netdata_patch_1_4_6: Add patch to run on Debian 10

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/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/test.yml

@@ -27,9 +27,6 @@ jobs:
           - kernel: '4.9.0'
             runs_on: ubuntu-24.04
             arch: 'x86_64'
-          - kernel: 'LATEST'
-            runs_on: ["s390x", "docker-noble-main"]
-            arch: 's390x'
     steps:
       - uses: actions/checkout@v4
         name: Checkout

BPF-CHECKPOINT-COMMIT

@@ -1 +1 @@
-b408473ea01b2e499d23503e2bf898416da9d7ac
+d5fb316e2af1d947f0f6c3666e373a54d9f27c6f

CHECKPOINT-COMMIT

@@ -1 +1 @@
-2ad6d23f465a4f851e3bcf6d74c315ce7b2c205b
+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
+

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,
@@ -1970,6 +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
@@ -2851,7 +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**.
@@ -3101,10 +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
  *
@@ -5369,7 +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.
@@ -5519,11 +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
@@ -6046,11 +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),
@@ -6197,10 +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)	\
@@ -7080,6 +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 {

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)

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.c

@@ -2885,7 +2885,7 @@ int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id,
 	return btf_commit_type(btf, sz);
 }
 
-struct btf_ext_sec_setup_param {
+struct btf_ext_sec_info_param {
 	__u32 off;
 	__u32 len;
 	__u32 min_rec_size;
@@ -2893,14 +2893,20 @@ struct btf_ext_sec_setup_param {
 	const char *desc;
 };
 
-static int btf_ext_setup_info(struct btf_ext *btf_ext,
-			      struct btf_ext_sec_setup_param *ext_sec)
+/*
+ * Parse a single info subsection of the BTF.ext info data:
+ *  - validate subsection structure and elements
+ *  - save info subsection start and sizing details in struct btf_ext
+ *  - endian-independent operation, for calling before byte-swapping
+ */
+static int btf_ext_parse_sec_info(struct btf_ext *btf_ext,
+				  struct btf_ext_sec_info_param *ext_sec,
+				  bool is_native)
 {
 	const struct btf_ext_info_sec *sinfo;
 	struct btf_ext_info *ext_info;
 	__u32 info_left, record_size;
 	size_t sec_cnt = 0;
-	/* The start of the info sec (including the __u32 record_size). */
 	void *info;
 
 	if (ext_sec->len == 0)
@@ -2912,6 +2918,7 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext,
 		return -EINVAL;
 	}
 
+	/* The start of the info sec (including the __u32 record_size). */
 	info = btf_ext->data + btf_ext->hdr->hdr_len + ext_sec->off;
 	info_left = ext_sec->len;
 
@@ -2927,9 +2934,13 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext,
 		return -EINVAL;
 	}
 
-	/* The record size needs to meet the minimum standard */
-	record_size = *(__u32 *)info;
+	/* The record size needs to meet either the minimum standard or, when
+	 * handling non-native endianness data, the exact standard so as
+	 * to allow safe byte-swapping.
+	 */
+	record_size = is_native ? *(__u32 *)info : bswap_32(*(__u32 *)info);
 	if (record_size < ext_sec->min_rec_size ||
+	    (!is_native && record_size != ext_sec->min_rec_size) ||
 	    record_size & 0x03) {
 		pr_debug("%s section in .BTF.ext has invalid record size %u\n",
 			 ext_sec->desc, record_size);
@@ -2941,7 +2952,7 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext,
 
 	/* If no records, return failure now so .BTF.ext won't be used. */
 	if (!info_left) {
-		pr_debug("%s section in .BTF.ext has no records", ext_sec->desc);
+		pr_debug("%s section in .BTF.ext has no records\n", ext_sec->desc);
 		return -EINVAL;
 	}
 
@@ -2956,7 +2967,7 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext,
 			return -EINVAL;
 		}
 
-		num_records = sinfo->num_info;
+		num_records = is_native ? sinfo->num_info : bswap_32(sinfo->num_info);
 		if (num_records == 0) {
 			pr_debug("%s section has incorrect num_records in .BTF.ext\n",
 			     ext_sec->desc);
@@ -2984,64 +2995,157 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext,
 	return 0;
 }
 
