Merge branch 'BPF static linker: support externs'

Andrii Nakryiko says:

====================

Add BPF static linker support for extern resolution of global variables,
functions, and BTF-defined maps.

This patch set consists of 4 parts:
  - few patches are extending bpftool to simplify working with BTF dump;
  - libbpf object loading logic is extended to support __hidden functions and
    overriden (unused) __weak functions; also BTF-defined map parsing logic is
    refactored to be re-used by linker;
  - the crux of the patch set is BPF static linker logic extension to perform
    extern resolution for three categories: global variables, BPF
    sub-programs, BTF-defined maps;
  - a set of selftests that validate that all the combinations of
    extern/weak/__hidden are working as expected.

See respective patches for more details.

One aspect hasn't been addressed yet and is going to be resolved in the next
patch set, but is worth mentioning. With BPF static linking of multiple .o
files, dealing with static everything becomes more problematic for BPF
skeleton and in general for any by name look up APIs. This is due to static
entities are allowed to have non-unique name. Historically this was never
a problem due to BPF programs were always confined to a single C file. That
changes now and needs to be addressed. The thinking so far is for BPF static
linker to prepend filename to each static variable and static map (which is
currently not supported by libbpf, btw), so that they can be unambiguously
resolved by (mostly) unique name. Mostly, because even filenames can be
duplicated, but that should be rare and easy to address by wiser choice of
filenames by users. Fortunately, static BPF subprograms don't suffer from this
issues, as they are not independent entities and are neither exposed in BPF
skeleton, nor is lookup-able by any of libbpf APIs (and there is little reason
to do that anyways).

This and few other things will be the topic of the next set of patches.

Some tests rely on Clang fix ([0]), so need latest Clang built from main.

  [0] https://reviews.llvm.org/D100362

v2->v3:
  - allow only STV_DEFAULT and STV_HIDDEN ELF symbol visibility (Yonghong);
  - update selftests' README for required Clang 13 fix dependency (Alexei);
  - comments, typos, slight code changes (Yonghong, Alexei);

v1->v2:
  - make map externs support full attribute list, adjust linked_maps selftest
    to demonstrate that typedef works now (though no shared header file was
    added to simplicity sake) (Alexei);
  - remove commented out parts from selftests and fix few minor code style
    issues;
  - special __weak map definition semantics not yet implemented and will be
    addressed in a follow up.
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

tools/bpf/bpftool/btf.c

@@ -71,7 +71,9 @@ static const char *btf_var_linkage_str(__u32 linkage)
 	case BTF_VAR_STATIC:
 		return "static";
 	case BTF_VAR_GLOBAL_ALLOCATED:
-		return "global-alloc";
+		return "global";
+	case BTF_VAR_GLOBAL_EXTERN:
+		return "extern";
 	default:
 		return "(unknown)";
 	}
@@ -98,26 +100,28 @@ static const char *btf_str(const struct btf *btf, __u32 off)
 	return btf__name_by_offset(btf, off) ? : "(invalid)";
 }
 
+static int btf_kind_safe(int kind)
+{
+	return kind <= BTF_KIND_MAX ? kind : BTF_KIND_UNKN;
+}
+
 static int dump_btf_type(const struct btf *btf, __u32 id,
 			 const struct btf_type *t)
 {
 	json_writer_t *w = json_wtr;
-	int kind, safe_kind;
-
-	kind = BTF_INFO_KIND(t->info);
-	safe_kind = kind <= BTF_KIND_MAX ? kind : BTF_KIND_UNKN;
+	int kind = btf_kind(t);
 
 	if (json_output) {
 		jsonw_start_object(w);
 		jsonw_uint_field(w, "id", id);
-		jsonw_string_field(w, "kind", btf_kind_str[safe_kind]);
+		jsonw_string_field(w, "kind", btf_kind_str[btf_kind_safe(kind)]);
 		jsonw_string_field(w, "name", btf_str(btf, t->name_off));
 	} else {
-		printf("[%u] %s '%s'", id, btf_kind_str[safe_kind],
+		printf("[%u] %s '%s'", id, btf_kind_str[btf_kind_safe(kind)],
 		       btf_str(btf, t->name_off));
 	}
 
