1 files changed, 395 insertions, 180 deletions

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 77dc24d58302..9aa19c89f758 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -57,7 +57,7 @@ struct btf {
 	 * representation is broken up into three independently allocated
 	 * memory regions to be able to modify them independently.
 	 * raw_data is nulled out at that point, but can be later allocated
-	 * and cached again if user calls btf__get_raw_data(), at which point
+	 * and cached again if user calls btf__raw_data(), at which point
 	 * raw_data will contain a contiguous copy of header, types, and
 	 * strings:
 	 *
@@ -189,12 +189,17 @@ int libbpf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_
 	return 0;
 }
 
+static void *btf_add_type_offs_mem(struct btf *btf, size_t add_cnt)
+{
+	return libbpf_add_mem((void **)&btf->type_offs, &btf->type_offs_cap, sizeof(__u32),
+			      btf->nr_types, BTF_MAX_NR_TYPES, add_cnt);
+}
+
 static int btf_add_type_idx_entry(struct btf *btf, __u32 type_off)
 {
 	__u32 *p;
 
-	p = libbpf_add_mem((void **)&btf->type_offs, &btf->type_offs_cap, sizeof(__u32),
-			   btf->nr_types, BTF_MAX_NR_TYPES, 1);
+	p = btf_add_type_offs_mem(btf, 1);
 	if (!p)
 		return -ENOMEM;
 
@@ -231,17 +236,23 @@ static int btf_parse_hdr(struct btf *btf)
 		}
 		btf_bswap_hdr(hdr);
 	} else if (hdr->magic != BTF_MAGIC) {
-		pr_debug("Invalid BTF magic:%x\n", hdr->magic);
+		pr_debug("Invalid BTF magic: %x\n", hdr->magic);
+		return -EINVAL;
+	}
+
+	if (btf->raw_size < hdr->hdr_len) {
+		pr_debug("BTF header len %u larger than data size %u\n",
+			 hdr->hdr_len, btf->raw_size);
 		return -EINVAL;
 	}
 
-	meta_left = btf->raw_size - sizeof(*hdr);
-	if (meta_left < hdr->str_off + hdr->str_len) {
-		pr_debug("Invalid BTF total size:%u\n", btf->raw_size);
+	meta_left = btf->raw_size - hdr->hdr_len;
+	if (meta_left < (long long)hdr->str_off + hdr->str_len) {
+		pr_debug("Invalid BTF total size: %u\n", btf->raw_size);
 		return -EINVAL;
 	}
 
-	if (hdr->type_off + hdr->type_len > hdr->str_off) {
+	if ((long long)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;
@@ -288,6 +299,7 @@ static int btf_type_size(const struct btf_type *t)
 	case BTF_KIND_TYPEDEF:
 	case BTF_KIND_FUNC:
 	case BTF_KIND_FLOAT:
+	case BTF_KIND_TYPE_TAG:
 		return base_size;
 	case BTF_KIND_INT:
 		return base_size + sizeof(__u32);
@@ -304,6 +316,8 @@ static int btf_type_size(const struct btf_type *t)
 		return base_size + sizeof(struct btf_var);
 	case BTF_KIND_DATASEC:
 		return base_size + vlen * sizeof(struct btf_var_secinfo);
+	case BTF_KIND_DECL_TAG:
+		return base_size + sizeof(struct btf_decl_tag);
 	default:
 		pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t));
 		return -EINVAL;
@@ -336,6 +350,7 @@ static int btf_bswap_type_rest(struct btf_type *t)
 	case BTF_KIND_TYPEDEF:
 	case BTF_KIND_FUNC:
 	case BTF_KIND_FLOAT:
+	case BTF_KIND_TYPE_TAG:
 		return 0;
 	case BTF_KIND_INT:
 		*(__u32 *)(t + 1) = bswap_32(*(__u32 *)(t + 1));
@@ -376,6 +391,9 @@ static int btf_bswap_type_rest(struct btf_type *t)
 			v->size = bswap_32(v->size);
 		}
 		return 0;
+	case BTF_KIND_DECL_TAG:
+		btf_decl_tag(t)->component_idx = bswap_32(btf_decl_tag(t)->component_idx);
+		return 0;
 	default:
 		pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t));
 		return -EINVAL;
@@ -425,13 +443,18 @@ __u32 btf__get_nr_types(const struct btf *btf)
 	return btf->start_id + btf->nr_types - 1;
 }
 
