Merge branch 'libbpf: split BTF support'

Andrii Nakryiko says:

====================
This patch set adds support for generating and deduplicating split BTF. This
is an enhancement to the BTF, which allows to designate one BTF as the "base
BTF" (e.g., vmlinux BTF), and one or more other BTFs as "split BTF" (e.g.,
kernel module BTF), which are building upon and extending base BTF with extra
types and strings.

Once loaded, split BTF appears as a single unified BTF superset of base BTF,
with continuous and transparent numbering scheme. This allows all the existing
users of BTF to work correctly and stay agnostic to the base/split BTFs
composition.  The only difference is in how to instantiate split BTF: it
requires base BTF to be alread instantiated and passed to btf__new_xxx_split()
or btf__parse_xxx_split() "constructors" explicitly.

This split approach is necessary if we are to have a reasonably-sized kernel
module BTFs. By deduping each kernel module's BTF individually, resulting
module BTFs contain copies of a lot of kernel types that are already present
in vmlinux BTF. Even those single copies result in a big BTF size bloat. On my
kernel configuration with 700 modules built, non-split BTF approach results in
115MBs of BTFs across all modules. With split BTF deduplication approach,
total size is down to 5.2MBs total, which is on part with vmlinux BTF (at
around 4MBs). This seems reasonable and practical. As to why we'd need kernel
module BTFs, that should be pretty obvious to anyone using BPF at this point,
as it allows all the BTF-powered features to be used with kernel modules:
tp_btf, fentry/fexit/fmod_ret, lsm, bpf_iter, etc.

This patch set is a pre-requisite to adding split BTF support to pahole, which
is a prerequisite to integrating split BTF into the Linux kernel build setup
to generate BTF for kernel modules. The latter will come as a follow-up patch
series once this series makes it to the libbpf and pahole makes use of it.

Patch #4 introduces necessary basic support for split BTF into libbpf APIs.
Patch #8 implements minimal changes to BTF dedup algorithm to allow
deduplicating split BTFs. Patch #11 adds extra -B flag to bpftool to allow to
specify the path to base BTF for cases when one wants to dump or inspect split
BTF. All the rest are refactorings, clean ups, bug fixes and selftests.

v1->v2:
  - addressed Song's feedback.
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

tools/bpf/bpftool/btf.c

@@ -358,8 +358,12 @@ static int dump_btf_raw(const struct btf *btf,
 		}
 	} else {
 		int cnt = btf__get_nr_types(btf);
+		int start_id = 1;
 
-		for (i = 1; i <= cnt; i++) {
+		if (base_btf)
+			start_id = btf__get_nr_types(base_btf) + 1;
+
+		for (i = start_id; i <= cnt; i++) {
 			t = btf__type_by_id(btf, i);
 			dump_btf_type(btf, i, t);
 		}
@@ -438,7 +442,6 @@ static int do_dump(int argc, char **argv)
 		return -1;
 	}
 	src = GET_ARG();
-
 	if (is_prefix(src, "map")) {
 		struct bpf_map_info info = {};
 		__u32 len = sizeof(info);
@@ -499,7 +502,7 @@ static int do_dump(int argc, char **argv)
 		}
 		NEXT_ARG();
 	} else if (is_prefix(src, "file")) {
-		btf = btf__parse(*argv, NULL);
+		btf = btf__parse_split(*argv, base_btf);
 		if (IS_ERR(btf)) {
 			err = -PTR_ERR(btf);
 			btf = NULL;

tools/bpf/bpftool/main.c

@@ -11,6 +11,7 @@
 
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
+#include <bpf/btf.h>
 
 #include "main.h"
 
@@ -28,6 +29,7 @@ bool show_pinned;
 bool block_mount;
 bool verifier_logs;
 bool relaxed_maps;
+struct btf *base_btf;
 struct pinned_obj_table prog_table;
 struct pinned_obj_table map_table;
 struct pinned_obj_table link_table;
@@ -391,6 +393,7 @@ int main(int argc, char **argv)
 		{ "mapcompat",	no_argument,	NULL,	'm' },
 		{ "nomount",	no_argument,	NULL,	'n' },
 		{ "debug",	no_argument,	NULL,	'd' },
+		{ "base-btf",	required_argument, NULL, 'B' },
 		{ 0 }
 	};
 	int opt, ret;
@@ -407,7 +410,7 @@ int main(int argc, char **argv)
 	hash_init(link_table.table);
 
 	opterr = 0;
-	while ((opt = getopt_long(argc, argv, "Vhpjfmnd",
+	while ((opt = getopt_long(argc, argv, "VhpjfmndB:",
 				  options, NULL)) >= 0) {
 		switch (opt) {
 		case 'V':
@@ -441,6 +444,15 @@ int main(int argc, char **argv)
 			libbpf_set_print(print_all_levels);
 			verifier_logs = true;
 			break;
+		case 'B':
+			base_btf = btf__parse(optarg, NULL);
+			if (libbpf_get_error(base_btf)) {
+				p_err("failed to parse base BTF at '%s': %ld\n",
+				      optarg, libbpf_get_error(base_btf));
+				base_btf = NULL;
+				return -1;
+			}
+			break;
 		default:
 			p_err("unrecognized option '%s'", argv[optind - 1]);
 			if (json_output)
@@ -465,6 +477,7 @@ int main(int argc, char **argv)
 		delete_pinned_obj_table(&map_table);
 		delete_pinned_obj_table(&link_table);
 	}
+	btf__free(base_btf);
 
 	return ret;
 }

tools/bpf/bpftool/main.h

@@ -90,6 +90,7 @@ extern bool show_pids;
 extern bool block_mount;
 extern bool verifier_logs;
 extern bool relaxed_maps;
+extern struct btf *base_btf;
 extern struct pinned_obj_table prog_table;
 extern struct pinned_obj_table map_table;
 extern struct pinned_obj_table link_table;

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);
-		return -EINVAL;
-	}
-
-	if (meta_left < hdr->str_off) {
-		pr_debug("Invalid BTF string section offset:%u\n", hdr->str_off);
+	if (meta_left < hdr->str_off + hdr->str_len) {
+		pr_debug("Invalid BTF total size:%u\n", btf->raw_size);
 		return -EINVAL;
 	}
 
