Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
The following pull-request contains BPF updates for your *net-next* tree.

There is a small merge conflict in libbpf (Cc Andrii so he's in the loop
as well):

        for (i = 1; i <= btf__get_nr_types(btf); i++) {
                t = (struct btf_type *)btf__type_by_id(btf, i);

                if (!has_datasec && btf_is_var(t)) {
                        /* replace VAR with INT */
                        t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0);
  <<<<<<< HEAD
                        /*
                         * using size = 1 is the safest choice, 4 will be too
                         * big and cause kernel BTF validation failure if
                         * original variable took less than 4 bytes
                         */
                        t->size = 1;
                        *(int *)(t+1) = BTF_INT_ENC(0, 0, 8);
                } else if (!has_datasec && kind == BTF_KIND_DATASEC) {
  =======
                        t->size = sizeof(int);
                        *(int *)(t + 1) = BTF_INT_ENC(0, 0, 32);
                } else if (!has_datasec && btf_is_datasec(t)) {
  >>>>>>> 72ef80b5ee131e96172f19e74b4f98fa3404efe8
                        /* replace DATASEC with STRUCT */

Conflict is between the two commits 1d4126c4e119 ("libbpf: sanitize VAR to
conservative 1-byte INT") and b03bc6853c0e ("libbpf: convert libbpf code to
use new btf helpers"), so we need to pick the sanitation fixup as well as
use the new btf_is_datasec() helper and the whitespace cleanup. Looks like
the following:

  [...]
                if (!has_datasec && btf_is_var(t)) {
                        /* replace VAR with INT */
                        t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0);
                        /*
                         * using size = 1 is the safest choice, 4 will be too
                         * big and cause kernel BTF validation failure if
                         * original variable took less than 4 bytes
                         */
                        t->size = 1;
                        *(int *)(t + 1) = BTF_INT_ENC(0, 0, 8);
                } else if (!has_datasec && btf_is_datasec(t)) {
                        /* replace DATASEC with STRUCT */
  [...]

The main changes are:

1) Addition of core parts of compile once - run everywhere (co-re) effort,
   that is, relocation of fields offsets in libbpf as well as exposure of
   kernel's own BTF via sysfs and loading through libbpf, from Andrii.

   More info on co-re: http://vger.kernel.org/bpfconf2019.html#session-2
   and http://vger.kernel.org/lpc-bpf2018.html#session-2

2) Enable passing input flags to the BPF flow dissector to customize parsing
   and allowing it to stop early similar to the C based one, from Stanislav.

3) Add a BPF helper function that allows generating SYN cookies from XDP and
   tc BPF, from Petar.

4) Add devmap hash-based map type for more flexibility in device lookup for
   redirects, from Toke.

5) Improvements to XDP forwarding sample code now utilizing recently enabled
   devmap lookups, from Jesper.

6) Add support for reporting the effective cgroup progs in bpftool, from Jakub
   and Takshak.

7) Fix reading kernel config from bpftool via /proc/config.gz, from Peter.

8) Fix AF_XDP umem pages mapping for 32 bit architectures, from Ivan.

9) Follow-up to add two more BPF loop tests for the selftest suite, from Alexei.

10) Add perf event output helper also for other skb-based program types, from Allan.

11) Fix a co-re related compilation error in selftests, from Yonghong.
====================

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>

7 files changed, 1402 insertions, 286 deletions

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index d821107f55f9..1aa189a9112a 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -20,13 +20,6 @@
 #define BTF_MAX_NR_TYPES 0x7fffffff
 #define BTF_MAX_STR_OFFSET 0x7fffffff
 
-#define IS_MODIFIER(k) (((k) == BTF_KIND_TYPEDEF) || \
-		((k) == BTF_KIND_VOLATILE) || \
-		((k) == BTF_KIND_CONST) || \
-		((k) == BTF_KIND_RESTRICT))
-
-#define IS_VAR(k) ((k) == BTF_KIND_VAR)
-
 static struct btf_type btf_void;
 
 struct btf {
@@ -43,47 +36,6 @@ struct btf {
 	int fd;
 };
 
-struct btf_ext_info {
-	/*
-	 * info points to the individual info section (e.g. func_info and
-	 * line_info) from the .BTF.ext. It does not include the __u32 rec_size.
-	 */
-	void *info;
-	__u32 rec_size;
-	__u32 len;
-};
-
-struct btf_ext {
-	union {
-		struct btf_ext_header *hdr;
-		void *data;
-	};
-	struct btf_ext_info func_info;
-	struct btf_ext_info line_info;
-	__u32 data_size;
-};
-
-struct btf_ext_info_sec {
-	__u32	sec_name_off;
-	__u32	num_info;
-	/* Followed by num_info * record_size number of bytes */
-	__u8	data[0];
-};
-
-/* The minimum bpf_func_info checked by the loader */
-struct bpf_func_info_min {
-	__u32   insn_off;
-	__u32   type_id;
-};
-
-/* The minimum bpf_line_info checked by the loader */
-struct bpf_line_info_min {
-	__u32	insn_off;
-	__u32	file_name_off;
-	__u32	line_off;
-	__u32	line_col;
-};
-
 static inline __u64 ptr_to_u64(const void *ptr)
 {
 	return (__u64) (unsigned long) ptr;
@@ -193,9 +145,9 @@ static int btf_parse_str_sec(struct btf *btf)
 static int btf_type_size(struct btf_type *t)
 {
 	int base_size = sizeof(struct btf_type);
-	__u16 vlen = BTF_INFO_VLEN(t->info);
+	__u16 vlen = btf_vlen(t);
 
-	switch (BTF_INFO_KIND(t->info)) {
+	switch (btf_kind(t)) {
 	case BTF_KIND_FWD:
 	case BTF_KIND_CONST:
 	case BTF_KIND_VOLATILE:
@@ -220,7 +172,7 @@ static int btf_type_size(struct btf_type *t)
 	case BTF_KIND_DATASEC:
 		return base_size + vlen * sizeof(struct btf_var_secinfo);
 	default:
-		pr_debug("Unsupported BTF_KIND:%u\n", BTF_INFO_KIND(t->info));
+		pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t));
 		return -EINVAL;
 	}
 }
@@ -264,7 +216,7 @@ const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id)
 
 static bool btf_type_is_void(const struct btf_type *t)
 {
-	return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD;
+	return t == &btf_void || btf_is_fwd(t);
 }
 
 static bool btf_type_is_void_or_null(const struct btf_type *t)
@@ -285,7 +237,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 	t = btf__type_by_id(btf, type_id);
 	for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t);
 	     i++) {
-		switch (BTF_INFO_KIND(t->info)) {
+		switch (btf_kind(t)) {
 		case BTF_KIND_INT:
 		case BTF_KIND_STRUCT:
 		case BTF_KIND_UNION:
@@ -304,7 +256,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 			type_id = t->type;
 			break;
 		case BTF_KIND_ARRAY:
-			array = (const struct btf_array *)(t + 1);
+			array = btf_array(t);
 			if (nelems && array->nelems > UINT32_MAX / nelems)
 				return -E2BIG;
 			nelems *= array->nelems;
@@ -335,8 +287,7 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id)
 	t = btf__type_by_id(btf, type_id);
 	while (depth < MAX_RESOLVE_DEPTH &&
 	       !btf_type_is_void_or_null(t) &&
-	       (IS_MODIFIER(BTF_INFO_KIND(t->info)) ||
-		IS_VAR(BTF_INFO_KIND(t->info)))) {
+	       (btf_is_mod(t) || btf_is_typedef(t) || btf_is_var(t))) {
 		type_id = t->type;
 		t = btf__type_by_id(btf, type_id);
 		depth++;
@@ -555,11 +506,11 @@ static int compare_vsi_off(const void *_a, const void *_b)
 static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf,
 			     struct btf_type *t)
 {
-	__u32 size = 0, off = 0, i, vars = BTF_INFO_VLEN(t->info);
+	__u32 size = 0, off = 0, i, vars = btf_vlen(t);
 	const char *name = btf__name_by_offset(btf, t->name_off);
 	const struct btf_type *t_var;
 	struct btf_var_secinfo *vsi;
-	struct btf_var *var;
+	const struct btf_var *var;
 	int ret;
 
 	if (!name) {
@@ -575,12 +526,11 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf,
 
 	t->size = size;
 
-	for (i = 0, vsi = (struct btf_var_secinfo *)(t + 1);
-	     i < vars; i++, vsi++) {
+	for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) {
 		t_var = btf__type_by_id(btf, vsi->type);
-		var = (struct btf_var *)(t_var + 1);
+		var = btf_var(t_var);
 
-		if (BTF_INFO_KIND(t_var->info) != BTF_KIND_VAR) {
+		if (!btf_is_var(t_var)) {
 			pr_debug("Non-VAR type seen in section %s\n", name);
 			return -EINVAL;
 		}
@@ -596,7 +546,8 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf,
 
 		ret = bpf_object__variable_offset(obj, name, &off);
 		if (ret) {
-			pr_debug("No offset found in symbol table for VAR %s\n", name);
+			pr_debug("No offset found in symbol table for VAR %s\n",
+				 name);
 			return -ENOENT;
 		}
 
@@ -620,7 +571,7 @@ int btf__finalize_data(struct bpf_object *obj, struct btf *btf)
 		 * is section size and global variable offset. We use
 		 * the info from the ELF itself for this purpose.
 		 */
-		if (BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC) {
+		if (btf_is_datasec(t)) {
 			err = btf_fixup_datasec(obj, btf, t);
 			if (err)
 				break;
@@ -775,14 +726,13 @@ int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
 		return -EINVAL;
 	}
 
-	if (BTF_INFO_KIND(container_type->info) != BTF_KIND_STRUCT ||
-	    BTF_INFO_VLEN(container_type->info) < 2) {
+	if (!btf_is_struct(container_type) || btf_vlen(container_type) < 2) {
 		pr_warning("map:%s container_name:%s is an invalid container struct\n",
 			   map_name, container_name);
 		return -EINVAL;
 	}
 
-	key = (struct btf_member *)(container_type + 1);
+	key = btf_members(container_type);
 	value = key + 1;
 
 	key_size = btf__resolve_size(btf, key->type);
@@ -832,6 +782,9 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext,
 	/* The start of the info sec (including the __u32 record_size). */
 	void *info;
 
+	if (ext_sec->len == 0)
+		return 0;
+
 	if (ext_sec->off & 0x03) {
 		pr_debug(".BTF.ext %s section is not aligned to 4 bytes\n",
 		     ext_sec->desc);
@@ -935,11 +888,24 @@ static int btf_ext_setup_line_info(struct btf_ext *btf_ext)
 	return btf_ext_setup_info(btf_ext, &param);
 }
 
+static int btf_ext_setup_offset_reloc(struct btf_ext *btf_ext)
+{
+	struct btf_ext_sec_setup_param param = {
+		.off = btf_ext->hdr->offset_reloc_off,
+		.len = btf_ext->hdr->offset_reloc_len,
+		.min_rec_size = sizeof(struct bpf_offset_reloc),
+		.ext_info = &btf_ext->offset_reloc_info,
+		.desc = "offset_reloc",
+	};
+
+	return btf_ext_setup_info(btf_ext, &param);
+}
+
 static int btf_ext_parse_hdr(__u8 *data, __u32 data_size)
 {
 	const struct btf_ext_header *hdr = (struct btf_ext_header *)data;
 
-	if (data_size < offsetof(struct btf_ext_header, func_info_off) ||
+	if (data_size < offsetofend(struct btf_ext_header, hdr_len) ||
 	    data_size < hdr->hdr_len) {
 		pr_debug("BTF.ext header not found");
 		return -EINVAL;
@@ -997,6 +963,9 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size)
 	}
 	memcpy(btf_ext->data, data, size);
 
+	if (btf_ext->hdr->hdr_len <
+	    offsetofend(struct btf_ext_header, line_info_len))
+		goto done;
 	err = btf_ext_setup_func_info(btf_ext);
 	if (err)
 		goto done;
@@ -1005,6 +974,13 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size)
 	if (err)
 		goto done;
 
