#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3]
-#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4]
-#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5]
-#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6]
-#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7]
-#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8]
+#define ___bpf_ctx_cast0()            ctx
+#define ___bpf_ctx_cast1(x)           ___bpf_ctx_cast0(), (void *)ctx[0]
+#define ___bpf_ctx_cast2(x, args...)  ___bpf_ctx_cast1(args), (void *)ctx[1]
+#define ___bpf_ctx_cast3(x, args...)  ___bpf_ctx_cast2(args), (void *)ctx[2]
+#define ___bpf_ctx_cast4(x, args...)  ___bpf_ctx_cast3(args), (void *)ctx[3]
+#define ___bpf_ctx_cast5(x, args...)  ___bpf_ctx_cast4(args), (void *)ctx[4]
+#define ___bpf_ctx_cast6(x, args...)  ___bpf_ctx_cast5(args), (void *)ctx[5]
+#define ___bpf_ctx_cast7(x, args...)  ___bpf_ctx_cast6(args), (void *)ctx[6]
+#define ___bpf_ctx_cast8(x, args...)  ___bpf_ctx_cast7(args), (void *)ctx[7]
+#define ___bpf_ctx_cast9(x, args...)  ___bpf_ctx_cast8(args), (void *)ctx[8]
 #define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9]
 #define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10]
 #define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11]
-#define ___bpf_ctx_cast(args...) \
-	___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args)
+#define ___bpf_ctx_cast(args...)      ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args)
 
 /*
  * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and
@@ -426,19 +415,13 @@ ____##name(unsigned long long *ctx, ##args)
 
 struct pt_regs;
 
-#define ___bpf_kprobe_args0() ctx
-#define ___bpf_kprobe_args1(x) \
-	___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx)
-#define ___bpf_kprobe_args2(x, args...) \
-	___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx)
-#define ___bpf_kprobe_args3(x, args...) \
-	___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx)
-#define ___bpf_kprobe_args4(x, args...) \
-	___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx)
-#define ___bpf_kprobe_args5(x, args...) \
-	___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx)
-#define ___bpf_kprobe_args(args...) \
-	___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)
+#define ___bpf_kprobe_args0()           ctx
+#define ___bpf_kprobe_args1(x)          ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx)
+#define ___bpf_kprobe_args2(x, args...) ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx)
+#define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx)
+#define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx)
+#define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx)
+#define ___bpf_kprobe_args(args...)     ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)
 
 /*
  * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for
@@ -464,11 +447,9 @@ typeof(name(0)) name(struct pt_regs *ctx)				    \
 static __attribute__((always_inline)) typeof(name(0))			    \
 ____##name(struct pt_regs *ctx, ##args)
 
-#define ___bpf_kretprobe_args0() ctx
-#define ___bpf_kretprobe_args1(x) \
-	___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx)
-#define ___bpf_kretprobe_args(args...) \
-	___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args)
+#define ___bpf_kretprobe_args0()       ctx
+#define ___bpf_kretprobe_args1(x)      ___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx)
+#define ___bpf_kretprobe_args(args...) ___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args)
 
 /*
  * BPF_KRETPROBE is similar to BPF_KPROBE, except, it only provides optional
@@ -489,4 +470,39 @@ typeof(name(0)) name(struct pt_regs *ctx)				    \
 }									    \
 static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
 
+#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_args(args...)     ___bpf_apply(___bpf_syscall_args, ___bpf_narg(args))(args)
+
+/*
+ * BPF_KPROBE_SYSCALL 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
+ * be necessary when using BPF helpers like bpf_perf_event_output().
+ *
+ * This macro relies on BPF CO-RE support.
+ */
+#define BPF_KPROBE_SYSCALL(name, args...)				    \
+name(struct pt_regs *ctx);						    \
+static __attribute__((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);		    \
+	_Pragma("GCC diagnostic push")					    \
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")		    \
+	return ____##name(___bpf_syscall_args(args));			    \
+	_Pragma("GCC diagnostic pop")					    \
+}									    \
+static __attribute__((always_inline)) typeof(name(0))			    \
+____##name(struct pt_regs *ctx, ##args)
+
 #endif

src/btf.c

@@ -454,7 +454,7 @@ const struct btf *btf__base_btf(const struct btf *btf)
 }
 
 /* internal helper returning non-const pointer to a type */
-struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id)
+struct btf_type *btf_type_by_id(const struct btf *btf, __u32 type_id)
 {
 	if (type_id == 0)
 		return &btf_void;
@@ -1124,54 +1124,86 @@ struct btf *btf__parse_split(const char *path, struct btf *base_btf)
 
 static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian);
 
-int btf__load_into_kernel(struct btf *btf)
+int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level)
 {
-	__u32 log_buf_size = 0, raw_size;
-	char *log_buf = NULL;
+	LIBBPF_OPTS(bpf_btf_load_opts, opts);
+	__u32 buf_sz = 0, raw_size;
+	char *buf = NULL, *tmp;
 	void *raw_data;
 	int err = 0;
 
 	if (btf->fd >= 0)
 		return libbpf_err(-EEXIST);
+	if (log_sz && !log_buf)
+		return libbpf_err(-EINVAL);
 
-retry_load:
-	if (log_buf_size) {
-		log_buf = malloc(log_buf_size);
-		if (!log_buf)
-			return libbpf_err(-ENOMEM);
-
-		*log_buf = 0;
-	}
-
+	/* cache native raw data representation */
 	raw_data = btf_get_raw_data(btf, &raw_size, false);
 	if (!raw_data) {
 		err = -ENOMEM;
 		goto done;
 	}
-	/* cache native raw data representation */
 	btf->raw_size = raw_size;
 	btf->raw_data = raw_data;
 
-	btf->fd = bpf_load_btf(raw_data, raw_size, log_buf, log_buf_size, false);
-	if (btf->fd < 0) {
-		if (!log_buf || errno == ENOSPC) {
-			log_buf_size = max((__u32)BPF_LOG_BUF_SIZE,
-					   log_buf_size << 1);
-			free(log_buf);
-			goto retry_load;
+retry_load:
+	/* if log_level is 0, we won't provide log_buf/log_size to the kernel,
+	 * initially. Only if BTF loading fails, we bump log_level to 1 and
+	 * retry, using either auto-allocated or custom log_buf. This way
+	 * non-NULL custom log_buf provides a buffer just in case, but hopes
+	 * for successful load and no need for log_buf.
+	 */
+	if (log_level) {
+		/* if caller didn't provide custom log_buf, we'll keep
+		 * allocating our own progressively bigger buffers for BTF
+		 * verification log
+		 */
+		if (!log_buf) {
+			buf_sz = max((__u32)BPF_LOG_BUF_SIZE, buf_sz * 2);
+			tmp = realloc(buf, buf_sz);
+			if (!tmp) {
+				err = -ENOMEM;
+				goto done;
+			}
+			buf = tmp;
+			buf[0] = '\0';
 		}
 
+		opts.log_buf = log_buf ? log_buf : buf;
+		opts.log_size = log_buf ? log_sz : buf_sz;
+		opts.log_level = log_level;
+	}
+
+	btf->fd = bpf_btf_load(raw_data, raw_size, &opts);
+	if (btf->fd < 0) {
+		/* time to turn on verbose mode and try again */
+		if (log_level == 0) {
+			log_level = 1;
+			goto retry_load;
+		}
+		/* only retry if caller didn't provide custom log_buf, but
+		 * make sure we can never overflow buf_sz
+		 */
+		if (!log_buf && errno == ENOSPC && buf_sz <= UINT_MAX / 2)
+			goto retry_load;
+
 		err = -errno;
-		pr_warn("Error loading BTF: %s(%d)\n", strerror(errno), errno);
-		if (*log_buf)
-			pr_warn("%s\n", log_buf);
-		goto done;
+		pr_warn("BTF loading error: %d\n", err);
+		/* don't print out contents of custom log_buf */
+		if (!log_buf && buf[0])
+			pr_warn("-- BEGIN BTF LOAD LOG ---\n%s\n-- END BTF LOAD LOG --\n", buf);
 	}
 
 done:
-	free(log_buf);
+	free(buf);
 	return libbpf_err(err);
 }
+
+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)
@@ -1588,20 +1620,37 @@ static int btf_commit_type(struct btf *btf, int data_sz)
 struct btf_pipe {
 	const struct btf *src;
 	struct btf *dst;
+	struct hashmap *str_off_map; /* map string offsets from src to dst */
 };
 
 static int btf_rewrite_str(__u32 *str_off, void *ctx)
 {
 	struct btf_pipe *p = ctx;
-	int off;
+	void *mapped_off;
+	int off, err;
 
 	if (!*str_off) /* nothing to do for empty strings */
 		return 0;
 
+	if (p->str_off_map &&
+	    hashmap__find(p->str_off_map, (void *)(long)*str_off, &mapped_off)) {
+		*str_off = (__u32)(long)mapped_off;
+		return 0;
+	}
+
 	off = btf__add_str(p->dst, btf__str_by_offset(p->src, *str_off));
 	if (off < 0)
 		return off;
 
+	/* Remember string mapping from src to dst.  It avoids
+	 * performing expensive string comparisons.
+	 */
+	if (p->str_off_map) {
+		err = hashmap__append(p->str_off_map, (void *)(long)*str_off, (void *)(long)off);
+		if (err)
+			return err;
+	}
+
 	*str_off = off;
 	return 0;
 }
@@ -1648,6 +1697,9 @@ static int btf_rewrite_type_ids(__u32 *type_id, void *ctx)
 	return 0;
 }
 
+static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx);
+static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx);
+
 int btf__add_btf(struct btf *btf, const struct btf *src_btf)
 {
 	struct btf_pipe p = { .src = src_btf, .dst = btf };
@@ -1681,6 +1733,11 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf)
 	if (!off)
 		return libbpf_err(-ENOMEM);
 
+	/* Map the string offsets from src_btf to the offsets from btf to improve performance */
+	p.str_off_map = hashmap__new(btf_dedup_identity_hash_fn, btf_dedup_equal_fn, NULL);
+	if (IS_ERR(p.str_off_map))
+		return libbpf_err(-ENOMEM);
+
 	/* bulk copy types data for all types from src_btf */
 	memcpy(t, src_btf->types_data, data_sz);
 
@@ -1722,6 +1779,8 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf)
 	btf->hdr->str_off += data_sz;
 	btf->nr_types += cnt;
 
+	hashmap__free(p.str_off_map);
+
 	/* return type ID of the first added BTF type */
 	return btf->start_id + btf->nr_types - cnt;
 err_out:
@@ -1735,6 +1794,8 @@ err_out:
 	 * wasn't modified, so doesn't need restoring, see big comment above */
 	btf->hdr->str_len = old_strs_len;
 
+	hashmap__free(p.str_off_map);
+
 	return libbpf_err(err);
 }
 
@@ -3075,7 +3136,7 @@ done:
 	return libbpf_err(err);
 }
 
-COMPAT_VERSION(bpf__dedup_deprecated, btf__dedup, LIBBPF_0.0.2)
+COMPAT_VERSION(btf__dedup_deprecated, btf__dedup, LIBBPF_0.0.2)
 int btf__dedup_deprecated(struct btf *btf, struct btf_ext *btf_ext, const void *unused_opts)
 {
 	LIBBPF_OPTS(btf_dedup_opts, opts, .btf_ext = btf_ext);

src/btf.h

@@ -147,11 +147,10 @@ LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id);
 LIBBPF_API int btf__align_of(const struct btf *btf, __u32 id);
 LIBBPF_API int btf__fd(const struct btf *btf);
 LIBBPF_API void btf__set_fd(struct btf *btf, int fd);
-LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__raw_data() instead")
-LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size);
 LIBBPF_API const void *btf__raw_data(const struct btf *btf, __u32 *size);
 LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
 LIBBPF_API const char *btf__str_by_offset(const struct btf *btf, __u32 offset);
+LIBBPF_DEPRECATED_SINCE(0, 7, "this API is not necessary when BTF-defined maps are used")
 LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
 				    __u32 expected_key_size,
 				    __u32 expected_value_size,
@@ -159,8 +158,7 @@ LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
 
 LIBBPF_API struct btf_ext *btf_ext__new(const __u8 *data, __u32 size);
 LIBBPF_API void btf_ext__free(struct btf_ext *btf_ext);
-LIBBPF_API const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext,
-					     __u32 *size);
+LIBBPF_API const void *btf_ext__raw_data(const struct btf_ext *btf_ext, __u32 *size);
 LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_func_info was never meant as a public API and has wrong assumptions embedded in it; it will be removed in the future libbpf versions")
 int btf_ext__reloc_func_info(const struct btf *btf,
 			     const struct btf_ext *btf_ext,
@@ -171,8 +169,10 @@ int btf_ext__reloc_line_info(const struct btf *btf,
 			     const struct btf_ext *btf_ext,
 			     const char *sec_name, __u32 insns_cnt,
 			     void **line_info, __u32 *cnt);
-LIBBPF_API __u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext);
-LIBBPF_API __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext);
+LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_func_info is deprecated; write custom func_info parsing to fetch rec_size")
+__u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext);
+LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_line_info is deprecated; write custom line_info parsing to fetch rec_size")
+__u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext);
 
 LIBBPF_API int btf__find_str(struct btf *btf, const char *s);
 LIBBPF_API int btf__add_str(struct btf *btf, const char *s);
@@ -313,12 +313,18 @@ LIBBPF_API struct btf_dump *btf_dump__new_deprecated(const struct btf *btf,
  *
  * The rest works just like in case of ___libbpf_override() usage with symbol
  * versioning.
+ *
+ * C++ compilers don't support __builtin_types_compatible_p(), so at least
+ * don't screw up compilation for them and let C++ users pick btf_dump__new
+ * vs btf_dump__new_deprecated explicitly.
  */
+#ifndef __cplusplus
 #define btf_dump__new(a1, a2, a3, a4) __builtin_choose_expr(				\
 	__builtin_types_compatible_p(typeof(a4), btf_dump_printf_fn_t) ||		\
 	__builtin_types_compatible_p(typeof(a4), void(void *, const char *, va_list)),	\
 	btf_dump__new_deprecated((void *)a1, (void *)a2, (void *)a3, (void *)a4),	\
 	btf_dump__new((void *)a1, (void *)a2, (void *)a3, (void *)a4))
+#endif
 
 LIBBPF_API void btf_dump__free(struct btf_dump *d);
 
@@ -369,8 +375,28 @@ btf_dump__dump_type_data(struct btf_dump *d, __u32 id,
 			 const struct btf_dump_type_data_opts *opts);
 
 /*
- * A set of helpers for easier BTF types handling
+ * A set of helpers for easier BTF types handling.
+ *
+ * The inline functions below rely on constants from the kernel headers which
+ * may not be available for applications including this header file. To avoid
+ * compilation errors, we define all the constants here that were added after
+ * the initial introduction of the BTF_KIND* constants.
  */
+#ifndef BTF_KIND_FUNC
+#define BTF_KIND_FUNC		12	/* Function	*/
+#define BTF_KIND_FUNC_PROTO	13	/* Function Proto	*/
+#endif
+#ifndef BTF_KIND_VAR
+#define BTF_KIND_VAR		14	/* Variable	*/
+#define BTF_KIND_DATASEC	15	/* Section	*/
+#endif
+#ifndef BTF_KIND_FLOAT
+#define BTF_KIND_FLOAT		16	/* Floating point	*/
+#endif
+/* The kernel header switched to enums, so these two were never #defined */
+#define BTF_KIND_DECL_TAG	17	/* Decl Tag */
+#define BTF_KIND_TYPE_TAG	18	/* Type Tag */
+
 static inline __u16 btf_kind(const struct btf_type *t)
 {
 	return BTF_INFO_KIND(t->info);

src/btf_dump.c

@@ -1861,14 +1861,16 @@ static int btf_dump_array_data(struct btf_dump *d,
 {
 	const struct btf_array *array = btf_array(t);
 	const struct btf_type *elem_type;
-	__u32 i, elem_size = 0, elem_type_id;
+	__u32 i, elem_type_id;
+	__s64 elem_size;
 	bool is_array_member;
 
 	elem_type_id = array->type;
 	elem_type = skip_mods_and_typedefs(d->btf, elem_type_id, NULL);
 	elem_size = btf__resolve_size(d->btf, elem_type_id);
 	if (elem_size <= 0) {
-		pr_warn("unexpected elem size %d for array type [%u]\n", elem_size, id);
+		pr_warn("unexpected elem size %zd for array type [%u]\n",
+			(ssize_t)elem_size, id);
 		return -EINVAL;
 	}
 
@@ -2321,8 +2323,8 @@ int btf_dump__dump_type_data(struct btf_dump *d, __u32 id,
 	if (!opts->indent_str)
 		d->typed_dump->indent_str[0] = '\t';
 	else
-		strncat(d->typed_dump->indent_str, opts->indent_str,
-			sizeof(d->typed_dump->indent_str) - 1);
+		libbpf_strlcpy(d->typed_dump->indent_str, opts->indent_str,
+			       sizeof(d->typed_dump->indent_str));
 
 	d->typed_dump->compact = OPTS_GET(opts, compact, false);
 	d->typed_dump->skip_names = OPTS_GET(opts, skip_names, false);

src/gen_loader.c

@@ -371,8 +371,9 @@ int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps)
 {
 	int i;
 