+__u32 btf__type_cnt(const struct btf *btf)
+{
+	return btf->start_id + btf->nr_types;
+}
+
 const struct btf *btf__base_btf(const struct btf *btf)
 {
 	return btf->base_btf;
 }
 
 /* internal helper returning non-const pointer to a type */
-struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id)
+struct btf_type *btf_type_by_id(const struct btf *btf, __u32 type_id)
 {
 	if (type_id == 0)
 		return &btf_void;
@@ -456,8 +479,8 @@ static int determine_ptr_size(const struct btf *btf)
 	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++) {
+	n = btf__type_cnt(btf);
+	for (i = 1; i < n; i++) {
 		t = btf__type_by_id(btf, i);
 		if (!btf_is_int(t))
 			continue;
@@ -517,9 +540,9 @@ int btf__set_pointer_size(struct btf *btf, size_t ptr_sz)
 
 static bool is_host_big_endian(void)
 {
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	return false;
-#elif __BYTE_ORDER == __BIG_ENDIAN
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 	return true;
 #else
 # error "Unrecognized __BYTE_ORDER__"
@@ -586,6 +609,8 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 		case BTF_KIND_CONST:
 		case BTF_KIND_RESTRICT:
 		case BTF_KIND_VAR:
+		case BTF_KIND_DECL_TAG:
+		case BTF_KIND_TYPE_TAG:
 			type_id = t->type;
 			break;
 		case BTF_KIND_ARRAY:
@@ -627,6 +652,7 @@ int btf__align_of(const struct btf *btf, __u32 id)
 	case BTF_KIND_VOLATILE:
 	case BTF_KIND_CONST:
 	case BTF_KIND_RESTRICT:
+	case BTF_KIND_TYPE_TAG:
 		return btf__align_of(btf, t->type);
 	case BTF_KIND_ARRAY:
 		return btf__align_of(btf, btf_array(t)->type);
@@ -673,12 +699,12 @@ 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, nr_types = btf__get_nr_types(btf);
+	__u32 i, nr_types = btf__type_cnt(btf);
 
 	if (!strcmp(type_name, "void"))
 		return 0;
 
-	for (i = 1; i <= 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);
 
@@ -689,15 +715,15 @@ __s32 btf__find_by_name(const struct btf *btf, const char *type_name)
 	return libbpf_err(-ENOENT);
 }
 
-__s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
-			     __u32 kind)
+static __s32 btf_find_by_name_kind(const struct btf *btf, int start_id,
+				   const char *type_name, __u32 kind)
 {
-	__u32 i, nr_types = btf__get_nr_types(btf);
+	__u32 i, nr_types = btf__type_cnt(btf);
 
 	if (kind == BTF_KIND_UNKN || !strcmp(type_name, "void"))
 		return 0;
 
-	for (i = 1; i <= nr_types; i++) {
+	for (i = start_id; i < nr_types; i++) {
 		const struct btf_type *t = btf__type_by_id(btf, i);
 		const char *name;
 
@@ -711,6 +737,18 @@ __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
 	return libbpf_err(-ENOENT);
 }
 
+__s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name,
+				 __u32 kind)
+{
+	return btf_find_by_name_kind(btf, btf->start_id, type_name, kind);
+}
+
+__s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
+			     __u32 kind)
+{
+	return btf_find_by_name_kind(btf, 1, type_name, kind);
+}
+
 static bool btf_is_modifiable(const struct btf *btf)
 {
 	return (void *)btf->hdr != btf->raw_data;
@@ -758,7 +796,7 @@ static struct btf *btf_new_empty(struct btf *base_btf)
 
 	if (base_btf) {
 		btf->base_btf = base_btf;
-		btf->start_id = btf__get_nr_types(base_btf) + 1;
+		btf->start_id = btf__type_cnt(base_btf);
 		btf->start_str_off = base_btf->hdr->str_len;
 	}
 
@@ -808,7 +846,7 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf)
 
 	if (base_btf) {
 		btf->base_btf = base_btf;
-		btf->start_id = btf__get_nr_types(base_btf) + 1;
+		btf->start_id = btf__type_cnt(base_btf);
 		btf->start_str_off = base_btf->hdr->str_len;
 	}
 
@@ -863,7 +901,7 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
 		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
 	}
 
-	fd = open(path, O_RDONLY);
+	fd = open(path, O_RDONLY | O_CLOEXEC);
 	if (fd < 0) {
 		err = -errno;
 		pr_warn("failed to open %s: %s\n", path, strerror(errno));
@@ -1084,149 +1122,88 @@ struct btf *btf__parse_split(const char *path, struct btf *base_btf)
 	return libbpf_ptr(btf_parse(path, base_btf, NULL));
 }
 