+	if (btf_ext->hdr->hdr_len <
+	    offsetofend(struct btf_ext_header, offset_reloc_len))
+		goto done;
+	err = btf_ext_setup_offset_reloc(btf_ext);
+	if (err)
+		goto done;
+
 done:
 	if (err) {
 		btf_ext__free(btf_ext);
@@ -1441,10 +1417,9 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
 	d->map[0] = 0;
 	for (i = 1; i <= btf->nr_types; i++) {
 		struct btf_type *t = d->btf->types[i];
-		__u16 kind = BTF_INFO_KIND(t->info);
 
 		/* VAR and DATASEC are never deduped and are self-canonical */
-		if (kind == BTF_KIND_VAR || kind == BTF_KIND_DATASEC)
+		if (btf_is_var(t) || btf_is_datasec(t))
 			d->map[i] = i;
 		else
 			d->map[i] = BTF_UNPROCESSED_ID;
@@ -1485,11 +1460,11 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx)
 		if (r)
 			return r;
 
-		switch (BTF_INFO_KIND(t->info)) {
+		switch (btf_kind(t)) {
 		case BTF_KIND_STRUCT:
 		case BTF_KIND_UNION: {
-			struct btf_member *m = (struct btf_member *)(t + 1);
-			__u16 vlen = BTF_INFO_VLEN(t->info);
+			struct btf_member *m = btf_members(t);
+			__u16 vlen = btf_vlen(t);
 
 			for (j = 0; j < vlen; j++) {
 				r = fn(&m->name_off, ctx);
@@ -1500,8 +1475,8 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx)
 			break;
 		}
 		case BTF_KIND_ENUM: {
-			struct btf_enum *m = (struct btf_enum *)(t + 1);
-			__u16 vlen = BTF_INFO_VLEN(t->info);
+			struct btf_enum *m = btf_enum(t);
+			__u16 vlen = btf_vlen(t);
 
 			for (j = 0; j < vlen; j++) {
 				r = fn(&m->name_off, ctx);
@@ -1512,8 +1487,8 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx)
 			break;
 		}
 		case BTF_KIND_FUNC_PROTO: {
-			struct btf_param *m = (struct btf_param *)(t + 1);
-			__u16 vlen = BTF_INFO_VLEN(t->info);
+			struct btf_param *m = btf_params(t);
+			__u16 vlen = btf_vlen(t);
 
 			for (j = 0; j < vlen; j++) {
 				r = fn(&m->name_off, ctx);
@@ -1802,16 +1777,16 @@ static long btf_hash_enum(struct btf_type *t)
 /* Check structural equality of two ENUMs. */
 static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2)
 {
-	struct btf_enum *m1, *m2;
+	const struct btf_enum *m1, *m2;
 	__u16 vlen;
 	int i;
 
 	if (!btf_equal_common(t1, t2))
 		return false;
 
-	vlen = BTF_INFO_VLEN(t1->info);
-	m1 = (struct btf_enum *)(t1 + 1);
-	m2 = (struct btf_enum *)(t2 + 1);
+	vlen = btf_vlen(t1);
+	m1 = btf_enum(t1);
+	m2 = btf_enum(t2);
 	for (i = 0; i < vlen; i++) {
 		if (m1->name_off != m2->name_off || m1->val != m2->val)
 			return false;
@@ -1823,8 +1798,7 @@ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2)
 
 static inline bool btf_is_enum_fwd(struct btf_type *t)
 {
-	return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM &&
-	       BTF_INFO_VLEN(t->info) == 0;
+	return btf_is_enum(t) && btf_vlen(t) == 0;
 }
 
 static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2)
@@ -1844,8 +1818,8 @@ static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2)
  */
 static long btf_hash_struct(struct btf_type *t)
 {
-	struct btf_member *member = (struct btf_member *)(t + 1);
-	__u32 vlen = BTF_INFO_VLEN(t->info);
+	const struct btf_member *member = btf_members(t);
+	__u32 vlen = btf_vlen(t);
 	long h = btf_hash_common(t);
 	int i;
 
@@ -1865,16 +1839,16 @@ static long btf_hash_struct(struct btf_type *t)
  */
 static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2)
 {
-	struct btf_member *m1, *m2;
+	const struct btf_member *m1, *m2;
 	__u16 vlen;
 	int i;
 
 	if (!btf_equal_common(t1, t2))
 		return false;
 
-	vlen = BTF_INFO_VLEN(t1->info);
-	m1 = (struct btf_member *)(t1 + 1);
-	m2 = (struct btf_member *)(t2 + 1);
+	vlen = btf_vlen(t1);
+	m1 = btf_members(t1);
+	m2 = btf_members(t2);
 	for (i = 0; i < vlen; i++) {
 		if (m1->name_off != m2->name_off || m1->offset != m2->offset)
 			return false;
@@ -1891,7 +1865,7 @@ static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2)
  */
 static long btf_hash_array(struct btf_type *t)
 {
-	struct btf_array *info = (struct btf_array *)(t + 1);
+	const struct btf_array *info = btf_array(t);
 	long h = btf_hash_common(t);
 
 	h = hash_combine(h, info->type);
@@ -1909,13 +1883,13 @@ static long btf_hash_array(struct btf_type *t)
  */
 static bool btf_equal_array(struct btf_type *t1, struct btf_type *t2)
 {
-	struct btf_array *info1, *info2;
+	const struct btf_array *info1, *info2;
 
 	if (!btf_equal_common(t1, t2))
 		return false;
 
-	info1 = (struct btf_array *)(t1 + 1);
-	info2 = (struct btf_array *)(t2 + 1);
+	info1 = btf_array(t1);
+	info2 = btf_array(t2);
 	return info1->type == info2->type &&
 	       info1->index_type == info2->index_type &&
 	       info1->nelems == info2->nelems;
@@ -1928,14 +1902,10 @@ static bool btf_equal_array(struct btf_type *t1, struct btf_type *t2)
  */
 static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2)
 {
-	struct btf_array *info1, *info2;
-
 	if (!btf_equal_common(t1, t2))
 		return false;
 
-	info1 = (struct btf_array *)(t1 + 1);
-	info2 = (struct btf_array *)(t2 + 1);
-	return info1->nelems == info2->nelems;
+	return btf_array(t1)->nelems == btf_array(t2)->nelems;
 }
 
 /*
@@ -1945,8 +1915,8 @@ static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2)
  */
 static long btf_hash_fnproto(struct btf_type *t)
 {
-	struct btf_param *member = (struct btf_param *)(t + 1);
-	__u16 vlen = BTF_INFO_VLEN(t->info);
+	const struct btf_param *member = btf_params(t);
+	__u16 vlen = btf_vlen(t);
 	long h = btf_hash_common(t);
 	int i;
 
@@ -1967,16 +1937,16 @@ static long btf_hash_fnproto(struct btf_type *t)
  */
 static bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2)
 {
-	struct btf_param *m1, *m2;
+	const struct btf_param *m1, *m2;
 	__u16 vlen;
 	int i;
 
 	if (!btf_equal_common(t1, t2))
 		return false;
 
-	vlen = BTF_INFO_VLEN(t1->info);
-	m1 = (struct btf_param *)(t1 + 1);
-	m2 = (struct btf_param *)(t2 + 1);
+	vlen = btf_vlen(t1);
+	m1 = btf_params(t1);
+	m2 = btf_params(t2);
 	for (i = 0; i < vlen; i++) {
 		if (m1->name_off != m2->name_off || m1->type != m2->type)
 			return false;
@@ -1993,7 +1963,7 @@ static bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2)
  */
 static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2)
 {
-	struct btf_param *m1, *m2;
+	const struct btf_param *m1, *m2;
 	__u16 vlen;
 	int i;
 
@@ -2001,9 +1971,9 @@ static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2)
 	if (t1->name_off != t2->name_off || t1->info != t2->info)
 		return false;
 
-	vlen = BTF_INFO_VLEN(t1->info);
-	m1 = (struct btf_param *)(t1 + 1);
-	m2 = (struct btf_param *)(t2 + 1);
+	vlen = btf_vlen(t1);
+	m1 = btf_params(t1);
+	m2 = btf_params(t2);
 	for (i = 0; i < vlen; i++) {
 		if (m1->name_off != m2->name_off)
 			return false;
@@ -2029,7 +1999,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 	__u32 cand_id;
 	long h;
 
-	switch (BTF_INFO_KIND(t->info)) {
+	switch (btf_kind(t)) {
 	case BTF_KIND_CONST:
 	case BTF_KIND_VOLATILE:
 	case BTF_KIND_RESTRICT:
@@ -2142,13 +2112,13 @@ static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id)
 {
 	__u32 orig_type_id = type_id;
 
-	if (BTF_INFO_KIND(d->btf->types[type_id]->info) != BTF_KIND_FWD)
+	if (!btf_is_fwd(d->btf->types[type_id]))
 		return type_id;
 
 	while (is_type_mapped(d, type_id) && d->map[type_id] != type_id)
 		type_id = d->map[type_id];
 
-	if (BTF_INFO_KIND(d->btf->types[type_id]->info) != BTF_KIND_FWD)
+	if (!btf_is_fwd(d->btf->types[type_id]))
 		return type_id;
 
 	return orig_type_id;
@@ -2157,7 +2127,7 @@ static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id)
 
 static inline __u16 btf_fwd_kind(struct btf_type *t)
 {
-	return BTF_INFO_KFLAG(t->info) ? BTF_KIND_UNION : BTF_KIND_STRUCT;
+	return btf_kflag(t) ? BTF_KIND_UNION : BTF_KIND_STRUCT;
 }
 
 /*
@@ -2278,8 +2248,8 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 
 	cand_type = d->btf->types[cand_id];
 	canon_type = d->btf->types[canon_id];
-	cand_kind = BTF_INFO_KIND(cand_type->info);
-	canon_kind = BTF_INFO_KIND(canon_type->info);
+	cand_kind = btf_kind(cand_type);
+	canon_kind = btf_kind(canon_type);
 
 	if (cand_type->name_off != canon_type->name_off)
 		return 0;
@@ -2328,12 +2298,12 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 		return btf_dedup_is_equiv(d, cand_type->type, canon_type->type);
 
 	case BTF_KIND_ARRAY: {
-		struct btf_array *cand_arr, *canon_arr;
+		const struct btf_array *cand_arr, *canon_arr;
 
 		if (!btf_compat_array(cand_type, canon_type))
 			return 0;
-		cand_arr = (struct btf_array *)(cand_type + 1);
-		canon_arr = (struct btf_array *)(canon_type + 1);
+		cand_arr = btf_array(cand_type);
+		canon_arr = btf_array(canon_type);
 		eq = btf_dedup_is_equiv(d,
 			cand_arr->index_type, canon_arr->index_type);
 		if (eq <= 0)
@@ -2343,14 +2313,14 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 
 	case BTF_KIND_STRUCT:
 	case BTF_KIND_UNION: {
-		struct btf_member *cand_m, *canon_m;
+		const struct btf_member *cand_m, *canon_m;
 		__u16 vlen;
 
 		if (!btf_shallow_equal_struct(cand_type, canon_type))
 			return 0;
-		vlen = BTF_INFO_VLEN(cand_type->info);
-		cand_m = (struct btf_member *)(cand_type + 1);
-		canon_m = (struct btf_member *)(canon_type + 1);
+		vlen = btf_vlen(cand_type);
+		cand_m = btf_members(cand_type);
+		canon_m = btf_members(canon_type);
 		for (i = 0; i < vlen; i++) {
 			eq = btf_dedup_is_equiv(d, cand_m->type, canon_m->type);
 			if (eq <= 0)
@@ -2363,7 +2333,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 	}
 
 	case BTF_KIND_FUNC_PROTO: {
-		struct btf_param *cand_p, *canon_p;
+		const struct btf_param *cand_p, *canon_p;
 		__u16 vlen;
 
 		if (!btf_compat_fnproto(cand_type, canon_type))
@@ -2371,9 +2341,9 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 		eq = btf_dedup_is_equiv(d, cand_type->type, canon_type->type);
 		if (eq <= 0)
 			return eq;
-		vlen = BTF_INFO_VLEN(cand_type->info);
-		cand_p = (struct btf_param *)(cand_type + 1);
-		canon_p = (struct btf_param *)(canon_type + 1);
+		vlen = btf_vlen(cand_type);
+		cand_p = btf_params(cand_type);
+		canon_p = btf_params(canon_type);
 		for (i = 0; i < vlen; i++) {
 			eq = btf_dedup_is_equiv(d, cand_p->type, canon_p->type);
 			if (eq <= 0)
@@ -2428,8 +2398,8 @@ static void btf_dedup_merge_hypot_map(struct btf_dedup *d)
 		targ_type_id = d->hypot_map[cand_type_id];
 		t_id = resolve_type_id(d, targ_type_id);
 		c_id = resolve_type_id(d, cand_type_id);
-		t_kind = BTF_INFO_KIND(d->btf->types[t_id]->info);
-		c_kind = BTF_INFO_KIND(d->btf->types[c_id]->info);
+		t_kind = btf_kind(d->btf->types[t_id]);
+		c_kind = btf_kind(d->btf->types[c_id]);
 		/*
 		 * Resolve FWD into STRUCT/UNION.
 		 * It's ok to resolve FWD into STRUCT/UNION that's not yet
@@ -2498,7 +2468,7 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
 		return 0;
 
 	t = d->btf->types[type_id];
-	kind = BTF_INFO_KIND(t->info);
+	kind = btf_kind(t);
 
 	if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION)
 		return 0;
@@ -2593,7 +2563,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 	t = d->btf->types[type_id];
 	d->map[type_id] = BTF_IN_PROGRESS_ID;
 