-	if (hdr->type_off >= hdr->str_off) {
-		pr_debug("BTF type section offset >= string section offset. No type?\n");
+	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 & 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 +429,7 @@ 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;
 }
 
 /* internal helper returning non-const pointer to a type */
@@ -417,13 +437,14 @@ 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 +453,13 @@ 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;
@@ -717,7 +742,7 @@ 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 +750,21 @@ 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 +778,22 @@ 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 +802,16 @@ 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 +844,13 @@ struct btf *btf__new(const void *data, __u32 size)
 	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 +928,7 @@ 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 +973,17 @@ struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext)
 	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 +1037,7 @@ 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 +1046,38 @@ struct btf *btf__parse_raw(const char *path)
 	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 +1261,8 @@ 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 +1305,10 @@ 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;
 }
@@ -1363,17 +1455,19 @@ 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 +1512,9 @@ 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 +1545,10 @@ 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 +1580,14 @@ 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 +1602,7 @@ 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 +1618,14 @@ 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 +1652,12 @@ 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 +1676,20 @@ 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 +1702,7 @@ 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 +1736,7 @@ 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 +1754,7 @@ 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 +1777,7 @@ 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 +1805,7 @@ 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 +1827,14 @@ 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 +1857,7 @@ 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 +1895,11 @@ 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 +1921,7 @@ 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 +1956,7 @@ 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 +1981,7 @@ 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 +2006,7 @@ 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 +2026,7 @@ 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 +2053,7 @@ 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 +2193,7 @@ 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 +2213,7 @@ 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 +2236,7 @@ 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 +2259,7 @@ 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 +2281,7 @@ 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 +2312,7 @@ 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 +2330,7 @@ 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 +2353,7 @@ 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 +2375,7 @@ 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 +2396,7 @@ 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 +2718,7 @@ 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 +2877,11 @@ 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 +2944,20 @@ 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 +2998,7 @@ 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 +3038,7 @@ 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 +3058,15 @@ 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 +3076,12 @@ 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 +3105,8 @@ 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 +3186,53 @@ 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 +3249,71 @@ 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 +3578,66 @@ 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 +3731,8 @@ 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 +3785,19 @@ 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 +3908,18 @@ 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 +3945,9 @@ 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 +3985,7 @@ 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 +4068,16 @@ 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 +4092,26 @@ 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 +4195,10 @@ 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 +4213,8 @@ 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 +4357,8 @@ 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 +4382,44 @@ 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 +4551,8 @@ 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;
 	}

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,

tools/lib/bpf/libbpf.map

@@ -337,3 +337,12 @@ LIBBPF_0.2.0 {
 		perf_buffer__consume_buffer;
 		xsk_socket__create_shared;
 } LIBBPF_0.1.0;
+
+LIBBPF_0.3.0 {
+	global:
+		btf__parse_elf_split;
+		btf__parse_raw_split;
+		btf__parse_split;
+		btf__new_empty_split;
+		btf__new_split;
+} LIBBPF_0.2.0;

tools/testing/selftests/bpf/Makefile

@@ -386,7 +386,7 @@ TRUNNER_TESTS_DIR := prog_tests
 TRUNNER_BPF_PROGS_DIR := progs
 TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c	\
 			 network_helpers.c testing_helpers.c		\
-			 flow_dissector_load.h
+			 btf_helpers.c	flow_dissector_load.h
 TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read				\
 		       $(wildcard progs/btf_dump_test_case_*.c)
 TRUNNER_BPF_BUILD_RULE := CLANG_BPF_BUILD_RULE