-static int btf_ext_setup_func_info(struct btf_ext *btf_ext)
+/* Parse all info secs in the BTF.ext info data */
+static int btf_ext_parse_info(struct btf_ext *btf_ext, bool is_native)
 {
-	struct btf_ext_sec_setup_param param = {
+	struct btf_ext_sec_info_param func_info = {
 		.off = btf_ext->hdr->func_info_off,
 		.len = btf_ext->hdr->func_info_len,
 		.min_rec_size = sizeof(struct bpf_func_info_min),
 		.ext_info = &btf_ext->func_info,
 		.desc = "func_info"
 	};
-
-	return btf_ext_setup_info(btf_ext, &param);
-}
-
-static int btf_ext_setup_line_info(struct btf_ext *btf_ext)
-{
-	struct btf_ext_sec_setup_param param = {
+	struct btf_ext_sec_info_param line_info = {
 		.off = btf_ext->hdr->line_info_off,
 		.len = btf_ext->hdr->line_info_len,
 		.min_rec_size = sizeof(struct bpf_line_info_min),
 		.ext_info = &btf_ext->line_info,
 		.desc = "line_info",
 	};
-
-	return btf_ext_setup_info(btf_ext, &param);
-}
-
-static int btf_ext_setup_core_relos(struct btf_ext *btf_ext)
-{
-	struct btf_ext_sec_setup_param param = {
+	struct btf_ext_sec_info_param core_relo = {
 		.off = btf_ext->hdr->core_relo_off,
 		.len = btf_ext->hdr->core_relo_len,
 		.min_rec_size = sizeof(struct bpf_core_relo),
 		.ext_info = &btf_ext->core_relo_info,
 		.desc = "core_relo",
 	};
+	int err;
 
-	return btf_ext_setup_info(btf_ext, &param);
+	err = btf_ext_parse_sec_info(btf_ext, &func_info, is_native);
+	if (err)
+		return err;
+
+	err = btf_ext_parse_sec_info(btf_ext, &line_info, is_native);
+	if (err)
+		return err;
+
+	if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len))
+		return 0; /* skip core relos parsing */
+
+	err = btf_ext_parse_sec_info(btf_ext, &core_relo, is_native);
+	if (err)
+		return err;
+
+	return 0;
 }
 
-static int btf_ext_parse_hdr(__u8 *data, __u32 data_size)
+/* Swap byte-order of BTF.ext header with any endianness */
+static void btf_ext_bswap_hdr(struct btf_ext_header *h)
 {
-	const struct btf_ext_header *hdr = (struct btf_ext_header *)data;
+	bool is_native = h->magic == BTF_MAGIC;
+	__u32 hdr_len;
 