-	switch (BTF_INFO_KIND(t->info)) {
+	switch (btf_kind(t)) {
 	case BTF_KIND_CONST:
 	case BTF_KIND_VOLATILE:
 	case BTF_KIND_RESTRICT:
@@ -2617,7 +2587,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 		break;
 
 	case BTF_KIND_ARRAY: {
-		struct btf_array *info = (struct btf_array *)(t + 1);
+		struct btf_array *info = btf_array(t);
 
 		ref_type_id = btf_dedup_ref_type(d, info->type);
 		if (ref_type_id < 0)
@@ -2651,8 +2621,8 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 			return ref_type_id;
 		t->type = ref_type_id;
 
-		vlen = BTF_INFO_VLEN(t->info);
-		param = (struct btf_param *)(t + 1);
+		vlen = btf_vlen(t);
+		param = btf_params(t);
 		for (i = 0; i < vlen; i++) {
 			ref_type_id = btf_dedup_ref_type(d, param->type);
 			if (ref_type_id < 0)
@@ -2792,7 +2762,7 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
 	struct btf_type *t = d->btf->types[type_id];
 	int i, r;
 
-	switch (BTF_INFO_KIND(t->info)) {
+	switch (btf_kind(t)) {
 	case BTF_KIND_INT:
 	case BTF_KIND_ENUM:
 		break;
@@ -2812,7 +2782,7 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
 		break;
 
 	case BTF_KIND_ARRAY: {
-		struct btf_array *arr_info = (struct btf_array *)(t + 1);
+		struct btf_array *arr_info = btf_array(t);
 
 		r = btf_dedup_remap_type_id(d, arr_info->type);
 		if (r < 0)
@@ -2827,8 +2797,8 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
 
 	case BTF_KIND_STRUCT:
 	case BTF_KIND_UNION: {
-		struct btf_member *member = (struct btf_member *)(t + 1);
-		__u16 vlen = BTF_INFO_VLEN(t->info);
+		struct btf_member *member = btf_members(t);
+		__u16 vlen = btf_vlen(t);
 
 		for (i = 0; i < vlen; i++) {
 			r = btf_dedup_remap_type_id(d, member->type);
@@ -2841,8 +2811,8 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
 	}
 
 	case BTF_KIND_FUNC_PROTO: {
-		struct btf_param *param = (struct btf_param *)(t + 1);
-		__u16 vlen = BTF_INFO_VLEN(t->info);
+		struct btf_param *param = btf_params(t);
+		__u16 vlen = btf_vlen(t);
 
 		r = btf_dedup_remap_type_id(d, t->type);
 		if (r < 0)
@@ -2860,8 +2830,8 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
 	}
 
 	case BTF_KIND_DATASEC: {
-		struct btf_var_secinfo *var = (struct btf_var_secinfo *)(t + 1);
-		__u16 vlen = BTF_INFO_VLEN(t->info);
+		struct btf_var_secinfo *var = btf_var_secinfos(t);
+		__u16 vlen = btf_vlen(t);
 
 		for (i = 0; i < vlen; i++) {
 			r = btf_dedup_remap_type_id(d, var->type);
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 88a52ae56fc6..9cb44b4fbf60 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -5,6 +5,7 @@
 #define __LIBBPF_BTF_H
 
 #include <stdarg.h>
+#include <linux/btf.h>
 #include <linux/types.h>
 
 #ifdef __cplusplus
@@ -57,6 +58,10 @@ struct btf_ext_header {
 	__u32	func_info_len;
 	__u32	line_info_off;
 	__u32	line_info_len;
+
+	/* optional part of .BTF.ext header */
+	__u32	offset_reloc_off;
+	__u32	offset_reloc_len;
 };
 
 LIBBPF_API void btf__free(struct btf *btf);
@@ -120,6 +125,183 @@ LIBBPF_API void btf_dump__free(struct btf_dump *d);
 
 LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id);
 
+/*
+ * A set of helpers for easier BTF types handling
+ */
+static inline __u16 btf_kind(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info);
+}
+
+static inline __u16 btf_vlen(const struct btf_type *t)
+{
+	return BTF_INFO_VLEN(t->info);
+}
+
+static inline bool btf_kflag(const struct btf_type *t)
+{
+	return BTF_INFO_KFLAG(t->info);
+}
+
+static inline bool btf_is_int(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_INT;
+}
+
+static inline bool btf_is_ptr(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_PTR;
+}
+
+static inline bool btf_is_array(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_ARRAY;
+}
+
+static inline bool btf_is_struct(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_STRUCT;
+}
+
+static inline bool btf_is_union(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_UNION;
+}
+
+static inline bool btf_is_composite(const struct btf_type *t)
+{
+	__u16 kind = btf_kind(t);
+
+	return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION;
+}
+
+static inline bool btf_is_enum(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_ENUM;
+}
+
+static inline bool btf_is_fwd(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_FWD;
+}
+
+static inline bool btf_is_typedef(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_TYPEDEF;
+}
+
+static inline bool btf_is_volatile(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_VOLATILE;
+}
+
+static inline bool btf_is_const(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_CONST;
+}
+
+static inline bool btf_is_restrict(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_RESTRICT;
+}
+
+static inline bool btf_is_mod(const struct btf_type *t)
+{
+	__u16 kind = btf_kind(t);
+
+	return kind == BTF_KIND_VOLATILE ||
+	       kind == BTF_KIND_CONST ||
+	       kind == BTF_KIND_RESTRICT;
+}
+
+static inline bool btf_is_func(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_FUNC;
+}
+
+static inline bool btf_is_func_proto(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_FUNC_PROTO;
+}
+
+static inline bool btf_is_var(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_VAR;
+}
+
+static inline bool btf_is_datasec(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_DATASEC;
+}
+
+static inline __u8 btf_int_encoding(const struct btf_type *t)
+{
+	return BTF_INT_ENCODING(*(__u32 *)(t + 1));
+}
+
+static inline __u8 btf_int_offset(const struct btf_type *t)
+{
+	return BTF_INT_OFFSET(*(__u32 *)(t + 1));
+}
+
+static inline __u8 btf_int_bits(const struct btf_type *t)
+{
+	return BTF_INT_BITS(*(__u32 *)(t + 1));
+}
+
+static inline struct btf_array *btf_array(const struct btf_type *t)
+{
+	return (struct btf_array *)(t + 1);
+}
+
+static inline struct btf_enum *btf_enum(const struct btf_type *t)
+{
+	return (struct btf_enum *)(t + 1);
+}
+
+static inline struct btf_member *btf_members(const struct btf_type *t)
+{
+	return (struct btf_member *)(t + 1);
+}
+
+/* Get bit offset of a member with specified index. */
+static inline __u32 btf_member_bit_offset(const struct btf_type *t,
+					  __u32 member_idx)
+{
+	const struct btf_member *m = btf_members(t) + member_idx;
+	bool kflag = btf_kflag(t);
+
+	return kflag ? BTF_MEMBER_BIT_OFFSET(m->offset) : m->offset;
+}
+/*
+ * Get bitfield size of a member, assuming t is BTF_KIND_STRUCT or
+ * BTF_KIND_UNION. If member is not a bitfield, zero is returned.
+ */
+static inline __u32 btf_member_bitfield_size(const struct btf_type *t,
+					     __u32 member_idx)
+{
+	const struct btf_member *m = btf_members(t) + member_idx;
+	bool kflag = btf_kflag(t);
+
+	return kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0;
+}
+
+static inline struct btf_param *btf_params(const struct btf_type *t)
+{
+	return (struct btf_param *)(t + 1);
+}
+
+static inline struct btf_var *btf_var(const struct btf_type *t)
+{
+	return (struct btf_var *)(t + 1);
+}
+
+static inline struct btf_var_secinfo *
+btf_var_secinfos(const struct btf_type *t)
+{
+	return (struct btf_var_secinfo *)(t + 1);
+}
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 7065bb5b2752..715967762312 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -100,21 +100,6 @@ static bool str_equal_fn(const void *a, const void *b, void *ctx)
 	return strcmp(a, b) == 0;
 }
 
-static __u16 btf_kind_of(const struct btf_type *t)
-{
-	return BTF_INFO_KIND(t->info);
-}
-
-static __u16 btf_vlen_of(const struct btf_type *t)
-{
-	return BTF_INFO_VLEN(t->info);
-}
-
-static bool btf_kflag_of(const struct btf_type *t)
-{
-	return BTF_INFO_KFLAG(t->info);
-}
-
 static const char *btf_name_of(const struct btf_dump *d, __u32 name_off)
 {
 	return btf__name_by_offset(d->btf, name_off);
@@ -349,7 +334,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 	 */
 	struct btf_dump_type_aux_state *tstate = &d->type_states[id];
 	const struct btf_type *t;
-	__u16 kind, vlen;
+	__u16 vlen;
 	int err, i;
 
 	/* return true, letting typedefs know that it's ok to be emitted */
@@ -357,18 +342,16 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 		return 1;
 
 	t = btf__type_by_id(d->btf, id);
-	kind = btf_kind_of(t);
 
 	if (tstate->order_state == ORDERING) {
 		/* type loop, but resolvable through fwd declaration */
-		if ((kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION) &&
-		    through_ptr && t->name_off != 0)
+		if (btf_is_composite(t) && through_ptr && t->name_off != 0)
 			return 0;
 		pr_warning("unsatisfiable type cycle, id:[%u]\n", id);
 		return -ELOOP;
 	}
 
-	switch (kind) {
+	switch (btf_kind(t)) {
 	case BTF_KIND_INT:
 		tstate->order_state = ORDERED;
 		return 0;
@@ -378,14 +361,12 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 		tstate->order_state = ORDERED;
 		return err;
 
-	case BTF_KIND_ARRAY: {
-		const struct btf_array *a = (void *)(t + 1);
+	case BTF_KIND_ARRAY:
+		return btf_dump_order_type(d, btf_array(t)->type, through_ptr);
 
-		return btf_dump_order_type(d, a->type, through_ptr);
-	}
 	case BTF_KIND_STRUCT:
 	case BTF_KIND_UNION: {
-		const struct btf_member *m = (void *)(t + 1);
+		const struct btf_member *m = btf_members(t);
 		/*
 		 * struct/union is part of strong link, only if it's embedded
 		 * (so no ptr in a path) or it's anonymous (so has to be
@@ -396,7 +377,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 
 		tstate->order_state = ORDERING;
 
-		vlen = btf_vlen_of(t);
+		vlen = btf_vlen(t);
 		for (i = 0; i < vlen; i++, m++) {
 			err = btf_dump_order_type(d, m->type, false);
 			if (err < 0)
@@ -447,7 +428,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 		return btf_dump_order_type(d, t->type, through_ptr);
 
 	case BTF_KIND_FUNC_PROTO: {
-		const struct btf_param *p = (void *)(t + 1);
+		const struct btf_param *p = btf_params(t);
 		bool is_strong;
 
 		err = btf_dump_order_type(d, t->type, through_ptr);
@@ -455,7 +436,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 			return err;
 		is_strong = err > 0;
 
