Merge branch 'libbpf:master' into master

Bump to latest uraimo/run-on-arch-action@v2.8.1 version, hoping that
fixes the CI.

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

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

@@ -12,6 +12,9 @@ inputs:
     description: 'where is vmlinux file'
     required: true
     default: '${{ github.workspace }}/vmlinux'
+  llvm-version:
+    description: 'llvm version'
+    required: true
 
 runs:
   using: "composite"
@@ -28,4 +31,6 @@ runs:
         export REPO_ROOT="${{ github.workspace }}"
         export REPO_PATH="${{ inputs.repo-path }}"
         export VMLINUX_BTF="${{ inputs.vmlinux }}"
+        export LLVM_VERSION="${{ inputs.llvm-version }}"
+
         ${{ github.action_path }}/build_selftests.sh

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

@@ -10,22 +10,21 @@ foldable start prepare_selftests "Building selftests"
 
 LIBBPF_PATH="${REPO_ROOT}"
 
-llvm_default_version() {
-	echo "16"
-}
-
 llvm_latest_version() {
-	echo "17"
+	echo "19"
 }
 
-LLVM_VERSION=$(llvm_default_version)
 if [[ "${LLVM_VERSION}" == $(llvm_latest_version) ]]; then
 	REPO_DISTRO_SUFFIX=""
 else
 	REPO_DISTRO_SUFFIX="-${LLVM_VERSION}"
 fi
 
-echo "deb https://apt.llvm.org/focal/ llvm-toolchain-focal${REPO_DISTRO_SUFFIX} main" \
+DISTRIB_CODENAME="noble"
+test -f /etc/lsb-release && . /etc/lsb-release
+echo "${DISTRIB_CODENAME}"
+
+echo "deb https://apt.llvm.org/${DISTRIB_CODENAME}/ llvm-toolchain-${DISTRIB_CODENAME}${REPO_DISTRO_SUFFIX} main" \
 	| sudo tee /etc/apt/sources.list.d/llvm.list
 
 PREPARE_SELFTESTS_SCRIPT=${THISDIR}/prepare_selftests-${KERNEL}.sh

.github/actions/vmtest/action.yml

@@ -13,6 +13,10 @@ inputs:
     description: 'pahole rev or master'
     required: true
     default: 'master'
+  llvm-version:
+    description: 'llvm version'
+    required: false
+    default: '17'
 runs:
   using: "composite"
   steps:
@@ -38,6 +42,7 @@ runs:
       with:
         pahole: ${{ inputs.pahole }}
         arch: ${{ inputs.arch }}
+        llvm-version: ${{ inputs.llvm-version }}
     # 1. download CHECKPOINT kernel source
     - name: Get checkpoint commit
       shell: bash
@@ -93,6 +98,7 @@ runs:
       with:
         repo-path: '.kernel'
         kernel: ${{ inputs.kernel }}
+        llvm-version: ${{ inputs.llvm-version }}
     # 4. prepare rootfs
     - name: prepare rootfs
       uses: libbpf/ci/prepare-rootfs@main

.github/workflows/build.yml

@@ -70,7 +70,7 @@ jobs:
       - run: source /tmp/ci_setup && sudo -E $CI_ROOT/managers/ubuntu.sh
         if: matrix.arch == 'x86'
         name: Setup
-      - uses: uraimo/run-on-arch-action@v2.7.1
+      - uses: uraimo/run-on-arch-action@v2.8.1
         name: Build in docker
         if: matrix.arch != 'x86'
         with:

.github/workflows/cifuzz.yml

@@ -33,7 +33,7 @@ jobs:
           dry-run: false
           sanitizer: ${{ matrix.sanitizer }}
       - name: Upload Crash
-        uses: actions/upload-artifact@v1
+        uses: actions/upload-artifact@v4
         if: failure() && steps.build.outcome == 'success'
         with:
           name: ${{ matrix.sanitizer }}-artifacts

.github/workflows/pahole.yml

@@ -1,13 +1,13 @@
 name: pahole-staging
 
 on:
+  workflow_dispatch:
   schedule:
     - cron:  '0 18 * * *'
 
-
 jobs:
   vmtest:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-20.04
     name: Kernel LATEST + staging pahole
     env:
       STAGING: tmp.master

.github/workflows/test.yml

@@ -13,23 +13,20 @@ concurrency:
 jobs:
   vmtest:
     runs-on: ${{ matrix.runs_on }}
-    name: Kernel ${{ matrix.kernel }} on ${{ matrix.runs_on }} + selftests
+    name: Kernel ${{ matrix.kernel }} on ${{ matrix.arch }} + selftests
     strategy:
       fail-fast: false
       matrix:
         include:
           - kernel: 'LATEST'
-            runs_on: ubuntu-20.04
+            runs_on: ubuntu-24.04
             arch: 'x86_64'
           - kernel: '5.5.0'
-            runs_on: ubuntu-20.04
+            runs_on: ubuntu-24.04
             arch: 'x86_64'
           - kernel: '4.9.0'
-            runs_on: ubuntu-20.04
+            runs_on: ubuntu-24.04
             arch: 'x86_64'
-          - kernel: 'LATEST'
-            runs_on: s390x
-            arch: 's390x'
     steps:
       - uses: actions/checkout@v4
         name: Checkout

.mailmap

@@ -8,6 +8,7 @@ Dan Carpenter <error27@gmail.com> <dan.carpenter@oracle.com>
 Geliang Tang <geliang@kernel.org> <geliang.tang@suse.com>
 Herbert Xu <herbert@gondor.apana.org.au>
 Jakub Kicinski <kuba@kernel.org> <jakub.kicinski@netronome.com>
+Kees Cook <kees@kernel.org> <keescook@chromium.org>
 Leo Yan <leo.yan@linux.dev> <leo.yan@linaro.org>
 Mark Starovoytov <mstarovo@pm.me> <mstarovoitov@marvell.com>
 Maxim Mikityanskiy <maxtram95@gmail.com> <maximmi@mellanox.com>
@@ -15,4 +16,6 @@ Maxim Mikityanskiy <maxtram95@gmail.com> <maximmi@nvidia.com>
 Puranjay Mohan <puranjay@kernel.org> <puranjay12@gmail.com>
 Quentin Monnet <qmo@kernel.org> <quentin@isovalent.com>
 Quentin Monnet <qmo@kernel.org> <quentin.monnet@netronome.com>
+Stanislav Fomichev <sdf@fomichev.me> <sdf@google.com>
+Vadim Fedorenko <vadim.fedorenko@linux.dev> <vadfed@meta.com>
 Vadim Fedorenko <vadim.fedorenko@linux.dev> <vfedorenko@novek.ru>

BPF-CHECKPOINT-COMMIT

@@ -1 +1 @@
-62da3acd28955e7299babebdfcb14243b789e773
+d5fb316e2af1d947f0f6c3666e373a54d9f27c6f

CHECKPOINT-COMMIT

@@ -1 +1 @@
-531876c80004ecff7bfdbd8ba6c6b48835ef5e22
+c6fb8030b4baa01c850f99fc6da051b1017edc46

ci/diffs/0003-selftests-bpf-Fix-uprobe-consumer-test.patch

@@ -0,0 +1,58 @@
+From affb32e4f056883f285f8535b766293b85752fb4 Mon Sep 17 00:00:00 2001
+From: Jiri Olsa <jolsa@kernel.org>
+Date: Tue, 24 Sep 2024 13:07:30 +0200
+Subject: [PATCH] selftests/bpf: Fix uprobe consumer test
+
+With newly merged code the uprobe behaviour is slightly different
+and affects uprobe consumer test.
+
+We no longer need to check if the uprobe object is still preserved
+after removing last uretprobe, because it stays as long as there's
+pending/installed uretprobe instance.
+
+This allows to run uretprobe consumers registered 'after' uprobe was
+hit even if previous uretprobe got unregistered before being hit.
+
+The uprobe object will be now removed after the last uprobe ref is
+released and in such case it's held by ri->uprobe (return instance)
+which is released after the uretprobe is hit.
+
+Reported-by: Ihor Solodrai <ihor.solodrai@pm.me>
+Signed-off-by: Jiri Olsa <jolsa@kernel.org>
+Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
+Tested-by: Ihor Solodrai <ihor.solodrai@pm.me>
+Closes: https://lore.kernel.org/bpf/w6U8Z9fdhjnkSp2UaFaV1fGqJXvfLEtDKEUyGDkwmoruDJ_AgF_c0FFhrkeKW18OqiP-05s9yDKiT6X-Ns-avN_ABf0dcUkXqbSJN1TQSXo=@pm.me/
+---
+ .../testing/selftests/bpf/prog_tests/uprobe_multi_test.c | 9 +--------
+ 1 file changed, 1 insertion(+), 8 deletions(-)
+
+diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+index 844f6fc8487b..c1ac813ff9ba 100644
+--- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
++++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+@@ -869,21 +869,14 @@ static void consumer_test(struct uprobe_multi_consumers *skel,
+ 			fmt = "prog 0/1: uprobe";
+ 		} else {
+ 			/*
+-			 * uprobe return is tricky ;-)
+-			 *
+ 			 * to trigger uretprobe consumer, the uretprobe needs to be installed,
+ 			 * which means one of the 'return' uprobes was alive when probe was hit:
+ 			 *
+ 			 *   idxs: 2/3 uprobe return in 'installed' mask
+-			 *
+-			 * in addition if 'after' state removes everything that was installed in
+-			 * 'before' state, then uprobe kernel object goes away and return uprobe
+-			 * is not installed and we won't hit it even if it's in 'after' state.
+ 			 */
+ 			unsigned long had_uretprobes  = before & 0b1100; /* is uretprobe installed */
+-			unsigned long probe_preserved = before & after;  /* did uprobe go away */
+ 
+-			if (had_uretprobes && probe_preserved && test_bit(idx, after))
++			if (had_uretprobes && test_bit(idx, after))
+ 				val++;
+ 			fmt = "idx 2/3: uretprobe";
+ 		}
+-- 
+2.34.1
+

ci/vmtest/configs/DENYLIST

@@ -12,3 +12,4 @@ xdp_bonding/xdp_bonding_features     # started failing after net merge from 359e
 tc_redirect/tc_redirect_dtime # uapi breakage after net-next commit 885c36e59f46 ("net: Re-use and set mono_delivery_time bit for userspace tstamp packets")
 migrate_reuseport/IPv4 TCP_NEW_SYN_RECV reqsk_timer_handler # flaky, under investigation
 migrate_reuseport/IPv6 TCP_NEW_SYN_RECV reqsk_timer_handler # flaky, under investigation
+verify_pkcs7_sig # keeps failing

ci/vmtest/run_selftests.sh

@@ -67,12 +67,14 @@ local_configs_path=${PROJECT_NAME}/vmtest/configs
 DENYLIST=$(read_lists \
 	"$configs_path/DENYLIST" \
 	"$configs_path/DENYLIST.${ARCH}" \
+	"$local_configs_path/DENYLIST" \
 	"$local_configs_path/DENYLIST-${KERNEL}" \
 	"$local_configs_path/DENYLIST-${KERNEL}.${ARCH}" \
 )
 ALLOWLIST=$(read_lists \
 	"$configs_path/ALLOWLIST" \
 	"$configs_path/ALLOWLIST.${ARCH}" \
+	"$local_configs_path/ALLOWLIST" \
 	"$local_configs_path/ALLOWLIST-${KERNEL}" \
 	"$local_configs_path/ALLOWLIST-${KERNEL}.${ARCH}" \
 )

docs/program_types.rst

@@ -121,6 +121,8 @@ described in more detail in the footnotes.
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
 | ``BPF_PROG_TYPE_LWT_XMIT``                |                                        | ``lwt_xmit``                     |           |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
+| ``BPF_PROG_TYPE_NETFILTER``               |                                        | ``netfilter``                    |           |
++-------------------------------------------+----------------------------------------+----------------------------------+-----------+
 | ``BPF_PROG_TYPE_PERF_EVENT``              |                                        | ``perf_event``                   |           |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
 | ``BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE`` |                                        | ``raw_tp.w+`` [#rawtp]_          |           |
@@ -131,11 +133,23 @@ described in more detail in the footnotes.
 +                                           +                                        +----------------------------------+-----------+
 |                                           |                                        | ``raw_tracepoint+``              |           |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
-| ``BPF_PROG_TYPE_SCHED_ACT``               |                                        | ``action``                       |           |
+| ``BPF_PROG_TYPE_SCHED_ACT``               |                                        | ``action`` [#tc_legacy]_         |           |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
-| ``BPF_PROG_TYPE_SCHED_CLS``               |                                        | ``classifier``                   |           |
+| ``BPF_PROG_TYPE_SCHED_CLS``               |                                        | ``classifier`` [#tc_legacy]_     |           |
 +                                           +                                        +----------------------------------+-----------+
-|                                           |                                        | ``tc``                           |           |
+|                                           |                                        | ``tc`` [#tc_legacy]_             |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_NETKIT_PRIMARY``                 | ``netkit/primary``               |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_NETKIT_PEER``                    | ``netkit/peer``                  |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_TCX_INGRESS``                    | ``tc/ingress``                   |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_TCX_EGRESS``                     | ``tc/egress``                    |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_TCX_INGRESS``                    | ``tcx/ingress``                  |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_TCX_EGRESS``                     | ``tcx/egress``                   |           |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
 | ``BPF_PROG_TYPE_SK_LOOKUP``               | ``BPF_SK_LOOKUP``                      | ``sk_lookup``                    |           |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
@@ -155,7 +169,9 @@ described in more detail in the footnotes.
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
 | ``BPF_PROG_TYPE_SOCK_OPS``                | ``BPF_CGROUP_SOCK_OPS``                | ``sockops``                      |           |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
-| ``BPF_PROG_TYPE_STRUCT_OPS``              |                                        | ``struct_ops+``                  |           |
+| ``BPF_PROG_TYPE_STRUCT_OPS``              |                                        | ``struct_ops+`` [#struct_ops]_   |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``struct_ops.s+`` [#struct_ops]_ | Yes       |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
 | ``BPF_PROG_TYPE_SYSCALL``                 |                                        | ``syscall``                      | Yes       |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
@@ -209,5 +225,11 @@ described in more detail in the footnotes.
               ``a-zA-Z0-9_.*?``.
 .. [#lsm] The ``lsm`` attachment format is ``lsm[.s]/<hook>``.
 .. [#rawtp] The ``raw_tp`` attach format is ``raw_tracepoint[.w]/<tracepoint>``.
+.. [#tc_legacy] The ``tc``, ``classifier`` and ``action`` attach types are deprecated, use
+                ``tcx/*`` instead.
+.. [#struct_ops] The ``struct_ops`` attach format supports ``struct_ops[.s]/<name>`` convention,
+                 but ``name`` is ignored and it is recommended to just use plain
+                 ``SEC("struct_ops[.s]")``. The attachments are defined in a struct initializer
+                 that is tagged with ``SEC(".struct_ops[.link]")``.
 .. [#tp] The ``tracepoint`` attach format is ``tracepoint/<category>/<name>``.
 .. [#iter] The ``iter`` attach format is ``iter[.s]/<struct-name>``.

include/uapi/linux/bpf.h

@@ -1121,6 +1121,9 @@ enum bpf_attach_type {
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
+/* Add BPF_LINK_TYPE(type, name) in bpf_types.h to keep bpf_link_type_strs[]
+ * in sync with the definitions below.
+ */
 enum bpf_link_type {
 	BPF_LINK_TYPE_UNSPEC = 0,
 	BPF_LINK_TYPE_RAW_TRACEPOINT = 1,
@@ -1425,6 +1428,8 @@ enum {
 #define BPF_F_TEST_RUN_ON_CPU	(1U << 0)
 /* If set, XDP frames will be transmitted after processing */
 #define BPF_F_TEST_XDP_LIVE_FRAMES	(1U << 1)
+/* If set, apply CHECKSUM_COMPLETE to skb and validate the checksum */
+#define BPF_F_TEST_SKB_CHECKSUM_COMPLETE	(1U << 2)
 
 /* type for BPF_ENABLE_STATS */
 enum bpf_stats_type {
@@ -1968,6 +1973,8 @@ union bpf_attr {
  * 		program.
  * 	Return
  * 		The SMP id of the processor running the program.
+ * 	Attributes
+ * 		__bpf_fastcall
  *
  * long bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags)
  * 	Description
@@ -2849,7 +2856,7 @@ union bpf_attr {
  * 		  **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**,
  * 		  **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**,
  * 		  **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**,
- * 		  **TCP_BPF_RTO_MIN**.
+ *		  **TCP_BPF_RTO_MIN**, **TCP_BPF_SOCK_OPS_CB_FLAGS**.
  * 		* **IPPROTO_IP**, which supports *optname* **IP_TOS**.
  * 		* **IPPROTO_IPV6**, which supports the following *optname*\ s:
  * 		  **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**.
@@ -3099,10 +3106,6 @@ union bpf_attr {
  * 		with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration
  * 		option, and in this case it only works on functions tagged with
  * 		**ALLOW_ERROR_INJECTION** in the kernel code.
- *
- * 		Also, the helper is only available for the architectures having
- * 		the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing,
- * 		x86 architecture is the only one to support this feature.
  * 	Return
  * 		0
  *
@@ -5367,7 +5370,7 @@ union bpf_attr {
  *		Currently, the **flags** must be 0. Currently, nr_loops is
  *		limited to 1 << 23 (~8 million) loops.
  *
- *		long (\*callback_fn)(u32 index, void \*ctx);
+ *		long (\*callback_fn)(u64 index, void \*ctx);
  *
  *		where **index** is the current index in the loop. The index
  *		is zero-indexed.
@@ -5517,11 +5520,12 @@ union bpf_attr {
  *		**-EOPNOTSUPP** if the hash calculation failed or **-EINVAL** if
  *		invalid arguments are passed.
  *
- * void *bpf_kptr_xchg(void *map_value, void *ptr)
+ * void *bpf_kptr_xchg(void *dst, void *ptr)
  *	Description
- *		Exchange kptr at pointer *map_value* with *ptr*, and return the
- *		old value. *ptr* can be NULL, otherwise it must be a referenced
- *		pointer which will be released when this helper is called.
+ *		Exchange kptr at pointer *dst* with *ptr*, and return the old value.
+ *		*dst* can be map value or local kptr. *ptr* can be NULL, otherwise
+ *		it must be a referenced pointer which will be released when this helper
+ *		is called.
  *	Return
  *		The old value of kptr (which can be NULL). The returned pointer
  *		if not NULL, is a reference which must be released using its
@@ -6044,11 +6048,6 @@ enum {
 	BPF_F_MARK_ENFORCE		= (1ULL << 6),
 };
 