-	if (data_size < offsetofend(struct btf_ext_header, hdr_len) ||
-	    data_size < hdr->hdr_len) {
-		pr_debug("BTF.ext header not found");
+	hdr_len = is_native ? h->hdr_len : bswap_32(h->hdr_len);
+
+	h->magic = bswap_16(h->magic);
+	h->hdr_len = bswap_32(h->hdr_len);
+	h->func_info_off = bswap_32(h->func_info_off);
+	h->func_info_len = bswap_32(h->func_info_len);
+	h->line_info_off = bswap_32(h->line_info_off);
+	h->line_info_len = bswap_32(h->line_info_len);
+
+	if (hdr_len < offsetofend(struct btf_ext_header, core_relo_len))
+		return;
+
+	h->core_relo_off = bswap_32(h->core_relo_off);
+	h->core_relo_len = bswap_32(h->core_relo_len);
+}
+
+/* Swap byte-order of generic info subsection */
+static void btf_ext_bswap_info_sec(void *info, __u32 len, bool is_native,
+				   info_rec_bswap_fn bswap_fn)
+{
+	struct btf_ext_info_sec *sec;
+	__u32 info_left, rec_size, *rs;
+
+	if (len == 0)
+		return;
+
+	rs = info;				/* info record size */
+	rec_size = is_native ? *rs : bswap_32(*rs);
+	*rs = bswap_32(*rs);
+
+	sec = info + sizeof(__u32);		/* info sec #1 */
+	info_left = len - sizeof(__u32);
+	while (info_left) {
+		unsigned int sec_hdrlen = sizeof(struct btf_ext_info_sec);
+		__u32 i, num_recs;
+		void *p;
+
+		num_recs = is_native ? sec->num_info : bswap_32(sec->num_info);
+		sec->sec_name_off = bswap_32(sec->sec_name_off);
+		sec->num_info = bswap_32(sec->num_info);
+		p = sec->data;			/* info rec #1 */
+		for (i = 0; i < num_recs; i++, p += rec_size)
+			bswap_fn(p);
+		sec = p;
+		info_left -= sec_hdrlen + (__u64)rec_size * num_recs;
+	}
+}
+
+/*
+ * Swap byte-order of all info data in a BTF.ext section
+ *  - requires BTF.ext hdr in native endianness
+ */
+static void btf_ext_bswap_info(struct btf_ext *btf_ext, void *data)
+{
+	const bool is_native = btf_ext->swapped_endian;
+	const struct btf_ext_header *h = data;
+	void *info;
+
+	/* Swap func_info subsection byte-order */
+	info = data + h->hdr_len + h->func_info_off;
+	btf_ext_bswap_info_sec(info, h->func_info_len, is_native,
+			       (info_rec_bswap_fn)bpf_func_info_bswap);
+
+	/* Swap line_info subsection byte-order */
+	info = data + h->hdr_len + h->line_info_off;
+	btf_ext_bswap_info_sec(info, h->line_info_len, is_native,
+			       (info_rec_bswap_fn)bpf_line_info_bswap);
+
+	/* Swap core_relo subsection byte-order (if present) */
+	if (h->hdr_len < offsetofend(struct btf_ext_header, core_relo_len))
+		return;
+
+	info = data + h->hdr_len + h->core_relo_off;
+	btf_ext_bswap_info_sec(info, h->core_relo_len, is_native,
+			       (info_rec_bswap_fn)bpf_core_relo_bswap);
+}
+
+/* Parse hdr data and info sections: check and convert to native endianness */
+static int btf_ext_parse(struct btf_ext *btf_ext)
+{
+	__u32 hdr_len, data_size = btf_ext->data_size;
+	struct btf_ext_header *hdr = btf_ext->hdr;
+	bool swapped_endian = false;
+	int err;
+
+	if (data_size < offsetofend(struct btf_ext_header, hdr_len)) {
+		pr_debug("BTF.ext header too short\n");
 		return -EINVAL;
 	}
 
+	hdr_len = hdr->hdr_len;
 	if (hdr->magic == bswap_16(BTF_MAGIC)) {
-		pr_warn("BTF.ext in non-native endianness is not supported\n");
-		return -ENOTSUP;
+		swapped_endian = true;
+		hdr_len = bswap_32(hdr_len);
 	} else if (hdr->magic != BTF_MAGIC) {
 		pr_debug("Invalid BTF.ext magic:%x\n", hdr->magic);
 		return -EINVAL;
 	}
 
-	if (hdr->version != BTF_VERSION) {
+	/* Ensure known version of structs, current BTF_VERSION == 1 */
+	if (hdr->version != 1) {
 		pr_debug("Unsupported BTF.ext version:%u\n", hdr->version);
 		return -ENOTSUP;
 	}
@@ -3051,11 +3155,39 @@ static int btf_ext_parse_hdr(__u8 *data, __u32 data_size)
 		return -ENOTSUP;
 	}
 
-	if (data_size == hdr->hdr_len) {
+	if (data_size < hdr_len) {
+		pr_debug("BTF.ext header not found\n");
+		return -EINVAL;
+	} else if (data_size == hdr_len) {
 		pr_debug("BTF.ext has no data\n");
 		return -EINVAL;
 	}
 
+	/* Verify mandatory hdr info details present */
+	if (hdr_len < offsetofend(struct btf_ext_header, line_info_len)) {
+		pr_warn("BTF.ext header missing func_info, line_info\n");
+		return -EINVAL;
+	}
+
+	/* Keep hdr native byte-order in memory for introspection */
+	if (swapped_endian)
+		btf_ext_bswap_hdr(btf_ext->hdr);
+
+	/* Validate info subsections and cache key metadata */
+	err = btf_ext_parse_info(btf_ext, !swapped_endian);
+	if (err)
+		return err;
+
+	/* Keep infos native byte-order in memory for introspection */
+	if (swapped_endian)
+		btf_ext_bswap_info(btf_ext, btf_ext->data);
+
+	/*
+	 * Set btf_ext->swapped_endian only after all header and info data has
+	 * been swapped, helping bswap functions determine if their data are
+	 * in native byte-order when called.
+	 */
+	btf_ext->swapped_endian = swapped_endian;
 	return 0;
 }
 