-		vlen = btf_vlen_of(t);
+		vlen = btf_vlen(t);
 		for (i = 0; i < vlen; i++, p++) {
 			err = btf_dump_order_type(d, p->type, through_ptr);
 			if (err < 0)
@@ -553,7 +534,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
 		return;
 
 	t = btf__type_by_id(d->btf, id);
-	kind = btf_kind_of(t);
+	kind = btf_kind(t);
 
 	if (top_level_def && t->name_off == 0) {
 		pr_warning("unexpected nameless definition, id:[%u]\n", id);
@@ -618,12 +599,9 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
 	case BTF_KIND_RESTRICT:
 		btf_dump_emit_type(d, t->type, cont_id);
 		break;
-	case BTF_KIND_ARRAY: {
-		const struct btf_array *a = (void *)(t + 1);
-
-		btf_dump_emit_type(d, a->type, cont_id);
+	case BTF_KIND_ARRAY:
+		btf_dump_emit_type(d, btf_array(t)->type, cont_id);
 		break;
-	}
 	case BTF_KIND_FWD:
 		btf_dump_emit_fwd_def(d, id, t);
 		btf_dump_printf(d, ";\n\n");
@@ -656,8 +634,8 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
 		 * applicable
 		 */
 		if (top_level_def || t->name_off == 0) {
-			const struct btf_member *m = (void *)(t + 1);
-			__u16 vlen = btf_vlen_of(t);
+			const struct btf_member *m = btf_members(t);
+			__u16 vlen = btf_vlen(t);
 			int i, new_cont_id;
 
 			new_cont_id = t->name_off == 0 ? cont_id : id;
@@ -678,8 +656,8 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
 		}
 		break;
 	case BTF_KIND_FUNC_PROTO: {
-		const struct btf_param *p = (void *)(t + 1);
-		__u16 vlen = btf_vlen_of(t);
+		const struct btf_param *p = btf_params(t);
+		__u16 vlen = btf_vlen(t);
 		int i;
 
 		btf_dump_emit_type(d, t->type, cont_id);
@@ -696,7 +674,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
 static int btf_align_of(const struct btf *btf, __u32 id)
 {
 	const struct btf_type *t = btf__type_by_id(btf, id);
-	__u16 kind = btf_kind_of(t);
+	__u16 kind = btf_kind(t);
 
 	switch (kind) {
 	case BTF_KIND_INT:
@@ -709,15 +687,12 @@ static int btf_align_of(const struct btf *btf, __u32 id)
 	case BTF_KIND_CONST:
 	case BTF_KIND_RESTRICT:
 		return btf_align_of(btf, t->type);
-	case BTF_KIND_ARRAY: {
-		const struct btf_array *a = (void *)(t + 1);
-
-		return btf_align_of(btf, a->type);
-	}
+	case BTF_KIND_ARRAY:
+		return btf_align_of(btf, btf_array(t)->type);
 	case BTF_KIND_STRUCT:
 	case BTF_KIND_UNION: {
-		const struct btf_member *m = (void *)(t + 1);
-		__u16 vlen = btf_vlen_of(t);
+		const struct btf_member *m = btf_members(t);
+		__u16 vlen = btf_vlen(t);
 		int i, align = 1;
 
 		for (i = 0; i < vlen; i++, m++)
@@ -726,7 +701,7 @@ static int btf_align_of(const struct btf *btf, __u32 id)
 		return align;
 	}
 	default:
-		pr_warning("unsupported BTF_KIND:%u\n", btf_kind_of(t));
+		pr_warning("unsupported BTF_KIND:%u\n", btf_kind(t));
 		return 1;
 	}
 }
@@ -737,20 +712,18 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id,
 	const struct btf_member *m;
 	int align, i, bit_sz;
 	__u16 vlen;
-	bool kflag;
 
 	align = btf_align_of(btf, id);
 	/* size of a non-packed struct has to be a multiple of its alignment*/
 	if (t->size % align)
 		return true;
 
-	m = (void *)(t + 1);
-	kflag = btf_kflag_of(t);
-	vlen = btf_vlen_of(t);
+	m = btf_members(t);
+	vlen = btf_vlen(t);
 	/* all non-bitfield fields have to be naturally aligned */
 	for (i = 0; i < vlen; i++, m++) {
 		align = btf_align_of(btf, m->type);
-		bit_sz = kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0;
+		bit_sz = btf_member_bitfield_size(t, i);
 		if (bit_sz == 0 && m->offset % (8 * align) != 0)
 			return true;
 	}
@@ -807,7 +780,7 @@ static void btf_dump_emit_struct_fwd(struct btf_dump *d, __u32 id,
 				     const struct btf_type *t)
 {
 	btf_dump_printf(d, "%s %s",
-			btf_kind_of(t) == BTF_KIND_STRUCT ? "struct" : "union",
+			btf_is_struct(t) ? "struct" : "union",
 			btf_dump_type_name(d, id));
 }
 
@@ -816,12 +789,11 @@ static void btf_dump_emit_struct_def(struct btf_dump *d,
 				     const struct btf_type *t,
 				     int lvl)
 {
-	const struct btf_member *m = (void *)(t + 1);
-	bool kflag = btf_kflag_of(t), is_struct;
+	const struct btf_member *m = btf_members(t);
+	bool is_struct = btf_is_struct(t);
 	int align, i, packed, off = 0;
-	__u16 vlen = btf_vlen_of(t);
+	__u16 vlen = btf_vlen(t);
 
-	is_struct = btf_kind_of(t) == BTF_KIND_STRUCT;
 	packed = is_struct ? btf_is_struct_packed(d->btf, id, t) : 0;
 	align = packed ? 1 : btf_align_of(d->btf, id);
 
@@ -835,8 +807,8 @@ static void btf_dump_emit_struct_def(struct btf_dump *d,
 		int m_off, m_sz;
 
 		fname = btf_name_of(d, m->name_off);
-		m_sz = kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0;
-		m_off = kflag ? BTF_MEMBER_BIT_OFFSET(m->offset) : m->offset;
+		m_sz = btf_member_bitfield_size(t, i);
+		m_off = btf_member_bit_offset(t, i);
 		align = packed ? 1 : btf_align_of(d->btf, m->type);
 
 		btf_dump_emit_bit_padding(d, off, m_off, m_sz, align, lvl + 1);
@@ -870,8 +842,8 @@ static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id,
 				   const struct btf_type *t,
 				   int lvl)
 {
-	const struct btf_enum *v = (void *)(t+1);
-	__u16 vlen = btf_vlen_of(t);
+	const struct btf_enum *v = btf_enum(t);
+	__u16 vlen = btf_vlen(t);
 	const char *name;
 	size_t dup_cnt;
 	int i;
@@ -905,7 +877,7 @@ static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id,
 {
 	const char *name = btf_dump_type_name(d, id);
 
-	if (btf_kflag_of(t))
+	if (btf_kflag(t))
 		btf_dump_printf(d, "union %s", name);
 	else
 		btf_dump_printf(d, "struct %s", name);
@@ -987,7 +959,6 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id,
 	struct id_stack decl_stack;
 	const struct btf_type *t;
 	int err, stack_start;
-	__u16 kind;
 
 	stack_start = d->decl_stack_cnt;
 	for (;;) {
@@ -1008,8 +979,7 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id,
 			break;
 
 		t = btf__type_by_id(d->btf, id);
-		kind = btf_kind_of(t);
-		switch (kind) {
+		switch (btf_kind(t)) {
 		case BTF_KIND_PTR:
 		case BTF_KIND_VOLATILE:
 		case BTF_KIND_CONST:
@@ -1017,12 +987,9 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id,
 		case BTF_KIND_FUNC_PROTO:
 			id = t->type;
 			break;
-		case BTF_KIND_ARRAY: {
-			const struct btf_array *a = (void *)(t + 1);
-
-			id = a->type;
+		case BTF_KIND_ARRAY:
+			id = btf_array(t)->type;
 			break;
-		}
 		case BTF_KIND_INT:
 		case BTF_KIND_ENUM:
 		case BTF_KIND_FWD:
@@ -1032,7 +999,7 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id,
 			goto done;
 		default:
 			pr_warning("unexpected type in decl chain, kind:%u, id:[%u]\n",
-				   kind, id);
+				   btf_kind(t), id);
 			goto done;
 		}
 	}
@@ -1070,7 +1037,7 @@ static void btf_dump_emit_mods(struct btf_dump *d, struct id_stack *decl_stack)
 		id = decl_stack->ids[decl_stack->cnt - 1];
 		t = btf__type_by_id(d->btf, id);
 
-		switch (btf_kind_of(t)) {
+		switch (btf_kind(t)) {
 		case BTF_KIND_VOLATILE:
 			btf_dump_printf(d, "volatile ");
 			break;
@@ -1087,20 +1054,6 @@ static void btf_dump_emit_mods(struct btf_dump *d, struct id_stack *decl_stack)
 	}
 }
 
-static bool btf_is_mod_kind(const struct btf *btf, __u32 id)
-{
-	const struct btf_type *t = btf__type_by_id(btf, id);
-
-	switch (btf_kind_of(t)) {
-	case BTF_KIND_VOLATILE:
-	case BTF_KIND_CONST:
-	case BTF_KIND_RESTRICT:
-		return true;
-	default:
-		return false;
-	}
-}
-
 static void btf_dump_emit_name(const struct btf_dump *d,
 			       const char *name, bool last_was_ptr)
 {
@@ -1139,7 +1092,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 		}
 
 		t = btf__type_by_id(d->btf, id);
-		kind = btf_kind_of(t);
+		kind = btf_kind(t);
 
 		switch (kind) {
 		case BTF_KIND_INT:
@@ -1185,7 +1138,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 			btf_dump_printf(d, " restrict");
 			break;
 		case BTF_KIND_ARRAY: {
-			const struct btf_array *a = (void *)(t + 1);
+			const struct btf_array *a = btf_array(t);
 			const struct btf_type *next_t;
 			__u32 next_id;
 			bool multidim;
@@ -1201,7 +1154,8 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 			 */
 			while (decls->cnt) {
 				next_id = decls->ids[decls->cnt - 1];
-				if (btf_is_mod_kind(d->btf, next_id))
+				next_t = btf__type_by_id(d->btf, next_id);
+				if (btf_is_mod(next_t))
 					decls->cnt--;
 				else
 					break;
@@ -1214,7 +1168,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 			}
 
 			next_t = btf__type_by_id(d->btf, next_id);
-			multidim = btf_kind_of(next_t) == BTF_KIND_ARRAY;
+			multidim = btf_is_array(next_t);
 			/* we need space if we have named non-pointer */
 			if (fname[0] && !last_was_ptr)
 				btf_dump_printf(d, " ");
@@ -1228,8 +1182,8 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 			return;
 		}
 		case BTF_KIND_FUNC_PROTO: {
-			const struct btf_param *p = (void *)(t + 1);
-			__u16 vlen = btf_vlen_of(t);
+			const struct btf_param *p = btf_params(t);
+			__u16 vlen = btf_vlen(t);
 			int i;
 
 			btf_dump_emit_mods(d, decls);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 2586b6cb8f34..2233f919dd88 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -39,6 +39,7 @@
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <sys/vfs.h>
+#include <sys/utsname.h>
 #include <tools/libc_compat.h>
 #include <libelf.h>
 #include <gelf.h>
@@ -48,6 +49,7 @@
 #include "btf.h"
 #include "str_error.h"
 #include "libbpf_internal.h"
+#include "hashmap.h"
 
 #ifndef EM_BPF
 #define EM_BPF 247
@@ -75,9 +77,12 @@ static int __base_pr(enum libbpf_print_level level, const char *format,
 
 static libbpf_print_fn_t __libbpf_pr = __base_pr;
 
-void libbpf_set_print(libbpf_print_fn_t fn)
+libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn)
 {
+	libbpf_print_fn_t old_print_fn = __libbpf_pr;
+
 	__libbpf_pr = fn;
+	return old_print_fn;
 }
 