-/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */
-enum {
-	BPF_F_INGRESS			= (1ULL << 0),
-};
-
 /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
 enum {
 	BPF_F_TUNINFO_IPV6		= (1ULL << 0),
@@ -6195,10 +6194,12 @@ enum {
 	BPF_F_BPRM_SECUREEXEC	= (1ULL << 0),
 };
 
-/* Flags for bpf_redirect_map helper */
+/* Flags for bpf_redirect and bpf_redirect_map helpers */
 enum {
-	BPF_F_BROADCAST		= (1ULL << 3),
-	BPF_F_EXCLUDE_INGRESS	= (1ULL << 4),
+	BPF_F_INGRESS		= (1ULL << 0), /* used for skb path */
+	BPF_F_BROADCAST		= (1ULL << 3), /* used for XDP path */
+	BPF_F_EXCLUDE_INGRESS	= (1ULL << 4), /* used for XDP path */
+#define BPF_F_REDIRECT_FLAGS (BPF_F_INGRESS | BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS)
 };
 
 #define __bpf_md_ptr(type, name)	\
@@ -7078,6 +7079,7 @@ enum {
 	TCP_BPF_SYN		= 1005, /* Copy the TCP header */
 	TCP_BPF_SYN_IP		= 1006, /* Copy the IP[46] and TCP header */
 	TCP_BPF_SYN_MAC         = 1007, /* Copy the MAC, IP[46], and TCP header */
+	TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */
 };
 
 enum {
@@ -7510,4 +7512,13 @@ struct bpf_iter_num {
 	__u64 __opaque[1];
 } __attribute__((aligned(8)));
 
+/*
+ * Flags to control BPF kfunc behaviour.
+ *     - BPF_F_PAD_ZEROS: Pad destination buffer with zeros. (See the respective
+ *       helper documentation for details.)
+ */
+enum bpf_kfunc_flags {
+	BPF_F_PAD_ZEROS = (1ULL << 0),
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */

include/uapi/linux/if_xdp.h

@@ -41,6 +41,10 @@
  */
 #define XDP_UMEM_TX_SW_CSUM		(1 << 1)
 
+/* Request to reserve tx_metadata_len bytes of per-chunk metadata.
+ */
+#define XDP_UMEM_TX_METADATA_LEN	(1 << 2)
+
 struct sockaddr_xdp {
 	__u16 sxdp_family;
 	__u16 sxdp_flags;

include/uapi/linux/netdev.h

@@ -93,6 +93,7 @@ enum {
 	NETDEV_A_PAGE_POOL_INFLIGHT,
 	NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
 	NETDEV_A_PAGE_POOL_DETACH_TIME,
+	NETDEV_A_PAGE_POOL_DMABUF,
 
 	__NETDEV_A_PAGE_POOL_MAX,
 	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
@@ -131,6 +132,7 @@ enum {
 	NETDEV_A_QUEUE_IFINDEX,
 	NETDEV_A_QUEUE_TYPE,
 	NETDEV_A_QUEUE_NAPI_ID,
+	NETDEV_A_QUEUE_DMABUF,
 
 	__NETDEV_A_QUEUE_MAX,
 	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
@@ -173,6 +175,16 @@ enum {
 	NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1)
 };
 
+enum {
+	NETDEV_A_DMABUF_IFINDEX = 1,
+	NETDEV_A_DMABUF_QUEUES,
+	NETDEV_A_DMABUF_FD,
+	NETDEV_A_DMABUF_ID,
+
+	__NETDEV_A_DMABUF_MAX,
+	NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1)
+};
+
 enum {
 	NETDEV_CMD_DEV_GET = 1,
 	NETDEV_CMD_DEV_ADD_NTF,
@@ -186,6 +198,7 @@ enum {
 	NETDEV_CMD_QUEUE_GET,
 	NETDEV_CMD_NAPI_GET,
 	NETDEV_CMD_QSTATS_GET,
+	NETDEV_CMD_BIND_RX,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)

include/uapi/linux/perf_event.h

@@ -1349,12 +1349,14 @@ union perf_mem_data_src {
 #define PERF_MEM_LVLNUM_L2	0x02 /* L2 */
 #define PERF_MEM_LVLNUM_L3	0x03 /* L3 */
 #define PERF_MEM_LVLNUM_L4	0x04 /* L4 */
-/* 5-0x7 available */
+#define PERF_MEM_LVLNUM_L2_MHB	0x05 /* L2 Miss Handling Buffer */
+#define PERF_MEM_LVLNUM_MSC	0x06 /* Memory-side Cache */
+/* 0x7 available */
 #define PERF_MEM_LVLNUM_UNC	0x08 /* Uncached */
 #define PERF_MEM_LVLNUM_CXL	0x09 /* CXL */
 #define PERF_MEM_LVLNUM_IO	0x0a /* I/O */
 #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */
-#define PERF_MEM_LVLNUM_LFB	0x0c /* LFB */
+#define PERF_MEM_LVLNUM_LFB	0x0c /* LFB / L1 Miss Handling Buffer */
 #define PERF_MEM_LVLNUM_RAM	0x0d /* RAM */
 #define PERF_MEM_LVLNUM_PMEM	0x0e /* PMEM */
 #define PERF_MEM_LVLNUM_NA	0x0f /* N/A */

src/Makefile

@@ -55,7 +55,7 @@ STATIC_OBJDIR := $(OBJDIR)/staticobjs
 OBJS := bpf.o btf.o libbpf.o libbpf_errno.o netlink.o \
 	nlattr.o str_error.o libbpf_probes.o bpf_prog_linfo.o \
 	btf_dump.o hashmap.o ringbuf.o strset.o linker.o gen_loader.o \
-	relo_core.o usdt.o zip.o elf.o features.o
+	relo_core.o usdt.o zip.o elf.o features.o btf_iter.o btf_relocate.o
 SHARED_OBJS := $(addprefix $(SHARED_OBJDIR)/,$(OBJS))
 STATIC_OBJS := $(addprefix $(STATIC_OBJDIR)/,$(OBJS))
 
@@ -119,13 +119,13 @@ $(OBJDIR)/libbpf.so.$(LIBBPF_VERSION): $(SHARED_OBJS)
 		  -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \
 		  $^ $(ALL_LDFLAGS) -o $@
 
-$(OBJDIR)/libbpf.pc: force
+$(OBJDIR)/libbpf.pc: force | $(OBJDIR)
 	$(Q)sed -e "s|@PREFIX@|$(PREFIX)|" \
 		-e "s|@LIBDIR@|$(LIBDIR_PC)|" \
 		-e "s|@VERSION@|$(LIBBPF_VERSION)|" \
 		< libbpf.pc.template > $@
 
-$(STATIC_OBJDIR) $(SHARED_OBJDIR):
+$(OBJDIR) $(STATIC_OBJDIR) $(SHARED_OBJDIR):
 	$(call msg,MKDIR,$@)
 	$(Q)mkdir -p $@
 

src/bpf.h

@@ -100,7 +100,7 @@ struct bpf_prog_load_opts {
 	__u32 log_level;
 	__u32 log_size;
 	char *log_buf;
-	/* output: actual total log contents size (including termintaing zero).
+	/* output: actual total log contents size (including terminating zero).
 	 * It could be both larger than original log_size (if log was
 	 * truncated), or smaller (if log buffer wasn't filled completely).
 	 * If kernel doesn't support this feature, log_size is left unchanged.
@@ -129,7 +129,7 @@ struct bpf_btf_load_opts {
 	char *log_buf;
 	__u32 log_level;
 	__u32 log_size;
-	/* output: actual total log contents size (including termintaing zero).
+	/* output: actual total log contents size (including terminating zero).
 	 * It could be both larger than original log_size (if log was
 	 * truncated), or smaller (if log buffer wasn't filled completely).
 	 * If kernel doesn't support this feature, log_size is left unchanged.

src/bpf_gen_internal.h

@@ -34,6 +34,7 @@ struct bpf_gen {
 	void *data_cur;
 	void *insn_start;
 	void *insn_cur;
+	bool swapped_endian;
 	ssize_t cleanup_label;
 	__u32 nr_progs;
 	__u32 nr_maps;

src/bpf_helper_defs.h

@@ -44,6 +44,14 @@ struct bpf_dynptr;
 struct iphdr;
 struct ipv6hdr;
 
+#ifndef __bpf_fastcall
+#if __has_attribute(bpf_fastcall)
+#define __bpf_fastcall __attribute__((bpf_fastcall))
+#else
+#define __bpf_fastcall
+#endif
+#endif
+
 /*
  * bpf_map_lookup_elem
  *
@@ -203,7 +211,7 @@ static __u32 (* const bpf_get_prandom_u32)(void) = (void *) 7;
  * Returns
  * 	The SMP id of the processor running the program.
  */
-static __u32 (* const bpf_get_smp_processor_id)(void) = (void *) 8;
+static __bpf_fastcall __u32 (* const bpf_get_smp_processor_id)(void) = (void *) 8;
 
 /*
  * bpf_skb_store_bytes
@@ -1224,7 +1232,7 @@ static long (* const bpf_set_hash)(struct __sk_buff *skb, __u32 hash) = (void *)
  * 	  **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**,
  * 	  **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**,
  * 	  **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**,
- * 	  **TCP_BPF_RTO_MIN**.
+ * 	  **TCP_BPF_RTO_MIN**, **TCP_BPF_SOCK_OPS_CB_FLAGS**.
  * 	* **IPPROTO_IP**, which supports *optname* **IP_TOS**.
  * 	* **IPPROTO_IPV6**, which supports the following *optname*\ s:
  * 	  **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**.
@@ -1511,10 +1519,6 @@ static long (* const bpf_getsockopt)(void *bpf_socket, int level, int optname, v
  * 	option, and in this case it only works on functions tagged with
  * 	**ALLOW_ERROR_INJECTION** in the kernel code.
  *
- * 	Also, the helper is only available for the architectures having
- * 	the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing,
- * 	x86 architecture is the only one to support this feature.
- *
  * Returns
  * 	0
  */
@@ -4220,7 +4224,7 @@ static long (* const bpf_find_vma)(struct task_struct *task, __u64 addr, void *c
  * 	Currently, the **flags** must be 0. Currently, nr_loops is
  * 	limited to 1 << 23 (~8 million) loops.
  *
- * 	long (\*callback_fn)(u32 index, void \*ctx);
+ * 	long (\*callback_fn)(u64 index, void \*ctx);
  *
  * 	where **index** is the current index in the loop. The index
  * 	is zero-indexed.
@@ -4424,9 +4428,10 @@ static long (* const bpf_ima_file_hash)(struct file *file, void *dst, __u32 size
 /*
  * bpf_kptr_xchg
  *
- * 	Exchange kptr at pointer *map_value* with *ptr*, and return the
- * 	old value. *ptr* can be NULL, otherwise it must be a referenced
- * 	pointer which will be released when this helper is called.
+ * 	Exchange kptr at pointer *dst* with *ptr*, and return the old value.
+ * 	*dst* can be map value or local kptr. *ptr* can be NULL, otherwise
+ * 	it must be a referenced pointer which will be released when this helper
+ * 	is called.
  *
  * Returns
  * 	The old value of kptr (which can be NULL). The returned pointer
@@ -4434,7 +4439,7 @@ static long (* const bpf_ima_file_hash)(struct file *file, void *dst, __u32 size
  * 	corresponding release function, or moved into a BPF map before
  * 	program exit.
  */
-static void *(* const bpf_kptr_xchg)(void *map_value, void *ptr) = (void *) 194;
+static void *(* const bpf_kptr_xchg)(void *dst, void *ptr) = (void *) 194;
 
 /*
  * bpf_map_lookup_percpu_elem

src/bpf_helpers.h

@@ -185,6 +185,7 @@ enum libbpf_tristate {
 #define __kptr_untrusted __attribute__((btf_type_tag("kptr_untrusted")))
 #define __kptr __attribute__((btf_type_tag("kptr")))
 #define __percpu_kptr __attribute__((btf_type_tag("percpu_kptr")))
+#define __uptr __attribute__((btf_type_tag("uptr")))
 
 #if defined (__clang__)
 #define bpf_ksym_exists(sym) ({						\
@@ -341,7 +342,7 @@ extern void bpf_iter_num_destroy(struct bpf_iter_num *it) __weak __ksym;
  * I.e., it looks almost like high-level for each loop in other languages,
  * supports continue/break, and is verifiable by BPF verifier.
  *
- * For iterating integers, the difference betwen bpf_for_each(num, i, N, M)
+ * For iterating integers, the difference between bpf_for_each(num, i, N, M)
  * and bpf_for(i, N, M) is in that bpf_for() provides additional proof to
  * verifier that i is in [N, M) range, and in bpf_for_each() case i is `int
  * *`, not just `int`. So for integers bpf_for() is more convenient.

src/bpf_tracing.h

@@ -163,7 +163,7 @@
 
 struct pt_regs___s390 {
 	unsigned long orig_gpr2;
-};
+} __attribute__((preserve_access_index));
 
 /* s390 provides user_pt_regs instead of struct pt_regs to userspace */
 #define __PT_REGS_CAST(x) ((const user_pt_regs *)(x))
@@ -179,7 +179,7 @@ struct pt_regs___s390 {
 #define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
 #define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
 #define __PT_PARM6_SYSCALL_REG gprs[7]
-#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x)
+#define PT_REGS_PARM1_SYSCALL(x) (((const struct pt_regs___s390 *)(x))->__PT_PARM1_SYSCALL_REG)
 #define PT_REGS_PARM1_CORE_SYSCALL(x) \
 	BPF_CORE_READ((const struct pt_regs___s390 *)(x), __PT_PARM1_SYSCALL_REG)
 
@@ -222,7 +222,7 @@ struct pt_regs___s390 {
 
 struct pt_regs___arm64 {
 	unsigned long orig_x0;
-};
+} __attribute__((preserve_access_index));
 
 /* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
 #define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x))
@@ -241,7 +241,7 @@ struct pt_regs___arm64 {
 #define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
 #define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
 #define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
-#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x)
+#define PT_REGS_PARM1_SYSCALL(x) (((const struct pt_regs___arm64 *)(x))->__PT_PARM1_SYSCALL_REG)
 #define PT_REGS_PARM1_CORE_SYSCALL(x) \
 	BPF_CORE_READ((const struct pt_regs___arm64 *)(x), __PT_PARM1_SYSCALL_REG)
 
@@ -351,6 +351,10 @@ struct pt_regs___arm64 {
  * https://github.com/riscv-non-isa/riscv-elf-psabi-doc/blob/master/riscv-cc.adoc#risc-v-calling-conventions
  */
 
+struct pt_regs___riscv {
+	unsigned long orig_a0;
+} __attribute__((preserve_access_index));
+
 /* riscv provides struct user_regs_struct instead of struct pt_regs to userspace */
 #define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x))
 #define __PT_PARM1_REG a0
@@ -362,12 +366,15 @@ struct pt_regs___arm64 {
 #define __PT_PARM7_REG a6
 #define __PT_PARM8_REG a7
 
-#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG
+#define __PT_PARM1_SYSCALL_REG orig_a0
 #define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
 #define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
 #define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
 #define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
 #define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
+#define PT_REGS_PARM1_SYSCALL(x) (((const struct pt_regs___riscv *)(x))->__PT_PARM1_SYSCALL_REG)
+#define PT_REGS_PARM1_CORE_SYSCALL(x) \
+	BPF_CORE_READ((const struct pt_regs___riscv *)(x), __PT_PARM1_SYSCALL_REG)
 
 #define __PT_RET_REG ra
 #define __PT_FP_REG s0
@@ -473,7 +480,7 @@ struct pt_regs;
 #endif
 /*
  * Similarly, syscall-specific conventions might differ between function call
- * conventions within each architecutre. All supported architectures pass
+ * conventions within each architecture. All supported architectures pass
  * either 6 or 7 syscall arguments in registers.
  *
  * See syscall(2) manpage for succinct table with information on each arch.
@@ -515,7 +522,7 @@ struct pt_regs;
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = (ctx)->link; })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
 
-#elif defined(bpf_target_sparc)
+#elif defined(bpf_target_sparc) || defined(bpf_target_arm64)
 