-	if (nr_progs != gen->nr_progs || nr_maps != gen->nr_maps) {
-		pr_warn("progs/maps mismatch\n");
+	if (nr_progs < gen->nr_progs || nr_maps != gen->nr_maps) {
+		pr_warn("nr_progs %d/%d nr_maps %d/%d mismatch\n",
+			nr_progs, gen->nr_progs, nr_maps, gen->nr_maps);
 		gen->error = -EFAULT;
 		return gen->error;
 	}
@@ -462,8 +463,7 @@ void bpf_gen__map_create(struct bpf_gen *gen,
 	attr.map_flags = map_attr->map_flags;
 	attr.map_extra = map_attr->map_extra;
 	if (map_name)
-		memcpy(attr.map_name, map_name,
-		       min((unsigned)strlen(map_name), BPF_OBJ_NAME_LEN - 1));
+		libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name));
 	attr.numa_node = map_attr->numa_node;
 	attr.map_ifindex = map_attr->map_ifindex;
 	attr.max_entries = max_entries;
@@ -687,27 +687,29 @@ static void emit_relo_kfunc_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo
 		return;
 	}
 	kdesc->off = btf_fd_idx;
-	/* set a default value for imm */
+	/* jump to success case */
+	emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3));
+	/* set value for imm, off as 0 */
 	emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, offsetof(struct bpf_insn, imm), 0));
-	/* skip success case store if ret < 0 */
-	emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 1));
+	emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0));
+	/* skip success case for ret < 0 */
+	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 10));
 	/* store btf_id into insn[insn_idx].imm */
 	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, offsetof(struct bpf_insn, imm)));
+	/* obtain fd in BPF_REG_9 */
+	emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_7));
+	emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32));
+	/* jump to fd_array store if fd denotes module BTF */
+	emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 2));
+	/* set the default value for off */
+	emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0));
+	/* skip BTF fd store for vmlinux BTF */
+	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 4));
 	/* load fd_array slot pointer */
 	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE,
 					 0, 0, 0, blob_fd_array_off(gen, btf_fd_idx)));
-	/* skip store of BTF fd if ret < 0 */
-	emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 3));
 	/* store BTF fd in slot */
-	emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_7));
-	emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32));
 	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_9, 0));
-	/* set a default value for off */
-	emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0));
-	/* skip insn->off store if ret < 0 */
-	emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 2));
-	/* skip if vmlinux BTF */
-	emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_9, 0, 1));
 	/* store index into insn[insn_idx].off */
 	emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), btf_fd_idx));
 log:
@@ -806,9 +808,8 @@ static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo,
 			       kdesc->insn + offsetof(struct bpf_insn, imm));
 		move_blob2blob(gen, insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 4,
 			       kdesc->insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm));
-		emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_8, offsetof(struct bpf_insn, imm)));
-		/* jump over src_reg adjustment if imm is not 0 */
-		emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 3));
+		/* jump over src_reg adjustment if imm is not 0, reuse BPF_REG_0 from move_blob2blob */
+		emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3));
 		goto clear_src_reg;
 	}
 	/* remember insn offset, so we can copy BTF ID and FD later */
@@ -816,17 +817,20 @@ static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo,
 	emit_bpf_find_by_name_kind(gen, relo);
 	if (!relo->is_weak)
 		emit_check_err(gen);
-	/* set default values as 0 */
+	/* jump to success case */
+	emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3));
+	/* set values for insn[insn_idx].imm, insn[insn_idx + 1].imm as 0 */
 	emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, offsetof(struct bpf_insn, imm), 0));
 	emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 0));
-	/* skip success case stores if ret < 0 */
-	emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 4));
+	/* skip success case for ret < 0 */
+	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 4));
 	/* store btf_id into insn[insn_idx].imm */
 	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, offsetof(struct bpf_insn, imm)));
 	/* store btf_obj_fd into insn[insn_idx + 1].imm */
 	emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32));
 	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7,
 			      sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm)));
+	/* skip src_reg adjustment */
 	emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3));
 clear_src_reg:
 	/* clear bpf_object__relocate_data's src_reg assignment, otherwise we get a verifier failure */
@@ -838,6 +842,22 @@ clear_src_reg:
 	emit_ksym_relo_log(gen, relo, kdesc->ref);
 }
 
+void bpf_gen__record_relo_core(struct bpf_gen *gen,
+			       const struct bpf_core_relo *core_relo)
+{
+	struct bpf_core_relo *relos;
+
+	relos = libbpf_reallocarray(gen->core_relos, gen->core_relo_cnt + 1, sizeof(*relos));
+	if (!relos) {
+		gen->error = -ENOMEM;
+		return;
+	}
+	gen->core_relos = relos;
+	relos += gen->core_relo_cnt;
+	memcpy(relos, core_relo, sizeof(*relos));
+	gen->core_relo_cnt++;
+}
+
 static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insns)
 {
 	int insn;
@@ -870,6 +890,15 @@ static void emit_relos(struct bpf_gen *gen, int insns)
 		emit_relo(gen, gen->relos + i, insns);
 }
 
+static void cleanup_core_relo(struct bpf_gen *gen)
+{
+	if (!gen->core_relo_cnt)
+		return;
+	free(gen->core_relos);
+	gen->core_relo_cnt = 0;
+	gen->core_relos = NULL;
+}
+
 static void cleanup_relos(struct bpf_gen *gen, int insns)
 {
 	int i, insn;
@@ -897,6 +926,7 @@ static void cleanup_relos(struct bpf_gen *gen, int insns)
 		gen->relo_cnt = 0;
 		gen->relos = NULL;
 	}
+	cleanup_core_relo(gen);
 }
 
 void bpf_gen__prog_load(struct bpf_gen *gen,
@@ -904,12 +934,13 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
 			const char *license, struct bpf_insn *insns, size_t insn_cnt,
 			struct bpf_prog_load_opts *load_attr, int prog_idx)
 {
-	int attr_size = offsetofend(union bpf_attr, fd_array);
-	int prog_load_attr, license_off, insns_off, func_info, line_info;
+	int prog_load_attr, license_off, insns_off, func_info, line_info, core_relos;
+	int attr_size = offsetofend(union bpf_attr, core_relo_rec_size);
 	union bpf_attr attr;
 
 	memset(&attr, 0, attr_size);
-	pr_debug("gen: prog_load: type %d insns_cnt %zd\n", prog_type, insn_cnt);
+	pr_debug("gen: prog_load: type %d insns_cnt %zd progi_idx %d\n",
+		 prog_type, insn_cnt, prog_idx);
 	/* add license string to blob of bytes */
 	license_off = add_data(gen, license, strlen(license) + 1);
 	/* add insns to blob of bytes */
@@ -933,8 +964,12 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
 	line_info = add_data(gen, load_attr->line_info,
 			     attr.line_info_cnt * attr.line_info_rec_size);
 
-	memcpy(attr.prog_name, prog_name,
-	       min((unsigned)strlen(prog_name), BPF_OBJ_NAME_LEN - 1));
+	attr.core_relo_rec_size = sizeof(struct bpf_core_relo);
+	attr.core_relo_cnt = gen->core_relo_cnt;
+	core_relos = add_data(gen, gen->core_relos,
+			     attr.core_relo_cnt * attr.core_relo_rec_size);
+
+	libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
 	prog_load_attr = add_data(gen, &attr, attr_size);
 
 	/* populate union bpf_attr with a pointer to license */
@@ -949,6 +984,9 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
 	/* populate union bpf_attr with a pointer to line_info */
 	emit_rel_store(gen, attr_field(prog_load_attr, line_info), line_info);
 
+	/* populate union bpf_attr with a pointer to core_relos */
+	emit_rel_store(gen, attr_field(prog_load_attr, core_relos), core_relos);
+
 	/* populate union bpf_attr fd_array with a pointer to data where map_fds are saved */
 	emit_rel_store(gen, attr_field(prog_load_attr, fd_array), gen->fd_array);
 
@@ -979,9 +1017,11 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
 	debug_ret(gen, "prog_load %s insn_cnt %d", attr.prog_name, attr.insn_cnt);
 	/* successful or not, close btf module FDs used in extern ksyms and attach_btf_obj_fd */
 	cleanup_relos(gen, insns_off);
-	if (gen->attach_kind)
+	if (gen->attach_kind) {
 		emit_sys_close_blob(gen,
 				    attr_field(prog_load_attr, attach_btf_obj_fd));
+		gen->attach_kind = 0;
+	}
 	emit_check_err(gen);
 	/* remember prog_fd in the stack, if successful */
 	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7,
@@ -1027,6 +1067,33 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue,
 	emit_check_err(gen);
 }
 
+void bpf_gen__populate_outer_map(struct bpf_gen *gen, int outer_map_idx, int slot,
+				 int inner_map_idx)
+{
+	int attr_size = offsetofend(union bpf_attr, flags);
+	int map_update_attr, key;
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_size);
+	pr_debug("gen: populate_outer_map: outer %d key %d inner %d\n",
+		 outer_map_idx, slot, inner_map_idx);
+
+	key = add_data(gen, &slot, sizeof(slot));
+
+	map_update_attr = add_data(gen, &attr, attr_size);
+	move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4,
+		       blob_fd_array_off(gen, outer_map_idx));
+	emit_rel_store(gen, attr_field(map_update_attr, key), key);
+	emit_rel_store(gen, attr_field(map_update_attr, value),
+		       blob_fd_array_off(gen, inner_map_idx));
+
+	/* emit MAP_UPDATE_ELEM command */
+	emit_sys_bpf(gen, BPF_MAP_UPDATE_ELEM, map_update_attr, attr_size);
+	debug_ret(gen, "populate_outer_map outer %d key %d inner %d",
+		  outer_map_idx, slot, inner_map_idx);
+	emit_check_err(gen);
+}
+
 void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx)
 {
 	int attr_size = offsetofend(union bpf_attr, map_fd);

src/hashmap.c

@@ -75,7 +75,7 @@ void hashmap__clear(struct hashmap *map)
 
 void hashmap__free(struct hashmap *map)
 {
-	if (!map)
+	if (IS_ERR_OR_NULL(map))
 		return;
 
 	hashmap__clear(map);
@@ -238,4 +238,3 @@ bool hashmap__delete(struct hashmap *map, const void *key,
 
 	return true;
 }
-

src/libbpf.h

@@ -108,20 +108,83 @@ struct bpf_object_open_opts {
 	 * struct_ops, etc) will need actual kernel BTF at /sys/kernel/btf/vmlinux.
 	 */
 	const char *btf_custom_path;
+	/* Pointer to a buffer for storing kernel logs for applicable BPF
+	 * commands. Valid kernel_log_size has to be specified as well and are
+	 * passed-through to bpf() syscall. Keep in mind that kernel might
+	 * fail operation with -ENOSPC error if provided buffer is too small
+	 * to contain entire log output.
+	 * See the comment below for kernel_log_level for interaction between
+	 * log_buf and log_level settings.
+	 *
+	 * If specified, this log buffer will be passed for:
+	 *   - each BPF progral load (BPF_PROG_LOAD) attempt, unless overriden
+	 *     with bpf_program__set_log() on per-program level, to get
+	 *     BPF verifier log output.
+	 *   - during BPF object's BTF load into kernel (BPF_BTF_LOAD) to get
+	 *     BTF sanity checking log.
+	 *
+	 * Each BPF command (BPF_BTF_LOAD or BPF_PROG_LOAD) will overwrite
+	 * previous contents, so if you need more fine-grained control, set
+	 * per-program buffer with bpf_program__set_log_buf() to preserve each
+	 * individual program's verification log. Keep using kernel_log_buf
+	 * for BTF verification log, if necessary.
+	 */
+	char *kernel_log_buf;
+	size_t kernel_log_size;
+	/*
+	 * Log level can be set independently from log buffer. Log_level=0
+	 * means that libbpf will attempt loading BTF or program without any
+	 * logging requested, but will retry with either its own or custom log
+	 * buffer, if provided, and log_level=1 on any error.
+	 * And vice versa, setting log_level>0 will request BTF or prog
+	 * loading with verbose log from the first attempt (and as such also
+	 * for successfully loaded BTF or program), and the actual log buffer
+	 * could be either libbpf's own auto-allocated log buffer, if
+	 * kernel_log_buffer is NULL, or user-provided custom kernel_log_buf.
+	 * If user didn't provide custom log buffer, libbpf will emit captured
+	 * logs through its print callback.
+	 */
+	__u32 kernel_log_level;
+
+	size_t :0;
 };
-#define bpf_object_open_opts__last_field btf_custom_path
+#define bpf_object_open_opts__last_field kernel_log_level
 
 LIBBPF_API struct bpf_object *bpf_object__open(const char *path);
+
+/**
+ * @brief **bpf_object__open_file()** creates a bpf_object by opening
+ * the BPF ELF object file pointed to by the passed path and loading it
+ * into memory.
+ * @param path BPF object file path
+ * @param opts options for how to load the bpf object, this parameter is
+ * optional and can be set to NULL
+ * @return pointer to the new bpf_object; or NULL is returned on error,
+ * error code is stored in errno
+ */
 LIBBPF_API struct bpf_object *
 bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts);
+
+/**
+ * @brief **bpf_object__open_mem()** creates a bpf_object by reading
+ * the BPF objects raw bytes from a memory buffer containing a valid
+ * BPF ELF object file.
+ * @param obj_buf pointer to the buffer containing ELF file bytes
+ * @param obj_buf_sz number of bytes in the buffer
+ * @param opts options for how to load the bpf object
+ * @return pointer to the new bpf_object; or NULL is returned on error,
+ * error code is stored in errno
+ */
 LIBBPF_API struct bpf_object *
 bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz,
 		     const struct bpf_object_open_opts *opts);
 
 /* deprecated bpf_object__open variants */
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__open_mem() instead")
 LIBBPF_API struct bpf_object *
 bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz,
 			const char *name);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__open_file() instead")
 LIBBPF_API struct bpf_object *
 bpf_object__open_xattr(struct bpf_object_open_attr *attr);
 
@@ -153,6 +216,7 @@ struct bpf_object_load_attr {
 
 /* Load/unload object into/from kernel */
 LIBBPF_API int bpf_object__load(struct bpf_object *obj);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__load() instead")
 LIBBPF_API int bpf_object__load_xattr(struct bpf_object_load_attr *attr);
 LIBBPF_DEPRECATED_SINCE(0, 6, "bpf_object__unload() is deprecated, use bpf_object__close() instead")
 LIBBPF_API int bpf_object__unload(struct bpf_object *obj);
@@ -165,6 +229,7 @@ struct btf;
 LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj);
 LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj);
 
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__find_program_by_name() instead")
 LIBBPF_API struct bpf_program *
 bpf_object__find_program_by_title(const struct bpf_object *obj,
 				  const char *title);
@@ -181,8 +246,10 @@ struct bpf_object *bpf_object__next(struct bpf_object *prev);
 	     (pos) = (tmp), (tmp) = bpf_object__next(tmp))
 
 typedef void (*bpf_object_clear_priv_t)(struct bpf_object *, void *);
+LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated")
 LIBBPF_API int bpf_object__set_priv(struct bpf_object *obj, void *priv,
 				    bpf_object_clear_priv_t clear_priv);
+LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated")
 LIBBPF_API void *bpf_object__priv(const struct bpf_object *prog);
 
 LIBBPF_API int
@@ -214,9 +281,10 @@ bpf_object__prev_program(const struct bpf_object *obj, struct bpf_program *prog)
 
 typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, void *);
 
+LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated")
 LIBBPF_API int bpf_program__set_priv(struct bpf_program *prog, void *priv,
 				     bpf_program_clear_priv_t clear_priv);
-
+LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated")
 LIBBPF_API void *bpf_program__priv(const struct bpf_program *prog);
 LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog,
 					 __u32 ifindex);
@@ -277,7 +345,31 @@ LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated"
 LIBBPF_API int bpf_program__unpin_instance(struct bpf_program *prog,
 					   const char *path,
 					   int instance);
+
+/**
+ * @brief **bpf_program__pin()** pins the BPF program to a file
+ * in the BPF FS specified by a path. This increments the programs
+ * reference count, allowing it to stay loaded after the process
+ * which loaded it has exited.
+ *
+ * @param prog BPF program to pin, must already be loaded
+ * @param path file path in a BPF file system
+ * @return 0, on success; negative error code, otherwise
+ */
 LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path);
+
+/**
+ * @brief **bpf_program__unpin()** unpins the BPF program from a file
+ * in the BPFFS specified by a path. This decrements the programs
+ * reference count.
+ *
+ * The file pinning the BPF program can also be unlinked by a different
+ * process in which case this function will return an error.
+ *
+ * @param prog BPF program to unpin
+ * @param path file path to the pin in a BPF file system
+ * @return 0, on success; negative error code, otherwise
+ */
 LIBBPF_API int bpf_program__unpin(struct bpf_program *prog, const char *path);
 LIBBPF_API void bpf_program__unload(struct bpf_program *prog);
 
@@ -348,10 +440,41 @@ struct bpf_uprobe_opts {
 };
 #define bpf_uprobe_opts__last_field retprobe
 