 __printf(2, 3)
@@ -1013,23 +1018,21 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 	return 0;
 }
 
-static const struct btf_type *skip_mods_and_typedefs(const struct btf *btf,
-						     __u32 id)
+static const struct btf_type *
+skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id)
 {
 	const struct btf_type *t = btf__type_by_id(btf, id);
 
-	while (true) {
-		switch (BTF_INFO_KIND(t->info)) {
-		case BTF_KIND_VOLATILE:
-		case BTF_KIND_CONST:
-		case BTF_KIND_RESTRICT:
-		case BTF_KIND_TYPEDEF:
-			t = btf__type_by_id(btf, t->type);
-			break;
-		default:
-			return t;
-		}
+	if (res_id)
+		*res_id = id;
+
+	while (btf_is_mod(t) || btf_is_typedef(t)) {
+		if (res_id)
+			*res_id = t->type;
+		t = btf__type_by_id(btf, t->type);
 	}
+
+	return t;
 }
 
 /*
@@ -1042,14 +1045,14 @@ static const struct btf_type *skip_mods_and_typedefs(const struct btf *btf,
 static bool get_map_field_int(const char *map_name, const struct btf *btf,
 			      const struct btf_type *def,
 			      const struct btf_member *m, __u32 *res) {
-	const struct btf_type *t = skip_mods_and_typedefs(btf, m->type);
+	const struct btf_type *t = skip_mods_and_typedefs(btf, m->type, NULL);
 	const char *name = btf__name_by_offset(btf, m->name_off);
 	const struct btf_array *arr_info;
 	const struct btf_type *arr_t;
 
-	if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) {
+	if (!btf_is_ptr(t)) {
 		pr_warning("map '%s': attr '%s': expected PTR, got %u.\n",
-			   map_name, name, BTF_INFO_KIND(t->info));
+			   map_name, name, btf_kind(t));
 		return false;
 	}
 
@@ -1059,12 +1062,12 @@ static bool get_map_field_int(const char *map_name, const struct btf *btf,
 			   map_name, name, t->type);
 		return false;
 	}
-	if (BTF_INFO_KIND(arr_t->info) != BTF_KIND_ARRAY) {
+	if (!btf_is_array(arr_t)) {
 		pr_warning("map '%s': attr '%s': expected ARRAY, got %u.\n",
-			   map_name, name, BTF_INFO_KIND(arr_t->info));
+			   map_name, name, btf_kind(arr_t));
 		return false;
 	}
-	arr_info = (const void *)(arr_t + 1);
+	arr_info = btf_array(arr_t);
 	*res = arr_info->nelems;
 	return true;
 }
@@ -1082,11 +1085,11 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 	struct bpf_map *map;
 	int vlen, i;
 
-	vi = (const struct btf_var_secinfo *)(const void *)(sec + 1) + var_idx;
+	vi = btf_var_secinfos(sec) + var_idx;
 	var = btf__type_by_id(obj->btf, vi->type);
-	var_extra = (const void *)(var + 1);
+	var_extra = btf_var(var);
 	map_name = btf__name_by_offset(obj->btf, var->name_off);
-	vlen = BTF_INFO_VLEN(var->info);
+	vlen = btf_vlen(var);
 
 	if (map_name == NULL || map_name[0] == '\0') {
 		pr_warning("map #%d: empty name.\n", var_idx);
@@ -1096,9 +1099,9 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 		pr_warning("map '%s' BTF data is corrupted.\n", map_name);
 		return -EINVAL;
 	}
-	if (BTF_INFO_KIND(var->info) != BTF_KIND_VAR) {
+	if (!btf_is_var(var)) {
 		pr_warning("map '%s': unexpected var kind %u.\n",
-			   map_name, BTF_INFO_KIND(var->info));
+			   map_name, btf_kind(var));
 		return -EINVAL;
 	}
 	if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED &&
@@ -1108,10 +1111,10 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 		return -EOPNOTSUPP;
 	}
 
-	def = skip_mods_and_typedefs(obj->btf, var->type);
-	if (BTF_INFO_KIND(def->info) != BTF_KIND_STRUCT) {
+	def = skip_mods_and_typedefs(obj->btf, var->type, NULL);
+	if (!btf_is_struct(def)) {
 		pr_warning("map '%s': unexpected def kind %u.\n",
-			   map_name, BTF_INFO_KIND(var->info));
+			   map_name, btf_kind(var));
 		return -EINVAL;
 	}
 	if (def->size > vi->size) {
@@ -1134,8 +1137,8 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 	pr_debug("map '%s': at sec_idx %d, offset %zu.\n",
 		 map_name, map->sec_idx, map->sec_offset);
 
-	vlen = BTF_INFO_VLEN(def->info);
-	m = (const void *)(def + 1);
+	vlen = btf_vlen(def);
+	m = btf_members(def);
 	for (i = 0; i < vlen; i++, m++) {
 		const char *name = btf__name_by_offset(obj->btf, m->name_off);
 
@@ -1185,9 +1188,9 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 					   map_name, m->type);
 				return -EINVAL;
 			}
-			if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) {
+			if (!btf_is_ptr(t)) {
 				pr_warning("map '%s': key spec is not PTR: %u.\n",
-					   map_name, BTF_INFO_KIND(t->info));
+					   map_name, btf_kind(t));
 				return -EINVAL;
 			}
 			sz = btf__resolve_size(obj->btf, t->type);
@@ -1228,9 +1231,9 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 					   map_name, m->type);
 				return -EINVAL;
 			}
-			if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) {
+			if (!btf_is_ptr(t)) {
 				pr_warning("map '%s': value spec is not PTR: %u.\n",
-					   map_name, BTF_INFO_KIND(t->info));
+					   map_name, btf_kind(t));
 				return -EINVAL;
 			}
 			sz = btf__resolve_size(obj->btf, t->type);
@@ -1291,7 +1294,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict)
 	nr_types = btf__get_nr_types(obj->btf);
 	for (i = 1; i <= nr_types; i++) {
 		t = btf__type_by_id(obj->btf, i);
-		if (BTF_INFO_KIND(t->info) != BTF_KIND_DATASEC)
+		if (!btf_is_datasec(t))
 			continue;
 		name = btf__name_by_offset(obj->btf, t->name_off);
 		if (strcmp(name, MAPS_ELF_SEC) == 0) {
@@ -1305,7 +1308,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict)
 		return -ENOENT;
 	}
 
-	vlen = BTF_INFO_VLEN(sec->info);
+	vlen = btf_vlen(sec);
 	for (i = 0; i < vlen; i++) {
 		err = bpf_object__init_user_btf_map(obj, sec, i,
 						    obj->efile.btf_maps_shndx,
@@ -1366,16 +1369,14 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj)
 	struct btf *btf = obj->btf;
 	struct btf_type *t;
 	int i, j, vlen;
-	__u16 kind;
 
 	if (!obj->btf || (has_func && has_datasec))
 		return;
 
 	for (i = 1; i <= btf__get_nr_types(btf); i++) {
 		t = (struct btf_type *)btf__type_by_id(btf, i);
-		kind = BTF_INFO_KIND(t->info);
 
-		if (!has_datasec && kind == BTF_KIND_VAR) {
+		if (!has_datasec && btf_is_var(t)) {
 			/* replace VAR with INT */
 			t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0);
 			/*
@@ -1384,11 +1385,11 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj)
 			 * original variable took less than 4 bytes
 			 */
 			t->size = 1;
-			*(int *)(t+1) = BTF_INT_ENC(0, 0, 8);
-		} else if (!has_datasec && kind == BTF_KIND_DATASEC) {
+			*(int *)(t + 1) = BTF_INT_ENC(0, 0, 8);
+		} else if (!has_datasec && btf_is_datasec(t)) {
 			/* replace DATASEC with STRUCT */
-			struct btf_var_secinfo *v = (void *)(t + 1);
-			struct btf_member *m = (void *)(t + 1);
+			const struct btf_var_secinfo *v = btf_var_secinfos(t);
+			struct btf_member *m = btf_members(t);
 			struct btf_type *vt;
 			char *name;
 
@@ -1399,7 +1400,7 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj)
 				name++;
 			}
 
-			vlen = BTF_INFO_VLEN(t->info);
+			vlen = btf_vlen(t);
 			t->info = BTF_INFO_ENC(BTF_KIND_STRUCT, 0, vlen);
 			for (j = 0; j < vlen; j++, v++, m++) {
 				/* order of field assignments is important */
@@ -1409,12 +1410,12 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj)
 				vt = (void *)btf__type_by_id(btf, v->type);
 				m->name_off = vt->name_off;
 			}
-		} else if (!has_func && kind == BTF_KIND_FUNC_PROTO) {
+		} else if (!has_func && btf_is_func_proto(t)) {
 			/* replace FUNC_PROTO with ENUM */
-			vlen = BTF_INFO_VLEN(t->info);
+			vlen = btf_vlen(t);
 			t->info = BTF_INFO_ENC(BTF_KIND_ENUM, 0, vlen);
 			t->size = sizeof(__u32); /* kernel enforced */
-		} else if (!has_func && kind == BTF_KIND_FUNC) {
+		} else if (!has_func && btf_is_func(t)) {
 			/* replace FUNC with TYPEDEF */
 			t->info = BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0);
 		}
@@ -1772,15 +1773,22 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
 			 (long long) sym.st_value, sym.st_name, name);
 
 		shdr_idx = sym.st_shndx;
+		insn_idx = rel.r_offset / sizeof(struct bpf_insn);
+		pr_debug("relocation: insn_idx=%u, shdr_idx=%u\n",
+			 insn_idx, shdr_idx);
+
+		if (shdr_idx >= SHN_LORESERVE) {
+			pr_warning("relocation: not yet supported relo for non-static global \'%s\' variable in special section (0x%x) found in insns[%d].code 0x%x\n",
+				   name, shdr_idx, insn_idx,
+				   insns[insn_idx].code);
+			return -LIBBPF_ERRNO__RELOC;
+		}
 		if (!bpf_object__relo_in_known_section(obj, shdr_idx)) {
 			pr_warning("Program '%s' contains unrecognized relo data pointing to section %u\n",
 				   prog->section_name, shdr_idx);
 			return -LIBBPF_ERRNO__RELOC;
 		}
 
-		insn_idx = rel.r_offset / sizeof(struct bpf_insn);
-		pr_debug("relocation: insn_idx=%u\n", insn_idx);
-
 		if (insns[insn_idx].code == (BPF_JMP | BPF_CALL)) {
 			if (insns[insn_idx].src_reg != BPF_PSEUDO_CALL) {
 				pr_warning("incorrect bpf_call opcode\n");
@@ -2294,6 +2302,894 @@ bpf_program_reloc_btf_ext(struct bpf_program *prog, struct bpf_object *obj,
 	return 0;
 }
 