-static int compare_vsi_off(const void *_a, const void *_b)
-{
-	const struct btf_var_secinfo *a = _a;
-	const struct btf_var_secinfo *b = _b;
-
-	return a->offset - b->offset;
-}
-
-static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf,
-			     struct btf_type *t)
-{
-	__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;
-	const struct btf_var *var;
-	int ret;
-
-	if (!name) {
-		pr_debug("No name found in string section for DATASEC kind.\n");
-		return -ENOENT;
-	}
-
-	/* .extern datasec size and var offsets were set correctly during
-	 * extern collection step, so just skip straight to sorting variables
-	 */
-	if (t->size)
-		goto sort_vars;
-
-	ret = bpf_object__section_size(obj, name, &size);
-	if (ret || !size || (t->size && t->size != size)) {
-		pr_debug("Invalid size for section %s: %u bytes\n", name, size);
-		return -ENOENT;
-	}
-
-	t->size = size;
-
-	for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) {
-		t_var = btf__type_by_id(btf, vsi->type);
-		var = btf_var(t_var);
-
-		if (!btf_is_var(t_var)) {
-			pr_debug("Non-VAR type seen in section %s\n", name);
-			return -EINVAL;
-		}
-
-		if (var->linkage == BTF_VAR_STATIC)
-			continue;
-
-		name = btf__name_by_offset(btf, t_var->name_off);
-		if (!name) {
-			pr_debug("No name found in string section for VAR kind\n");
-			return -ENOENT;
-		}
-
-		ret = bpf_object__variable_offset(obj, name, &off);
-		if (ret) {
-			pr_debug("No offset found in symbol table for VAR %s\n",
-				 name);
-			return -ENOENT;
-		}
-
-		vsi->offset = off;
-	}
-
-sort_vars:
-	qsort(btf_var_secinfos(t), vars, sizeof(*vsi), compare_vsi_off);
-	return 0;
-}
-
-int btf__finalize_data(struct bpf_object *obj, struct btf *btf)
-{
-	int err = 0;
-	__u32 i;
-
-	for (i = 1; i <= btf->nr_types; i++) {
-		struct btf_type *t = btf_type_by_id(btf, i);
-
-		/* Loader needs to fix up some of the things compiler
-		 * couldn't get its hands on while emitting BTF. This
-		 * is section size and global variable offset. We use
-		 * the info from the ELF itself for this purpose.
-		 */
-		if (btf_is_datasec(t)) {
-			err = btf_fixup_datasec(obj, btf, t);
-			if (err)
-				break;
-		}
-	}
-
-	return libbpf_err(err);
-}
-
 static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian);
 
-int btf__load_into_kernel(struct btf *btf)
+int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level)
 {
-	__u32 log_buf_size = 0, raw_size;
-	char *log_buf = NULL;
+	LIBBPF_OPTS(bpf_btf_load_opts, opts);
+	__u32 buf_sz = 0, raw_size;
+	char *buf = NULL, *tmp;
 	void *raw_data;
 	int err = 0;
 
 	if (btf->fd >= 0)
 		return libbpf_err(-EEXIST);
+	if (log_sz && !log_buf)
+		return libbpf_err(-EINVAL);
 
-retry_load:
-	if (log_buf_size) {
-		log_buf = malloc(log_buf_size);
-		if (!log_buf)
-			return libbpf_err(-ENOMEM);
-
-		*log_buf = 0;
-	}
-
+	/* cache native raw data representation */
 	raw_data = btf_get_raw_data(btf, &raw_size, false);
 	if (!raw_data) {
 		err = -ENOMEM;
 		goto done;
 	}
-	/* cache native raw data representation */
 	btf->raw_size = raw_size;
 	btf->raw_data = raw_data;
 