tools/testing/selftests/bpf/btf_helpers.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <stdio.h>
+#include <errno.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
+#include "test_progs.h"
+
+static const char * const btf_kind_str_mapping[] = {
+	[BTF_KIND_UNKN]		= "UNKNOWN",
+	[BTF_KIND_INT]		= "INT",
+	[BTF_KIND_PTR]		= "PTR",
+	[BTF_KIND_ARRAY]	= "ARRAY",
+	[BTF_KIND_STRUCT]	= "STRUCT",
+	[BTF_KIND_UNION]	= "UNION",
+	[BTF_KIND_ENUM]		= "ENUM",
+	[BTF_KIND_FWD]		= "FWD",
+	[BTF_KIND_TYPEDEF]	= "TYPEDEF",
+	[BTF_KIND_VOLATILE]	= "VOLATILE",
+	[BTF_KIND_CONST]	= "CONST",
+	[BTF_KIND_RESTRICT]	= "RESTRICT",
+	[BTF_KIND_FUNC]		= "FUNC",
+	[BTF_KIND_FUNC_PROTO]	= "FUNC_PROTO",
+	[BTF_KIND_VAR]		= "VAR",
+	[BTF_KIND_DATASEC]	= "DATASEC",
+};
+
+static const char *btf_kind_str(__u16 kind)
+{
+	if (kind > BTF_KIND_DATASEC)
+		return "UNKNOWN";
+	return btf_kind_str_mapping[kind];
+}
+
+static const char *btf_int_enc_str(__u8 encoding)
+{
+	switch (encoding) {
+	case 0:
+		return "(none)";
+	case BTF_INT_SIGNED:
+		return "SIGNED";
+	case BTF_INT_CHAR:
+		return "CHAR";
+	case BTF_INT_BOOL:
+		return "BOOL";
+	default:
+		return "UNKN";
+	}
+}
+
+static const char *btf_var_linkage_str(__u32 linkage)
+{
+	switch (linkage) {
+	case BTF_VAR_STATIC:
+		return "static";
+	case BTF_VAR_GLOBAL_ALLOCATED:
+		return "global-alloc";
+	default:
+		return "(unknown)";
+	}
+}
+
+static const char *btf_func_linkage_str(const struct btf_type *t)
+{
+	switch (btf_vlen(t)) {
+	case BTF_FUNC_STATIC:
+		return "static";
+	case BTF_FUNC_GLOBAL:
+		return "global";
+	case BTF_FUNC_EXTERN:
+		return "extern";
+	default:
+		return "(unknown)";
+	}
+}
+
+static const char *btf_str(const struct btf *btf, __u32 off)
+{
+	if (!off)
+		return "(anon)";
+	return btf__str_by_offset(btf, off) ?: "(invalid)";
+}
+
+int fprintf_btf_type_raw(FILE *out, const struct btf *btf, __u32 id)
+{
+	const struct btf_type *t;
+	int kind, i;
+	__u32 vlen;
+
+	t = btf__type_by_id(btf, id);
+	if (!t)
+		return -EINVAL;
+
+	vlen = btf_vlen(t);
+	kind = btf_kind(t);
+
+	fprintf(out, "[%u] %s '%s'", id, btf_kind_str(kind), btf_str(btf, t->name_off));
+
+	switch (kind) {
+	case BTF_KIND_INT:
+		fprintf(out, " size=%u bits_offset=%u nr_bits=%u encoding=%s",
+			t->size, btf_int_offset(t), btf_int_bits(t),
+			btf_int_enc_str(btf_int_encoding(t)));
+		break;
+	case BTF_KIND_PTR:
+	case BTF_KIND_CONST:
+	case BTF_KIND_VOLATILE:
+	case BTF_KIND_RESTRICT:
+	case BTF_KIND_TYPEDEF:
+		fprintf(out, " type_id=%u", t->type);
+		break;
+	case BTF_KIND_ARRAY: {
+		const struct btf_array *arr = btf_array(t);
+
+		fprintf(out, " type_id=%u index_type_id=%u nr_elems=%u",
+			arr->type, arr->index_type, arr->nelems);
+		break;
+	}
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION: {
+		const struct btf_member *m = btf_members(t);
+
+		fprintf(out, " size=%u vlen=%u", t->size, vlen);
+		for (i = 0; i < vlen; i++, m++) {
+			__u32 bit_off, bit_sz;
+
+			bit_off = btf_member_bit_offset(t, i);
+			bit_sz = btf_member_bitfield_size(t, i);
+			fprintf(out, "\n\t'%s' type_id=%u bits_offset=%u",
+				btf_str(btf, m->name_off), m->type, bit_off);
+			if (bit_sz)
+				fprintf(out, " bitfield_size=%u", bit_sz);
+		}
+		break;
+	}
+	case BTF_KIND_ENUM: {
+		const struct btf_enum *v = btf_enum(t);
+
+		fprintf(out, " size=%u vlen=%u", t->size, vlen);
+		for (i = 0; i < vlen; i++, v++) {
+			fprintf(out, "\n\t'%s' val=%u",
+				btf_str(btf, v->name_off), v->val);
+		}
+		break;
+	}
+	case BTF_KIND_FWD:
+		fprintf(out, " fwd_kind=%s", btf_kflag(t) ? "union" : "struct");
+		break;
+	case BTF_KIND_FUNC:
+		fprintf(out, " type_id=%u linkage=%s", t->type, btf_func_linkage_str(t));
+		break;
+	case BTF_KIND_FUNC_PROTO: {
+		const struct btf_param *p = btf_params(t);
+
+		fprintf(out, " ret_type_id=%u vlen=%u", t->type, vlen);
+		for (i = 0; i < vlen; i++, p++) {
+			fprintf(out, "\n\t'%s' type_id=%u",
+				btf_str(btf, p->name_off), p->type);
+		}
+		break;
+	}
+	case BTF_KIND_VAR:
+		fprintf(out, " type_id=%u, linkage=%s",
+			t->type, btf_var_linkage_str(btf_var(t)->linkage));
+		break;
+	case BTF_KIND_DATASEC: {
+		const struct btf_var_secinfo *v = btf_var_secinfos(t);
+
+		fprintf(out, " size=%u vlen=%u", t->size, vlen);
+		for (i = 0; i < vlen; i++, v++) {
+			fprintf(out, "\n\ttype_id=%u offset=%u size=%u",
+				v->type, v->offset, v->size);
+		}
+		break;
+	}
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+/* Print raw BTF type dump into a local buffer and return string pointer back.
+ * Buffer *will* be overwritten by subsequent btf_type_raw_dump() calls
+ */
+const char *btf_type_raw_dump(const struct btf *btf, int type_id)
+{
+	static char buf[16 * 1024];
+	FILE *buf_file;
+
+	buf_file = fmemopen(buf, sizeof(buf) - 1, "w");
+	if (!buf_file) {
+		fprintf(stderr, "Failed to open memstream: %d\n", errno);
+		return NULL;
+	}
+
+	fprintf_btf_type_raw(buf_file, btf, type_id);
+	fflush(buf_file);
+	fclose(buf_file);
+
+	return buf;
+}
+
+int btf_validate_raw(struct btf *btf, int nr_types, const char *exp_types[])
+{
+	int i;
+	bool ok = true;
+
+	ASSERT_EQ(btf__get_nr_types(btf), nr_types, "btf_nr_types");
+
+	for (i = 1; i <= nr_types; i++) {
+		if (!ASSERT_STREQ(btf_type_raw_dump(btf, i), exp_types[i - 1], "raw_dump"))
+			ok = false;
+	}
+
+	return ok;
+}
+
+static void btf_dump_printf(void *ctx, const char *fmt, va_list args)
+{
+	vfprintf(ctx, fmt, args);
+}
+
+/* Print BTF-to-C dump into a local buffer and return string pointer back.
+ * Buffer *will* be overwritten by subsequent btf_type_raw_dump() calls
+ */
+const char *btf_type_c_dump(const struct btf *btf)
+{
+	static char buf[16 * 1024];
+	FILE *buf_file;
+	struct btf_dump *d = NULL;
+	struct btf_dump_opts opts = {};
+	int err, i;
+
+	buf_file = fmemopen(buf, sizeof(buf) - 1, "w");
+	if (!buf_file) {
+		fprintf(stderr, "Failed to open memstream: %d\n", errno);
+		return NULL;
+	}
+
+	opts.ctx = buf_file;
+	d = btf_dump__new(btf, NULL, &opts, btf_dump_printf);
+	if (libbpf_get_error(d)) {
+		fprintf(stderr, "Failed to create btf_dump instance: %ld\n", libbpf_get_error(d));
+		return NULL;
+	}
+
+	for (i = 1; i <= btf__get_nr_types(btf); i++) {
+		err = btf_dump__dump_type(d, i);
+		if (err) {
+			fprintf(stderr, "Failed to dump type [%d]: %d\n", i, err);
+			return NULL;
+		}
+	}
+
+	fflush(buf_file);
+	fclose(buf_file);
+	return buf;
+}

