Merge remote-tracking branch 'torvalds/master' into perf/core

To pick up fixes and check what UAPI headers need to be synched.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

11 files changed, 1197 insertions, 554 deletions

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index d27e34133973..bba48ff4c5c0 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -67,11 +67,12 @@ static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
 
 static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size)
 {
+	int retries = 5;
 	int fd;
 
 	do {
 		fd = sys_bpf(BPF_PROG_LOAD, attr, size);
-	} while (fd < 0 && errno == EAGAIN);
+	} while (fd < 0 && errno == EAGAIN && retries-- > 0);
 
 	return fd;
 }
@@ -214,59 +215,55 @@ alloc_zero_tailing_info(const void *orecord, __u32 cnt,
 	return info;
 }
 
-int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
-			   char *log_buf, size_t log_buf_sz)
+int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr)
 {
 	void *finfo = NULL, *linfo = NULL;
 	union bpf_attr attr;
-	__u32 log_level;
 	int fd;
 
-	if (!load_attr || !log_buf != !log_buf_sz)
+	if (!load_attr->log_buf != !load_attr->log_buf_sz)
 		return -EINVAL;
 
-	log_level = load_attr->log_level;
-	if (log_level > (4 | 2 | 1) || (log_level && !log_buf))
+	if (load_attr->log_level > (4 | 2 | 1) || (load_attr->log_level && !load_attr->log_buf))
 		return -EINVAL;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = load_attr->prog_type;
 	attr.expected_attach_type = load_attr->expected_attach_type;
-	if (attr.prog_type == BPF_PROG_TYPE_STRUCT_OPS ||
-	    attr.prog_type == BPF_PROG_TYPE_LSM) {
-		attr.attach_btf_id = load_attr->attach_btf_id;
-	} else if (attr.prog_type == BPF_PROG_TYPE_TRACING ||
-		   attr.prog_type == BPF_PROG_TYPE_EXT) {
-		attr.attach_btf_id = load_attr->attach_btf_id;
+
+	if (load_attr->attach_prog_fd)
 		attr.attach_prog_fd = load_attr->attach_prog_fd;
-	} else {
-		attr.prog_ifindex = load_attr->prog_ifindex;
-		attr.kern_version = load_attr->kern_version;
-	}
-	attr.insn_cnt = (__u32)load_attr->insns_cnt;
+	else
+		attr.attach_btf_obj_fd = load_attr->attach_btf_obj_fd;
+	attr.attach_btf_id = load_attr->attach_btf_id;
+
+	attr.prog_ifindex = load_attr->prog_ifindex;
+	attr.kern_version = load_attr->kern_version;
+
+	attr.insn_cnt = (__u32)load_attr->insn_cnt;
 	attr.insns = ptr_to_u64(load_attr->insns);
 	attr.license = ptr_to_u64(load_attr->license);
 
-	attr.log_level = log_level;
-	if (log_level) {
-		attr.log_buf = ptr_to_u64(log_buf);
-		attr.log_size = log_buf_sz;
-	} else {
-		attr.log_buf = ptr_to_u64(NULL);
-		attr.log_size = 0;
+	attr.log_level = load_attr->log_level;
+	if (attr.log_level) {
+		attr.log_buf = ptr_to_u64(load_attr->log_buf);
+		attr.log_size = load_attr->log_buf_sz;
 	}
 
 	attr.prog_btf_fd = load_attr->prog_btf_fd;
+	attr.prog_flags = load_attr->prog_flags;
+
 	attr.func_info_rec_size = load_attr->func_info_rec_size;
 	attr.func_info_cnt = load_attr->func_info_cnt;
 	attr.func_info = ptr_to_u64(load_attr->func_info);
+
 	attr.line_info_rec_size = load_attr->line_info_rec_size;
 	attr.line_info_cnt = load_attr->line_info_cnt;
 	attr.line_info = ptr_to_u64(load_attr->line_info);
+
 	if (load_attr->name)
 		memcpy(attr.prog_name, load_attr->name,
-		       min(strlen(load_attr->name), BPF_OBJ_NAME_LEN - 1));
-	attr.prog_flags = load_attr->prog_flags;
+		       min(strlen(load_attr->name), (size_t)BPF_OBJ_NAME_LEN - 1));
 
 	fd = sys_bpf_prog_load(&attr, sizeof(attr));
 	if (fd >= 0)
@@ -306,19 +303,19 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 		}
 
 		fd = sys_bpf_prog_load(&attr, sizeof(attr));
-
 		if (fd >= 0)
 			goto done;
 	}
 
-	if (log_level || !log_buf)
+	if (load_attr->log_level || !load_attr->log_buf)
 		goto done;
 
 	/* Try again with log */
-	attr.log_buf = ptr_to_u64(log_buf);
-	attr.log_size = log_buf_sz;
+	attr.log_buf = ptr_to_u64(load_attr->log_buf);
+	attr.log_size = load_attr->log_buf_sz;
 	attr.log_level = 1;
-	log_buf[0] = 0;
+	load_attr->log_buf[0] = 0;
+
 	fd = sys_bpf_prog_load(&attr, sizeof(attr));
 done:
 	free(finfo);
@@ -326,6 +323,49 @@ done:
 	return fd;
 }
 
+int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
+			   char *log_buf, size_t log_buf_sz)
+{
+	struct bpf_prog_load_params p = {};
+
+	if (!load_attr || !log_buf != !log_buf_sz)
+		return -EINVAL;
+
+	p.prog_type = load_attr->prog_type;
+	p.expected_attach_type = load_attr->expected_attach_type;
+	switch (p.prog_type) {
+	case BPF_PROG_TYPE_STRUCT_OPS:
+	case BPF_PROG_TYPE_LSM:
+		p.attach_btf_id = load_attr->attach_btf_id;
+		break;
+	case BPF_PROG_TYPE_TRACING:
+	case BPF_PROG_TYPE_EXT:
+		p.attach_btf_id = load_attr->attach_btf_id;
+		p.attach_prog_fd = load_attr->attach_prog_fd;
+		break;
+	default:
+		p.prog_ifindex = load_attr->prog_ifindex;
+		p.kern_version = load_attr->kern_version;
+	}
+	p.insn_cnt = load_attr->insns_cnt;
+	p.insns = load_attr->insns;
+	p.license = load_attr->license;
+	p.log_level = load_attr->log_level;
+	p.log_buf = log_buf;
+	p.log_buf_sz = log_buf_sz;
+	p.prog_btf_fd = load_attr->prog_btf_fd;
+	p.func_info_rec_size = load_attr->func_info_rec_size;
+	p.func_info_cnt = load_attr->func_info_cnt;
+	p.func_info = load_attr->func_info;
+	p.line_info_rec_size = load_attr->line_info_rec_size;
+	p.line_info_cnt = load_attr->line_info_cnt;
+	p.line_info = load_attr->line_info;
+	p.name = load_attr->name;
+	p.prog_flags = load_attr->prog_flags;
+
+	return libbpf__bpf_prog_load(&p);
+}
+
 int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 		     size_t insns_cnt, const char *license,
 		     __u32 kern_version, char *log_buf,
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 231b07203e3d..3c3f2bc6c652 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -78,10 +78,32 @@ struct btf {
 	void *types_data;
 	size_t types_data_cap; /* used size stored in hdr->type_len */
 
-	/* type ID to `struct btf_type *` lookup index */
+	/* type ID to `struct btf_type *` lookup index
+	 * type_offs[0] corresponds to the first non-VOID type:
+	 *   - for base BTF it's type [1];
+	 *   - for split BTF it's the first non-base BTF type.
+	 */
 	__u32 *type_offs;
 	size_t type_offs_cap;
+	/* number of types in this BTF instance:
+	 *   - doesn't include special [0] void type;
+	 *   - for split BTF counts number of types added on top of base BTF.
+	 */
 	__u32 nr_types;
+	/* if not NULL, points to the base BTF on top of which the current
+	 * split BTF is based
+	 */
+	struct btf *base_btf;
+	/* BTF type ID of the first type in this BTF instance:
+	 *   - for base BTF it's equal to 1;
+	 *   - for split BTF it's equal to biggest type ID of base BTF plus 1.
+	 */
+	int start_id;
+	/* logical string offset of this BTF instance:
+	 *   - for base BTF it's equal to 0;
+	 *   - for split BTF it's equal to total size of base BTF's string section size.
+	 */
+	int start_str_off;
 
 	void *strs_data;
 	size_t strs_data_cap; /* used size stored in hdr->str_len */
@@ -90,6 +112,14 @@ struct btf {
 	struct hashmap *strs_hash;
 	/* whether strings are already deduplicated */
 	bool strs_deduped;
+	/* extra indirection layer to make strings hashmap work with stable
+	 * string offsets and ability to transparently choose between
+	 * btf->strs_data or btf_dedup->strs_data as a source of strings.
+	 * This is used for BTF strings dedup to transfer deduplicated strings
+	 * data back to struct btf without re-building strings index.
+	 */
+	void **strs_data_ptr;
+
 	/* BTF object FD, if loaded into kernel */
 	int fd;
 
@@ -168,7 +198,7 @@ static int btf_add_type_idx_entry(struct btf *btf, __u32 type_off)
 	__u32 *p;
 
 	p = btf_add_mem((void **)&btf->type_offs, &btf->type_offs_cap, sizeof(__u32),
-			btf->nr_types + 1, BTF_MAX_NR_TYPES, 1);
+			btf->nr_types, BTF_MAX_NR_TYPES, 1);
 	if (!p)
 		return -ENOMEM;
 
@@ -215,22 +245,18 @@ static int btf_parse_hdr(struct btf *btf)
 		return -EINVAL;
 	}
 
-	if (meta_left < hdr->type_off) {
-		pr_debug("Invalid BTF type section offset:%u\n", hdr->type_off);
+	if (meta_left < hdr->str_off + hdr->str_len) {
+		pr_debug("Invalid BTF total size:%u\n", btf->raw_size);
 		return -EINVAL;
 	}
 
-	if (meta_left < hdr->str_off) {
-		pr_debug("Invalid BTF string section offset:%u\n", hdr->str_off);
+	if (hdr->type_off + hdr->type_len > hdr->str_off) {
+		pr_debug("Invalid BTF data sections layout: type data at %u + %u, strings data at %u + %u\n",
+			 hdr->type_off, hdr->type_len, hdr->str_off, hdr->str_len);
 		return -EINVAL;
 	}
 
-	if (hdr->type_off >= hdr->str_off) {
-		pr_debug("BTF type section offset >= string section offset. No type?\n");
-		return -EINVAL;
-	}
-
-	if (hdr->type_off & 0x02) {
+	if (hdr->type_off % 4) {
 		pr_debug("BTF type section is not aligned to 4 bytes\n");
 		return -EINVAL;
 	}
@@ -244,12 +270,16 @@ static int btf_parse_str_sec(struct btf *btf)
 	const char *start = btf->strs_data;
 	const char *end = start + btf->hdr->str_len;
 
-	if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_STR_OFFSET ||
-	    start[0] || end[-1]) {
+	if (btf->base_btf && hdr->str_len == 0)
+		return 0;
+	if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_STR_OFFSET || end[-1]) {
+		pr_debug("Invalid BTF string section\n");
+		return -EINVAL;
+	}
+	if (!btf->base_btf && start[0]) {
 		pr_debug("Invalid BTF string section\n");
 		return -EINVAL;
 	}
-
 	return 0;
 }
 
@@ -364,19 +394,9 @@ static int btf_parse_type_sec(struct btf *btf)
 	struct btf_header *hdr = btf->hdr;
 	void *next_type = btf->types_data;
 	void *end_type = next_type + hdr->type_len;
-	int err, i = 0, type_size;
-
-	/* VOID (type_id == 0) is specially handled by btf__get_type_by_id(),
-	 * so ensure we can never properly use its offset from index by
-	 * setting it to a large value
-	 */
-	err = btf_add_type_idx_entry(btf, UINT_MAX);
-	if (err)
-		return err;
+	int err, type_size;
 
 	while (next_type + sizeof(struct btf_type) <= end_type) {
-		i++;
-
 		if (btf->swapped_endian)
 			btf_bswap_type_base(next_type);
 
@@ -384,7 +404,7 @@ static int btf_parse_type_sec(struct btf *btf)
 		if (type_size < 0)
 			return type_size;
 		if (next_type + type_size > end_type) {
-			pr_warn("BTF type [%d] is malformed\n", i);
+			pr_warn("BTF type [%d] is malformed\n", btf->start_id + btf->nr_types);
 			return -EINVAL;
 		}
 
@@ -409,7 +429,12 @@ static int btf_parse_type_sec(struct btf *btf)
 
 __u32 btf__get_nr_types(const struct btf *btf)
 {
-	return btf->nr_types;
+	return btf->start_id + btf->nr_types - 1;
+}
+
+const struct btf *btf__base_btf(const struct btf *btf)
+{
+	return btf->base_btf;
 }
 
 /* internal helper returning non-const pointer to a type */
@@ -417,13 +442,14 @@ static struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id)
 {
 	if (type_id == 0)
 		return &btf_void;
-
-	return btf->types_data + btf->type_offs[type_id];
+	if (type_id < btf->start_id)
+		return btf_type_by_id(btf->base_btf, type_id);
+	return btf->types_data + btf->type_offs[type_id - btf->start_id];
 }
 
 const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id)
 {
-	if (type_id > btf->nr_types)
+	if (type_id >= btf->start_id + btf->nr_types)
 		return NULL;
 	return btf_type_by_id((struct btf *)btf, type_id);
 }
@@ -432,9 +458,13 @@ static int determine_ptr_size(const struct btf *btf)
 {
 	const struct btf_type *t;
 	const char *name;
-	int i;
+	int i, n;
 