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = PT_REGS_RET(ctx); })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
@@ -651,7 +658,7 @@ struct pt_regs;
  * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and
  * similar kinds of BPF programs, that accept input arguments as a single
  * pointer to untyped u64 array, where each u64 can actually be a typed
- * pointer or integer of different size. Instead of requring user to write
+ * pointer or integer of different size. Instead of requiring user to write
  * manual casts and work with array elements by index, BPF_PROG macro
  * allows user to declare a list of named and typed input arguments in the
  * same syntax as for normal C function. All the casting is hidden and
@@ -801,7 +808,7 @@ struct pt_regs;
  * tp_btf/fentry/fexit BPF programs. It hides the underlying platform-specific
  * low-level way of getting kprobe input arguments from struct pt_regs, and
  * provides a familiar typed and named function arguments syntax and
- * semantics of accessing kprobe input paremeters.
+ * semantics of accessing kprobe 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().

src/btf.h

@@ -18,6 +18,7 @@ extern "C" {
 
 #define BTF_ELF_SEC ".BTF"
 #define BTF_EXT_ELF_SEC ".BTF.ext"
+#define BTF_BASE_ELF_SEC ".BTF.base"
 #define MAPS_ELF_SEC ".maps"
 
 struct btf;
@@ -107,6 +108,27 @@ LIBBPF_API struct btf *btf__new_empty(void);
  */
 LIBBPF_API struct btf *btf__new_empty_split(struct btf *base_btf);
 
+/**
+ * @brief **btf__distill_base()** creates new versions of the split BTF
+ * *src_btf* and its base BTF. The new base BTF will only contain the types
+ * needed to improve robustness of the split BTF to small changes in base BTF.
+ * When that split BTF is loaded against a (possibly changed) base, this
+ * distilled base BTF will help update references to that (possibly changed)
+ * base BTF.
+ *
+ * Both the new split and its associated new base BTF must be freed by
+ * the caller.
+ *
+ * If successful, 0 is returned and **new_base_btf** and **new_split_btf**
+ * will point at new base/split BTF. Both the new split and its associated
+ * new base BTF must be freed by the caller.
+ *
+ * A negative value is returned on error and the thread-local `errno` variable
+ * is set to the error code as well.
+ */
+LIBBPF_API int btf__distill_base(const struct btf *src_btf, struct btf **new_base_btf,
+				 struct btf **new_split_btf);
+
 LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext);
 LIBBPF_API struct btf *btf__parse_split(const char *path, struct btf *base_btf);
 LIBBPF_API struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext);
@@ -145,6 +167,9 @@ LIBBPF_API const char *btf__str_by_offset(const struct btf *btf, __u32 offset);
 LIBBPF_API struct btf_ext *btf_ext__new(const __u8 *data, __u32 size);
 LIBBPF_API void btf_ext__free(struct btf_ext *btf_ext);
 LIBBPF_API const void *btf_ext__raw_data(const struct btf_ext *btf_ext, __u32 *size);
+LIBBPF_API enum btf_endianness btf_ext__endianness(const struct btf_ext *btf_ext);
+LIBBPF_API int btf_ext__set_endianness(struct btf_ext *btf_ext,
+				       enum btf_endianness endian);
 
 LIBBPF_API int btf__find_str(struct btf *btf, const char *s);
 LIBBPF_API int btf__add_str(struct btf *btf, const char *s);
@@ -231,6 +256,20 @@ struct btf_dedup_opts {
 
 LIBBPF_API int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts);
 
+/**
+ * @brief **btf__relocate()** will check the split BTF *btf* for references
+ * to base BTF kinds, and verify those references are compatible with
+ * *base_btf*; if they are, *btf* is adjusted such that is re-parented to
+ * *base_btf* and type ids and strings are adjusted to accommodate this.
+ *
+ * If successful, 0 is returned and **btf** now has **base_btf** as its
+ * base.
+ *
+ * A negative value is returned on error and the thread-local `errno` variable
+ * is set to the error code as well.
+ */
+LIBBPF_API int btf__relocate(struct btf *btf, const struct btf *base_btf);
+
 struct btf_dump;
 
 struct btf_dump_opts {
@@ -250,7 +289,7 @@ LIBBPF_API void btf_dump__free(struct btf_dump *d);
 LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id);
 
 struct btf_dump_emit_type_decl_opts {
-	/* size of this struct, for forward/backward compatiblity */
+	/* size of this struct, for forward/backward compatibility */
 	size_t sz;
 	/* optional field name for type declaration, e.g.:
 	 * - struct my_struct <FNAME>

src/btf_dump.c

@@ -304,7 +304,7 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id)
  * definition, in which case they have to be declared inline as part of field
  * type declaration; or as a top-level anonymous enum, typically used for
  * declaring global constants. It's impossible to distinguish between two
- * without knowning whether given enum type was referenced from other type:
+ * without knowing whether given enum type was referenced from other type:
  * top-level anonymous enum won't be referenced by anything, while embedded
  * one will.
  */
@@ -867,8 +867,8 @@ static void btf_dump_emit_bit_padding(const struct btf_dump *d,
 	} pads[] = {
 		{"long", d->ptr_sz * 8}, {"int", 32}, {"short", 16}, {"char", 8}
 	};
-	int new_off, pad_bits, bits, i;
-	const char *pad_type;
+	int new_off = 0, pad_bits = 0, bits, i;
+	const char *pad_type = NULL;
 
 	if (cur_off >= next_off)
 		return; /* no gap */
@@ -1304,7 +1304,7 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id,
 			 * chain, restore stack, emit warning, and try to
 			 * proceed nevertheless
 			 */
-			pr_warn("not enough memory for decl stack:%d", err);
+			pr_warn("not enough memory for decl stack: %d\n", err);
 			d->decl_stack_cnt = stack_start;
 			return;
 		}
@@ -1559,10 +1559,12 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 			 * Clang for BPF target generates func_proto with no
 			 * args as a func_proto with a single void arg (e.g.,
 			 * `int (*f)(void)` vs just `int (*f)()`). We are
-			 * going to pretend there are no args for such case.
+			 * going to emit valid empty args (void) syntax for
+			 * such case. Similarly and conveniently, valid
+			 * no args case can be special-cased here as well.
 			 */
-			if (vlen == 1 && p->type == 0) {
-				btf_dump_printf(d, ")");
+			if (vlen == 0 || (vlen == 1 && p->type == 0)) {
+				btf_dump_printf(d, "void)");
 				return;
 			}
 

src/btf_iter.c

@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/* Copyright (c) 2021 Facebook */
+/* Copyright (c) 2024, Oracle and/or its affiliates. */
+
+#ifdef __KERNEL__
+#include <linux/bpf.h>
+#include <linux/btf.h>
+
+#define btf_var_secinfos(t)	(struct btf_var_secinfo *)btf_type_var_secinfo(t)
+
+#else
+#include "btf.h"
+#include "libbpf_internal.h"
+#endif
+
+int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t,
+			enum btf_field_iter_kind iter_kind)
+{
+	it->p = NULL;
+	it->m_idx = -1;
+	it->off_idx = 0;
+	it->vlen = 0;
+
+	switch (iter_kind) {
+	case BTF_FIELD_ITER_IDS:
+		switch (btf_kind(t)) {
+		case BTF_KIND_UNKN:
+		case BTF_KIND_INT:
+		case BTF_KIND_FLOAT:
+		case BTF_KIND_ENUM:
+		case BTF_KIND_ENUM64:
+			it->desc = (struct btf_field_desc) {};
+			break;
+		case BTF_KIND_FWD:
+		case BTF_KIND_CONST:
+		case BTF_KIND_VOLATILE:
+		case BTF_KIND_RESTRICT:
+		case BTF_KIND_PTR:
+		case BTF_KIND_TYPEDEF:
+		case BTF_KIND_FUNC:
+		case BTF_KIND_VAR:
+		case BTF_KIND_DECL_TAG:
+		case BTF_KIND_TYPE_TAG:
+			it->desc = (struct btf_field_desc) { 1, {offsetof(struct btf_type, type)} };
+			break;
+		case BTF_KIND_ARRAY:
+			it->desc = (struct btf_field_desc) {
+				2, {sizeof(struct btf_type) + offsetof(struct btf_array, type),
+				sizeof(struct btf_type) + offsetof(struct btf_array, index_type)}
+			};
+			break;
+		case BTF_KIND_STRUCT:
+		case BTF_KIND_UNION:
+			it->desc = (struct btf_field_desc) {
+				0, {},
+				sizeof(struct btf_member),
+				1, {offsetof(struct btf_member, type)}
+			};
+			break;
+		case BTF_KIND_FUNC_PROTO:
+			it->desc = (struct btf_field_desc) {
+				1, {offsetof(struct btf_type, type)},
+				sizeof(struct btf_param),
+				1, {offsetof(struct btf_param, type)}
+			};
+			break;
+		case BTF_KIND_DATASEC:
+			it->desc = (struct btf_field_desc) {
+				0, {},
+				sizeof(struct btf_var_secinfo),
+				1, {offsetof(struct btf_var_secinfo, type)}
+			};
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case BTF_FIELD_ITER_STRS:
+		switch (btf_kind(t)) {
+		case BTF_KIND_UNKN:
+			it->desc = (struct btf_field_desc) {};
+			break;
+		case BTF_KIND_INT:
+		case BTF_KIND_FLOAT:
+		case BTF_KIND_FWD:
+		case BTF_KIND_ARRAY:
+		case BTF_KIND_CONST:
+		case BTF_KIND_VOLATILE:
+		case BTF_KIND_RESTRICT:
+		case BTF_KIND_PTR:
+		case BTF_KIND_TYPEDEF:
+		case BTF_KIND_FUNC:
+		case BTF_KIND_VAR:
+		case BTF_KIND_DECL_TAG:
+		case BTF_KIND_TYPE_TAG:
+		case BTF_KIND_DATASEC:
+			it->desc = (struct btf_field_desc) {
+				1, {offsetof(struct btf_type, name_off)}
+			};
+			break;
+		case BTF_KIND_ENUM:
+			it->desc = (struct btf_field_desc) {
+				1, {offsetof(struct btf_type, name_off)},
+				sizeof(struct btf_enum),
+				1, {offsetof(struct btf_enum, name_off)}
+			};
+			break;
+		case BTF_KIND_ENUM64:
+			it->desc = (struct btf_field_desc) {
+				1, {offsetof(struct btf_type, name_off)},
+				sizeof(struct btf_enum64),
+				1, {offsetof(struct btf_enum64, name_off)}
+			};
+			break;
+		case BTF_KIND_STRUCT:
+		case BTF_KIND_UNION:
+			it->desc = (struct btf_field_desc) {
+				1, {offsetof(struct btf_type, name_off)},
+				sizeof(struct btf_member),
+				1, {offsetof(struct btf_member, name_off)}
+			};
+			break;
+		case BTF_KIND_FUNC_PROTO:
+			it->desc = (struct btf_field_desc) {
+				1, {offsetof(struct btf_type, name_off)},
+				sizeof(struct btf_param),
+				1, {offsetof(struct btf_param, name_off)}
+			};
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (it->desc.m_sz)
+		it->vlen = btf_vlen(t);
+
+	it->p = t;
+	return 0;
+}
+
+__u32 *btf_field_iter_next(struct btf_field_iter *it)
+{
+	if (!it->p)
+		return NULL;
+
+	if (it->m_idx < 0) {
+		if (it->off_idx < it->desc.t_off_cnt)
+			return it->p + it->desc.t_offs[it->off_idx++];
+		/* move to per-member iteration */
+		it->m_idx = 0;
+		it->p += sizeof(struct btf_type);
+		it->off_idx = 0;
+	}
+
+	/* if type doesn't have members, stop */
+	if (it->desc.m_sz == 0) {
+		it->p = NULL;
+		return NULL;
+	}
+
+	if (it->off_idx >= it->desc.m_off_cnt) {
+		/* exhausted this member's fields, go to the next member */
+		it->m_idx++;
+		it->p += it->desc.m_sz;
+		it->off_idx = 0;
+	}
+
+	if (it->m_idx < it->vlen)
+		return it->p + it->desc.m_offs[it->off_idx++];
+
+	it->p = NULL;
+	return NULL;
+}