tools/testing/selftests/bpf/btf_helpers.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2020 Facebook */
+#ifndef __BTF_HELPERS_H
+#define __BTF_HELPERS_H
+
+#include <stdio.h>
+#include <bpf/btf.h>
+
+int fprintf_btf_type_raw(FILE *out, const struct btf *btf, __u32 id);
+const char *btf_type_raw_dump(const struct btf *btf, int type_id);
+int btf_validate_raw(struct btf *btf, int nr_types, const char *exp_types[]);
+
+#define VALIDATE_RAW_BTF(btf, raw_types...)				\
+	btf_validate_raw(btf,						\
+			 sizeof((const char *[]){raw_types})/sizeof(void *),\
+			 (const char *[]){raw_types})
+
+const char *btf_type_c_dump(const struct btf *btf);
+#endif

tools/testing/selftests/bpf/prog_tests/btf.c

@@ -6652,7 +6652,7 @@ static void do_test_dedup(unsigned int test_num)
 	const void *test_btf_data, *expect_btf_data;
 	const char *ret_test_next_str, *ret_expect_next_str;
 	const char *test_strs, *expect_strs;
-	const char *test_str_cur, *test_str_end;
+	const char *test_str_cur;
 	const char *expect_str_cur, *expect_str_end;
 	unsigned int raw_btf_size;
 	void *raw_btf;
@@ -6719,12 +6719,18 @@ static void do_test_dedup(unsigned int test_num)
 		goto done;
 	}
 
-	test_str_cur = test_strs;
-	test_str_end = test_strs + test_hdr->str_len;
 	expect_str_cur = expect_strs;
 	expect_str_end = expect_strs + expect_hdr->str_len;
-	while (test_str_cur < test_str_end && expect_str_cur < expect_str_end) {
+	while (expect_str_cur < expect_str_end) {
 		size_t test_len, expect_len;
+		int off;
+
+		off = btf__find_str(test_btf, expect_str_cur);
+		if (CHECK(off < 0, "exp str '%s' not found: %d\n", expect_str_cur, off)) {
+			err = -1;
+			goto done;
+		}
+		test_str_cur = btf__str_by_offset(test_btf, off);
 
 		test_len = strlen(test_str_cur);
 		expect_len = strlen(expect_str_cur);
@@ -6741,15 +6747,8 @@ static void do_test_dedup(unsigned int test_num)
 			err = -1;
 			goto done;
 		}
-		test_str_cur += test_len + 1;
 		expect_str_cur += expect_len + 1;
 	}
-	if (CHECK(test_str_cur != test_str_end,
-		  "test_str_cur:%p != test_str_end:%p",
-		  test_str_cur, test_str_end)) {
-		err = -1;
-		goto done;
-	}
 
 	test_nr_types = btf__get_nr_types(test_btf);
 	expect_nr_types = btf__get_nr_types(expect_btf);
@@ -6775,10 +6774,21 @@ static void do_test_dedup(unsigned int test_num)
 			err = -1;
 			goto done;
 		}
-		if (CHECK(memcmp((void *)test_type,
-				 (void *)expect_type,
-				 test_size),
-			  "type #%d: contents differ", i)) {
+		if (CHECK(btf_kind(test_type) != btf_kind(expect_type),
+			  "type %d kind: exp %d != got %u\n",
+			  i, btf_kind(expect_type), btf_kind(test_type))) {
+			err = -1;
+			goto done;
+		}
+		if (CHECK(test_type->info != expect_type->info,
+			  "type %d info: exp %d != got %u\n",
+			  i, expect_type->info, test_type->info)) {
+			err = -1;
+			goto done;
+		}
+		if (CHECK(test_type->size != expect_type->size,
+			  "type %d size/type: exp %d != got %u\n",
+			  i, expect_type->size, test_type->size)) {
 			err = -1;
 			goto done;
 		}

tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <test_progs.h>
+#include <bpf/btf.h>
+#include "btf_helpers.h"
+
+static void test_split_simple() {
+	const struct btf_type *t;
+	struct btf *btf1, *btf2;
+	int str_off, err;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+
+	btf__set_pointer_size(btf1, 8); /* enforce 64-bit arch */
+
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);	/* [1] int */
+	btf__add_ptr(btf1, 1);				/* [2] ptr to int */
+	btf__add_struct(btf1, "s1", 4);			/* [3] struct s1 { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*      int f1; */
+							/* } */
+
+	VALIDATE_RAW_BTF(
+		btf1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1",
+		"[3] STRUCT 's1' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0");
+
+	ASSERT_STREQ(btf_type_c_dump(btf1), "\
+struct s1 {\n\
+	int f1;\n\
+};\n\n", "c_dump");
+
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+
+	/* pointer size should be "inherited" from main BTF */
+	ASSERT_EQ(btf__pointer_size(btf2), 8, "inherit_ptr_sz");
+
+	str_off = btf__find_str(btf2, "int");
+	ASSERT_NEQ(str_off, -ENOENT, "str_int_missing");
+
+	t = btf__type_by_id(btf2, 1);
+	if (!ASSERT_OK_PTR(t, "int_type"))
+		goto cleanup;
+	ASSERT_EQ(btf_is_int(t), true, "int_kind");
+	ASSERT_STREQ(btf__str_by_offset(btf2, t->name_off), "int", "int_name");
+
+	btf__add_struct(btf2, "s2", 16);		/* [4] struct s2 {	*/
+	btf__add_field(btf2, "f1", 6, 0, 0);		/*      struct s1 f1;	*/
+	btf__add_field(btf2, "f2", 5, 32, 0);		/*      int f2;		*/
+	btf__add_field(btf2, "f3", 2, 64, 0);		/*      int *f3;	*/
+							/* } */
+
+	/* duplicated int */
+	btf__add_int(btf2, "int", 4, BTF_INT_SIGNED);	/* [5] int */
+
+	/* duplicated struct s1 */
+	btf__add_struct(btf2, "s1", 4);			/* [6] struct s1 { */
+	btf__add_field(btf2, "f1", 5, 0, 0);		/*      int f1; */
+							/* } */
+
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1",
+		"[3] STRUCT 's1' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[4] STRUCT 's2' size=16 vlen=3\n"
+		"\t'f1' type_id=6 bits_offset=0\n"
+		"\t'f2' type_id=5 bits_offset=32\n"
+		"\t'f3' type_id=2 bits_offset=64",
+		"[5] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[6] STRUCT 's1' size=4 vlen=1\n"
+		"\t'f1' type_id=5 bits_offset=0");
+
+	ASSERT_STREQ(btf_type_c_dump(btf2), "\
+struct s1 {\n\
+	int f1;\n\
+};\n\
+\n\
+struct s1___2 {\n\
+	int f1;\n\
+};\n\
+\n\
+struct s2 {\n\
+	struct s1___2 f1;\n\
+	int f2;\n\
+	int *f3;\n\
+};\n\n", "c_dump");
+
+	err = btf__dedup(btf2, NULL, NULL);
+	if (!ASSERT_OK(err, "btf_dedup"))
+		goto cleanup;
+
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1",
+		"[3] STRUCT 's1' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[4] STRUCT 's2' size=16 vlen=3\n"
+		"\t'f1' type_id=3 bits_offset=0\n"
+		"\t'f2' type_id=1 bits_offset=32\n"
+		"\t'f3' type_id=2 bits_offset=64");
+
+	ASSERT_STREQ(btf_type_c_dump(btf2), "\
+struct s1 {\n\
+	int f1;\n\
+};\n\
+\n\
+struct s2 {\n\
+	struct s1 f1;\n\
+	int f2;\n\
+	int *f3;\n\
+};\n\n", "c_dump");
+
+cleanup:
+	btf__free(btf2);
+	btf__free(btf1);
+}
+
+static void test_split_fwd_resolve() {
+	struct btf *btf1, *btf2;
+	int err;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+
+	btf__set_pointer_size(btf1, 8); /* enforce 64-bit arch */
+
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);	/* [1] int */
+	btf__add_ptr(btf1, 4);				/* [2] ptr to struct s1 */
+	btf__add_ptr(btf1, 5);				/* [3] ptr to struct s2 */
+	btf__add_struct(btf1, "s1", 16);		/* [4] struct s1 { */
+	btf__add_field(btf1, "f1", 2, 0, 0);		/*      struct s1 *f1; */
+	btf__add_field(btf1, "f2", 3, 64, 0);		/*      struct s2 *f2; */
+							/* } */
+	btf__add_struct(btf1, "s2", 4);			/* [5] struct s2 { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*      int f1; */
+							/* } */
+
+	VALIDATE_RAW_BTF(
+		btf1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=4",
+		"[3] PTR '(anon)' type_id=5",
+		"[4] STRUCT 's1' size=16 vlen=2\n"
+		"\t'f1' type_id=2 bits_offset=0\n"
+		"\t'f2' type_id=3 bits_offset=64",
+		"[5] STRUCT 's2' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0");
+
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+
+	btf__add_int(btf2, "int", 4, BTF_INT_SIGNED);	/* [6] int */
+	btf__add_ptr(btf2, 10);				/* [7] ptr to struct s1 */
+	btf__add_fwd(btf2, "s2", BTF_FWD_STRUCT);	/* [8] fwd for struct s2 */
+	btf__add_ptr(btf2, 8);				/* [9] ptr to fwd struct s2 */
+	btf__add_struct(btf2, "s1", 16);		/* [10] struct s1 { */
+	btf__add_field(btf2, "f1", 7, 0, 0);		/*      struct s1 *f1; */
+	btf__add_field(btf2, "f2", 9, 64, 0);		/*      struct s2 *f2; */
+							/* } */
+
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=4",
+		"[3] PTR '(anon)' type_id=5",
+		"[4] STRUCT 's1' size=16 vlen=2\n"
+		"\t'f1' type_id=2 bits_offset=0\n"
+		"\t'f2' type_id=3 bits_offset=64",
+		"[5] STRUCT 's2' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[6] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[7] PTR '(anon)' type_id=10",
+		"[8] FWD 's2' fwd_kind=struct",
+		"[9] PTR '(anon)' type_id=8",
+		"[10] STRUCT 's1' size=16 vlen=2\n"
+		"\t'f1' type_id=7 bits_offset=0\n"
+		"\t'f2' type_id=9 bits_offset=64");
+
+	err = btf__dedup(btf2, NULL, NULL);
+	if (!ASSERT_OK(err, "btf_dedup"))
+		goto cleanup;
+
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=4",
+		"[3] PTR '(anon)' type_id=5",
+		"[4] STRUCT 's1' size=16 vlen=2\n"
+		"\t'f1' type_id=2 bits_offset=0\n"
+		"\t'f2' type_id=3 bits_offset=64",
+		"[5] STRUCT 's2' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0");
+
+cleanup:
+	btf__free(btf2);
+	btf__free(btf1);
+}
+
+static void test_split_struct_duped() {
+	struct btf *btf1, *btf2;
+	int err;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+
+	btf__set_pointer_size(btf1, 8); /* enforce 64-bit arch */
+
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);	/* [1] int */
+	btf__add_ptr(btf1, 5);				/* [2] ptr to struct s1 */
+	btf__add_fwd(btf1, "s2", BTF_FWD_STRUCT);	/* [3] fwd for struct s2 */
+	btf__add_ptr(btf1, 3);				/* [4] ptr to fwd struct s2 */
+	btf__add_struct(btf1, "s1", 16);		/* [5] struct s1 { */
+	btf__add_field(btf1, "f1", 2, 0, 0);		/*      struct s1 *f1; */
+	btf__add_field(btf1, "f2", 4, 64, 0);		/*      struct s2 *f2; */
+							/* } */
+
+	VALIDATE_RAW_BTF(
+		btf1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=5",
+		"[3] FWD 's2' fwd_kind=struct",
+		"[4] PTR '(anon)' type_id=3",
+		"[5] STRUCT 's1' size=16 vlen=2\n"
+		"\t'f1' type_id=2 bits_offset=0\n"
+		"\t'f2' type_id=4 bits_offset=64");
+
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+
+	btf__add_int(btf2, "int", 4, BTF_INT_SIGNED);	/* [6] int */
+	btf__add_ptr(btf2, 10);				/* [7] ptr to struct s1 */
+	btf__add_fwd(btf2, "s2", BTF_FWD_STRUCT);	/* [8] fwd for struct s2 */
+	btf__add_ptr(btf2, 11);				/* [9] ptr to struct s2 */
+	btf__add_struct(btf2, "s1", 16);		/* [10] struct s1 { */
+	btf__add_field(btf2, "f1", 7, 0, 0);		/*      struct s1 *f1; */
+	btf__add_field(btf2, "f2", 9, 64, 0);		/*      struct s2 *f2; */
+							/* } */
+	btf__add_struct(btf2, "s2", 40);		/* [11] struct s2 {	*/
+	btf__add_field(btf2, "f1", 7, 0, 0);		/*      struct s1 *f1;	*/
+	btf__add_field(btf2, "f2", 9, 64, 0);		/*      struct s2 *f2;	*/
+	btf__add_field(btf2, "f3", 6, 128, 0);		/*      int f3;		*/
+	btf__add_field(btf2, "f4", 10, 192, 0);		/*      struct s1 f4;	*/
+							/* } */
+	btf__add_ptr(btf2, 8);				/* [12] ptr to fwd struct s2 */
+	btf__add_struct(btf2, "s3", 8);			/* [13] struct s3 { */
+	btf__add_field(btf2, "f1", 12, 0, 0);		/*      struct s2 *f1; (fwd) */
+							/* } */
+
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=5",
+		"[3] FWD 's2' fwd_kind=struct",
+		"[4] PTR '(anon)' type_id=3",
+		"[5] STRUCT 's1' size=16 vlen=2\n"
+		"\t'f1' type_id=2 bits_offset=0\n"
+		"\t'f2' type_id=4 bits_offset=64",
+		"[6] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[7] PTR '(anon)' type_id=10",
+		"[8] FWD 's2' fwd_kind=struct",
+		"[9] PTR '(anon)' type_id=11",
+		"[10] STRUCT 's1' size=16 vlen=2\n"
+		"\t'f1' type_id=7 bits_offset=0\n"
+		"\t'f2' type_id=9 bits_offset=64",
+		"[11] STRUCT 's2' size=40 vlen=4\n"
+		"\t'f1' type_id=7 bits_offset=0\n"
+		"\t'f2' type_id=9 bits_offset=64\n"
+		"\t'f3' type_id=6 bits_offset=128\n"
+		"\t'f4' type_id=10 bits_offset=192",
+		"[12] PTR '(anon)' type_id=8",
+		"[13] STRUCT 's3' size=8 vlen=1\n"
+		"\t'f1' type_id=12 bits_offset=0");
+
+	err = btf__dedup(btf2, NULL, NULL);
+	if (!ASSERT_OK(err, "btf_dedup"))
+		goto cleanup;
+
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=5",
+		"[3] FWD 's2' fwd_kind=struct",
+		"[4] PTR '(anon)' type_id=3",
+		"[5] STRUCT 's1' size=16 vlen=2\n"
+		"\t'f1' type_id=2 bits_offset=0\n"
+		"\t'f2' type_id=4 bits_offset=64",
+		"[6] PTR '(anon)' type_id=8",
+		"[7] PTR '(anon)' type_id=9",
+		"[8] STRUCT 's1' size=16 vlen=2\n"
+		"\t'f1' type_id=6 bits_offset=0\n"
+		"\t'f2' type_id=7 bits_offset=64",
+		"[9] STRUCT 's2' size=40 vlen=4\n"
+		"\t'f1' type_id=6 bits_offset=0\n"
+		"\t'f2' type_id=7 bits_offset=64\n"
+		"\t'f3' type_id=1 bits_offset=128\n"
+		"\t'f4' type_id=8 bits_offset=192",
+		"[10] STRUCT 's3' size=8 vlen=1\n"
+		"\t'f1' type_id=7 bits_offset=0");
+
+cleanup:
+	btf__free(btf2);
+	btf__free(btf1);
+}
+
+void test_btf_dedup_split()
+{
+	if (test__start_subtest("split_simple"))
+		test_split_simple();
+	if (test__start_subtest("split_struct_duped"))
+		test_split_struct_duped();
+	if (test__start_subtest("split_fwd_resolve"))
+		test_split_fwd_resolve();
+}