@@ -3067,6 +3199,7 @@ void btf_ext__free(struct btf_ext *btf_ext)
 	free(btf_ext->line_info.sec_idxs);
 	free(btf_ext->core_relo_info.sec_idxs);
 	free(btf_ext->data);
+	free(btf_ext->data_swapped);
 	free(btf_ext);
 }
 
@@ -3087,29 +3220,7 @@ struct btf_ext *btf_ext__new(const __u8 *data, __u32 size)
 	}
 	memcpy(btf_ext->data, data, size);
 
-	err = btf_ext_parse_hdr(btf_ext->data, size);
-	if (err)
-		goto done;
-
-	if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, line_info_len)) {
-		err = -EINVAL;
-		goto done;
-	}
-
-	err = btf_ext_setup_func_info(btf_ext);
-	if (err)
-		goto done;
-
-	err = btf_ext_setup_line_info(btf_ext);
-	if (err)
-		goto done;
-
-	if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len))
-		goto done; /* skip core relos parsing */
-
-	err = btf_ext_setup_core_relos(btf_ext);
-	if (err)
-		goto done;
+	err = btf_ext_parse(btf_ext);
 
 done:
 	if (err) {
@@ -3120,15 +3231,66 @@ done:
 	return btf_ext;
 }
 
+static void *btf_ext_raw_data(const struct btf_ext *btf_ext_ro, bool swap_endian)
+{
+	struct btf_ext *btf_ext = (struct btf_ext *)btf_ext_ro;
+	const __u32 data_sz = btf_ext->data_size;
+	void *data;
+
+	/* Return native data (always present) or swapped data if present */
+	if (!swap_endian)
+		return btf_ext->data;
+	else if (btf_ext->data_swapped)
+		return btf_ext->data_swapped;
+
+	/* Recreate missing swapped data, then cache and return */
+	data = calloc(1, data_sz);
+	if (!data)
+		return NULL;
+	memcpy(data, btf_ext->data, data_sz);
+
+	btf_ext_bswap_info(btf_ext, data);
+	btf_ext_bswap_hdr(data);
+	btf_ext->data_swapped = data;
+	return data;
+}
+
 const void *btf_ext__raw_data(const struct btf_ext *btf_ext, __u32 *size)
 {
+	void *data;
+
+	data = btf_ext_raw_data(btf_ext, btf_ext->swapped_endian);
+	if (!data)
+		return errno = ENOMEM, NULL;
+
 	*size = btf_ext->data_size;
-	return btf_ext->data;
+	return data;
 }
 
 __attribute__((alias("btf_ext__raw_data")))
 const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, __u32 *size);
 
+enum btf_endianness btf_ext__endianness(const struct btf_ext *btf_ext)
+{
+	if (is_host_big_endian())
+		return btf_ext->swapped_endian ? BTF_LITTLE_ENDIAN : BTF_BIG_ENDIAN;
+	else
+		return btf_ext->swapped_endian ? BTF_BIG_ENDIAN : BTF_LITTLE_ENDIAN;
+}
+
+int btf_ext__set_endianness(struct btf_ext *btf_ext, enum btf_endianness endian)
+{
+	if (endian != BTF_LITTLE_ENDIAN && endian != BTF_BIG_ENDIAN)
+		return libbpf_err(-EINVAL);
+
+	btf_ext->swapped_endian = is_host_big_endian() != (endian == BTF_BIG_ENDIAN);
+
+	if (!btf_ext->swapped_endian) {
+		free(btf_ext->data_swapped);
+		btf_ext->data_swapped = NULL;
+	}
+	return 0;
+}
 
 struct btf_dedup;
 
@@ -3291,7 +3453,7 @@ int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts)
 
 	d = btf_dedup_new(btf, opts);
 	if (IS_ERR(d)) {
-		pr_debug("btf_dedup_new failed: %ld", PTR_ERR(d));
+		pr_debug("btf_dedup_new failed: %ld\n", PTR_ERR(d));
 		return libbpf_err(-EINVAL);
 	}
 