-	btf->fd = bpf_load_btf(raw_data, raw_size, log_buf, log_buf_size, false);
+retry_load:
+	/* if log_level is 0, we won't provide log_buf/log_size to the kernel,
+	 * initially. Only if BTF loading fails, we bump log_level to 1 and
+	 * retry, using either auto-allocated or custom log_buf. This way
+	 * non-NULL custom log_buf provides a buffer just in case, but hopes
+	 * for successful load and no need for log_buf.
+	 */
+	if (log_level) {
+		/* if caller didn't provide custom log_buf, we'll keep
+		 * allocating our own progressively bigger buffers for BTF
+		 * verification log
+		 */
+		if (!log_buf) {
+			buf_sz = max((__u32)BPF_LOG_BUF_SIZE, buf_sz * 2);
+			tmp = realloc(buf, buf_sz);
+			if (!tmp) {
+				err = -ENOMEM;
+				goto done;
+			}
+			buf = tmp;
+			buf[0] = '\0';
+		}
+
+		opts.log_buf = log_buf ? log_buf : buf;
+		opts.log_size = log_buf ? log_sz : buf_sz;
+		opts.log_level = log_level;
+	}
+
+	btf->fd = bpf_btf_load(raw_data, raw_size, &opts);
 	if (btf->fd < 0) {
-		if (!log_buf || errno == ENOSPC) {
-			log_buf_size = max((__u32)BPF_LOG_BUF_SIZE,
-					   log_buf_size << 1);
-			free(log_buf);
+		/* time to turn on verbose mode and try again */
+		if (log_level == 0) {
+			log_level = 1;
 			goto retry_load;
 		}
+		/* only retry if caller didn't provide custom log_buf, but
+		 * make sure we can never overflow buf_sz
+		 */
+		if (!log_buf && errno == ENOSPC && buf_sz <= UINT_MAX / 2)
+			goto retry_load;
 
 		err = -errno;
-		pr_warn("Error loading BTF: %s(%d)\n", strerror(errno), errno);
-		if (*log_buf)
-			pr_warn("%s\n", log_buf);
-		goto done;
+		pr_warn("BTF loading error: %d\n", err);
+		/* don't print out contents of custom log_buf */
+		if (!log_buf && buf[0])
+			pr_warn("-- BEGIN BTF LOAD LOG ---\n%s\n-- END BTF LOAD LOG --\n", buf);
 	}
 
 done:
-	free(log_buf);
+	free(buf);
 	return libbpf_err(err);
 }
+
+int btf__load_into_kernel(struct btf *btf)
+{
+	return btf_load_into_kernel(btf, NULL, 0, 0);
+}
+
 int btf__load(struct btf *) __attribute__((alias("btf__load_into_kernel")));
 
 int btf__fd(const struct btf *btf)
@@ -1294,7 +1271,7 @@ err_out:
 	return NULL;
 }
 
-const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size)
+const void *btf__raw_data(const struct btf *btf_ro, __u32 *size)
 {
 	struct btf *btf = (struct btf *)btf_ro;
 	__u32 data_sz;
@@ -1302,7 +1279,7 @@ const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size)
 
 	data = btf_get_raw_data(btf, &data_sz, btf->swapped_endian);
 	if (!data)
-		return errno = -ENOMEM, NULL;
+		return errno = ENOMEM, NULL;
 
 	btf->raw_size = data_sz;
 	if (btf->swapped_endian)
@@ -1313,6 +1290,9 @@ const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size)
 	return data;
 }
 
+__attribute__((alias("btf__raw_data")))
+const void *btf__get_raw_data(const struct btf *btf, __u32 *size);
+
 const char *btf__str_by_offset(const struct btf *btf, __u32 offset)
 {
 	if (offset < btf->start_str_off)
@@ -1685,6 +1665,111 @@ int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_t
 	return btf_commit_type(btf, sz);
 }
 