-	for (i = 1; i <= btf->nr_types; i++) {
+	if (btf->base_btf && btf->base_btf->ptr_sz > 0)
+		return btf->base_btf->ptr_sz;
+
+	n = btf__get_nr_types(btf);
+	for (i = 1; i <= n; i++) {
 		t = btf__type_by_id(btf, i);
 		if (!btf_is_int(t))
 			continue;
@@ -649,12 +679,12 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id)
 
 __s32 btf__find_by_name(const struct btf *btf, const char *type_name)
 {
-	__u32 i;
+	__u32 i, nr_types = btf__get_nr_types(btf);
 
 	if (!strcmp(type_name, "void"))
 		return 0;
 
-	for (i = 1; i <= btf->nr_types; i++) {
+	for (i = 1; i <= nr_types; i++) {
 		const struct btf_type *t = btf__type_by_id(btf, i);
 		const char *name = btf__name_by_offset(btf, t->name_off);
 
@@ -668,12 +698,12 @@ __s32 btf__find_by_name(const struct btf *btf, const char *type_name)
 __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
 			     __u32 kind)
 {
-	__u32 i;
+	__u32 i, nr_types = btf__get_nr_types(btf);
 
 	if (kind == BTF_KIND_UNKN || !strcmp(type_name, "void"))
 		return 0;
 
-	for (i = 1; i <= btf->nr_types; i++) {
+	for (i = 1; i <= nr_types; i++) {
 		const struct btf_type *t = btf__type_by_id(btf, i);
 		const char *name;
 
@@ -717,7 +747,7 @@ void btf__free(struct btf *btf)
 	free(btf);
 }
 
-struct btf *btf__new_empty(void)
+static struct btf *btf_new_empty(struct btf *base_btf)
 {
 	struct btf *btf;
 
@@ -725,12 +755,21 @@ struct btf *btf__new_empty(void)
 	if (!btf)
 		return ERR_PTR(-ENOMEM);
 
+	btf->nr_types = 0;
+	btf->start_id = 1;
+	btf->start_str_off = 0;
 	btf->fd = -1;
 	btf->ptr_sz = sizeof(void *);
 	btf->swapped_endian = false;
 
+	if (base_btf) {
+		btf->base_btf = base_btf;
+		btf->start_id = btf__get_nr_types(base_btf) + 1;
+		btf->start_str_off = base_btf->hdr->str_len;
+	}
+
 	/* +1 for empty string at offset 0 */
-	btf->raw_size = sizeof(struct btf_header) + 1;
+	btf->raw_size = sizeof(struct btf_header) + (base_btf ? 0 : 1);
 	btf->raw_data = calloc(1, btf->raw_size);
 	if (!btf->raw_data) {
 		free(btf);
@@ -744,12 +783,22 @@ struct btf *btf__new_empty(void)
 
 	btf->types_data = btf->raw_data + btf->hdr->hdr_len;
 	btf->strs_data = btf->raw_data + btf->hdr->hdr_len;
-	btf->hdr->str_len = 1; /* empty string at offset 0 */
+	btf->hdr->str_len = base_btf ? 0 : 1; /* empty string at offset 0 */
 
 	return btf;
 }
 
-struct btf *btf__new(const void *data, __u32 size)
+struct btf *btf__new_empty(void)
+{
+	return btf_new_empty(NULL);
+}
+
+struct btf *btf__new_empty_split(struct btf *base_btf)
+{
+	return btf_new_empty(base_btf);
+}
+
+static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf)
 {
 	struct btf *btf;
 	int err;
@@ -758,6 +807,16 @@ struct btf *btf__new(const void *data, __u32 size)
 	if (!btf)
 		return ERR_PTR(-ENOMEM);
 
+	btf->nr_types = 0;
+	btf->start_id = 1;
+	btf->start_str_off = 0;
+
+	if (base_btf) {
+		btf->base_btf = base_btf;
+		btf->start_id = btf__get_nr_types(base_btf) + 1;
+		btf->start_str_off = base_btf->hdr->str_len;
+	}
+
 	btf->raw_data = malloc(size);
 	if (!btf->raw_data) {
 		err = -ENOMEM;
@@ -790,7 +849,13 @@ done:
 	return btf;
 }
 
-struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext)
+struct btf *btf__new(const void *data, __u32 size)
+{
+	return btf_new(data, size, NULL);
+}
+
+static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
+				 struct btf_ext **btf_ext)
 {
 	Elf_Data *btf_data = NULL, *btf_ext_data = NULL;
 	int err = 0, fd = -1, idx = 0;
@@ -868,7 +933,7 @@ struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext)
 		err = -ENOENT;
 		goto done;
 	}
-	btf = btf__new(btf_data->d_buf, btf_data->d_size);
+	btf = btf_new(btf_data->d_buf, btf_data->d_size, base_btf);
 	if (IS_ERR(btf))
 		goto done;
 
@@ -913,7 +978,17 @@ done:
 	return btf;
 }
 
-struct btf *btf__parse_raw(const char *path)
+struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext)
+{
+	return btf_parse_elf(path, NULL, btf_ext);
+}
+
+struct btf *btf__parse_elf_split(const char *path, struct btf *base_btf)
+{
+	return btf_parse_elf(path, base_btf, NULL);
+}
+
+static struct btf *btf_parse_raw(const char *path, struct btf *base_btf)
 {
 	struct btf *btf = NULL;
 	void *data = NULL;
@@ -967,7 +1042,7 @@ struct btf *btf__parse_raw(const char *path)
 	}
 
 	/* finally parse BTF data */
-	btf = btf__new(data, sz);
+	btf = btf_new(data, sz, base_btf);
 
 err_out:
 	free(data);
@@ -976,18 +1051,38 @@ err_out:
 	return err ? ERR_PTR(err) : btf;
 }
 
-struct btf *btf__parse(const char *path, struct btf_ext **btf_ext)
+struct btf *btf__parse_raw(const char *path)
+{
+	return btf_parse_raw(path, NULL);
+}
+
+struct btf *btf__parse_raw_split(const char *path, struct btf *base_btf)
+{
+	return btf_parse_raw(path, base_btf);
+}
+
+static struct btf *btf_parse(const char *path, struct btf *base_btf, struct btf_ext **btf_ext)
 {
 	struct btf *btf;
 
 	if (btf_ext)
 		*btf_ext = NULL;
 
-	btf = btf__parse_raw(path);
+	btf = btf_parse_raw(path, base_btf);
 	if (!IS_ERR(btf) || PTR_ERR(btf) != -EPROTO)
 		return btf;
 
-	return btf__parse_elf(path, btf_ext);
+	return btf_parse_elf(path, base_btf, btf_ext);
+}
+
+struct btf *btf__parse(const char *path, struct btf_ext **btf_ext)
+{
+	return btf_parse(path, NULL, btf_ext);
+}
+
+struct btf *btf__parse_split(const char *path, struct btf *base_btf)
+{
+	return btf_parse(path, base_btf, NULL);
 }
 
 static int compare_vsi_off(const void *_a, const void *_b)
@@ -1171,8 +1266,8 @@ static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endi
 
 	memcpy(p, btf->types_data, hdr->type_len);
 	if (swap_endian) {
-		for (i = 1; i <= btf->nr_types; i++) {
-			t = p  + btf->type_offs[i];
+		for (i = 0; i < btf->nr_types; i++) {
+			t = p + btf->type_offs[i];
 			/* btf_bswap_type_rest() relies on native t->info, so
 			 * we swap base type info after we swapped all the
 			 * additional information
@@ -1215,8 +1310,10 @@ const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size)
 
 const char *btf__str_by_offset(const struct btf *btf, __u32 offset)
 {
-	if (offset < btf->hdr->str_len)
-		return btf->strs_data + offset;
+	if (offset < btf->start_str_off)
+		return btf__str_by_offset(btf->base_btf, offset);
+	else if (offset - btf->start_str_off < btf->hdr->str_len)
+		return btf->strs_data + (offset - btf->start_str_off);
 	else
 		return NULL;
 }
@@ -1226,35 +1323,27 @@ const char *btf__name_by_offset(const struct btf *btf, __u32 offset)
 	return btf__str_by_offset(btf, offset);
 }
 
-int btf__get_from_id(__u32 id, struct btf **btf)
+struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf)
 {
-	struct bpf_btf_info btf_info = { 0 };
+	struct bpf_btf_info btf_info;
 	__u32 len = sizeof(btf_info);
 	__u32 last_size;
-	int btf_fd;
+	struct btf *btf;
 	void *ptr;
 	int err;
 
-	err = 0;
-	*btf = NULL;
-	btf_fd = bpf_btf_get_fd_by_id(id);
-	if (btf_fd < 0)
-		return 0;
-
 	/* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so
 	 * let's start with a sane default - 4KiB here - and resize it only if
 	 * bpf_obj_get_info_by_fd() needs a bigger buffer.
 	 */
-	btf_info.btf_size = 4096;
-	last_size = btf_info.btf_size;
+	last_size = 4096;
 	ptr = malloc(last_size);
-	if (!ptr) {
-		err = -ENOMEM;
-		goto exit_free;
-	}
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
 
-	memset(ptr, 0, last_size);
+	memset(&btf_info, 0, sizeof(btf_info));
 	btf_info.btf = ptr_to_u64(ptr);
+	btf_info.btf_size = last_size;
 	err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
 
 	if (!err && btf_info.btf_size > last_size) {
@@ -1263,31 +1352,48 @@ int btf__get_from_id(__u32 id, struct btf **btf)
 		last_size = btf_info.btf_size;
 		temp_ptr = realloc(ptr, last_size);
 		if (!temp_ptr) {
-			err = -ENOMEM;
+			btf = ERR_PTR(-ENOMEM);
 			goto exit_free;
 		}
 		ptr = temp_ptr;
-		memset(ptr, 0, last_size);
+
+		len = sizeof(btf_info);
+		memset(&btf_info, 0, sizeof(btf_info));
 		btf_info.btf = ptr_to_u64(ptr);
+		btf_info.btf_size = last_size;
+
 		err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
 	}
 
 	if (err || btf_info.btf_size > last_size) {
-		err = errno;
+		btf = err ? ERR_PTR(-errno) : ERR_PTR(-E2BIG);
 		goto exit_free;
 	}
 
-	*btf = btf__new((__u8 *)(long)btf_info.btf, btf_info.btf_size);
-	if (IS_ERR(*btf)) {
-		err = PTR_ERR(*btf);
-		*btf = NULL;
-	}
+	btf = btf_new(ptr, btf_info.btf_size, base_btf);
 
 exit_free:
-	close(btf_fd);
 	free(ptr);
+	return btf;
+}
 
-	return err;
+int btf__get_from_id(__u32 id, struct btf **btf)
+{
+	struct btf *res;
+	int btf_fd;
+
+	*btf = NULL;
+	btf_fd = bpf_btf_get_fd_by_id(id);
+	if (btf_fd < 0)
+		return -errno;
+
+	res = btf_get_from_fd(btf_fd, NULL);
+	close(btf_fd);
+	if (IS_ERR(res))
+		return PTR_ERR(res);
+
+	*btf = res;
+	return 0;
 }
 
 int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
@@ -1363,17 +1469,19 @@ int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
 
 static size_t strs_hash_fn(const void *key, void *ctx)
 {
-	struct btf *btf = ctx;
-	const char *str = btf->strs_data + (long)key;
+	const struct btf *btf = ctx;
+	const char *strs = *btf->strs_data_ptr;
+	const char *str = strs + (long)key;
 
 	return str_hash(str);
 }
 
 static bool strs_hash_equal_fn(const void *key1, const void *key2, void *ctx)
 {
-	struct btf *btf = ctx;
-	const char *str1 = btf->strs_data + (long)key1;
-	const char *str2 = btf->strs_data + (long)key2;
+	const struct btf *btf = ctx;
+	const char *strs = *btf->strs_data_ptr;
+	const char *str1 = strs + (long)key1;
+	const char *str2 = strs + (long)key2;
 
 	return strcmp(str1, str2) == 0;
 }
@@ -1418,6 +1526,9 @@ static int btf_ensure_modifiable(struct btf *btf)
 	memcpy(types, btf->types_data, btf->hdr->type_len);
 	memcpy(strs, btf->strs_data, btf->hdr->str_len);
 
+	/* make hashmap below use btf->strs_data as a source of strings */
+	btf->strs_data_ptr = &btf->strs_data;
+
 	/* build lookup index for all strings */
 	hash = hashmap__new(strs_hash_fn, strs_hash_equal_fn, btf);
 	if (IS_ERR(hash)) {
@@ -1448,7 +1559,10 @@ static int btf_ensure_modifiable(struct btf *btf)
 	/* if BTF was created from scratch, all strings are guaranteed to be
 	 * unique and deduplicated
 	 */
-	btf->strs_deduped = btf->hdr->str_len <= 1;
+	if (btf->hdr->str_len == 0)
+		btf->strs_deduped = true;
+	if (!btf->base_btf && btf->hdr->str_len == 1)
+		btf->strs_deduped = true;
 
 	/* invalidate raw_data representation */
 	btf_invalidate_raw_data(btf);
@@ -1480,6 +1594,14 @@ int btf__find_str(struct btf *btf, const char *s)
 	long old_off, new_off, len;
 	void *p;
 
+	if (btf->base_btf) {
+		int ret;
+
+		ret = btf__find_str(btf->base_btf, s);
+		if (ret != -ENOENT)
+			return ret;
+	}
+
 	/* BTF needs to be in a modifiable state to build string lookup index */
 	if (btf_ensure_modifiable(btf))
 		return -ENOMEM;
@@ -1494,7 +1616,7 @@ int btf__find_str(struct btf *btf, const char *s)
 	memcpy(p, s, len);
 
 	if (hashmap__find(btf->strs_hash, (void *)new_off, (void **)&old_off))
-		return old_off;
+		return btf->start_str_off + old_off;
 
 	return -ENOENT;
 }
@@ -1510,6 +1632,14 @@ int btf__add_str(struct btf *btf, const char *s)
 	void *p;
 	int err;
 
+	if (btf->base_btf) {
+		int ret;
+
+		ret = btf__find_str(btf->base_btf, s);
+		if (ret != -ENOENT)
+			return ret;
+	}
+
 	if (btf_ensure_modifiable(btf))
 		return -ENOMEM;
 
@@ -1536,12 +1666,12 @@ int btf__add_str(struct btf *btf, const char *s)
 	err = hashmap__insert(btf->strs_hash, (void *)new_off, (void *)new_off,
 			      HASHMAP_ADD, (const void **)&old_off, NULL);
 	if (err == -EEXIST)
-		return old_off; /* duplicated string, return existing offset */
+		return btf->start_str_off + old_off; /* duplicated string, return existing offset */
 	if (err)
 		return err;
 
 	btf->hdr->str_len += len; /* new unique string, adjust data length */
-	return new_off;
+	return btf->start_str_off + new_off;
 }
 
 static void *btf_add_type_mem(struct btf *btf, size_t add_sz)
@@ -1560,6 +1690,20 @@ static void btf_type_inc_vlen(struct btf_type *t)
 	t->info = btf_type_info(btf_kind(t), btf_vlen(t) + 1, btf_kflag(t));
 }
 
+static int btf_commit_type(struct btf *btf, int data_sz)
+{
+	int err;
+
+	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
+	if (err)
+		return err;
+
+	btf->hdr->type_len += data_sz;
+	btf->hdr->str_off += data_sz;
+	btf->nr_types++;
+	return btf->start_id + btf->nr_types - 1;
+}
+
 /*
  * Append new BTF_KIND_INT type with:
  *   - *name* - non-empty, non-NULL type name;
@@ -1572,7 +1716,7 @@ static void btf_type_inc_vlen(struct btf_type *t)
 int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding)
 {
 	struct btf_type *t;
-	int sz, err, name_off;
+	int sz, name_off;
 
 	/* non-empty name */
 	if (!name || !name[0])
@@ -1606,14 +1750,7 @@ int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding
 	/* set INT info, we don't allow setting legacy bit offset/size */
 	*(__u32 *)(t + 1) = (encoding << 24) | (byte_sz * 8);
 
-	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
-	if (err)
-		return err;
-
-	btf->hdr->type_len += sz;
-	btf->hdr->str_off += sz;
-	btf->nr_types++;
-	return btf->nr_types;
+	return btf_commit_type(btf, sz);
 }
 
 /* it's completely legal to append BTF types with type IDs pointing forward to
@@ -1631,7 +1768,7 @@ static int validate_type_id(int id)
 static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref_type_id)
 {
 	struct btf_type *t;
-	int sz, name_off = 0, err;
+	int sz, name_off = 0;
 
 	if (validate_type_id(ref_type_id))
 		return -EINVAL;
@@ -1654,14 +1791,7 @@ static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref
 	t->info = btf_type_info(kind, 0, 0);
 	t->type = ref_type_id;
 
-	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
-	if (err)
-		return err;
-
-	btf->hdr->type_len += sz;
-	btf->hdr->str_off += sz;
-	btf->nr_types++;
-	return btf->nr_types;
+	return btf_commit_type(btf, sz);
 }
 
 /*
@@ -1689,7 +1819,7 @@ int btf__add_array(struct btf *btf, int index_type_id, int elem_type_id, __u32 n
 {
 	struct btf_type *t;
 	struct btf_array *a;
-	int sz, err;
+	int sz;
 
 	if (validate_type_id(index_type_id) || validate_type_id(elem_type_id))
 		return -EINVAL;
@@ -1711,21 +1841,14 @@ int btf__add_array(struct btf *btf, int index_type_id, int elem_type_id, __u32 n
 	a->index_type = index_type_id;
 	a->nelems = nr_elems;
 
-	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
-	if (err)
-		return err;
-
-	btf->hdr->type_len += sz;
-	btf->hdr->str_off += sz;
-	btf->nr_types++;
-	return btf->nr_types;
+	return btf_commit_type(btf, sz);
 }
 
 /* generic STRUCT/UNION append function */
 static int btf_add_composite(struct btf *btf, int kind, const char *name, __u32 bytes_sz)
 {
 	struct btf_type *t;
-	int sz, err, name_off = 0;
+	int sz, name_off = 0;
 
 	if (btf_ensure_modifiable(btf))
 		return -ENOMEM;
@@ -1748,14 +1871,7 @@ static int btf_add_composite(struct btf *btf, int kind, const char *name, __u32
 	t->info = btf_type_info(kind, 0, 0);
 	t->size = bytes_sz;
 
-	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
-	if (err)
-		return err;
-
-	btf->hdr->type_len += sz;
-	btf->hdr->str_off += sz;
-	btf->nr_types++;
-	return btf->nr_types;
+	return btf_commit_type(btf, sz);
 }
 
 /*
@@ -1793,6 +1909,11 @@ int btf__add_union(struct btf *btf, const char *name, __u32 byte_sz)
 	return btf_add_composite(btf, BTF_KIND_UNION, name, byte_sz);
 }
 
+static struct btf_type *btf_last_type(struct btf *btf)
+{
+	return btf_type_by_id(btf, btf__get_nr_types(btf));
+}
+
 /*
  * Append new field for the current STRUCT/UNION type with:
  *   - *name* - name of the field, can be NULL or empty for anonymous field;
@@ -1814,7 +1935,7 @@ int btf__add_field(struct btf *btf, const char *name, int type_id,
 	/* last type should be union/struct */
 	if (btf->nr_types == 0)
 		return -EINVAL;
-	t = btf_type_by_id(btf, btf->nr_types);
+	t = btf_last_type(btf);
 	if (!btf_is_composite(t))
 		return -EINVAL;
 
@@ -1849,7 +1970,7 @@ int btf__add_field(struct btf *btf, const char *name, int type_id,
 	m->offset = bit_offset | (bit_size << 24);
 
 	/* btf_add_type_mem can invalidate t pointer */
-	t = btf_type_by_id(btf, btf->nr_types);
+	t = btf_last_type(btf);
 	/* update parent type's vlen and kflag */
 	t->info = btf_type_info(btf_kind(t), btf_vlen(t) + 1, is_bitfield || btf_kflag(t));
 
@@ -1874,7 +1995,7 @@ int btf__add_field(struct btf *btf, const char *name, int type_id,
 int btf__add_enum(struct btf *btf, const char *name, __u32 byte_sz)
 {
 	struct btf_type *t;
-	int sz, err, name_off = 0;
+	int sz, name_off = 0;
 
 	/* byte_sz must be power of 2 */
 	if (!byte_sz || (byte_sz & (byte_sz - 1)) || byte_sz > 8)
@@ -1899,14 +2020,7 @@ int btf__add_enum(struct btf *btf, const char *name, __u32 byte_sz)
 	t->info = btf_type_info(BTF_KIND_ENUM, 0, 0);
 	t->size = byte_sz;
 
-	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
-	if (err)
-		return err;
-
-	btf->hdr->type_len += sz;
-	btf->hdr->str_off += sz;
-	btf->nr_types++;
-	return btf->nr_types;
+	return btf_commit_type(btf, sz);
 }
 
 /*
@@ -1926,7 +2040,7 @@ int btf__add_enum_value(struct btf *btf, const char *name, __s64 value)
 	/* last type should be BTF_KIND_ENUM */
 	if (btf->nr_types == 0)
 		return -EINVAL;
-	t = btf_type_by_id(btf, btf->nr_types);
+	t = btf_last_type(btf);
 	if (!btf_is_enum(t))
 		return -EINVAL;
 
@@ -1953,7 +2067,7 @@ int btf__add_enum_value(struct btf *btf, const char *name, __s64 value)
 	v->val = value;
 
 	/* update parent type's vlen */
-	t = btf_type_by_id(btf, btf->nr_types);
+	t = btf_last_type(btf);
 	btf_type_inc_vlen(t);
 
 	btf->hdr->type_len += sz;
@@ -2093,7 +2207,7 @@ int btf__add_func(struct btf *btf, const char *name,
 int btf__add_func_proto(struct btf *btf, int ret_type_id)
 {
 	struct btf_type *t;
-	int sz, err;
+	int sz;
 
 	if (validate_type_id(ret_type_id))
 		return -EINVAL;
@@ -2113,14 +2227,7 @@ int btf__add_func_proto(struct btf *btf, int ret_type_id)
 	t->info = btf_type_info(BTF_KIND_FUNC_PROTO, 0, 0);
 	t->type = ret_type_id;
 
-	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
-	if (err)
-		return err;
-
-	btf->hdr->type_len += sz;
-	btf->hdr->str_off += sz;
-	btf->nr_types++;
-	return btf->nr_types;
+	return btf_commit_type(btf, sz);
 }
 
 /*
@@ -2143,7 +2250,7 @@ int btf__add_func_param(struct btf *btf, const char *name, int type_id)
 	/* last type should be BTF_KIND_FUNC_PROTO */
 	if (btf->nr_types == 0)
 		return -EINVAL;
-	t = btf_type_by_id(btf, btf->nr_types);
+	t = btf_last_type(btf);
 	if (!btf_is_func_proto(t))
 		return -EINVAL;
 
@@ -2166,7 +2273,7 @@ int btf__add_func_param(struct btf *btf, const char *name, int type_id)
 	p->type = type_id;
 
 	/* update parent type's vlen */
-	t = btf_type_by_id(btf, btf->nr_types);
+	t = btf_last_type(btf);
 	btf_type_inc_vlen(t);
 
 	btf->hdr->type_len += sz;
@@ -2188,7 +2295,7 @@ int btf__add_var(struct btf *btf, const char *name, int linkage, int type_id)
 {
 	struct btf_type *t;
 	struct btf_var *v;
-	int sz, err, name_off;
+	int sz, name_off;
 
 	/* non-empty name */
 	if (!name || !name[0])
@@ -2219,14 +2326,7 @@ int btf__add_var(struct btf *btf, const char *name, int linkage, int type_id)
 	v = btf_var(t);
 	v->linkage = linkage;
 
-	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
-	if (err)
-		return err;
-
-	btf->hdr->type_len += sz;
-	btf->hdr->str_off += sz;
-	btf->nr_types++;
-	return btf->nr_types;
+	return btf_commit_type(btf, sz);
 }
 
 /*
@@ -2244,7 +2344,7 @@ int btf__add_var(struct btf *btf, const char *name, int linkage, int type_id)
 int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz)
 {
 	struct btf_type *t;
-	int sz, err, name_off;
+	int sz, name_off;
 
 	/* non-empty name */
 	if (!name || !name[0])
@@ -2267,14 +2367,7 @@ int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz)
 	t->info = btf_type_info(BTF_KIND_DATASEC, 0, 0);
 	t->size = byte_sz;
 
-	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
-	if (err)
-		return err;
-
-	btf->hdr->type_len += sz;
-	btf->hdr->str_off += sz;
-	btf->nr_types++;
-	return btf->nr_types;
+	return btf_commit_type(btf, sz);
 }
 
 /*
@@ -2296,7 +2389,7 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __
 	/* last type should be BTF_KIND_DATASEC */
 	if (btf->nr_types == 0)
 		return -EINVAL;
-	t = btf_type_by_id(btf, btf->nr_types);
+	t = btf_last_type(btf);
 	if (!btf_is_datasec(t))
 		return -EINVAL;
 
@@ -2317,7 +2410,7 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __
 	v->size = byte_sz;
 
 	/* update parent type's vlen */
-	t = btf_type_by_id(btf, btf->nr_types);
+	t = btf_last_type(btf);
 	btf_type_inc_vlen(t);
 
 	btf->hdr->type_len += sz;
@@ -2639,6 +2732,7 @@ struct btf_dedup;
 static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
 				       const struct btf_dedup_opts *opts);
 static void btf_dedup_free(struct btf_dedup *d);
+static int btf_dedup_prep(struct btf_dedup *d);
 static int btf_dedup_strings(struct btf_dedup *d);
 static int btf_dedup_prim_types(struct btf_dedup *d);
 static int btf_dedup_struct_types(struct btf_dedup *d);
@@ -2797,6 +2891,11 @@ int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
 	if (btf_ensure_modifiable(btf))
 		return -ENOMEM;
 
+	err = btf_dedup_prep(d);
+	if (err) {
+		pr_debug("btf_dedup_prep failed:%d\n", err);
+		goto done;
+	}
 	err = btf_dedup_strings(d);
 	if (err < 0) {
 		pr_debug("btf_dedup_strings failed:%d\n", err);
@@ -2859,21 +2958,20 @@ struct btf_dedup {
 	__u32 *hypot_list;
 	size_t hypot_cnt;
 	size_t hypot_cap;
+	/* Whether hypothetical mapping, if successful, would need to adjust
+	 * already canonicalized types (due to a new forward declaration to
+	 * concrete type resolution). In such case, during split BTF dedup
+	 * candidate type would still be considered as different, because base
+	 * BTF is considered to be immutable.
+	 */
+	bool hypot_adjust_canon;
 	/* Various option modifying behavior of algorithm */
 	struct btf_dedup_opts opts;
-};
-
-struct btf_str_ptr {
-	const char *str;
-	__u32 new_off;
-	bool used;
-};
-
-struct btf_str_ptrs {
-	struct btf_str_ptr *ptrs;
-	const char *data;
-	__u32 cnt;
-	__u32 cap;
+	/* temporary strings deduplication state */
+	void *strs_data;
+	size_t strs_cap;
+	size_t strs_len;
+	struct hashmap* strs_hash;
 };
 
 static long hash_combine(long h, long value)
@@ -2914,6 +3012,7 @@ static void btf_dedup_clear_hypot_map(struct btf_dedup *d)
 	for (i = 0; i < d->hypot_cnt; i++)
 		d->hypot_map[d->hypot_list[i]] = BTF_UNPROCESSED_ID;
 	d->hypot_cnt = 0;
+	d->hypot_adjust_canon = false;
 }
 
 static void btf_dedup_free(struct btf_dedup *d)
@@ -2953,7 +3052,7 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
 {
 	struct btf_dedup *d = calloc(1, sizeof(struct btf_dedup));
 	hashmap_hash_fn hash_fn = btf_dedup_identity_hash_fn;
-	int i, err = 0;
+	int i, err = 0, type_cnt;
 
 	if (!d)
 		return ERR_PTR(-ENOMEM);
@@ -2973,14 +3072,15 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
 		goto done;
 	}
 
-	d->map = malloc(sizeof(__u32) * (1 + btf->nr_types));
+	type_cnt = btf__get_nr_types(btf) + 1;
+	d->map = malloc(sizeof(__u32) * type_cnt);
 	if (!d->map) {
 		err = -ENOMEM;
 		goto done;
 	}
 	/* special BTF "void" type is made canonical immediately */
 	d->map[0] = 0;
-	for (i = 1; i <= btf->nr_types; i++) {
+	for (i = 1; i < type_cnt; i++) {
 		struct btf_type *t = btf_type_by_id(d->btf, i);
 
 		/* VAR and DATASEC are never deduped and are self-canonical */
@@ -2990,12 +3090,12 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
 			d->map[i] = BTF_UNPROCESSED_ID;
 	}
 
-	d->hypot_map = malloc(sizeof(__u32) * (1 + btf->nr_types));
+	d->hypot_map = malloc(sizeof(__u32) * type_cnt);
 	if (!d->hypot_map) {
 		err = -ENOMEM;
 		goto done;
 	}
-	for (i = 0; i <= btf->nr_types; i++)
+	for (i = 0; i < type_cnt; i++)
 		d->hypot_map[i] = BTF_UNPROCESSED_ID;
 
 done:
@@ -3019,8 +3119,8 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx)
 	int i, j, r, rec_size;
 	struct btf_type *t;
 
-	for (i = 1; i <= d->btf->nr_types; i++) {
-		t = btf_type_by_id(d->btf, i);
+	for (i = 0; i < d->btf->nr_types; i++) {
+		t = btf_type_by_id(d->btf, d->btf->start_id + i);
 		r = fn(&t->name_off, ctx);
 		if (r)
 			return r;
@@ -3100,64 +3200,53 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx)
 	return 0;
 }
 
-static int str_sort_by_content(const void *a1, const void *a2)
+static int strs_dedup_remap_str_off(__u32 *str_off_ptr, void *ctx)
 {
-	const struct btf_str_ptr *p1 = a1;
-	const struct btf_str_ptr *p2 = a2;
-
-	return strcmp(p1->str, p2->str);
-}
-
-static int str_sort_by_offset(const void *a1, const void *a2)
-{
-	const struct btf_str_ptr *p1 = a1;
-	const struct btf_str_ptr *p2 = a2;
-
-	if (p1->str != p2->str)
-		return p1->str < p2->str ? -1 : 1;
-	return 0;
-}
-
-static int btf_dedup_str_ptr_cmp(const void *str_ptr, const void *pelem)
-{
-	const struct btf_str_ptr *p = pelem;
-
-	if (str_ptr != p->str)
-		return (const char *)str_ptr < p->str ? -1 : 1;
-	return 0;
-}
-
-static int btf_str_mark_as_used(__u32 *str_off_ptr, void *ctx)
-{
-	struct btf_str_ptrs *strs;
-	struct btf_str_ptr *s;
+	struct btf_dedup *d = ctx;
+	__u32 str_off = *str_off_ptr;
+	long old_off, new_off, len;
+	const char *s;
+	void *p;
+	int err;
 
-	if (*str_off_ptr == 0)
+	/* don't touch empty string or string in main BTF */
+	if (str_off == 0 || str_off < d->btf->start_str_off)
 		return 0;
 
-	strs = ctx;
-	s = bsearch(strs->data + *str_off_ptr, strs->ptrs, strs->cnt,
-		    sizeof(struct btf_str_ptr), btf_dedup_str_ptr_cmp);
-	if (!s)
-		return -EINVAL;
-	s->used = true;
-	return 0;
-}
+	s = btf__str_by_offset(d->btf, str_off);
+	if (d->btf->base_btf) {
+		err = btf__find_str(d->btf->base_btf, s);
+		if (err >= 0) {
+			*str_off_ptr = err;
+			return 0;
+		}
+		if (err != -ENOENT)
+			return err;
+	}
 
-static int btf_str_remap_offset(__u32 *str_off_ptr, void *ctx)
-{
-	struct btf_str_ptrs *strs;
-	struct btf_str_ptr *s;
+	len = strlen(s) + 1;
 
-	if (*str_off_ptr == 0)
-		return 0;
+	new_off = d->strs_len;
+	p = btf_add_mem(&d->strs_data, &d->strs_cap, 1, new_off, BTF_MAX_STR_OFFSET, len);
+	if (!p)
+		return -ENOMEM;
 
-	strs = ctx;
-	s = bsearch(strs->data + *str_off_ptr, strs->ptrs, strs->cnt,
-		    sizeof(struct btf_str_ptr), btf_dedup_str_ptr_cmp);
-	if (!s)
-		return -EINVAL;
-	*str_off_ptr = s->new_off;
+	memcpy(p, s, len);
+
+	/* Now attempt to add the string, but only if the string with the same
+	 * contents doesn't exist already (HASHMAP_ADD strategy). If such
+	 * string exists, we'll get its offset in old_off (that's old_key).
+	 */
+	err = hashmap__insert(d->strs_hash, (void *)new_off, (void *)new_off,
+			      HASHMAP_ADD, (const void **)&old_off, NULL);
+	if (err == -EEXIST) {
+		*str_off_ptr = d->btf->start_str_off + old_off;
+	} else if (err) {
+		return err;
+	} else {
+		*str_off_ptr = d->btf->start_str_off + new_off;
+		d->strs_len += len;
+	}
 	return 0;
 }
 
@@ -3174,118 +3263,71 @@ static int btf_str_remap_offset(__u32 *str_off_ptr, void *ctx)
  */
 static int btf_dedup_strings(struct btf_dedup *d)
 {
-	char *start = d->btf->strs_data;
-	char *end = start + d->btf->hdr->str_len;
-	char *p = start, *tmp_strs = NULL;
-	struct btf_str_ptrs strs = {
-		.cnt = 0,
-		.cap = 0,
-		.ptrs = NULL,
-		.data = start,
-	};
-	int i, j, err = 0, grp_idx;
-	bool grp_used;
+	char *s;
+	int err;
 
 	if (d->btf->strs_deduped)
 		return 0;
 
-	/* build index of all strings */
-	while (p < end) {
-		if (strs.cnt + 1 > strs.cap) {
-			struct btf_str_ptr *new_ptrs;
-
-			strs.cap += max(strs.cnt / 2, 16U);
-			new_ptrs = libbpf_reallocarray(strs.ptrs, strs.cap, sizeof(strs.ptrs[0]));
-			if (!new_ptrs) {
-				err = -ENOMEM;
-				goto done;
-			}
-			strs.ptrs = new_ptrs;
-		}
-
-		strs.ptrs[strs.cnt].str = p;
-		strs.ptrs[strs.cnt].used = false;
-
-		p += strlen(p) + 1;
-		strs.cnt++;
-	}
+	/* temporarily switch to use btf_dedup's strs_data for strings for hash
+	 * functions; later we'll just transfer hashmap to struct btf as is,
+	 * along the strs_data
+	 */
+	d->btf->strs_data_ptr = &d->strs_data;
 
-	/* temporary storage for deduplicated strings */
-	tmp_strs = malloc(d->btf->hdr->str_len);
-	if (!tmp_strs) {
-		err = -ENOMEM;
-		goto done;
+	d->strs_hash = hashmap__new(strs_hash_fn, strs_hash_equal_fn, d->btf);
+	if (IS_ERR(d->strs_hash)) {
+		err = PTR_ERR(d->strs_hash);
+		d->strs_hash = NULL;
+		goto err_out;
 	}
 
-	/* mark all used strings */
-	strs.ptrs[0].used = true;
-	err = btf_for_each_str_off(d, btf_str_mark_as_used, &strs);
-	if (err)
-		goto done;
-
-	/* sort strings by context, so that we can identify duplicates */
-	qsort(strs.ptrs, strs.cnt, sizeof(strs.ptrs[0]), str_sort_by_content);
-
-	/*
-	 * iterate groups of equal strings and if any instance in a group was
-	 * referenced, emit single instance and remember new offset
-	 */
-	p = tmp_strs;
-	grp_idx = 0;
-	grp_used = strs.ptrs[0].used;
-	/* iterate past end to avoid code duplication after loop */
-	for (i = 1; i <= strs.cnt; i++) {
-		/*
-		 * when i == strs.cnt, we want to skip string comparison and go
-		 * straight to handling last group of strings (otherwise we'd
-		 * need to handle last group after the loop w/ duplicated code)
-		 */
-		if (i < strs.cnt &&
-		    !strcmp(strs.ptrs[i].str, strs.ptrs[grp_idx].str)) {
-			grp_used = grp_used || strs.ptrs[i].used;
-			continue;
-		}
+	if (!d->btf->base_btf) {
+		s = btf_add_mem(&d->strs_data, &d->strs_cap, 1, d->strs_len, BTF_MAX_STR_OFFSET, 1);
+		if (!s)
+			return -ENOMEM;
+		/* initial empty string */
+		s[0] = 0;
+		d->strs_len = 1;
 
-		/*
-		 * this check would have been required after the loop to handle
-		 * last group of strings, but due to <= condition in a loop
-		 * we avoid that duplication
+		/* insert empty string; we won't be looking it up during strings
+		 * dedup, but it's good to have it for generic BTF string lookups
 		 */
-		if (grp_used) {
-			int new_off = p - tmp_strs;
-			__u32 len = strlen(strs.ptrs[grp_idx].str);
-
-			memmove(p, strs.ptrs[grp_idx].str, len + 1);
-			for (j = grp_idx; j < i; j++)
-				strs.ptrs[j].new_off = new_off;
-			p += len + 1;
-		}
-
-		if (i < strs.cnt) {
-			grp_idx = i;
-			grp_used = strs.ptrs[i].used;
-		}
+		err = hashmap__insert(d->strs_hash, (void *)0, (void *)0,
+				      HASHMAP_ADD, NULL, NULL);
+		if (err)
+			goto err_out;
 	}
 
-	/* replace original strings with deduped ones */
-	d->btf->hdr->str_len = p - tmp_strs;
-	memmove(start, tmp_strs, d->btf->hdr->str_len);
-	end = start + d->btf->hdr->str_len;
-
-	/* restore original order for further binary search lookups */
-	qsort(strs.ptrs, strs.cnt, sizeof(strs.ptrs[0]), str_sort_by_offset);
-
 	/* remap string offsets */
-	err = btf_for_each_str_off(d, btf_str_remap_offset, &strs);
+	err = btf_for_each_str_off(d, strs_dedup_remap_str_off, d);
 	if (err)
-		goto done;
+		goto err_out;
 
-	d->btf->hdr->str_len = end - start;
+	/* replace BTF string data and hash with deduped ones */
+	free(d->btf->strs_data);
+	hashmap__free(d->btf->strs_hash);
+	d->btf->strs_data = d->strs_data;
+	d->btf->strs_data_cap = d->strs_cap;
+	d->btf->hdr->str_len = d->strs_len;
+	d->btf->strs_hash = d->strs_hash;
+	/* now point strs_data_ptr back to btf->strs_data */
+	d->btf->strs_data_ptr = &d->btf->strs_data;
+
+	d->strs_data = d->strs_hash = NULL;
+	d->strs_len = d->strs_cap = 0;
 	d->btf->strs_deduped = true;
+	return 0;
+
+err_out:
+	free(d->strs_data);
+	hashmap__free(d->strs_hash);
+	d->strs_data = d->strs_hash = NULL;
+	d->strs_len = d->strs_cap = 0;
+
+	/* restore strings pointer for existing d->btf->strs_hash back */
+	d->btf->strs_data_ptr = &d->strs_data;
 
-done:
-	free(tmp_strs);
-	free(strs.ptrs);
 	return err;
 }
 
@@ -3550,6 +3592,66 @@ static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2)
 	return true;
 }
 