@@ -4192,7 +4354,7 @@ static bool btf_dedup_identical_structs(struct btf_dedup *d, __u32 id1, __u32 id
  * and canonical graphs are not compatible structurally, whole graphs are
  * incompatible. If types are structurally equivalent (i.e., all information
  * except referenced type IDs is exactly the same), a mapping from `canon_id` to
- * a `cand_id` is recored in hypothetical mapping (`btf_dedup->hypot_map`).
+ * a `cand_id` is recoded in hypothetical mapping (`btf_dedup->hypot_map`).
  * If a type references other types, then those referenced types are checked
  * for equivalence recursively.
  *
@@ -4230,7 +4392,7 @@ static bool btf_dedup_identical_structs(struct btf_dedup *d, __u32 id1, __u32 id
  * consists of portions of the graph that come from multiple compilation units.
  * This is due to the fact that types within single compilation unit are always
  * deduplicated and FWDs are already resolved, if referenced struct/union
- * definiton is available. So, if we had unresolved FWD and found corresponding
+ * definition is available. So, if we had unresolved FWD and found corresponding
  * STRUCT/UNION, they will be from different compilation units. This
  * consequently means that when we "link" FWD to corresponding STRUCT/UNION,
  * type graph will likely have at least two different BTF types that describe

src/btf.h

@@ -167,6 +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);
@@ -286,7 +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;
 		}

src/btf_relocate.c

@@ -428,7 +428,7 @@ static int btf_relocate_rewrite_strs(struct btf_relocate *r, __u32 i)
 		} else {
 			off = r->str_map[*str_off];
 			if (!off) {
-				pr_warn("string '%s' [offset %u] is not mapped to base BTF",
+				pr_warn("string '%s' [offset %u] is not mapped to base BTF\n",
 					btf__str_by_offset(r->btf, off), *str_off);
 				return -ENOENT;
 			}

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

@@ -694,6 +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;
 
@@ -940,6 +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)
 {
@@ -986,7 +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;
@@ -1116,7 +1132,7 @@ 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;
@@ -1506,6 +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;
 
@@ -1571,6 +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));
@@ -1599,19 +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
@@ -1848,7 +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 = '_';
@@ -3581,11 +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;
 }
@@ -3953,6 +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
 	 */
@@ -3985,7 +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)
@@ -4389,7 +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 *
@@ -5094,6 +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,
@@ -5107,8 +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;
 	}
 
@@ -5118,11 +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;
 }
 
@@ -5439,8 +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,
@@ -7352,8 +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;
@@ -7443,6 +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)) {
@@ -7474,9 +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,
@@ -7992,7 +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);
@@ -8498,8 +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);
@@ -9059,6 +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;
@@ -9091,6 +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;
 }
@@ -11688,7 +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;
@@ -12755,7 +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);
 	}
@@ -13829,7 +13905,7 @@ int bpf_object__open_subskeleton(struct bpf_object_subskeleton *s)
 		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);
@@ -13872,46 +13948,11 @@ int bpf_object__load_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;
-		size_t mmap_sz = bpf_map_mmap_sz(map);
-		int prot, map_fd = map->fd;
-		void **mmaped = map_skel->mmaped;
 
-		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;

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.
  *
@@ -1593,11 +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

src/libbpf.map

@@ -421,8 +421,11 @@ 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>
@@ -448,11 +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
  *   ......
  *
@@ -484,6 +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;
@@ -511,6 +514,32 @@ 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,
@@ -588,6 +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/libbpf_probes.c

@@ -97,6 +97,9 @@ __u32 get_kernel_version(void)
 	if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3)
 		return 0;
 
+	if (major == 4 && minor == 19 && patch > 255)
+		return KERNEL_VERSION(major, minor, 255);
+
 	return KERNEL_VERSION(major, minor, patch);
 }
 

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) {
@@ -1109,6 +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;
@@ -1168,6 +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;
@@ -1413,7 +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;
@@ -1962,7 +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.
 		 */
@@ -2415,6 +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
@@ -2628,6 +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;
 	}
 
@@ -2696,6 +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;
@@ -2740,6 +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;