+static int btf_rewrite_type_ids(__u32 *type_id, void *ctx)
+{
+	struct btf *btf = ctx;
+
+	if (!*type_id) /* nothing to do for VOID references */
+		return 0;
+
+	/* we haven't updated btf's type count yet, so
+	 * btf->start_id + btf->nr_types - 1 is the type ID offset we should
+	 * add to all newly added BTF types
+	 */
+	*type_id += btf->start_id + btf->nr_types - 1;
+	return 0;
+}
+
+int btf__add_btf(struct btf *btf, const struct btf *src_btf)
+{
+	struct btf_pipe p = { .src = src_btf, .dst = btf };
+	int data_sz, sz, cnt, i, err, old_strs_len;
+	__u32 *off;
+	void *t;
+
+	/* appending split BTF isn't supported yet */
+	if (src_btf->base_btf)
+		return libbpf_err(-ENOTSUP);
+
+	/* deconstruct BTF, if necessary, and invalidate raw_data */
+	if (btf_ensure_modifiable(btf))
+		return libbpf_err(-ENOMEM);
+
+	/* remember original strings section size if we have to roll back
+	 * partial strings section changes
+	 */
+	old_strs_len = btf->hdr->str_len;
+
+	data_sz = src_btf->hdr->type_len;
+	cnt = btf__type_cnt(src_btf) - 1;
+
+	/* pre-allocate enough memory for new types */
+	t = btf_add_type_mem(btf, data_sz);
+	if (!t)
+		return libbpf_err(-ENOMEM);
+
+	/* pre-allocate enough memory for type offset index for new types */
+	off = btf_add_type_offs_mem(btf, cnt);
+	if (!off)
+		return libbpf_err(-ENOMEM);
+
+	/* bulk copy types data for all types from src_btf */
+	memcpy(t, src_btf->types_data, data_sz);
+
+	for (i = 0; i < cnt; i++) {
+		sz = btf_type_size(t);
+		if (sz < 0) {
+			/* unlikely, has to be corrupted src_btf */
+			err = sz;
+			goto err_out;
+		}
+
+		/* fill out type ID to type offset mapping for lookups by type ID */
+		*off = t - btf->types_data;
+
+		/* add, dedup, and remap strings referenced by this BTF type */
+		err = btf_type_visit_str_offs(t, btf_rewrite_str, &p);
+		if (err)
+			goto err_out;
+
+		/* remap all type IDs referenced from this BTF type */
+		err = btf_type_visit_type_ids(t, btf_rewrite_type_ids, btf);
+		if (err)
+			goto err_out;
+
+		/* go to next type data and type offset index entry */
+		t += sz;
+		off++;
+	}
+
+	/* Up until now any of the copied type data was effectively invisible,
+	 * so if we exited early before this point due to error, BTF would be
+	 * effectively unmodified. There would be extra internal memory
+	 * pre-allocated, but it would not be available for querying.  But now
+	 * that we've copied and rewritten all the data successfully, we can
+	 * update type count and various internal offsets and sizes to
+	 * "commit" the changes and made them visible to the outside world.
+	 */
+	btf->hdr->type_len += data_sz;
+	btf->hdr->str_off += data_sz;
+	btf->nr_types += cnt;
+
+	/* return type ID of the first added BTF type */
+	return btf->start_id + btf->nr_types - cnt;
+err_out:
+	/* zero out preallocated memory as if it was just allocated with
+	 * libbpf_add_mem()
+	 */
+	memset(btf->types_data + btf->hdr->type_len, 0, data_sz);
+	memset(btf->strs_data + old_strs_len, 0, btf->hdr->str_len - old_strs_len);
+
+	/* and now restore original strings section size; types data size
+	 * wasn't modified, so doesn't need restoring, see big comment above */
+	btf->hdr->str_len = old_strs_len;
+
+	return libbpf_err(err);
+}
+
 /*
  * Append new BTF_KIND_INT type with:
  *   - *name* - non-empty, non-NULL type name;
@@ -1933,7 +2018,7 @@ int btf__add_union(struct btf *btf, const char *name, __u32 byte_sz)
 
 static struct btf_type *btf_last_type(struct btf *btf)
 {
-	return btf_type_by_id(btf, btf__get_nr_types(btf));
+	return btf_type_by_id(btf, btf__type_cnt(btf) - 1);
 }
 
 /*
@@ -2187,6 +2272,22 @@ int btf__add_restrict(struct btf *btf, int ref_type_id)
 }
 
 /*
+ * Append new BTF_KIND_TYPE_TAG type with:
+ *   - *value*, non-empty/non-NULL tag value;
+ *   - *ref_type_id* - referenced type ID, it might not exist yet;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id)
+{
+	if (!value|| !value[0])
+		return libbpf_err(-EINVAL);
+
+	return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id);
+}
+
+/*
  * Append new BTF_KIND_FUNC type with:
  *   - *name*, non-empty/non-NULL name;
  *   - *proto_type_id* - FUNC_PROTO's type ID, it might not exist yet;
@@ -2440,6 +2541,48 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __
 	return 0;
 }
 