src/btf_relocate.c

@@ -0,0 +1,519 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/* Copyright (c) 2024, Oracle and/or its affiliates. */
+
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE
+#endif
+
+#ifdef __KERNEL__
+#include <linux/bpf.h>
+#include <linux/bsearch.h>
+#include <linux/btf.h>
+#include <linux/sort.h>
+#include <linux/string.h>
+#include <linux/bpf_verifier.h>
+
+#define btf_type_by_id				(struct btf_type *)btf_type_by_id
+#define btf__type_cnt				btf_nr_types
+#define btf__base_btf				btf_base_btf
+#define btf__name_by_offset			btf_name_by_offset
+#define btf__str_by_offset			btf_str_by_offset
+#define btf_kflag				btf_type_kflag
+
+#define calloc(nmemb, sz)			kvcalloc(nmemb, sz, GFP_KERNEL | __GFP_NOWARN)
+#define free(ptr)				kvfree(ptr)
+#define qsort(base, num, sz, cmp)		sort(base, num, sz, cmp, NULL)
+
+#else
+
+#include "btf.h"
+#include "bpf.h"
+#include "libbpf.h"
+#include "libbpf_internal.h"
+
+#endif /* __KERNEL__ */
+
+struct btf;
+
+struct btf_relocate {
+	struct btf *btf;
+	const struct btf *base_btf;
+	const struct btf *dist_base_btf;
+	unsigned int nr_base_types;
+	unsigned int nr_split_types;
+	unsigned int nr_dist_base_types;
+	int dist_str_len;
+	int base_str_len;
+	__u32 *id_map;
+	__u32 *str_map;
+};
+
+/* Set temporarily in relocation id_map if distilled base struct/union is
+ * embedded in a split BTF struct/union; in such a case, size information must
+ * match between distilled base BTF and base BTF representation of type.
+ */
+#define BTF_IS_EMBEDDED ((__u32)-1)
+
+/* <name, size, id> triple used in sorting/searching distilled base BTF. */
+struct btf_name_info {
+	const char *name;
+	/* set when search requires a size match */
+	bool needs_size: 1;
+	unsigned int size: 31;
+	__u32 id;
+};
+
+static int btf_relocate_rewrite_type_id(struct btf_relocate *r, __u32 i)
+{
+	struct btf_type *t = btf_type_by_id(r->btf, i);
+	struct btf_field_iter it;
+	__u32 *id;
+	int err;
+
+	err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS);
+	if (err)
+		return err;
+
+	while ((id = btf_field_iter_next(&it)))
+		*id = r->id_map[*id];
+	return 0;
+}
+
+/* Simple string comparison used for sorting within BTF, since all distilled
+ * types are named.  If strings match, and size is non-zero for both elements
+ * fall back to using size for ordering.
+ */
+static int cmp_btf_name_size(const void *n1, const void *n2)
+{
+	const struct btf_name_info *ni1 = n1;
+	const struct btf_name_info *ni2 = n2;
+	int name_diff = strcmp(ni1->name, ni2->name);
+
+	if (!name_diff && ni1->needs_size && ni2->needs_size)
+		return ni2->size - ni1->size;
+	return name_diff;
+}
+
+/* Binary search with a small twist; find leftmost element that matches
+ * so that we can then iterate through all exact matches.  So for example
+ * searching { "a", "bb", "bb", "c" }  we would always match on the
+ * leftmost "bb".
+ */
+static struct btf_name_info *search_btf_name_size(struct btf_name_info *key,
+						  struct btf_name_info *vals,
+						  int nelems)
+{
+	struct btf_name_info *ret = NULL;
+	int high = nelems - 1;
+	int low = 0;
+
+	while (low <= high) {
+		int mid = (low + high)/2;
+		struct btf_name_info *val = &vals[mid];
+		int diff = cmp_btf_name_size(key, val);
+
+		if (diff == 0)
+			ret = val;
+		/* even if found, keep searching for leftmost match */
+		if (diff <= 0)
+			high = mid - 1;
+		else
+			low = mid + 1;
+	}
+	return ret;
+}
+
+/* If a member of a split BTF struct/union refers to a base BTF
+ * struct/union, mark that struct/union id temporarily in the id_map
+ * with BTF_IS_EMBEDDED.  Members can be const/restrict/volatile/typedef
+ * reference types, but if a pointer is encountered, the type is no longer
+ * considered embedded.
+ */
+static int btf_mark_embedded_composite_type_ids(struct btf_relocate *r, __u32 i)
+{
+	struct btf_type *t = btf_type_by_id(r->btf, i);
+	struct btf_field_iter it;
+	__u32 *id;
+	int err;
+
+	if (!btf_is_composite(t))
+		return 0;
+
+	err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS);
+	if (err)
+		return err;
+
+	while ((id = btf_field_iter_next(&it))) {
+		__u32 next_id = *id;
+
+		while (next_id) {
+			t = btf_type_by_id(r->btf, next_id);
+			switch (btf_kind(t)) {
+			case BTF_KIND_CONST:
+			case BTF_KIND_RESTRICT:
+			case BTF_KIND_VOLATILE:
+			case BTF_KIND_TYPEDEF:
+			case BTF_KIND_TYPE_TAG:
+				next_id = t->type;
+				break;
+			case BTF_KIND_ARRAY: {
+				struct btf_array *a = btf_array(t);
+
+				next_id = a->type;
+				break;
+			}
+			case BTF_KIND_STRUCT:
+			case BTF_KIND_UNION:
+				if (next_id < r->nr_dist_base_types)
+					r->id_map[next_id] = BTF_IS_EMBEDDED;
+				next_id = 0;
+				break;
+			default:
+				next_id = 0;
+				break;
+			}
+		}
+	}
+
+	return 0;
+}
+
+/* Build a map from distilled base BTF ids to base BTF ids. To do so, iterate
+ * through base BTF looking up distilled type (using binary search) equivalents.
+ */
+static int btf_relocate_map_distilled_base(struct btf_relocate *r)
+{
+	struct btf_name_info *info, *info_end;
+	struct btf_type *base_t, *dist_t;
+	__u8 *base_name_cnt = NULL;
+	int err = 0;
+	__u32 id;
+
+	/* generate a sort index array of name/type ids sorted by name for
+	 * distilled base BTF to speed name-based lookups.
+	 */
+	info = calloc(r->nr_dist_base_types, sizeof(*info));
+	if (!info) {
+		err = -ENOMEM;
+		goto done;
+	}
+	info_end = info + r->nr_dist_base_types;
+	for (id = 0; id < r->nr_dist_base_types; id++) {
+		dist_t = btf_type_by_id(r->dist_base_btf, id);
+		info[id].name = btf__name_by_offset(r->dist_base_btf, dist_t->name_off);
+		info[id].id = id;
+		info[id].size = dist_t->size;
+		info[id].needs_size = true;
+	}
+	qsort(info, r->nr_dist_base_types, sizeof(*info), cmp_btf_name_size);
+
+	/* Mark distilled base struct/union members of split BTF structs/unions
+	 * in id_map with BTF_IS_EMBEDDED; this signals that these types
+	 * need to match both name and size, otherwise embedding the base
+	 * struct/union in the split type is invalid.
+	 */
+	for (id = r->nr_dist_base_types; id < r->nr_split_types; id++) {
+		err = btf_mark_embedded_composite_type_ids(r, id);
+		if (err)
+			goto done;
+	}
+
+	/* Collect name counts for composite types in base BTF.  If multiple
+	 * instances of a struct/union of the same name exist, we need to use
+	 * size to determine which to map to since name alone is ambiguous.
+	 */
+	base_name_cnt = calloc(r->base_str_len, sizeof(*base_name_cnt));
+	if (!base_name_cnt) {
+		err = -ENOMEM;
+		goto done;
+	}
+	for (id = 1; id < r->nr_base_types; id++) {
+		base_t = btf_type_by_id(r->base_btf, id);
+		if (!btf_is_composite(base_t) || !base_t->name_off)
+			continue;
+		if (base_name_cnt[base_t->name_off] < 255)
+			base_name_cnt[base_t->name_off]++;
+	}
+
+	/* Now search base BTF for matching distilled base BTF types. */
+	for (id = 1; id < r->nr_base_types; id++) {
+		struct btf_name_info *dist_info, base_info = {};
+		int dist_kind, base_kind;
+
+		base_t = btf_type_by_id(r->base_btf, id);
+		/* distilled base consists of named types only. */
+		if (!base_t->name_off)
+			continue;
+		base_kind = btf_kind(base_t);
+		base_info.id = id;
+		base_info.name = btf__name_by_offset(r->base_btf, base_t->name_off);
+		switch (base_kind) {
+		case BTF_KIND_INT:
+		case BTF_KIND_FLOAT:
+		case BTF_KIND_ENUM:
+		case BTF_KIND_ENUM64:
+			/* These types should match both name and size */
+			base_info.needs_size = true;
+			base_info.size = base_t->size;
+			break;
+		case BTF_KIND_FWD:
+			/* No size considerations for fwds. */
+			break;
+		case BTF_KIND_STRUCT:
+		case BTF_KIND_UNION:
+			/* Size only needs to be used for struct/union if there
+			 * are multiple types in base BTF with the same name.
+			 * If there are multiple _distilled_ types with the same
+			 * name (a very unlikely scenario), that doesn't matter
+			 * unless corresponding _base_ types to match them are
+			 * missing.
+			 */
+			base_info.needs_size = base_name_cnt[base_t->name_off] > 1;
+			base_info.size = base_t->size;
+			break;
+		default:
+			continue;
+		}
+		/* iterate over all matching distilled base types */
+		for (dist_info = search_btf_name_size(&base_info, info, r->nr_dist_base_types);
+		     dist_info != NULL && dist_info < info_end &&
+		     cmp_btf_name_size(&base_info, dist_info) == 0;
+		     dist_info++) {
+			if (!dist_info->id || dist_info->id >= r->nr_dist_base_types) {
+				pr_warn("base BTF id [%d] maps to invalid distilled base BTF id [%d]\n",
+					id, dist_info->id);
+				err = -EINVAL;
+				goto done;
+			}
+			dist_t = btf_type_by_id(r->dist_base_btf, dist_info->id);
+			dist_kind = btf_kind(dist_t);
+
+			/* Validate that the found distilled type is compatible.
+			 * Do not error out on mismatch as another match may
+			 * occur for an identically-named type.
+			 */
+			switch (dist_kind) {
+			case BTF_KIND_FWD:
+				switch (base_kind) {
+				case BTF_KIND_FWD:
+					if (btf_kflag(dist_t) != btf_kflag(base_t))
+						continue;
+					break;
+				case BTF_KIND_STRUCT:
+					if (btf_kflag(base_t))
+						continue;
+					break;
+				case BTF_KIND_UNION:
+					if (!btf_kflag(base_t))
+						continue;
+					break;
+				default:
+					continue;
+				}
+				break;
+			case BTF_KIND_INT:
+				if (dist_kind != base_kind ||
+				    btf_int_encoding(base_t) != btf_int_encoding(dist_t))
+					continue;
+				break;
+			case BTF_KIND_FLOAT:
+				if (dist_kind != base_kind)
+					continue;
+				break;
+			case BTF_KIND_ENUM:
+				/* ENUM and ENUM64 are encoded as sized ENUM in
+				 * distilled base BTF.
+				 */
+				if (base_kind != dist_kind && base_kind != BTF_KIND_ENUM64)
+					continue;
+				break;
+			case BTF_KIND_STRUCT:
+			case BTF_KIND_UNION:
+				/* size verification is required for embedded
+				 * struct/unions.
+				 */
+				if (r->id_map[dist_info->id] == BTF_IS_EMBEDDED &&
+				    base_t->size != dist_t->size)
+					continue;
+				break;
+			default:
+				continue;
+			}
+			if (r->id_map[dist_info->id] &&
+			    r->id_map[dist_info->id] != BTF_IS_EMBEDDED) {
+				/* we already have a match; this tells us that
+				 * multiple base types of the same name
+				 * have the same size, since for cases where
+				 * multiple types have the same name we match
+				 * on name and size.  In this case, we have
+				 * no way of determining which to relocate
+				 * to in base BTF, so error out.
+				 */
+				pr_warn("distilled base BTF type '%s' [%u], size %u has multiple candidates of the same size (ids [%u, %u]) in base BTF\n",
+					base_info.name, dist_info->id,
+					base_t->size, id, r->id_map[dist_info->id]);
+				err = -EINVAL;
+				goto done;
+			}
+			/* map id and name */
+			r->id_map[dist_info->id] = id;
+			r->str_map[dist_t->name_off] = base_t->name_off;
+		}
+	}
+	/* ensure all distilled BTF ids now have a mapping... */
+	for (id = 1; id < r->nr_dist_base_types; id++) {
+		const char *name;
+
+		if (r->id_map[id] && r->id_map[id] != BTF_IS_EMBEDDED)
+			continue;
+		dist_t = btf_type_by_id(r->dist_base_btf, id);
+		name = btf__name_by_offset(r->dist_base_btf, dist_t->name_off);
+		pr_warn("distilled base BTF type '%s' [%d] is not mapped to base BTF id\n",
+			name, id);
+		err = -EINVAL;
+		break;
+	}
+done:
+	free(base_name_cnt);
+	free(info);
+	return err;
+}
+
+/* distilled base should only have named int/float/enum/fwd/struct/union types. */
+static int btf_relocate_validate_distilled_base(struct btf_relocate *r)
+{
+	unsigned int i;
+
+	for (i = 1; i < r->nr_dist_base_types; i++) {
+		struct btf_type *t = btf_type_by_id(r->dist_base_btf, i);
+		int kind = btf_kind(t);
+
+		switch (kind) {
+		case BTF_KIND_INT:
+		case BTF_KIND_FLOAT:
+		case BTF_KIND_ENUM:
+		case BTF_KIND_STRUCT:
+		case BTF_KIND_UNION:
+		case BTF_KIND_FWD:
+			if (t->name_off)
+				break;
+			pr_warn("type [%d], kind [%d] is invalid for distilled base BTF; it is anonymous\n",
+				i, kind);
+			return -EINVAL;
+		default:
+			pr_warn("type [%d] in distilled based BTF has unexpected kind [%d]\n",
+				i, kind);
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+static int btf_relocate_rewrite_strs(struct btf_relocate *r, __u32 i)
+{
+	struct btf_type *t = btf_type_by_id(r->btf, i);
+	struct btf_field_iter it;
+	__u32 *str_off;
+	int off, err;
+
+	err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_STRS);
+	if (err)
+		return err;
+
+	while ((str_off = btf_field_iter_next(&it))) {
+		if (!*str_off)
+			continue;
+		if (*str_off >= r->dist_str_len) {
+			*str_off += r->base_str_len - r->dist_str_len;
+		} else {
+			off = r->str_map[*str_off];
+			if (!off) {
+				pr_warn("string '%s' [offset %u] is not mapped to base BTF\n",
+					btf__str_by_offset(r->btf, off), *str_off);
+				return -ENOENT;
+			}
+			*str_off = off;
+		}
+	}
+	return 0;
+}
+
+/* If successful, output of relocation is updated BTF with base BTF pointing
+ * at base_btf, and type ids, strings adjusted accordingly.
+ */
+int btf_relocate(struct btf *btf, const struct btf *base_btf, __u32 **id_map)
+{
+	unsigned int nr_types = btf__type_cnt(btf);
+	const struct btf_header *dist_base_hdr;
+	const struct btf_header *base_hdr;
+	struct btf_relocate r = {};
+	int err = 0;
+	__u32 id, i;
+
+	r.dist_base_btf = btf__base_btf(btf);
+	if (!base_btf || r.dist_base_btf == base_btf)
+		return -EINVAL;
+
+	r.nr_dist_base_types = btf__type_cnt(r.dist_base_btf);
+	r.nr_base_types = btf__type_cnt(base_btf);
+	r.nr_split_types = nr_types - r.nr_dist_base_types;
+	r.btf = btf;
+	r.base_btf = base_btf;
+
+	r.id_map = calloc(nr_types, sizeof(*r.id_map));
+	r.str_map = calloc(btf_header(r.dist_base_btf)->str_len, sizeof(*r.str_map));
+	dist_base_hdr = btf_header(r.dist_base_btf);
+	base_hdr = btf_header(r.base_btf);
+	r.dist_str_len = dist_base_hdr->str_len;
+	r.base_str_len = base_hdr->str_len;
+	if (!r.id_map || !r.str_map) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	err = btf_relocate_validate_distilled_base(&r);
+	if (err)
+		goto err_out;
+
+	/* Split BTF ids need to be adjusted as base and distilled base
+	 * have different numbers of types, changing the start id of split
+	 * BTF.
+	 */
+	for (id = r.nr_dist_base_types; id < nr_types; id++)
+		r.id_map[id] = id + r.nr_base_types - r.nr_dist_base_types;
+
+	/* Build a map from distilled base ids to actual base BTF ids; it is used
+	 * to update split BTF id references.  Also build a str_map mapping from
+	 * distilled base BTF names to base BTF names.
+	 */
+	err = btf_relocate_map_distilled_base(&r);
+	if (err)
+		goto err_out;
+
+	/* Next, rewrite type ids in split BTF, replacing split ids with updated
+	 * ids based on number of types in base BTF, and base ids with
+	 * relocated ids from base_btf.
+	 */
+	for (i = 0, id = r.nr_dist_base_types; i < r.nr_split_types; i++, id++) {
+		err = btf_relocate_rewrite_type_id(&r, id);
+		if (err)
+			goto err_out;
+	}
+	/* String offsets now need to be updated using the str_map. */
+	for (i = 0; i < r.nr_split_types; i++) {
+		err = btf_relocate_rewrite_strs(&r, i + r.nr_dist_base_types);
+		if (err)
+			goto err_out;
+	}
+	/* Finally reset base BTF to be base_btf */
+	btf_set_base_btf(btf, base_btf);
+
+	if (id_map) {
+		*id_map = r.id_map;
+		r.id_map = NULL;
+	}
+err_out:
+	free(r.id_map);
+	free(r.str_map);
+	return err;
+}

src/elf.c

@@ -28,6 +28,9 @@ int elf_open(const char *binary_path, struct elf_fd *elf_fd)
 	int fd, ret;
 	Elf *elf;
 
+	elf_fd->elf = NULL;
+	elf_fd->fd = -1;
+
 	if (elf_version(EV_CURRENT) == EV_NONE) {
 		pr_warn("elf: failed to init libelf for %s\n", binary_path);
 		return -LIBBPF_ERRNO__LIBELF;

src/gen_loader.c

@@ -401,6 +401,15 @@ int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps)
 		opts->insns_sz = gen->insn_cur - gen->insn_start;
 		opts->data = gen->data_start;
 		opts->data_sz = gen->data_cur - gen->data_start;
+
+		/* use target endianness for embedded loader */
+		if (gen->swapped_endian) {
+			struct bpf_insn *insn = (struct bpf_insn *)opts->insns;
+			int insn_cnt = opts->insns_sz / sizeof(struct bpf_insn);
+
+			for (i = 0; i < insn_cnt; i++)
+				bpf_insn_bswap(insn++);
+		}
 	}
 	return gen->error;
 }
@@ -414,6 +423,28 @@ void bpf_gen__free(struct bpf_gen *gen)
 	free(gen);
 }
 
+/*
+ * Fields of bpf_attr are set to values in native byte-order before being
+ * written to the target-bound data blob, and may need endian conversion.
+ * This macro allows providing the correct value in situ more simply than
+ * writing a separate converter for *all fields* of *all records* included
+ * in union bpf_attr. Note that sizeof(rval) should match the assignment
+ * target to avoid runtime problems.
+ */
+#define tgt_endian(rval) ({					\
+	typeof(rval) _val = (rval);				\
+	if (gen->swapped_endian) {				\
+		switch (sizeof(_val)) {				\
+		case 1: break;					\
+		case 2: _val = bswap_16(_val); break;		\
+		case 4: _val = bswap_32(_val); break;		\
+		case 8: _val = bswap_64(_val); break;		\
+		default: pr_warn("unsupported bswap size!\n");	\
+		}						\
+	}							\
+	_val;							\
+})
+
 void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data,
 		       __u32 btf_raw_size)
 {
@@ -422,11 +453,12 @@ void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data,
 	union bpf_attr attr;
 
 	memset(&attr, 0, attr_size);
-	pr_debug("gen: load_btf: size %d\n", btf_raw_size);
 	btf_data = add_data(gen, btf_raw_data, btf_raw_size);
 
-	attr.btf_size = btf_raw_size;
+	attr.btf_size = tgt_endian(btf_raw_size);
 	btf_load_attr = add_data(gen, &attr, attr_size);
+	pr_debug("gen: load_btf: off %d size %d, attr: off %d size %d\n",
+		 btf_data, btf_raw_size, btf_load_attr, attr_size);
 
 	/* populate union bpf_attr with user provided log details */
 	move_ctx2blob(gen, attr_field(btf_load_attr, btf_log_level), 4,
@@ -457,28 +489,29 @@ void bpf_gen__map_create(struct bpf_gen *gen,
 	union bpf_attr attr;
 
 	memset(&attr, 0, attr_size);
-	attr.map_type = map_type;
-	attr.key_size = key_size;
-	attr.value_size = value_size;
-	attr.map_flags = map_attr->map_flags;
-	attr.map_extra = map_attr->map_extra;
+	attr.map_type = tgt_endian(map_type);
+	attr.key_size = tgt_endian(key_size);
+	attr.value_size = tgt_endian(value_size);
+	attr.map_flags = tgt_endian(map_attr->map_flags);
+	attr.map_extra = tgt_endian(map_attr->map_extra);
 	if (map_name)
 		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;
-	attr.btf_key_type_id = map_attr->btf_key_type_id;
-	attr.btf_value_type_id = map_attr->btf_value_type_id;
-
-	pr_debug("gen: map_create: %s idx %d type %d value_type_id %d\n",
-		 attr.map_name, map_idx, map_type, attr.btf_value_type_id);
+	attr.numa_node = tgt_endian(map_attr->numa_node);
+	attr.map_ifindex = tgt_endian(map_attr->map_ifindex);
+	attr.max_entries = tgt_endian(max_entries);
+	attr.btf_key_type_id = tgt_endian(map_attr->btf_key_type_id);
+	attr.btf_value_type_id = tgt_endian(map_attr->btf_value_type_id);
 
 	map_create_attr = add_data(gen, &attr, attr_size);
-	if (attr.btf_value_type_id)
+	pr_debug("gen: map_create: %s idx %d type %d value_type_id %d, attr: off %d size %d\n",
+		 map_name, map_idx, map_type, map_attr->btf_value_type_id,
+		 map_create_attr, attr_size);
+
+	if (map_attr->btf_value_type_id)
 		/* populate union bpf_attr with btf_fd saved in the stack earlier */
 		move_stack2blob(gen, attr_field(map_create_attr, btf_fd), 4,
 				stack_off(btf_fd));
-	switch (attr.map_type) {
+	switch (map_type) {
 	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
 	case BPF_MAP_TYPE_HASH_OF_MAPS:
 		move_stack2blob(gen, attr_field(map_create_attr, inner_map_fd), 4,
@@ -498,8 +531,8 @@ void bpf_gen__map_create(struct bpf_gen *gen,
 	/* emit MAP_CREATE command */
 	emit_sys_bpf(gen, BPF_MAP_CREATE, map_create_attr, attr_size);
 	debug_ret(gen, "map_create %s idx %d type %d value_size %d value_btf_id %d",
-		  attr.map_name, map_idx, map_type, value_size,
-		  attr.btf_value_type_id);
+		  map_name, map_idx, map_type, value_size,
+		  map_attr->btf_value_type_id);
 	emit_check_err(gen);
 	/* remember map_fd in the stack, if successful */
 	if (map_idx < 0) {
@@ -784,12 +817,12 @@ log:
 	emit_ksym_relo_log(gen, relo, kdesc->ref);
 }
 