+#define BPF_CORE_SPEC_MAX_LEN 64
+
+/* represents BPF CO-RE field or array element accessor */
+struct bpf_core_accessor {
+	__u32 type_id;		/* struct/union type or array element type */
+	__u32 idx;		/* field index or array index */
+	const char *name;	/* field name or NULL for array accessor */
+};
+
+struct bpf_core_spec {
+	const struct btf *btf;
+	/* high-level spec: named fields and array indices only */
+	struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN];
+	/* high-level spec length */
+	int len;
+	/* raw, low-level spec: 1-to-1 with accessor spec string */
+	int raw_spec[BPF_CORE_SPEC_MAX_LEN];
+	/* raw spec length */
+	int raw_len;
+	/* field byte offset represented by spec */
+	__u32 offset;
+};
+
+static bool str_is_empty(const char *s)
+{
+	return !s || !s[0];
+}
+
+/*
+ * Turn bpf_offset_reloc into a low- and high-level spec representation,
+ * validating correctness along the way, as well as calculating resulting
+ * field offset (in bytes), specified by accessor string. Low-level spec
+ * captures every single level of nestedness, including traversing anonymous
+ * struct/union members. High-level one only captures semantically meaningful
+ * "turning points": named fields and array indicies.
+ * E.g., for this case:
+ *
+ *   struct sample {
+ *       int __unimportant;
+ *       struct {
+ *           int __1;
+ *           int __2;
+ *           int a[7];
+ *       };
+ *   };
+ *
+ *   struct sample *s = ...;
+ *
+ *   int x = &s->a[3]; // access string = '0:1:2:3'
+ *
+ * Low-level spec has 1:1 mapping with each element of access string (it's
+ * just a parsed access string representation): [0, 1, 2, 3].
+ *
+ * High-level spec will capture only 3 points:
+ *   - intial zero-index access by pointer (&s->... is the same as &s[0]...);
+ *   - field 'a' access (corresponds to '2' in low-level spec);
+ *   - array element #3 access (corresponds to '3' in low-level spec).
+ *
+ */
+static int bpf_core_spec_parse(const struct btf *btf,
+			       __u32 type_id,
+			       const char *spec_str,
+			       struct bpf_core_spec *spec)
+{
+	int access_idx, parsed_len, i;
+	const struct btf_type *t;
+	const char *name;
+	__u32 id;
+	__s64 sz;
+
+	if (str_is_empty(spec_str) || *spec_str == ':')
+		return -EINVAL;
+
+	memset(spec, 0, sizeof(*spec));
+	spec->btf = btf;
+
+	/* parse spec_str="0:1:2:3:4" into array raw_spec=[0, 1, 2, 3, 4] */
+	while (*spec_str) {
+		if (*spec_str == ':')
+			++spec_str;
+		if (sscanf(spec_str, "%d%n", &access_idx, &parsed_len) != 1)
+			return -EINVAL;
+		if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN)
+			return -E2BIG;
+		spec_str += parsed_len;
+		spec->raw_spec[spec->raw_len++] = access_idx;
+	}
+
+	if (spec->raw_len == 0)
+		return -EINVAL;
+
+	/* first spec value is always reloc type array index */
+	t = skip_mods_and_typedefs(btf, type_id, &id);
+	if (!t)
+		return -EINVAL;
+
+	access_idx = spec->raw_spec[0];
+	spec->spec[0].type_id = id;
+	spec->spec[0].idx = access_idx;
+	spec->len++;
+
+	sz = btf__resolve_size(btf, id);
+	if (sz < 0)
+		return sz;
+	spec->offset = access_idx * sz;
+
+	for (i = 1; i < spec->raw_len; i++) {
+		t = skip_mods_and_typedefs(btf, id, &id);
+		if (!t)
+			return -EINVAL;
+
+		access_idx = spec->raw_spec[i];
+
+		if (btf_is_composite(t)) {
+			const struct btf_member *m;
+			__u32 offset;
+
+			if (access_idx >= btf_vlen(t))
+				return -EINVAL;
+			if (btf_member_bitfield_size(t, access_idx))
+				return -EINVAL;
+
+			offset = btf_member_bit_offset(t, access_idx);
+			if (offset % 8)
+				return -EINVAL;
+			spec->offset += offset / 8;
+
+			m = btf_members(t) + access_idx;
+			if (m->name_off) {
+				name = btf__name_by_offset(btf, m->name_off);
+				if (str_is_empty(name))
+					return -EINVAL;
+
+				spec->spec[spec->len].type_id = id;
+				spec->spec[spec->len].idx = access_idx;
+				spec->spec[spec->len].name = name;
+				spec->len++;
+			}
+
+			id = m->type;
+		} else if (btf_is_array(t)) {
+			const struct btf_array *a = btf_array(t);
+
+			t = skip_mods_and_typedefs(btf, a->type, &id);
+			if (!t || access_idx >= a->nelems)
+				return -EINVAL;
+
+			spec->spec[spec->len].type_id = id;
+			spec->spec[spec->len].idx = access_idx;
+			spec->len++;
+
+			sz = btf__resolve_size(btf, id);
+			if (sz < 0)
+				return sz;
+			spec->offset += access_idx * sz;
+		} else {
+			pr_warning("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %d\n",
+				   type_id, spec_str, i, id, btf_kind(t));
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static bool bpf_core_is_flavor_sep(const char *s)
+{
+	/* check X___Y name pattern, where X and Y are not underscores */
+	return s[0] != '_' &&				      /* X */
+	       s[1] == '_' && s[2] == '_' && s[3] == '_' &&   /* ___ */
+	       s[4] != '_';				      /* Y */
+}
+
+/* Given 'some_struct_name___with_flavor' return the length of a name prefix
+ * before last triple underscore. Struct name part after last triple
+ * underscore is ignored by BPF CO-RE relocation during relocation matching.
+ */
+static size_t bpf_core_essential_name_len(const char *name)
+{
+	size_t n = strlen(name);
+	int i;
+
+	for (i = n - 5; i >= 0; i--) {
+		if (bpf_core_is_flavor_sep(name + i))
+			return i + 1;
+	}
+	return n;
+}
+
+/* dynamically sized list of type IDs */
+struct ids_vec {
+	__u32 *data;
+	int len;
+};
+
+static void bpf_core_free_cands(struct ids_vec *cand_ids)
+{
+	free(cand_ids->data);
+	free(cand_ids);
+}
+
+static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf,
+					   __u32 local_type_id,
+					   const struct btf *targ_btf)
+{
+	size_t local_essent_len, targ_essent_len;
+	const char *local_name, *targ_name;
+	const struct btf_type *t;
+	struct ids_vec *cand_ids;
+	__u32 *new_ids;
+	int i, err, n;
+
+	t = btf__type_by_id(local_btf, local_type_id);
+	if (!t)
+		return ERR_PTR(-EINVAL);
+
+	local_name = btf__name_by_offset(local_btf, t->name_off);
+	if (str_is_empty(local_name))
+		return ERR_PTR(-EINVAL);
+	local_essent_len = bpf_core_essential_name_len(local_name);
+
+	cand_ids = calloc(1, sizeof(*cand_ids));
+	if (!cand_ids)
+		return ERR_PTR(-ENOMEM);
+
+	n = btf__get_nr_types(targ_btf);
+	for (i = 1; i <= n; i++) {
+		t = btf__type_by_id(targ_btf, i);
+		targ_name = btf__name_by_offset(targ_btf, t->name_off);
+		if (str_is_empty(targ_name))
+			continue;
+
+		targ_essent_len = bpf_core_essential_name_len(targ_name);
+		if (targ_essent_len != local_essent_len)
+			continue;
+
+		if (strncmp(local_name, targ_name, local_essent_len) == 0) {
+			pr_debug("[%d] %s: found candidate [%d] %s\n",
+				 local_type_id, local_name, i, targ_name);
+			new_ids = realloc(cand_ids->data, cand_ids->len + 1);
+			if (!new_ids) {
+				err = -ENOMEM;
+				goto err_out;
+			}
+			cand_ids->data = new_ids;
+			cand_ids->data[cand_ids->len++] = i;
+		}
+	}
+	return cand_ids;
+err_out:
+	bpf_core_free_cands(cand_ids);
+	return ERR_PTR(err);
+}
+
+/* Check two types for compatibility, skipping const/volatile/restrict and
+ * typedefs, to ensure we are relocating offset to the compatible entities:
+ *   - any two STRUCTs/UNIONs are compatible and can be mixed;
+ *   - any two FWDs are compatible;
+ *   - any two PTRs are always compatible;
+ *   - for ENUMs, check sizes, names are ignored;
+ *   - for INT, size and bitness should match, signedness is ignored;
+ *   - for ARRAY, dimensionality is ignored, element types are checked for
+ *     compatibility recursively;
+ *   - everything else shouldn't be ever a target of relocation.
+ * These rules are not set in stone and probably will be adjusted as we get
+ * more experience with using BPF CO-RE relocations.
+ */
+static int bpf_core_fields_are_compat(const struct btf *local_btf,
+				      __u32 local_id,
+				      const struct btf *targ_btf,
+				      __u32 targ_id)
+{
+	const struct btf_type *local_type, *targ_type;
+
+recur:
+	local_type = skip_mods_and_typedefs(local_btf, local_id, &local_id);
+	targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id);
+	if (!local_type || !targ_type)
+		return -EINVAL;
+
+	if (btf_is_composite(local_type) && btf_is_composite(targ_type))
+		return 1;
+	if (btf_kind(local_type) != btf_kind(targ_type))
+		return 0;
+
+	switch (btf_kind(local_type)) {
+	case BTF_KIND_FWD:
+	case BTF_KIND_PTR:
+		return 1;
+	case BTF_KIND_ENUM:
+		return local_type->size == targ_type->size;
+	case BTF_KIND_INT:
+		return btf_int_offset(local_type) == 0 &&
+		       btf_int_offset(targ_type) == 0 &&
+		       local_type->size == targ_type->size &&
+		       btf_int_bits(local_type) == btf_int_bits(targ_type);
+	case BTF_KIND_ARRAY:
+		local_id = btf_array(local_type)->type;
+		targ_id = btf_array(targ_type)->type;
+		goto recur;
+	default:
+		pr_warning("unexpected kind %d relocated, local [%d], target [%d]\n",
+			   btf_kind(local_type), local_id, targ_id);
+		return 0;
+	}
+}
+
+/*
+ * Given single high-level named field accessor in local type, find
+ * corresponding high-level accessor for a target type. Along the way,
+ * maintain low-level spec for target as well. Also keep updating target
+ * offset.
+ *
+ * Searching is performed through recursive exhaustive enumeration of all
+ * fields of a struct/union. If there are any anonymous (embedded)
+ * structs/unions, they are recursively searched as well. If field with
+ * desired name is found, check compatibility between local and target types,
+ * before returning result.
+ *
+ * 1 is returned, if field is found.
+ * 0 is returned if no compatible field is found.
+ * <0 is returned on error.
+ */
+static int bpf_core_match_member(const struct btf *local_btf,
+				 const struct bpf_core_accessor *local_acc,
+				 const struct btf *targ_btf,
+				 __u32 targ_id,
+				 struct bpf_core_spec *spec,
+				 __u32 *next_targ_id)
+{
+	const struct btf_type *local_type, *targ_type;
+	const struct btf_member *local_member, *m;
+	const char *local_name, *targ_name;
+	__u32 local_id;
+	int i, n, found;
+
+	targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id);
+	if (!targ_type)
+		return -EINVAL;
+	if (!btf_is_composite(targ_type))
+		return 0;
+
+	local_id = local_acc->type_id;
+	local_type = btf__type_by_id(local_btf, local_id);
+	local_member = btf_members(local_type) + local_acc->idx;
+	local_name = btf__name_by_offset(local_btf, local_member->name_off);
+
+	n = btf_vlen(targ_type);
+	m = btf_members(targ_type);
+	for (i = 0; i < n; i++, m++) {
+		__u32 offset;
+
+		/* bitfield relocations not supported */
+		if (btf_member_bitfield_size(targ_type, i))
+			continue;
+		offset = btf_member_bit_offset(targ_type, i);
+		if (offset % 8)
+			continue;
+
+		/* too deep struct/union/array nesting */
+		if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN)
+			return -E2BIG;
+
+		/* speculate this member will be the good one */
+		spec->offset += offset / 8;
+		spec->raw_spec[spec->raw_len++] = i;
+
+		targ_name = btf__name_by_offset(targ_btf, m->name_off);
+		if (str_is_empty(targ_name)) {
+			/* embedded struct/union, we need to go deeper */
+			found = bpf_core_match_member(local_btf, local_acc,
+						      targ_btf, m->type,
+						      spec, next_targ_id);
+			if (found) /* either found or error */
+				return found;
+		} else if (strcmp(local_name, targ_name) == 0) {
+			/* matching named field */
+			struct bpf_core_accessor *targ_acc;
+
+			targ_acc = &spec->spec[spec->len++];
+			targ_acc->type_id = targ_id;
+			targ_acc->idx = i;
+			targ_acc->name = targ_name;
+
+			*next_targ_id = m->type;
+			found = bpf_core_fields_are_compat(local_btf,
+							   local_member->type,
+							   targ_btf, m->type);
+			if (!found)
+				spec->len--; /* pop accessor */
+			return found;
+		}
+		/* member turned out not to be what we looked for */
+		spec->offset -= offset / 8;
+		spec->raw_len--;
+	}
+
+	return 0;
+}
+
+/*
+ * Try to match local spec to a target type and, if successful, produce full
+ * target spec (high-level, low-level + offset).
+ */
+static int bpf_core_spec_match(struct bpf_core_spec *local_spec,
+			       const struct btf *targ_btf, __u32 targ_id,
+			       struct bpf_core_spec *targ_spec)
+{
+	const struct btf_type *targ_type;
+	const struct bpf_core_accessor *local_acc;
+	struct bpf_core_accessor *targ_acc;
+	int i, sz, matched;
+
+	memset(targ_spec, 0, sizeof(*targ_spec));
+	targ_spec->btf = targ_btf;
+
+	local_acc = &local_spec->spec[0];
+	targ_acc = &targ_spec->spec[0];
+
+	for (i = 0; i < local_spec->len; i++, local_acc++, targ_acc++) {
+		targ_type = skip_mods_and_typedefs(targ_spec->btf, targ_id,
+						   &targ_id);
+		if (!targ_type)
+			return -EINVAL;
+
+		if (local_acc->name) {
+			matched = bpf_core_match_member(local_spec->btf,
+							local_acc,
+							targ_btf, targ_id,
+							targ_spec, &targ_id);
+			if (matched <= 0)
+				return matched;
+		} else {
+			/* for i=0, targ_id is already treated as array element
+			 * type (because it's the original struct), for others
+			 * we should find array element type first
+			 */
+			if (i > 0) {
+				const struct btf_array *a;
+
+				if (!btf_is_array(targ_type))
+					return 0;
+
+				a = btf_array(targ_type);
+				if (local_acc->idx >= a->nelems)
+					return 0;
+				if (!skip_mods_and_typedefs(targ_btf, a->type,
+							    &targ_id))
+					return -EINVAL;
+			}
+
+			/* too deep struct/union/array nesting */
+			if (targ_spec->raw_len == BPF_CORE_SPEC_MAX_LEN)
+				return -E2BIG;
+
+			targ_acc->type_id = targ_id;
+			targ_acc->idx = local_acc->idx;
+			targ_acc->name = NULL;
+			targ_spec->len++;
+			targ_spec->raw_spec[targ_spec->raw_len] = targ_acc->idx;