+/**
+ * @brief **bpf_program__attach_uprobe()** attaches a BPF program
+ * to the userspace function which is found by binary path and
+ * offset. You can optionally specify a particular proccess to attach
+ * to. You can also optionally attach the program to the function
+ * exit instead of entry.
+ *
+ * @param prog BPF program to attach
+ * @param retprobe Attach to function exit
+ * @param pid Process ID to attach the uprobe to, 0 for self (own process),
+ * -1 for all processes
+ * @param binary_path Path to binary that contains the function symbol
+ * @param func_offset Offset within the binary of the function symbol
+ * @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_uprobe(const struct bpf_program *prog, bool retprobe,
 			   pid_t pid, const char *binary_path,
 			   size_t func_offset);
+
+/**
+ * @brief **bpf_program__attach_uprobe_opts()** is just like
+ * bpf_program__attach_uprobe() except with a options struct
+ * for various configurations.
+ *
+ * @param prog BPF program to attach
+ * @param pid Process ID to attach the uprobe to, 0 for self (own process),
+ * -1 for all processes
+ * @param binary_path Path to binary that contains the function symbol
+ * @param func_offset Offset within the binary of the function symbol
+ * @param opts Options for altering program attachment
+ * @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_uprobe_opts(const struct bpf_program *prog, pid_t pid,
 				const char *binary_path, size_t func_offset,
@@ -473,26 +596,39 @@ LIBBPF_API int bpf_program__nth_fd(const struct bpf_program *prog, int n);
 /*
  * Adjust type of BPF program. Default is kprobe.
  */
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead")
 LIBBPF_API int bpf_program__set_socket_filter(struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead")
 LIBBPF_API int bpf_program__set_tracepoint(struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead")
 LIBBPF_API int bpf_program__set_raw_tracepoint(struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead")
 LIBBPF_API int bpf_program__set_kprobe(struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead")
 LIBBPF_API int bpf_program__set_lsm(struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead")
 LIBBPF_API int bpf_program__set_sched_cls(struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead")
 LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead")
 LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead")
 LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead")
 LIBBPF_API int bpf_program__set_tracing(struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead")
 LIBBPF_API int bpf_program__set_struct_ops(struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead")
 LIBBPF_API int bpf_program__set_extension(struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead")
 LIBBPF_API int bpf_program__set_sk_lookup(struct bpf_program *prog);
 
-LIBBPF_API enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog);
+LIBBPF_API enum bpf_prog_type bpf_program__type(const struct bpf_program *prog);
 LIBBPF_API void bpf_program__set_type(struct bpf_program *prog,
 				      enum bpf_prog_type type);
 
 LIBBPF_API enum bpf_attach_type
-bpf_program__get_expected_attach_type(const struct bpf_program *prog);
+bpf_program__expected_attach_type(const struct bpf_program *prog);
 LIBBPF_API void
 bpf_program__set_expected_attach_type(struct bpf_program *prog,
 				      enum bpf_attach_type type);
@@ -500,22 +636,44 @@ bpf_program__set_expected_attach_type(struct bpf_program *prog,
 LIBBPF_API __u32 bpf_program__flags(const struct bpf_program *prog);
 LIBBPF_API int bpf_program__set_flags(struct bpf_program *prog, __u32 flags);
 
+/* Per-program log level and log buffer getters/setters.
+ * See bpf_object_open_opts comments regarding log_level and log_buf
+ * interactions.
+ */
+LIBBPF_API __u32 bpf_program__log_level(const struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_log_level(struct bpf_program *prog, __u32 log_level);
+LIBBPF_API const char *bpf_program__log_buf(const struct bpf_program *prog, size_t *log_size);
+LIBBPF_API int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log_size);
+
 LIBBPF_API int
 bpf_program__set_attach_target(struct bpf_program *prog, int attach_prog_fd,
 			       const char *attach_func_name);
 
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead")
 LIBBPF_API bool bpf_program__is_socket_filter(const struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead")
 LIBBPF_API bool bpf_program__is_tracepoint(const struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead")
 LIBBPF_API bool bpf_program__is_raw_tracepoint(const struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead")
 LIBBPF_API bool bpf_program__is_kprobe(const struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead")
 LIBBPF_API bool bpf_program__is_lsm(const struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead")
 LIBBPF_API bool bpf_program__is_sched_cls(const struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead")
 LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead")
 LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead")
 LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead")
 LIBBPF_API bool bpf_program__is_tracing(const struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead")
 LIBBPF_API bool bpf_program__is_struct_ops(const struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead")
 LIBBPF_API bool bpf_program__is_extension(const struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead")
 LIBBPF_API bool bpf_program__is_sk_lookup(const struct bpf_program *prog);
 
 /*
@@ -550,7 +708,8 @@ bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name);
  * Get bpf_map through the offset of corresponding struct bpf_map_def
  * in the BPF object file.
  */
-LIBBPF_API struct bpf_map *
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__find_map_by_name() instead")
+struct bpf_map *
 bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset);
 
 LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__next_map() instead")
@@ -578,7 +737,8 @@ bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *map);
 LIBBPF_API int bpf_map__fd(const struct bpf_map *map);
 LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd);
 /* get map definition */
-LIBBPF_API const struct bpf_map_def *bpf_map__def(const struct bpf_map *map);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 8, "use appropriate getters or setters instead")
+const struct bpf_map_def *bpf_map__def(const struct bpf_map *map);
 /* get map name */
 LIBBPF_API const char *bpf_map__name(const struct bpf_map *map);
 /* get/set map type */
@@ -587,6 +747,7 @@ LIBBPF_API int bpf_map__set_type(struct bpf_map *map, enum bpf_map_type type);
 /* get/set map size (max_entries) */
 LIBBPF_API __u32 bpf_map__max_entries(const struct bpf_map *map);
 LIBBPF_API int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_map__set_max_entries() instead")
 LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries);
 /* get/set map flags */
 LIBBPF_API __u32 bpf_map__map_flags(const struct bpf_map *map);
@@ -611,12 +772,15 @@ LIBBPF_API __u64 bpf_map__map_extra(const struct bpf_map *map);
 LIBBPF_API int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra);
 
 typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
+LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated")
 LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv,
 				 bpf_map_clear_priv_t clear_priv);
+LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated")
 LIBBPF_API void *bpf_map__priv(const struct bpf_map *map);
 LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map,
 					  const void *data, size_t size);
 LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_map__type() instead")
 LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map);
 
 /**
@@ -628,7 +792,6 @@ LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map);
  */
 LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map);
 LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path);
-LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map);
 LIBBPF_API const char *bpf_map__pin_path(const struct bpf_map *map);
 LIBBPF_API bool bpf_map__is_pinned(const struct bpf_map *map);
 LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path);
@@ -680,6 +843,7 @@ struct bpf_prog_load_attr {
 	int prog_flags;
 };
 
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__open() and bpf_object__load() instead")
 LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 				   struct bpf_object **pobj, int *prog_fd);
 LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__open() and bpf_object__load() instead")
@@ -702,13 +866,42 @@ struct bpf_xdp_set_link_opts {
 };
 #define bpf_xdp_set_link_opts__last_field old_fd
 
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_attach() instead")
 LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_attach() instead")
 LIBBPF_API int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags,
 					const struct bpf_xdp_set_link_opts *opts);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_query_id() instead")
 LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_query() instead")
 LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
 				     size_t info_size, __u32 flags);
 
+struct bpf_xdp_attach_opts {
+	size_t sz;
+	int old_prog_fd;
+	size_t :0;
+};
+#define bpf_xdp_attach_opts__last_field old_prog_fd
+
+struct bpf_xdp_query_opts {
+	size_t sz;
+	__u32 prog_id;		/* output */
+	__u32 drv_prog_id;	/* output */
+	__u32 hw_prog_id;	/* output */
+	__u32 skb_prog_id;	/* output */
+	__u8 attach_mode;	/* output */
+	size_t :0;
+};
+#define bpf_xdp_query_opts__last_field attach_mode
+
+LIBBPF_API int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags,
+			      const struct bpf_xdp_attach_opts *opts);
+LIBBPF_API int bpf_xdp_detach(int ifindex, __u32 flags,
+			      const struct bpf_xdp_attach_opts *opts);
+LIBBPF_API int bpf_xdp_query(int ifindex, int flags, struct bpf_xdp_query_opts *opts);
+LIBBPF_API int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id);
+
 /* TC related API */
 enum bpf_tc_attach_point {
 	BPF_TC_INGRESS = 1 << 0,
@@ -898,6 +1091,7 @@ LIBBPF_API int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_i
 typedef enum bpf_perf_event_ret
 	(*bpf_perf_event_print_t)(struct perf_event_header *hdr,
 				  void *private_data);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use perf_buffer__poll() or  perf_buffer__consume() instead")
 LIBBPF_API enum bpf_perf_event_ret
 bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
 			   void **copy_mem, size_t *copy_size,
@@ -924,13 +1118,57 @@ bpf_prog_linfo__lfind(const struct bpf_prog_linfo *prog_linfo,
  * user, causing subsequent probes to fail. In this case, the caller may want
  * to adjust that limit with setrlimit().
  */
-LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type,
-				    __u32 ifindex);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_prog_type() instead")
+LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_map_type() instead")
 LIBBPF_API bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex);
-LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id,
-				 enum bpf_prog_type prog_type, __u32 ifindex);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_helper() instead")
+LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type, __u32 ifindex);
+LIBBPF_DEPRECATED_SINCE(0, 8, "implement your own or use bpftool for feature detection")
 LIBBPF_API bool bpf_probe_large_insn_limit(__u32 ifindex);
 
+/**
+ * @brief **libbpf_probe_bpf_prog_type()** detects if host kernel supports
+ * BPF programs of a given type.
+ * @param prog_type BPF program type to detect kernel support for
+ * @param opts reserved for future extensibility, should be NULL
+ * @return 1, if given program type is supported; 0, if given program type is
+ * not supported; negative error code if feature detection failed or can't be
+ * performed
+ *
+ * Make sure the process has required set of CAP_* permissions (or runs as
+ * root) when performing feature checking.
+ */
+LIBBPF_API int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts);
+/**
+ * @brief **libbpf_probe_bpf_map_type()** detects if host kernel supports
+ * BPF maps of a given type.
+ * @param map_type BPF map type to detect kernel support for
+ * @param opts reserved for future extensibility, should be NULL
+ * @return 1, if given map type is supported; 0, if given map type is
+ * not supported; negative error code if feature detection failed or can't be
+ * performed
+ *
+ * Make sure the process has required set of CAP_* permissions (or runs as
+ * root) when performing feature checking.
+ */
+LIBBPF_API int libbpf_probe_bpf_map_type(enum bpf_map_type map_type, const void *opts);
+/**
+ * @brief **libbpf_probe_bpf_helper()** detects if host kernel supports the
+ * use of a given BPF helper from specified BPF program type.
+ * @param prog_type BPF program type used to check the support of BPF helper
+ * @param helper_id BPF helper ID (enum bpf_func_id) to check support for
+ * @param opts reserved for future extensibility, should be NULL
+ * @return 1, if given combination of program type and helper is supported; 0,
+ * if the combination is not supported; negative error code if feature
+ * detection for provided input arguments failed or can't be performed
+ *
+ * Make sure the process has required set of CAP_* permissions (or runs as
+ * root) when performing feature checking.
+ */
+LIBBPF_API int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type,
+				       enum bpf_func_id helper_id, const void *opts);
+
 /*
  * Get bpf_prog_info in continuous memory
  *
@@ -1035,11 +1273,11 @@ struct bpf_object_skeleton {
 	struct bpf_object **obj;
 
 	int map_cnt;
-	int map_skel_sz; /* sizeof(struct bpf_skeleton_map) */
+	int map_skel_sz; /* sizeof(struct bpf_map_skeleton) */
 	struct bpf_map_skeleton *maps;
 
 	int prog_cnt;
-	int prog_skel_sz; /* sizeof(struct bpf_skeleton_prog) */
+	int prog_skel_sz; /* sizeof(struct bpf_prog_skeleton) */
 	struct bpf_prog_skeleton *progs;
 };
 

src/libbpf.map

@@ -247,6 +247,7 @@ LIBBPF_0.0.8 {
 		bpf_link_create;
 		bpf_link_update;
 		bpf_map__set_initial_value;
+		bpf_prog_attach_opts;
 		bpf_program__attach_cgroup;
 		bpf_program__attach_lsm;
 		bpf_program__is_lsm;
@@ -419,3 +420,22 @@ LIBBPF_0.6.0 {
 		perf_buffer__new_raw;
 		perf_buffer__new_raw_deprecated;
 } LIBBPF_0.5.0;
+
+LIBBPF_0.7.0 {
+	global:
+		bpf_btf_load;
+		bpf_program__expected_attach_type;
+		bpf_program__log_buf;
+		bpf_program__log_level;
+		bpf_program__set_log_buf;
+		bpf_program__set_log_level;
+		bpf_program__type;
+		bpf_xdp_attach;
+		bpf_xdp_detach;
+		bpf_xdp_query;
+		bpf_xdp_query_id;
+		libbpf_probe_bpf_helper;
+		libbpf_probe_bpf_map_type;
+		libbpf_probe_bpf_prog_type;
+		libbpf_set_memlock_rlim_max;
+};

src/libbpf_common.h

@@ -40,6 +40,11 @@
 #else
 #define __LIBBPF_MARK_DEPRECATED_0_7(X)
 #endif
+#if __LIBBPF_CURRENT_VERSION_GEQ(0, 8)
+#define __LIBBPF_MARK_DEPRECATED_0_8(X) X
+#else
+#define __LIBBPF_MARK_DEPRECATED_0_8(X)
+#endif
 
 /* This set of internal macros allows to do "function overloading" based on
  * number of arguments provided by used in backwards-compatible way during the

src/libbpf_internal.h

@@ -92,6 +92,9 @@
 # define offsetofend(TYPE, FIELD) \
 	(offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD))
 #endif
+#ifndef __alias
+#define __alias(symbol) __attribute__((alias(#symbol)))
+#endif
 
 /* Check whether a string `str` has prefix `pfx`, regardless if `pfx` is
  * a string literal known at compilation time or char * pointer known only at
@@ -169,10 +172,31 @@ static inline void *libbpf_reallocarray(void *ptr, size_t nmemb, size_t size)
 	return realloc(ptr, total);
 }
 
+/* Copy up to sz - 1 bytes from zero-terminated src string and ensure that dst
+ * is zero-terminated string no matter what (unless sz == 0, in which case
+ * it's a no-op). It's conceptually close to FreeBSD's strlcpy(), but differs
+ * in what is returned. Given this is internal helper, it's trivial to extend
+ * this, when necessary. Use this instead of strncpy inside libbpf source code.
+ */
+static inline void libbpf_strlcpy(char *dst, const char *src, size_t sz)
+{
+	size_t i;
+
+	if (sz == 0)
+		return;
+
+	sz--;
+	for (i = 0; i < sz && src[i]; i++)
+		dst[i] = src[i];
+	dst[i] = '\0';
+}
+
+__u32 get_kernel_version(void);
+
 struct btf;
 struct btf_type;
 
-struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id);
+struct btf_type *btf_type_by_id(const struct btf *btf, __u32 type_id);
 const char *btf_kind_str(const struct btf_type *t);
 const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id);
 
@@ -272,11 +296,51 @@ static inline bool libbpf_validate_opts(const char *opts,
 					(opts)->sz - __off);		      \
 })
 
+enum kern_feature_id {
+	/* v4.14: kernel support for program & map names. */
+	FEAT_PROG_NAME,
+	/* v5.2: kernel support for global data sections. */
+	FEAT_GLOBAL_DATA,
+	/* BTF support */
+	FEAT_BTF,
+	/* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */
+	FEAT_BTF_FUNC,
+	/* BTF_KIND_VAR and BTF_KIND_DATASEC support */
+	FEAT_BTF_DATASEC,
+	/* BTF_FUNC_GLOBAL is supported */
+	FEAT_BTF_GLOBAL_FUNC,
+	/* BPF_F_MMAPABLE is supported for arrays */
+	FEAT_ARRAY_MMAP,
+	/* kernel support for expected_attach_type in BPF_PROG_LOAD */
+	FEAT_EXP_ATTACH_TYPE,
+	/* bpf_probe_read_{kernel,user}[_str] helpers */
+	FEAT_PROBE_READ_KERN,
+	/* BPF_PROG_BIND_MAP is supported */
+	FEAT_PROG_BIND_MAP,
+	/* Kernel support for module BTFs */
+	FEAT_MODULE_BTF,
+	/* BTF_KIND_FLOAT support */
+	FEAT_BTF_FLOAT,
+	/* BPF perf link support */
+	FEAT_PERF_LINK,
+	/* BTF_KIND_DECL_TAG support */
+	FEAT_BTF_DECL_TAG,
+	/* BTF_KIND_TYPE_TAG support */
+	FEAT_BTF_TYPE_TAG,
+	/* memcg-based accounting for BPF maps and progs */
+	FEAT_MEMCG_ACCOUNT,
+	__FEAT_CNT,
+};
+
+int probe_memcg_account(void);
+bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id);
+int bump_rlimit_memlock(void);
 
 int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz);
 int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz);
 int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
 			 const char *str_sec, size_t str_len);
+int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level);
 
 struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf);
 void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type,

src/libbpf_legacy.h

@@ -45,7 +45,6 @@ enum libbpf_strict_mode {
 	 * (positive) error code.
 	 */
 	LIBBPF_STRICT_DIRECT_ERRS = 0x02,
-
 	/*
 	 * Enforce strict BPF program section (SEC()) names.
 	 * E.g., while prefiously SEC("xdp_whatever") or SEC("perf_event_blah") were
@@ -63,6 +62,22 @@ enum libbpf_strict_mode {
 	 * Clients can maintain it on their own if it is valuable for them.
 	 */
 	LIBBPF_STRICT_NO_OBJECT_LIST = 0x08,
+	/*
+	 * Automatically bump RLIMIT_MEMLOCK using setrlimit() before the
+	 * first BPF program or map creation operation. This is done only if
+	 * kernel is too old to support memcg-based memory accounting for BPF
+	 * subsystem. By default, RLIMIT_MEMLOCK limit is set to RLIM_INFINITY,
+	 * but it can be overriden with libbpf_set_memlock_rlim_max() API.
+	 * Note that libbpf_set_memlock_rlim_max() needs to be called before
+	 * the very first bpf_prog_load(), bpf_map_create() or bpf_object__load()
+	 * operation.
+	 */
+	LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK = 0x10,
+	/*
+	 * Error out on any SEC("maps") map definition, which are deprecated
+	 * in favor of BTF-defined map definitions in SEC(".maps").
+	 */
+	LIBBPF_STRICT_MAP_DEFINITIONS = 0x20,
 