-static __u32 src_reg_mask(void)
+static __u32 src_reg_mask(struct bpf_gen *gen)
 {
-#if defined(__LITTLE_ENDIAN_BITFIELD)
-	return 0x0f; /* src_reg,dst_reg,... */
-#elif defined(__BIG_ENDIAN_BITFIELD)
-	return 0xf0; /* dst_reg,src_reg,... */
+#if defined(__LITTLE_ENDIAN_BITFIELD) /* src_reg,dst_reg,... */
+	return gen->swapped_endian ? 0xf0 : 0x0f;
+#elif defined(__BIG_ENDIAN_BITFIELD) /* dst_reg,src_reg,... */
+	return gen->swapped_endian ? 0x0f : 0xf0;
 #else
 #error "Unsupported bit endianness, cannot proceed"
 #endif
@@ -840,7 +873,7 @@ static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo,
 	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 3));
 clear_src_reg:
 	/* clear bpf_object__relocate_data's src_reg assignment, otherwise we get a verifier failure */
-	reg_mask = src_reg_mask();
+	reg_mask = src_reg_mask(gen);
 	emit(gen, BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_8, offsetofend(struct bpf_insn, code)));
 	emit(gen, BPF_ALU32_IMM(BPF_AND, BPF_REG_9, reg_mask));
 	emit(gen, BPF_STX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, offsetofend(struct bpf_insn, code)));
@@ -931,48 +964,94 @@ static void cleanup_relos(struct bpf_gen *gen, int insns)
 	cleanup_core_relo(gen);
 }
 
+/* Convert func, line, and core relo info blobs to target endianness */
+static void info_blob_bswap(struct bpf_gen *gen, int func_info, int line_info,
+			    int core_relos, struct bpf_prog_load_opts *load_attr)
+{
+	struct bpf_func_info *fi = gen->data_start + func_info;
+	struct bpf_line_info *li = gen->data_start + line_info;
+	struct bpf_core_relo *cr = gen->data_start + core_relos;
+	int i;
+
+	for (i = 0; i < load_attr->func_info_cnt; i++)
+		bpf_func_info_bswap(fi++);
+
+	for (i = 0; i < load_attr->line_info_cnt; i++)
+		bpf_line_info_bswap(li++);
+
+	for (i = 0; i < gen->core_relo_cnt; i++)
+		bpf_core_relo_bswap(cr++);
+}
+
 void bpf_gen__prog_load(struct bpf_gen *gen,
 			enum bpf_prog_type prog_type, const char *prog_name,
 			const char *license, struct bpf_insn *insns, size_t insn_cnt,
 			struct bpf_prog_load_opts *load_attr, int prog_idx)
 {
+	int func_info_tot_sz = load_attr->func_info_cnt *
+			       load_attr->func_info_rec_size;
+	int line_info_tot_sz = load_attr->line_info_cnt *
+			       load_attr->line_info_rec_size;
+	int core_relo_tot_sz = gen->core_relo_cnt *
+			       sizeof(struct bpf_core_relo);
 	int prog_load_attr, license_off, insns_off, func_info, line_info, core_relos;
 	int attr_size = offsetofend(union bpf_attr, core_relo_rec_size);
 	union bpf_attr attr;
 
 	memset(&attr, 0, attr_size);
-	pr_debug("gen: prog_load: type %d insns_cnt %zd progi_idx %d\n",
-		 prog_type, insn_cnt, prog_idx);
 	/* add license string to blob of bytes */
 	license_off = add_data(gen, license, strlen(license) + 1);
 	/* add insns to blob of bytes */
 	insns_off = add_data(gen, insns, insn_cnt * sizeof(struct bpf_insn));
+	pr_debug("gen: prog_load: prog_idx %d type %d insn off %d insns_cnt %zd license off %d\n",
+		 prog_idx, prog_type, insns_off, insn_cnt, license_off);
 
-	attr.prog_type = prog_type;
-	attr.expected_attach_type = load_attr->expected_attach_type;
-	attr.attach_btf_id = load_attr->attach_btf_id;
-	attr.prog_ifindex = load_attr->prog_ifindex;
+	/* convert blob insns to target endianness */
+	if (gen->swapped_endian) {
+		struct bpf_insn *insn = gen->data_start + insns_off;
+		int i;
+
+		for (i = 0; i < insn_cnt; i++, insn++)
+			bpf_insn_bswap(insn);
+	}
+
+	attr.prog_type = tgt_endian(prog_type);
+	attr.expected_attach_type = tgt_endian(load_attr->expected_attach_type);
+	attr.attach_btf_id = tgt_endian(load_attr->attach_btf_id);
+	attr.prog_ifindex = tgt_endian(load_attr->prog_ifindex);
 	attr.kern_version = 0;
-	attr.insn_cnt = (__u32)insn_cnt;
-	attr.prog_flags = load_attr->prog_flags;
+	attr.insn_cnt = tgt_endian((__u32)insn_cnt);
+	attr.prog_flags = tgt_endian(load_attr->prog_flags);
 
-	attr.func_info_rec_size = load_attr->func_info_rec_size;
-	attr.func_info_cnt = load_attr->func_info_cnt;
-	func_info = add_data(gen, load_attr->func_info,
-			     attr.func_info_cnt * attr.func_info_rec_size);
+	attr.func_info_rec_size = tgt_endian(load_attr->func_info_rec_size);
+	attr.func_info_cnt = tgt_endian(load_attr->func_info_cnt);
+	func_info = add_data(gen, load_attr->func_info, func_info_tot_sz);
+	pr_debug("gen: prog_load: func_info: off %d cnt %d rec size %d\n",
+		 func_info, load_attr->func_info_cnt,
+		 load_attr->func_info_rec_size);
 
-	attr.line_info_rec_size = load_attr->line_info_rec_size;
-	attr.line_info_cnt = load_attr->line_info_cnt;
-	line_info = add_data(gen, load_attr->line_info,
-			     attr.line_info_cnt * attr.line_info_rec_size);
+	attr.line_info_rec_size = tgt_endian(load_attr->line_info_rec_size);
+	attr.line_info_cnt = tgt_endian(load_attr->line_info_cnt);
+	line_info = add_data(gen, load_attr->line_info, line_info_tot_sz);
+	pr_debug("gen: prog_load: line_info: off %d cnt %d rec size %d\n",
+		 line_info, load_attr->line_info_cnt,
+		 load_attr->line_info_rec_size);
 
-	attr.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);
+	attr.core_relo_rec_size = tgt_endian((__u32)sizeof(struct bpf_core_relo));
+	attr.core_relo_cnt = tgt_endian(gen->core_relo_cnt);
+	core_relos = add_data(gen, gen->core_relos, core_relo_tot_sz);
+	pr_debug("gen: prog_load: core_relos: off %d cnt %d rec size %zd\n",
+		 core_relos, gen->core_relo_cnt,
+		 sizeof(struct bpf_core_relo));
+
+	/* convert all info blobs to target endianness */
+	if (gen->swapped_endian)
+		info_blob_bswap(gen, func_info, line_info, core_relos, load_attr);
 
 	libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
 	prog_load_attr = add_data(gen, &attr, attr_size);
+	pr_debug("gen: prog_load: attr: off %d size %d\n",
+		 prog_load_attr, attr_size);
 
 	/* populate union bpf_attr with a pointer to license */
 	emit_rel_store(gen, attr_field(prog_load_attr, license), license_off);
@@ -1040,7 +1119,6 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue,
 	int zero = 0;
 
 	memset(&attr, 0, attr_size);
-	pr_debug("gen: map_update_elem: idx %d\n", map_idx);
 
 	value = add_data(gen, pvalue, value_size);
 	key = add_data(gen, &zero, sizeof(zero));
@@ -1068,6 +1146,8 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue,
 	emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel));
 
 	map_update_attr = add_data(gen, &attr, attr_size);
+	pr_debug("gen: map_update_elem: idx %d, value: off %d size %d, attr: off %d size %d\n",
+		 map_idx, value, value_size, map_update_attr, attr_size);
 	move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4,
 		       blob_fd_array_off(gen, map_idx));
 	emit_rel_store(gen, attr_field(map_update_attr, key), key);
@@ -1084,14 +1164,16 @@ void bpf_gen__populate_outer_map(struct bpf_gen *gen, int outer_map_idx, int slo
 	int attr_size = offsetofend(union bpf_attr, flags);
 	int map_update_attr, key;
 	union bpf_attr attr;
+	int tgt_slot;
 
 	memset(&attr, 0, attr_size);
-	pr_debug("gen: populate_outer_map: outer %d key %d inner %d\n",
-		 outer_map_idx, slot, inner_map_idx);
 
-	key = add_data(gen, &slot, sizeof(slot));
+	tgt_slot = tgt_endian(slot);
+	key = add_data(gen, &tgt_slot, sizeof(tgt_slot));
 
 	map_update_attr = add_data(gen, &attr, attr_size);
+	pr_debug("gen: populate_outer_map: outer %d key %d inner %d, attr: off %d size %d\n",
+		 outer_map_idx, slot, inner_map_idx, map_update_attr, attr_size);
 	move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4,
 		       blob_fd_array_off(gen, outer_map_idx));
 	emit_rel_store(gen, attr_field(map_update_attr, key), key);
@@ -1112,8 +1194,9 @@ void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx)
 	union bpf_attr attr;
 
 	memset(&attr, 0, attr_size);
-	pr_debug("gen: map_freeze: idx %d\n", map_idx);
 	map_freeze_attr = add_data(gen, &attr, attr_size);
+	pr_debug("gen: map_freeze: idx %d, attr: off %d size %d\n",
+		 map_idx, map_freeze_attr, attr_size);
 	move_blob2blob(gen, attr_field(map_freeze_attr, map_fd), 4,
 		       blob_fd_array_off(gen, map_idx));
 	/* emit MAP_FREEZE command */

src/hashmap.h

@@ -166,8 +166,8 @@ bool hashmap_find(const struct hashmap *map, long key, long *value);
  * @bkt: integer used as a bucket loop cursor
  */
 #define hashmap__for_each_entry(map, cur, bkt)				    \
-	for (bkt = 0; bkt < map->cap; bkt++)				    \
-		for (cur = map->buckets[bkt]; cur; cur = cur->next)
+	for (bkt = 0; bkt < (map)->cap; bkt++)				    \
+		for (cur = (map)->buckets[bkt]; cur; cur = cur->next)
 
 /*
  * hashmap__for_each_entry_safe - iterate over all entries in hashmap, safe
@@ -178,8 +178,8 @@ bool hashmap_find(const struct hashmap *map, long key, long *value);
  * @bkt: integer used as a bucket loop cursor
  */
 #define hashmap__for_each_entry_safe(map, cur, tmp, bkt)		    \
-	for (bkt = 0; bkt < map->cap; bkt++)				    \
-		for (cur = map->buckets[bkt];				    \
+	for (bkt = 0; bkt < (map)->cap; bkt++)				    \
+		for (cur = (map)->buckets[bkt];				    \
 		     cur && ({tmp = cur->next; true; });		    \
 		     cur = tmp)
 
@@ -190,19 +190,19 @@ bool hashmap_find(const struct hashmap *map, long key, long *value);
  * @key: key to iterate entries for
  */
 #define hashmap__for_each_key_entry(map, cur, _key)			    \
-	for (cur = map->buckets						    \
-		     ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
+	for (cur = (map)->buckets					    \
+		     ? (map)->buckets[hash_bits((map)->hash_fn((_key), (map)->ctx), (map)->cap_bits)] \
 		     : NULL;						    \
 	     cur;							    \
 	     cur = cur->next)						    \
-		if (map->equal_fn(cur->key, (_key), map->ctx))
+		if ((map)->equal_fn(cur->key, (_key), (map)->ctx))
 
 #define hashmap__for_each_key_entry_safe(map, cur, tmp, _key)		    \
-	for (cur = map->buckets						    \
-		     ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
+	for (cur = (map)->buckets					    \
+		     ? (map)->buckets[hash_bits((map)->hash_fn((_key), (map)->ctx), (map)->cap_bits)] \
 		     : NULL;						    \
 	     cur && ({ tmp = cur->next; true; });			    \
 	     cur = tmp)							    \
-		if (map->equal_fn(cur->key, (_key), map->ctx))
+		if ((map)->equal_fn(cur->key, (_key), (map)->ctx))
 
 #endif /* __LIBBPF_HASHMAP_H */

src/libbpf.c

@@ -496,8 +496,6 @@ struct bpf_program {
 };
 
 struct bpf_struct_ops {
-	const char *tname;
-	const struct btf_type *type;
 	struct bpf_program **progs;
 	__u32 *kern_func_off;
 	/* e.g. struct tcp_congestion_ops in bpf_prog's btf format */
@@ -572,6 +570,7 @@ struct bpf_map {
 	bool pinned;
 	bool reused;
 	bool autocreate;
+	bool autoattach;
 	__u64 map_extra;
 };
 
@@ -695,6 +694,8 @@ struct bpf_object {
 	/* Information when doing ELF related work. Only valid if efile.elf is not NULL */
 	struct elf_state efile;
 
+	unsigned char byteorder;
+
 	struct btf *btf;
 	struct btf_ext *btf_ext;
 
@@ -941,6 +942,20 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
 	return 0;
 }
 
+static void bpf_object_bswap_progs(struct bpf_object *obj)
+{
+	struct bpf_program *prog = obj->programs;
+	struct bpf_insn *insn;
+	int p, i;
+
+	for (p = 0; p < obj->nr_programs; p++, prog++) {
+		insn = prog->insns;
+		for (i = 0; i < prog->insns_cnt; i++, insn++)
+			bpf_insn_bswap(insn);
+	}
+	pr_debug("converted %zu BPF programs to native byte order\n", obj->nr_programs);
+}
+
 static const struct btf_member *
 find_member_by_offset(const struct btf_type *t, __u32 bit_offset)
 {
@@ -987,7 +1002,7 @@ find_struct_ops_kern_types(struct bpf_object *obj, const char *tname_raw,
 {
 	const struct btf_type *kern_type, *kern_vtype;
 	const struct btf_member *kern_data_member;
-	struct btf *btf;
+	struct btf *btf = NULL;
 	__s32 kern_vtype_id, kern_type_id;
 	char tname[256];
 	__u32 i;
@@ -1082,11 +1097,14 @@ static int bpf_object_adjust_struct_ops_autoload(struct bpf_object *obj)
 			continue;
 
 		for (j = 0; j < obj->nr_maps; ++j) {
+			const struct btf_type *type;
+
 			map = &obj->maps[j];
 			if (!bpf_map__is_struct_ops(map))
 				continue;
 
-			vlen = btf_vlen(map->st_ops->type);
+			type = btf__type_by_id(obj->btf, map->st_ops->type_id);
+			vlen = btf_vlen(type);
 			for (k = 0; k < vlen; ++k) {
 				slot_prog = map->st_ops->progs[k];
 				if (prog != slot_prog)
@@ -1114,14 +1132,14 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map)
 	const struct btf *btf = obj->btf;
 	struct bpf_struct_ops *st_ops;
 	const struct btf *kern_btf;
-	struct module_btf *mod_btf;
+	struct module_btf *mod_btf = NULL;
 	void *data, *kern_data;
 	const char *tname;
 	int err;
 
 	st_ops = map->st_ops;
-	type = st_ops->type;
-	tname = st_ops->tname;
+	type = btf__type_by_id(btf, st_ops->type_id);
+	tname = btf__name_by_offset(btf, type->name_off);
 	err = find_struct_ops_kern_types(obj, tname, &mod_btf,
 					 &kern_type, &kern_type_id,
 					 &kern_vtype, &kern_vtype_id,
@@ -1400,6 +1418,7 @@ static int init_struct_ops_maps(struct bpf_object *obj, const char *sec_name,
 		map->def.value_size = type->size;
 		map->def.max_entries = 1;
 		map->def.map_flags = strcmp(sec_name, STRUCT_OPS_LINK_SEC) == 0 ? BPF_F_LINK : 0;
+		map->autoattach = true;
 
 		map->st_ops = calloc(1, sizeof(*map->st_ops));
 		if (!map->st_ops)
@@ -1421,8 +1440,6 @@ static int init_struct_ops_maps(struct bpf_object *obj, const char *sec_name,
 		memcpy(st_ops->data,
 		       data->d_buf + vsi->offset,
 		       type->size);
-		st_ops->tname = tname;
-		st_ops->type = type;
 		st_ops->type_id = type_id;
 
 		pr_debug("struct_ops init: struct %s(type_id=%u) %s found at offset %u\n",
@@ -1505,6 +1522,7 @@ static void bpf_object__elf_finish(struct bpf_object *obj)
 
 	elf_end(obj->efile.elf);
 	obj->efile.elf = NULL;
+	obj->efile.ehdr = NULL;
 	obj->efile.symbols = NULL;
 	obj->efile.arena_data = NULL;
 