+/*
+ * Append new BTF_KIND_DECL_TAG type with:
+ *   - *value* - non-empty/non-NULL string;
+ *   - *ref_type_id* - referenced type ID, it might not exist yet;
+ *   - *component_idx* - -1 for tagging reference type, otherwise struct/union
+ *     member or function argument index;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id,
+		 int component_idx)
+{
+	struct btf_type *t;
+	int sz, value_off;
+
+	if (!value || !value[0] || component_idx < -1)
+		return libbpf_err(-EINVAL);
+
+	if (validate_type_id(ref_type_id))
+		return libbpf_err(-EINVAL);
+
+	if (btf_ensure_modifiable(btf))
+		return libbpf_err(-ENOMEM);
+
+	sz = sizeof(struct btf_type) + sizeof(struct btf_decl_tag);
+	t = btf_add_type_mem(btf, sz);
+	if (!t)
+		return libbpf_err(-ENOMEM);
+
+	value_off = btf__add_str(btf, value);
+	if (value_off < 0)
+		return value_off;
+
+	t->name_off = value_off;
+	t->info = btf_type_info(BTF_KIND_DECL_TAG, 0, false);
+	t->type = ref_type_id;
+	btf_decl_tag(t)->component_idx = component_idx;
+
+	return btf_commit_type(btf, sz);
+}
+
 struct btf_ext_sec_setup_param {
 	__u32 off;
 	__u32 len;
@@ -2620,15 +2763,11 @@ void btf_ext__free(struct btf_ext *btf_ext)
 	free(btf_ext);
 }
 
-struct btf_ext *btf_ext__new(__u8 *data, __u32 size)
+struct btf_ext *btf_ext__new(const __u8 *data, __u32 size)
 {
 	struct btf_ext *btf_ext;
 	int err;
 
-	err = btf_ext_parse_hdr(data, size);
-	if (err)
-		return libbpf_err_ptr(err);
-
 	btf_ext = calloc(1, sizeof(struct btf_ext));
 	if (!btf_ext)
 		return libbpf_err_ptr(-ENOMEM);
@@ -2641,6 +2780,10 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size)
 	}
 	memcpy(btf_ext->data, data, size);
 
+	err = btf_ext_parse_hdr(btf_ext->data, size);
+	if (err)
+		goto done;
+
 	if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, line_info_len)) {
 		err = -EINVAL;
 		goto done;
@@ -2755,8 +2898,7 @@ __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext)
 
 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 struct btf_dedup *btf_dedup_new(struct btf *btf, 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);
@@ -2903,19 +3045,26 @@ static int btf_dedup_remap_types(struct btf_dedup *d);
  * deduplicating structs/unions is described in greater details in comments for
  * `btf_dedup_is_equiv` function.
  */
-int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
-	       const struct btf_dedup_opts *opts)
+
+DEFAULT_VERSION(btf__dedup_v0_6_0, btf__dedup, LIBBPF_0.6.0)
+int btf__dedup_v0_6_0(struct btf *btf, const struct btf_dedup_opts *opts)
 {
-	struct btf_dedup *d = btf_dedup_new(btf, btf_ext, opts);
+	struct btf_dedup *d;
 	int err;
 
+	if (!OPTS_VALID(opts, btf_dedup_opts))
+		return libbpf_err(-EINVAL);
+
+	d = btf_dedup_new(btf, opts);
 	if (IS_ERR(d)) {
 		pr_debug("btf_dedup_new failed: %ld", PTR_ERR(d));
 		return libbpf_err(-EINVAL);
 	}
 
-	if (btf_ensure_modifiable(btf))
-		return libbpf_err(-ENOMEM);
+	if (btf_ensure_modifiable(btf)) {
+		err = -ENOMEM;
+		goto done;
+	}
 
 	err = btf_dedup_prep(d);
 	if (err) {
@@ -2958,6 +3107,19 @@ done:
 	return libbpf_err(err);
 }
 
+COMPAT_VERSION(btf__dedup_deprecated, btf__dedup, LIBBPF_0.0.2)
+int btf__dedup_deprecated(struct btf *btf, struct btf_ext *btf_ext, const void *unused_opts)
+{
+	LIBBPF_OPTS(btf_dedup_opts, opts, .btf_ext = btf_ext);
+
+	if (unused_opts) {
+		pr_warn("please use new version of btf__dedup() that supports options\n");
+		return libbpf_err(-ENOTSUP);
+	}
+
+	return btf__dedup(btf, &opts);
+}
+
 #define BTF_UNPROCESSED_ID ((__u32)-1)
 #define BTF_IN_PROGRESS_ID ((__u32)-2)
 
@@ -3070,8 +3232,7 @@ static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx)
 	return k1 == k2;
 }
 
-static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
-				       const struct btf_dedup_opts *opts)
+static struct btf_dedup *btf_dedup_new(struct btf *btf, const struct btf_dedup_opts *opts)
 {
 	struct btf_dedup *d = calloc(1, sizeof(struct btf_dedup));
 	hashmap_hash_fn hash_fn = btf_dedup_identity_hash_fn;
@@ -3080,13 +3241,11 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
 	if (!d)
 		return ERR_PTR(-ENOMEM);
 