+			targ_spec->raw_len++;
+
+			sz = btf__resolve_size(targ_btf, targ_id);
+			if (sz < 0)
+				return sz;
+			targ_spec->offset += local_acc->idx * sz;
+		}
+	}
+
+	return 1;
+}
+
+/*
+ * Patch relocatable BPF instruction.
+ * Expected insn->imm value is provided for validation, as well as the new
+ * relocated value.
+ *
+ * Currently three kinds of BPF instructions are supported:
+ * 1. rX = <imm> (assignment with immediate operand);
+ * 2. rX += <imm> (arithmetic operations with immediate operand);
+ * 3. *(rX) = <imm> (indirect memory assignment with immediate operand).
+ *
+ * If actual insn->imm value is wrong, bail out.
+ */
+static int bpf_core_reloc_insn(struct bpf_program *prog, int insn_off,
+			       __u32 orig_off, __u32 new_off)
+{
+	struct bpf_insn *insn;
+	int insn_idx;
+	__u8 class;
+
+	if (insn_off % sizeof(struct bpf_insn))
+		return -EINVAL;
+	insn_idx = insn_off / sizeof(struct bpf_insn);
+
+	insn = &prog->insns[insn_idx];
+	class = BPF_CLASS(insn->code);
+
+	if (class == BPF_ALU || class == BPF_ALU64) {
+		if (BPF_SRC(insn->code) != BPF_K)
+			return -EINVAL;
+		if (insn->imm != orig_off)
+			return -EINVAL;
+		insn->imm = new_off;
+		pr_debug("prog '%s': patched insn #%d (ALU/ALU64) imm %d -> %d\n",
+			 bpf_program__title(prog, false),
+			 insn_idx, orig_off, new_off);
+	} else {
+		pr_warning("prog '%s': trying to relocate unrecognized insn #%d, code:%x, src:%x, dst:%x, off:%x, imm:%x\n",
+			   bpf_program__title(prog, false),
+			   insn_idx, insn->code, insn->src_reg, insn->dst_reg,
+			   insn->off, insn->imm);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static struct btf *btf_load_raw(const char *path)
+{
+	struct btf *btf;
+	size_t read_cnt;
+	struct stat st;
+	void *data;
+	FILE *f;
+
+	if (stat(path, &st))
+		return ERR_PTR(-errno);
+
+	data = malloc(st.st_size);
+	if (!data)
+		return ERR_PTR(-ENOMEM);
+
+	f = fopen(path, "rb");
+	if (!f) {
+		btf = ERR_PTR(-errno);
+		goto cleanup;
+	}
+
+	read_cnt = fread(data, 1, st.st_size, f);
+	fclose(f);
+	if (read_cnt < st.st_size) {
+		btf = ERR_PTR(-EBADF);
+		goto cleanup;
+	}
+
+	btf = btf__new(data, read_cnt);
+
+cleanup:
+	free(data);
+	return btf;
+}
+
+/*
+ * Probe few well-known locations for vmlinux kernel image and try to load BTF
+ * data out of it to use for target BTF.
+ */
+static struct btf *bpf_core_find_kernel_btf(void)
+{
+	struct {
+		const char *path_fmt;
+		bool raw_btf;
+	} locations[] = {
+		/* try canonical vmlinux BTF through sysfs first */
+		{ "/sys/kernel/btf/vmlinux", true /* raw BTF */ },
+		/* fall back to trying to find vmlinux ELF on disk otherwise */
+		{ "/boot/vmlinux-%1$s" },
+		{ "/lib/modules/%1$s/vmlinux-%1$s" },
+		{ "/lib/modules/%1$s/build/vmlinux" },
+		{ "/usr/lib/modules/%1$s/kernel/vmlinux" },
+		{ "/usr/lib/debug/boot/vmlinux-%1$s" },
+		{ "/usr/lib/debug/boot/vmlinux-%1$s.debug" },
+		{ "/usr/lib/debug/lib/modules/%1$s/vmlinux" },
+	};
+	char path[PATH_MAX + 1];
+	struct utsname buf;
+	struct btf *btf;
+	int i;
+
+	uname(&buf);
+
+	for (i = 0; i < ARRAY_SIZE(locations); i++) {
+		snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release);
+
+		if (access(path, R_OK))
+			continue;
+
+		if (locations[i].raw_btf)
+			btf = btf_load_raw(path);
+		else
+			btf = btf__parse_elf(path, NULL);
+
+		pr_debug("loading kernel BTF '%s': %ld\n",
+			 path, IS_ERR(btf) ? PTR_ERR(btf) : 0);
+		if (IS_ERR(btf))
+			continue;
+
+		return btf;
+	}
+
+	pr_warning("failed to find valid kernel BTF\n");
+	return ERR_PTR(-ESRCH);
+}
+
+/* Output spec definition in the format:
+ * [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>,
+ * where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b
+ */
+static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec)
+{
+	const struct btf_type *t;
+	const char *s;
+	__u32 type_id;
+	int i;
+
+	type_id = spec->spec[0].type_id;
+	t = btf__type_by_id(spec->btf, type_id);
+	s = btf__name_by_offset(spec->btf, t->name_off);
+	libbpf_print(level, "[%u] %s + ", type_id, s);
+
+	for (i = 0; i < spec->raw_len; i++)
+		libbpf_print(level, "%d%s", spec->raw_spec[i],
+			     i == spec->raw_len - 1 ? " => " : ":");
+
+	libbpf_print(level, "%u @ &x", spec->offset);
+
+	for (i = 0; i < spec->len; i++) {
+		if (spec->spec[i].name)
+			libbpf_print(level, ".%s", spec->spec[i].name);
+		else
+			libbpf_print(level, "[%u]", spec->spec[i].idx);
+	}
+
+}
+
+static size_t bpf_core_hash_fn(const void *key, void *ctx)
+{
+	return (size_t)key;
+}
+
+static bool bpf_core_equal_fn(const void *k1, const void *k2, void *ctx)
+{
+	return k1 == k2;
+}
+
+static void *u32_as_hash_key(__u32 x)
+{
+	return (void *)(uintptr_t)x;
+}
+
+/*
+ * CO-RE relocate single instruction.
+ *
+ * The outline and important points of the algorithm:
+ * 1. For given local type, find corresponding candidate target types.
+ *    Candidate type is a type with the same "essential" name, ignoring
+ *    everything after last triple underscore (___). E.g., `sample`,
+ *    `sample___flavor_one`, `sample___flavor_another_one`, are all candidates
+ *    for each other. Names with triple underscore are referred to as
+ *    "flavors" and are useful, among other things, to allow to
+ *    specify/support incompatible variations of the same kernel struct, which
+ *    might differ between different kernel versions and/or build
+ *    configurations.
+ *
+ *    N.B. Struct "flavors" could be generated by bpftool's BTF-to-C
+ *    converter, when deduplicated BTF of a kernel still contains more than
+ *    one different types with the same name. In that case, ___2, ___3, etc
+ *    are appended starting from second name conflict. But start flavors are
+ *    also useful to be defined "locally", in BPF program, to extract same
+ *    data from incompatible changes between different kernel
+ *    versions/configurations. For instance, to handle field renames between
+ *    kernel versions, one can use two flavors of the struct name with the
+ *    same common name and use conditional relocations to extract that field,
+ *    depending on target kernel version.
+ * 2. For each candidate type, try to match local specification to this
+ *    candidate target type. Matching involves finding corresponding
+ *    high-level spec accessors, meaning that all named fields should match,
+ *    as well as all array accesses should be within the actual bounds. Also,
+ *    types should be compatible (see bpf_core_fields_are_compat for details).
+ * 3. It is supported and expected that there might be multiple flavors
+ *    matching the spec. As long as all the specs resolve to the same set of
+ *    offsets across all candidates, there is not error. If there is any
+ *    ambiguity, CO-RE relocation will fail. This is necessary to accomodate
+ *    imprefection of BTF deduplication, which can cause slight duplication of
+ *    the same BTF type, if some directly or indirectly referenced (by
+ *    pointer) type gets resolved to different actual types in different
+ *    object files. If such situation occurs, deduplicated BTF will end up
+ *    with two (or more) structurally identical types, which differ only in
+ *    types they refer to through pointer. This should be OK in most cases and
+ *    is not an error.
+ * 4. Candidate types search is performed by linearly scanning through all
+ *    types in target BTF. It is anticipated that this is overall more
+ *    efficient memory-wise and not significantly worse (if not better)
+ *    CPU-wise compared to prebuilding a map from all local type names to
+ *    a list of candidate type names. It's also sped up by caching resolved
+ *    list of matching candidates per each local "root" type ID, that has at
+ *    least one bpf_offset_reloc associated with it. This list is shared
+ *    between multiple relocations for the same type ID and is updated as some
+ *    of the candidates are pruned due to structural incompatibility.
+ */
+static int bpf_core_reloc_offset(struct bpf_program *prog,
+				 const struct bpf_offset_reloc *relo,
+				 int relo_idx,
+				 const struct btf *local_btf,
+				 const struct btf *targ_btf,
+				 struct hashmap *cand_cache)
+{
+	const char *prog_name = bpf_program__title(prog, false);
+	struct bpf_core_spec local_spec, cand_spec, targ_spec;
+	const void *type_key = u32_as_hash_key(relo->type_id);
+	const struct btf_type *local_type, *cand_type;
+	const char *local_name, *cand_name;
+	struct ids_vec *cand_ids;
+	__u32 local_id, cand_id;
+	const char *spec_str;
+	int i, j, err;
+
+	local_id = relo->type_id;
+	local_type = btf__type_by_id(local_btf, local_id);
+	if (!local_type)
+		return -EINVAL;
+
+	local_name = btf__name_by_offset(local_btf, local_type->name_off);
+	if (str_is_empty(local_name))
+		return -EINVAL;
+
+	spec_str = btf__name_by_offset(local_btf, relo->access_str_off);
+	if (str_is_empty(spec_str))
+		return -EINVAL;
+
+	err = bpf_core_spec_parse(local_btf, local_id, spec_str, &local_spec);
+	if (err) {
+		pr_warning("prog '%s': relo #%d: parsing [%d] %s + %s failed: %d\n",
+			   prog_name, relo_idx, local_id, local_name, spec_str,
+			   err);
+		return -EINVAL;
+	}
+
+	pr_debug("prog '%s': relo #%d: spec is ", prog_name, relo_idx);
+	bpf_core_dump_spec(LIBBPF_DEBUG, &local_spec);
+	libbpf_print(LIBBPF_DEBUG, "\n");
+
+	if (!hashmap__find(cand_cache, type_key, (void **)&cand_ids)) {
+		cand_ids = bpf_core_find_cands(local_btf, local_id, targ_btf);
+		if (IS_ERR(cand_ids)) {
+			pr_warning("prog '%s': relo #%d: target candidate search failed for [%d] %s: %ld",
+				   prog_name, relo_idx, local_id, local_name,
+				   PTR_ERR(cand_ids));
+			return PTR_ERR(cand_ids);
+		}
+		err = hashmap__set(cand_cache, type_key, cand_ids, NULL, NULL);
+		if (err) {
+			bpf_core_free_cands(cand_ids);
+			return err;
+		}
+	}
+
+	for (i = 0, j = 0; i < cand_ids->len; i++) {
+		cand_id = cand_ids->data[i];
+		cand_type = btf__type_by_id(targ_btf, cand_id);
+		cand_name = btf__name_by_offset(targ_btf, cand_type->name_off);
+
+		err = bpf_core_spec_match(&local_spec, targ_btf,
+					  cand_id, &cand_spec);
+		pr_debug("prog '%s': relo #%d: matching candidate #%d %s against spec ",
+			 prog_name, relo_idx, i, cand_name);
+		bpf_core_dump_spec(LIBBPF_DEBUG, &cand_spec);
+		libbpf_print(LIBBPF_DEBUG, ": %d\n", err);
+		if (err < 0) {
+			pr_warning("prog '%s': relo #%d: matching error: %d\n",
+				   prog_name, relo_idx, err);
+			return err;
+		}
+		if (err == 0)
+			continue;
+
+		if (j == 0) {
+			targ_spec = cand_spec;
+		} else if (cand_spec.offset != targ_spec.offset) {
+			/* if there are many candidates, they should all
+			 * resolve to the same offset
+			 */
+			pr_warning("prog '%s': relo #%d: offset ambiguity: %u != %u\n",
+				   prog_name, relo_idx, cand_spec.offset,
+				   targ_spec.offset);
+			return -EINVAL;
+		}
+
+		cand_ids->data[j++] = cand_spec.spec[0].type_id;
+	}
+
+	cand_ids->len = j;
+	if (cand_ids->len == 0) {
+		pr_warning("prog '%s': relo #%d: no matching targets found for [%d] %s + %s\n",
+			   prog_name, relo_idx, local_id, local_name, spec_str);
+		return -ESRCH;
+	}
+
+	err = bpf_core_reloc_insn(prog, relo->insn_off,
+				  local_spec.offset, targ_spec.offset);
+	if (err) {
+		pr_warning("prog '%s': relo #%d: failed to patch insn at offset %d: %d\n",
+			   prog_name, relo_idx, relo->insn_off, err);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+bpf_core_reloc_offsets(struct bpf_object *obj, const char *targ_btf_path)
+{
+	const struct btf_ext_info_sec *sec;
+	const struct bpf_offset_reloc *rec;
+	const struct btf_ext_info *seg;
+	struct hashmap_entry *entry;
+	struct hashmap *cand_cache = NULL;
+	struct bpf_program *prog;
+	struct btf *targ_btf;
+	const char *sec_name;
+	int i, err = 0;
+
+	if (targ_btf_path)
+		targ_btf = btf__parse_elf(targ_btf_path, NULL);
+	else
+		targ_btf = bpf_core_find_kernel_btf();
+	if (IS_ERR(targ_btf)) {
+		pr_warning("failed to get target BTF: %ld\n",
+			   PTR_ERR(targ_btf));
+		return PTR_ERR(targ_btf);
+	}
+
+	cand_cache = hashmap__new(bpf_core_hash_fn, bpf_core_equal_fn, NULL);
+	if (IS_ERR(cand_cache)) {
+		err = PTR_ERR(cand_cache);
+		goto out;
+	}
+
+	seg = &obj->btf_ext->offset_reloc_info;
+	for_each_btf_ext_sec(seg, sec) {
+		sec_name = btf__name_by_offset(obj->btf, sec->sec_name_off);
+		if (str_is_empty(sec_name)) {
+			err = -EINVAL;
+			goto out;
+		}
+		prog = bpf_object__find_program_by_title(obj, sec_name);
+		if (!prog) {
+			pr_warning("failed to find program '%s' for CO-RE offset relocation\n",
+				   sec_name);
+			err = -EINVAL;
+			goto out;
+		}
+
+		pr_debug("prog '%s': performing %d CO-RE offset relocs\n",
+			 sec_name, sec->num_info);
+
+		for_each_btf_ext_rec(seg, sec, i, rec) {
+			err = bpf_core_reloc_offset(prog, rec, i, obj->btf,
+						    targ_btf, cand_cache);
+			if (err) {
+				pr_warning("prog '%s': relo #%d: failed to relocate: %d\n",
+					   sec_name, i, err);
+				goto out;
+			}
+		}
+	}
+
+out:
+	btf__free(targ_btf);
+	if (!IS_ERR_OR_NULL(cand_cache)) {
+		hashmap__for_each_entry(cand_cache, entry, i) {
+			bpf_core_free_cands(entry->value);
+		}
+		hashmap__free(cand_cache);
+	}
+	return err;
+}
+
+static int
+bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path)
+{
+	int err = 0;
+
+	if (obj->btf_ext->offset_reloc_info.len)
+		err = bpf_core_reloc_offsets(obj, targ_btf_path);
+
+	return err;
+}
+
 static int
 bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 			struct reloc_desc *relo)
@@ -2401,14 +3297,21 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
 	return 0;
 }
 
