1 files changed, 1053 insertions, 264 deletions

diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index b352ab041160..c81362a001ba 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -4,6 +4,7 @@
 #define _GNU_SOURCE
 #include <errno.h>
 #include <fcntl.h>
+#include <signal.h>
 #include <stdarg.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -11,38 +12,70 @@
 #include <time.h>
 #include <unistd.h>
 #include <net/if.h>
+#include <sys/ioctl.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <sys/syscall.h>
+#include <dirent.h>
 
 #include <linux/err.h>
+#include <linux/perf_event.h>
 #include <linux/sizes.h>
 
 #include <bpf/bpf.h>
 #include <bpf/btf.h>
+#include <bpf/hashmap.h>
 #include <bpf/libbpf.h>
+#include <bpf/libbpf_internal.h>
+#include <bpf/skel_internal.h>
 
 #include "cfg.h"
 #include "main.h"
 #include "xlated_dumper.h"
 
+#define BPF_METADATA_PREFIX "bpf_metadata_"
+#define BPF_METADATA_PREFIX_LEN (sizeof(BPF_METADATA_PREFIX) - 1)
+
 enum dump_mode {
 	DUMP_JITED,
 	DUMP_XLATED,
 };
 
+static const bool attach_types[] = {
+	[BPF_SK_SKB_STREAM_PARSER] = true,
+	[BPF_SK_SKB_STREAM_VERDICT] = true,
+	[BPF_SK_SKB_VERDICT] = true,
+	[BPF_SK_MSG_VERDICT] = true,
+	[BPF_FLOW_DISSECTOR] = true,
+	[__MAX_BPF_ATTACH_TYPE] = false,
+};
+
+/* Textual representations traditionally used by the program and kept around
+ * for the sake of backwards compatibility.
+ */
 static const char * const attach_type_strings[] = {
 	[BPF_SK_SKB_STREAM_PARSER] = "stream_parser",
 	[BPF_SK_SKB_STREAM_VERDICT] = "stream_verdict",
+	[BPF_SK_SKB_VERDICT] = "skb_verdict",
 	[BPF_SK_MSG_VERDICT] = "msg_verdict",
-	[BPF_FLOW_DISSECTOR] = "flow_dissector",
 	[__MAX_BPF_ATTACH_TYPE] = NULL,
 };
 
+static struct hashmap *prog_table;
+
 static enum bpf_attach_type parse_attach_type(const char *str)
 {
 	enum bpf_attach_type type;
 
 	for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) {
+		if (attach_types[type]) {
+			const char *attach_type_str;
+
+			attach_type_str = libbpf_bpf_attach_type_str(type);
+			if (!strcmp(str, attach_type_str))
+				return type;
+		}
+
 		if (attach_type_strings[type] &&
 		    is_prefix(str, attach_type_strings[type]))
 			return type;
@@ -51,6 +84,76 @@ static enum bpf_attach_type parse_attach_type(const char *str)
 	return __MAX_BPF_ATTACH_TYPE;
 }
 
+static int prep_prog_info(struct bpf_prog_info *const info, enum dump_mode mode,
+			  void **info_data, size_t *const info_data_sz)
+{
+	struct bpf_prog_info holder = {};
+	size_t needed = 0;
+	void *ptr;
+
+	if (mode == DUMP_JITED) {
+		holder.jited_prog_len = info->jited_prog_len;
+		needed += info->jited_prog_len;
+	} else {
+		holder.xlated_prog_len = info->xlated_prog_len;
+		needed += info->xlated_prog_len;
+	}
+
+	holder.nr_jited_ksyms = info->nr_jited_ksyms;
+	needed += info->nr_jited_ksyms * sizeof(__u64);
+
+	holder.nr_jited_func_lens = info->nr_jited_func_lens;
+	needed += info->nr_jited_func_lens * sizeof(__u32);
+
+	holder.nr_func_info = info->nr_func_info;
+	holder.func_info_rec_size = info->func_info_rec_size;
+	needed += info->nr_func_info * info->func_info_rec_size;
+
+	holder.nr_line_info = info->nr_line_info;
+	holder.line_info_rec_size = info->line_info_rec_size;
+	needed += info->nr_line_info * info->line_info_rec_size;
+
+	holder.nr_jited_line_info = info->nr_jited_line_info;
+	holder.jited_line_info_rec_size = info->jited_line_info_rec_size;
+	needed += info->nr_jited_line_info * info->jited_line_info_rec_size;
+
+	if (needed > *info_data_sz) {
+		ptr = realloc(*info_data, needed);
+		if (!ptr)
+			return -1;
+
+		*info_data = ptr;
+		*info_data_sz = needed;
+	}
+	ptr = *info_data;
+
+	if (mode == DUMP_JITED) {
+		holder.jited_prog_insns = ptr_to_u64(ptr);
+		ptr += holder.jited_prog_len;
+	} else {
+		holder.xlated_prog_insns = ptr_to_u64(ptr);
+		ptr += holder.xlated_prog_len;
+	}
+
+	holder.jited_ksyms = ptr_to_u64(ptr);
+	ptr += holder.nr_jited_ksyms * sizeof(__u64);
+
+	holder.jited_func_lens = ptr_to_u64(ptr);
+	ptr += holder.nr_jited_func_lens * sizeof(__u32);
+
+	holder.func_info = ptr_to_u64(ptr);
+	ptr += holder.nr_func_info * holder.func_info_rec_size;
+
+	holder.line_info = ptr_to_u64(ptr);
+	ptr += holder.nr_line_info * holder.line_info_rec_size;
+
+	holder.jited_line_info = ptr_to_u64(ptr);
+	ptr += holder.nr_jited_line_info * holder.jited_line_info_rec_size;
+
+	*info = holder;
+	return 0;
+}
+
 static void print_boot_time(__u64 nsecs, char *buf, unsigned int size)
 {
 	struct timespec real_time_ts, boot_time_ts;
@@ -82,198 +185,246 @@ static void print_boot_time(__u64 nsecs, char *buf, unsigned int size)
 		strftime(buf, size, "%FT%T%z", &load_tm);
 }
 
-static int prog_fd_by_nametag(void *nametag, int **fds, bool tag)
+static void show_prog_maps(int fd, __u32 num_maps)
 {
-	unsigned int id = 0;
-	int fd, nb_fds = 0;
-	void *tmp;
+	struct bpf_prog_info info = {};
+	__u32 len = sizeof(info);
+	__u32 map_ids[num_maps];
+	unsigned int i;
 	int err;
 
-	while (true) {
-		struct bpf_prog_info info = {};
-		__u32 len = sizeof(info);
+	info.nr_map_ids = num_maps;
+	info.map_ids = ptr_to_u64(map_ids);
 
-		err = bpf_prog_get_next_id(id, &id);
-		if (err) {
-			if (errno != ENOENT) {
-				p_err("%s", strerror(errno));
-				goto err_close_fds;
-			}
-			return nb_fds;
-		}
+	err = bpf_obj_get_info_by_fd(fd, &info, &len);
+	if (err || !info.nr_map_ids)
+		return;
 
-		fd = bpf_prog_get_fd_by_id(id);
-		if (fd < 0) {
-			p_err("can't get prog by id (%u): %s",
-			      id, strerror(errno));
-			goto err_close_fds;
-		}
+	if (json_output) {
+		jsonw_name(json_wtr, "map_ids");
+		jsonw_start_array(json_wtr);
+		for (i = 0; i < info.nr_map_ids; i++)
+			jsonw_uint(json_wtr, map_ids[i]);
+		jsonw_end_array(json_wtr);
+	} else {
+		printf("  map_ids ");
+		for (i = 0; i < info.nr_map_ids; i++)
+			printf("%u%s", map_ids[i],
+			       i == info.nr_map_ids - 1 ? "" : ",");
+	}
+}
 