 	__LIBBPF_STRICT_LAST,
 };
@@ -71,6 +86,23 @@ LIBBPF_API int libbpf_set_strict_mode(enum libbpf_strict_mode mode);
 
 #define DECLARE_LIBBPF_OPTS LIBBPF_OPTS
 
+/* "Discouraged" APIs which don't follow consistent libbpf naming patterns.
+ * They are normally a trivial aliases or wrappers for proper APIs and are
+ * left to minimize unnecessary disruption for users of libbpf. But they
+ * shouldn't be used going forward.
+ */
+
+struct bpf_program;
+struct bpf_map;
+struct btf;
+struct btf_ext;
+
+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);
+LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size);
+LIBBPF_API const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, __u32 *size);
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif

src/libbpf_probes.c

@@ -48,28 +48,20 @@ static int get_vendor_id(int ifindex)
 	return strtol(buf, NULL, 0);
 }
 
-static int get_kernel_version(void)
+static int probe_prog_load(enum bpf_prog_type prog_type,
+			   const struct bpf_insn *insns, size_t insns_cnt,
+			   char *log_buf, size_t log_buf_sz,
+			   __u32 ifindex)
 {
-	int version, subversion, patchlevel;
-	struct utsname utsn;
-
-	/* Return 0 on failure, and attempt to probe with empty kversion */
-	if (uname(&utsn))
-		return 0;
-
-	if (sscanf(utsn.release, "%d.%d.%d",
-		   &version, &subversion, &patchlevel) != 3)
-		return 0;
-
-	return (version << 16) + (subversion << 8) + patchlevel;
-}
-
-static void
-probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
-	   size_t insns_cnt, char *buf, size_t buf_len, __u32 ifindex)
-{
-	LIBBPF_OPTS(bpf_prog_load_opts, opts);
-	int fd;
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		.log_buf = log_buf,
+		.log_size = log_buf_sz,
+		.log_level = log_buf ? 1 : 0,
+		.prog_ifindex = ifindex,
+	);
+	int fd, err, exp_err = 0;
+	const char *exp_msg = NULL;
+	char buf[4096];
 
 	switch (prog_type) {
 	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
@@ -84,6 +76,38 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
 	case BPF_PROG_TYPE_KPROBE:
 		opts.kern_version = get_kernel_version();
 		break;
+	case BPF_PROG_TYPE_LIRC_MODE2:
+		opts.expected_attach_type = BPF_LIRC_MODE2;
+		break;
+	case BPF_PROG_TYPE_TRACING:
+	case BPF_PROG_TYPE_LSM:
+		opts.log_buf = buf;
+		opts.log_size = sizeof(buf);
+		opts.log_level = 1;
+		if (prog_type == BPF_PROG_TYPE_TRACING)
+			opts.expected_attach_type = BPF_TRACE_FENTRY;
+		else
+			opts.expected_attach_type = BPF_MODIFY_RETURN;
+		opts.attach_btf_id = 1;
+
+		exp_err = -EINVAL;
+		exp_msg = "attach_btf_id 1 is not a function";
+		break;
+	case BPF_PROG_TYPE_EXT:
+		opts.log_buf = buf;
+		opts.log_size = sizeof(buf);
+		opts.log_level = 1;
+		opts.attach_btf_id = 1;
+
+		exp_err = -EINVAL;
+		exp_msg = "Cannot replace kernel functions";
+		break;
+	case BPF_PROG_TYPE_SYSCALL:
+		opts.prog_flags = BPF_F_SLEEPABLE;
+		break;
+	case BPF_PROG_TYPE_STRUCT_OPS:
+		exp_err = -524; /* -ENOTSUPP */
+		break;
 	case BPF_PROG_TYPE_UNSPEC:
 	case BPF_PROG_TYPE_SOCKET_FILTER:
 	case BPF_PROG_TYPE_SCHED_CLS:
@@ -103,25 +127,42 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
 	case BPF_PROG_TYPE_RAW_TRACEPOINT:
 	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
 	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
-	case BPF_PROG_TYPE_LIRC_MODE2:
 	case BPF_PROG_TYPE_SK_REUSEPORT:
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
-	case BPF_PROG_TYPE_TRACING:
-	case BPF_PROG_TYPE_STRUCT_OPS:
-	case BPF_PROG_TYPE_EXT:
-	case BPF_PROG_TYPE_LSM:
-	default:
 		break;
+	default:
+		return -EOPNOTSUPP;
 	}
 
-	opts.prog_ifindex = ifindex;
-	opts.log_buf = buf;
-	opts.log_size = buf_len;
-
-	fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, NULL);
+	fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, &opts);
+	err = -errno;
 	if (fd >= 0)
 		close(fd);
+	if (exp_err) {
+		if (fd >= 0 || err != exp_err)
+			return 0;
+		if (exp_msg && !strstr(buf, exp_msg))
+			return 0;
+		return 1;
+	}
+	return fd >= 0 ? 1 : 0;
+}
+
+int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts)
+{
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN()
+	};
+	const size_t insn_cnt = ARRAY_SIZE(insns);
+	int ret;
+
+	if (opts)
+		return libbpf_err(-EINVAL);
+
+	ret = probe_prog_load(prog_type, insns, insn_cnt, NULL, 0, 0);
+	return libbpf_err(ret);
 }
 
 bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex)
@@ -131,12 +172,16 @@ bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex)
 		BPF_EXIT_INSN()
 	};
 
+	/* prefer libbpf_probe_bpf_prog_type() unless offload is requested */
+	if (ifindex == 0)
+		return libbpf_probe_bpf_prog_type(prog_type, NULL) == 1;
+
 	if (ifindex && prog_type == BPF_PROG_TYPE_SCHED_CLS)
 		/* nfp returns -EINVAL on exit(0) with TC offload */
 		insns[0].imm = 2;
 
 	errno = 0;
-	probe_load(prog_type, insns, ARRAY_SIZE(insns), NULL, 0, ifindex);
+	probe_prog_load(prog_type, insns, ARRAY_SIZE(insns), NULL, 0, ifindex);
 
 	return errno != EINVAL && errno != EOPNOTSUPP;
 }
@@ -164,7 +209,7 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
 	memcpy(raw_btf + hdr.hdr_len, raw_types, hdr.type_len);
 	memcpy(raw_btf + hdr.hdr_len + hdr.type_len, str_sec, hdr.str_len);
 
-	btf_fd = bpf_load_btf(raw_btf, btf_len, NULL, 0, false);
+	btf_fd = bpf_btf_load(raw_btf, btf_len, NULL);
 
 	free(raw_btf);
 	return btf_fd;
@@ -197,16 +242,18 @@ static int load_local_storage_btf(void)
 				     strs, sizeof(strs));
 }
 
-bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
+static int probe_map_create(enum bpf_map_type map_type, __u32 ifindex)
 {
-	int key_size, value_size, max_entries, map_flags;
+	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;
+	int fd = -1, btf_fd = -1, fd_inner = -1, exp_err = 0, err;
+
+	opts.map_ifindex = ifindex;
 
 	key_size	= sizeof(__u32);
 	value_size	= sizeof(__u32);
 	max_entries	= 1;
-	map_flags	= 0;
 
 	switch (map_type) {
 	case BPF_MAP_TYPE_STACK_TRACE:
@@ -215,7 +262,7 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 	case BPF_MAP_TYPE_LPM_TRIE:
 		key_size	= sizeof(__u64);
 		value_size	= sizeof(__u64);
-		map_flags	= BPF_F_NO_PREALLOC;
+		opts.map_flags	= BPF_F_NO_PREALLOC;
 		break;
 	case BPF_MAP_TYPE_CGROUP_STORAGE:
 	case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE:
@@ -234,17 +281,25 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 		btf_value_type_id = 3;
 		value_size = 8;
 		max_entries = 0;
-		map_flags = BPF_F_NO_PREALLOC;
+		opts.map_flags = BPF_F_NO_PREALLOC;
 		btf_fd = load_local_storage_btf();
 		if (btf_fd < 0)
-			return false;
+			return btf_fd;
 		break;
 	case BPF_MAP_TYPE_RINGBUF:
 		key_size = 0;
 		value_size = 0;
 		max_entries = 4096;
 		break;
-	case BPF_MAP_TYPE_UNSPEC:
+	case BPF_MAP_TYPE_STRUCT_OPS:
+		/* we'll get -ENOTSUPP for invalid BTF type ID for struct_ops */
+		opts.btf_vmlinux_value_type_id = 1;
+		exp_err = -524; /* -ENOTSUPP */
+		break;
+	case BPF_MAP_TYPE_BLOOM_FILTER:
+		key_size = 0;
+		max_entries = 1;
+		break;
 	case BPF_MAP_TYPE_HASH:
 	case BPF_MAP_TYPE_ARRAY:
 	case BPF_MAP_TYPE_PROG_ARRAY:
@@ -263,49 +318,114 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 	case BPF_MAP_TYPE_XSKMAP:
 	case BPF_MAP_TYPE_SOCKHASH:
 	case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
-	case BPF_MAP_TYPE_STRUCT_OPS:
-	default:
 		break;
+	case BPF_MAP_TYPE_UNSPEC:
+	default:
+		return -EOPNOTSUPP;
 	}
 
 	if (map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
 	    map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
-		LIBBPF_OPTS(bpf_map_create_opts, opts);
-
 		/* TODO: probe for device, once libbpf has a function to create
 		 * map-in-map for offload
 		 */
 		if (ifindex)
-			return false;
+			goto cleanup;
 
 		fd_inner = bpf_map_create(BPF_MAP_TYPE_HASH, NULL,
 					  sizeof(__u32), sizeof(__u32), 1, NULL);
 		if (fd_inner < 0)
-			return false;
+			goto cleanup;
 
 		opts.inner_map_fd = fd_inner;
-		fd = bpf_map_create(map_type, NULL, sizeof(__u32), sizeof(__u32), 1, &opts);
-		close(fd_inner);
-	} else {
-		LIBBPF_OPTS(bpf_map_create_opts, opts);
-
-		/* Note: No other restriction on map type probes for offload */
-		opts.map_flags = map_flags;
-		opts.map_ifindex = ifindex;
-		if (btf_fd >= 0) {
-			opts.btf_fd = btf_fd;
-			opts.btf_key_type_id = btf_key_type_id;
-			opts.btf_value_type_id = btf_value_type_id;
-		}
-
-		fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries, &opts);
 	}
+
+	if (btf_fd >= 0) {
+		opts.btf_fd = btf_fd;
+		opts.btf_key_type_id = btf_key_type_id;
+		opts.btf_value_type_id = btf_value_type_id;
+	}
+
+	fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries, &opts);
+	err = -errno;
+
+cleanup:
 	if (fd >= 0)
 		close(fd);
+	if (fd_inner >= 0)
+		close(fd_inner);
 	if (btf_fd >= 0)
 		close(btf_fd);
 
-	return fd >= 0;
+	if (exp_err)
+		return fd < 0 && err == exp_err ? 1 : 0;
+	else
+		return fd >= 0 ? 1 : 0;
+}
+
+int libbpf_probe_bpf_map_type(enum bpf_map_type map_type, const void *opts)
+{
+	int ret;
+
+	if (opts)
+		return libbpf_err(-EINVAL);
+
+	ret = probe_map_create(map_type, 0);
+	return libbpf_err(ret);
+}
+
+bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
+{
+	return probe_map_create(map_type, ifindex) == 1;
+}
+
+int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, enum bpf_func_id helper_id,
+			    const void *opts)
+{
+	struct bpf_insn insns[] = {
+		BPF_EMIT_CALL((__u32)helper_id),
+		BPF_EXIT_INSN(),
+	};
+	const size_t insn_cnt = ARRAY_SIZE(insns);
+	char buf[4096];
+	int ret;
+
+	if (opts)
+		return libbpf_err(-EINVAL);
+
+	/* we can't successfully load all prog types to check for BPF helper
+	 * support, so bail out with -EOPNOTSUPP error
+	 */
+	switch (prog_type) {
+	case BPF_PROG_TYPE_TRACING:
+	case BPF_PROG_TYPE_EXT:
+	case BPF_PROG_TYPE_LSM:
+	case BPF_PROG_TYPE_STRUCT_OPS:
+		return -EOPNOTSUPP;
+	default:
+		break;
+	}
+
+	buf[0] = '\0';
+	ret = probe_prog_load(prog_type, insns, insn_cnt, buf, sizeof(buf), 0);
+	if (ret < 0)
+		return libbpf_err(ret);
+
+	/* If BPF verifier doesn't recognize BPF helper ID (enum bpf_func_id)
+	 * at all, it will emit something like "invalid func unknown#181".
+	 * If BPF verifier recognizes BPF helper but it's not supported for
+	 * given BPF program type, it will emit "unknown func bpf_sys_bpf#166".
+	 * In both cases, provided combination of BPF program type and BPF
+	 * helper is not supported by the kernel.
+	 * In all other cases, probe_prog_load() above will either succeed (e.g.,
+	 * because BPF helper happens to accept no input arguments or it
+	 * accepts one input argument and initial PTR_TO_CTX is fine for
+	 * that), or we'll get some more specific BPF verifier error about
+	 * some unsatisfied conditions.
+	 */
+	if (ret == 0 && (strstr(buf, "invalid func ") || strstr(buf, "unknown func ")))
+		return 0;
+	return 1; /* assume supported */
 }
 
 bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type,
@@ -318,8 +438,7 @@ bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type,
 	char buf[4096] = {};
 	bool res;
 
-	probe_load(prog_type, insns, ARRAY_SIZE(insns), buf, sizeof(buf),
-		   ifindex);
+	probe_prog_load(prog_type, insns, ARRAY_SIZE(insns), buf, sizeof(buf), ifindex);
 	res = !grep(buf, "invalid func ") && !grep(buf, "unknown func ");
 
 	if (ifindex) {
@@ -351,8 +470,8 @@ bool bpf_probe_large_insn_limit(__u32 ifindex)
 	insns[BPF_MAXINSNS] = BPF_EXIT_INSN();
 
 	errno = 0;
-	probe_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0,
-		   ifindex);
+	probe_prog_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0,
+			ifindex);
 
 	return errno != E2BIG && errno != EINVAL;
 }

src/libbpf_version.h

@@ -4,6 +4,6 @@
 #define __LIBBPF_VERSION_H
 
 #define LIBBPF_MAJOR_VERSION 0
-#define LIBBPF_MINOR_VERSION 6
+#define LIBBPF_MINOR_VERSION 7
 
 #endif /* __LIBBPF_VERSION_H */

src/netlink.c

@@ -217,6 +217,28 @@ static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd,
 	return libbpf_netlink_send_recv(&req, NULL, NULL, NULL);
 }
 
+int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts)
+{
+	int old_prog_fd, err;
+
+	if (!OPTS_VALID(opts, bpf_xdp_attach_opts))
+		return libbpf_err(-EINVAL);
+
+	old_prog_fd = OPTS_GET(opts, old_prog_fd, 0);
+	if (old_prog_fd)
+		flags |= XDP_FLAGS_REPLACE;
+	else
+		old_prog_fd = -1;
+
+	err = __bpf_set_link_xdp_fd_replace(ifindex, prog_fd, old_prog_fd, flags);
+	return libbpf_err(err);
+}
+
+int bpf_xdp_detach(int ifindex, __u32 flags, const struct bpf_xdp_attach_opts *opts)
+{
+	return bpf_xdp_attach(ifindex, -1, flags, opts);
+}
+
 int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags,
 			     const struct bpf_xdp_set_link_opts *opts)
 {
@@ -303,69 +325,98 @@ static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb)
 	return 0;
 }
 
-int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
-			  size_t info_size, __u32 flags)
+int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
 {
-	struct xdp_id_md xdp_id = {};
-	__u32 mask;
-	int ret;
 	struct libbpf_nla_req req = {
 		.nh.nlmsg_len      = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
 		.nh.nlmsg_type     = RTM_GETLINK,
 		.nh.nlmsg_flags    = NLM_F_DUMP | NLM_F_REQUEST,
 		.ifinfo.ifi_family = AF_PACKET,
 	};
+	struct xdp_id_md xdp_id = {};
+	int err;
 
-	if (flags & ~XDP_FLAGS_MASK || !info_size)
+	if (!OPTS_VALID(opts, bpf_xdp_query_opts))
+		return libbpf_err(-EINVAL);
+
+	if (xdp_flags & ~XDP_FLAGS_MASK)
 		return libbpf_err(-EINVAL);
 
 	/* Check whether the single {HW,DRV,SKB} mode is set */
-	flags &= (XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE);
-	mask = flags - 1;
-	if (flags && flags & mask)
+	xdp_flags &= XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE;
+	if (xdp_flags & (xdp_flags - 1))
 		return libbpf_err(-EINVAL);
 
 	xdp_id.ifindex = ifindex;
-	xdp_id.flags = flags;
+	xdp_id.flags = xdp_flags;
 
-	ret = libbpf_netlink_send_recv(&req, __dump_link_nlmsg,
+	err = libbpf_netlink_send_recv(&req, __dump_link_nlmsg,
 				       get_xdp_info, &xdp_id);
-	if (!ret) {
-		size_t sz = min(info_size, sizeof(xdp_id.info));
+	if (err)
+		return libbpf_err(err);
 