@@ -1570,6 +1588,16 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 		goto errout;
 	}
 
+	/* Validate ELF object endianness... */
+	if (ehdr->e_ident[EI_DATA] != ELFDATA2LSB &&
+	    ehdr->e_ident[EI_DATA] != ELFDATA2MSB) {
+		err = -LIBBPF_ERRNO__ENDIAN;
+		pr_warn("elf: '%s' has unknown byte order\n", obj->path);
+		goto errout;
+	}
+	/* and save after bpf_object_open() frees ELF data */
+	obj->byteorder = ehdr->e_ident[EI_DATA];
+
 	if (elf_getshdrstrndx(elf, &obj->efile.shstrndx)) {
 		pr_warn("elf: failed to get section names section index for %s: %s\n",
 			obj->path, elf_errmsg(-1));
@@ -1598,19 +1626,15 @@ errout:
 	return err;
 }
 
-static int bpf_object__check_endianness(struct bpf_object *obj)
+static bool is_native_endianness(struct bpf_object *obj)
 {
 #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
-	if (obj->efile.ehdr->e_ident[EI_DATA] == ELFDATA2LSB)
-		return 0;
+	return obj->byteorder == ELFDATA2LSB;
 #elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
-	if (obj->efile.ehdr->e_ident[EI_DATA] == ELFDATA2MSB)
-		return 0;
+	return obj->byteorder == ELFDATA2MSB;
 #else
 # error "Unrecognized __BYTE_ORDER__"
 #endif
-	pr_warn("elf: endianness mismatch in %s.\n", obj->path);
-	return -LIBBPF_ERRNO__ENDIAN;
 }
 
 static int
@@ -1847,7 +1871,7 @@ static char *internal_map_name(struct bpf_object *obj, const char *real_name)
 	snprintf(map_name, sizeof(map_name), "%.*s%.*s", pfx_len, obj->name,
 		 sfx_len, real_name);
 
-	/* sanitise map name to characters allowed by kernel */
+	/* sanities map name to characters allowed by kernel */
 	for (p = map_name; *p && p < map_name + sizeof(map_name); p++)
 		if (!isalnum(*p) && *p != '_' && *p != '.')
 			*p = '_';
@@ -3580,11 +3604,12 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 report:
 	if (err) {
 		btf_mandatory = kernel_needs_btf(obj);
-		pr_warn("Error loading .BTF into kernel: %d. %s\n", err,
-			btf_mandatory ? "BTF is mandatory, can't proceed."
-				      : "BTF is optional, ignoring.");
-		if (!btf_mandatory)
+		if (btf_mandatory) {
+			pr_warn("Error loading .BTF into kernel: %d. BTF is mandatory, can't proceed.\n", err);
+		} else {
+			pr_info("Error loading .BTF into kernel: %d. BTF is optional, ignoring.\n", err);
 			err = 0;
+		}
 	}
 	return err;
 }
@@ -3952,6 +3977,10 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 		return -LIBBPF_ERRNO__FORMAT;
 	}
 
+	/* change BPF program insns to native endianness for introspection */
+	if (!is_native_endianness(obj))
+		bpf_object_bswap_progs(obj);
+
 	/* sort BPF programs by section name and in-section instruction offset
 	 * for faster search
 	 */
@@ -3984,7 +4013,7 @@ static bool sym_is_subprog(const Elf64_Sym *sym, int text_shndx)
 		return true;
 
 	/* global function */
-	return bind == STB_GLOBAL && type == STT_FUNC;
+	return (bind == STB_GLOBAL || bind == STB_WEAK) && type == STT_FUNC;
 }
 
 static int find_extern_btf_id(const struct btf *btf, const char *ext_name)
@@ -4388,7 +4417,7 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
 
 static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog)
 {
-	return prog->sec_idx == obj->efile.text_shndx && obj->nr_programs > 1;
+	return prog->sec_idx == obj->efile.text_shndx;
 }
 
 struct bpf_program *
@@ -4819,6 +4848,20 @@ int bpf_map__set_autocreate(struct bpf_map *map, bool autocreate)
 	return 0;
 }
 
+int bpf_map__set_autoattach(struct bpf_map *map, bool autoattach)
+{
+	if (!bpf_map__is_struct_ops(map))
+		return libbpf_err(-EINVAL);
+
+	map->autoattach = autoattach;
+	return 0;
+}
+
+bool bpf_map__autoattach(const struct bpf_map *map)
+{
+	return map->autoattach;
+}
+
 int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 {
 	struct bpf_map_info info;
@@ -5079,6 +5122,7 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
 	enum libbpf_map_type map_type = map->libbpf_type;
 	char *cp, errmsg[STRERR_BUFSIZE];
 	int err, zero = 0;
+	size_t mmap_sz;
 
 	if (obj->gen_loader) {
 		bpf_gen__map_update_elem(obj->gen_loader, map - obj->maps,
@@ -5092,8 +5136,8 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
 	if (err) {
 		err = -errno;
 		cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
-		pr_warn("Error setting initial map(%s) contents: %s\n",
-			map->name, cp);
+		pr_warn("map '%s': failed to set initial contents: %s\n",
+			bpf_map__name(map), cp);
 		return err;
 	}
 
@@ -5103,11 +5147,43 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
 		if (err) {
 			err = -errno;
 			cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
-			pr_warn("Error freezing map(%s) as read-only: %s\n",
-				map->name, cp);
+			pr_warn("map '%s': failed to freeze as read-only: %s\n",
+				bpf_map__name(map), cp);
 			return err;
 		}
 	}
+
+	/* Remap anonymous mmap()-ed "map initialization image" as
+	 * a BPF map-backed mmap()-ed memory, but preserving the same
+	 * memory address. This will cause kernel to change process'
+	 * page table to point to a different piece of kernel memory,
+	 * but from userspace point of view memory address (and its
+	 * contents, being identical at this point) will stay the
+	 * same. This mapping will be released by bpf_object__close()
+	 * as per normal clean up procedure.
+	 */
+	mmap_sz = bpf_map_mmap_sz(map);
+	if (map->def.map_flags & BPF_F_MMAPABLE) {
+		void *mmaped;
+		int prot;
+
+		if (map->def.map_flags & BPF_F_RDONLY_PROG)
+			prot = PROT_READ;
+		else
+			prot = PROT_READ | PROT_WRITE;
+		mmaped = mmap(map->mmaped, mmap_sz, prot, MAP_SHARED | MAP_FIXED, map->fd, 0);
+		if (mmaped == MAP_FAILED) {
+			err = -errno;
+			pr_warn("map '%s': failed to re-mmap() contents: %d\n",
+				bpf_map__name(map), err);
+			return err;
+		}
+		map->mmaped = mmaped;
+	} else if (map->mmaped) {
+		munmap(map->mmaped, mmap_sz);
+		map->mmaped = NULL;
+	}
+
 	return 0;
 }
 
@@ -5424,8 +5500,7 @@ retry:
 				err = bpf_object__populate_internal_map(obj, map);
 				if (err < 0)
 					goto err_out;
-			}
-			if (map->def.type == BPF_MAP_TYPE_ARENA) {
+			} else if (map->def.type == BPF_MAP_TYPE_ARENA) {
 				map->mmaped = mmap((void *)(long)map->map_extra,
 						   bpf_map_mmap_sz(map), PROT_READ | PROT_WRITE,
 						   map->map_extra ? MAP_SHARED | MAP_FIXED : MAP_SHARED,
@@ -7337,8 +7412,14 @@ static int libbpf_prepare_prog_load(struct bpf_program *prog,
 		opts->prog_flags |= BPF_F_XDP_HAS_FRAGS;
 
 	/* special check for usdt to use uprobe_multi link */
-	if ((def & SEC_USDT) && kernel_supports(prog->obj, FEAT_UPROBE_MULTI_LINK))
+	if ((def & SEC_USDT) && kernel_supports(prog->obj, FEAT_UPROBE_MULTI_LINK)) {
+		/* for BPF_TRACE_UPROBE_MULTI, user might want to query expected_attach_type
+		 * in prog, and expected_attach_type we set in kernel is from opts, so we
+		 * update both.
+		 */
 		prog->expected_attach_type = BPF_TRACE_UPROBE_MULTI;
+		opts->expected_attach_type = BPF_TRACE_UPROBE_MULTI;
+	}
 
 	if ((def & SEC_ATTACH_BTF) && !prog->attach_btf_id) {
 		int btf_obj_fd = 0, btf_type_id = 0, err;
@@ -7428,6 +7509,7 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog
 	load_attr.attach_btf_id = prog->attach_btf_id;
 	load_attr.kern_version = kern_version;
 	load_attr.prog_ifindex = prog->prog_ifindex;
+	load_attr.expected_attach_type = prog->expected_attach_type;
 
 	/* specify func_info/line_info only if kernel supports them */
 	if (obj->btf && btf__fd(obj->btf) >= 0 && kernel_supports(obj, FEAT_BTF_FUNC)) {
@@ -7459,9 +7541,6 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog
 		insns_cnt = prog->insns_cnt;
 	}
 
-	/* allow prog_prepare_load_fn to change expected_attach_type */
-	load_attr.expected_attach_type = prog->expected_attach_type;
-
 	if (obj->gen_loader) {
 		bpf_gen__prog_load(obj->gen_loader, prog->type, prog->name,
 				   license, insns, insns_cnt, &load_attr,
@@ -7890,16 +7969,19 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object
 }
 
 static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, size_t obj_buf_sz,
+					  const char *obj_name,
 					  const struct bpf_object_open_opts *opts)
 {
-	const char *obj_name, *kconfig, *btf_tmp_path, *token_path;
+	const char *kconfig, *btf_tmp_path, *token_path;
 	struct bpf_object *obj;
-	char tmp_name[64];
 	int err;
 	char *log_buf;
 	size_t log_size;
 	__u32 log_level;
 
+	if (obj_buf && !obj_name)
+		return ERR_PTR(-EINVAL);
+
 	if (elf_version(EV_CURRENT) == EV_NONE) {
 		pr_warn("failed to init libelf for %s\n",
 			path ? : "(mem buf)");
@@ -7909,16 +7991,12 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf,
 	if (!OPTS_VALID(opts, bpf_object_open_opts))
 		return ERR_PTR(-EINVAL);
 
-	obj_name = OPTS_GET(opts, object_name, NULL);
+	obj_name = OPTS_GET(opts, object_name, NULL) ?: obj_name;
 	if (obj_buf) {
-		if (!obj_name) {
-			snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx",
-				 (unsigned long)obj_buf,
-				 (unsigned long)obj_buf_sz);
-			obj_name = tmp_name;
-		}
 		path = obj_name;
 		pr_debug("loading object '%s' from buffer\n", obj_name);
+	} else {
+		pr_debug("loading object from %s\n", path);
 	}
 
 	log_buf = OPTS_GET(opts, kernel_log_buf, NULL);
@@ -7978,7 +8056,6 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf,
 	}
 
 	err = bpf_object__elf_init(obj);
-	err = err ? : bpf_object__check_endianness(obj);
 	err = err ? : bpf_object__elf_collect(obj);
 	err = err ? : bpf_object__collect_externs(obj);
 	err = err ? : bpf_object_fixup_btf(obj);
@@ -8002,9 +8079,7 @@ bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts)
 	if (!path)
 		return libbpf_err_ptr(-EINVAL);
 
-	pr_debug("loading %s\n", path);
-
-	return libbpf_ptr(bpf_object_open(path, NULL, 0, opts));
+	return libbpf_ptr(bpf_object_open(path, NULL, 0, NULL, opts));
 }
 
 struct bpf_object *bpf_object__open(const char *path)
@@ -8016,10 +8091,15 @@ struct bpf_object *
 bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz,
 		     const struct bpf_object_open_opts *opts)
 {
+	char tmp_name[64];
+
 	if (!obj_buf || obj_buf_sz == 0)
 		return libbpf_err_ptr(-EINVAL);
 
-	return libbpf_ptr(bpf_object_open(NULL, obj_buf, obj_buf_sz, opts));
+	/* create a (quite useless) default "name" for this memory buffer object */
+	snprintf(tmp_name, sizeof(tmp_name), "%lx-%zx", (unsigned long)obj_buf, obj_buf_sz);
+
+	return libbpf_ptr(bpf_object_open(NULL, obj_buf, obj_buf_sz, tmp_name, opts));
 }
 
 static int bpf_object_unload(struct bpf_object *obj)
@@ -8429,11 +8509,13 @@ static int bpf_object__resolve_externs(struct bpf_object *obj,
 
 static void bpf_map_prepare_vdata(const struct bpf_map *map)
 {
+	const struct btf_type *type;
 	struct bpf_struct_ops *st_ops;
 	__u32 i;
 
 	st_ops = map->st_ops;
-	for (i = 0; i < btf_vlen(st_ops->type); i++) {
+	type = btf__type_by_id(map->obj->btf, st_ops->type_id);
+	for (i = 0; i < btf_vlen(type); i++) {
 		struct bpf_program *prog = st_ops->progs[i];
 		void *kern_data;
 		int prog_fd;
@@ -8479,8 +8561,15 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch
 		return libbpf_err(-EINVAL);
 	}
 
-	if (obj->gen_loader)
+	/* Disallow kernel loading programs of non-native endianness but
+	 * permit cross-endian creation of "light skeleton".
+	 */
+	if (obj->gen_loader) {
 		bpf_gen__init(obj->gen_loader, extra_log_level, obj->nr_programs, obj->nr_maps);
+	} else if (!is_native_endianness(obj)) {
+		pr_warn("object '%s': loading non-native endianness is unsupported\n", obj->name);
+		return libbpf_err(-LIBBPF_ERRNO__ENDIAN);
+	}
 
 	err = bpf_object_prepare_token(obj);
 	err = err ? : bpf_object__probe_loading(obj);
@@ -9040,6 +9129,11 @@ unsigned int bpf_object__kversion(const struct bpf_object *obj)
 	return obj ? obj->kern_version : 0;
 }
 
+int bpf_object__token_fd(const struct bpf_object *obj)
+{
+	return obj->token_fd ?: -1;
+}
+
 struct btf *bpf_object__btf(const struct bpf_object *obj)
 {
 	return obj ? obj->btf : NULL;
@@ -9072,6 +9166,7 @@ int bpf_object__gen_loader(struct bpf_object *obj, struct gen_loader_opts *opts)
 	if (!gen)
 		return -ENOMEM;
 	gen->opts = opts;
+	gen->swapped_endian = !is_native_endianness(obj);
 	obj->gen_loader = gen;
 	return 0;
 }
@@ -9696,6 +9791,7 @@ static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj,
 static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
 					    Elf64_Shdr *shdr, Elf_Data *data)
 {
+	const struct btf_type *type;
 	const struct btf_member *member;
 	struct bpf_struct_ops *st_ops;
 	struct bpf_program *prog;
@@ -9755,13 +9851,14 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
 		}
 		insn_idx = sym->st_value / BPF_INSN_SZ;
 
-		member = find_member_by_offset(st_ops->type, moff * 8);
+		type = btf__type_by_id(btf, st_ops->type_id);
+		member = find_member_by_offset(type, moff * 8);
 		if (!member) {
 			pr_warn("struct_ops reloc %s: cannot find member at moff %u\n",
 				map->name, moff);
 			return -EINVAL;
 		}
-		member_idx = member - btf_members(st_ops->type);
+		member_idx = member - btf_members(type);
 		name = btf__name_by_offset(btf, member->name_off);
 
 		if (!resolve_func_ptr(btf, member->type, NULL)) {
@@ -10359,7 +10456,7 @@ __bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i)
 struct bpf_map *
 bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *prev)
 {
-	if (prev == NULL)
+	if (prev == NULL && obj != NULL)
 		return obj->maps;
 
 	return __bpf_map__iter(prev, obj, 1);
@@ -10368,7 +10465,7 @@ bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *prev)
 struct bpf_map *
 bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *next)
 {
-	if (next == NULL) {
+	if (next == NULL && obj != NULL) {
 		if (!obj->nr_maps)
 			return NULL;
 		return obj->maps + obj->nr_maps - 1;
@@ -11667,7 +11764,7 @@ static int attach_uprobe_multi(const struct bpf_program *prog, long cookie, stru
 		ret = 0;
 		break;
 	case 3:
-		opts.retprobe = strcmp(probe_type, "uretprobe.multi") == 0;
+		opts.retprobe = str_has_pfx(probe_type, "uretprobe.multi");
 		*link = bpf_program__attach_uprobe_multi(prog, -1, binary_path, func_name, &opts);
 		ret = libbpf_get_error(*link);
 		break;
@@ -12734,7 +12831,7 @@ struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog,
 	}
 
 	if (prog->type != BPF_PROG_TYPE_EXT) {
-		pr_warn("prog '%s': only BPF_PROG_TYPE_EXT can attach as freplace",
+		pr_warn("prog '%s': only BPF_PROG_TYPE_EXT can attach as freplace\n",
 			prog->name);
 		return libbpf_err_ptr(-EINVAL);
 	}
@@ -12900,8 +12997,10 @@ struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map)
 	__u32 zero = 0;
 	int err, fd;
 