-		err = bpf_obj_get_info_by_fd(fd, &info, &len);
-		if (err) {
-			p_err("can't get prog info (%u): %s",
-			      id, strerror(errno));
-			goto err_close_fd;
+static void *find_metadata(int prog_fd, struct bpf_map_info *map_info)
+{
+	struct bpf_prog_info prog_info;
+	__u32 prog_info_len;
+	__u32 map_info_len;
+	void *value = NULL;
+	__u32 *map_ids;
+	int nr_maps;
+	int key = 0;
+	int map_fd;
+	int ret;
+	__u32 i;
+
+	memset(&prog_info, 0, sizeof(prog_info));
+	prog_info_len = sizeof(prog_info);
+	ret = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &prog_info_len);
+	if (ret)
+		return NULL;
+
+	if (!prog_info.nr_map_ids)
+		return NULL;
+
+	map_ids = calloc(prog_info.nr_map_ids, sizeof(__u32));
+	if (!map_ids)
+		return NULL;
+
+	nr_maps = prog_info.nr_map_ids;
+	memset(&prog_info, 0, sizeof(prog_info));
+	prog_info.nr_map_ids = nr_maps;
+	prog_info.map_ids = ptr_to_u64(map_ids);
+	prog_info_len = sizeof(prog_info);
+
+	ret = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &prog_info_len);
+	if (ret)
+		goto free_map_ids;
+
+	for (i = 0; i < prog_info.nr_map_ids; i++) {
+		map_fd = bpf_map_get_fd_by_id(map_ids[i]);
+		if (map_fd < 0)
+			goto free_map_ids;
+
+		memset(map_info, 0, sizeof(*map_info));
+		map_info_len = sizeof(*map_info);
+		ret = bpf_obj_get_info_by_fd(map_fd, map_info, &map_info_len);
+		if (ret < 0) {
+			close(map_fd);
+			goto free_map_ids;
 		}
 
-		if ((tag && memcmp(nametag, info.tag, BPF_TAG_SIZE)) ||
-		    (!tag && strncmp(nametag, info.name, BPF_OBJ_NAME_LEN))) {
-			close(fd);
+		if (map_info->type != BPF_MAP_TYPE_ARRAY ||
+		    map_info->key_size != sizeof(int) ||
+		    map_info->max_entries != 1 ||
+		    !map_info->btf_value_type_id ||
+		    !strstr(map_info->name, ".rodata")) {
+			close(map_fd);
 			continue;
 		}
 
-		if (nb_fds > 0) {
-			tmp = realloc(*fds, (nb_fds + 1) * sizeof(int));
-			if (!tmp) {
-				p_err("failed to realloc");
-				goto err_close_fd;
-			}
-			*fds = tmp;
+		value = malloc(map_info->value_size);
+		if (!value) {
+			close(map_fd);
+			goto free_map_ids;
+		}
+
+		if (bpf_map_lookup_elem(map_fd, &key, value)) {
+			close(map_fd);
+			free(value);
+			value = NULL;
+			goto free_map_ids;
 		}
-		(*fds)[nb_fds++] = fd;
+
+		close(map_fd);
+		break;
 	}
 
-err_close_fd:
-	close(fd);
-err_close_fds:
-	while (--nb_fds >= 0)
-		close((*fds)[nb_fds]);
-	return -1;
+free_map_ids:
+	free(map_ids);
+	return value;
 }
 
-static int prog_parse_fds(int *argc, char ***argv, int **fds)
+static bool has_metadata_prefix(const char *s)
 {
-	if (is_prefix(**argv, "id")) {
-		unsigned int id;
-		char *endptr;
-
-		NEXT_ARGP();
+	return strncmp(s, BPF_METADATA_PREFIX, BPF_METADATA_PREFIX_LEN) == 0;
+}
 
-		id = strtoul(**argv, &endptr, 0);
-		if (*endptr) {
-			p_err("can't parse %s as ID", **argv);
-			return -1;
-		}
-		NEXT_ARGP();
+static void show_prog_metadata(int fd, __u32 num_maps)
+{
+	const struct btf_type *t_datasec, *t_var;
+	struct bpf_map_info map_info;
+	struct btf_var_secinfo *vsi;
+	bool printed_header = false;
+	unsigned int i, vlen;
+	void *value = NULL;
+	const char *name;
+	struct btf *btf;
+	int err;
 
-		(*fds)[0] = bpf_prog_get_fd_by_id(id);
-		if ((*fds)[0] < 0) {
-			p_err("get by id (%u): %s", id, strerror(errno));
-			return -1;
-		}
-		return 1;
-	} else if (is_prefix(**argv, "tag")) {
-		unsigned char tag[BPF_TAG_SIZE];
+	if (!num_maps)
+		return;
 
-		NEXT_ARGP();
+	memset(&map_info, 0, sizeof(map_info));
+	value = find_metadata(fd, &map_info);
+	if (!value)
+		return;
 
-		if (sscanf(**argv, BPF_TAG_FMT, tag, tag + 1, tag + 2,
-			   tag + 3, tag + 4, tag + 5, tag + 6, tag + 7)
-		    != BPF_TAG_SIZE) {
-			p_err("can't parse tag");
-			return -1;
-		}
-		NEXT_ARGP();
+	btf = btf__load_from_kernel_by_id(map_info.btf_id);
+	if (libbpf_get_error(btf))
+		goto out_free;
 
-		return prog_fd_by_nametag(tag, fds, true);
-	} else if (is_prefix(**argv, "name")) {
-		char *name;
+	t_datasec = btf__type_by_id(btf, map_info.btf_value_type_id);
+	if (!btf_is_datasec(t_datasec))
+		goto out_free;
 
-		NEXT_ARGP();
+	vlen = btf_vlen(t_datasec);
+	vsi = btf_var_secinfos(t_datasec);
 
-		name = **argv;
-		if (strlen(name) > BPF_OBJ_NAME_LEN - 1) {
-			p_err("can't parse name");
-			return -1;
-		}
-		NEXT_ARGP();
+	/* We don't proceed to check the kinds of the elements of the DATASEC.
+	 * The verifier enforces them to be BTF_KIND_VAR.
+	 */
 
-		return prog_fd_by_nametag(name, fds, false);
-	} else if (is_prefix(**argv, "pinned")) {
-		char *path;
+	if (json_output) {
+		struct btf_dumper d = {
+			.btf = btf,
+			.jw = json_wtr,
+			.is_plain_text = false,
+		};
 
-		NEXT_ARGP();
+		for (i = 0; i < vlen; i++, vsi++) {
+			t_var = btf__type_by_id(btf, vsi->type);
+			name = btf__name_by_offset(btf, t_var->name_off);
 
-		path = **argv;
-		NEXT_ARGP();
+			if (!has_metadata_prefix(name))
+				continue;
 
-		(*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_PROG);
-		if ((*fds)[0] < 0)
-			return -1;
-		return 1;
-	}
+			if (!printed_header) {
+				jsonw_name(json_wtr, "metadata");
+				jsonw_start_object(json_wtr);
+				printed_header = true;
+			}
 
-	p_err("expected 'id', 'tag', 'name' or 'pinned', got: '%s'?", **argv);
-	return -1;
-}
+			jsonw_name(json_wtr, name + BPF_METADATA_PREFIX_LEN);
+			err = btf_dumper_type(&d, t_var->type, value + vsi->offset);
+			if (err) {
+				p_err("btf dump failed: %d", err);
+				break;
+			}
+		}
+		if (printed_header)
+			jsonw_end_object(json_wtr);
+	} else {
+		json_writer_t *btf_wtr;
+		struct btf_dumper d = {
+			.btf = btf,
+			.is_plain_text = true,
+		};
 
-int prog_parse_fd(int *argc, char ***argv)
-{
-	int *fds = NULL;
-	int nb_fds, fd;
+		for (i = 0; i < vlen; i++, vsi++) {
+			t_var = btf__type_by_id(btf, vsi->type);
+			name = btf__name_by_offset(btf, t_var->name_off);
 