-		memcpy(info, &xdp_id.info, sz);
-		memset((void *) info + sz, 0, info_size - sz);
-	}
-
-	return libbpf_err(ret);
-}
-
-static __u32 get_xdp_id(struct xdp_link_info *info, __u32 flags)
-{
-	flags &= XDP_FLAGS_MODES;
-
-	if (info->attach_mode != XDP_ATTACHED_MULTI && !flags)
-		return info->prog_id;
-	if (flags & XDP_FLAGS_DRV_MODE)
-		return info->drv_prog_id;
-	if (flags & XDP_FLAGS_HW_MODE)
-		return info->hw_prog_id;
-	if (flags & XDP_FLAGS_SKB_MODE)
-		return info->skb_prog_id;
+	OPTS_SET(opts, prog_id, xdp_id.info.prog_id);
+	OPTS_SET(opts, drv_prog_id, xdp_id.info.drv_prog_id);
+	OPTS_SET(opts, hw_prog_id, xdp_id.info.hw_prog_id);
+	OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id);
+	OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode);
 
 	return 0;
 }
 
-int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags)
+int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
+			  size_t info_size, __u32 flags)
 {
-	struct xdp_link_info info;
+	LIBBPF_OPTS(bpf_xdp_query_opts, opts);
+	size_t sz;
+	int err;
+
+	if (!info_size)
+		return libbpf_err(-EINVAL);
+
+	err = bpf_xdp_query(ifindex, flags, &opts);
+	if (err)
+		return libbpf_err(err);
+
+	/* struct xdp_link_info field layout matches struct bpf_xdp_query_opts
+	 * layout after sz field
+	 */
+	sz = min(info_size, offsetofend(struct xdp_link_info, attach_mode));
+	memcpy(info, &opts.prog_id, sz);
+	memset((void *)info + sz, 0, info_size - sz);
+
+	return 0;
+}
+
+int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id)
+{
+	LIBBPF_OPTS(bpf_xdp_query_opts, opts);
 	int ret;
 
-	ret = bpf_get_link_xdp_info(ifindex, &info, sizeof(info), flags);
-	if (!ret)
-		*prog_id = get_xdp_id(&info, flags);
+	ret = bpf_xdp_query(ifindex, flags, &opts);
+	if (ret)
+		return libbpf_err(ret);
 
-	return libbpf_err(ret);
+	flags &= XDP_FLAGS_MODES;
+
+	if (opts.attach_mode != XDP_ATTACHED_MULTI && !flags)
+		*prog_id = opts.prog_id;
+	else if (flags & XDP_FLAGS_DRV_MODE)
+		*prog_id = opts.drv_prog_id;
+	else if (flags & XDP_FLAGS_HW_MODE)
+		*prog_id = opts.hw_prog_id;
+	else if (flags & XDP_FLAGS_SKB_MODE)
+		*prog_id = opts.skb_prog_id;
+	else
+		*prog_id = 0;
+
+	return 0;
+}
+
+
+int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags)
+{
+	return bpf_xdp_query_id(ifindex, flags, prog_id);
 }
 
 typedef int (*qdisc_config_t)(struct libbpf_nla_req *req);

src/relo_core.c

@@ -1,6 +1,60 @@
 // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 /* Copyright (c) 2019 Facebook */
 
+#ifdef __KERNEL__
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/string.h>
+#include <linux/bpf_verifier.h>
+#include "relo_core.h"
+
+static const char *btf_kind_str(const struct btf_type *t)
+{
+	return btf_type_str(t);
+}
+
+static bool is_ldimm64_insn(struct bpf_insn *insn)
+{
+	return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
+}
+
+static const struct btf_type *
+skip_mods_and_typedefs(const struct btf *btf, u32 id, u32 *res_id)
+{
+	return btf_type_skip_modifiers(btf, id, res_id);
+}
+
+static const char *btf__name_by_offset(const struct btf *btf, u32 offset)
+{
+	return btf_name_by_offset(btf, offset);
+}
+
+static s64 btf__resolve_size(const struct btf *btf, u32 type_id)
+{
+	const struct btf_type *t;
+	int size;
+
+	t = btf_type_by_id(btf, type_id);
+	t = btf_resolve_size(btf, t, &size);
+	if (IS_ERR(t))
+		return PTR_ERR(t);
+	return size;
+}
+
+enum libbpf_print_level {
+	LIBBPF_WARN,
+	LIBBPF_INFO,
+	LIBBPF_DEBUG,
+};
+
+#undef pr_warn
+#undef pr_info
+#undef pr_debug
+#define pr_warn(fmt, log, ...)	bpf_log((void *)log, fmt, "", ##__VA_ARGS__)
+#define pr_info(fmt, log, ...)	bpf_log((void *)log, fmt, "", ##__VA_ARGS__)
+#define pr_debug(fmt, log, ...)	bpf_log((void *)log, fmt, "", ##__VA_ARGS__)
+#define libbpf_print(level, fmt, ...)	bpf_log((void *)prog_name, fmt, ##__VA_ARGS__)
+#else
 #include <stdio.h>
 #include <string.h>
 #include <errno.h>
@@ -12,33 +66,7 @@
 #include "btf.h"
 #include "str_error.h"
 #include "libbpf_internal.h"
-
-#define BPF_CORE_SPEC_MAX_LEN 64
-
-/* represents BPF CO-RE field or array element accessor */
-struct bpf_core_accessor {
-	__u32 type_id;		/* struct/union type or array element type */
-	__u32 idx;		/* field index or array index */
-	const char *name;	/* field name or NULL for array accessor */
-};
-
-struct bpf_core_spec {
-	const struct btf *btf;
-	/* high-level spec: named fields and array indices only */
-	struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN];
-	/* original unresolved (no skip_mods_or_typedefs) root type ID */
-	__u32 root_type_id;
-	/* CO-RE relocation kind */
-	enum bpf_core_relo_kind relo_kind;
-	/* high-level spec length */
-	int len;
-	/* raw, low-level spec: 1-to-1 with accessor spec string */
-	int raw_spec[BPF_CORE_SPEC_MAX_LEN];
-	/* raw spec length */
-	int raw_len;
-	/* field bit offset represented by spec */
-	__u32 bit_offset;
-};
+#endif
 
 static bool is_flex_arr(const struct btf *btf,
 			const struct bpf_core_accessor *acc,
@@ -51,25 +79,25 @@ static bool is_flex_arr(const struct btf *btf,
 		return false;
 
 	/* has to be the last member of enclosing struct */
-	t = btf__type_by_id(btf, acc->type_id);
+	t = btf_type_by_id(btf, acc->type_id);
 	return acc->idx == btf_vlen(t) - 1;
 }
 
 static const char *core_relo_kind_str(enum bpf_core_relo_kind kind)
 {
 	switch (kind) {
-	case BPF_FIELD_BYTE_OFFSET: return "byte_off";
-	case BPF_FIELD_BYTE_SIZE: return "byte_sz";
-	case BPF_FIELD_EXISTS: return "field_exists";
-	case BPF_FIELD_SIGNED: return "signed";
-	case BPF_FIELD_LSHIFT_U64: return "lshift_u64";
-	case BPF_FIELD_RSHIFT_U64: return "rshift_u64";
-	case BPF_TYPE_ID_LOCAL: return "local_type_id";
-	case BPF_TYPE_ID_TARGET: return "target_type_id";
-	case BPF_TYPE_EXISTS: return "type_exists";
-	case BPF_TYPE_SIZE: return "type_size";
-	case BPF_ENUMVAL_EXISTS: return "enumval_exists";
-	case BPF_ENUMVAL_VALUE: return "enumval_value";
+	case BPF_CORE_FIELD_BYTE_OFFSET: return "byte_off";
+	case BPF_CORE_FIELD_BYTE_SIZE: return "byte_sz";
+	case BPF_CORE_FIELD_EXISTS: return "field_exists";
+	case BPF_CORE_FIELD_SIGNED: return "signed";
+	case BPF_CORE_FIELD_LSHIFT_U64: return "lshift_u64";
+	case BPF_CORE_FIELD_RSHIFT_U64: return "rshift_u64";
+	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_SIZE: return "type_size";
+	case BPF_CORE_ENUMVAL_EXISTS: return "enumval_exists";
+	case BPF_CORE_ENUMVAL_VALUE: return "enumval_value";
 	default: return "unknown";
 	}
 }
@@ -77,12 +105,12 @@ static const char *core_relo_kind_str(enum bpf_core_relo_kind kind)
 static bool core_relo_is_field_based(enum bpf_core_relo_kind kind)
 {
 	switch (kind) {
-	case BPF_FIELD_BYTE_OFFSET:
-	case BPF_FIELD_BYTE_SIZE:
-	case BPF_FIELD_EXISTS:
-	case BPF_FIELD_SIGNED:
-	case BPF_FIELD_LSHIFT_U64:
-	case BPF_FIELD_RSHIFT_U64:
+	case BPF_CORE_FIELD_BYTE_OFFSET:
+	case BPF_CORE_FIELD_BYTE_SIZE:
+	case BPF_CORE_FIELD_EXISTS:
+	case BPF_CORE_FIELD_SIGNED:
+	case BPF_CORE_FIELD_LSHIFT_U64:
+	case BPF_CORE_FIELD_RSHIFT_U64:
 		return true;
 	default:
 		return false;
@@ -92,10 +120,10 @@ static bool core_relo_is_field_based(enum bpf_core_relo_kind kind)
 static bool core_relo_is_type_based(enum bpf_core_relo_kind kind)
 {
 	switch (kind) {
-	case BPF_TYPE_ID_LOCAL:
-	case BPF_TYPE_ID_TARGET:
-	case BPF_TYPE_EXISTS:
-	case BPF_TYPE_SIZE:
+	case BPF_CORE_TYPE_ID_LOCAL:
+	case BPF_CORE_TYPE_ID_TARGET:
+	case BPF_CORE_TYPE_EXISTS:
+	case BPF_CORE_TYPE_SIZE:
 		return true;
 	default:
 		return false;
@@ -105,8 +133,8 @@ static bool core_relo_is_type_based(enum bpf_core_relo_kind kind)
 static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind)
 {
 	switch (kind) {
-	case BPF_ENUMVAL_EXISTS:
-	case BPF_ENUMVAL_VALUE:
+	case BPF_CORE_ENUMVAL_EXISTS:
+	case BPF_CORE_ENUMVAL_VALUE:
 		return true;
 	default:
 		return false;
@@ -150,7 +178,7 @@ static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind)
  * Enum value-based relocations (ENUMVAL_EXISTS/ENUMVAL_VALUE) use access
  * string to specify enumerator's value index that need to be relocated.
  */
-static int bpf_core_parse_spec(const struct btf *btf,
+static int bpf_core_parse_spec(const char *prog_name, const struct btf *btf,
 			       __u32 type_id,
 			       const char *spec_str,
 			       enum bpf_core_relo_kind relo_kind,
@@ -272,8 +300,8 @@ static int bpf_core_parse_spec(const struct btf *btf,
 				return sz;
 			spec->bit_offset += access_idx * sz * 8;
 		} else {
-			pr_warn("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %s\n",
-				type_id, spec_str, i, id, btf_kind_str(t));
+			pr_warn("prog '%s': relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %s\n",
+				prog_name, type_id, spec_str, i, id, btf_kind_str(t));
 			return -EINVAL;
 		}
 	}
@@ -346,8 +374,6 @@ recur:
 		targ_id = btf_array(targ_type)->type;
 		goto recur;
 	default:
-		pr_warn("unexpected kind %d relocated, local [%d], target [%d]\n",
-			btf_kind(local_type), local_id, targ_id);
 		return 0;
 	}
 }
@@ -388,7 +414,7 @@ static int bpf_core_match_member(const struct btf *local_btf,
 		return 0;
 
 	local_id = local_acc->type_id;
-	local_type = btf__type_by_id(local_btf, local_id);
+	local_type = btf_type_by_id(local_btf, local_id);
 	local_member = btf_members(local_type) + local_acc->idx;
 	local_name = btf__name_by_offset(local_btf, local_member->name_off);
 
@@ -571,7 +597,7 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 
 	*field_sz = 0;
 
-	if (relo->kind == BPF_FIELD_EXISTS) {
+	if (relo->kind == BPF_CORE_FIELD_EXISTS) {
 		*val = spec ? 1 : 0;
 		return 0;
 	}
@@ -580,11 +606,11 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 		return -EUCLEAN; /* request instruction poisoning */
 
 	acc = &spec->spec[spec->len - 1];
-	t = btf__type_by_id(spec->btf, acc->type_id);
+	t = btf_type_by_id(spec->btf, acc->type_id);
 
 	/* a[n] accessor needs special handling */
 	if (!acc->name) {
-		if (relo->kind == BPF_FIELD_BYTE_OFFSET) {
+		if (relo->kind == BPF_CORE_FIELD_BYTE_OFFSET) {
 			*val = spec->bit_offset / 8;
 			/* remember field size for load/store mem size */
 			sz = btf__resolve_size(spec->btf, acc->type_id);
@@ -592,7 +618,7 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 				return -EINVAL;
 			*field_sz = sz;
 			*type_id = acc->type_id;
-		} else if (relo->kind == BPF_FIELD_BYTE_SIZE) {
+		} else if (relo->kind == BPF_CORE_FIELD_BYTE_SIZE) {
 			sz = btf__resolve_size(spec->btf, acc->type_id);
 			if (sz < 0)
 				return -EINVAL;
@@ -644,36 +670,36 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 		*validate = !bitfield;
 
 	switch (relo->kind) {
-	case BPF_FIELD_BYTE_OFFSET:
+	case BPF_CORE_FIELD_BYTE_OFFSET:
 		*val = byte_off;
 		if (!bitfield) {
 			*field_sz = byte_sz;
 			*type_id = field_type_id;
 		}
 		break;
-	case BPF_FIELD_BYTE_SIZE:
+	case BPF_CORE_FIELD_BYTE_SIZE:
 		*val = byte_sz;
 		break;
-	case BPF_FIELD_SIGNED:
+	case BPF_CORE_FIELD_SIGNED:
 		/* enums will be assumed unsigned */
 		*val = btf_is_enum(mt) ||
 		       (btf_int_encoding(mt) & BTF_INT_SIGNED);
 		if (validate)
 			*validate = true; /* signedness is never ambiguous */
 		break;
-	case BPF_FIELD_LSHIFT_U64:
+	case BPF_CORE_FIELD_LSHIFT_U64:
 #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 		*val = 64 - (bit_off + bit_sz - byte_off  * 8);
 #else
 		*val = (8 - byte_sz) * 8 + (bit_off - byte_off * 8);
 #endif
 		break;
-	case BPF_FIELD_RSHIFT_U64:
+	case BPF_CORE_FIELD_RSHIFT_U64:
 		*val = 64 - bit_sz;
 		if (validate)
 			*validate = true; /* right shift is never ambiguous */
 		break;
-	case BPF_FIELD_EXISTS:
+	case BPF_CORE_FIELD_EXISTS:
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -683,10 +709,14 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 
 static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo,
 				   const struct bpf_core_spec *spec,
-				   __u32 *val)
+				   __u32 *val, bool *validate)
 {
 	__s64 sz;
 
+	/* by default, always check expected value in bpf_insn */
+	if (validate)
+		*validate = true;
+
 	/* type-based relos return zero when target type is not found */
 	if (!spec) {
 		*val = 0;
@@ -694,20 +724,25 @@ static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo,
 	}
 
 	switch (relo->kind) {
-	case BPF_TYPE_ID_TARGET:
+	case BPF_CORE_TYPE_ID_TARGET:
 		*val = spec->root_type_id;
+		/* type ID, embedded in bpf_insn, might change during linking,
+		 * so enforcing it is pointless
+		 */
+		if (validate)
+			*validate = false;
 		break;
-	case BPF_TYPE_EXISTS:
+	case BPF_CORE_TYPE_EXISTS:
 		*val = 1;
 		break;
-	case BPF_TYPE_SIZE:
+	case BPF_CORE_TYPE_SIZE:
 		sz = btf__resolve_size(spec->btf, spec->root_type_id);
 		if (sz < 0)
 			return -EINVAL;
 		*val = sz;
 		break;
-	case BPF_TYPE_ID_LOCAL:
-	/* BPF_TYPE_ID_LOCAL is handled specially and shouldn't get here */
+	case BPF_CORE_TYPE_ID_LOCAL:
+	/* BPF_CORE_TYPE_ID_LOCAL is handled specially and shouldn't get here */
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -723,13 +758,13 @@ static int bpf_core_calc_enumval_relo(const struct bpf_core_relo *relo,
 	const struct btf_enum *e;
 
 	switch (relo->kind) {
-	case BPF_ENUMVAL_EXISTS:
+	case BPF_CORE_ENUMVAL_EXISTS:
 		*val = spec ? 1 : 0;
 		break;
-	case BPF_ENUMVAL_VALUE:
+	case BPF_CORE_ENUMVAL_VALUE:
 		if (!spec)
 			return -EUCLEAN; /* request instruction poisoning */
-		t = btf__type_by_id(spec->btf, spec->spec[0].type_id);
+		t = btf_type_by_id(spec->btf, spec->spec[0].type_id);
 		e = btf_enum(t) + spec->spec[0].idx;
 		*val = e->val;
 		break;
@@ -805,8 +840,8 @@ static int bpf_core_calc_relo(const char *prog_name,
 		if (res->orig_sz != res->new_sz) {
 			const struct btf_type *orig_t, *new_t;
 
-			orig_t = btf__type_by_id(local_spec->btf, res->orig_type_id);
-			new_t = btf__type_by_id(targ_spec->btf, res->new_type_id);
+			orig_t = btf_type_by_id(local_spec->btf, res->orig_type_id);
+			new_t = btf_type_by_id(targ_spec->btf, res->new_type_id);
 