tools/testing/selftests/bpf/prog_tests/btf_split.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <test_progs.h>
+#include <bpf/btf.h>
+
+static char *dump_buf;
+static size_t dump_buf_sz;
+static FILE *dump_buf_file;
+
+static void btf_dump_printf(void *ctx, const char *fmt, va_list args)
+{
+	vfprintf(ctx, fmt, args);
+}
+
+void test_btf_split() {
+	struct btf_dump_opts opts;
+	struct btf_dump *d = NULL;
+	const struct btf_type *t;
+	struct btf *btf1, *btf2;
+	int str_off, i, err;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+
+	btf__set_pointer_size(btf1, 8); /* enforce 64-bit arch */
+
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);	/* [1] int */
+	btf__add_ptr(btf1, 1);				/* [2] ptr to int */
+
+	btf__add_struct(btf1, "s1", 4);			/* [3] struct s1 { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*      int f1; */
+							/* } */
+
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+
+	/* pointer size should be "inherited" from main BTF */
+	ASSERT_EQ(btf__pointer_size(btf2), 8, "inherit_ptr_sz");
+
+	str_off = btf__find_str(btf2, "int");
+	ASSERT_NEQ(str_off, -ENOENT, "str_int_missing");
+
+	t = btf__type_by_id(btf2, 1);
+	if (!ASSERT_OK_PTR(t, "int_type"))
+		goto cleanup;
+	ASSERT_EQ(btf_is_int(t), true, "int_kind");
+	ASSERT_STREQ(btf__str_by_offset(btf2, t->name_off), "int", "int_name");
+
+	btf__add_struct(btf2, "s2", 16);		/* [4] struct s2 {	*/
+	btf__add_field(btf2, "f1", 3, 0, 0);		/*      struct s1 f1;	*/
+	btf__add_field(btf2, "f2", 1, 32, 0);		/*      int f2;		*/
+	btf__add_field(btf2, "f3", 2, 64, 0);		/*      int *f3;	*/
+							/* } */
+
+	t = btf__type_by_id(btf1, 4);
+	ASSERT_NULL(t, "split_type_in_main");
+
+	t = btf__type_by_id(btf2, 4);
+	if (!ASSERT_OK_PTR(t, "split_struct_type"))
+		goto cleanup;
+	ASSERT_EQ(btf_is_struct(t), true, "split_struct_kind");
+	ASSERT_EQ(btf_vlen(t), 3, "split_struct_vlen");
+	ASSERT_STREQ(btf__str_by_offset(btf2, t->name_off), "s2", "split_struct_name");
+
+	/* BTF-to-C dump of split BTF */
+	dump_buf_file = open_memstream(&dump_buf, &dump_buf_sz);
+	if (!ASSERT_OK_PTR(dump_buf_file, "dump_memstream"))
+		return;
+	opts.ctx = dump_buf_file;
+	d = btf_dump__new(btf2, NULL, &opts, btf_dump_printf);
+	if (!ASSERT_OK_PTR(d, "btf_dump__new"))
+		goto cleanup;
+	for (i = 1; i <= btf__get_nr_types(btf2); i++) {
+		err = btf_dump__dump_type(d, i);
+		ASSERT_OK(err, "dump_type_ok");
+	}
+	fflush(dump_buf_file);
+	dump_buf[dump_buf_sz] = 0; /* some libc implementations don't do this */
+	ASSERT_STREQ(dump_buf,
+"struct s1 {\n"
+"	int f1;\n"
+"};\n"
+"\n"
+"struct s2 {\n"
+"	struct s1 f1;\n"
+"	int f2;\n"
+"	int *f3;\n"
+"};\n\n", "c_dump");
+
+cleanup:
+	if (dump_buf_file)
+		fclose(dump_buf_file);
+	free(dump_buf);
+	btf_dump__free(d);
+	btf__free(btf1);
+	btf__free(btf2);
+}