-	d->opts.dont_resolve_fwds = opts && opts->dont_resolve_fwds;
-	/* dedup_table_size is now used only to force collisions in tests */
-	if (opts && opts->dedup_table_size == 1)
+	if (OPTS_GET(opts, force_collisions, false))
 		hash_fn = btf_dedup_collision_hash_fn;
 
 	d->btf = btf;
-	d->btf_ext = btf_ext;
+	d->btf_ext = OPTS_GET(opts, btf_ext, NULL);
 
 	d->dedup_table = hashmap__new(hash_fn, btf_dedup_equal_fn, NULL);
 	if (IS_ERR(d->dedup_table)) {
@@ -3095,7 +3254,7 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
 		goto done;
 	}
 
-	type_cnt = btf__get_nr_types(btf) + 1;
+	type_cnt = btf__type_cnt(btf);
 	d->map = malloc(sizeof(__u32) * type_cnt);
 	if (!d->map) {
 		err = -ENOMEM;
@@ -3256,8 +3415,8 @@ static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2)
 	       t1->size == t2->size;
 }
 
-/* Calculate type signature hash of INT. */
-static long btf_hash_int(struct btf_type *t)
+/* Calculate type signature hash of INT or TAG. */
+static long btf_hash_int_decl_tag(struct btf_type *t)
 {
 	__u32 info = *(__u32 *)(t + 1);
 	long h;
@@ -3267,8 +3426,8 @@ static long btf_hash_int(struct btf_type *t)
 	return h;
 }
 
-/* Check structural equality of two INTs. */
-static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2)
+/* Check structural equality of two INTs or TAGs. */
+static bool btf_equal_int_tag(struct btf_type *t1, struct btf_type *t2)
 {
 	__u32 info1, info2;
 
@@ -3350,8 +3509,8 @@ static long btf_hash_struct(struct btf_type *t)
 }
 
 /*
- * Check structural compatibility of two FUNC_PROTOs, ignoring referenced type
- * IDs. This check is performed during type graph equivalence check and
+ * Check structural compatibility of two STRUCTs/UNIONs, ignoring referenced
+ * type IDs. This check is performed during type graph equivalence check and
  * referenced types equivalence is checked separately.
  */
 static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2)
@@ -3532,10 +3691,12 @@ static int btf_dedup_prep(struct btf_dedup *d)
 		case BTF_KIND_TYPEDEF:
 		case BTF_KIND_FUNC:
 		case BTF_KIND_FLOAT:
+		case BTF_KIND_TYPE_TAG:
 			h = btf_hash_common(t);
 			break;
 		case BTF_KIND_INT:
-			h = btf_hash_int(t);
+		case BTF_KIND_DECL_TAG:
+			h = btf_hash_int_decl_tag(t);
 			break;
 		case BTF_KIND_ENUM:
 			h = btf_hash_enum(t);
@@ -3590,14 +3751,16 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 	case BTF_KIND_FUNC_PROTO:
 	case BTF_KIND_VAR:
 	case BTF_KIND_DATASEC:
+	case BTF_KIND_DECL_TAG:
+	case BTF_KIND_TYPE_TAG:
 		return 0;
 
 	case BTF_KIND_INT:
-		h = btf_hash_int(t);
+		h = btf_hash_int_decl_tag(t);
 		for_each_dedup_cand(d, hash_entry, h) {
 			cand_id = (__u32)(long)hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
-			if (btf_equal_int(t, cand)) {
+			if (btf_equal_int_tag(t, cand)) {
 				new_id = cand_id;
 				break;
 			}
@@ -3613,8 +3776,6 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 				new_id = cand_id;
 				break;
 			}
-			if (d->opts.dont_resolve_fwds)
-				continue;
 			if (btf_compat_enum(t, cand)) {
 				if (btf_is_enum_fwd(t)) {
 					/* resolve fwd to full enum */
@@ -3722,6 +3883,31 @@ static int btf_dedup_identical_arrays(struct btf_dedup *d, __u32 id1, __u32 id2)
 	return btf_equal_array(t1, t2);
 }
 