-	switch (BTF_INFO_KIND(t->info)) {
+	switch (kind) {
 	case BTF_KIND_INT: {
 		__u32 v = *(__u32 *)(t + 1);
 		const char *enc;
@@ -300,7 +304,8 @@ static int dump_btf_type(const struct btf *btf, __u32 id,
 		break;
 	}
 	case BTF_KIND_DATASEC: {
-		const struct btf_var_secinfo *v = (const void *)(t+1);
+		const struct btf_var_secinfo *v = (const void *)(t + 1);
+		const struct btf_type *vt;
 		__u16 vlen = BTF_INFO_VLEN(t->info);
 		int i;
 
@@ -322,6 +327,13 @@ static int dump_btf_type(const struct btf *btf, __u32 id,
 			} else {
 				printf("\n\ttype_id=%u offset=%u size=%u",
 				       v->type, v->offset, v->size);
+
+				if (v->type <= btf__get_nr_types(btf)) {
+					vt = btf__type_by_id(btf, v->type);
+					printf(" (%s '%s')",
+					       btf_kind_str[btf_kind_safe(btf_kind(vt))],
+					       btf_str(btf, vt->name_off));
+				}
 			}
 		}
 		if (json_output)

tools/lib/bpf/bpf_helpers.h

@@ -25,9 +25,16 @@
 /*
  * Helper macro to place programs, maps, license in
  * different sections in elf_bpf file. Section names
- * are interpreted by elf_bpf loader
+ * are interpreted by libbpf depending on the context (BPF programs, BPF maps,
+ * extern variables, etc).
+ * To allow use of SEC() with externs (e.g., for extern .maps declarations),
+ * make sure __attribute__((unused)) doesn't trigger compilation warning.
  */
-#define SEC(NAME) __attribute__((section(NAME), used))
+#define SEC(name) \
+	_Pragma("GCC diagnostic push")					    \
+	_Pragma("GCC diagnostic ignored \"-Wignored-attributes\"")	    \
+	__attribute__((section(name), used))				    \
+	_Pragma("GCC diagnostic pop")					    \
 
 /* Avoid 'linux/stddef.h' definition of '__always_inline'. */
 #undef __always_inline
@@ -40,6 +47,14 @@
 #define __weak __attribute__((weak))
 #endif
 
+/*
+ * Use __hidden attribute to mark a non-static BPF subprogram effectively
+ * static for BPF verifier's verification algorithm purposes, allowing more
+ * extensive and permissive BPF verification process, taking into account
+ * subprogram's caller context.
+ */
+#define __hidden __attribute__((visibility("hidden")))
+
 /* When utilizing vmlinux.h with BPF CO-RE, user BPF programs can't include
  * any system-level headers (such as stddef.h, linux/version.h, etc), and
  * commonly-used macros like NULL and KERNEL_VERSION aren't available through

tools/lib/bpf/btf.c

@@ -1605,11 +1605,6 @@ static void *btf_add_type_mem(struct btf *btf, size_t add_sz)
 			      btf->hdr->type_len, UINT_MAX, add_sz);
 }
 
-static __u32 btf_type_info(int kind, int vlen, int kflag)
-{
-	return (kflag << 31) | (kind << 24) | vlen;
-}
-
 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));

tools/lib/bpf/libbpf.c

@@ -69,8 +69,7 @@
 #define __printf(a, b)	__attribute__((format(printf, a, b)))
 
 static struct bpf_map *bpf_object__add_map(struct bpf_object *obj);
-static const struct btf_type *
-skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id);
+static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog);
 
 static int __base_pr(enum libbpf_print_level level, const char *format,
 		     va_list args)
@@ -274,6 +273,7 @@ struct bpf_program {
 	bpf_program_clear_priv_t clear_priv;
 
 	bool load;
+	bool mark_btf_static;
 	enum bpf_prog_type type;
 	enum bpf_attach_type expected_attach_type;
 	int prog_ifindex;
@@ -500,8 +500,6 @@ static Elf_Scn *elf_sec_by_name(const struct bpf_object *obj, const char *name);
 static int elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn, GElf_Shdr *hdr);
 static const char *elf_sec_name(const struct bpf_object *obj, Elf_Scn *scn);
 static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn);
-static int elf_sym_by_sec_off(const struct bpf_object *obj, size_t sec_idx,
-			      size_t off, __u32 sym_type, GElf_Sym *sym);
 
 void bpf_program__unload(struct bpf_program *prog)
 {
@@ -642,25 +640,29 @@ static int
 bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
 			 const char *sec_name, int sec_idx)
 {
+	Elf_Data *symbols = obj->efile.symbols;
 	struct bpf_program *prog, *progs;
 	void *data = sec_data->d_buf;
-	size_t sec_sz = sec_data->d_size, sec_off, prog_sz;
-	int nr_progs, err;
+	size_t sec_sz = sec_data->d_size, sec_off, prog_sz, nr_syms;
+	int nr_progs, err, i;
 	const char *name;
 	GElf_Sym sym;
 
 	progs = obj->programs;
 	nr_progs = obj->nr_programs;
+	nr_syms = symbols->d_size / sizeof(GElf_Sym);
 	sec_off = 0;
 
-	while (sec_off < sec_sz) {
-		if (elf_sym_by_sec_off(obj, sec_idx, sec_off, STT_FUNC, &sym)) {
-			pr_warn("sec '%s': failed to find program symbol at offset %zu\n",
-				sec_name, sec_off);
-			return -LIBBPF_ERRNO__FORMAT;
-		}
+	for (i = 0; i < nr_syms; i++) {
+		if (!gelf_getsym(symbols, i, &sym))
+			continue;
+		if (sym.st_shndx != sec_idx)
+			continue;
+		if (GELF_ST_TYPE(sym.st_info) != STT_FUNC)
+			continue;
 
 		prog_sz = sym.st_size;
+		sec_off = sym.st_value;
 
 		name = elf_sym_str(obj, sym.st_name);
 		if (!name) {
@@ -698,10 +700,17 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
 		if (err)
 			return err;
 
+		/* if function is a global/weak symbol, but has hidden
+		 * visibility (STV_HIDDEN), mark its BTF FUNC as static to
+		 * enable more permissive BPF verification mode with more
+		 * outside context available to BPF verifier
+		 */
+		if (GELF_ST_BIND(sym.st_info) != STB_LOCAL
+		    && GELF_ST_VISIBILITY(sym.st_other) == STV_HIDDEN)
+			prog->mark_btf_static = true;
+
 		nr_progs++;
 		obj->nr_programs = nr_progs;
-
-		sec_off += prog_sz;
 	}
 
 	return 0;
@@ -1895,7 +1904,7 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 	return 0;
 }
 
-static const struct btf_type *
+const struct btf_type *
 skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id)
 {
 	const struct btf_type *t = btf__type_by_id(btf, id);
@@ -1950,16 +1959,11 @@ static const char *__btf_kind_str(__u16 kind)
 	}
 }
 
-static const char *btf_kind_str(const struct btf_type *t)
+const char *btf_kind_str(const struct btf_type *t)
 {
 	return __btf_kind_str(btf_kind(t));
 }
 
-static enum btf_func_linkage btf_func_linkage(const struct btf_type *t)
-{
-	return (enum btf_func_linkage)BTF_INFO_VLEN(t->info);
-}
-
 /*
  * Fetch integer attribute of BTF map definition. Such attributes are
  * represented using a pointer to an array, in which dimensionality of array
@@ -2014,255 +2018,262 @@ static int build_map_pin_path(struct bpf_map *map, const char *path)
 	return bpf_map__set_pin_path(map, buf);
 }
 
-
-static int parse_btf_map_def(struct bpf_object *obj,
-			     struct bpf_map *map,
-			     const struct btf_type *def,
-			     bool strict, bool is_inner,
-			     const char *pin_root_path)
+int parse_btf_map_def(const char *map_name, struct btf *btf,
+		      const struct btf_type *def_t, bool strict,
+		      struct btf_map_def *map_def, struct btf_map_def *inner_def)
 {
 	const struct btf_type *t;
 	const struct btf_member *m;
+	bool is_inner = inner_def == NULL;
 	int vlen, i;
 
-	vlen = btf_vlen(def);
-	m = btf_members(def);
+	vlen = btf_vlen(def_t);
+	m = btf_members(def_t);
 	for (i = 0; i < vlen; i++, m++) {
-		const char *name = btf__name_by_offset(obj->btf, m->name_off);
+		const char *name = btf__name_by_offset(btf, m->name_off);
 
 		if (!name) {
-			pr_warn("map '%s': invalid field #%d.\n", map->name, i);
+			pr_warn("map '%s': invalid field #%d.\n", map_name, i);
 			return -EINVAL;
 		}
 		if (strcmp(name, "type") == 0) {
-			if (!get_map_field_int(map->name, obj->btf, m,
-					       &map->def.type))
+			if (!get_map_field_int(map_name, btf, m, &map_def->map_type))
 				return -EINVAL;
-			pr_debug("map '%s': found type = %u.\n",
-				 map->name, map->def.type);
+			map_def->parts |= MAP_DEF_MAP_TYPE;
 		} else if (strcmp(name, "max_entries") == 0) {
-			if (!get_map_field_int(map->name, obj->btf, m,
-					       &map->def.max_entries))
+			if (!get_map_field_int(map_name, btf, m, &map_def->max_entries))
 				return -EINVAL;
-			pr_debug("map '%s': found max_entries = %u.\n",
-				 map->name, map->def.max_entries);
+			map_def->parts |= MAP_DEF_MAX_ENTRIES;
 		} else if (strcmp(name, "map_flags") == 0) {
-			if (!get_map_field_int(map->name, obj->btf, m,
-					       &map->def.map_flags))
+			if (!get_map_field_int(map_name, btf, m, &map_def->map_flags))
 				return -EINVAL;
-			pr_debug("map '%s': found map_flags = %u.\n",
-				 map->name, map->def.map_flags);
+			map_def->parts |= MAP_DEF_MAP_FLAGS;
 		} else if (strcmp(name, "numa_node") == 0) {
-			if (!get_map_field_int(map->name, obj->btf, m, &map->numa_node))
+			if (!get_map_field_int(map_name, btf, m, &map_def->numa_node))
 				return -EINVAL;
-			pr_debug("map '%s': found numa_node = %u.\n", map->name, map->numa_node);
+			map_def->parts |= MAP_DEF_NUMA_NODE;
 		} else if (strcmp(name, "key_size") == 0) {
 			__u32 sz;
 
-			if (!get_map_field_int(map->name, obj->btf, m, &sz))
+			if (!get_map_field_int(map_name, btf, m, &sz))
 				return -EINVAL;
-			pr_debug("map '%s': found key_size = %u.\n",
-				 map->name, sz);
-			if (map->def.key_size && map->def.key_size != sz) {
+			if (map_def->key_size && map_def->key_size != sz) {
 				pr_warn("map '%s': conflicting key size %u != %u.\n",
-					map->name, map->def.key_size, sz);
+					map_name, map_def->key_size, sz);
 				return -EINVAL;
 			}
-			map->def.key_size = sz;
+			map_def->key_size = sz;
+			map_def->parts |= MAP_DEF_KEY_SIZE;
 		} else if (strcmp(name, "key") == 0) {
 			__s64 sz;
 
-			t = btf__type_by_id(obj->btf, m->type);
+			t = btf__type_by_id(btf, m->type);
 			if (!t) {
 				pr_warn("map '%s': key type [%d] not found.\n",
-					map->name, m->type);
+					map_name, m->type);
 				return -EINVAL;
 			}
 			if (!btf_is_ptr(t)) {
 				pr_warn("map '%s': key spec is not PTR: %s.\n",
-					map->name, btf_kind_str(t));
+					map_name, btf_kind_str(t));
 				return -EINVAL;
 			}
-			sz = btf__resolve_size(obj->btf, t->type);
+			sz = btf__resolve_size(btf, t->type);
 			if (sz < 0) {
 				pr_warn("map '%s': can't determine key size for type [%u]: %zd.\n",
-					map->name, t->type, (ssize_t)sz);
+					map_name, t->type, (ssize_t)sz);
 				return sz;
 			}
-			pr_debug("map '%s': found key [%u], sz = %zd.\n",
-				 map->name, t->type, (ssize_t)sz);
-			if (map->def.key_size && map->def.key_size != sz) {
+			if (map_def->key_size && map_def->key_size != sz) {
 				pr_warn("map '%s': conflicting key size %u != %zd.\n",
-					map->name, map->def.key_size, (ssize_t)sz);
+					map_name, map_def->key_size, (ssize_t)sz);
 				return -EINVAL;
 			}
-			map->def.key_size = sz;
-			map->btf_key_type_id = t->type;
+			map_def->key_size = sz;
+			map_def->key_type_id = t->type;
+			map_def->parts |= MAP_DEF_KEY_SIZE | MAP_DEF_KEY_TYPE;
 		} else if (strcmp(name, "value_size") == 0) {
 			__u32 sz;
 
-			if (!get_map_field_int(map->name, obj->btf, m, &sz))
+			if (!get_map_field_int(map_name, btf, m, &sz))
 				return -EINVAL;
-			pr_debug("map '%s': found value_size = %u.\n",
-				 map->name, sz);
-			if (map->def.value_size && map->def.value_size != sz) {
+			if (map_def->value_size && map_def->value_size != sz) {
 				pr_warn("map '%s': conflicting value size %u != %u.\n",
-					map->name, map->def.value_size, sz);
+					map_name, map_def->value_size, sz);
 				return -EINVAL;
 			}
-			map->def.value_size = sz;
+			map_def->value_size = sz;
+			map_def->parts |= MAP_DEF_VALUE_SIZE;
 		} else if (strcmp(name, "value") == 0) {
 			__s64 sz;
 
-			t = btf__type_by_id(obj->btf, m->type);
+			t = btf__type_by_id(btf, m->type);
 			if (!t) {
 				pr_warn("map '%s': value type [%d] not found.\n",
-					map->name, m->type);
+					map_name, m->type);
 				return -EINVAL;
 			}
 			if (!btf_is_ptr(t)) {
 				pr_warn("map '%s': value spec is not PTR: %s.\n",
-					map->name, btf_kind_str(t));
+					map_name, btf_kind_str(t));
 				return -EINVAL;
 			}
-			sz = btf__resolve_size(obj->btf, t->type);
+			sz = btf__resolve_size(btf, t->type);
 			if (sz < 0) {
 				pr_warn("map '%s': can't determine value size for type [%u]: %zd.\n",
-					map->name, t->type, (ssize_t)sz);
+					map_name, t->type, (ssize_t)sz);
 				return sz;
 			}
-			pr_debug("map '%s': found value [%u], sz = %zd.\n",
-				 map->name, t->type, (ssize_t)sz);
-			if (map->def.value_size && map->def.value_size != sz) {
+			if (map_def->value_size && map_def->value_size != sz) {
 				pr_warn("map '%s': conflicting value size %u != %zd.\n",
-					map->name, map->def.value_size, (ssize_t)sz);
+					map_name, map_def->value_size, (ssize_t)sz);
 				return -EINVAL;
 			}
-			map->def.value_size = sz;
-			map->btf_value_type_id = t->type;
+			map_def->value_size = sz;
+			map_def->value_type_id = t->type;
+			map_def->parts |= MAP_DEF_VALUE_SIZE | MAP_DEF_VALUE_TYPE;
 		}
 		else if (strcmp(name, "values") == 0) {
+			char inner_map_name[128];
 			int err;
 
 			if (is_inner) {
 				pr_warn("map '%s': multi-level inner maps not supported.\n",
-					map->name);
+					map_name);
 				return -ENOTSUP;
 			}
 			if (i != vlen - 1) {
 				pr_warn("map '%s': '%s' member should be last.\n",
-					map->name, name);
+					map_name, name);
 				return -EINVAL;
 			}
-			if (!bpf_map_type__is_map_in_map(map->def.type)) {
+			if (!bpf_map_type__is_map_in_map(map_def->map_type)) {
 				pr_warn("map '%s': should be map-in-map.\n",
-					map->name);
+					map_name);
 				return -ENOTSUP;
 			}
-			if (map->def.value_size && map->def.value_size != 4) {
+			if (map_def->value_size && map_def->value_size != 4) {
 				pr_warn("map '%s': conflicting value size %u != 4.\n",
-					map->name, map->def.value_size);
+					map_name, map_def->value_size);
 				return -EINVAL;
 			}
-			map->def.value_size = 4;
-			t = btf__type_by_id(obj->btf, m->type);
+			map_def->value_size = 4;
+			t = btf__type_by_id(btf, m->type);
 			if (!t) {
 				pr_warn("map '%s': map-in-map inner type [%d] not found.\n",
-					map->name, m->type);
+					map_name, m->type);
 				return -EINVAL;
 			}
 			if (!btf_is_array(t) || btf_array(t)->nelems) {
 				pr_warn("map '%s': map-in-map inner spec is not a zero-sized array.\n",
-					map->name);
+					map_name);
 				return -EINVAL;
 			}
-			t = skip_mods_and_typedefs(obj->btf, btf_array(t)->type,
-						   NULL);
+			t = skip_mods_and_typedefs(btf, btf_array(t)->type, NULL);
 			if (!btf_is_ptr(t)) {
 				pr_warn("map '%s': map-in-map inner def is of unexpected kind %s.\n",
-					map->name, btf_kind_str(t));
+					map_name, btf_kind_str(t));
 				return -EINVAL;
 			}
-			t = skip_mods_and_typedefs(obj->btf, t->type, NULL);
+			t = skip_mods_and_typedefs(btf, t->type, NULL);
 			if (!btf_is_struct(t)) {
 				pr_warn("map '%s': map-in-map inner def is of unexpected kind %s.\n",
-					map->name, btf_kind_str(t));
+					map_name, btf_kind_str(t));
 				return -EINVAL;
 			}
 
-			map->inner_map = calloc(1, sizeof(*map->inner_map));
-			if (!map->inner_map)
-				return -ENOMEM;
-			map->inner_map->fd = -1;
-			map->inner_map->sec_idx = obj->efile.btf_maps_shndx;
-			map->inner_map->name = malloc(strlen(map->name) +
-						      sizeof(".inner") + 1);
-			if (!map->inner_map->name)
-				return -ENOMEM;
-			sprintf(map->inner_map->name, "%s.inner", map->name);
-
-			err = parse_btf_map_def(obj, map->inner_map, t, strict,
-						true /* is_inner */, NULL);
+			snprintf(inner_map_name, sizeof(inner_map_name), "%s.inner", map_name);
+			err = parse_btf_map_def(inner_map_name, btf, t, strict, inner_def, NULL);
 			if (err)
 				return err;
+
+			map_def->parts |= MAP_DEF_INNER_MAP;
 		} else if (strcmp(name, "pinning") == 0) {
 			__u32 val;
-			int err;
 
 			if (is_inner) {
-				pr_debug("map '%s': inner def can't be pinned.\n",
-					 map->name);
+				pr_warn("map '%s': inner def can't be pinned.\n", map_name);
 				return -EINVAL;
 			}
-			if (!get_map_field_int(map->name, obj->btf, m, &val))
+			if (!get_map_field_int(map_name, btf, m, &val))
 				return -EINVAL;
-			pr_debug("map '%s': found pinning = %u.\n",
-				 map->name, val);
-
-			if (val != LIBBPF_PIN_NONE &&
-			    val != LIBBPF_PIN_BY_NAME) {
+			if (val != LIBBPF_PIN_NONE && val != LIBBPF_PIN_BY_NAME) {
 				pr_warn("map '%s': invalid pinning value %u.\n",
-					map->name, val);
+					map_name, val);
 				return -EINVAL;
 			}
-			if (val == LIBBPF_PIN_BY_NAME) {
-				err = build_map_pin_path(map, pin_root_path);
-				if (err) {
-					pr_warn("map '%s': couldn't build pin path.\n",
-						map->name);
-					return err;
-				}
-			}
+			map_def->pinning = val;
+			map_def->parts |= MAP_DEF_PINNING;
 		} else {
 			if (strict) {
-				pr_warn("map '%s': unknown field '%s'.\n",
-					map->name, name);
+				pr_warn("map '%s': unknown field '%s'.\n", map_name, name);
 				return -ENOTSUP;
 			}
-			pr_debug("map '%s': ignoring unknown field '%s'.\n",
-				 map->name, name);
+			pr_debug("map '%s': ignoring unknown field '%s'.\n", map_name, name);
 		}
 	}
 
-	if (map->def.type == BPF_MAP_TYPE_UNSPEC) {
-		pr_warn("map '%s': map type isn't specified.\n", map->name);
+	if (map_def->map_type == BPF_MAP_TYPE_UNSPEC) {
+		pr_warn("map '%s': map type isn't specified.\n", map_name);
 		return -EINVAL;
 	}
 
 	return 0;
 }
 
+static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def)
+{
+	map->def.type = def->map_type;
+	map->def.key_size = def->key_size;
+	map->def.value_size = def->value_size;
+	map->def.max_entries = def->max_entries;
+	map->def.map_flags = def->map_flags;
+
+	map->numa_node = def->numa_node;
+	map->btf_key_type_id = def->key_type_id;
+	map->btf_value_type_id = def->value_type_id;
+
+	if (def->parts & MAP_DEF_MAP_TYPE)
+		pr_debug("map '%s': found type = %u.\n", map->name, def->map_type);
+
+	if (def->parts & MAP_DEF_KEY_TYPE)
+		pr_debug("map '%s': found key [%u], sz = %u.\n",
+			 map->name, def->key_type_id, def->key_size);
+	else if (def->parts & MAP_DEF_KEY_SIZE)
+		pr_debug("map '%s': found key_size = %u.\n", map->name, def->key_size);
+
+	if (def->parts & MAP_DEF_VALUE_TYPE)
+		pr_debug("map '%s': found value [%u], sz = %u.\n",
+			 map->name, def->value_type_id, def->value_size);
+	else if (def->parts & MAP_DEF_VALUE_SIZE)
+		pr_debug("map '%s': found value_size = %u.\n", map->name, def->value_size);
+
+	if (def->parts & MAP_DEF_MAX_ENTRIES)
+		pr_debug("map '%s': found max_entries = %u.\n", map->name, def->max_entries);
+	if (def->parts & MAP_DEF_MAP_FLAGS)
+		pr_debug("map '%s': found map_flags = %u.\n", map->name, def->map_flags);
+	if (def->parts & MAP_DEF_PINNING)
+		pr_debug("map '%s': found pinning = %u.\n", map->name, def->pinning);
+	if (def->parts & MAP_DEF_NUMA_NODE)
+		pr_debug("map '%s': found numa_node = %u.\n", map->name, def->numa_node);
+
+	if (def->parts & MAP_DEF_INNER_MAP)
+		pr_debug("map '%s': found inner map definition.\n", map->name);
+}
+
 static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 					 const struct btf_type *sec,
 					 int var_idx, int sec_idx,
 					 const Elf_Data *data, bool strict,
 					 const char *pin_root_path)
 {
+	struct btf_map_def map_def = {}, inner_def = {};
 	const struct btf_type *var, *def;
 	const struct btf_var_secinfo *vi;
 	const struct btf_var *var_extra;
 	const char *map_name;
 	struct bpf_map *map;
+	int err;
 