tools/testing/selftests/bpf/prog_tests/btf_write.c

@@ -2,6 +2,7 @@
 /* Copyright (c) 2020 Facebook */
 #include <test_progs.h>
 #include <bpf/btf.h>
+#include "btf_helpers.h"
 
 static int duration = 0;
 
@@ -39,6 +40,8 @@ void test_btf_write() {
 	ASSERT_EQ(t->size, 4, "int_sz");
 	ASSERT_EQ(btf_int_encoding(t), BTF_INT_SIGNED, "int_enc");
 	ASSERT_EQ(btf_int_bits(t), 32, "int_bits");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 1),
+		     "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", "raw_dump");
 
 	/* invalid int size */
 	id = btf__add_int(btf, "bad sz int", 7, 0);
@@ -59,24 +62,32 @@ void test_btf_write() {
 	t = btf__type_by_id(btf, 2);
 	ASSERT_EQ(btf_kind(t), BTF_KIND_PTR, "ptr_kind");
 	ASSERT_EQ(t->type, 1, "ptr_type");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 2),
+		     "[2] PTR '(anon)' type_id=1", "raw_dump");
 
 	id = btf__add_const(btf, 5); /* points forward to restrict */
 	ASSERT_EQ(id, 3, "const_id");
 	t = btf__type_by_id(btf, 3);
 	ASSERT_EQ(btf_kind(t), BTF_KIND_CONST, "const_kind");
 	ASSERT_EQ(t->type, 5, "const_type");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 3),
+		     "[3] CONST '(anon)' type_id=5", "raw_dump");
 
 	id = btf__add_volatile(btf, 3);
 	ASSERT_EQ(id, 4, "volatile_id");
 	t = btf__type_by_id(btf, 4);
 	ASSERT_EQ(btf_kind(t), BTF_KIND_VOLATILE, "volatile_kind");
 	ASSERT_EQ(t->type, 3, "volatile_type");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 4),
+		     "[4] VOLATILE '(anon)' type_id=3", "raw_dump");
 
 	id = btf__add_restrict(btf, 4);
 	ASSERT_EQ(id, 5, "restrict_id");
 	t = btf__type_by_id(btf, 5);
 	ASSERT_EQ(btf_kind(t), BTF_KIND_RESTRICT, "restrict_kind");
 	ASSERT_EQ(t->type, 4, "restrict_type");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 5),
+		     "[5] RESTRICT '(anon)' type_id=4", "raw_dump");
 
 	/* ARRAY */
 	id = btf__add_array(btf, 1, 2, 10); /* int *[10] */
@@ -86,6 +97,8 @@ void test_btf_write() {
 	ASSERT_EQ(btf_array(t)->index_type, 1, "array_index_type");
 	ASSERT_EQ(btf_array(t)->type, 2, "array_elem_type");
 	ASSERT_EQ(btf_array(t)->nelems, 10, "array_nelems");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 6),
+		     "[6] ARRAY '(anon)' type_id=2 index_type_id=1 nr_elems=10", "raw_dump");
 
 	/* STRUCT */
 	err = btf__add_field(btf, "field", 1, 0, 0);
@@ -113,6 +126,10 @@ void test_btf_write() {
 	ASSERT_EQ(m->type, 1, "f2_type");
 	ASSERT_EQ(btf_member_bit_offset(t, 1), 32, "f2_bit_off");
 	ASSERT_EQ(btf_member_bitfield_size(t, 1), 16, "f2_bit_sz");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 7),
+		     "[7] STRUCT 's1' size=8 vlen=2\n"
+		     "\t'f1' type_id=1 bits_offset=0\n"
+		     "\t'f2' type_id=1 bits_offset=32 bitfield_size=16", "raw_dump");
 
 	/* UNION */
 	id = btf__add_union(btf, "u1", 8);
@@ -136,6 +153,9 @@ void test_btf_write() {
 	ASSERT_EQ(m->type, 1, "f1_type");
 	ASSERT_EQ(btf_member_bit_offset(t, 0), 0, "f1_bit_off");
 	ASSERT_EQ(btf_member_bitfield_size(t, 0), 16, "f1_bit_sz");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 8),
+		     "[8] UNION 'u1' size=8 vlen=1\n"
+		     "\t'f1' type_id=1 bits_offset=0 bitfield_size=16", "raw_dump");
 
 	/* ENUM */
 	id = btf__add_enum(btf, "e1", 4);
@@ -156,6 +176,10 @@ void test_btf_write() {
 	v = btf_enum(t) + 1;
 	ASSERT_STREQ(btf__str_by_offset(btf, v->name_off), "v2", "v2_name");
 	ASSERT_EQ(v->val, 2, "v2_val");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 9),
+		     "[9] ENUM 'e1' size=4 vlen=2\n"
+		     "\t'v1' val=1\n"
+		     "\t'v2' val=2", "raw_dump");
 
 	/* FWDs */
 	id = btf__add_fwd(btf, "struct_fwd", BTF_FWD_STRUCT);
@@ -164,6 +188,8 @@ void test_btf_write() {
 	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "struct_fwd", "fwd_name");
 	ASSERT_EQ(btf_kind(t), BTF_KIND_FWD, "fwd_kind");
 	ASSERT_EQ(btf_kflag(t), 0, "fwd_kflag");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 10),
+		     "[10] FWD 'struct_fwd' fwd_kind=struct", "raw_dump");
 
 	id = btf__add_fwd(btf, "union_fwd", BTF_FWD_UNION);
 	ASSERT_EQ(id, 11, "union_fwd_id");
@@ -171,6 +197,8 @@ void test_btf_write() {
 	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "union_fwd", "fwd_name");
 	ASSERT_EQ(btf_kind(t), BTF_KIND_FWD, "fwd_kind");
 	ASSERT_EQ(btf_kflag(t), 1, "fwd_kflag");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 11),
+		     "[11] FWD 'union_fwd' fwd_kind=union", "raw_dump");
 
 	id = btf__add_fwd(btf, "enum_fwd", BTF_FWD_ENUM);
 	ASSERT_EQ(id, 12, "enum_fwd_id");
@@ -179,6 +207,8 @@ void test_btf_write() {
 	ASSERT_EQ(btf_kind(t), BTF_KIND_ENUM, "enum_fwd_kind");
 	ASSERT_EQ(btf_vlen(t), 0, "enum_fwd_kind");
 	ASSERT_EQ(t->size, 4, "enum_fwd_sz");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 12),
+		     "[12] ENUM 'enum_fwd' size=4 vlen=0", "raw_dump");
 
 	/* TYPEDEF */
 	id = btf__add_typedef(btf, "typedef1", 1);
@@ -187,6 +217,8 @@ void test_btf_write() {
 	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "typedef1", "typedef_name");
 	ASSERT_EQ(btf_kind(t), BTF_KIND_TYPEDEF, "typedef_kind");
 	ASSERT_EQ(t->type, 1, "typedef_type");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 13),
+		     "[13] TYPEDEF 'typedef1' type_id=1", "raw_dump");
 
 	/* FUNC & FUNC_PROTO */
 	id = btf__add_func(btf, "func1", BTF_FUNC_GLOBAL, 15);
@@ -196,6 +228,8 @@ void test_btf_write() {
 	ASSERT_EQ(t->type, 15, "func_type");
 	ASSERT_EQ(btf_kind(t), BTF_KIND_FUNC, "func_kind");
 	ASSERT_EQ(btf_vlen(t), BTF_FUNC_GLOBAL, "func_vlen");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 14),
+		     "[14] FUNC 'func1' type_id=15 linkage=global", "raw_dump");
 
 	id = btf__add_func_proto(btf, 1);
 	ASSERT_EQ(id, 15, "func_proto_id");
@@ -214,6 +248,10 @@ void test_btf_write() {
 	p = btf_params(t) + 1;
 	ASSERT_STREQ(btf__str_by_offset(btf, p->name_off), "p2", "p2_name");
 	ASSERT_EQ(p->type, 2, "p2_type");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 15),
+		     "[15] FUNC_PROTO '(anon)' ret_type_id=1 vlen=2\n"
+		     "\t'p1' type_id=1\n"
+		     "\t'p2' type_id=2", "raw_dump");
 
 	/* VAR */
 	id = btf__add_var(btf, "var1", BTF_VAR_GLOBAL_ALLOCATED, 1);
@@ -223,6 +261,8 @@ void test_btf_write() {
 	ASSERT_EQ(btf_kind(t), BTF_KIND_VAR, "var_kind");
 	ASSERT_EQ(t->type, 1, "var_type");
 	ASSERT_EQ(btf_var(t)->linkage, BTF_VAR_GLOBAL_ALLOCATED, "var_type");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 16),
+		     "[16] VAR 'var1' type_id=1, linkage=global-alloc", "raw_dump");
 
 	/* DATASECT */
 	id = btf__add_datasec(btf, "datasec1", 12);
@@ -239,6 +279,9 @@ void test_btf_write() {
 	ASSERT_EQ(vi->type, 1, "v1_type");
 	ASSERT_EQ(vi->offset, 4, "v1_off");
 	ASSERT_EQ(vi->size, 8, "v1_sz");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 17),
+		     "[17] DATASEC 'datasec1' size=12 vlen=1\n"
+		     "\ttype_id=1 offset=4 size=8", "raw_dump");
 
 	btf__free(btf);
 }

tools/testing/selftests/bpf/test_progs.h

@@ -141,6 +141,17 @@ extern int test__join_cgroup(const char *path);
 	___ok;								\
 })
 
+#define ASSERT_NEQ(actual, expected, name) ({				\
+	static int duration = 0;					\
+	typeof(actual) ___act = (actual);				\
+	typeof(expected) ___exp = (expected);				\
+	bool ___ok = ___act != ___exp;					\
+	CHECK(!___ok, (name),						\
+	      "unexpected %s: actual %lld == expected %lld\n",		\
+	      (name), (long long)(___act), (long long)(___exp));	\
+	___ok;								\
+})
+
 #define ASSERT_STREQ(actual, expected, name) ({				\
 	static int duration = 0;					\
 	const char *___act = actual;					\