-
 static int
-bpf_object__relocate(struct bpf_object *obj)
+bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 {
 	struct bpf_program *prog;
 	size_t i;
 	int err;
 
+	if (obj->btf_ext) {
+		err = bpf_object__relocate_core(obj, targ_btf_path);
+		if (err) {
+			pr_warning("failed to perform CO-RE relocations: %d\n",
+				   err);
+			return err;
+		}
+	}
 	for (i = 0; i < obj->nr_programs; i++) {
 		prog = &obj->programs[i];
 
@@ -2809,7 +3712,7 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
 	obj->loaded = true;
 
 	CHECK_ERR(bpf_object__create_maps(obj), err, out);
-	CHECK_ERR(bpf_object__relocate(obj), err, out);
+	CHECK_ERR(bpf_object__relocate(obj, attr->target_btf_path), err, out);
 	CHECK_ERR(bpf_object__load_progs(obj, attr->log_level), err, out);
 
 	return 0;
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 5cbf459ece0b..e8f70977d137 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -57,7 +57,7 @@ enum libbpf_print_level {
 typedef int (*libbpf_print_fn_t)(enum libbpf_print_level level,
 				 const char *, va_list ap);
 
-LIBBPF_API void libbpf_set_print(libbpf_print_fn_t fn);
+LIBBPF_API libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn);
 
 /* Hide internal to user */
 struct bpf_object;
@@ -92,6 +92,7 @@ LIBBPF_API void bpf_object__close(struct bpf_object *object);
 struct bpf_object_load_attr {
 	struct bpf_object *obj;
 	int log_level;
+	const char *target_btf_path;
 };
 
 /* Load/unload object into/from kernel */
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 2ac29bd36226..2e83a34f8c79 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -29,6 +29,10 @@
 #ifndef max
 # define max(x, y) ((x) < (y) ? (y) : (x))
 #endif
+#ifndef offsetofend
+# define offsetofend(TYPE, FIELD) \
+	(offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD))
+#endif
 
 extern void libbpf_print(enum libbpf_print_level level,
 			 const char *format, ...)
@@ -46,4 +50,105 @@ do {				\
 int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
 			 const char *str_sec, size_t str_len);
 
+struct btf_ext_info {
+	/*
+	 * info points to the individual info section (e.g. func_info and
+	 * line_info) from the .BTF.ext. It does not include the __u32 rec_size.
+	 */
+	void *info;
+	__u32 rec_size;
+	__u32 len;
+};
+
+#define for_each_btf_ext_sec(seg, sec)					\
+	for (sec = (seg)->info;						\
+	     (void *)sec < (seg)->info + (seg)->len;			\
+	     sec = (void *)sec + sizeof(struct btf_ext_info_sec) +	\
+		   (seg)->rec_size * sec->num_info)
+
+#define for_each_btf_ext_rec(seg, sec, i, rec)				\
+	for (i = 0, rec = (void *)&(sec)->data;				\
+	     i < (sec)->num_info;					\
+	     i++, rec = (void *)rec + (seg)->rec_size)
+
+struct btf_ext {
+	union {
+		struct btf_ext_header *hdr;
+		void *data;
+	};
+	struct btf_ext_info func_info;
+	struct btf_ext_info line_info;
+	struct btf_ext_info offset_reloc_info;
+	__u32 data_size;
+};
+
+struct btf_ext_info_sec {
+	__u32	sec_name_off;
+	__u32	num_info;
+	/* Followed by num_info * record_size number of bytes */
+	__u8	data[0];
+};
+
+/* The minimum bpf_func_info checked by the loader */
+struct bpf_func_info_min {
+	__u32   insn_off;
+	__u32   type_id;
+};
+
+/* The minimum bpf_line_info checked by the loader */
+struct bpf_line_info_min {
+	__u32	insn_off;
+	__u32	file_name_off;
+	__u32	line_off;
+	__u32	line_col;
+};
+
+/* The minimum bpf_offset_reloc checked by the loader
+ *
+ * Offset relocation captures the following data:
+ * - insn_off - instruction offset (in bytes) within a BPF program that needs
+ *   its insn->imm field to be relocated with actual offset;
+ * - type_id - BTF type ID of the "root" (containing) entity of a relocatable
+ *   offset;
+ * - access_str_off - offset into corresponding .BTF string section. String
+ *   itself encodes an accessed field using a sequence of field and array
+ *   indicies, separated by colon (:). It's conceptually very close to LLVM's
+ *   getelementptr ([0]) instruction's arguments for identifying offset to 
+ *   a field.
+ *
+ * Example to provide a better feel.
+ *
+ *   struct sample {
+ *       int a;
+ *       struct {
+ *           int b[10];
+ *       };
+ *   };
+ *
+ *   struct sample *s = ...;
+ *   int x = &s->a;     // encoded as "0:0" (a is field #0)
+ *   int y = &s->b[5];  // encoded as "0:1:0:5" (anon struct is field #1, 
+ *                      // b is field #0 inside anon struct, accessing elem #5)
+ *   int z = &s[10]->b; // encoded as "10:1" (ptr is used as an array)
+ *
+ * type_id for all relocs in this example  will capture BTF type id of
+ * `struct sample`.
+ *
+ * Such relocation is emitted when using __builtin_preserve_access_index()
+ * Clang built-in, passing expression that captures field address, e.g.:
+ *
+ * bpf_probe_read(&dst, sizeof(dst),
+ *		  __builtin_preserve_access_index(&src->a.b.c));
+ *
+ * In this case Clang will emit offset relocation recording necessary data to
+ * be able to find offset of embedded `a.b.c` field within `src` struct.
+ *
+ *   [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction
+ */
+struct bpf_offset_reloc {
+	__u32   insn_off;
+	__u32   type_id;
+	__u32   access_str_off;
+};
+
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index ace1a0708d99..4b0b0364f5fc 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -244,6 +244,7 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
 	case BPF_MAP_TYPE_HASH_OF_MAPS:
 	case BPF_MAP_TYPE_DEVMAP:
+	case BPF_MAP_TYPE_DEVMAP_HASH:
 	case BPF_MAP_TYPE_SOCKMAP:
 	case BPF_MAP_TYPE_CPUMAP:
 	case BPF_MAP_TYPE_XSKMAP: