Merge branch 'next' into for-linus

Prepare input updates for 5.20 (or 6.0) merge window.

1 files changed, 1790 insertions, 393 deletions

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 7f10dd501a52..e89cc9c885b3 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -156,14 +156,6 @@ enum libbpf_strict_mode libbpf_mode = LIBBPF_STRICT_NONE;
 
 int libbpf_set_strict_mode(enum libbpf_strict_mode mode)
 {
-	/* __LIBBPF_STRICT_LAST is the last power-of-2 value used + 1, so to
-	 * get all possible values we compensate last +1, and then (2*x - 1)
-	 * to get the bit mask
-	 */
-	if (mode != LIBBPF_STRICT_ALL
-	    && (mode & ~((__LIBBPF_STRICT_LAST - 1) * 2 - 1)))
-		return errno = EINVAL, -EINVAL;
-
 	libbpf_mode = mode;
 	return 0;
 }
@@ -209,12 +201,6 @@ struct reloc_desc {
 	};
 };
 
-struct bpf_sec_def;
-
-typedef int (*init_fn_t)(struct bpf_program *prog, long cookie);
-typedef int (*preload_fn_t)(struct bpf_program *prog, struct bpf_prog_load_opts *opts, long cookie);
-typedef struct bpf_link *(*attach_fn_t)(const struct bpf_program *prog, long cookie);
-
 /* stored as sec_def->cookie for all libbpf-supported SEC()s */
 enum sec_def_flags {
 	SEC_NONE = 0,
@@ -235,17 +221,22 @@ enum sec_def_flags {
 	SEC_SLEEPABLE = 8,
 	/* allow non-strict prefix matching */
 	SEC_SLOPPY_PFX = 16,
+	/* BPF program support non-linear XDP buffer */
+	SEC_XDP_FRAGS = 32,
+	/* deprecated sec definitions not supposed to be used */
+	SEC_DEPRECATED = 64,
 };
 
 struct bpf_sec_def {
-	const char *sec;
+	char *sec;
 	enum bpf_prog_type prog_type;
 	enum bpf_attach_type expected_attach_type;
 	long cookie;
+	int handler_id;
 
-	init_fn_t init_fn;
-	preload_fn_t preload_fn;
-	attach_fn_t attach_fn;
+	libbpf_prog_setup_fn_t prog_setup_fn;
+	libbpf_prog_prepare_load_fn_t prog_prepare_load_fn;
+	libbpf_prog_attach_fn_t prog_attach_fn;
 };
 
 /*
@@ -311,7 +302,7 @@ struct bpf_program {
 	void *priv;
 	bpf_program_clear_priv_t clear_priv;
 
-	bool load;
+	bool autoload;
 	bool mark_btf_static;
 	enum bpf_prog_type type;
 	enum bpf_attach_type expected_attach_type;
@@ -366,6 +357,7 @@ enum libbpf_map_type {
 };
 
 struct bpf_map {
+	struct bpf_object *obj;
 	char *name;
 	/* real_name is defined for special internal maps (.rodata*,
 	 * .data*, .bss, .kconfig) and preserves their original ELF section
@@ -395,7 +387,7 @@ struct bpf_map {
 	char *pin_path;
 	bool pinned;
 	bool reused;
-	bool skipped;
+	bool autocreate;
 	__u64 map_extra;
 };
 
@@ -492,6 +484,8 @@ struct elf_state {
 	int st_ops_shndx;
 };
 
+struct usdt_manager;
+
 struct bpf_object {
 	char name[BPF_OBJ_NAME_LEN];
 	char license[64];
@@ -554,6 +548,8 @@ struct bpf_object {
 	size_t fd_array_cap;
 	size_t fd_array_cnt;
 
+	struct usdt_manager *usdt_man;
+
 	char path[];
 };
 
@@ -677,7 +673,18 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog,
 	prog->insns_cnt = prog->sec_insn_cnt;
 
 	prog->type = BPF_PROG_TYPE_UNSPEC;
-	prog->load = true;
+
+	/* libbpf's convention for SEC("?abc...") is that it's just like
+	 * SEC("abc...") but the corresponding bpf_program starts out with
+	 * autoload set to false.
+	 */
+	if (sec_name[0] == '?') {
+		prog->autoload = false;
+		/* from now on forget there was ? in section name */
+		sec_name++;
+	} else {
+		prog->autoload = true;
+	}
 
 	prog->instances.fds = NULL;
 	prog->instances.nr = -1;
@@ -1227,10 +1234,8 @@ static void bpf_object__elf_finish(struct bpf_object *obj)
 	if (!obj->efile.elf)
 		return;
 
-	if (obj->efile.elf) {
-		elf_end(obj->efile.elf);
-		obj->efile.elf = NULL;
-	}
+	elf_end(obj->efile.elf);
+	obj->efile.elf = NULL;
 	obj->efile.symbols = NULL;
 	obj->efile.st_ops_data = NULL;
 
@@ -1378,22 +1383,20 @@ static bool bpf_map_type__is_map_in_map(enum bpf_map_type type)
 
 static int find_elf_sec_sz(const struct bpf_object *obj, const char *name, __u32 *size)
 {
-	int ret = -ENOENT;
 	Elf_Data *data;
 	Elf_Scn *scn;
 
-	*size = 0;
 	if (!name)
 		return -EINVAL;
 
 	scn = elf_sec_by_name(obj, name);
 	data = elf_sec_data(obj, scn);
 	if (data) {
-		ret = 0; /* found it */
 		*size = data->d_size;
+		return 0; /* found it */
 	}
 
-	return *size ? 0 : ret;
+	return -ENOENT;
 }
 
 static int find_elf_var_offset(const struct bpf_object *obj, const char *name, __u32 *off)
@@ -1408,8 +1411,11 @@ static int find_elf_var_offset(const struct bpf_object *obj, const char *name, _
 	for (si = 0; si < symbols->d_size / sizeof(Elf64_Sym); si++) {
 		Elf64_Sym *sym = elf_sym_by_idx(obj, si);
 
-		if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL ||
-		    ELF64_ST_TYPE(sym->st_info) != STT_OBJECT)
+		if (ELF64_ST_TYPE(sym->st_info) != STT_OBJECT)
+			continue;
+
+		if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL &&
+		    ELF64_ST_BIND(sym->st_info) != STB_WEAK)
 			continue;
 
 		sname = elf_sym_str(obj, sym->st_name);
@@ -1428,36 +1434,21 @@ static int find_elf_var_offset(const struct bpf_object *obj, const char *name, _
 
 static struct bpf_map *bpf_object__add_map(struct bpf_object *obj)
 {
-	struct bpf_map *new_maps;
-	size_t new_cap;
-	int i;
-
-	if (obj->nr_maps < obj->maps_cap)
-		return &obj->maps[obj->nr_maps++];
-
-	new_cap = max((size_t)4, obj->maps_cap * 3 / 2);
-	new_maps = libbpf_reallocarray(obj->maps, new_cap, sizeof(*obj->maps));
-	if (!new_maps) {
-		pr_warn("alloc maps for object failed\n");
-		return ERR_PTR(-ENOMEM);
-	}
+	struct bpf_map *map;
+	int err;
 
-	obj->maps_cap = new_cap;
-	obj->maps = new_maps;
+	err = libbpf_ensure_mem((void **)&obj->maps, &obj->maps_cap,
+				sizeof(*obj->maps), obj->nr_maps + 1);
+	if (err)
+		return ERR_PTR(err);
 
-	/* zero out new maps */
-	memset(obj->maps + obj->nr_maps, 0,
-	       (obj->maps_cap - obj->nr_maps) * sizeof(*obj->maps));
-	/*
-	 * fill all fd with -1 so won't close incorrect fd (fd=0 is stdin)
-	 * when failure (zclose won't close negative fd)).
-	 */
-	for (i = obj->nr_maps; i < obj->maps_cap; i++) {
-		obj->maps[i].fd = -1;
-		obj->maps[i].inner_map_fd = -1;
-	}
+	map = &obj->maps[obj->nr_maps++];
+	map->obj = obj;
+	map->fd = -1;
+	map->inner_map_fd = -1;
+	map->autocreate = true;
 
-	return &obj->maps[obj->nr_maps++];
+	return map;
 }
 
 static size_t bpf_map_mmap_sz(const struct bpf_map *map)
@@ -1529,6 +1520,9 @@ static char *internal_map_name(struct bpf_object *obj, const char *real_name)
 }
 
 static int
+bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map);
+
+static int
 bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 			      const char *real_name, int sec_idx, void *data, size_t data_sz)
 {
@@ -1575,6 +1569,9 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 		return err;
 	}
 
+	/* failures are fine because of maps like .rodata.str1.1 */
+	(void) bpf_map_find_btf_info(obj, map);
+
 	if (data)
 		memcpy(map->mmaped, data, data_sz);
 
@@ -1937,6 +1934,11 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 	if (obj->efile.maps_shndx < 0)
 		return 0;
 
+	if (libbpf_mode & LIBBPF_STRICT_MAP_DEFINITIONS) {
+		pr_warn("legacy map definitions in SEC(\"maps\") are not supported\n");
+		return -EOPNOTSUPP;
+	}
+
 	if (!symbols)
 		return -EINVAL;
 
@@ -1999,6 +2001,8 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
+		pr_warn("map '%s' (legacy): legacy map definitions are deprecated, use BTF-defined maps instead\n", map_name);
+
 		if (ELF64_ST_BIND(sym->st_info) == STB_LOCAL) {
 			pr_warn("map '%s' (legacy): static maps are not supported\n", map_name);
 			return -ENOTSUP;
@@ -2050,6 +2054,9 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 			}
 			memcpy(&map->def, def, sizeof(struct bpf_map_def));
 		}
+
+		/* btf info may not exist but fill it in if it does exist */
+		(void) bpf_map_find_btf_info(obj, map);
 	}
 	return 0;
 }
@@ -2538,6 +2545,10 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 		fill_map_from_def(map->inner_map, &inner_def);
 	}
 
+	err = bpf_map_find_btf_info(obj, map);
+	if (err)
+		return err;
+
 	return 0;
 }
 
@@ -2740,6 +2751,9 @@ static int bpf_object__init_btf(struct bpf_object *obj,
 		btf__set_pointer_size(obj->btf, 8);
 	}
 	if (btf_ext_data) {
+		struct btf_ext_info *ext_segs[3];
+		int seg_num, sec_num;
+
 		if (!obj->btf) {
 			pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n",
 				 BTF_EXT_ELF_SEC, BTF_ELF_SEC);
@@ -2753,6 +2767,43 @@ static int bpf_object__init_btf(struct bpf_object *obj,
 			obj->btf_ext = NULL;
 			goto out;
 		}
+
+		/* setup .BTF.ext to ELF section mapping */
+		ext_segs[0] = &obj->btf_ext->func_info;
+		ext_segs[1] = &obj->btf_ext->line_info;
+		ext_segs[2] = &obj->btf_ext->core_relo_info;
+		for (seg_num = 0; seg_num < ARRAY_SIZE(ext_segs); seg_num++) {
+			struct btf_ext_info *seg = ext_segs[seg_num];
+			const struct btf_ext_info_sec *sec;
+			const char *sec_name;
+			Elf_Scn *scn;
+
+			if (seg->sec_cnt == 0)
+				continue;
+
+			seg->sec_idxs = calloc(seg->sec_cnt, sizeof(*seg->sec_idxs));
+			if (!seg->sec_idxs) {
+				err = -ENOMEM;
+				goto out;
+			}
+
+			sec_num = 0;
+			for_each_btf_ext_sec(seg, sec) {
+				/* preventively increment index to avoid doing
+				 * this before every continue below
+				 */
+				sec_num++;
+
+				sec_name = btf__name_by_offset(obj->btf, sec->sec_name_off);
+				if (str_is_empty(sec_name))
+					continue;
+				scn = elf_sec_by_name(obj, sec_name);
+				if (!scn)
+					continue;
+
+				seg->sec_idxs[sec_num - 1] = elf_ndxscn(scn);
+			}
+		}
 	}
 out:
 	if (err && libbpf_needs_btf(obj)) {
@@ -2792,7 +2843,7 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf,
 		goto sort_vars;
 
 	ret = find_elf_sec_sz(obj, name, &size);
-	if (ret || !size || (t->size && t->size != size)) {
+	if (ret || !size) {
 		pr_debug("Invalid size for section %s: %u bytes\n", name, size);
 		return -ENOENT;
 	}
@@ -2911,7 +2962,7 @@ static bool obj_needs_vmlinux_btf(const struct bpf_object *obj)
 	}
 
 	bpf_object__for_each_program(prog, obj) {
-		if (!prog->load)
+		if (!prog->autoload)
 			continue;
 		if (prog_needs_vmlinux_btf(prog))
 			return true;
@@ -3836,7 +3887,14 @@ static bool prog_is_subprog(const struct bpf_object *obj,
 	 * .text programs are subprograms (even if they are not called from
 	 * other programs), because libbpf never explicitly supported mixing
 	 * SEC()-designated BPF programs and .text entry-point BPF programs.
+	 *
+	 * In libbpf 1.0 strict mode, we always consider .text
+	 * programs to be subprograms.
 	 */
+
+	if (libbpf_mode & LIBBPF_STRICT_SEC_NAME)
+		return prog->sec_idx == obj->efile.text_shndx;
+
 	return prog->sec_idx == obj->efile.text_shndx && obj->nr_programs > 1;
 }
 
@@ -4181,6 +4239,9 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map)
 	__u32 key_type_id = 0, value_type_id = 0;
 	int ret;
 
+	if (!obj->btf)
+		return -ENOENT;
+
 	/* if it's BTF-defined map, we don't need to search for type IDs.
 	 * For struct_ops map, it does not need btf_key_type_id and
 	 * btf_value_type_id.
@@ -4190,9 +4251,13 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map)
 		return 0;
 
 	if (!bpf_map__is_internal(map)) {
+		pr_warn("Use of BPF_ANNOTATE_KV_PAIR is deprecated, use BTF-defined maps in .maps section instead\n");
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
 		ret = btf__get_map_kv_tids(obj->btf, map->name, def->key_size,
 					   def->value_size, &key_type_id,
 					   &value_type_id);
+#pragma GCC diagnostic pop
 	} else {
 		/*
 		 * LLVM annotates global data differently in BTF, that is,
@@ -4245,6 +4310,20 @@ static int bpf_get_map_info_from_fdinfo(int fd, struct bpf_map_info *info)
 	return 0;
 }
 
+bool bpf_map__autocreate(const struct bpf_map *map)
+{
+	return map->autocreate;
+}
+
+int bpf_map__set_autocreate(struct bpf_map *map, bool autocreate)
+{
+	if (map->obj->loaded)
+		return libbpf_err(-EBUSY);
+
+	map->autocreate = autocreate;
+	return 0;
+}
+
 int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 {
 	struct bpf_map_info info = {};
@@ -4564,7 +4643,7 @@ static int probe_kern_probe_read_kernel(void)
 	};
 	int fd, insn_cnt = ARRAY_SIZE(insns);
 
-	fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", insns, insn_cnt, NULL);
+	fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL);
 	return probe_fd(fd);
 }
 
@@ -4655,6 +4734,18 @@ static int probe_perf_link(void)
 	return link_fd < 0 && err == -EBADF;
 }
 
+static int probe_kern_bpf_cookie(void)
+{
+	struct bpf_insn insns[] = {
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie),
+		BPF_EXIT_INSN(),
+	};
+	int ret, insn_cnt = ARRAY_SIZE(insns);
+
+	ret = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", insns, insn_cnt, NULL);
+	return probe_fd(ret);
+}
+
 enum kern_feature_result {
 	FEAT_UNKNOWN = 0,
 	FEAT_SUPPORTED = 1,
@@ -4717,6 +4808,9 @@ static struct kern_feature_desc {
 	[FEAT_MEMCG_ACCOUNT] = {
 		"memcg-based memory accounting", probe_memcg_account,
 	},
+	[FEAT_BPF_COOKIE] = {
+		"BPF cookie support", probe_kern_bpf_cookie,
+	},
 };
 
 bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id)
@@ -4800,8 +4894,8 @@ bpf_object__reuse_map(struct bpf_map *map)
 	}
 
 	err = bpf_map__reuse_fd(map, pin_fd);
+	close(pin_fd);
 	if (err) {
-		close(pin_fd);
 		return err;
 	}
 	map->pinned = true;
@@ -4849,12 +4943,47 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
 
 static void bpf_map__destroy(struct bpf_map *map);
 
+static bool is_pow_of_2(size_t x)
+{
+	return x && (x & (x - 1));
+}
+
+static size_t adjust_ringbuf_sz(size_t sz)
+{
+	__u32 page_sz = sysconf(_SC_PAGE_SIZE);
+	__u32 mul;
+
+	/* if user forgot to set any size, make sure they see error */
+	if (sz == 0)
+		return 0;
+	/* Kernel expects BPF_MAP_TYPE_RINGBUF's max_entries to be
+	 * a power-of-2 multiple of kernel's page size. If user diligently
+	 * satisified these conditions, pass the size through.
+	 */
+	if ((sz % page_sz) == 0 && is_pow_of_2(sz / page_sz))
+		return sz;
+
+	/* Otherwise find closest (page_sz * power_of_2) product bigger than
+	 * user-set size to satisfy both user size request and kernel
+	 * requirements and substitute correct max_entries for map creation.
+	 */
+	for (mul = 1; mul <= UINT_MAX / page_sz; mul <<= 1) {
+		if (mul * page_sz > sz)
+			return mul * page_sz;
+	}
+
+	/* if it's impossible to satisfy the conditions (i.e., user size is
+	 * very close to UINT_MAX but is not a power-of-2 multiple of
+	 * page_size) then just return original size and let kernel reject it
+	 */
+	return sz;
+}
+
 static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, bool is_inner)
 {
 	LIBBPF_OPTS(bpf_map_create_opts, create_attr);
 	struct bpf_map_def *def = &map->def;
 	const char *map_name = NULL;
-	__u32 max_entries;
 	int err = 0;
 
 	if (kernel_supports(obj, FEAT_PROG_NAME))
@@ -4864,25 +4993,10 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 	create_attr.numa_node = map->numa_node;
 	create_attr.map_extra = map->map_extra;
 
-	if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && !def->max_entries) {
-		int nr_cpus;
-
-		nr_cpus = libbpf_num_possible_cpus();
-		if (nr_cpus < 0) {
-			pr_warn("map '%s': failed to determine number of system CPUs: %d\n",
-				map->name, nr_cpus);
-			return nr_cpus;
-		}
-		pr_debug("map '%s': setting size to %d\n", map->name, nr_cpus);
-		max_entries = nr_cpus;
-	} else {
-		max_entries = def->max_entries;
-	}
-
 	if (bpf_map__is_struct_ops(map))
 		create_attr.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id;
 
-	if (obj->btf && btf__fd(obj->btf) >= 0 && !bpf_map_find_btf_info(obj, map)) {
+	if (obj->btf && btf__fd(obj->btf) >= 0) {
 		create_attr.btf_fd = btf__fd(obj->btf);
 		create_attr.btf_key_type_id = map->btf_key_type_id;
 		create_attr.btf_value_type_id = map->btf_value_type_id;
@@ -4903,6 +5017,9 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 	}
 
 	switch (def->type) {
+	case BPF_MAP_TYPE_RINGBUF:
+		map->def.max_entries = adjust_ringbuf_sz(map->def.max_entries);
+		/* fallthrough */
 	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
 	case BPF_MAP_TYPE_CGROUP_ARRAY:
 	case BPF_MAP_TYPE_STACK_TRACE:
@@ -4916,7 +5033,6 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 	case BPF_MAP_TYPE_SOCKHASH:
 	case BPF_MAP_TYPE_QUEUE:
 	case BPF_MAP_TYPE_STACK:
-	case BPF_MAP_TYPE_RINGBUF:
 		create_attr.btf_fd = 0;
 		create_attr.btf_key_type_id = 0;
 		create_attr.btf_value_type_id = 0;
@@ -4928,7 +5044,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 
 	if (obj->gen_loader) {
 		bpf_gen__map_create(obj->gen_loader, def->type, map_name,
-				    def->key_size, def->value_size, max_entries,
+				    def->key_size, def->value_size, def->max_entries,
 				    &create_attr, is_inner ? -1 : map - obj->maps);
 		/* Pretend to have valid FD to pass various fd >= 0 checks.
 		 * This fd == 0 will not be used with any syscall and will be reset to -1 eventually.
@@ -4937,7 +5053,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 	} else {
 		map->fd = bpf_map_create(def->type, map_name,
 					 def->key_size, def->value_size,
-					 max_entries, &create_attr);
+					 def->max_entries, &create_attr);
 	}
 	if (map->fd < 0 && (create_attr.btf_key_type_id ||
 			    create_attr.btf_value_type_id)) {
@@ -4954,7 +5070,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 		map->btf_value_type_id = 0;
 		map->fd = bpf_map_create(def->type, map_name,
 					 def->key_size, def->value_size,
-					 max_entries, &create_attr);
+					 def->max_entries, &create_attr);
 	}
 
 	err = map->fd < 0 ? -errno : 0;
@@ -5058,6 +5174,24 @@ static int bpf_object_init_prog_arrays(struct bpf_object *obj)
 	return 0;
 }
 
+static int map_set_def_max_entries(struct bpf_map *map)
+{
+	if (map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && !map->def.max_entries) {
+		int nr_cpus;
+
+		nr_cpus = libbpf_num_possible_cpus();
+		if (nr_cpus < 0) {
+			pr_warn("map '%s': failed to determine number of system CPUs: %d\n",
+				map->name, nr_cpus);
+			return nr_cpus;
+		}
+		pr_debug("map '%s': setting size to %d\n", map->name, nr_cpus);
+		map->def.max_entries = nr_cpus;
+	}
+
+	return 0;
+}
+
 static int
 bpf_object__create_maps(struct bpf_object *obj)
 {
@@ -5084,12 +5218,18 @@ bpf_object__create_maps(struct bpf_object *obj)
 		 * bpf_object loading will succeed just fine even on old
 		 * kernels.
 		 */
-		if (bpf_map__is_internal(map) &&
-		    !kernel_supports(obj, FEAT_GLOBAL_DATA)) {
-			map->skipped = true;
+		if (bpf_map__is_internal(map) && !kernel_supports(obj, FEAT_GLOBAL_DATA))
+			map->autocreate = false;
+
+		if (!map->autocreate) {
+			pr_debug("map '%s': skipped auto-creating...\n", map->name);
 			continue;
 		}
 
+		err = map_set_def_max_entries(map);
+		if (err)
+			goto err_out;
+
 		retried = false;
 retry:
 		if (map->pin_path) {
@@ -5185,18 +5325,21 @@ size_t bpf_core_essential_name_len(const char *name)
 	return n;
 }
 
-static void bpf_core_free_cands(struct bpf_core_cand_list *cands)
+void bpf_core_free_cands(struct bpf_core_cand_list *cands)
 {
+	if (!cands)
+		return;
+
 	free(cands->cands);
 	free(cands);
 }
 
-static int bpf_core_add_cands(struct bpf_core_cand *local_cand,
-			      size_t local_essent_len,
-			      const struct btf *targ_btf,
-			      const char *targ_btf_name,
-			      int targ_start_id,
-			      struct bpf_core_cand_list *cands)
+int bpf_core_add_cands(struct bpf_core_cand *local_cand,
+		       size_t local_essent_len,
+		       const struct btf *targ_btf,
+		       const char *targ_btf_name,
+		       int targ_start_id,
+		       struct bpf_core_cand_list *cands)
 {
 	struct bpf_core_cand *new_cands, *cand;
 	const struct btf_type *t, *local_t;
@@ -5523,11 +5666,28 @@ static int record_relo_core(struct bpf_program *prog,
 	return 0;
 }
 
-static int bpf_core_apply_relo(struct bpf_program *prog,
-			       const struct bpf_core_relo *relo,
-			       int relo_idx,
-			       const struct btf *local_btf,
-			       struct hashmap *cand_cache)
+static const struct bpf_core_relo *find_relo_core(struct bpf_program *prog, int insn_idx)
+{
+	struct reloc_desc *relo;
+	int i;
+
+	for (i = 0; i < prog->nr_reloc; i++) {
+		relo = &prog->reloc_desc[i];
+		if (relo->type != RELO_CORE || relo->insn_idx != insn_idx)
+			continue;
+
+		return relo->core_relo;
+	}
+
+	return NULL;
+}
+
+static int bpf_core_resolve_relo(struct bpf_program *prog,
+				 const struct bpf_core_relo *relo,
+				 int relo_idx,
+				 const struct btf *local_btf,
+				 struct hashmap *cand_cache,
+				 struct bpf_core_relo_res *targ_res)
 {
 	struct bpf_core_spec specs_scratch[3] = {};
 	const void *type_key = u32_as_hash_key(relo->type_id);
@@ -5536,20 +5696,7 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 	const struct btf_type *local_type;
 	const char *local_name;
 	__u32 local_id = relo->type_id;
-	struct bpf_insn *insn;
-	int insn_idx, err;
-
-	if (relo->insn_off % BPF_INSN_SZ)
-		return -EINVAL;
-	insn_idx = relo->insn_off / BPF_INSN_SZ;
-	/* adjust insn_idx from section frame of reference to the local
-	 * program's frame of reference; (sub-)program code is not yet
-	 * relocated, so it's enough to just subtract in-section offset
-	 */
-	insn_idx = insn_idx - prog->sec_insn_off;
-	if (insn_idx >= prog->insns_cnt)
-		return -EINVAL;
-	insn = &prog->insns[insn_idx];
+	int err;
 
 	local_type = btf__type_by_id(local_btf, local_id);
 	if (!local_type)
@@ -5559,15 +5706,6 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 	if (!local_name)
 		return -EINVAL;
 
-	if (prog->obj->gen_loader) {
-		const char *spec_str = btf__name_by_offset(local_btf, relo->access_str_off);
-
-		pr_debug("record_relo_core: prog %td insn[%d] %s %s %s final insn_idx %d\n",
-			prog - prog->obj->programs, relo->insn_off / 8,
-			btf_kind_str(local_type), local_name, spec_str, insn_idx);
-		return record_relo_core(prog, relo, insn_idx);
-	}
-
 	if (relo->kind != BPF_CORE_TYPE_ID_LOCAL &&
 	    !hashmap__find(cand_cache, type_key, (void **)&cands)) {
 		cands = bpf_core_find_cands(prog->obj, local_btf, local_id);
@@ -5584,21 +5722,23 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 		}
 	}
 
-	return bpf_core_apply_relo_insn(prog_name, insn, insn_idx, relo,
-					relo_idx, local_btf, cands, specs_scratch);
+	return bpf_core_calc_relo_insn(prog_name, relo, relo_idx, local_btf, cands, specs_scratch,
+				       targ_res);
 }
 
 static int
 bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path)
 {
 	const struct btf_ext_info_sec *sec;
+	struct bpf_core_relo_res targ_res;
 	const struct bpf_core_relo *rec;
 	const struct btf_ext_info *seg;
 	struct hashmap_entry *entry;
 	struct hashmap *cand_cache = NULL;
 	struct bpf_program *prog;
+	struct bpf_insn *insn;
 	const char *sec_name;
-	int i, err = 0, insn_idx, sec_idx;
+	int i, err = 0, insn_idx, sec_idx, sec_num;
 
 	if (obj->btf_ext->core_relo_info.len == 0)
 		return 0;
@@ -5619,54 +5759,75 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path)
 	}
 
 	seg = &obj->btf_ext->core_relo_info;
+	sec_num = 0;
 	for_each_btf_ext_sec(seg, sec) {
+		sec_idx = seg->sec_idxs[sec_num];
+		sec_num++;
+
 		sec_name = btf__name_by_offset(obj->btf, sec->sec_name_off);
 		if (str_is_empty(sec_name)) {
 			err = -EINVAL;
 			goto out;
 		}
-		/* bpf_object's ELF is gone by now so it's not easy to find
-		 * section index by section name, but we can find *any*
-		 * bpf_program within desired section name and use it's
-		 * prog->sec_idx to do a proper search by section index and
-		 * instruction offset
-		 */
-		prog = NULL;
-		for (i = 0; i < obj->nr_programs; i++) {
-			prog = &obj->programs[i];
-			if (strcmp(prog->sec_name, sec_name) == 0)
-				break;
-		}
-		if (!prog) {
-			pr_warn("sec '%s': failed to find a BPF program\n", sec_name);
-			return -ENOENT;
-		}
-		sec_idx = prog->sec_idx;
 
-		pr_debug("sec '%s': found %d CO-RE relocations\n",
-			 sec_name, sec->num_info);
+		pr_debug("sec '%s': found %d CO-RE relocations\n", sec_name, sec->num_info);
 
 		for_each_btf_ext_rec(seg, sec, i, rec) {
+			if (rec->insn_off % BPF_INSN_SZ)
+				return -EINVAL;
 			insn_idx = rec->insn_off / BPF_INSN_SZ;
 			prog = find_prog_by_sec_insn(obj, sec_idx, insn_idx);
 			if (!prog) {
-				pr_warn("sec '%s': failed to find program at insn #%d for CO-RE offset relocation #%d\n",
-					sec_name, insn_idx, i);
-				err = -EINVAL;
-				goto out;
+				/* When __weak subprog is "overridden" by another instance
+				 * of the subprog from a different object file, linker still
+				 * appends all the .BTF.ext info that used to belong to that
+				 * eliminated subprogram.
+				 * This is similar to what x86-64 linker does for relocations.
+				 * So just ignore such relocations just like we ignore
+				 * subprog instructions when discovering subprograms.
+				 */
+				pr_debug("sec '%s': skipping CO-RE relocation #%d for insn #%d belonging to eliminated weak subprogram\n",
+					 sec_name, i, insn_idx);
+				continue;
 			}
 			/* no need to apply CO-RE relocation if the program is
 			 * not going to be loaded
 			 */
-			if (!prog->load)
+			if (!prog->autoload)
+				continue;
+
+			/* adjust insn_idx from section frame of reference to the local
+			 * program's frame of reference; (sub-)program code is not yet
+			 * relocated, so it's enough to just subtract in-section offset
+			 */
+			insn_idx = insn_idx - prog->sec_insn_off;
+			if (insn_idx >= prog->insns_cnt)
+				return -EINVAL;
+			insn = &prog->insns[insn_idx];
+
+			err = record_relo_core(prog, rec, insn_idx);
+			if (err) {
+				pr_warn("prog '%s': relo #%d: failed to record relocation: %d\n",
+					prog->name, i, err);
+				goto out;
+			}
+
+			if (prog->obj->gen_loader)
 				continue;
 
-			err = bpf_core_apply_relo(prog, rec, i, obj->btf, cand_cache);
+			err = bpf_core_resolve_relo(prog, rec, i, obj->btf, cand_cache, &targ_res);
 			if (err) {
 				pr_warn("prog '%s': relo #%d: failed to relocate: %d\n",
 					prog->name, i, err);
 				goto out;
 			}
+
+			err = bpf_core_patch_insn(prog->name, insn, insn_idx, rec, i, &targ_res);
+			if (err) {
+				pr_warn("prog '%s': relo #%d: failed to patch insn #%u: %d\n",
+					prog->name, i, insn_idx, err);
+				goto out;
+			}
 		}
 	}
 
@@ -5684,6 +5845,36 @@ out:
 	return err;
 }
 
+/* base map load ldimm64 special constant, used also for log fixup logic */
+#define MAP_LDIMM64_POISON_BASE 2001000000
+#define MAP_LDIMM64_POISON_PFX "200100"
+
+static void poison_map_ldimm64(struct bpf_program *prog, int relo_idx,
+			       int insn_idx, struct bpf_insn *insn,
+			       int map_idx, const struct bpf_map *map)
+{
+	int i;
+
+	pr_debug("prog '%s': relo #%d: poisoning insn #%d that loads map #%d '%s'\n",
+		 prog->name, relo_idx, insn_idx, map_idx, map->name);
+
+	/* we turn single ldimm64 into two identical invalid calls */
+	for (i = 0; i < 2; i++) {
+		insn->code = BPF_JMP | BPF_CALL;
+		insn->dst_reg = 0;
+		insn->src_reg = 0;
+		insn->off = 0;
+		/* if this instruction is reachable (not a dead code),
+		 * verifier will complain with something like:
+		 * invalid func unknown#2001000123
+		 * where lower 123 is map index into obj->maps[] array
+		 */
+		insn->imm = MAP_LDIMM64_POISON_BASE + map_idx;
+
+		insn++;
+	}
+}
+
 /* Relocate data references within program code:
  *  - map references;
  *  - global variable references;
@@ -5697,33 +5888,35 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
 	for (i = 0; i < prog->nr_reloc; i++) {
 		struct reloc_desc *relo = &prog->reloc_desc[i];
 		struct bpf_insn *insn = &prog->insns[relo->insn_idx];
+		const struct bpf_map *map;
 		struct extern_desc *ext;
 
 		switch (relo->type) {
 		case RELO_LD64:
+			map = &obj->maps[relo->map_idx];
 			if (obj->gen_loader) {
 				insn[0].src_reg = BPF_PSEUDO_MAP_IDX;
 				insn[0].imm = relo->map_idx;
-			} else {
+			} else if (map->autocreate) {
 				insn[0].src_reg = BPF_PSEUDO_MAP_FD;
-				insn[0].imm = obj->maps[relo->map_idx].fd;
+				insn[0].imm = map->fd;
+			} else {
+				poison_map_ldimm64(prog, i, relo->insn_idx, insn,
+						   relo->map_idx, map);
 			}
 			break;
 		case RELO_DATA:
+			map = &obj->maps[relo->map_idx];
 			insn[1].imm = insn[0].imm + relo->sym_off;
 			if (obj->gen_loader) {
 				insn[0].src_reg = BPF_PSEUDO_MAP_IDX_VALUE;
 				insn[0].imm = relo->map_idx;
-			} else {
-				const struct bpf_map *map = &obj->maps[relo->map_idx];
-
-				if (map->skipped) {
-					pr_warn("prog '%s': relo #%d: kernel doesn't support global data\n",
-						prog->name, i);
-					return -ENOTSUP;
-				}
+			} else if (map->autocreate) {
 				insn[0].src_reg = BPF_PSEUDO_MAP_VALUE;
-				insn[0].imm = obj->maps[relo->map_idx].fd;
+				insn[0].imm = map->fd;
+			} else {
+				poison_map_ldimm64(prog, i, relo->insn_idx, insn,
+						   relo->map_idx, map);
 			}
 			break;
 		case RELO_EXTERN_VAR:
@@ -5793,14 +5986,13 @@ static int adjust_prog_btf_ext_info(const struct bpf_object *obj,
 	void *rec, *rec_end, *new_prog_info;
 	const struct btf_ext_info_sec *sec;
 	size_t old_sz, new_sz;
-	const char *sec_name;
-	int i, off_adj;
+	int i, sec_num, sec_idx, off_adj;
 
+	sec_num = 0;
 	for_each_btf_ext_sec(ext_info, sec) {
-		sec_name = btf__name_by_offset(obj->btf, sec->sec_name_off);
-		if (!sec_name)
-			return -EINVAL;
-		if (strcmp(sec_name, prog->sec_name) != 0)
+		sec_idx = ext_info->sec_idxs[sec_num];
+		sec_num++;
+		if (prog->sec_idx != sec_idx)
 			continue;
 
 		for_each_btf_ext_rec(ext_info, sec, i, rec) {
@@ -6195,7 +6387,6 @@ bpf_object__relocate_calls(struct bpf_object *obj, struct bpf_program *prog)
 	if (err)
 		return err;
 
-
 	return 0;
 }
 
@@ -6256,8 +6447,7 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 				err);
 			return err;
 		}
-		if (obj->gen_loader)
-			bpf_object__sort_relos(obj);
+		bpf_object__sort_relos(obj);
 	}
 
 	/* Before relocating calls pre-process relocations and mark
@@ -6293,7 +6483,7 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 		 */
 		if (prog_is_subprog(obj, prog))
 			continue;
-		if (!prog->load)
+		if (!prog->autoload)
 			continue;
 
 		err = bpf_object__relocate_calls(obj, prog);
@@ -6308,7 +6498,7 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 		prog = &obj->programs[i];
 		if (prog_is_subprog(obj, prog))
 			continue;
-		if (!prog->load)
+		if (!prog->autoload)
 			continue;
 		err = bpf_object__relocate_data(obj, prog);
 		if (err) {
@@ -6317,8 +6507,7 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 			return err;
 		}
 	}
-	if (!obj->gen_loader)
-		bpf_object__free_relocs(obj);
+
 	return 0;
 }
 
@@ -6549,9 +6738,9 @@ static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program
 static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attach_name,
 				     int *btf_obj_fd, int *btf_type_id);
 
-/* this is called as prog->sec_def->preload_fn for libbpf-supported sec_defs */
-static int libbpf_preload_prog(struct bpf_program *prog,
-			       struct bpf_prog_load_opts *opts, long cookie)
+/* this is called as prog->sec_def->prog_prepare_load_fn for libbpf-supported sec_defs */
+static int libbpf_prepare_prog_load(struct bpf_program *prog,
+				    struct bpf_prog_load_opts *opts, long cookie)
 {
 	enum sec_def_flags def = cookie;
 
@@ -6562,13 +6751,35 @@ static int libbpf_preload_prog(struct bpf_program *prog,
 	if (def & SEC_SLEEPABLE)
 		opts->prog_flags |= BPF_F_SLEEPABLE;
 
-	if ((prog->type == BPF_PROG_TYPE_TRACING ||
-	     prog->type == BPF_PROG_TYPE_LSM ||
-	     prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) {
+	if (prog->type == BPF_PROG_TYPE_XDP && (def & SEC_XDP_FRAGS))
+		opts->prog_flags |= BPF_F_XDP_HAS_FRAGS;
+
+	if (def & SEC_DEPRECATED) {
+		pr_warn("SEC(\"%s\") is deprecated, please see https://github.com/libbpf/libbpf/wiki/Libbpf-1.0-migration-guide#bpf-program-sec-annotation-deprecations for details\n",
+			prog->sec_name);
+	}
+
+	if ((def & SEC_ATTACH_BTF) && !prog->attach_btf_id) {
 		int btf_obj_fd = 0, btf_type_id = 0, err;
 		const char *attach_name;
 
-		attach_name = str