-	fds = malloc(sizeof(int));
-	if (!fds) {
-		p_err("mem alloc failed");
-		return -1;
-	}
-	nb_fds = prog_parse_fds(argc, argv, &fds);
-	if (nb_fds != 1) {
-		if (nb_fds > 1) {
-			p_err("several programs match this handle");
-			while (nb_fds--)
-				close(fds[nb_fds]);
-		}
-		fd = -1;
-		goto exit_free;
-	}
+			if (!has_metadata_prefix(name))
+				continue;
 
-	fd = fds[0];
-exit_free:
-	free(fds);
-	return fd;
-}
+			if (!printed_header) {
+				printf("\tmetadata:");
 
-static void show_prog_maps(int fd, u32 num_maps)
-{
-	struct bpf_prog_info info = {};
-	__u32 len = sizeof(info);
-	__u32 map_ids[num_maps];
-	unsigned int i;
-	int err;
+				btf_wtr = jsonw_new(stdout);
+				if (!btf_wtr) {
+					p_err("jsonw alloc failed");
+					goto out_free;
+				}
+				d.jw = btf_wtr,
 
-	info.nr_map_ids = num_maps;
-	info.map_ids = ptr_to_u64(map_ids);
+				printed_header = true;
+			}
 
-	err = bpf_obj_get_info_by_fd(fd, &info, &len);
-	if (err || !info.nr_map_ids)
-		return;
+			printf("\n\t\t%s = ", name + BPF_METADATA_PREFIX_LEN);
 
-	if (json_output) {
-		jsonw_name(json_wtr, "map_ids");
-		jsonw_start_array(json_wtr);
-		for (i = 0; i < info.nr_map_ids; i++)
-			jsonw_uint(json_wtr, map_ids[i]);
-		jsonw_end_array(json_wtr);
-	} else {
-		printf("  map_ids ");
-		for (i = 0; i < info.nr_map_ids; i++)
-			printf("%u%s", map_ids[i],
-			       i == info.nr_map_ids - 1 ? "" : ",");
+			jsonw_reset(btf_wtr);
+			err = btf_dumper_type(&d, t_var->type, value + vsi->offset);
+			if (err) {
+				p_err("btf dump failed: %d", err);
+				break;
+			}
+		}
+		if (printed_header)
+			jsonw_destroy(&btf_wtr);
 	}
+
+out_free:
+	btf__free(btf);
+	free(value);
 }
 
-static void print_prog_header_json(struct bpf_prog_info *info)
+static void print_prog_header_json(struct bpf_prog_info *info, int fd)
 {
+	const char *prog_type_str;
+	char prog_name[MAX_PROG_FULL_NAME];
+
 	jsonw_uint_field(json_wtr, "id", info->id);
-	if (info->type < ARRAY_SIZE(prog_type_name))
-		jsonw_string_field(json_wtr, "type",
-				   prog_type_name[info->type]);
+	prog_type_str = libbpf_bpf_prog_type_str(info->type);
+
+	if (prog_type_str)
+		jsonw_string_field(json_wtr, "type", prog_type_str);
 	else
 		jsonw_uint_field(json_wtr, "type", info->type);
 
-	if (*info->name)
-		jsonw_string_field(json_wtr, "name", info->name);
+	if (*info->name) {
+		get_prog_full_name(info, fd, prog_name, sizeof(prog_name));
+		jsonw_string_field(json_wtr, "name", prog_name);
+	}
 
 	jsonw_name(json_wtr, "tag");
 	jsonw_printf(json_wtr, "\"" BPF_TAG_FMT "\"",
@@ -285,6 +436,8 @@ static void print_prog_header_json(struct bpf_prog_info *info)
 		jsonw_uint_field(json_wtr, "run_time_ns", info->run_time_ns);
 		jsonw_uint_field(json_wtr, "run_cnt", info->run_cnt);
 	}
+	if (info->recursion_misses)
+		jsonw_uint_field(json_wtr, "recursion_misses", info->recursion_misses);
 }
 
 static void print_prog_json(struct bpf_prog_info *info, int fd)
@@ -292,7 +445,7 @@ static void print_prog_json(struct bpf_prog_info *info, int fd)
 	char *memlock;
 
 	jsonw_start_object(json_wtr);
-	print_prog_header_json(info);
+	print_prog_header_json(info, fd);
 	print_dev_json(info->ifindex, info->netns_dev, info->netns_ino);
 
 	if (info->load_time) {
@@ -317,7 +470,7 @@ static void print_prog_json(struct bpf_prog_info *info, int fd)
 
 	memlock = get_fdinfo(fd, "memlock");
 	if (memlock)
-		jsonw_int_field(json_wtr, "bytes_memlock", atoi(memlock));
+		jsonw_int_field(json_wtr, "bytes_memlock", atoll(memlock));
 	free(memlock);
 
 	if (info->nr_map_ids)
@@ -326,31 +479,40 @@ static void print_prog_json(struct bpf_prog_info *info, int fd)
 	if (info->btf_id)
 		jsonw_int_field(json_wtr, "btf_id", info->btf_id);
 
-	if (!hash_empty(prog_table.table)) {
-		struct pinned_obj *obj;
+	if (!hashmap__empty(prog_table)) {
+		struct hashmap_entry *entry;
 
 		jsonw_name(json_wtr, "pinned");
 		jsonw_start_array(json_wtr);
-		hash_for_each_possible(prog_table.table, obj, hash, info->id) {
-			if (obj->id == info->id)
-				jsonw_string(json_wtr, obj->path);
-		}
+		hashmap__for_each_key_entry(prog_table, entry,
+					    u32_as_hash_field(info->id))
+			jsonw_string(json_wtr, entry->value);
 		jsonw_end_array(json_wtr);
 	}
 
+	emit_obj_refs_json(refs_table, info->id, json_wtr);
+
+	show_prog_metadata(fd, info->nr_map_ids);
+
 	jsonw_end_object(json_wtr);
 }
 
-static void print_prog_header_plain(struct bpf_prog_info *info)
+static void print_prog_header_plain(struct bpf_prog_info *info, int fd)
 {
+	const char *prog_type_str;
+	char prog_name[MAX_PROG_FULL_NAME];
+
 	printf("%u: ", info->id);
-	if (info->type < ARRAY_SIZE(prog_type_name))
-		printf("%s  ", prog_type_name[info->type]);
+	prog_type_str = libbpf_bpf_prog_type_str(info->type);
+	if (prog_type_str)
+		printf("%s  ", prog_type_str);
 	else
 		printf("type %u  ", info->type);
 
-	if (*info->name)
-		printf("name %s  ", info->name);
+	if (*info->name) {
+		get_prog_full_name(info, fd, prog_name, sizeof(prog_name));
+		printf("name %s  ", prog_name);
+	}
 
 	printf("tag ");
 	fprint_hex(stdout, info->tag, BPF_TAG_SIZE, "");
@@ -359,6 +521,8 @@ static void print_prog_header_plain(struct bpf_prog_info *info)
 	if (info->run_time_ns)
 		printf(" run_time_ns %lld run_cnt %lld",
 		       info->run_time_ns, info->run_cnt);
+	if (info->recursion_misses)
+		printf(" recursion_misses %lld", info->recursion_misses);
 	printf("\n");
 }
 
@@ -366,7 +530,7 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd)
 {
 	char *memlock;
 
-	print_prog_header_plain(info);
+	print_prog_header_plain(info, fd);
 
 	if (info->load_time) {
 		char buf[32];
@@ -392,19 +556,22 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd)
 	if (info->nr_map_ids)
 		show_prog_maps(fd, info->nr_map_ids);
 
-	if (!hash_empty(prog_table.table)) {
-		struct pinned_obj *obj;
+	if (!hashmap__empty(prog_table)) {
+		struct hashmap_entry *entry;
 
-		hash_for_each_possible(prog_table.table, obj, hash, info->id) {
-			if (obj->id == info->id)
-				printf("\n\tpinned %s", obj->path);
-		}
+		hashmap__for_each_key_entry(prog_table, entry,
+					    u32_as_hash_field(info->id))
+			printf("\n\tpinned %s", (char *)entry->value);
 	}
 
 	if (info->btf_id)
 		printf("\n\tbtf_id %d", info->btf_id);
 
+	emit_obj_refs_plain(refs_table, info->id, "\n\tpids ");
+
 	printf("\n");
+
+	show_prog_metadata(fd, info->nr_map_ids);
 }
 
 static int show_prog(int fd)
@@ -467,8 +634,16 @@ static int do_show(int argc, char **argv)
 	int err;
 	int fd;
 
-	if (show_pinned)
-		build_pinned_obj_table(&prog_table, BPF_OBJ_PROG);
+	if (show_pinned) {
+		prog_table = hashmap__new(hash_fn_for_key_as_id,
+					  equal_fn_for_key_as_id, NULL);
+		if (IS_ERR(prog_table)) {
+			p_err("failed to create hashmap for pinned paths");
+			return -1;
+		}
+		build_pinned_obj_table(prog_table, BPF_OBJ_PROG);
+	}
+	build_obj_refs_table(&refs_table, BPF_OBJ_PROG);
 
 	if (argc == 2)
 		return do_show_subset(argc, argv);
@@ -510,6 +685,11 @@ static int do_show(int argc, char **argv)
 	if (json_output)
 		jsonw_end_array(json_wtr);
 
+	delete_obj_refs_table(refs_table);
+
+	if (show_pinned)
+		delete_pinned_obj_table(prog_table);
+
 	return err;
 }
 
@@ -525,31 +705,34 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
 	char func_sig[1024];
 	unsigned char *buf;
 	__u32 member_len;
+	int fd, err = -1;
 	ssize_t n;
-	int fd;
 
 	if (mode == DUMP_JITED) {
 		if (info->jited_prog_len == 0 || !info->jited_prog_insns) {
 			p_info("no instructions returned");
 			return -1;
 		}
-		buf = (unsigned char *)(info->jited_prog_insns);
+		buf = u64_to_ptr(info->jited_prog_insns);
 		member_len = info->jited_prog_len;
 	} else {	/* DUMP_XLATED */
 		if (info->xlated_prog_len == 0 || !info->xlated_prog_insns) {
 			p_err("error retrieving insn dump: kernel.kptr_restrict set?");
 			return -1;
 		}
-		buf = (unsigned char *)info->xlated_prog_insns;
+		buf = u64_to_ptr(info->xlated_prog_insns);
 		member_len = info->xlated_prog_len;
 	}
 
-	if (info->btf_id && btf__get_from_id(info->btf_id, &btf)) {
-		p_err("failed to get btf");
-		return -1;
+	if (info->btf_id) {
+		btf = btf__load_from_kernel_by_id(info->btf_id);
+		if (libbpf_get_error(btf)) {
+			p_err("failed to get btf");
+			return -1;
+		}
 	}
 
-	func_info = (void *)info->func_info;
+	func_info = u64_to_ptr(info->func_info);
 
 	if (info->nr_line_info) {
 		prog_linfo = bpf_prog_linfo__new(info);
@@ -562,15 +745,15 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
 		if (fd < 0) {
 			p_err("can't open file %s: %s", filepath,
 			      strerror(errno));
-			return -1;
+			goto exit_free;
 		}
 
 		n = write(fd, buf, member_len);
 		close(fd);
-		if (n != member_len) {
+		if (n != (ssize_t)member_len) {
 			p_err("error writing output file: %s",
 			      n < 0 ? strerror(errno) : "short write");
-			return -1;
+			goto exit_free;
 		}
 
 		if (json_output)
@@ -584,7 +767,7 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
 						     info->netns_ino,
 						     &disasm_opt);
 			if (!name)
-				return -1;
+				goto exit_free;
 		}
 
 		if (info->nr_jited_func_lens && info->jited_func_lens) {
@@ -597,13 +780,13 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
 			__u32 i;
 			if (info->nr_jited_ksyms) {
 				kernel_syms_load(&dd);
-				ksyms = (__u64 *) info->jited_ksyms;
+				ksyms = u64_to_ptr(info->jited_ksyms);
 			}
 
 			if (json_output)
 				jsonw_start_array(json_wtr);
 
-			lens = (__u32 *) info->jited_func_lens;
+			lens = u64_to_ptr(info->jited_func_lens);
 			for (i = 0; i < info->nr_jited_func_lens; i++) {
 				if (ksyms) {
 					sym = kernel_syms_search(&dd, ksyms[i]);
@@ -664,7 +847,7 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
 	} else {
 		kernel_syms_load(&dd);
 		dd.nr_jited_ksyms = info->nr_jited_ksyms;
-		dd.jited_ksyms = (__u64 *) info->jited_ksyms;
+		dd.jited_ksyms = u64_to_ptr(info->jited_ksyms);
 		dd.btf = btf;
 		dd.func_info = func_info;
 		dd.finfo_rec_size = info->func_info_rec_size;
@@ -679,21 +862,28 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
 		kernel_syms_destroy(&dd);
 	}
 
-	return 0;
+	err = 0;
+
+exit_free:
+	btf__free(btf);
+	bpf_prog_linfo__free(prog_linfo);
+	return err;
 }
 
 static int do_dump(int argc, char **argv)
 {
-	struct bpf_prog_info_linear *info_linear;
+	struct bpf_prog_info info;
+	__u32 info_len = sizeof(info);
+	size_t info_data_sz = 0;
+	void *info_data = NULL;
 	char *filepath = NULL;
 	bool opcodes = false;
 	bool visual = false;
 	enum dump_mode mode;
 	bool linum = false;
-	int *fds = NULL;
 	int nb_fds, i = 0;
+	int *fds = NULL;
 	int err = -1;
-	__u64 arrays;
 
 	if (is_prefix(*argv, "jited")) {
 		if (disasm_init())
@@ -753,43 +943,44 @@ static int do_dump(int argc, char **argv)
 		goto exit_close;
 	}
 
-	if (mode == DUMP_JITED)
-		arrays = 1UL << BPF_PROG_INFO_JITED_INSNS;
-	else
-		arrays = 1UL << BPF_PROG_INFO_XLATED_INSNS;
-
-	arrays |= 1UL << BPF_PROG_INFO_JITED_KSYMS;
-	arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS;
-	arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO;
-	arrays |= 1UL << BPF_PROG_INFO_LINE_INFO;
-	arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO;
-
 	if (json_output && nb_fds > 1)
 		jsonw_start_array(json_wtr);	/* root array */
 	for (i = 0; i < nb_fds; i++) {
-		info_linear = bpf_program__get_prog_info_linear(fds[i], arrays);
-		if (IS_ERR_OR_NULL(info_linear)) {
+		memset(&info, 0, sizeof(info));
+
+		err = bpf_obj_get_info_by_fd(fds[i], &info, &info_len);
+		if (err) {
+			p_err("can't get prog info: %s", strerror(errno));
+			break;
+		}
+
+		err = prep_prog_info(&info, mode, &info_data, &info_data_sz);
+		if (err) {
+			p_err("can't grow prog info_data");
+			break;
+		}
+
+		err = bpf_obj_get_info_by_fd(fds[i], &info, &info_len);
+		if (err) {
 			p_err("can't get prog info: %s", strerror(errno));
 			break;
 		}
 
 		if (json_output && nb_fds > 1) {
 			jsonw_start_object(json_wtr);	/* prog object */
-			print_prog_header_json(&info_linear->info);
+			print_prog_header_json(&info, fds[i]);
 			jsonw_name(json_wtr, "insns");
 		} else if (nb_fds > 1) {
-			print_prog_header_plain(&info_linear->info);
+			print_prog_header_plain(&info, fds[i]);
 		}
 
-		err = prog_dump(&info_linear->info, mode, filepath, opcodes,
-				visual, linum);
+		err = prog_dump(&info, mode, filepath, opcodes, visual, linum);
 
 		if (json_output && nb_fds > 1)
 			jsonw_end_object(json_wtr);	/* prog object */
 		else if (i != nb_fds - 1 && nb_fds > 1)
 			printf("\n");
 
-		free(info_linear);
 		if (err)
 			break;
 		close(fds[i]);
@@ -801,6 +992,7 @@ exit_close:
 	for (; i < nb_fds; i++)
 		close(fds[i]);
 exit_free:
+	free(info_data);
 	free(fds);
 	return err;
 }
@@ -809,7 +1001,7 @@ static int do_pin(int argc, char **argv)
 {
 	int err;
 
-	err = do_pin_any(argc, argv, bpf_prog_get_fd_by_id);
+	err = do_pin_any(argc, argv, prog_parse_fd);
 	if (!err && json_output)
 		jsonw_null(json_wtr);
 	return err;
@@ -846,7 +1038,7 @@ static int parse_attach_detach_args(int argc, char **argv, int *progfd,
 	}
 
 	if (*attach_type == BPF_FLOW_DISSECTOR) {
-		*mapfd = -1;
+		*mapfd = 0;
 		return 0;
 	}
 
@@ -1068,12 +1260,12 @@ static int do_run(int argc, char **argv)
 {
 	char *data_fname_in = NULL, *data_fname_out = NULL;
 	char *ctx_fname_in = NULL, *ctx_fname_out = NULL;
-	struct bpf_prog_test_run_attr test_attr = {0};
 	const unsigned int default_size = SZ_32K;
 	void *data_in = NULL, *data_out = NULL;
 	void *ctx_in = NULL, *ctx_out = NULL;
 	unsigned int repeat = 1;
 	int fd, err;
+	LIBBPF_OPTS(bpf_test_run_opts, test_attr);
 
 	if (!REQ_ARGS(4))
 		return -1;
@@ -1191,14 +1383,13 @@ static int do_run(int argc, char **argv)
 			goto free_ctx_in;
 	}
 
-	test_attr.prog_fd	= fd;
 	test_attr.repeat	= repeat;
 	test_attr.data_in	= data_in;
 	test_attr.data_out	= data_out;
 	test_attr.ctx_in	= ctx_in;
 	test_attr.ctx_out	= ctx_out;
 
-	err = bpf_prog_test_run_xattr(&test_attr);
+	err = bpf_prog_test_run_opts(fd, &test_attr);
 	if (err) {
 		p_err("failed to run program: %s", strerror(errno));
 		goto free_ctx_out;
@@ -1243,13 +1434,31 @@ free_data_in:
 	return err;
 }
 
+static int
+get_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
+		      enum bpf_attach_type *expected_attach_type)
+{
+	libbpf_print_fn_t print_backup;
+	int ret;
+
+	ret = libbpf_prog_type_by_name(name, prog_type, expected_attach_type);
+	if (!ret)
+		return ret;
+
+	/* libbpf_prog_type_by_name() failed, let's re-run with debug level */
+	print_backup = libbpf_set_print(print_all_levels);
+	ret = libbpf_prog_type_by_name(name, prog_type, expected_attach_type);
+	libbpf_set_print(print_backup);
+
+	return ret;
+}
+
 static int load_with_options(int argc, char **argv, bool first_prog_only)
 {
 	enum bpf_prog_type common_prog_type = BPF_PROG_TYPE_UNSPEC;
 	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts,
 		.relaxed_maps = relaxed_maps,
 	);
-	struct bpf_object_load_attr load_attr = { 0 };
 	enum bpf_attach_type expected_attach_type;
 	struct map_replace *map_replace = NULL;
 	struct bpf_program *prog = NULL, *pos;
@@ -1271,8 +1480,6 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 
 	while (argc) {
 		if (is_prefix(*argv, "type")) {
-			char *type;
-
 			NEXT_ARG();
 
 			if (common_prog_type != BPF_PROG_TYPE_UNSPEC) {
@@ -1282,21 +1489,26 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 			if (!REQ_ARGS(1))
 				goto err_free_reuse_maps;
 
-			/* Put a '/' at the end of type to appease libbpf */
-			type = malloc(strlen(*argv) + 2);
-			if (!type) {
-				p_err("mem alloc failed");
-				goto err_free_reuse_maps;
-			}
-			*type = 0;
-			strcat(type, *argv);
-			strcat(type, "/");
-
-			err = libbpf_prog_type_by_name(type, &common_prog_type,
+			err = libbpf_prog_type_by_name(*argv, &common_prog_type,
 						       &expected_attach_type);
-			free(type);
-			if (err < 0)
-				goto err_free_reuse_maps;
+			if (err < 0) {
+				/* Put a '/' at the end of type to appease libbpf */
+				char *type = malloc(strlen(*argv) + 2);
+
+				if (!type) {
+					p_err("mem alloc failed");
+					goto err_free_reuse_maps;
+				}
+				*type = 0;
+				strcat(type, *argv);
+				strcat(type, "/");
+
+				err = get_prog_type_by_name(type, &common_prog_type,
+							    &expected_attach_type);
+				free(type);
+				if (err < 0)
+					goto err_free_reuse_maps;
+			}
 
 			NEXT_ARG();
 		} else if (is_prefix(*argv, "map")) {
@@ -1334,9 +1546,9 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 			if (fd < 0)
 				goto err_free_reuse_maps;
 
-			new_map_replace = reallocarray(map_replace,
-						       old_map_fds + 1,
-						       sizeof(*map_replace));
+			new_map_replace = libbpf_reallocarray(map_replace,
+							      old_map_fds + 1,
+							      sizeof(*map_replace));
 			if (!new_map_replace) {
 				p_err("mem alloc failed");
 				goto err_free_reuse_maps;
@@ -1380,8 +1592,12 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 
 	set_max_rlimit();
 
+	if (verifier_logs)
+		/* log_level1 + log_level2 + stats, but not stable UAPI */
+		open_opts.kernel_log_level = 1 + 2 + 4;
+
 	obj = bpf_object__open_file(file, &open_opts);
-	if (IS_ERR_OR_NULL(obj)) {
+	if (libbpf_get_error(obj)) {
 		p_err("failed to open object file");
 		goto err_free_reuse_maps;
 	}
@@ -1390,10 +1606,10 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 		enum bpf_prog_type prog_type = common_prog_type;
 
 		if (prog_type == BPF_PROG_TYPE_UNSPEC) {
-			const char *sec_name = bpf_program__title(pos, false);
+			const char *sec_name = bpf_program__section_name(pos);
 
-			err = libbpf_prog_type_by_name(sec_name, &prog_type,
-						       &expected_attach_type);
+			err = get_prog_type_by_name(sec_name, &prog_type,
+						    &expected_attach_type);
 			if (err < 0)
 				goto err_close_obj;
 		}
@@ -1434,7 +1650,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 	j = 0;
 	idx = 0;
 	bpf_object__for_each_map(map, obj) {
-		if (!bpf_map__is_offload_neutral(map))
+		if (bpf_map__type(map) != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
 			bpf_map__set_ifindex(map, ifindex);
 
 		if (j < old_map_fds && idx == map_replace[j].idx) {
@@ -1459,12 +1675,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 		goto err_close_obj;
 	}
 
-	load_attr.obj = obj;
-	if (verifier_logs)
-		/* log_level1 + log_level2 + stats, but not stable UAPI */
-		load_attr.log_level = 1 + 2 + 4;
-
-	err = bpf_object__load_xattr(&load_attr);
+	err = bpf_object__load(obj);
 	if (err) {
 		p_err("failed to load object file");
 		goto err_close_obj;
@@ -1475,7 +1686,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 		goto err_close_obj;
 
 	if (first_prog_only) {
-		prog = bpf_program__next(NULL, obj);
+		prog = bpf_object__next_program(obj, NULL);
 		if (!prog) {
 			p_err("object file doesn't contain any bpf program");
 			goto err_close_obj;
@@ -1484,7 +1695,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 		err = bpf_obj_pin(bpf_program__fd(prog), pinfile);
 		if (err) {
 			p_err("failed to pin program %s",
-			      bpf_program__title(prog, false));
+			      bpf_program__section_name(prog));
 			goto err_close_obj;
 		}
 	} else {
@@ -1519,6 +1730,11 @@ err_unpin:
 	else
 		bpf_object__unpin_programs(obj, pinfile);
 err_close_obj:
+	if (!legacy_libbpf) {
+		p_info("Warning: bpftool is now running in libbpf strict mode and has more stringent requirements about BPF programs.\n"
+		       "If it used to work for this object file but now doesn't, see --legacy option for more details.\n");
+	}
+
 	bpf_object__close(obj);
 err_free_reuse_maps:
 	for (i = 0; i < old_map_fds; i++)
@@ -1527,8 +1743,110 @@ err_free_reuse_maps:
 	return -1;
 }
 
+static int count_open_fds(void)
+{
+	DIR *dp = opendir("/proc/self/fd");
+	struct dirent *de;
+	int cnt = -3;
+
+	if (!dp)
+		return -1;
+
+	while ((de = readdir(dp)))
+		cnt++;
+
+	closedir(dp);
+	return cnt;
+}
+
+static int try_loader(struct gen_loader_opts *gen)
+{
+	struct bpf_load_and_run_opts opts = {};
+	struct bpf_loader_ctx *ctx;
+	int ctx_sz = sizeof(*ctx) + 64 * max(sizeof(struct bpf_map_desc),
+					     sizeof(struct bpf_prog_desc));
+	int log_buf_sz = (1u << 24) - 1;
+	int err, fds_before, fd_delta;
+	char *log_buf = NULL;
+
+	ctx = alloca(ctx_sz);
+	memset(ctx, 0, ctx_sz);
+	ctx->sz = ctx_sz;
+	if (verifier_logs) {
+		ctx->log_level = 1 + 2 + 4;
+		ctx->log_size = log_buf_sz;
+		log_buf = malloc(log_buf_sz);
+		if (!log_buf)
+			return -ENOMEM;
+		ctx->log_buf = (long) log_buf;
+	}
+	opts.ctx = ctx;
+	opts.data = gen->data;
+	opts.data_sz = gen->data_sz;
+	opts.insns = gen->insns;
+	opts.insns_sz = gen->insns_sz;
+	fds_before = count_open_fds();
+	err = bpf_load_and_run(&opts);
+	fd_delta = count_open_fds() - fds_before;
+	if (err < 0 || verifier_logs) {
+		fprintf(stderr, "err %d\n%s\n%s", err, opts.errstr, log_buf);
+		if (fd_delta && err < 0)
+			fprintf(stderr, "loader prog leaked %d FDs\n",
+				fd_delta);
+	}
+	free(log_buf);
+	return err;
+}
+
+static int do_loader(int argc, char **argv)
+{
+	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts);
+	DECLARE_LIBBPF_OPTS(gen_loader_opts, gen);
+	struct bpf_object *obj;
+	const char *file;
+	int err = 0;
+
+	if (!REQ_ARGS(1))
+		return -1;
+	file = GET_ARG();
+
+	if (verifier_logs)
+		/* log_level1 + log_level2 + stats, but not stable UAPI */
+		open_opts.kernel_log_level = 1 + 2 + 4;
+
+	obj = bpf_object__open_file(file, &open_opts);
+	if (libbpf_get_error(obj)) {
+		p_err("failed to open object file");
+		goto err_close_obj;
+	}
+
+	err = bpf_object__gen_loader(obj, &gen);
+	if (err)
+		goto err_close_obj;
+
+	err = bpf_object__load(obj);
+	if (err) {
+		p_err("failed to load object file");
+		goto err_close_obj;
+	}
+
+	if (verifier_logs) {
+		struct dump_data dd = {};
+
+		kernel_syms_load(&dd);
+		dump_xlated_plain(&dd, (void *)gen.insns, gen.insns_sz, false, false);
+		kernel_syms_destroy(&dd);
+	}
+	err = try_loader(&gen);
+err_close_obj:
+	bpf_object__close(obj);
+	return err;
+}
+
 static int do_load(int argc, char **argv)
 {
+	if (use_loader)
+		return do_loader(argc, argv);
 	return load_with_options(argc, argv, true);
 }
 
@@ -1537,6 +1855,473 @@ static int do_loadall(int argc, char **argv)
 	return load_with_options(argc, argv, false);
 }
 
+#ifdef BPFTOOL_WITHOUT_SKELETONS
+
+static int do_profile(int argc, char **argv)
+{
+	p_err("bpftool prog profile command is not supported. Please build bpftool with clang >= 10.0.0");
+	return 0;
+}
+
+#else /* BPFTOOL_WITHOUT_SKELETONS */
+
+#include "profiler.skel.h"
+
+struct profile_metric {
+	const char *name;
+	struct bpf_perf_event_value val;
+	struct perf_event_attr attr;
+	bool selected;
+
+	/* calculate ratios like instructions per cycle */
+	const int ratio_metric; /* 0 for N/A, 1 for index 0 (cycles) */
+	const char *ratio_desc;
+	const float ratio_mul;
+} metrics[] = {
+	{
+		.name = "cycles",
+		.attr = {
+			.type = PERF_TYPE_HARDWARE,
+			.config = PERF_COUNT_HW_CPU_CYCLES,
+			.exclude_user = 1,
+		},
+	},
+	{
+		.name = "instructions",
+		.attr = {
+			.type = PERF_TYPE_HARDWARE,
+			.config = PERF_COUNT_HW_INSTRUCTIONS,
+			.exclude_user = 1,
+		},
+		.ratio_metric = 1,
+		.ratio_desc = "insns per cycle",
+		.ratio_mul = 1.0,
+	},
+	{
+		.name = "l1d_loads",
+		.attr = {
+			.type = PERF_TYPE_HW_CACHE,
+			.config =
+				PERF_COUNT_HW_CACHE_L1D |
+				(PERF_COUNT_HW_CACHE_OP_READ << 8) |
+				(PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16),
+			.exclude_user = 1,
+		},
+	},
+	{
+		.name = "llc_misses",
+		.attr = {
+			.type = PERF_TYPE_HW_CACHE,
+			.config =
+				PERF_COUNT_HW_CACHE_LL |
+				(PERF_COUNT_HW_CACHE_OP_READ << 8) |
+				(PERF_COUNT_HW_CACHE_RESULT_MISS << 16),
+			.exclude_user = 1
+		},
+		.ratio_metric = 2,
+		.ratio_desc = "LLC misses per million insns",
+		.ratio_mul = 1e6,
+	},
+	{
+		.name = "itlb_misses",
+		.attr = {
+			.type = PERF_TYPE_HW_CACHE,
+			.config =
+				PERF_COUNT_HW_CACHE_ITLB |
+				(PERF_COUNT_HW_CACHE_OP_READ << 8) |
+				(PERF_COUNT_HW_CACHE_RESULT_MISS << 16),
+			.exclude_user = 1
+		},
+		.ratio_metric = 2,
+		.ratio_desc = "itlb misses per million insns",
+		.ratio_mul = 1e6,
+	},
+	{
+		.name = "dtlb_misses",
+		.attr = {
+			.type = PERF_TYPE_HW_CACHE,
+			.config =
+				PERF_COUNT_HW_CACHE_DTLB |
+				(PERF_COUNT_HW_CACHE_OP_READ << 8) |
+				(PERF_COUNT_HW_CACHE_RESULT_MISS << 16),
+			.exclude_user = 1
+		},
+		.ratio_metric = 2,
+		.ratio_desc = "dtlb misses per million insns",
+		.ratio_mul = 1e6,
+	},
+};
+
+static __u64 profile_total_count;
+
+#define MAX_NUM_PROFILE_METRICS 4
+
+static int profile_parse_metrics(int argc, char **argv)
+{
+	unsigned int metric_cnt;
+	int selected_cnt = 0;
+	unsigned int i;
+
+	metric_cnt = ARRAY_SIZE(metrics);
+
+	while (argc > 0) {
+		for (i = 0; i < metric_cnt; i++) {
+			if (is_prefix(argv[0], metrics[i].name)) {
+				if (!metrics[i].selected)
+					selected_cnt++;
+				metrics[i].selected = true;
+				break;
+			}
+		}
+		if (i == metric_cnt) {
+			p_err("unknown metric %s", argv[0]);
+			return -1;
+		}
+		NEXT_ARG();
+	}
+	if (selected_cnt > MAX_NUM_PROFILE_METRICS) {
+		p_err("too many (%d) metrics, please specify no more than %d metrics at at time",
+		      selected_cnt, MAX_NUM_PROFILE_METRICS);
+		return -1;
+	}
+	return selected_cnt;
+}
+
+static void profile_read_values(struct profiler_bpf *obj)
+{
+	__u32 m, cpu, num_cpu = obj->rodata->num_cpu;
+	int reading_map_fd, count_map_fd;
+	__u64 counts[num_cpu];
+	__u32 key = 0;
+	int err;
+
+	reading_map_fd = bpf_map__fd(obj->maps.accum_readings);
+	count_map_fd = bpf_map__fd(obj->maps.counts);
+	if (reading_map_fd < 0 || count_map_fd < 0) {
+		p_err("failed to get fd for map");
+		return;
+	}
+
+	err = bpf_map_lookup_elem(count_map_fd, &key, counts);
+	if (err) {
+		p_err("failed to read count_map: %s", strerror(errno));
+		return;
+	}
+
+	profile_total_count = 0;
+	for (cpu = 0; cpu < num_cpu; cpu++)
+		profile_total_count += counts[cpu];
+
+	for (m = 0; m < ARRAY_SIZE(metrics); m++) {
+		struct bpf_perf_event_value values[num_cpu];
+
+		if (!metrics[m].selected)
+			continue;
+
+		err = bpf_map_lookup_elem(reading_map_fd, &key, values);
+		if (err) {
+			p_err("failed to read reading_map: %s",
+			      strerror(errno));
+			return;
+		}
+		for (cpu = 0; cpu < num_cpu; cpu++) {
+			metrics[m].val.counter += values[cpu].counter;
+			metrics[m].val.enabled += values[cpu].enabled;
+			metrics[m].val.running += values[cpu].running;
+		}
+		key++;
+	}
+}
+
+static void profile_print_readings_json(void)
+{
+	__u32 m;
+
+	jsonw_start_array(json_wtr);
+	for (m = 0; m < ARRAY_SIZE(metrics); m++) {
+		if (!metrics[m].selected)
+			continue;
+		jsonw_start_object(json_wtr);
+		jsonw_string_field(json_wtr, "metric", metrics[m].name);
+		jsonw_lluint_field(json_wtr, "run_cnt", profile_total_count);
+		jsonw_lluint_field(json_wtr, "value", metrics[m].val.counter);
+		jsonw_lluint_field(json_wtr, "enabled", metrics[m].val.enabled);
+		jsonw_lluint_field(json_wtr, "running", metrics[m].val.running);
+
+		jsonw_end_object(json_wtr);
+	}
+	jsonw_end_array(json_wtr);
+}
+
+static void profile_print_readings_plain(void)
+{
+	__u32 m;
+
+	printf("\n%18llu %-20s\n", profile_total_count, "run_cnt");
+	for (m = 0; m < ARRAY_SIZE(metrics); m++) {
+		struct bpf_perf_event_value *val = &metrics[m].val;
+		int r;
+
+		if (!metrics[m].selected)
+			continue;
+		printf("%18llu %-20s", val->counter, metrics[m].name);
+
+		r = metrics[m].ratio_metric - 1;
+		if (r >= 0 && metrics[r].selected &&
+		    metrics[r].val.counter > 0) {
+			printf("# %8.2f %-30s",
+			       val->counter * metrics[m].ratio_mul /
+			       metrics[r].val.counter,
+			       metrics[m].ratio_desc);
+		} else {
+			printf("%-41s", "");
+		}
+
+		if (val->enabled > val->running)
+			printf("(%4.2f%%)",
+			       val->running * 100.0 / val->enabled);
+		printf("\n");
+	}
+}
+
+static void profile_print_readings(void)
+{
+	if (json_output)
+		profile_print_readings_json();
+	else
+		profile_print_readings_plain();
+}
+
+static char *profile_target_name(int tgt_fd)
+{
+	struct bpf_func_info func_info;
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
+	const struct btf_type *t;
+	__u32 func_info_rec_size;
+	struct btf *btf = NULL;
+	char *name = NULL;
+	int err;
+
+	err = bpf_obj_get_info_by_fd(tgt_fd, &info, &info_len);
+	if (err) {
+		p_err("failed to bpf_obj_get_info_by_fd for prog FD %d", tgt_fd);
+		goto out;
+	}
+
+	if (info.btf_id == 0) {
+		p_err("prog FD %d doesn't have valid btf", tgt_fd);
+		goto out;
+	}
+
+	func_info_rec_size = info.func_info_rec_size;
+	if (info.nr_func_info == 0) {
+		p_err("bpf_obj_get_info_by_fd for prog FD %d found 0 func_info", tgt_fd);
+		goto out;
+	}
+
+	memset(&info, 0, sizeof(info));
+	info.nr_func_info = 1;
+	info.func_info_rec_size = func_info_rec_size;
+	info.func_info = ptr_to_u64(&func_info);
+
+	err = bpf_obj_get_info_by_fd(tgt_fd, &info, &info_len);
+	if (err) {
+		p_err("failed to get func_info for prog FD %d", tgt_fd);
+		goto out;
+	}
+
+	btf = btf__load_from_kernel_by_id(info.btf_id);
+	if (libbpf_get_error(btf)) {
+		p_err("failed to load btf for prog FD %d", tgt_fd);
+		goto out;
+	}
+
+	t = btf__type_by_id(btf, func_info.type_id);
+	if (!t) {
+		p_err("btf %d doesn't have type %d",
+		      info.btf_id, func_info.type_id);
+		goto out;
+	}
+	name = strdup(btf__name_by_offset(btf, t->name_off));
+out:
+	btf__free(btf);
+	return name;
+}
+
+static struct profiler_bpf *profile_obj;
+static int profile_tgt_fd = -1;
+static char *profile_tgt_name;
+static int *profile_perf_events;
+static int profile_perf_event_cnt;
+
+static void profile_close_perf_events(struct profiler_bpf *obj)
+{
+	int i;
+
+	for (i = profile_perf_event_cnt - 1; i >= 0; i--)
+		close(profile_perf_events[i]);
+
+	free(profile_perf_events);
+	profile_perf_event_cnt = 0;
+}
+
+static int profile_open_perf_events(struct profiler_bpf *obj)
+{
+	unsigned int cpu, m;
+	int map_fd, pmu_fd;
+
+	profile_perf_events = calloc(
+		sizeof(int), obj->rodata->num_cpu * obj->rodata->num_metric);
+	if (!profile_perf_events) {
+		p_err("failed to allocate memory for perf_event array: %s",
+		      strerror(errno));
+		return -1;
+	}
+	map_fd = bpf_map__fd(obj->maps.events);
+	if (map_fd < 0) {
+		p_err("failed to get fd for events map");
+		return -1;
+	}
+
+	for (m = 0; m < ARRAY_SIZE(metrics); m++) {
+		if (!metrics[m].selected)
+			continue;
+		for (cpu = 0; cpu < obj->rodata->num_cpu; cpu++) {
+			pmu_fd = syscall(__NR_perf_event_open, &metrics[m].attr,
+					 -1/*pid*/, cpu, -1/*group_fd*/, 0);
+			if (pmu_fd < 0 ||
+			    bpf_map_update_elem(map_fd, &profile_perf_event_cnt,
+						&pmu_fd, BPF_ANY) ||
+			    ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) {
+				p_err("failed to create event %s on cpu %d",
+				      metrics[m].name, cpu);
+				return -1;
+			}
+			profile_perf_events[profile_perf_event_cnt++] = pmu_fd;
+		}
+	}
+	return 0;
+}
+
+static void profile_print_and_cleanup(void)
+{
+	profile_close_perf_events(profile_obj);
+	profile_read_values(profile_obj);
+	profile_print_readings();
+	profiler_bpf__destroy(profile_obj);
+
+	close(profile_tgt_fd);
+	free(profile_tgt_name);
+}
+
+static void int_exit(int signo)
+{
+	profile_print_and_cleanup();
+	exit(0);
+}
+
+static int do_profile(int argc, char **argv)
+{
+	int num_metric, num_cpu, err = -1;
+	struct bpf_program *prog;
+	unsigned long duration;
+	char *endptr;
+
+	/* we at least need two args for the prog and one metric */
+	if (!REQ_ARGS(3))
+		return -EINVAL;
+
+	/* parse target fd */
+	profile_tgt_fd = prog_parse_fd(&argc, &argv);
+	if (profile_tgt_fd < 0) {
+		p_err("failed to parse fd");
+		return -1;
+	}
+
+	/* parse profiling optional duration */
+	if (argc > 2 && is_prefix(argv[0], "duration")) {
+		NEXT_ARG();
+		duration = strtoul(*argv, &endptr, 0);
+		if (*endptr)
+			usage();
+		NEXT_ARG();
+	} else {
+		duration = UINT_MAX;
+	}
+
+	num_metric = profile_parse_metrics(argc, argv);
+	if (num_metric <= 0)
+		goto out;
+
+	num_cpu = libbpf_num_possible_cpus();
+	if (num_cpu <= 0) {
+		p_err("failed to identify number of CPUs");
+		goto out;
+	}
+
+	profile_obj = profiler_bpf__open();
+	if (!profile_obj) {
+		p_err("failed to open and/or load BPF object");
+		goto out;
+	}
+
+	profile_obj->rodata->num_cpu = num_cpu;
+	profile_obj->rodata->num_metric = num_metric;
+
+	/* adjust map sizes */
+	bpf_map__set_max_entries(profile_obj->maps.events, num_metric * num_cpu);
+	bpf_map__set_max_entries(profile_obj->maps.fentry_readings, num_metric);
+	bpf_map__set_max_entries(profile_obj->maps.accum_readings, num_metric);
+	bpf_map__set_max_entries(profile_obj->maps.counts, 1);
+
+	/* change target name */
+	profile_tgt_name = profile_target_name(profile_tgt_fd);
+	if (!profile_tgt_name)
+		goto out;
+
+	bpf_object__for_each_program(prog, profile_obj->obj) {
+		err = bpf_program__set_attach_target(prog, profile_tgt_fd,
+						     profile_tgt_name);
+		if (err) {
+			p_err("failed to set attach target\n");
+			goto out;
+		}
+	}
+
+	set_max_rlimit();
+	err = profiler_bpf__load(profile_obj);
+	if (err) {
+		p_err("failed to load profile_obj");
+		goto out;
+	}
+
+	err = profile_open_perf_events(profile_obj);
+	if (err)
+		goto out;
+
+	err = profiler_bpf__attach(profile_obj);
+	if (err) {
+		p_err("failed to attach profile_obj");
+		goto out;
+	}
+	signal(SIGINT, int_exit);
+
+	sleep(duration);
+	profile_print_and_cleanup();
+	return 0;
+
+out:
+	profile_close_perf_events(profile_obj);
+	if (profile_obj)
+		profiler_bpf__destroy(profile_obj);
+	close(profile_tgt_fd);
+	free(profile_tgt_name);
+	return err;
+}
+
+#endif /* BPFTOOL_WITHOUT_SKELETONS */
+
 static int do_help(int argc, char **argv)
 {
 	if (json_output) {
@@ -1545,23 +2330,24 @@ static int do_help(int argc, char **argv)
 	}
 
 	fprintf(stderr,
-		"Usage: %s %s { show | list } [PROG]\n"
-		"       %s %s dump xlated PROG [{ file FILE | opcodes | visual | linum }]\n"
-		"       %s %s dump jited  PROG [{ file FILE | opcodes | linum }]\n"
-		"       %s %s pin   PROG FILE\n"
-		"       %s %s { load | loadall } OBJ  PATH \\\n"
+		"Usage: %1$s %2$s { show | list } [PROG]\n"
+		"       %1$s %2$s dump xlated PROG [{ file FILE | opcodes | visual | linum }]\n"
+		"       %1$s %2$s dump jited  PROG [{ file FILE | opcodes | linum }]\n"
+		"       %1$s %2$s pin   PROG FILE\n"
+		"       %1$s %2$s { load | loadall } OBJ  PATH \\\n"
 		"                         [type TYPE] [dev NAME] \\\n"
 		"                         [map { idx IDX | name NAME } MAP]\\\n"
 		"                         [pinmaps MAP_DIR]\n"
-		"       %s %s attach PROG ATTACH_TYPE [MAP]\n"
-		"       %s %s detach PROG ATTACH_TYPE [MAP]\n"
-		"       %s %s run PROG \\\n"
+		"       %1$s %2$s attach PROG ATTACH_TYPE [MAP]\n"
+		"       %1$s %2$s detach PROG ATTACH_TYPE [MAP]\n"
+		"       %1$s %2$s run PROG \\\n"
 		"                         data_in FILE \\\n"
 		"                         [data_out FILE [data_size_out L]] \\\n"
 		"                         [ctx_in FILE [ctx_out FILE [ctx_size_out M]]] \\\n"
 		"                         [repeat N]\n"
-		"       %s %s tracelog\n"
-		"       %s %s help\n"
+		"       %1$s %2$s profile PROG [duration DURATION] METRICs\n"
+		"       %1$s %2$s tracelog\n"
+		"       %1$s %2$s help\n"
 		"\n"
 		"       " HELP_SPEC_MAP "\n"
 		"       " HELP_SPEC_PROGRAM "\n"
@@ -1572,16 +2358,18 @@ static int do_help(int argc, char **argv)
 		"                 sk_reuseport | flow_dissector | cgroup/sysctl |\n"
 		"                 cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n"
 		"                 cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n"
-		"                 cgroup/sendmsg4 | cgroup/sendmsg6 | cgroup/recvmsg4 |\n"
-		"                 cgroup/recvmsg6 | cgroup/getsockopt |\n"
-		"                 cgroup/setsockopt }\n"
-		"       ATTACH_TYPE := { msg_verdict | stream_verdict | stream_parser |\n"
-		"                        flow_dissector }\n"
-		"       " HELP_SPEC_OPTIONS "\n"
+		"                 cgroup/getpeername4 | cgroup/getpeername6 |\n"
+		"                 cgroup/getsockname4 | cgroup/getsockname6 | cgroup/sendmsg4 |\n"
+		"                 cgroup/sendmsg6 | cgroup/recvmsg4 | cgroup/recvmsg6 |\n"
+		"                 cgroup/getsockopt | cgroup/setsockopt | cgroup/sock_release |\n"
+		"                 struct_ops | fentry | fexit | freplace | sk_lookup }\n"
+		"       ATTACH_TYPE := { sk_msg_verdict | sk_skb_verdict | sk_skb_stream_verdict |\n"
+		"                        sk_skb_stream_parser | flow_dissector }\n"
+		"       METRIC := { cycles | instructions | l1d_loads | llc_misses | itlb_misses | dtlb_misses }\n"
+		"       " HELP_SPEC_OPTIONS " |\n"
+		"                    {-f|--bpffs} | {-m|--mapcompat} | {-n|--nomount} |\n"
+		"                    {-L|--use-loader} }\n"
 		"",
-		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
-		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
-		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
 		bin_name, argv[-2]);
 
 	return 0;
@@ -1599,6 +2387,7 @@ static const struct cmd cmds[] = {
 	{ "detach",	do_detach },
 	{ "tracelog",	do_tracelog },
 	{ "run",	do_run },
+	{ "profile",	do_profile },
 	{ 0 }
 };