 			/* There are two use cases in which it's safe to
 			 * adjust load/store's mem size:
@@ -835,8 +870,8 @@ static int bpf_core_calc_relo(const char *prog_name,
 			res->fail_memsz_adjust = true;
 		}
 	} else if (core_relo_is_type_based(relo->kind)) {
-		err = bpf_core_calc_type_relo(relo, local_spec, &res->orig_val);
-		err = err ?: bpf_core_calc_type_relo(relo, targ_spec, &res->new_val);
+		err = bpf_core_calc_type_relo(relo, local_spec, &res->orig_val, &res->validate);
+		err = err ?: bpf_core_calc_type_relo(relo, targ_spec, &res->new_val, NULL);
 	} else if (core_relo_is_enumval_based(relo->kind)) {
 		err = bpf_core_calc_enumval_relo(relo, local_spec, &res->orig_val);
 		err = err ?: bpf_core_calc_enumval_relo(relo, targ_spec, &res->new_val);
@@ -1045,7 +1080,7 @@ poison:
  * [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>,
  * where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b
  */
-static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec)
+static void bpf_core_dump_spec(const char *prog_name, int level, const struct bpf_core_spec *spec)
 {
 	const struct btf_type *t;
 	const struct btf_enum *e;
@@ -1054,7 +1089,7 @@ static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec)
 	int i;
 
 	type_id = spec->root_type_id;
-	t = btf__type_by_id(spec->btf, type_id);
+	t = btf_type_by_id(spec->btf, type_id);
 	s = btf__name_by_offset(spec->btf, t->name_off);
 
 	libbpf_print(level, "[%u] %s %s", type_id, btf_kind_str(t), str_is_empty(s) ? "<anon>" : s);
@@ -1147,9 +1182,12 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 			     const struct bpf_core_relo *relo,
 			     int relo_idx,
 			     const struct btf *local_btf,
-			     struct bpf_core_cand_list *cands)
+			     struct bpf_core_cand_list *cands,
+			     struct bpf_core_spec *specs_scratch)
 {
-	struct bpf_core_spec local_spec, cand_spec, targ_spec = {};
+	struct bpf_core_spec *local_spec = &specs_scratch[0];
+	struct bpf_core_spec *cand_spec = &specs_scratch[1];
+	struct bpf_core_spec *targ_spec = &specs_scratch[2];
 	struct bpf_core_relo_res cand_res, targ_res;
 	const struct btf_type *local_type;
 	const char *local_name;
@@ -1158,10 +1196,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 	int i, j, err;
 
 	local_id = relo->type_id;
-	local_type = btf__type_by_id(local_btf, local_id);
-	if (!local_type)
-		return -EINVAL;
-
+	local_type = btf_type_by_id(local_btf, local_id);
 	local_name = btf__name_by_offset(local_btf, local_type->name_off);
 	if (!local_name)
 		return -EINVAL;
@@ -1170,7 +1205,8 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 	if (str_is_empty(spec_str))
 		return -EINVAL;
 
-	err = bpf_core_parse_spec(local_btf, local_id, spec_str, relo->kind, &local_spec);
+	err = bpf_core_parse_spec(prog_name, local_btf, local_id, spec_str,
+				  relo->kind, local_spec);
 	if (err) {
 		pr_warn("prog '%s': relo #%d: parsing [%d] %s %s + %s failed: %d\n",
 			prog_name, relo_idx, local_id, btf_kind_str(local_type),
@@ -1181,15 +1217,17 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 
 	pr_debug("prog '%s': relo #%d: kind <%s> (%d), spec is ", prog_name,
 		 relo_idx, core_relo_kind_str(relo->kind), relo->kind);
-	bpf_core_dump_spec(LIBBPF_DEBUG, &local_spec);
+	bpf_core_dump_spec(prog_name, LIBBPF_DEBUG, local_spec);
 	libbpf_print(LIBBPF_DEBUG, "\n");
 
 	/* TYPE_ID_LOCAL relo is special and doesn't need candidate search */
-	if (relo->kind == BPF_TYPE_ID_LOCAL) {
-		targ_res.validate = true;
+	if (relo->kind == BPF_CORE_TYPE_ID_LOCAL) {
+		/* bpf_insn's imm value could get out of sync during linking */
+		memset(&targ_res, 0, sizeof(targ_res));
+		targ_res.validate = false;
 		targ_res.poison = false;
-		targ_res.orig_val = local_spec.root_type_id;
-		targ_res.new_val = local_spec.root_type_id;
+		targ_res.orig_val = local_spec->root_type_id;
+		targ_res.new_val = local_spec->root_type_id;
 		goto patch_insn;
 	}
 
@@ -1200,40 +1238,39 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 		return -EOPNOTSUPP;
 	}
 
-
 	for (i = 0, j = 0; i < cands->len; i++) {
-		err = bpf_core_spec_match(&local_spec, cands->cands[i].btf,
-					  cands->cands[i].id, &cand_spec);
+		err = bpf_core_spec_match(local_spec, cands->cands[i].btf,
+					  cands->cands[i].id, cand_spec);
 		if (err < 0) {
 			pr_warn("prog '%s': relo #%d: error matching candidate #%d ",
 				prog_name, relo_idx, i);
-			bpf_core_dump_spec(LIBBPF_WARN, &cand_spec);
+			bpf_core_dump_spec(prog_name, LIBBPF_WARN, cand_spec);
 			libbpf_print(LIBBPF_WARN, ": %d\n", err);
 			return err;
 		}
 
 		pr_debug("prog '%s': relo #%d: %s candidate #%d ", prog_name,
 			 relo_idx, err == 0 ? "non-matching" : "matching", i);
-		bpf_core_dump_spec(LIBBPF_DEBUG, &cand_spec);
+		bpf_core_dump_spec(prog_name, LIBBPF_DEBUG, cand_spec);
 		libbpf_print(LIBBPF_DEBUG, "\n");
 
 		if (err == 0)
 			continue;
 
-		err = bpf_core_calc_relo(prog_name, relo, relo_idx, &local_spec, &cand_spec, &cand_res);
+		err = bpf_core_calc_relo(prog_name, relo, relo_idx, local_spec, cand_spec, &cand_res);
 		if (err)
 			return err;
 
 		if (j == 0) {
 			targ_res = cand_res;
-			targ_spec = cand_spec;
-		} else if (cand_spec.bit_offset != targ_spec.bit_offset) {
+			*targ_spec = *cand_spec;
+		} else if (cand_spec->bit_offset != targ_spec->bit_offset) {
 			/* if there are many field relo candidates, they
 			 * should all resolve to the same bit offset
 			 */
 			pr_warn("prog '%s': relo #%d: field offset ambiguity: %u != %u\n",
-				prog_name, relo_idx, cand_spec.bit_offset,
-				targ_spec.bit_offset);
+				prog_name, relo_idx, cand_spec->bit_offset,
+				targ_spec->bit_offset);
 			return -EINVAL;
 		} else if (cand_res.poison != targ_res.poison || cand_res.new_val != targ_res.new_val) {
 			/* all candidates should result in the same relocation
@@ -1251,7 +1288,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 	}
 
 	/*
-	 * For BPF_FIELD_EXISTS relo or when used BPF program has field
+	 * For BPF_CORE_FIELD_EXISTS relo or when used BPF program has field
 	 * existence checks or kernel version/config checks, it's expected
 	 * that we might not find any candidates. In this case, if field
 	 * wasn't found in any candidate, the list of candidates shouldn't
@@ -1277,7 +1314,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 			 prog_name, relo_idx);
 
 		/* calculate single target relo result explicitly */
-		err = bpf_core_calc_relo(prog_name, relo, relo_idx, &local_spec, NULL, &targ_res);
+		err = bpf_core_calc_relo(prog_name, relo, relo_idx, local_spec, NULL, &targ_res);
 		if (err)
 			return err;
 	}

src/relo_core.h

@@ -4,81 +4,10 @@
 #ifndef __RELO_CORE_H
 #define __RELO_CORE_H
 
-/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value
- * has to be adjusted by relocations.
- */
-enum bpf_core_relo_kind {
-	BPF_FIELD_BYTE_OFFSET = 0,	/* field byte offset */
-	BPF_FIELD_BYTE_SIZE = 1,	/* field size in bytes */
-	BPF_FIELD_EXISTS = 2,		/* field existence in target kernel */
-	BPF_FIELD_SIGNED = 3,		/* field signedness (0 - unsigned, 1 - signed) */
-	BPF_FIELD_LSHIFT_U64 = 4,	/* bitfield-specific left bitshift */
-	BPF_FIELD_RSHIFT_U64 = 5,	/* bitfield-specific right bitshift */
-	BPF_TYPE_ID_LOCAL = 6,		/* type ID in local BPF object */
-	BPF_TYPE_ID_TARGET = 7,		/* type ID in target kernel */
-	BPF_TYPE_EXISTS = 8,		/* type existence in target kernel */
-	BPF_TYPE_SIZE = 9,		/* type size in bytes */
-	BPF_ENUMVAL_EXISTS = 10,	/* enum value existence in target kernel */
-	BPF_ENUMVAL_VALUE = 11,		/* enum value integer value */
-};
-
-/* The minimum bpf_core_relo checked by the loader
- *
- * CO-RE relocation captures the following data:
- * - insn_off - instruction offset (in bytes) within a BPF program that needs
- *   its insn->imm field to be relocated with actual field info;
- * - type_id - BTF type ID of the "root" (containing) entity of a relocatable
- *   type or field;
- * - access_str_off - offset into corresponding .BTF string section. String
- *   interpretation depends on specific relocation kind:
- *     - for field-based relocations, string encodes an accessed field using
- *     a sequence of field and array indices, separated by colon (:). It's
- *     conceptually very close to LLVM's getelementptr ([0]) instruction's
- *     arguments for identifying offset to a field.
- *     - for type-based relocations, strings is expected to be just "0";
- *     - for enum value-based relocations, string contains an index of enum
- *     value within its enum type;
- *
- * Example to provide a better feel.
- *
- *   struct sample {
- *       int a;
- *       struct {
- *           int b[10];
- *       };
- *   };
- *
- *   struct sample *s = ...;
- *   int x = &s->a;     // encoded as "0:0" (a is field #0)
- *   int y = &s->b[5];  // encoded as "0:1:0:5" (anon struct is field #1,
- *                      // b is field #0 inside anon struct, accessing elem #5)
- *   int z = &s[10]->b; // encoded as "10:1" (ptr is used as an array)
- *
- * type_id for all relocs in this example  will capture BTF type id of
- * `struct sample`.
- *
- * Such relocation is emitted when using __builtin_preserve_access_index()
- * Clang built-in, passing expression that captures field address, e.g.:
- *
- * bpf_probe_read(&dst, sizeof(dst),
- *		  __builtin_preserve_access_index(&src->a.b.c));
- *
- * In this case Clang will emit field relocation recording necessary data to
- * be able to find offset of embedded `a.b.c` field within `src` struct.
- *
- *   [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction
- */
-struct bpf_core_relo {
-	__u32   insn_off;
-	__u32   type_id;
-	__u32   access_str_off;
-	enum bpf_core_relo_kind kind;
-};
+#include <linux/bpf.h>
 
 struct bpf_core_cand {
 	const struct btf *btf;
-	const struct btf_type *t;
-	const char *name;
 	__u32 id;
 };
 
@@ -88,11 +17,39 @@ struct bpf_core_cand_list {
 	int len;
 };
 
+#define BPF_CORE_SPEC_MAX_LEN 64
+
+/* represents BPF CO-RE field or array element accessor */
+struct bpf_core_accessor {
+	__u32 type_id;		/* struct/union type or array element type */
+	__u32 idx;		/* field index or array index */
+	const char *name;	/* field name or NULL for array accessor */
+};
+
+struct bpf_core_spec {
+	const struct btf *btf;
+	/* high-level spec: named fields and array indices only */
+	struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN];
+	/* original unresolved (no skip_mods_or_typedefs) root type ID */
+	__u32 root_type_id;
+	/* CO-RE relocation kind */
+	enum bpf_core_relo_kind relo_kind;
+	/* high-level spec length */
+	int len;
+	/* raw, low-level spec: 1-to-1 with accessor spec string */
+	int raw_spec[BPF_CORE_SPEC_MAX_LEN];
+	/* raw spec length */
+	int raw_len;
+	/* field bit offset represented by spec */
+	__u32 bit_offset;
+};
+
 int bpf_core_apply_relo_insn(const char *prog_name,
 			     struct bpf_insn *insn, int insn_idx,
 			     const struct bpf_core_relo *relo, int relo_idx,
 			     const struct btf *local_btf,
-			     struct bpf_core_cand_list *cands);
+			     struct bpf_core_cand_list *cands,
+			     struct bpf_core_spec *specs_scratch);
 int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id,
 			      const struct btf *targ_btf, __u32 targ_id);
 

src/skel_internal.h

@@ -70,19 +70,85 @@ static inline int skel_closenz(int fd)
 	return -EINVAL;
 }
 
+#ifndef offsetofend
+#define offsetofend(TYPE, MEMBER) \
+	(offsetof(TYPE, MEMBER)	+ sizeof((((TYPE *)0)->MEMBER)))
+#endif
+
+static inline int skel_map_create(enum bpf_map_type map_type,
+				  const char *map_name,
+				  __u32 key_size,
+				  __u32 value_size,
+				  __u32 max_entries)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, map_extra);
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_sz);
+
+	attr.map_type = map_type;
+	strncpy(attr.map_name, map_name, sizeof(attr.map_name));
+	attr.key_size = key_size;
+	attr.value_size = value_size;
+	attr.max_entries = max_entries;
+
+	return skel_sys_bpf(BPF_MAP_CREATE, &attr, attr_sz);
+}
+
+static inline int skel_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;
+
+	memset(&attr, 0, attr_sz);
+	attr.map_fd = fd;
+	attr.key = (long) key;
+	attr.value = (long) value;
+	attr.flags = flags;
+
+	return skel_sys_bpf(BPF_MAP_UPDATE_ELEM, &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);
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_sz);
+	attr.raw_tracepoint.name = (long) name;
+	attr.raw_tracepoint.prog_fd = prog_fd;
+
+	return skel_sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, attr_sz);
+}
+
+static inline int skel_link_create(int prog_fd, int target_fd,
+				   enum bpf_attach_type attach_type)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, link_create.iter_info_len);
+	union bpf_attr 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;
+
+	return skel_sys_bpf(BPF_LINK_CREATE, &attr, attr_sz);
+}
+
 static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
 {
 	int map_fd = -1, prog_fd = -1, key = 0, err;
 	union bpf_attr attr;
 
-	map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1, NULL);
+	map_fd = skel_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1);
 	if (map_fd < 0) {
 		opts->errstr = "failed to create loader map";
 		err = -errno;
 		goto out;
 	}
 
-	err = bpf_map_update_elem(map_fd, &key, opts->data, 0);
+	err = skel_map_update_elem(map_fd, &key, opts->data, 0);
 	if (err < 0) {
 		opts->errstr = "failed to update loader map";
 		err = -errno;

src/xsk.c

@@ -548,8 +548,7 @@ static int xsk_get_max_queues(struct xsk_socket *xsk)
 		return -errno;
 
 	ifr.ifr_data = (void *)&channels;
-	memcpy(ifr.ifr_name, ctx->ifname, IFNAMSIZ - 1);
-	ifr.ifr_name[IFNAMSIZ - 1] = '\0';
+	libbpf_strlcpy(ifr.ifr_name, ctx->ifname, IFNAMSIZ);
 	err = ioctl(fd, SIOCETHTOOL, &ifr);
 	if (err && errno != EOPNOTSUPP) {
 		ret = -errno;
@@ -768,8 +767,7 @@ static int xsk_create_xsk_struct(int ifindex, struct xsk_socket *xsk)
 	}
 
 	ctx->ifindex = ifindex;
-	memcpy(ctx->ifname, ifname, IFNAMSIZ -1);
-	ctx->ifname[IFNAMSIZ - 1] = 0;
+	libbpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ);
 
 	xsk->ctx = ctx;
 	xsk->ctx->has_bpf_link = xsk_probe_bpf_link();
@@ -951,8 +949,7 @@ static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk,
 	ctx->refcount = 1;
 	ctx->umem = umem;
 	ctx->queue_id = queue_id;
-	memcpy(ctx->ifname, ifname, IFNAMSIZ - 1);
-	ctx->ifname[IFNAMSIZ - 1] = '\0';
+	libbpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ);
 
 	ctx->fill = fill;
 	ctx->comp = comp;

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

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

travis-ci/rootfs/mkrootfs_tweak.sh

@@ -25,7 +25,7 @@ set -eux
 /bin/mount proc /proc -t proc
 
 # Mount devtmpfs if not mounted
-if [[ -z $(/bin/mount -l -t devtmpfs) ]]; then
+if [[ -z $(/bin/mount -t devtmpfs) ]]; then
 	/bin/mount devtmpfs /dev -t devtmpfs
 fi
 

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

@@ -10,7 +10,8 @@ the master branch.
 ### Install prerequisites.
 
 ```
-$ sudo dnf install docker
+$ sudo dnf install docker        # RHEL
+$ sudo apt install -y docker.io  # Ubuntu
 ```
 
 ### Add services.
@@ -53,17 +54,18 @@ get the latest OS security fixes, use the following commands:
 $ sudo docker build \
       --pull \
       -f actions-runner-libbpf.Dockerfile \
-      -t iiilinuxibmcom/actions-runner-libbpf
+      -t iiilinuxibmcom/actions-runner-libbpf \
+      .
 $ sudo systemctl restart actions-runner-libbpf
 ```
 
 ## Removing persistent data
 
 The `actions-runner-libbpf` service stores various temporary data, such as
-runner  registration information, work directories and logs, in the
+runner registration information, work directories and logs, in the
 `actions-runner-libbpf` volume. In order to remove it and start from scratch,
-e.g. when switching the runner to a different repository, use the following
-commands:
+e.g. when upgrading the runner or switching it to a different repository, use
+the following commands:
 
 ```
 $ sudo systemctl stop actions-runner-libbpf

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

@@ -33,13 +33,15 @@ RUN ln -fs /etc/resolv.conf /usr/x86_64-linux-gnu/etc/
 ENV QEMU_LD_PREFIX=/usr/x86_64-linux-gnu
 