+/* Prepare split BTF for deduplication by calculating hashes of base BTF's
+ * types and initializing the rest of the state (canonical type mapping) for
+ * the fixed base BTF part.
+ */
+static int btf_dedup_prep(struct btf_dedup *d)
+{
+	struct btf_type *t;
+	int type_id;
+	long h;
+
+	if (!d->btf->base_btf)
+		return 0;
+
+	for (type_id = 1; type_id < d->btf->start_id; type_id++) {
+		t = btf_type_by_id(d->btf, type_id);
+
+		/* all base BTF types are self-canonical by definition */
+		d->map[type_id] = type_id;
+
+		switch (btf_kind(t)) {
+		case BTF_KIND_VAR:
+		case BTF_KIND_DATASEC:
+			/* VAR and DATASEC are never hash/deduplicated */
+			continue;
+		case BTF_KIND_CONST:
+		case BTF_KIND_VOLATILE:
+		case BTF_KIND_RESTRICT:
+		case BTF_KIND_PTR:
+		case BTF_KIND_FWD:
+		case BTF_KIND_TYPEDEF:
+		case BTF_KIND_FUNC:
+			h = btf_hash_common(t);
+			break;
+		case BTF_KIND_INT:
+			h = btf_hash_int(t);
+			break;
+		case BTF_KIND_ENUM:
+			h = btf_hash_enum(t);
+			break;
+		case BTF_KIND_STRUCT:
+		case BTF_KIND_UNION:
+			h = btf_hash_struct(t);
+			break;
+		case BTF_KIND_ARRAY:
+			h = btf_hash_array(t);
+			break;
+		case BTF_KIND_FUNC_PROTO:
+			h = btf_hash_fnproto(t);
+			break;
+		default:
+			pr_debug("unknown kind %d for type [%d]\n", btf_kind(t), type_id);
+			return -EINVAL;
+		}
+		if (btf_dedup_table_add(d, h, type_id))
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
 /*
  * Deduplicate primitive types, that can't reference other types, by calculating
  * their type signature hash and comparing them with any possible canonical
@@ -3643,8 +3745,8 @@ static int btf_dedup_prim_types(struct btf_dedup *d)
 {
 	int i, err;
 
-	for (i = 1; i <= d->btf->nr_types; i++) {
-		err = btf_dedup_prim_type(d, i);
+	for (i = 0; i < d->btf->nr_types; i++) {
+		err = btf_dedup_prim_type(d, d->btf->start_id + i);
 		if (err)
 			return err;
 	}
@@ -3697,6 +3799,19 @@ static inline __u16 btf_fwd_kind(struct btf_type *t)
 	return btf_kflag(t) ? BTF_KIND_UNION : BTF_KIND_STRUCT;
 }
 
+/* Check if given two types are identical ARRAY definitions */
+static int btf_dedup_identical_arrays(struct btf_dedup *d, __u32 id1, __u32 id2)
+{
+	struct btf_type *t1, *t2;
+
+	t1 = btf_type_by_id(d->btf, id1);
+	t2 = btf_type_by_id(d->btf, id2);
+	if (!btf_is_array(t1) || !btf_is_array(t2))
+		return 0;
+
+	return btf_equal_array(t1, t2);
+}
+
 /*
  * Check equivalence of BTF type graph formed by candidate struct/union (we'll
  * call it "candidate graph" in this description for brevity) to a type graph
@@ -3807,8 +3922,18 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 	canon_id = resolve_fwd_id(d, canon_id);
 
 	hypot_type_id = d->hypot_map[canon_id];
-	if (hypot_type_id <= BTF_MAX_NR_TYPES)
-		return hypot_type_id == cand_id;
+	if (hypot_type_id <= BTF_MAX_NR_TYPES) {
+		/* In some cases compiler will generate different DWARF types
+		 * for *identical* array type definitions and use them for
+		 * different fields within the *same* struct. This breaks type
+		 * equivalence check, which makes an assumption that candidate
+		 * types sub-graph has a consistent and deduped-by-compiler
+		 * types within a single CU. So work around that by explicitly
+		 * allowing identical array types here.
+		 */
+		return hypot_type_id == cand_id ||
+		       btf_dedup_identical_arrays(d, hypot_type_id, cand_id);
+	}
 
 	if (btf_dedup_hypot_map_add(d, canon_id, cand_id))
 		return -ENOMEM;
@@ -3834,6 +3959,9 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 		} else {
 			real_kind = cand_kind;
 			fwd_kind = btf_fwd_kind(canon_type);
+			/* we'd need to resolve base FWD to STRUCT/UNION */
+			if (fwd_kind == real_kind && canon_id < d->btf->start_id)
+				d->hypot_adjust_canon = true;
 		}
 		return fwd_kind == real_kind;
 	}
@@ -3871,8 +3999,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 			return 0;
 		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);
+		eq = btf_dedup_is_equiv(d, cand_arr->index_type, canon_arr->index_type);
 		if (eq <= 0)
 			return eq;
 		return btf_dedup_is_equiv(d, cand_arr->type, canon_arr->type);
@@ -3955,16 +4082,16 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
  */
 static void btf_dedup_merge_hypot_map(struct btf_dedup *d)
 {
-	__u32 cand_type_id, targ_type_id;
+	__u32 canon_type_id, targ_type_id;
 	__u16 t_kind, c_kind;
 	__u32 t_id, c_id;
 	int i;
 
 	for (i = 0; i < d->hypot_cnt; i++) {
-		cand_type_id = d->hypot_list[i];
-		targ_type_id = d->hypot_map[cand_type_id];
+		canon_type_id = d->hypot_list[i];
+		targ_type_id = d->hypot_map[canon_type_id];
 		t_id = resolve_type_id(d, targ_type_id);
-		c_id = resolve_type_id(d, cand_type_id);
+		c_id = resolve_type_id(d, canon_type_id);
 		t_kind = btf_kind(btf__type_by_id(d->btf, t_id));
 		c_kind = btf_kind(btf__type_by_id(d->btf, c_id));
 		/*
@@ -3979,9 +4106,26 @@ static void btf_dedup_merge_hypot_map(struct btf_dedup *d)
 		 * stability is not a requirement for STRUCT/UNION equivalence
 		 * checks, though.
 		 */
+
+		/* if it's the split BTF case, we still need to point base FWD
+		 * to STRUCT/UNION in a split BTF, because FWDs from split BTF
+		 * will be resolved against base FWD. If we don't point base
+		 * canonical FWD to the resolved STRUCT/UNION, then all the
+		 * FWDs in split BTF won't be correctly resolved to a proper
+		 * STRUCT/UNION.
+		 */
 		if (t_kind != BTF_KIND_FWD && c_kind == BTF_KIND_FWD)
 			d->map[c_id] = t_id;
-		else if (t_kind == BTF_KIND_FWD && c_kind != BTF_KIND_FWD)
+
+		/* if graph equivalence determined that we'd need to adjust
+		 * base canonical types, then we need to only point base FWDs
+		 * to STRUCTs/UNIONs and do no more modifications. For all
+		 * other purposes the type graphs were not equivalent.
+		 */
+		if (d->hypot_adjust_canon)
+			continue;
+		
+		if (t_kind == BTF_KIND_FWD && c_kind != BTF_KIND_FWD)
 			d->map[t_id] = c_id;
 
 		if ((t_kind == BTF_KIND_STRUCT || t_kind == BTF_KIND_UNION) &&
@@ -4065,8 +4209,10 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
 			return eq;
 		if (!eq)
 			continue;
-		new_id = cand_id;
 		btf_dedup_merge_hypot_map(d);
+		if (d->hypot_adjust_canon) /* not really equivalent */
+			continue;
+		new_id = cand_id;
 		break;
 	}
 
@@ -4081,8 +4227,8 @@ static int btf_dedup_struct_types(struct btf_dedup *d)
 {
 	int i, err;
 
-	for (i = 1; i <= d->btf->nr_types; i++) {
-		err = btf_dedup_struct_type(d, i);
+	for (i = 0; i < d->btf->nr_types; i++) {
+		err = btf_dedup_struct_type(d, d->btf->start_id + i);
 		if (err)
 			return err;
 	}
@@ -4225,8 +4371,8 @@ static int btf_dedup_ref_types(struct btf_dedup *d)
 {
 	int i, err;
 
-	for (i = 1; i <= d->btf->nr_types; i++) {
-		err = btf_dedup_ref_type(d, i);
+	for (i = 0; i < d->btf->nr_types; i++) {
+		err = btf_dedup_ref_type(d, d->btf->start_id + i);
 		if (err < 0)
 			return err;
 	}
@@ -4250,39 +4396,44 @@ static int btf_dedup_ref_types(struct btf_dedup *d)
 static int btf_dedup_compact_types(struct btf_dedup *d)
 {
 	__u32 *new_offs;
-	__u32 next_type_id = 1;
+	__u32 next_type_id = d->btf->start_id;
+	const struct btf_type *t;
 	void *p;
-	int i, len;
+	int i, id, len;
 
 	/* we are going to reuse hypot_map to store compaction remapping */
 	d->hypot_map[0] = 0;
-	for (i = 1; i <= d->btf->nr_types; i++)
-		d->hypot_map[i] = BTF_UNPROCESSED_ID;
+	/* base BTF types are not renumbered */
+	for (id = 1; id < d->btf->start_id; id++)
+		d->hypot_map[id] = id;
+	for (i = 0, id = d->btf->start_id; i < d->btf->nr_types; i++, id++)
+		d->hypot_map[id] = BTF_UNPROCESSED_ID;
 
 	p = d->btf->types_data;
 
-	for (i = 1; i <= d->btf->nr_types; i++) {
-		if (d->map[i] != i)
+	for (i = 0, id = d->btf->start_id; i < d->btf->nr_types; i++, id++) {
+		if (d->map[id] != id)
 			continue;
 
-		len = btf_type_size(btf__type_by_id(d->btf, i));
+		t = btf__type_by_id(d->btf, id);
+		len = btf_type_size(t);
 		if (len < 0)
 			return len;
 
-		memmove(p, btf__type_by_id(d->btf, i), len);
-		d->hypot_map[i] = next_type_id;
-		d->btf->type_offs[next_type_id] = p - d->btf->types_data;
+		memmove(p, t, len);
+		d->hypot_map[id] = next_type_id;
+		d->btf->type_offs[next_type_id - d->btf->start_id] = p - d->btf->types_data;
 		p += len;
 		next_type_id++;
 	}
 
 	/* shrink struct btf's internal types index and update btf_header */
-	d->btf->nr_types = next_type_id - 1;
-	d->btf->type_offs_cap = d->btf->nr_types + 1;
+	d->btf->nr_types = next_type_id - d->btf->start_id;
+	d->btf->type_offs_cap = d->btf->nr_types;
 	d->btf->hdr->type_len = p - d->btf->types_data;
 	new_offs = libbpf_reallocarray(d->btf->type_offs, d->btf->type_offs_cap,
 				       sizeof(*new_offs));
-	if (!new_offs)
+	if (d->btf->type_offs_cap && !new_offs)
 		return -ENOMEM;
 	d->btf->type_offs = new_offs;
 	d->btf->hdr->str_off = d->btf->hdr->type_len;
@@ -4414,8 +4565,8 @@ static int btf_dedup_remap_types(struct btf_dedup *d)
 {
 	int i, r;
 
-	for (i = 1; i <= d->btf->nr_types; i++) {
-		r = btf_dedup_remap_type(d, i);
+	for (i = 0; i < d->btf->nr_types; i++) {
+		r = btf_dedup_remap_type(d, d->btf->start_id + i);
 		if (r < 0)
 			return r;
 	}
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 57247240a20a..1237bcd1dd17 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -31,11 +31,19 @@ enum btf_endianness {
 };
 
 LIBBPF_API void btf__free(struct btf *btf);
+
 LIBBPF_API struct btf *btf__new(const void *data, __u32 size);
+LIBBPF_API struct btf *btf__new_split(const void *data, __u32 size, struct btf *base_btf);
 LIBBPF_API struct btf *btf__new_empty(void);
+LIBBPF_API struct btf *btf__new_empty_split(struct btf *base_btf);
+
 LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext);
+LIBBPF_API struct btf *btf__parse_split(const char *path, struct btf *base_btf);
 LIBBPF_API struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext);
+LIBBPF_API struct btf *btf__parse_elf_split(const char *path, struct btf *base_btf);
 LIBBPF_API struct btf *btf__parse_raw(const char *path);
+LIBBPF_API struct btf *btf__parse_raw_split(const char *path, struct btf *base_btf);
+
 LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf);
 LIBBPF_API int btf__load(struct btf *btf);
 LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
@@ -43,6 +51,7 @@ LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
 LIBBPF_API __s32 btf__find_by_name_kind(const struct btf *btf,
 					const char *type_name, __u32 kind);
 LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf);
+LIBBPF_API const struct btf *btf__base_btf(const struct btf *btf);
 LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf,
 						  __u32 id);
 LIBBPF_API size_t btf__pointer_size(const struct btf *btf);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 28baee7ba1ca..6ae748f6ea11 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -176,6 +176,8 @@ enum kern_feature_id {
 	FEAT_PROBE_READ_KERN,
 	/* BPF_PROG_BIND_MAP is supported */
 	FEAT_PROG_BIND_MAP,
+	/* Kernel support for module BTFs */
+	FEAT_MODULE_BTF,
 	__FEAT_CNT,
 };
 
@@ -276,6 +278,7 @@ struct bpf_program {
 	enum bpf_prog_type type;
 	enum bpf_attach_type expected_attach_type;
 	int prog_ifindex;
+	__u32 attach_btf_obj_fd;
 	__u32 attach_btf_id;
 	__u32 attach_prog_fd;
 	void *func_info;
@@ -402,6 +405,13 @@ struct extern_desc {
 
 static LIST_HEAD(bpf_objects_list);
 
+struct module_btf {
+	struct btf *btf;
+	char *name;
+	__u32 id;
+	int fd;
+};
+
 struct bpf_object {
 	char name[BPF_OBJ_NAME_LEN];
 	char license[64];
@@ -462,11 +472,19 @@ struct bpf_object {
 	struct list_head list;
 
 	struct btf *btf;
+	struct btf_ext *btf_ext;
+
 	/* Parse and load BTF vmlinux if any of the programs in the object need
 	 * it at load time.
 	 */
 	struct btf *btf_vmlinux;
-	struct btf_ext *btf_ext;
+	/* vmlinux BTF override for CO-RE relocations */
+	struct btf *btf_vmlinux_override;
+	/* Lazily initialized kernel module BTFs */
+	struct module_btf *btf_modules;
+	bool btf_modules_loaded;
+	size_t btf_module_cnt;
+	size_t btf_module_cap;
 
 	void *priv;
 	bpf_object_clear_priv_t clear_priv;
@@ -2500,7 +2518,7 @@ static int bpf_object__finalize_btf(struct bpf_object *obj)
 	return 0;
 }
 
-static inline bool libbpf_prog_needs_vmlinux_btf(struct bpf_program *prog)
+static bool prog_needs_vmlinux_btf(struct bpf_program *prog)
 {
 	if (prog->type == BPF_PROG_TYPE_STRUCT_OPS ||
 	    prog->type == BPF_PROG_TYPE_LSM)
@@ -2515,37 +2533,43 @@ static inline bool libbpf_prog_needs_vmlinux_btf(struct bpf_program *prog)
 	return false;
 }
 
-static int bpf_object__load_vmlinux_btf(struct bpf_object *obj)
+static bool obj_needs_vmlinux_btf(const struct bpf_object *obj)
 {
-	bool need_vmlinux_btf = false;
 	struct bpf_program *prog;
-	int i, err;
+	int i;
 
 	/* CO-RE relocations need kernel BTF */
 	if (obj->btf_ext && obj->btf_ext->core_relo_info.len)
-		need_vmlinux_btf = true;
+		return true;
 
 	/* Support for typed ksyms needs kernel BTF */
 	for (i = 0; i < obj->nr_extern; i++) {
 		const struct extern_desc *ext;
 
 		ext = &obj->externs[i];
-		if (ext->type == EXT_KSYM && ext->ksym.type_id) {
-			need_vmlinux_btf = true;
-			break;
-		}
+		if (ext->type == EXT_KSYM && ext->ksym.type_id)
+			return true;
 	}
 
 	bpf_object__for_each_program(prog, obj) {
 		if (!prog->load)
 			continue;
-		if (libbpf_prog_needs_vmlinux_btf(prog)) {
-			need_vmlinux_btf = true;
-			break;
-		}
+		if (prog_needs_vmlinux_btf(prog))
+			return true;
 	}
 
-	if (!need_vmlinux_btf)
+	return false;
+}
+
+static int bpf_object__load_vmlinux_btf(struct bpf_object *obj, bool force)
+{
+	int err;
+
+	/* btf_vmlinux could be loaded earlier */
+	if (obj->btf_vmlinux)
+		return 0;
+
+	if (!force && !obj_needs_vmlinux_btf(obj))
 		return 0;
 
 	obj->btf_vmlinux = libbpf_find_kernel_btf();
@@ -3960,6 +3984,35 @@ static int probe_prog_bind_map(void)
 	return ret >= 0;
 }
 
+static int probe_module_btf(void)
+{
+	static const char strs[] = "\0int";
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),
+	};
+	struct bpf_btf_info info;
+	__u32 len = sizeof(info);
+	char name[16];
+	int fd, err;
+
+	fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs));
+	if (fd < 0)
+		return 0; /* BTF not supported at all */
+
+	memset(&info, 0, sizeof(info));
+	info.name = ptr_to_u64(name);
+	info.name_len = sizeof(name);
+
+	/* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer;
+	 * kernel's module BTF support coincides with support for
+	 * name/name_len fields in struct bpf_btf_info.
+	 */
+	err = bpf_obj_get_info_by_fd(fd, &info, &len);
+	close(fd);
+	return !err;
+}
+
 enum kern_feature_result {
 	FEAT_UNKNOWN = 0,
 	FEAT_SUPPORTED = 1,
@@ -4003,7 +4056,10 @@ static struct kern_feature_desc {
 	},
 	[FEAT_PROG_BIND_MAP] = {
 		"BPF_PROG_BIND_MAP support", probe_prog_bind_map,
-	}
+	},
+	[FEAT_MODULE_BTF] = {
+		"module BTF support", probe_module_btf,
+	},
 };
 
 static bool kernel_supports(enum kern_feature_id feat_id)
@@ -4603,46 +4659,43 @@ static size_t bpf_core_essential_name_len(const char *name)
 	return n;
 }
 
-/* dynamically sized list of type IDs */
-struct ids_vec {
-	__u32 *data;
+struct core_cand
+{
+	const struct btf *btf;
+	const struct btf_type *t;
+	const char *name;
+	__u32 id;
+};
+
+/* dynamically sized list of type IDs and its associated struct btf */
+struct core_cand_list {
+	struct core_cand *cands;
 	int len;
 };
 
-static void bpf_core_free_cands(struct ids_vec *cand_ids)
+static void bpf_core_free_cands(struct core_cand_list *cands)
 {
-	free(cand_ids->data);
-	free(cand_ids);
+	free(cands->cands);
+	free(cands);
 }
 
-static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf,
-					   __u32 local_type_id,
-					   const struct btf *targ_btf)
+static int bpf_core_add_cands(struct core_cand *local_cand,
+			      size_t local_essent_len,
+			      const struct btf *targ_btf,
+			      const char *targ_btf_name,
+			      int targ_start_id,
+			      struct core_cand_list *cands)
 {
-	size_t local_essent_len, targ_essent_len;
-	const char *local_name, *targ_name;
-	const struct btf_type *t, *local_t;
-	struct ids_vec *cand_ids;
-	__u32 *new_ids;
-	int i, err, n;
-
-	local_t = btf__type_by_id(local_btf, local_type_id);
-	if (!local_t)
-		return ERR_PTR(-EINVAL);
-
-	local_name = btf__name_by_offset(local_btf, local_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);
+	struct core_cand *new_cands, *cand;
+	const struct btf_type *t;
+	const char *targ_name;
+	size_t targ_essent_len;
+	int n, i;
 
 	n = btf__get_nr_types(targ_btf);
-	for (i = 1; i <= n; i++) {
+	for (i = targ_start_id; i <= n; i++) {
 		t = btf__type_by_id(targ_btf, i);
-		if (btf_kind(t) != btf_kind(local_t))
+		if (btf_kind(t) != btf_kind(local_cand->t))
 			continue;
 
 		targ_name = btf__name_by_offset(targ_btf, t->name_off);
@@ -4653,24 +4706,174 @@ static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf,
 		if (targ_essent_len != local_essent_len)
 			continue;
 
-		if (strncmp(local_name, targ_name, local_essent_len) == 0) {
-			pr_debug("CO-RE relocating [%d] %s %s: found target candidate [%d] %s %s\n",
-				 local_type_id, btf_kind_str(local_t),
-				 local_name, i, btf_kind_str(t), targ_name);
-			new_ids = libbpf_reallocarray(cand_ids->data,
-						      cand_ids->len + 1,
-						      sizeof(*cand_ids->data));
-			if (!new_ids) {
-				err = -ENOMEM;
-				goto err_out;
-			}
-			cand_ids->data = new_ids;
-			cand_ids->data[cand_ids->len++] = i;
+		if (strncmp(local_cand->name, targ_name, local_essent_len) != 0)
+			continue;
+
+		pr_debug("CO-RE relocating [%d] %s %s: found target candidate [%d] %s %s in [%s]\n",
+			 local_cand->id, btf_kind_str(local_cand->t),
+			 local_cand->name, i, btf_kind_str(t), targ_name,
+			 targ_btf_name);
+		new_cands = libbpf_reallocarray(cands->cands, cands->len + 1,
+					      sizeof(*cands->cands));
+		if (!new_cands)
+			return -ENOMEM;
+
+		cand = &new_cands[cands->len];
+		cand->btf = targ_btf;
+		cand->t = t;
+		cand->name = targ_name;
+		cand->id = i;
+
+		cands->cands = new_cands;
+		cands->len++;
+	}
+	return 0;
+}
+
+static int load_module_btfs(struct bpf_object *obj)
+{
+	struct bpf_btf_info info;
+	struct module_btf *mod_btf;
+	struct btf *btf;
+	char name[64];
+	__u32 id = 0, len;
+	int err, fd;
+
+	if (obj->btf_modules_loaded)
+		return 0;
+
+	/* don't do this again, even if we find no module BTFs */
+	obj->btf_modules_loaded = true;
+
+	/* kernel too old to support module BTFs */
+	if (!kernel_supports(FEAT_MODULE_BTF))
+		return 0;
+
+	while (true) {
+		err = bpf_btf_get_next_id(id, &id);
+		if (err && errno == ENOENT)
+			return 0;
+		if (err) {
+			err = -errno;
+			pr_warn("failed to iterate BTF objects: %d\n", err);
+			return err;
+		}
+
+		fd = bpf_btf_get_fd_by_id(id);
+		if (fd < 0) {
+			if (errno == ENOENT)
+				continue; /* expected race: BTF was unloaded */
+			err = -errno;
+			pr_warn("failed to get BTF object #%d FD: %d\n", id, err);
+			return err;
 		}
+
+		len = sizeof(info);
+		memset(&info, 0, sizeof(info));
+		info.name = ptr_to_u64(name);
+		info.name_len = sizeof(name);
+
+		err = bpf_obj_get_info_by_fd(fd, &info, &len);
+		if (err) {
+			err = -errno;
+			pr_warn("failed to get BTF object #%d info: %d\n", id, err);
+			goto err_out;
+		}
+
+		/* ignore non-module BTFs */
+		if (!info.kernel_btf || strcmp(name, "vmlinux") == 0) {
+			close(fd);
+			continue;
+		}
+
+		btf = btf_get_from_fd(fd, obj->btf_vmlinux);
+		if (IS_ERR(btf)) {
+			pr_warn("failed to load module [%s]'s BTF object #%d: %ld\n",
+				name, id, PTR_ERR(btf));
+			err = PTR_ERR(btf);
+			goto err_out;
+		}
+
+		err = btf_ensure_mem((void **)&obj->btf_modules, &obj->btf_module_cap,
+				     sizeof(*obj->btf_modules), obj->btf_module_cnt + 1);
+		if (err)
+			goto err_out;
+
+		mod_btf = &obj->btf_modules[obj->btf_module_cnt++];
+
+		mod_btf->btf = btf;
+		mod_btf->id = id;
+		mod_btf->fd = fd;
+		mod_btf->name = strdup(name);
+		if (!mod_btf->name) {
+			err = -ENOMEM;
+			goto err_out;
+		}
+		continue;
+
+err_out:
+		close(fd);
+		return err;
+	}
+
+	return 0;
+}
+
+static struct core_cand_list *
+bpf_core_find_cands(struct bpf_object *obj, const struct btf *local_btf, __u32 local_type_id)
+{
+	struct core_cand local_cand = {};
+	struct core_cand_list *cands;
+	const struct btf *main_btf;
+	size_t local_essent_len;
+	int err, i;
+
+	local_cand.btf = local_btf;
+	local_cand.t = btf__type_by_id(local_btf, local_type_id);
+	if (!local_cand.t)
+		return ERR_PTR(-EINVAL);
+
+	local_cand.name = btf__name_by_offset(local_btf, local_cand.t->name_off);
+	if (str_is_empty(local_cand.name))
+		return ERR_PTR(-EINVAL);
+	local_essent_len = bpf_core_essential_name_len(local_cand.name);
+
+	cands = calloc(1, sizeof(*cands));
+	if (!cands)
+		return ERR_PTR(-ENOMEM);
+
+	/* Attempt to find target candidates in vmlinux BTF first */
+	main_btf = obj->btf_vmlinux_override ?: obj->btf_vmlinux;
+	err = bpf_core_add_cands(&local_cand, local_essent_len, main_btf, "vmlinux", 1, cands);
+	if (err)
+		goto err_out;
+
+	/* if vmlinux BTF has any candidate, don't got for module BTFs */
+	if (cands->len)
+		return cands;
+
+	/* if vmlinux BTF was overridden, don't attempt to load module BTFs */
+	if (obj->btf_vmlinux_override)
+		return cands;
+
+	/* now look through module BTFs, trying to still find candidates */
+	err = load_module_btfs(obj);
+	if (err)
+		goto err_out;
+
+	for (i = 0; i < obj->btf_module_cnt; i++) {
+		err = bpf_core_add_cands(&local_cand, local_essent_len,
+					 obj->btf_modules[i].btf,
+					 obj->btf_modules[i].name,
+					 btf__get_nr_types(obj->btf_vmlinux) + 1,
+					 cands);
+		if (err)
+			goto err_out;
 	}
-	return cand_ids;
+
+	return cands;
 err_out:
-	bpf_core_free_cands(cand_ids);
+	bpf_core_free_cands(cands);
 	return ERR_PTR(err);
 }
 
@@ -5664,7 +5867,6 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 			       const struct bpf_core_relo *relo,
 			       int relo_idx,
 			       const struct btf *local_btf,
-			       const struct btf *targ_btf,
 			       struct hashmap *cand_cache)
 {
 	struct bpf_core_spec local_spec, cand_spec, targ_spec = {};
@@ -5672,8 +5874,8 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 	struct bpf_core_relo_res cand_res, targ_res;
 	const struct btf_type *local_type;
 	const char *local_name;
-	struct ids_vec *cand_ids;
-	__u32 local_id, cand_id;
+	struct core_cand_list *cands = NULL;
+	__u32 local_id;
 	const char *spec_str;
 	int i, j, err;
 
@@ -5720,24 +5922,24 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 		return -EOPNOTSUPP;
 	}
 
-	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_warn("prog '%s': relo #%d: target candidate search failed for [%d] %s %s: %ld",
+	if (!hashmap__find(cand_cache, type_key, (void **)&cands)) {
+		cands = bpf_core_find_cands(prog->obj, local_btf, local_id);
+		if (IS_ERR(cands)) {
+			pr_warn("prog '%s': relo #%d: target candidate search failed for [%d] %s %s: %ld\n",
 				prog->name, relo_idx, local_id, btf_kind_str(local_type),
-				local_name, PTR_ERR(cand_ids));
-			return PTR_ERR(cand_ids);
+				local_name, PTR_ERR(cands));
+			return PTR_ERR(cands);
 		}
-		err = hashmap__set(cand_cache, type_key, cand_ids, NULL, NULL);
+		err = hashmap__set(cand_cache, type_key, cands, NULL, NULL);
 		if (err) {
-			bpf_core_free_cands(cand_ids);
+			bpf_core_free_cands(cands);
 			return err;
 		}
 	}
 
-	for (i = 0, j = 0; i < cand_ids->len; i++) {
-		cand_id = cand_ids->data[i];
-		err = bpf_core_spec_match(&local_spec, targ_btf, cand_id, &cand_spec);
+	for (i = 0, j = 0; i < cands->len; i++) {
+		err = bpf_core_spec_match(&local_spec, cands->cands[i].btf,
+					  cands->cands[i].id, &cand_spec);
 		if (err < 0) {
 			pr_warn("prog '%s': relo #%d: error matching candidate #%d ",
 				prog->name, relo_idx, i);
@@ -5781,7 +5983,7 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 			return -EINVAL;
 		}
 
-		cand_ids->data[j++] = cand_spec.root_type_id;
+		cands->cands[j++] = cands->cands[i];
 	}
 
 	/*
@@ -5793,7 +5995,7 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 	 * depending on relo's kind.
 	 */
 	if (j > 0)
-		cand_ids->len = j;
+		cands->len = j;
 
 	/*
 	 * If no candidates were found, it might be both a programmer error,
@@ -5837,20 +6039,19 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path)
 	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, insn_idx, sec_idx;
 
 	if (obj->btf_ext->core_relo_info.len == 0)
 		return 0;
 
-	if (targ_btf_path)
-		targ_btf = btf__parse(targ_btf_path, NULL);
-	else
-		targ_btf = obj->btf_vmlinux;
-	if (IS_ERR_OR_NULL(targ_btf)) {
-		pr_warn("failed to get target BTF: %ld\n", PTR_ERR(targ_btf));
-		return PTR_ERR(targ_btf);
+	if (targ_btf_path) {
+		obj->btf_vmlinux_override = btf__parse(targ_btf_path, NULL);
+		if (IS_ERR_OR_NULL(obj->btf_vmlinux_override)) {
+			err = PTR_ERR(obj->btf_vmlinux_override);
+			pr_warn("failed to parse target BTF: %d\n", err);
+			return err;
+		}
 	}
 
 	cand_cache = hashmap__new(bpf_core_hash_fn, bpf_core_equal_fn, NULL);
@@ -5902,8 +6103,7 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path)
 			if (!prog->load)
 				continue;
 
-			err = bpf_core_apply_relo(prog, rec, i, obj->btf,
-						  targ_btf, cand_cache);
+			err = bpf_core_apply_relo(prog, rec, i, obj->btf, cand_cache);
 			if (err) {
 				pr_warn("prog '%s': relo #%d: failed to relocate: %d\n",
 					prog->name, i, err);
@@ -5913,9 +6113,10 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path)
 	}
 
 out:
-	/* obj->btf_vmlinux is freed at the end of object load phase */
-	if (targ_btf != obj->btf_vmlinux)
-		btf__free(targ_btf);
+	/* obj->btf_vmlinux and module BTFs are freed after object load */
+	btf__free(obj->btf_vmlinux_override);
+	obj->btf_vmlinux_override = NULL;
+
 	if (!IS_ERR_OR_NULL(cand_cache)) {
 		hashmap__for_each_entry(cand_cache, entry, i) {
 			bpf_core_free_cands(entry->value);
@@ -6626,16 +6827,25 @@ static int
 load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	     char *license, __u32 kern_version, int *pfd)
 {
-	struct bpf_load_program_attr load_attr;
+	struct bpf_prog_load_params load_attr = {};
 	char *cp, errmsg[STRERR_BUFSIZE];
 	size_t log_buf_size = 0;
 	char *log_buf = NULL;
 	int btf_fd, ret;
 
+	if (prog->type == BPF_PROG_TYPE_UNSPEC) {
+		/*
+		 * The program type must be set.  Most likely we couldn't find a proper
+		 * section definition at load time, and thus we didn't infer the type.
+		 */
+		pr_warn("prog '%s': missing BPF prog type, check ELF section name '%s'\n",
+			prog->name, prog->sec_name);
+		return -EINVAL;
+	}
+
 	if (!insns || !insns_cnt)
 		return -EINVAL;
 
-	memset(&load_attr, 0, sizeof(struct bpf_load_program_attr));
 	load_attr.prog_type = prog->type;
 	/* old kernels might not support specifying expected_attach_type */
 	if (!kernel_supports(FEAT_EXP_ATTACH_TYPE) && prog->sec_def &&
@@ -6646,19 +6856,17 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	if (kernel_supports(FEAT_PROG_NAME))
 		load_attr.name = prog->name;
 	load_attr.insns = insns;
-	load_attr.insns_cnt = insns_cnt;
+	load_attr.insn_cnt = insns_cnt;
 	load_attr.license = license;
-	if (prog->type == BPF_PROG_TYPE_STRUCT_OPS ||
-	    prog->type == BPF_PROG_TYPE_LSM) {
-		load_attr.attach_btf_id = prog->attach_btf_id;
-	} else if (prog->type == BPF_PROG_TYPE_TRACING ||
-		   prog->type == BPF_PROG_TYPE_EXT) {
+	load_attr.attach_btf_id = prog->attach_btf_id;
+	if (prog->attach_prog_fd)
 		load_attr.attach_prog_fd = prog->attach_prog_fd;
-		load_attr.attach_btf_id = prog->attach_btf_id;
-	} else {
-		load_attr.kern_version = kern_version;
-		load_attr.prog_ifindex = prog->prog_ifindex;
-	}
+	else
+		load_attr.attach_btf_obj_fd = prog->attach_btf_obj_fd;
+	load_attr.attach_btf_id = prog->attach_btf_id;
+	load_attr.kern_version = kern_version;
+	load_attr.prog_ifindex = prog->prog_ifindex;
+
 	/* specify func_info/line_info only if kernel supports them */
 	btf_fd = bpf_object__btf_fd(prog->obj);
 	if (btf_fd >= 0 && kernel_supports(FEAT_BTF_FUNC)) {
@@ -6682,7 +6890,9 @@ retry_load:
 		*log_buf = 0;
 	}
 
-	ret = bpf_load_program_xattr(&load_attr, log_buf, log_buf_size);
+	load_attr.log_buf = log_buf;
+	load_attr.log_buf_sz = log_buf_size;
+	ret = libbpf__bpf_prog_load(&load_attr);
 
 	if (ret >= 0) {
 		if (log_buf && load_attr.log_level)
@@ -6723,9 +6933,9 @@ retry_load:
 		pr_warn("-- BEGIN DUMP LOG ---\n");
 		pr_warn("\n%s\n", log_buf);
 		pr_warn("-- END LOG --\n");
-	} else if (load_attr.insns_cnt >= BPF_MAXINSNS) {
+	} else if (load_attr.insn_cnt >= BPF_MAXINSNS) {
 		pr_warn("Program too large (%zu insns), at most %d insns\n",
-			load_attr.insns_cnt, BPF_MAXINSNS);
+			load_attr.insn_cnt, BPF_MAXINSNS);
 		ret = -LIBBPF_ERRNO__PROG2BIG;
 	} else if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) {
 		/* Wrong program type? */
@@ -6733,7 +6943,9 @@ retry_load:
 
 		load_attr.prog_type = BPF_PROG_TYPE_KPROBE;
 		load_attr.expected_attach_type = 0;
-		fd = bpf_load_program_xattr(&load_attr, NULL, 0);
+		load_attr.log_buf = NULL;
+		load_attr.log_buf_sz = 0;
+		fd = libbpf__bpf_prog_load(&load_attr);
 		if (fd >= 0) {
 			close(fd);
 			ret = -LIBBPF_ERRNO__PROGTYPE;
@@ -6746,11 +6958,11 @@ out:
 	return ret;
 }
 
-static int libbpf_find_attach_btf_id(struct bpf_program *prog);
+static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id);
 
 int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 {
-	int err = 0, fd, i, btf_id;
+	int err = 0, fd, i;
 
 	if (prog->obj->loaded) {
 		pr_warn("prog '%s': can't load after object was loaded\n", prog->name);
@@ -6760,10 +6972,14 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 	if ((prog->type == BPF_PROG_TYPE_TRACING ||
 	     prog->type == BPF_PROG_TYPE_LSM ||
 	     prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) {
-		btf_id = libbpf_find_attach_btf_id(prog);
-		if (btf_id <= 0)
-			return btf_id;
-		prog->attach_btf_id = btf_id;
+		int btf_obj_fd = 0, btf_type_id = 0;
+
+		err = libbpf_find_attach_btf_id(prog, &btf_obj_fd, &btf_type_id);
+		if (err)
+			return err;
+
+		prog->attach_btf_obj_fd = btf_obj_fd;
+		prog->attach_btf_id = btf_type_id;
 	}
 
 	if (prog->instances.nr < 0 || !prog->instances.fds) {
@@ -6923,9 +7139,12 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 
 	bpf_object__for_each_program(prog, obj) {
 		prog->sec_def = find_sec_def(prog->sec_name);
-		if (!prog->sec_def)
+		if (!prog->sec_def) {
 			/* couldn't guess, but user might manually specify */
+			pr_debug("prog '%s': unrecognized ELF section name '%s'\n",
+				prog->name, prog->sec_name);
 			continue;
+		}
 
 		if (prog->sec_def->is_sleepable)
 			prog->prog_flags |= BPF_F_SLEEPABLE;
@@ -7262,7 +7481,7 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
 	}
 
 	err = bpf_object__probe_loading(obj);
-	err = err ? : bpf_object__load_vmlinux_btf(obj);
+	err = err ? : bpf_object__load_vmlinux_btf(obj, false);
 	err = err ? : bpf_object__resolve_externs(obj, obj->kconfig);
 	err = err ? : bpf_object__sanitize_and_load_btf(obj);
 	err = err ? : bpf_object__sanitize_maps(obj);
@@ -7271,6 +7490,15 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
 	err = err ? : bpf_object__relocate(obj, attr->target_btf_path);
 	err = err ? : bpf_object__load_progs(obj, attr->log_level);
 
+	/* clean up module BTFs */
+	for (i = 0; i < obj->btf_module_cnt; i++) {
+		close(obj->btf_modules[i].fd);
+		btf__free(obj->btf_modules[i].btf);
+		free(obj->btf_modules[i].name);
+	}
+	free(obj->btf_modules);
+
+	/* clean up vmlinux BTF */
 	btf__free(obj->btf_vmlinux);
 	obj->btf_vmlinux = NULL;
 
@@ -7649,6 +7877,16 @@ bool bpf_map__is_pinned(const struct bpf_map *map)
 	return map->pinned;
 }
 
+static void sanitize_pin_path(char *s)
+{
+	/* bpffs disallows periods in path names */
+	while (*s) {
+		if (*s == '.')
+			*s = '_';
+		s++;
+	}
+}
+
 int bpf_object__pin_maps(struct bpf_object *obj, const char *path)
 {
 	struct bpf_map *map;
@@ -7678,6 +7916,7 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path)
 				err = -ENAMETOOLONG;
 				goto err_unpin_maps;
 			}
+			sanitize_pin_path(buf);
 			pin_path = buf;
 		} else if (!map->pin_path) {
 			continue;
@@ -7722,6 +7961,7 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path)
 				return -EINVAL;
 			else if (len >= PATH_MAX)
 				return -ENAMETOOLONG;
+			sanitize_pin_path(buf);
 			pin_path = buf;
 		} else if (!map->pin_path) {
 			continue;
@@ -8607,8 +8847,8 @@ static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix,
 	return btf__find_by_name_kind(btf, btf_type_name, kind);
 }
 
-static inline int __find_vmlinux_btf_id(struct btf *btf, const char *name,
-					enum bpf_attach_type attach_type)
+static inline int find_attach_btf_id(struct btf *btf, const char *name,
+				     enum bpf_attach_type attach_type)
 {
 	int err;
 
@@ -8624,9 +8864,6 @@ static inline int __find_vmlinux_btf_id(struct btf *btf, const char *name,
 	else
 		err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC);
 
-	if (err <= 0)
-		pr_warn("%s is not found in vmlinux BTF\n", name);
-
 	return err;
 }
 
@@ -8642,7 +8879,10 @@ int libbpf_find_vmlinux_btf_id(const char *name,
 		return -EINVAL;
 	}
 
-	err = __find_vmlinux_btf_id(btf, name, attach_type);
+	err = find_attach_btf_id(btf, name, attach_type);
+	if (err <= 0)
+		pr_warn("%s is not found in vmlinux BTF\n", name);
+
 	btf__free(btf);
 	return err;
 }
@@ -8680,11 +8920,49 @@ out:
 	return err;
 }
 