+/* Check if given two types are identical STRUCT/UNION definitions */
+static bool btf_dedup_identical_structs(struct btf_dedup *d, __u32 id1, __u32 id2)
+{
+	const struct btf_member *m1, *m2;
+	struct btf_type *t1, *t2;
+	int n, i;
+
+	t1 = btf_type_by_id(d->btf, id1);
+	t2 = btf_type_by_id(d->btf, id2);
+
+	if (!btf_is_composite(t1) || btf_kind(t1) != btf_kind(t2))
+		return false;
+
+	if (!btf_shallow_equal_struct(t1, t2))
+		return false;
+
+	m1 = btf_members(t1);
+	m2 = btf_members(t2);
+	for (i = 0, n = btf_vlen(t1); i < n; i++, m1++, m2++) {
+		if (m1->type != m2->type)
+			return false;
+	}
+	return true;
+}
+
 /*
  * 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
@@ -3833,6 +4019,8 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 
 	hypot_type_id = d->hypot_map[canon_id];
 	if (hypot_type_id <= BTF_MAX_NR_TYPES) {
+		if (hypot_type_id == cand_id)
+			return 1;
 		/* 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
@@ -3841,8 +4029,18 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 		 * 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_identical_arrays(d, hypot_type_id, cand_id))
+			return 1;
+		/* It turns out that similar situation can happen with
+		 * struct/union sometimes, sigh... Handle the case where
+		 * structs/unions are exactly the same, down to the referenced
+		 * type IDs. Anything more complicated (e.g., if referenced
+		 * types are different, but equivalent) is *way more*
+		 * complicated and requires a many-to-many equivalence mapping.
+		 */
+		if (btf_dedup_identical_structs(d, hypot_type_id, cand_id))
+			return 1;
+		return 0;
 	}
 
 	if (btf_dedup_hypot_map_add(d, canon_id, cand_id))
@@ -3857,8 +4055,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 		return 0;
 
 	/* FWD <--> STRUCT/UNION equivalence check, if enabled */
-	if (!d->opts.dont_resolve_fwds
-	    && (cand_kind == BTF_KIND_FWD || canon_kind == BTF_KIND_FWD)
+	if ((cand_kind == BTF_KIND_FWD || canon_kind == BTF_KIND_FWD)
 	    && cand_kind != canon_kind) {
 		__u16 real_kind;
 		__u16 fwd_kind;
@@ -3881,13 +4078,10 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 
 	switch (cand_kind) {
 	case BTF_KIND_INT:
-		return btf_equal_int(cand_type, canon_type);
+		return btf_equal_int_tag(cand_type, canon_type);
 
 	case BTF_KIND_ENUM:
-		if (d->opts.dont_resolve_fwds)
-			return btf_equal_enum(cand_type, canon_type);
-		else
-			return btf_compat_enum(cand_type, canon_type);
+		return btf_compat_enum(cand_type, canon_type);
 
 	case BTF_KIND_FWD:
 	case BTF_KIND_FLOAT:
@@ -3899,6 +4093,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 	case BTF_KIND_PTR:
 	case BTF_KIND_TYPEDEF:
 	case BTF_KIND_FUNC:
+	case BTF_KIND_TYPE_TAG:
 		if (cand_type->info != canon_type->info)
 			return 0;
 		return btf_dedup_is_equiv(d, cand_type->type, canon_type->type);
@@ -4194,6 +4389,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 	case BTF_KIND_PTR:
 	case BTF_KIND_TYPEDEF:
 	case BTF_KIND_FUNC:
+	case BTF_KIND_TYPE_TAG:
 		ref_type_id = btf_dedup_ref_type(d, t->type);
 		if (ref_type_id < 0)
 			return ref_type_id;
@@ -4210,6 +4406,23 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 		}
 		break;
 
+	case BTF_KIND_DECL_TAG:
+		ref_type_id = btf_dedup_ref_type(d, t->type);
+		if (ref_type_id < 0)
+			return ref_type_id;
+		t->type = ref_type_id;
+
+		h = btf_hash_int_decl_tag(t);
+		for_each_dedup_cand(d, hash_entry, h) {
+			cand_id = (__u32)(long)hash_entry->value;
+			cand = btf_type_by_id(d->btf, cand_id);
+			if (btf_equal_int_tag(t, cand)) {
+				new_id = cand_id;
+				break;
+			}
+		}
+		break;
+
 	case BTF_KIND_ARRAY: {
 		struct btf_array *info = btf_array(t);
 
@@ -4482,6 +4695,8 @@ int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ct
 	case BTF_KIND_TYPEDEF:
 	case BTF_KIND_FUNC:
 	case BTF_KIND_VAR:
+	case BTF_KIND_DECL_TAG:
+	case BTF_KIND_TYPE_TAG:
 		return visit(&t->type, ctx);
 
 	case BTF_KIND_ARRAY: {