 # amd64 Github Actions Runner.
+ARG version=2.285.0
 RUN useradd -m actions-runner
 RUN echo "actions-runner ALL=(ALL) NOPASSWD: ALL" >>/etc/sudoers
 RUN echo "Defaults env_keep += \"DEBIAN_FRONTEND\"" >>/etc/sudoers
+RUN usermod -a -G kvm actions-runner
 USER actions-runner
 ENV USER=actions-runner
 WORKDIR /home/actions-runner
-RUN curl -L https://github.com/actions/runner/releases/download/v2.283.2/actions-runner-linux-x64-2.283.2.tar.gz | tar -xz
+RUN curl -L https://github.com/actions/runner/releases/download/v${version}/actions-runner-linux-x64-${version}.tar.gz | tar -xz
 VOLUME /home/actions-runner
 
 # Scripts.

travis-ci/vmtest/build_pahole.sh

@@ -1,34 +0,0 @@
-#!/bin/bash
-
-set -eu
-
-source $(cd $(dirname $0) && pwd)/helpers.sh
-
-CWD=$(pwd)
-REPO_PATH=$1
-PAHOLE_ORIGIN=${PAHOLE_ORIGIN:-https://git.kernel.org/pub/scm/devel/pahole/pahole.git}
-PAHOLE_BRANCH=${PAHOLE_BRANCH:-master}
-
-travis_fold start build_pahole "Building pahole ${PAHOLE_ORIGIN} ${PAHOLE_BRANCH}"
-
-mkdir -p ${REPO_PATH}
-cd ${REPO_PATH}
-git init
-git remote add origin ${PAHOLE_ORIGIN}
-git fetch origin
-git checkout ${PAHOLE_BRANCH}
-
-# temporary work-around to bump pahole to 1.22 before it is officially released
-sed -i 's/DDWARVES_MINOR_VERSION=21/DDWARVES_MINOR_VERSION=22/' CMakeLists.txt
-
-mkdir -p build
-cd build
-cmake -DCMAKE_BUILD_TYPE=RelWithDebInfo -D__LIB=lib ..
-make -j$((4*$(nproc))) all
-sudo make install
-
-export LD_LIBRARY_PATH=${LD_LIBRARY_PATH:-}:/usr/local/lib
-ldd $(which pahole)
-pahole --version
-
-travis_fold end build_pahole

travis-ci/vmtest/checkout_latest_kernel.sh

@@ -1,54 +0,0 @@
-#!/bin/bash
-
-set -eu
-
-source $(cd $(dirname $0) && pwd)/helpers.sh
-
-CWD=$(pwd)
-LIBBPF_PATH=$(pwd)
-REPO_PATH=$1
-
-KERNEL_ORIGIN=${KERNEL_ORIGIN:-https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git}
-KERNEL_BRANCH=${KERNEL_BRANCH:-CHECKPOINT}
-if [[ "${KERNEL_BRANCH}" = 'CHECKPOINT' ]]; then
-  echo "using CHECKPOINT sha1"
-  LINUX_SHA=$(cat ${LIBBPF_PATH}/CHECKPOINT-COMMIT)
-else
-  echo "using ${KERNEL_BRANCH} sha1"
-  LINUX_SHA=$(git ls-remote ${KERNEL_ORIGIN} ${KERNEL_BRANCH} | awk '{print $1}')
-fi
-SNAPSHOT_URL=${KERNEL_ORIGIN}/snapshot/bpf-next-${LINUX_SHA}.tar.gz
-
-echo REPO_PATH = ${REPO_PATH}
-
-echo KERNEL_ORIGIN = ${KERNEL_ORIGIN}
-echo LINUX_SHA = ${LINUX_SHA}
-echo SNAPSHOT_URL = ${SNAPSHOT_URL}
-
-if [ ! -d "${REPO_PATH}" ]; then
-	echo
-	travis_fold start pull_kernel_srcs "Fetching kernel sources"
-
-	mkdir -p $(dirname "${REPO_PATH}")
-	cd $(dirname "${REPO_PATH}")
-	# attempt to fetch desired bpf-next repo snapshot
-	if wget -nv ${SNAPSHOT_URL} && tar xf bpf-next-${LINUX_SHA}.tar.gz --totals ; then
-		mv bpf-next-${LINUX_SHA} $(basename ${REPO_PATH})
-	else
-		# but fallback to git fetch approach if that fails
-		mkdir -p $(basename ${REPO_PATH})
-		cd $(basename ${REPO_PATH})
-		git init
-		git remote add bpf-next ${KERNEL_ORIGIN}
-		# try shallow clone first
-		git fetch --depth 32 bpf-next
-		# check if desired SHA exists
-		if ! git cat-file -e ${LINUX_SHA}^{commit} ; then
-			# if not, fetch all of bpf-next; slow and painful
-			git fetch bpf-next
-		fi
-		git reset --hard ${LINUX_SHA}
-	fi
-
-	travis_fold end pull_kernel_srcs
-fi

travis-ci/vmtest/configs/INDEX

@@ -1,9 +0,0 @@
-INDEX	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/INDEX
-x86_64/libbpf-vmtest-rootfs-2020.09.27.tar.zst	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/libbpf-vmtest-rootfs-2020.09.27.tar.zst
-x86_64/vmlinux-4.9.0.zst	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/vmlinux-4.9.0.zst
-x86_64/vmlinux-5.5.0-rc6.zst	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/vmlinux-5.5.0-rc6.zst
-x86_64/vmlinux-5.5.0.zst	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/vmlinux-5.5.0.zst
-x86_64/vmlinuz-5.5.0-rc6	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/vmlinuz-5.5.0-rc6
-x86_64/vmlinuz-5.5.0	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/vmlinuz-5.5.0
-x86_64/vmlinuz-4.9.0	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/vmlinuz-4.9.0
-s390x/libbpf-vmtest-rootfs-2021.03.24.tar.zst	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/s390x/libbpf-vmtest-rootfs-2021.03.24.tar.zst

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

@@ -3,6 +3,9 @@ atomics                                  # attach(add): actual -524 <= expected
 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)
@@ -12,6 +15,7 @@ fexit_bpf2bpf                            # freplace_attach_trace unexpected erro
 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)

travis-ci/vmtest/configs/config-latest.s390x

@@ -782,7 +782,7 @@ CONFIG_NETFILTER_NETLINK=y
 # CONFIG_NETFILTER_NETLINK_QUEUE is not set
 # CONFIG_NETFILTER_NETLINK_LOG is not set
 # CONFIG_NETFILTER_NETLINK_OSF is not set
-# CONFIG_NF_CONNTRACK is not set
+CONFIG_NF_CONNTRACK=y
 # CONFIG_NF_LOG_SYSLOG is not set
 CONFIG_NF_TABLES=y
 # CONFIG_NF_TABLES_INET is not set
@@ -871,6 +871,7 @@ CONFIG_NETFILTER_XT_MATCH_BPF=y
 #
 # IP: Netfilter Configuration
 #
+CONFIG_NF_DEFRAG_IPV4=y
 # CONFIG_NF_SOCKET_IPV4 is not set
 # CONFIG_NF_TPROXY_IPV4 is not set
 # CONFIG_NF_TABLES_IPV4 is not set
@@ -903,6 +904,7 @@ CONFIG_IP_NF_FILTER=y
 # CONFIG_IP6_NF_IPTABLES is not set
 # end of IPv6: Netfilter Configuration
 
+CONFIG_NF_DEFRAG_IPV6=y
 CONFIG_BPFILTER=y
 CONFIG_BPFILTER_UMH=y
 # CONFIG_IP_DCCP is not set

travis-ci/vmtest/configs/config-latest.x86_64

@@ -223,6 +223,8 @@ CONFIG_SHMEM=y
 CONFIG_AIO=y
 CONFIG_IO_URING=y
 CONFIG_ADVISE_SYSCALLS=y
+CONFIG_HAVE_ARCH_USERFAULTFD_WP=y
+CONFIG_HAVE_ARCH_USERFAULTFD_MINOR=y
 CONFIG_MEMBARRIER=y
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_ALL=y
@@ -236,7 +238,7 @@ CONFIG_BPF_JIT_DEFAULT_ON=y
 CONFIG_USERMODE_DRIVER=y
 CONFIG_BPF_PRELOAD=y
 CONFIG_BPF_PRELOAD_UMD=y
-# CONFIG_USERFAULTFD is not set
+CONFIG_USERFAULTFD=y
 CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE=y
 CONFIG_RSEQ=y
 # CONFIG_DEBUG_RSEQ is not set
@@ -975,7 +977,7 @@ CONFIG_NETFILTER_NETLINK=y
 CONFIG_NETFILTER_NETLINK_QUEUE=y
 CONFIG_NETFILTER_NETLINK_LOG=y
 # CONFIG_NETFILTER_NETLINK_OSF is not set
-# CONFIG_NF_CONNTRACK is not set
+CONFIG_NF_CONNTRACK=y
 # CONFIG_NF_LOG_NETDEV is not set
 # CONFIG_NF_TABLES is not set
 CONFIG_NETFILTER_XTABLES=y
@@ -1048,6 +1050,7 @@ CONFIG_NETFILTER_XT_MATCH_STATISTIC=y
 #
 # IP: Netfilter Configuration
 #
+CONFIG_NF_DEFRAG_IPV4=y
 # CONFIG_NF_SOCKET_IPV4 is not set
 # CONFIG_NF_TPROXY_IPV4 is not set
 # CONFIG_NF_DUP_IPV4 is not set
@@ -1089,6 +1092,7 @@ CONFIG_IP6_NF_IPTABLES=y
 # CONFIG_IP6_NF_SECURITY is not set
 # end of IPv6: Netfilter Configuration
 
+CONFIG_NF_DEFRAG_IPV6=y
 CONFIG_BPFILTER=y
 CONFIG_BPFILTER_UMH=m
 # CONFIG_IP_DCCP is not set
@@ -1791,7 +1795,14 @@ CONFIG_BCMA_POSSIBLE=y
 # end of Multifunction device drivers
 
 # CONFIG_REGULATOR is not set
-# CONFIG_RC_CORE is not set
+CONFIG_RC_CORE=y
+# CONFIG_RC_MAP is not set
+CONFIG_LIRC=y
+CONFIG_BPF_LIRC_MODE2=y
+# CONFIG_RC_DECODERS is not set
+CONFIG_RC_DEVICES=y
+CONFIG_RC_LOOPBACK=y
+# CONFIG_IR_SERIAL is not set
 # CONFIG_MEDIA_CEC_SUPPORT is not set
 # CONFIG_MEDIA_SUPPORT is not set
 

travis-ci/vmtest/helpers.sh

@@ -23,8 +23,6 @@ travis_fold() {
   fi
 }
 
-ARCH=$(uname -m)
-
 __print() {
   local TITLE=""
   if [[ -n $2 ]]; then

travis-ci/vmtest/prepare_selftests.sh

@@ -1,21 +0,0 @@
-#!/bin/bash
-
-set -eu
-
-source $(cd $(dirname $0) && pwd)/helpers.sh
-
-REPO_PATH=${1:-}
-
-if [[ ! -z "$REPO_PATH" ]]; then
-	${VMTEST_ROOT}/checkout_latest_kernel.sh ${REPO_PATH}
-	cd ${REPO_PATH}
-fi
-
-if [[ "${KERNEL}" = 'LATEST' ]]; then
-	travis_fold start build_kernel "Kernel build"
-
-	cp "$VMTEST_ROOT"/configs/config-latest."$ARCH" .config
-	make -j $((4*$(nproc))) olddefconfig all >/dev/null
-	travis_fold end build_kernel
-fi
-