-static int libbpf_find_attach_btf_id(struct bpf_program *prog)
+static int find_kernel_btf_id(struct bpf_object *obj, const char *attach_name,
+			      enum bpf_attach_type attach_type,
+			      int *btf_obj_fd, int *btf_type_id)
+{
+	int ret, i;
+
+	ret = find_attach_btf_id(obj->btf_vmlinux, attach_name, attach_type);
+	if (ret > 0) {
+		*btf_obj_fd = 0; /* vmlinux BTF */
+		*btf_type_id = ret;
+		return 0;
+	}
+	if (ret != -ENOENT)
+		return ret;
+
+	ret = load_module_btfs(obj);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < obj->btf_module_cnt; i++) {
+		const struct module_btf *mod = &obj->btf_modules[i];
+
+		ret = find_attach_btf_id(mod->btf, attach_name, attach_type);
+		if (ret > 0) {
+			*btf_obj_fd = mod->fd;
+			*btf_type_id = ret;
+			return 0;
+		}
+		if (ret == -ENOENT)
+			continue;
+
+		return ret;
+	}
+
+	return -ESRCH;
+}
+
+static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id)
 {
 	enum bpf_attach_type attach_type = prog->expected_attach_type;
 	__u32 attach_prog_fd = prog->attach_prog_fd;
-	const char *name = prog->sec_name;
+	const char *name = prog->sec_name, *attach_name;
+	const struct bpf_sec_def *sec = NULL;
 	int i, err;
 
 	if (!name)
@@ -8695,17 +8973,37 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog)
 			continue;
 		if (strncmp(name, section_defs[i].sec, section_defs[i].len))
 			continue;
-		if (attach_prog_fd)
-			err = libbpf_find_prog_btf_id(name + section_defs[i].len,
-						      attach_prog_fd);
-		else
-			err = __find_vmlinux_btf_id(prog->obj->btf_vmlinux,
-						    name + section_defs[i].len,
-						    attach_type);
+
+		sec = &section_defs[i];
+		break;
+	}
+
+	if (!sec) {
+		pr_warn("failed to identify BTF ID based on ELF section name '%s'\n", name);
+		return -ESRCH;
+	}
+	attach_name = name + sec->len;
+
+	/* BPF program's BTF ID */
+	if (attach_prog_fd) {
+		err = libbpf_find_prog_btf_id(attach_name, attach_prog_fd);
+		if (err < 0) {
+			pr_warn("failed to find BPF program (FD %d) BTF ID for '%s': %d\n",
+				 attach_prog_fd, attach_name, err);
+			return err;
+		}
+		*btf_obj_fd = 0;
+		*btf_type_id = err;
+		return 0;
+	}
+
+	/* kernel/module BTF ID */
+	err = find_kernel_btf_id(prog->obj, attach_name, attach_type, btf_obj_fd, btf_type_id);
+	if (err) {
+		pr_warn("failed to find kernel BTF type ID of '%s': %d\n", attach_name, err);
 		return err;
 	}
-	pr_warn("failed to identify btf_id based on ELF section name '%s'\n", name);
-	return -ESRCH;
+	return 0;
 }
 
 int libbpf_attach_type_by_name(const char *name,
@@ -10578,22 +10876,33 @@ int bpf_program__set_attach_target(struct bpf_program *prog,
 				   int attach_prog_fd,
 				   const char *attach_func_name)
 {
-	int btf_id;
+	int btf_obj_fd = 0, btf_id = 0, err;
 
 	if (!prog || attach_prog_fd < 0 || !attach_func_name)
 		return -EINVAL;
 
-	if (attach_prog_fd)
+	if (prog->obj->loaded)
+		return -EINVAL;
+
+	if (attach_prog_fd) {
 		btf_id = libbpf_find_prog_btf_id(attach_func_name,
 						 attach_prog_fd);
-	else
-		btf_id = libbpf_find_vmlinux_btf_id(attach_func_name,
-						    prog->expected_attach_type);
-
-	if (btf_id < 0)
-		return btf_id;
+		if (btf_id < 0)
+			return btf_id;
+	} else {
+		/* load btf_vmlinux, if not yet */
+		err = bpf_object__load_vmlinux_btf(prog->obj, true);
+		if (err)
+			return err;
+		err = find_kernel_btf_id(prog->obj, attach_func_name,
+					 prog->expected_attach_type,
+					 &btf_obj_fd, &btf_id);
+		if (err)
+			return err;
+	}
 
 	prog->attach_btf_id = btf_id;
+	prog->attach_btf_obj_fd = btf_obj_fd;
 	prog->attach_prog_fd = attach_prog_fd;
 	return 0;
 }
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 6909ee81113a..3c35eb401931 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -536,6 +536,7 @@ LIBBPF_API int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 				ring_buffer_sample_fn sample_cb, void *ctx);
 LIBBPF_API int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms);
 LIBBPF_API int ring_buffer__consume(struct ring_buffer *rb);
+LIBBPF_API int ring_buffer__epoll_fd(const struct ring_buffer *rb);
 
 /* Perf buffer APIs */
 struct perf_buffer;
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 4ebfadf45b47..1c0fd2dd233a 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -337,3 +337,16 @@ LIBBPF_0.2.0 {
 		perf_buffer__consume_buffer;
 		xsk_socket__create_shared;
 } LIBBPF_0.1.0;
+
+LIBBPF_0.3.0 {
+	global:
+		btf__base_btf;
+		btf__parse_elf_split;
+		btf__parse_raw_split;
+		btf__parse_split;
+		btf__new_empty_split;
+		btf__new_split;
+		ring_buffer__epoll_fd;
+		xsk_setup_xdp_prog;
+		xsk_socket__update_xskmap;
+} LIBBPF_0.2.0;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index d99bc847bf84..969d0ac592ba 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -151,10 +151,41 @@ int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz);
 int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
 			 const char *str_sec, size_t str_len);
 
+struct bpf_prog_load_params {
+	enum bpf_prog_type prog_type;
+	enum bpf_attach_type expected_attach_type;
+	const char *name;
+	const struct bpf_insn *insns;
+	size_t insn_cnt;
+	const char *license;
+	__u32 kern_version;
+	__u32 attach_prog_fd;
+	__u32 attach_btf_obj_fd;
+	__u32 attach_btf_id;
+	__u32 prog_ifindex;
+	__u32 prog_btf_fd;
+	__u32 prog_flags;
+
+	__u32 func_info_rec_size;
+	const void *func_info;
+	__u32 func_info_cnt;
+
+	__u32 line_info_rec_size;
+	const void *line_info;
+	__u32 line_info_cnt;
+
+	__u32 log_level;
+	char *log_buf;
+	size_t log_buf_sz;
+};
+
+int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr);
+
 int bpf_object__section_size(const struct bpf_object *obj, const char *name,
 			     __u32 *size);
 int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
 				__u32 *off);
+struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf);
 
 struct btf_ext_info {
 	/*
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index 5482a9b7ae2d..ecaae2927ab8 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -230,6 +230,7 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 		break;
 	case BPF_MAP_TYPE_SK_STORAGE:
 	case BPF_MAP_TYPE_INODE_STORAGE:
+	case BPF_MAP_TYPE_TASK_STORAGE:
 		btf_key_type_id = 1;
 		btf_value_type_id = 3;
 		value_size = 8;
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 5c6522c89af1..8caaafe7e312 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -278,7 +278,13 @@ int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms)
 		err = ringbuf_process_ring(ring);
 		if (err < 0)
 			return err;
-		res += cnt;
+		res += err;
 	}
 	return cnt < 0 ? -errno : res;
 }
+
+/* Get an fd that can be used to sleep until data is available in the ring(s) */
+int ring_buffer__epoll_fd(const struct ring_buffer *rb)
+{
+	return rb->epoll_fd;
+}
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 9bc537d0b92d..e3e41ceeb1bc 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -566,8 +566,35 @@ static int xsk_set_bpf_maps(struct xsk_socket *xsk)
 				   &xsk->fd, 0);
 }
 
-static int xsk_setup_xdp_prog(struct xsk_socket *xsk)
+static int xsk_create_xsk_struct(int ifindex, struct xsk_socket *xsk)
 {
+	char ifname[IFNAMSIZ];
+	struct xsk_ctx *ctx;
+	char *interface;
+
+	ctx = calloc(1, sizeof(*ctx));
+	if (!ctx)
+		return -ENOMEM;
+
+	interface = if_indextoname(ifindex, &ifname[0]);
+	if (!interface) {
+		free(ctx);
+		return -errno;
+	}
+
+	ctx->ifindex = ifindex;
+	memcpy(ctx->ifname, ifname, IFNAMSIZ -1);
+	ctx->ifname[IFNAMSIZ - 1] = 0;
+
+	xsk->ctx = ctx;
+
+	return 0;
+}
+
+static int __xsk_setup_xdp_prog(struct xsk_socket *_xdp,
+				int *xsks_map_fd)
+{
+	struct xsk_socket *xsk = _xdp;
 	struct xsk_ctx *ctx = xsk->ctx;
 	__u32 prog_id = 0;
 	int err;
@@ -584,8 +611,7 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk)
 
 		err = xsk_load_xdp_prog(xsk);
 		if (err) {
-			xsk_delete_bpf_maps(xsk);
-			return err;
+			goto err_load_xdp_prog;
 		}
 	} else {
 		ctx->prog_fd = bpf_prog_get_fd_by_id(prog_id);
@@ -598,15 +624,29 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk)
 		}
 	}
 
-	if (xsk->rx)
+	if (xsk->rx) {
 		err = xsk_set_bpf_maps(xsk);
-	if (err) {
-		xsk_delete_bpf_maps(xsk);
-		close(ctx->prog_fd);
-		return err;
+		if (err) {
+			if (!prog_id) {
+				goto err_set_bpf_maps;
+			} else {
+				close(ctx->prog_fd);
+				return err;
+			}
+		}
 	}
+	if (xsks_map_fd)
+		*xsks_map_fd = ctx->xsks_map_fd;
 
 	return 0;
+
+err_set_bpf_maps:
+	close(ctx->prog_fd);
+	bpf_set_link_xdp_fd(ctx->ifindex, -1, 0);
+err_load_xdp_prog:
+	xsk_delete_bpf_maps(xsk);
+
+	return err;
 }
 
 static struct xsk_ctx *xsk_get_ctx(struct xsk_umem *umem, int ifindex,
@@ -689,6 +729,40 @@ static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk,
 	return ctx;
 }
 
+static void xsk_destroy_xsk_struct(struct xsk_socket *xsk)
+{
+	free(xsk->ctx);
+	free(xsk);
+}
+
+int xsk_socket__update_xskmap(struct xsk_socket *xsk, int fd)
+{
+	xsk->ctx->xsks_map_fd = fd;
+	return xsk_set_bpf_maps(xsk);
+}
+
+int xsk_setup_xdp_prog(int ifindex, int *xsks_map_fd)
+{
+	struct xsk_socket *xsk;
+	int res;
+
+	xsk = calloc(1, sizeof(*xsk));
+	if (!xsk)
+		return -ENOMEM;
+
+	res = xsk_create_xsk_struct(ifindex, xsk);
+	if (res) {
+		free(xsk);
+		return -EINVAL;
+	}
+
+	res = __xsk_setup_xdp_prog(xsk, xsks_map_fd);
+
+	xsk_destroy_xsk_struct(xsk);
+
+	return res;
+}
+
 int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 			      const char *ifname,
 			      __u32 queue_id, struct xsk_umem *umem,
@@ -838,7 +912,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 	ctx->prog_fd = -1;
 
 	if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) {
-		err = xsk_setup_xdp_prog(xsk);
+		err = __xsk_setup_xdp_prog(xsk, NULL);
 		if (err)
 			goto out_mmap_tx;
 	}
diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h
index 1069c46364ff..e9f121f5d129 100644
--- a/tools/lib/bpf/xsk.h
+++ b/tools/lib/bpf/xsk.h
@@ -113,8 +113,7 @@ static inline __u32 xsk_cons_nb_avail(struct xsk_ring_cons *r, __u32 nb)
 	return (entries > nb) ? nb : entries;
 }
 
-static inline size_t xsk_ring_prod__reserve(struct xsk_ring_prod *prod,
-					    size_t nb, __u32 *idx)
+static inline __u32 xsk_ring_prod__reserve(struct xsk_ring_prod *prod, __u32 nb, __u32 *idx)
 {
 	if (xsk_prod_nb_free(prod, nb) < nb)
 		return 0;
@@ -125,7 +124,7 @@ static inline size_t xsk_ring_prod__reserve(struct xsk_ring_prod *prod,
 	return nb;
 }
 
-static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, size_t nb)
+static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, __u32 nb)
 {
 	/* Make sure everything has been written to the ring before indicating
 	 * this to the kernel by writing the producer pointer.
@@ -135,10 +134,9 @@ static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, size_t nb)
 	*prod->producer += nb;
 }
 
-static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons,
-					 size_t nb, __u32 *idx)
+static inline __u32 xsk_ring_cons__peek(struct xsk_ring_cons *cons, __u32 nb, __u32 *idx)
 {
-	size_t entries = xsk_cons_nb_avail(cons, nb);
+	__u32 entries = xsk_cons_nb_avail(cons, nb);
 
 	if (entries > 0) {
 		/* Make sure we do not speculatively read the data before
@@ -153,7 +151,12 @@ static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons,
 	return entries;
 }
 
-static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, size_t nb)
+static inline void xsk_ring_cons__cancel(struct xsk_ring_cons *cons, __u32 nb)
+{
+	cons->cached_cons -= nb;
+}
+
+static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, __u32 nb)
 {
 	/* Make sure data has been read before indicating we are done
 	 * with the entries by updating the consumer pointer.
@@ -201,6 +204,11 @@ struct xsk_umem_config {
 	__u32 flags;
 };
 
+LIBBPF_API int xsk_setup_xdp_prog(int ifindex,
+				  int *xsks_map_fd);
+LIBBPF_API int xsk_socket__update_xskmap(struct xsk_socket *xsk,
+					 int xsks_map_fd);
+
 /* Flags for the libbpf_flags field. */
 #define XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD (1 << 0)