-	if (!bpf_map__is_struct_ops(map))
+	if (!bpf_map__is_struct_ops(map)) {
+		pr_warn("map '%s': can't attach non-struct_ops map\n", map->name);
 		return libbpf_err_ptr(-EINVAL);
+	}
 
 	if (map->fd < 0) {
 		pr_warn("map '%s': can't attach BPF map without FD (was it created?)\n", map->name);
@@ -13694,14 +13793,15 @@ int libbpf_num_possible_cpus(void)
 
 static int populate_skeleton_maps(const struct bpf_object *obj,
 				  struct bpf_map_skeleton *maps,
-				  size_t map_cnt)
+				  size_t map_cnt, size_t map_skel_sz)
 {
 	int i;
 
 	for (i = 0; i < map_cnt; i++) {
-		struct bpf_map **map = maps[i].map;
-		const char *name = maps[i].name;
-		void **mmaped = maps[i].mmaped;
+		struct bpf_map_skeleton *map_skel = (void *)maps + i * map_skel_sz;
+		struct bpf_map **map = map_skel->map;
+		const char *name = map_skel->name;
+		void **mmaped = map_skel->mmaped;
 
 		*map = bpf_object__find_map_by_name(obj, name);
 		if (!*map) {
@@ -13718,13 +13818,14 @@ static int populate_skeleton_maps(const struct bpf_object *obj,
 
 static int populate_skeleton_progs(const struct bpf_object *obj,
 				   struct bpf_prog_skeleton *progs,
-				   size_t prog_cnt)
+				   size_t prog_cnt, size_t prog_skel_sz)
 {
 	int i;
 
 	for (i = 0; i < prog_cnt; i++) {
-		struct bpf_program **prog = progs[i].prog;
-		const char *name = progs[i].name;
+		struct bpf_prog_skeleton *prog_skel = (void *)progs + i * prog_skel_sz;
+		struct bpf_program **prog = prog_skel->prog;
+		const char *name = prog_skel->name;
 
 		*prog = bpf_object__find_program_by_name(obj, name);
 		if (!*prog) {
@@ -13738,40 +13839,24 @@ static int populate_skeleton_progs(const struct bpf_object *obj,
 int bpf_object__open_skeleton(struct bpf_object_skeleton *s,
 			      const struct bpf_object_open_opts *opts)
 {
-	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, skel_opts,
-		.object_name = s->name,
-	);
 	struct bpf_object *obj;
 	int err;
 
-	/* Attempt to preserve opts->object_name, unless overriden by user
-	 * explicitly. Overwriting object name for skeletons is discouraged,
-	 * as it breaks global data maps, because they contain object name
-	 * prefix as their own map name prefix. When skeleton is generated,
-	 * bpftool is making an assumption that this name will stay the same.
-	 */
-	if (opts) {
-		memcpy(&skel_opts, opts, sizeof(*opts));
-		if (!opts->object_name)
-			skel_opts.object_name = s->name;
-	}
-
-	obj = bpf_object__open_mem(s->data, s->data_sz, &skel_opts);
-	err = libbpf_get_error(obj);
-	if (err) {
-		pr_warn("failed to initialize skeleton BPF object '%s': %d\n",
-			s->name, err);
+	obj = bpf_object_open(NULL, s->data, s->data_sz, s->name, opts);
+	if (IS_ERR(obj)) {
+		err = PTR_ERR(obj);
+		pr_warn("failed to initialize skeleton BPF object '%s': %d\n", s->name, err);
 		return libbpf_err(err);
 	}
 
 	*s->obj = obj;
-	err = populate_skeleton_maps(obj, s->maps, s->map_cnt);
+	err = populate_skeleton_maps(obj, s->maps, s->map_cnt, s->map_skel_sz);
 	if (err) {
 		pr_warn("failed to populate skeleton maps for '%s': %d\n", s->name, err);
 		return libbpf_err(err);
 	}
 
-	err = populate_skeleton_progs(obj, s->progs, s->prog_cnt);
+	err = populate_skeleton_progs(obj, s->progs, s->prog_cnt, s->prog_skel_sz);
 	if (err) {
 		pr_warn("failed to populate skeleton progs for '%s': %d\n", s->name, err);
 		return libbpf_err(err);
@@ -13801,26 +13886,26 @@ int bpf_object__open_subskeleton(struct bpf_object_subskeleton *s)
 		return libbpf_err(-errno);
 	}
 
-	err = populate_skeleton_maps(s->obj, s->maps, s->map_cnt);
+	err = populate_skeleton_maps(s->obj, s->maps, s->map_cnt, s->map_skel_sz);
 	if (err) {
 		pr_warn("failed to populate subskeleton maps: %d\n", err);
 		return libbpf_err(err);
 	}
 
-	err = populate_skeleton_progs(s->obj, s->progs, s->prog_cnt);
+	err = populate_skeleton_progs(s->obj, s->progs, s->prog_cnt, s->prog_skel_sz);
 	if (err) {
 		pr_warn("failed to populate subskeleton maps: %d\n", err);
 		return libbpf_err(err);
 	}
 
 	for (var_idx = 0; var_idx < s->var_cnt; var_idx++) {
-		var_skel = &s->vars[var_idx];
+		var_skel = (void *)s->vars + var_idx * s->var_skel_sz;
 		map = *var_skel->map;
 		map_type_id = bpf_map__btf_value_type_id(map);
 		map_type = btf__type_by_id(btf, map_type_id);
 
 		if (!btf_is_datasec(map_type)) {
-			pr_warn("type for map '%1$s' is not a datasec: %2$s",
+			pr_warn("type for map '%1$s' is not a datasec: %2$s\n",
 				bpf_map__name(map),
 				__btf_kind_str(btf_kind(map_type)));
 			return libbpf_err(-EINVAL);
@@ -13861,47 +13946,13 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s)
 	}
 
 	for (i = 0; i < s->map_cnt; i++) {
-		struct bpf_map *map = *s->maps[i].map;
-		size_t mmap_sz = bpf_map_mmap_sz(map);
-		int prot, map_fd = map->fd;
-		void **mmaped = s->maps[i].mmaped;
+		struct bpf_map_skeleton *map_skel = (void *)s->maps + i * s->map_skel_sz;
+		struct bpf_map *map = *map_skel->map;
 
-		if (!mmaped)
+		if (!map_skel->mmaped)
 			continue;
 
-		if (!(map->def.map_flags & BPF_F_MMAPABLE)) {
-			*mmaped = NULL;
-			continue;
-		}
-
-		if (map->def.type == BPF_MAP_TYPE_ARENA) {
-			*mmaped = map->mmaped;
-			continue;
-		}
-
-		if (map->def.map_flags & BPF_F_RDONLY_PROG)
-			prot = PROT_READ;
-		else
-			prot = PROT_READ | PROT_WRITE;
-
-		/* Remap anonymous mmap()-ed "map initialization image" as
-		 * a BPF map-backed mmap()-ed memory, but preserving the same
-		 * memory address. This will cause kernel to change process'
-		 * page table to point to a different piece of kernel memory,
-		 * but from userspace point of view memory address (and its
-		 * contents, being identical at this point) will stay the
-		 * same. This mapping will be released by bpf_object__close()
-		 * as per normal clean up procedure, so we don't need to worry
-		 * about it from skeleton's clean up perspective.
-		 */
-		*mmaped = mmap(map->mmaped, mmap_sz, prot, MAP_SHARED | MAP_FIXED, map_fd, 0);
-		if (*mmaped == MAP_FAILED) {
-			err = -errno;
-			*mmaped = NULL;
-			pr_warn("failed to re-mmap() map '%s': %d\n",
-				 bpf_map__name(map), err);
-			return libbpf_err(err);
-		}
+		*map_skel->mmaped = map->mmaped;
 	}
 
 	return 0;
@@ -13912,8 +13963,9 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s)
 	int i, err;
 
 	for (i = 0; i < s->prog_cnt; i++) {
-		struct bpf_program *prog = *s->progs[i].prog;
-		struct bpf_link **link = s->progs[i].link;
+		struct bpf_prog_skeleton *prog_skel = (void *)s->progs + i * s->prog_skel_sz;
+		struct bpf_program *prog = *prog_skel->prog;
+		struct bpf_link **link = prog_skel->link;
 
 		if (!prog->autoload || !prog->autoattach)
 			continue;
@@ -13945,6 +13997,38 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s)
 		 */
 	}
 
+
+	for (i = 0; i < s->map_cnt; i++) {
+		struct bpf_map_skeleton *map_skel = (void *)s->maps + i * s->map_skel_sz;
+		struct bpf_map *map = *map_skel->map;
+		struct bpf_link **link;
+
+		if (!map->autocreate || !map->autoattach)
+			continue;
+
+		/* only struct_ops maps can be attached */
+		if (!bpf_map__is_struct_ops(map))
+			continue;
+
+		/* skeleton is created with earlier version of bpftool, notify user */
+		if (s->map_skel_sz < offsetofend(struct bpf_map_skeleton, link)) {
+			pr_warn("map '%s': BPF skeleton version is old, skipping map auto-attachment...\n",
+				bpf_map__name(map));
+			continue;
+		}
+
+		link = map_skel->link;
+		if (*link)
+			continue;
+
+		*link = bpf_map__attach_struct_ops(map);
+		if (!*link) {
+			err = -errno;
+			pr_warn("map '%s': failed to auto-attach: %d\n", bpf_map__name(map), err);
+			return libbpf_err(err);
+		}
+	}
+
 	return 0;
 }
 
@@ -13953,11 +14037,25 @@ void bpf_object__detach_skeleton(struct bpf_object_skeleton *s)
 	int i;
 
 	for (i = 0; i < s->prog_cnt; i++) {
-		struct bpf_link **link = s->progs[i].link;
+		struct bpf_prog_skeleton *prog_skel = (void *)s->progs + i * s->prog_skel_sz;
+		struct bpf_link **link = prog_skel->link;
 
 		bpf_link__destroy(*link);
 		*link = NULL;
 	}
+
+	if (s->map_skel_sz < sizeof(struct bpf_map_skeleton))
+		return;
+
+	for (i = 0; i < s->map_cnt; i++) {
+		struct bpf_map_skeleton *map_skel = (void *)s->maps + i * s->map_skel_sz;
+		struct bpf_link **link = map_skel->link;
+
+		if (link) {
+			bpf_link__destroy(*link);
+			*link = NULL;
+		}
+	}
 }
 
 void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s)
@@ -13965,8 +14063,7 @@ void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s)
 	if (!s)
 		return;
 
-	if (s->progs)
-		bpf_object__detach_skeleton(s);
+	bpf_object__detach_skeleton(s);
 	if (s->obj)
 		bpf_object__close(*s->obj);
 	free(s->maps);

src/libbpf.h

@@ -152,7 +152,7 @@ struct bpf_object_open_opts {
 	 * log_buf and log_level settings.
 	 *
 	 * If specified, this log buffer will be passed for:
-	 *   - each BPF progral load (BPF_PROG_LOAD) attempt, unless overriden
+	 *   - each BPF progral load (BPF_PROG_LOAD) attempt, unless overridden
 	 *     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
@@ -294,6 +294,14 @@ LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj);
 LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj);
 LIBBPF_API int bpf_object__set_kversion(struct bpf_object *obj, __u32 kern_version);
 
+/**
+ * @brief **bpf_object__token_fd** is an accessor for BPF token FD associated
+ * with BPF object.
+ * @param obj Pointer to a valid BPF object
+ * @return BPF token FD or -1, if it wasn't set
+ */
+LIBBPF_API int bpf_object__token_fd(const struct bpf_object *obj);
+
 struct btf;
 LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj);
 LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj);
@@ -455,7 +463,7 @@ LIBBPF_API int bpf_link__destroy(struct bpf_link *link);
 /**
  * @brief **bpf_program__attach()** is a generic function for attaching
  * a BPF program based on auto-detection of program type, attach type,
- * and extra paremeters, where applicable.
+ * and extra parameters, where applicable.
  *
  * @param prog BPF program to attach
  * @return Reference to the newly created BPF link; or NULL is returned on error,
@@ -679,7 +687,7 @@ struct bpf_uprobe_opts {
 /**
  * @brief **bpf_program__attach_uprobe()** attaches a BPF program
  * to the userspace function which is found by binary path and
- * offset. You can optionally specify a particular proccess to attach
+ * offset. You can optionally specify a particular process to attach
  * to. You can also optionally attach the program to the function
  * exit instead of entry.
  *
@@ -978,6 +986,23 @@ bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *map);
 LIBBPF_API int bpf_map__set_autocreate(struct bpf_map *map, bool autocreate);
 LIBBPF_API bool bpf_map__autocreate(const struct bpf_map *map);
 
+/**
+ * @brief **bpf_map__set_autoattach()** sets whether libbpf has to auto-attach
+ * map during BPF skeleton attach phase.
+ * @param map the BPF map instance
+ * @param autoattach whether to attach map during BPF skeleton attach phase
+ * @return 0 on success; negative error code, otherwise
+ */
+LIBBPF_API int bpf_map__set_autoattach(struct bpf_map *map, bool autoattach);
+
+/**
+ * @brief **bpf_map__autoattach()** returns whether BPF map is configured to
+ * auto-attach during BPF skeleton attach phase.
+ * @param map the BPF map instance
+ * @return true if map is set to auto-attach during skeleton attach phase; false, otherwise
+ */
+LIBBPF_API bool bpf_map__autoattach(const struct bpf_map *map);
+
 /**
  * @brief **bpf_map__fd()** gets the file descriptor of the passed
  * BPF map
@@ -1576,11 +1601,11 @@ LIBBPF_API int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_i
  * memory region of the ring buffer.
  * This ring buffer can be used to implement a custom events consumer.
  * The ring buffer starts with the *struct perf_event_mmap_page*, which
- * holds the ring buffer managment fields, when accessing the header
+ * holds the ring buffer management fields, when accessing the header
  * structure it's important to be SMP aware.
  * You can refer to *perf_event_read_simple* for a simple example.
  * @param pb the perf buffer structure
- * @param buf_idx the buffer index to retreive
+ * @param buf_idx the buffer index to retrieve
  * @param buf (out) gets the base pointer of the mmap()'ed memory
  * @param buf_size (out) gets the size of the mmap()'ed region
  * @return 0 on success, negative error code for failure
@@ -1672,6 +1697,7 @@ struct bpf_map_skeleton {
 	const char *name;
 	struct bpf_map **map;
 	void **mmaped;
+	struct bpf_link **link;
 };
 
 struct bpf_prog_skeleton {

src/libbpf.map

@@ -419,6 +419,13 @@ LIBBPF_1.4.0 {
 
 LIBBPF_1.5.0 {
 	global:
+		btf__distill_base;
+		btf__relocate;
+		btf_ext__endianness;
+		btf_ext__set_endianness;
+		bpf_map__autoattach;
+		bpf_map__set_autoattach;
+		bpf_object__token_fd;
 		bpf_program__attach_sockmap;
 		ring__consume_n;
 		ring_buffer__consume_n;

src/libbpf_internal.h

@@ -10,6 +10,7 @@
 #define __LIBBPF_LIBBPF_INTERNAL_H
 
 #include <stdlib.h>
+#include <byteswap.h>
 #include <limits.h>
 #include <errno.h>
 #include <linux/err.h>
@@ -234,6 +235,9 @@ struct btf_type;
 struct btf_type *btf_type_by_id(const struct btf *btf, __u32 type_id);
 const char *btf_kind_str(const struct btf_type *t);
 const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id);
+const struct btf_header *btf_header(const struct btf *btf);
+void btf_set_base_btf(struct btf *btf, const struct btf *base_btf);
+int btf_relocate(struct btf *btf, const struct btf *base_btf, __u32 **id_map);
 
 static inline enum btf_func_linkage btf_func_linkage(const struct btf_type *t)
 {
@@ -445,11 +449,11 @@ struct btf_ext_info {
  *
  * The func_info subsection layout:
  *   record size for struct bpf_func_info in the func_info subsection
- *   struct btf_sec_func_info for section #1
+ *   struct btf_ext_info_sec for section #1
  *   a list of bpf_func_info records for section #1
  *     where struct bpf_func_info mimics one in include/uapi/linux/bpf.h
  *     but may not be identical
- *   struct btf_sec_func_info for section #2
+ *   struct btf_ext_info_sec for section #2
  *   a list of bpf_func_info records for section #2
  *   ......
  *
@@ -481,6 +485,8 @@ struct btf_ext {
 		struct btf_ext_header *hdr;
 		void *data;
 	};
+	void *data_swapped;
+	bool swapped_endian;
 	struct btf_ext_info func_info;
 	struct btf_ext_info line_info;
 	struct btf_ext_info core_relo_info;
@@ -508,11 +514,59 @@ struct bpf_line_info_min {
 	__u32	line_col;
 };
 
+/* Functions to byte-swap info records */
+
+typedef void (*info_rec_bswap_fn)(void *);
+
+static inline void bpf_func_info_bswap(struct bpf_func_info *i)
+{
+	i->insn_off = bswap_32(i->insn_off);
+	i->type_id = bswap_32(i->type_id);
+}
+
+static inline void bpf_line_info_bswap(struct bpf_line_info *i)
+{
+	i->insn_off = bswap_32(i->insn_off);
+	i->file_name_off = bswap_32(i->file_name_off);
+	i->line_off = bswap_32(i->line_off);
+	i->line_col = bswap_32(i->line_col);
+}
+
+static inline void bpf_core_relo_bswap(struct bpf_core_relo *i)
+{
+	i->insn_off = bswap_32(i->insn_off);
+	i->type_id = bswap_32(i->type_id);
+	i->access_str_off = bswap_32(i->access_str_off);
+	i->kind = bswap_32(i->kind);
+}
+
+enum btf_field_iter_kind {
+	BTF_FIELD_ITER_IDS,
+	BTF_FIELD_ITER_STRS,
+};
+
+struct btf_field_desc {
+	/* once-per-type offsets */
+	int t_off_cnt, t_offs[2];
+	/* member struct size, or zero, if no members */
+	int m_sz;
+	/* repeated per-member offsets */
+	int m_off_cnt, m_offs[1];
+};
+
+struct btf_field_iter {
+	struct btf_field_desc desc;
+	void *p;
+	int m_idx;
+	int off_idx;
+	int vlen;
+};
+
+int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t, enum btf_field_iter_kind iter_kind);
+__u32 *btf_field_iter_next(struct btf_field_iter *it);
 
 typedef int (*type_id_visit_fn)(__u32 *type_id, void *ctx);
 typedef int (*str_off_visit_fn)(__u32 *str_off, void *ctx);
-int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ctx);
-int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ctx);
 int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx);
 int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void *ctx);
 __s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name,
@@ -563,6 +617,16 @@ static inline bool is_ldimm64_insn(struct bpf_insn *insn)
 	return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
 }
 
+static inline void bpf_insn_bswap(struct bpf_insn *insn)
+{
+	__u8 tmp_reg = insn->dst_reg;
+
+	insn->dst_reg = insn->src_reg;
+	insn->src_reg = tmp_reg;
+	insn->off = bswap_16(insn->off);
+	insn->imm = bswap_32(insn->imm);
+}
+
 /* Unconditionally dup FD, ensuring it doesn't use [0, 2] range.
  * Original FD is not closed or altered in any other way.
  * Preserves original FD value, if it's invalid (negative).

src/libbpf_legacy.h

@@ -76,7 +76,7 @@ enum libbpf_strict_mode {
 	 * first BPF program or map creation operation. This is done only if
 	 * kernel is too old to support memcg-based memory accounting for BPF
 	 * subsystem. By default, RLIMIT_MEMLOCK limit is set to RLIM_INFINITY,
-	 * but it can be overriden with libbpf_set_memlock_rlim() API.
+	 * but it can be overridden with libbpf_set_memlock_rlim() API.
 	 * Note that libbpf_set_memlock_rlim() needs to be called before
 	 * the very first bpf_prog_load(), bpf_map_create() or bpf_object__load()
 	 * operation.
@@ -97,7 +97,7 @@ LIBBPF_API int libbpf_set_strict_mode(enum libbpf_strict_mode mode);
  * @brief **libbpf_get_error()** extracts the error code from the passed
  * pointer
  * @param ptr pointer returned from libbpf API function
- * @return error code; or 0 if no error occured
+ * @return error code; or 0 if no error occurred
  *
  * Note, as of libbpf 1.0 this function is not necessary and not recommended
  * to be used. Libbpf doesn't return error code embedded into the pointer

src/linker.c

@@ -135,6 +135,7 @@ struct bpf_linker {
 	int fd;
 	Elf *elf;
 	Elf64_Ehdr *elf_hdr;
+	bool swapped_endian;
 
 	/* Output sections metadata */
 	struct dst_sec *secs;
@@ -324,13 +325,8 @@ static int init_output_elf(struct bpf_linker *linker, const char *file)
 
 	linker->elf_hdr->e_machine = EM_BPF;
 	linker->elf_hdr->e_type = ET_REL;
-#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
-	linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2LSB;
-#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
-	linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2MSB;
-#else
-#error "Unknown __BYTE_ORDER__"
-#endif
+	/* Set unknown ELF endianness, assign later from input files */
+	linker->elf_hdr->e_ident[EI_DATA] = ELFDATANONE;
 
 	/* STRTAB */
 	/* initialize strset with an empty string to conform to ELF */
@@ -396,6 +392,8 @@ static int init_output_elf(struct bpf_linker *linker, const char *file)
 		pr_warn_elf("failed to create SYMTAB data");
 		return -EINVAL;
 	}
+	/* Ensure libelf translates byte-order of symbol records */
+	sec->data->d_type = ELF_T_SYM;
 
 	str_off = strset__add_str(linker->strtab_strs, sec->sec_name);
 	if (str_off < 0)
@@ -539,19 +537,21 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename,
 				const struct bpf_linker_file_opts *opts,
 				struct src_obj *obj)
 {
-#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
-	const int host_endianness = ELFDATA2LSB;
-#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
-	const int host_endianness = ELFDATA2MSB;
-#else
-#error "Unknown __BYTE_ORDER__"
-#endif
 	int err = 0;
 	Elf_Scn *scn;
 	Elf_Data *data;
 	Elf64_Ehdr *ehdr;
 	Elf64_Shdr *shdr;
 	struct src_sec *sec;
+	unsigned char obj_byteorder;
+	unsigned char link_byteorder = linker->elf_hdr->e_ident[EI_DATA];
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	const unsigned char host_byteorder = ELFDATA2LSB;
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+	const unsigned char host_byteorder = ELFDATA2MSB;
+#else
+#error "Unknown __BYTE_ORDER__"
+#endif
 
 	pr_debug("linker: adding object file '%s'...\n", filename);
 
@@ -577,11 +577,25 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename,
 		pr_warn_elf("failed to get ELF header for %s", filename);
 		return err;
 	}
-	if (ehdr->e_ident[EI_DATA] != host_endianness) {
+
+	/* Linker output endianness set by first input object */
+	obj_byteorder = ehdr->e_ident[EI_DATA];
+	if (obj_byteorder != ELFDATA2LSB && obj_byteorder != ELFDATA2MSB) {
 		err = -EOPNOTSUPP;
-		pr_warn_elf("unsupported byte order of ELF file %s", filename);
+		pr_warn("unknown byte order of ELF file %s\n", filename);
 		return err;
 	}
+	if (link_byteorder == ELFDATANONE) {
+		linker->elf_hdr->e_ident[EI_DATA] = obj_byteorder;
+		linker->swapped_endian = obj_byteorder != host_byteorder;
+		pr_debug("linker: set %s-endian output byte order\n",
+			 obj_byteorder == ELFDATA2MSB ? "big" : "little");
+	} else if (link_byteorder != obj_byteorder) {
+		err = -EOPNOTSUPP;
+		pr_warn("byte order mismatch with ELF file %s\n", filename);
+		return err;
+	}
+
 	if (ehdr->e_type != ET_REL
 	    || ehdr->e_machine != EM_BPF
 	    || ehdr->e_ident[EI_CLASS] != ELFCLASS64) {
@@ -957,19 +971,33 @@ static int check_btf_str_off(__u32 *str_off, void *ctx)
 static int linker_sanity_check_btf(struct src_obj *obj)
 {
 	struct btf_type *t;
-	int i, n, err = 0;
+	int i, n, err;
 
 	if (!obj->btf)
 		return 0;
 
 	n = btf__type_cnt(obj->btf);
 	for (i = 1; i < n; i++) {
+		struct btf_field_iter it;
+		__u32 *type_id, *str_off;
+
 		t = btf_type_by_id(obj->btf, i);
 
-		err = err ?: btf_type_visit_type_ids(t, check_btf_type_id, obj->btf);
-		err = err ?: btf_type_visit_str_offs(t, check_btf_str_off, obj->btf);
+		err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS);
 		if (err)
 			return err;
+		while ((type_id = btf_field_iter_next(&it))) {
+			if (*type_id >= n)
+				return -EINVAL;
+		}
+
+		err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_STRS);
+		if (err)
+			return err;
+		while ((str_off = btf_field_iter_next(&it))) {
+			if (!btf__str_by_offset(obj->btf, *str_off))
+				return -EINVAL;
+		}
 	}
 
 	return 0;
@@ -1095,6 +1123,24 @@ static bool sec_content_is_same(struct dst_sec *dst_sec, struct src_sec *src_sec
 	return true;
 }
 
+static bool is_exec_sec(struct dst_sec *sec)
+{
+	if (!sec || sec->ephemeral)
+		return false;
+	return (sec->shdr->sh_type == SHT_PROGBITS) &&
+	       (sec->shdr->sh_flags & SHF_EXECINSTR);
+}
+
+static void exec_sec_bswap(void *raw_data, int size)
+{
+	const int insn_cnt = size / sizeof(struct bpf_insn);
+	struct bpf_insn *insn = raw_data;
+	int i;
+
+	for (i = 0; i < insn_cnt; i++, insn++)
+		bpf_insn_bswap(insn);
+}
+
 static int extend_sec(struct bpf_linker *linker, struct dst_sec *dst, struct src_sec *src)
 {
 	void *tmp;
@@ -1154,6 +1200,10 @@ static int extend_sec(struct bpf_linker *linker, struct dst_sec *dst, struct src
 		memset(dst->raw_data + dst->sec_sz, 0, dst_align_sz - dst->sec_sz);
 		/* now copy src data at a properly aligned offset */
 		memcpy(dst->raw_data + dst_align_sz, src->data->d_buf, src->shdr->sh_size);
+
+		/* convert added bpf insns to native byte-order */
+		if (linker->swapped_endian && is_exec_sec(dst))
+			exec_sec_bswap(dst->raw_data + dst_align_sz, src->shdr->sh_size);
 	}
 
 	dst->sec_sz = dst_final_sz;
@@ -1399,7 +1449,7 @@ recur:
 		return true;
 	case BTF_KIND_PTR:
 		/* just validate overall shape of the referenced type, so no
-		 * contents comparison for struct/union, and allowd fwd vs
+		 * contents comparison for struct/union, and allowed fwd vs
 		 * struct/union
 		 */
 		exact = false;
@@ -1948,7 +1998,7 @@ static int linker_append_elf_sym(struct bpf_linker *linker, struct src_obj *obj,
 
 		/* If existing symbol is a strong resolved symbol, bail out,
 		 * because we lost resolution battle have nothing to
-		 * contribute. We already checked abover that there is no
+		 * contribute. We already checked above that there is no
 		 * strong-strong conflict. We also already tightened binding
 		 * and visibility, so nothing else to contribute at that point.
 		 */
@@ -2213,10 +2263,17 @@ static int linker_fixup_btf(struct src_obj *obj)
 		vi = btf_var_secinfos(t);
 		for (j = 0, m = btf_vlen(t); j < m; j++, vi++) {
 			const struct btf_type *vt = btf__type_by_id(obj->btf, vi->type);
-			const char *var_name = btf__str_by_offset(obj->btf, vt->name_off);
-			int var_linkage = btf_var(vt)->linkage;
+			const char *var_name;
+			int var_linkage;
 			Elf64_Sym *sym;
 
+			/* could be a variable or function */
+			if (!btf_is_var(vt))
+				continue;
+
+			var_name = btf__str_by_offset(obj->btf, vt->name_off);
+			var_linkage = btf_var(vt)->linkage;
+
 			/* no need to patch up static or extern vars */
 			if (var_linkage != BTF_VAR_GLOBAL_ALLOCATED)
 				continue;
@@ -2234,26 +2291,10 @@ static int linker_fixup_btf(struct src_obj *obj)
 	return 0;
 }
 
-static int remap_type_id(__u32 *type_id, void *ctx)
-{
-	int *id_map = ctx;
-	int new_id = id_map[*type_id];
-
-	/* Error out if the type wasn't remapped. Ignore VOID which stays VOID. */
-	if (new_id == 0 && *type_id != 0) {
-		pr_warn("failed to find new ID mapping for original BTF type ID %u\n", *type_id);
-		return -EINVAL;
-	}
-
-	*type_id = id_map[*type_id];
-
-	return 0;
-}
-
 static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
 {
 	const struct btf_type *t;
-	int i, j, n, start_id, id;
+	int i, j, n, start_id, id, err;
 	const char *name;
 
 	if (!obj->btf)
@@ -2324,9 +2365,25 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
 	n = btf__type_cnt(linker->btf);
 	for (i = start_id; i < n; i++) {
 		struct btf_type *dst_t = btf_type_by_id(linker->btf, i);
+		struct btf_field_iter it;
+		__u32 *type_id;
 
-		if (btf_type_visit_type_ids(dst_t, remap_type_id, obj->btf_type_map))
-			return -EINVAL;
+		err = btf_field_iter_init(&it, dst_t, BTF_FIELD_ITER_IDS);
+		if (err)
+			return err;
+
+		while ((type_id = btf_field_iter_next(&it))) {
+			int new_id = obj->btf_type_map[*type_id];
+
+			/* Error out if the type wasn't remapped. Ignore VOID which stays VOID. */
+			if (new_id == 0 && *type_id != 0) {
+				pr_warn("failed to find new ID mapping for original BTF type ID %u\n",
+					*type_id);
+				return -EINVAL;
+			}
+
+			*type_id = obj->btf_type_map[*type_id];
+		}
 	}
 
 	/* Rewrite VAR/FUNC underlying types (i.e., FUNC's FUNC_PROTO and VAR's
@@ -2394,6 +2451,10 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
 			if (glob_sym && glob_sym->var_idx >= 0) {
 				__s64 sz;
 
+				/* FUNCs don't have size, nothing to update */
+				if (btf_is_func(t))
+					continue;
+
 				dst_var = &dst_sec->sec_vars[glob_sym->var_idx];
 				/* Because underlying BTF type might have
 				 * changed, so might its size have changed, so
@@ -2607,6 +2668,10 @@ int bpf_linker__finalize(struct bpf_linker *linker)
 		if (!sec->scn)
 			continue;
 
+		/* restore sections with bpf insns to target byte-order */
+		if (linker->swapped_endian && is_exec_sec(sec))
+			exec_sec_bswap(sec->raw_data, sec->sec_sz);
+
 		sec->data->d_buf = sec->raw_data;
 	}
 
@@ -2675,6 +2740,7 @@ static int emit_elf_data_sec(struct bpf_linker *linker, const char *sec_name,
 
 static int finalize_btf(struct bpf_linker *linker)
 {
+	enum btf_endianness link_endianness;
 	LIBBPF_OPTS(btf_dedup_opts, opts);
 	struct btf *btf = linker->btf;
 	const void *raw_data;
@@ -2719,6 +2785,13 @@ static int finalize_btf(struct bpf_linker *linker)
 		return err;
 	}
 
+	/* Set .BTF and .BTF.ext output byte order */
+	link_endianness = linker->elf_hdr->e_ident[EI_DATA] == ELFDATA2MSB ?
+			  BTF_BIG_ENDIAN : BTF_LITTLE_ENDIAN;
+	btf__set_endianness(linker->btf, link_endianness);
+	if (linker->btf_ext)
+		btf_ext__set_endianness(linker->btf_ext, link_endianness);
+
 	/* Emit .BTF section */
 	raw_data = btf__raw_data(linker->btf, &raw_sz);
 	if (!raw_data)

src/relo_core.c

@@ -1339,7 +1339,7 @@ int bpf_core_calc_relo_insn(const char *prog_name,
 					  cands->cands[i].id, cand_spec);
 		if (err < 0) {
 			bpf_core_format_spec(spec_buf, sizeof(spec_buf), cand_spec);
-			pr_warn("prog '%s': relo #%d: error matching candidate #%d %s: %d\n ",
+			pr_warn("prog '%s': relo #%d: error matching candidate #%d %s: %d\n",
 				prog_name, relo_idx, i, spec_buf, err);
 			return err;
 		}

src/skel_internal.h

@@ -107,7 +107,7 @@ static inline void skel_free(const void *p)
  * The loader program will perform probe_read_kernel() from maps.rodata.initial_value.
  * skel_finalize_map_data() sets skel->rodata to point to actual value in a bpf map and
  * does maps.rodata.initial_value = ~0ULL to signal skel_free_map_data() that kvfree
- * is not nessary.
+ * is not necessary.
  *
  * For user space:
  * skel_prep_map_data() mmaps anon memory into skel->rodata that can be accessed directly.
@@ -351,10 +351,11 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
 	attr.test.ctx_size_in = opts->ctx->sz;
 	err = skel_sys_bpf(BPF_PROG_RUN, &attr, test_run_attr_sz);
 	if (err < 0 || (int)attr.test.retval < 0) {
-		opts->errstr = "failed to execute loader prog";
 		if (err < 0) {
+			opts->errstr = "failed to execute loader prog";
 			set_err;
 		} else {
+			opts->errstr = "error returned by loader prog";
 			err = (int)attr.test.retval;
 #ifndef __KERNEL__
 			errno = -err;

src/usdt.bpf.h

@@ -39,7 +39,7 @@ enum __bpf_usdt_arg_type {
 struct __bpf_usdt_arg_spec {
 	/* u64 scalar interpreted depending on arg_type, see below */
 	__u64 val_off;
-	/* arg location case, see bpf_udst_arg() for details */
+	/* arg location case, see bpf_usdt_arg() for details */
 	enum __bpf_usdt_arg_type arg_type;
 	/* offset of referenced register within struct pt_regs */
 	short reg_off;

src/zip.c

@@ -223,7 +223,7 @@ struct zip_archive *zip_archive_open(const char *path)
 	if (!archive) {
 		munmap(data, size);
 		return ERR_PTR(-ENOMEM);
-	};
+	}
 
 	archive->data = data;
 	archive->size = size;