travis-ci/vmtest/run.sh

@@ -1,569 +0,0 @@
-#!/bin/bash
-
-set -uo pipefail
-trap 'exit 2' ERR
-
-source $(cd $(dirname $0) && pwd)/helpers.sh
-
-usage () {
-	USAGE_STRING="usage: $0 [-k KERNELRELEASE|-b DIR] [[-r ROOTFSVERSION] [-fo]|-I] [-Si] [-d DIR] IMG
-       $0 [-k KERNELRELEASE] -l
-       $0 -h
-
-Run "${PROJECT_NAME}" tests in a virtual machine.
-
-This exits with status 0 on success, 1 if the virtual machine ran successfully
-but tests failed, and 2 if we encountered a fatal error.
-
-This script uses sudo to work around a libguestfs bug.
-
-Arguments:
-  IMG                 path of virtual machine disk image to create
-
-Versions:
-  -k, --kernel=KERNELRELEASE
-                       kernel release to test. This is a glob pattern; the
-                       newest (sorted by version number) release that matches
-                       the pattern is used (default: newest available release)
-
-  -b, --build DIR      use the kernel built in the given directory. This option
-                       cannot be combined with -k
-
-  -r, --rootfs=ROOTFSVERSION
-                       version of root filesystem to use (default: newest
-                       available version)
-
-Setup:
-  -f, --force          overwrite IMG if it already exists
-
-  -o, --one-shot       one-shot mode. By default, this script saves a clean copy
-                       of the downloaded root filesystem image and vmlinux and
-                       makes a copy (reflinked, when possible) for executing the
-                       virtual machine. This allows subsequent runs to skip
-                       downloading these files. If this option is given, the
-                       root filesystem image and vmlinux are always
-                       re-downloaded and are not saved. This option implies -f
-
-  -s, --setup-cmd      setup commands run on VM boot. Whitespace characters
-                       should be escaped with preceding '\'.
-
-  -I, --skip-image     skip creating the disk image; use the existing one at
-                       IMG. This option cannot be combined with -r, -f, or -o
-
-  -S, --skip-source    skip copying the source files and init scripts
-
-Miscellaneous:
-  -i, --interactive    interactive mode. Boot the virtual machine into an
-                       interactive shell instead of automatically running tests
-
-  -d, --dir=DIR        working directory to use for downloading and caching
-                       files (default: current working directory)
-
-  -l, --list           list available kernel releases instead of running tests.
-                       The list may be filtered with -k
-
-  -h, --help           display this help message and exit"
-
-	case "$1" in
-		out)
-			echo "$USAGE_STRING"
-			exit 0
-			;;
-		err)
-			echo "$USAGE_STRING" >&2
-			exit 2
-			;;
-	esac
-}
-
-TEMP=$(getopt -o 'k:b:r:fos:ISid:lh' --long 'kernel:,build:,rootfs:,force,one-shot,setup-cmd,skip-image,skip-source:,interactive,dir:,list,help' -n "$0" -- "$@")
-eval set -- "$TEMP"
-unset TEMP
-
-unset KERNELRELEASE
-unset BUILDDIR
-unset ROOTFSVERSION
-unset IMG
-unset SETUPCMD
-FORCE=0
-ONESHOT=0
-SKIPIMG=0
-SKIPSOURCE=0
-APPEND=""
-DIR="$PWD"
-LIST=0
-
-# by default will copy all files that aren't listed in git exclusions
-# but it doesn't work for entire kernel tree very well
-# so for full kernel tree you may need to SOURCE_FULLCOPY=0
-SOURCE_FULLCOPY=${SOURCE_FULLCOPY:-1}
-
-while true; do
-	case "$1" in
-		-k|--kernel)
-			KERNELRELEASE="$2"
-			shift 2
-			;;
-		-b|--build)
-			BUILDDIR="$2"
-			shift 2
-			;;
-		-r|--rootfs)
-			ROOTFSVERSION="$2"
-			shift 2
-			;;
-		-f|--force)
-			FORCE=1
-			shift
-			;;
-		-o|--one-shot)
-			ONESHOT=1
-			FORCE=1
-			shift
-			;;
-		-s|--setup-cmd)
-			SETUPCMD="$2"
-			shift 2
-			;;
-		-I|--skip-image)
-			SKIPIMG=1
-			shift
-			;;
-		-S|--skip-source)
-			SKIPSOURCE=1
-			shift
-			;;
-		-i|--interactive)
-			APPEND=" single"
-			shift
-			;;
-		-d|--dir)
-			DIR="$2"
-			shift 2
-			;;
-		-l|--list)
-			LIST=1
-			;;
-		-h|--help)
-			usage out
-			;;
-		--)
-			shift
-			break
-			;;
-		*)
-			usage err
-			;;
-	esac
-done
-if [[ -v BUILDDIR ]]; then
-	if [[ -v KERNELRELEASE ]]; then
-		usage err
-	fi
-elif [[ ! -v KERNELRELEASE ]]; then
-	KERNELRELEASE='*'
-fi
-if [[ $SKIPIMG -ne 0 && ( -v ROOTFSVERSION || $FORCE -ne 0 ) ]]; then
-	usage err
-fi
-if (( LIST )); then
-	if [[ $# -ne 0 || -v BUILDDIR || -v ROOTFSVERSION || $FORCE -ne 0 ||
-	      $SKIPIMG -ne 0 || $SKIPSOURCE -ne 0 || -n $APPEND ]]; then
-		usage err
-	fi
-else
-	if [[ $# -ne 1 ]]; then
-		usage err
-	fi
-	IMG="${!OPTIND}"
-fi
-if [[ "${SOURCE_FULLCOPY}" == "1" ]]; then
-	img_size=2G
-else
-	img_size=8G
-fi
-
-unset URLS
-cache_urls() {
-	if ! declare -p URLS &> /dev/null; then
-		# This URL contains a mapping from file names to URLs where
-		# those files can be downloaded.
-		declare -gA URLS
-		while IFS=$'\t' read -r name url; do
-			URLS["$name"]="$url"
-		done < <(cat "${VMTEST_ROOT}/configs/INDEX")
-	fi
-}
-
-matching_kernel_releases() {
-	local pattern="$1"
-	{
-	for file in "${!URLS[@]}"; do
-		if [[ $file =~ ^${ARCH}/vmlinux-(.*).zst$ ]]; then
-			release="${BASH_REMATCH[1]}"
-			case "$release" in
-				$pattern)
-					# sort -V handles rc versions properly
-					# if we use "~" instead of "-".
-					echo "${release//-rc/~rc}"
-					;;
-			esac
-		fi
-	done
-	} | sort -rV | sed 's/~rc/-rc/g'
-}
-
-newest_rootfs_version() {
-	{
-	for file in "${!URLS[@]}"; do
-		if [[ $file =~ ^${ARCH}/${PROJECT_NAME}-vmtest-rootfs-(.*)\.tar\.zst$ ]]; then
-			echo "${BASH_REMATCH[1]}"
-		fi
-	done
-	} | sort -rV | head -1
-}
-
-download() {
-	local file="$1"
-	cache_urls
-	if [[ ! -v URLS[$file] ]]; then
-		echo "$file not found" >&2
-		return 1
-	fi
-	echo "Downloading $file..." >&2
-	curl -Lf "${URLS[$file]}" "${@:2}"
-}
-
-set_nocow() {
-	touch "$@"
-	chattr +C "$@" >/dev/null 2>&1 || true
-}
-
-cp_img() {
-	set_nocow "$2"
-	cp --reflink=auto "$1" "$2"
-}
-
-create_rootfs_img() {
-	local path="$1"
-	set_nocow "$path"
-	truncate -s "$img_size" "$path"
-	mkfs.ext4 -q "$path"
-}
-
-download_rootfs() {
-	local rootfsversion="$1"
-	download "${ARCH}/${PROJECT_NAME}-vmtest-rootfs-$rootfsversion.tar.zst" |
-		zstd -d
-}
-
-tar_in() {
-	local dst_path="$1"
-	# guestfish --remote does not forward file descriptors, which prevents
-	# us from using `tar-in -` or bash process substitution. We don't want
-	# to copy all the data into a temporary file, so use a FIFO.
-	tmp=$(mktemp -d)
-	mkfifo "$tmp/fifo"
-	cat >"$tmp/fifo" &
-	local cat_pid=$!
-	guestfish --remote tar-in "$tmp/fifo" "$dst_path"
-	wait "$cat_pid"
-	rm -r "$tmp"
-	tmp=
-}
-
-if (( LIST )); then
-	cache_urls
-	matching_kernel_releases "$KERNELRELEASE"
-	exit 0
-fi
-
-if [[ $FORCE -eq 0 && $SKIPIMG -eq 0 && -e $IMG ]]; then
-	echo "$IMG already exists; use -f to overwrite it or -I to reuse it" >&2
-	exit 1
-fi
-
-# Only go to the network if it's actually a glob pattern.
-if [[ -v BUILDDIR ]]; then
-	KERNELRELEASE="$(make -C "$BUILDDIR" -s kernelrelease)"
-elif [[ ! $KERNELRELEASE =~ ^([^\\*?[]|\\[*?[])*\\?$ ]]; then
-	# We need to cache the list of URLs outside of the command
-	# substitution, which happens in a subshell.
-	cache_urls
-	KERNELRELEASE="$(matching_kernel_releases "$KERNELRELEASE" | head -1)"
-	if [[ -z $KERNELRELEASE ]]; then
-		echo "No matching kernel release found" >&2
-		exit 1
-	fi
-fi
-if [[ $SKIPIMG -eq 0 && ! -v ROOTFSVERSION ]]; then
-	cache_urls
-	ROOTFSVERSION="$(newest_rootfs_version)"
-fi
-
-travis_fold start vmlinux_setup "Preparing Linux image"
-
-echo "Kernel release: $KERNELRELEASE" >&2
-echo
-
-if (( SKIPIMG )); then
-	echo "Not extracting root filesystem" >&2
-else
-	echo "Root filesystem version: $ROOTFSVERSION" >&2
-fi
-echo "Disk image: $IMG" >&2
-
-tmp=
-ARCH_DIR="$DIR/$ARCH"
-mkdir -p "$ARCH_DIR"
-
-cleanup() {
-	if [[ -n $tmp ]]; then
-		rm -rf "$tmp" || true
-	fi
-	guestfish --remote exit 2>/dev/null || true
-}
-trap cleanup EXIT
-
-if [[ -v BUILDDIR ]]; then
-	vmlinuz="$BUILDDIR/$(make -C "$BUILDDIR" -s image_name)"
-else
-	vmlinuz="${ARCH_DIR}/vmlinuz-${KERNELRELEASE}"
-	if [[ ! -e $vmlinuz ]]; then
-		tmp="$(mktemp "$vmlinuz.XXX.part")"
-		download "${ARCH}/vmlinuz-${KERNELRELEASE}" -o "$tmp"
-		mv "$tmp" "$vmlinuz"
-		tmp=
-	fi
-fi
-
-# Mount and set up the rootfs image. Use a persistent guestfish session in
-# order to avoid the startup overhead.
-# Work around https://bugs.launchpad.net/fuel/+bug/1467579.
-sudo chmod +r /boot/vmlinuz*
-eval "$(guestfish --listen)"
-if (( ONESHOT )); then
-	rm -f "$IMG"
-	create_rootfs_img "$IMG"
-	guestfish --remote \
-		add "$IMG" label:img : \
-		launch : \
-		mount /dev/disk/guestfs/img /
-	download_rootfs "$ROOTFSVERSION" | tar_in /
-else
-	if (( ! SKIPIMG )); then
-		rootfs_img="${ARCH_DIR}/${PROJECT_NAME}-vmtest-rootfs-${ROOTFSVERSION}.img"
-
-		if [[ ! -e $rootfs_img ]]; then
-			tmp="$(mktemp "$rootfs_img.XXX.part")"
-			set_nocow "$tmp"
-			truncate -s "$img_size" "$tmp"
-			mkfs.ext4 -q "$tmp"
-
-			# libguestfs supports hotplugging only with a libvirt
-			# backend, which we are not using here, so handle the
-			# temporary image in a separate session.
-			download_rootfs "$ROOTFSVERSION" |
-				guestfish -a "$tmp" tar-in - /
-
-			mv "$tmp" "$rootfs_img"
-			tmp=
-		fi
-
-		rm -f "$IMG"
-		cp_img "$rootfs_img" "$IMG"
-	fi
-	guestfish --remote \
-		add "$IMG" label:img : \
-		launch : \
-		mount /dev/disk/guestfs/img /
-fi
-
-# Install vmlinux.
-vmlinux="/boot/vmlinux-${KERNELRELEASE}"
-if [[ -v BUILDDIR || $ONESHOT -eq 0 ]]; then
-	if [[ -v BUILDDIR ]]; then
-		source_vmlinux="${BUILDDIR}/vmlinux"
-	else
-		source_vmlinux="${ARCH_DIR}/vmlinux-${KERNELRELEASE}"
-		if [[ ! -e $source_vmlinux ]]; then
-			tmp="$(mktemp "$source_vmlinux.XXX.part")"
-			download "${ARCH}/vmlinux-${KERNELRELEASE}.zst" | zstd -dfo "$tmp"
-			mv "$tmp" "$source_vmlinux"
-			tmp=
-		fi
-	fi
-else
-	source_vmlinux="${ARCH_DIR}/vmlinux-${KERNELRELEASE}"
-	download "${ARCH}/vmlinux-${KERNELRELEASE}.zst" | zstd -d >"$source_vmlinux"
-fi
-echo "Copying vmlinux..." >&2
-guestfish --remote \
-	upload "$source_vmlinux" "$vmlinux" : \
-	chmod 644 "$vmlinux"
-
-travis_fold end vmlinux_setup
-
-REPO_PATH="${SELFTEST_REPO_PATH:-travis-ci/vmtest/bpf-next}"
-LIBBPF_PATH="${REPO_ROOT}" \
-	VMTEST_ROOT="${VMTEST_ROOT}" \
-	REPO_PATH="${REPO_PATH}" \
-	VMLINUX_BTF=$(realpath ${source_vmlinux}) ${VMTEST_ROOT}/build_selftests.sh
-
-travis_fold start bpftool_checks "Running bpftool checks..."
-bpftool_exitstatus=
-if [[ "${KERNEL}" = 'LATEST' ]]; then
-	# "&& true" does not change the return code (it is not executed if the
-	# Python script fails), but it prevents the trap on ERR set at the top
-	# of this file to trigger on failure.
-	"${REPO_ROOT}/${REPO_PATH}/tools/testing/selftests/bpf/test_bpftool_synctypes.py" && true
-	bpftool_exitstatus=$?
-	if [[ "$bpftool_exitstatus" -eq 0 ]]; then
-		print_notice bpftool_checks "bpftool checks passed successfully."
-	else
-		print_error bpftool_checks "bpftool checks returned ${bpftool_exitstatus}."
-	fi
-	bpftool_exitstatus="bpftool:${bpftool_exitstatus}"
-else
-	echo "bpftool checks skipped."
-fi
-travis_fold end bpftool_checks
-
-travis_fold start vm_init "Starting virtual machine..."
-
-if (( SKIPSOURCE )); then
-	echo "Not copying source files..." >&2
-else
-	echo "Copying source files..." >&2
-	# Copy the source files in.
-	guestfish --remote \
-		mkdir-p "/${PROJECT_NAME}" : \
-		chmod 0755 "/${PROJECT_NAME}"
-	if [[ "${SOURCE_FULLCOPY}" == "1" ]]; then
-		git ls-files -z | tar --null --files-from=- -c | tar_in "/${PROJECT_NAME}"
-	else
-		guestfish --remote \
-			mkdir-p "/${PROJECT_NAME}/selftests" : \
-			chmod 0755 "/${PROJECT_NAME}/selftests" : \
-			mkdir-p "/${PROJECT_NAME}/travis-ci" : \
-			chmod 0755 "/${PROJECT_NAME}/travis-ci"
-		tree --du -shaC "${REPO_ROOT}/selftests/bpf"
-		tar -C "${REPO_ROOT}/selftests" -c bpf | tar_in "/${PROJECT_NAME}/selftests"
-		tar -C "${REPO_ROOT}/travis-ci" -c vmtest | tar_in "/${PROJECT_NAME}/travis-ci"
-	fi
-fi
-
-tmp=$(mktemp)
-cat <<HERE >"$tmp"
-"#!/bin/sh
-
-echo 'Skipping setup commands'
-echo vm_start:0 > /exitstatus
-chmod 644 /exitstatus
-HERE
-
-# Create the init scripts.
-if [[ ! -z SETUPCMD ]]; then
-	# Unescape whitespace characters.
-	setup_cmd=$(sed 's/\(\\\)\([[:space:]]\)/\2/g' <<< "${SETUPCMD}")
-	kernel="${KERNELRELEASE}"
-	if [[ -v BUILDDIR ]]; then kernel='latest'; fi
-	setup_envvars="export KERNEL=${kernel}"
-	cat <<HERE >"$tmp"
-#!/bin/sh
-set -eux
-
-echo 'Running setup commands'
-${setup_envvars}
-set +e
-${setup_cmd}; exitstatus=\$?
-echo -e '$(travis_fold start collect_status "Collect status")'
-set -e
-# If setup command did not write its exit status to /exitstatus, do it now
-if [[ ! -s /exitstatus ]]; then
-	echo setup_cmd:\$exitstatus > /exitstatus
-fi
-chmod 644 /exitstatus
-echo -e '$(travis_fold end collect_status)'
-echo -e '$(travis_fold start shutdown Shutdown)'
-HERE
-fi
-
-guestfish --remote \
-	upload "$tmp" /etc/rcS.d/S50-run-tests : \
-	chmod 755 /etc/rcS.d/S50-run-tests
-
-cat <<HERE >"$tmp"
-#!/bin/sh
-
-poweroff
-HERE
-guestfish --remote \
-	upload "$tmp" /etc/rcS.d/S99-poweroff : \
-	chmod 755 /etc/rcS.d/S99-poweroff
-rm "$tmp"
-tmp=
-
-guestfish --remote exit
-
-echo "Starting VM with $(nproc) CPUs..."
-
-case "$ARCH" in
-s390x)
-	qemu="qemu-system-s390x"
-	console="ttyS1"
-	smp=2
-	kvm_accel="-enable-kvm"
-	tcg_accel="-machine accel=tcg"
-	;;
-x86_64)
-	qemu="qemu-system-x86_64"
-	console="ttyS0,115200"
-	smp=$(nproc)
-	kvm_accel="-cpu kvm64 -enable-kvm"
-	tcg_accel="-cpu qemu64 -machine accel=tcg"
-	;;
-*)
-	echo "Unsupported architecture"
-	exit 1
-	;;
-esac
-if kvm-ok ; then
-  accel=$kvm_accel
-else
-  accel=$tcg_accel
-fi
-"$qemu" -nodefaults -display none -serial mon:stdio \
-  ${accel} -smp "$smp" -m 4G \
-  -drive file="$IMG",format=raw,index=1,media=disk,if=virtio,cache=none \
-  -kernel "$vmlinuz" -append "root=/dev/vda rw console=$console kernel.panic=-1 $APPEND"
-
-# Set exit status to 1 if at least one group test returned non-0
-exitfile="${bpftool_exitstatus}${bpftool_exitstatus:+\n}"
-exitfile+="$(guestfish --ro -a "$IMG" -i cat /exitstatus 2>/dev/null)"
-exitstatus="$(echo -e "$exitfile" | awk --field-separator ':' \
-	'BEGIN { s=0 } { if ($2) {s=1} } END { print s }')"
-
-if [[ "$exitstatus" =~ ^[0-9]+$ ]]; then
-	printf '\nTests exit status: %s\n' "$exitstatus" >&2
-else
-	printf '\nCould not read tests exit status ("%s")\n' "$exitstatus" >&2
-	exitstatus=1
-fi
-
-travis_fold end shutdown
-
-# Final summary - Don't use a fold, keep it visible
-echo -e "\033[1;33mTest Results:\033[0m"
-echo -e "$exitfile" | while read result; do
-	testgroup=${result%:*}
-	status=${result#*:}
-	# Print final result for each group of tests
-	if [[ "$status" -eq 0 ]]; then
-		printf "%20s: \033[1;32mPASS\033[0m\n" "$testgroup"
-	else
-		printf "%20s: \033[1;31mFAIL\033[0m (returned %s)\n" "$testgroup" "$status"
-	fi
-done
-
-exit "$exitstatus"

travis-ci/vmtest/run_selftests.sh

@@ -4,6 +4,8 @@ set -euo pipefail
 
 source $(cd $(dirname $0) && pwd)/helpers.sh
 
+ARCH=$(uname -m)
+
 STATUS_FILE=/exitstatus
 
 read_lists() {
@@ -47,11 +49,11 @@ test_verifier() {
 
 travis_fold end vm_init
 
-configs_path=libbpf/travis-ci/vmtest/configs
+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 libbpf/selftests/bpf
+cd ${PROJECT_NAME}/selftests/bpf
 
 test_progs
 

travis-ci/vmtest/run_vmtest.sh

@@ -1,53 +0,0 @@
-#!/bin/bash
-
-set -eu
-
-source $(cd $(dirname $0) && pwd)/helpers.sh
-
-VMTEST_SETUPCMD="GITHUB_WORKFLOW=${GITHUB_WORKFLOW:-} PROJECT_NAME=${PROJECT_NAME} ./${PROJECT_NAME}/travis-ci/vmtest/run_selftests.sh"
-
-# if CHECKOUT_KERNEL is 1 code will consider that kernel code lives elsewhere
-# if 0 it will consider that REPO_ROOT is a kernel tree
-CHECKOUT_KERNEL=${CHECKOUT_KERNEL:-1}
-
-echo "KERNEL: $KERNEL"
-echo
-
-# Build latest pahole
-${VMTEST_ROOT}/build_pahole.sh travis-ci/vmtest/pahole
-
-travis_fold start install_clang "Installing Clang/LLVM"
-
-wget -O - https://apt.llvm.org/llvm-snapshot.gpg.key | sudo apt-key add -
-sudo add-apt-repository "deb http://apt.llvm.org/focal/ llvm-toolchain-focal main"
-sudo apt-get update
-sudo apt-get install --allow-downgrades -y libc6=2.31-0ubuntu9.2
-sudo aptitude install -y g++ libelf-dev
-sudo aptitude install -y clang-14 llvm-14
-
-travis_fold end install_clang
-
-# Build selftests (and latest kernel, if necessary)
-
-if [[ "$CHECKOUT_KERNEL" == "1" ]]; then
-  ${VMTEST_ROOT}/prepare_selftests.sh travis-ci/vmtest/bpf-next
-else
-  ${VMTEST_ROOT}/prepare_selftests.sh
-fi
-
-travis_fold start adduser_to_kvm "Add user ${USER}"
-sudo adduser "${USER}" kvm
-travis_fold stop adduser_to_kvm
-
-# Escape whitespace characters.
-setup_cmd=$(sed 's/\([[:space:]]\)/\\\1/g' <<< "${VMTEST_SETUPCMD}")
-
-if [[ "${KERNEL}" = 'LATEST' ]]; then
-  if [[ "$CHECKOUT_KERNEL" == "1" ]]; then
-    sudo -E sudo -E -u "${USER}" "${VMTEST_ROOT}/run.sh" -b travis-ci/vmtest/bpf-next -o -d ~ -s "${setup_cmd}" ~/root.img
-  else
-    sudo -E sudo -E -u "${USER}" "${VMTEST_ROOT}/run.sh" -b "${REPO_ROOT}" -o -d ~ -s "${setup_cmd}" ~/root.img
-  fi
-else
-  sudo -E sudo -E -u "${USER}" "${VMTEST_ROOT}/run.sh" -k "${KERNEL}*" -o -d ~ -s "${setup_cmd}" ~/root.img
-fi