 	vi = btf_var_secinfos(sec) + var_idx;
 	var = btf__type_by_id(obj->btf, vi->type);
@@ -2316,7 +2327,35 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 	pr_debug("map '%s': at sec_idx %d, offset %zu.\n",
 		 map_name, map->sec_idx, map->sec_offset);
 
-	return parse_btf_map_def(obj, map, def, strict, false, pin_root_path);
+	err = parse_btf_map_def(map->name, obj->btf, def, strict, &map_def, &inner_def);
+	if (err)
+		return err;
+
+	fill_map_from_def(map, &map_def);
+
+	if (map_def.pinning == LIBBPF_PIN_BY_NAME) {
+		err = build_map_pin_path(map, pin_root_path);
+		if (err) {
+			pr_warn("map '%s': couldn't build pin path.\n", map->name);
+			return err;
+		}
+	}
+
+	if (map_def.parts & MAP_DEF_INNER_MAP) {
+		map->inner_map = calloc(1, sizeof(*map->inner_map));
+		if (!map->inner_map)
+			return -ENOMEM;
+		map->inner_map->fd = -1;
+		map->inner_map->sec_idx = sec_idx;
+		map->inner_map->name = malloc(strlen(map_name) + sizeof(".inner") + 1);
+		if (!map->inner_map->name)
+			return -ENOMEM;
+		sprintf(map->inner_map->name, "%s.inner", map_name);
+
+		fill_map_from_def(map->inner_map, &inner_def);
+	}
+
+	return 0;
 }
 
 static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict,
@@ -2618,7 +2657,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 {
 	struct btf *kern_btf = obj->btf;
 	bool btf_mandatory, sanitize;
-	int err = 0;
+	int i, err = 0;
 
 	if (!obj->btf)
 		return 0;
@@ -2632,6 +2671,38 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 		return 0;
 	}
 
+	/* Even though some subprogs are global/weak, user might prefer more
+	 * permissive BPF verification process that BPF verifier performs for
+	 * static functions, taking into account more context from the caller
+	 * functions. In such case, they need to mark such subprogs with
+	 * __attribute__((visibility("hidden"))) and libbpf will adjust
+	 * corresponding FUNC BTF type to be marked as static and trigger more
+	 * involved BPF verification process.
+	 */
+	for (i = 0; i < obj->nr_programs; i++) {
+		struct bpf_program *prog = &obj->programs[i];
+		struct btf_type *t;
+		const char *name;
+		int j, n;
+
+		if (!prog->mark_btf_static || !prog_is_subprog(obj, prog))
+			continue;
+
+		n = btf__get_nr_types(obj->btf);
+		for (j = 1; j <= n; j++) {
+			t = btf_type_by_id(obj->btf, j);
+			if (!btf_is_func(t) || btf_func_linkage(t) != BTF_FUNC_GLOBAL)
+				continue;
+
+			name = btf__str_by_offset(obj->btf, t->name_off);
+			if (strcmp(name, prog->name) != 0)
+				continue;
+
+			t->info = btf_type_info(BTF_KIND_FUNC, BTF_FUNC_STATIC, 0);
+			break;
+		}
+	}
+
 	sanitize = btf_needs_sanitization(obj);
 	if (sanitize) {
 		const void *raw_data;
@@ -2782,26 +2853,6 @@ static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn)
 	return data;
 }
 
-static int elf_sym_by_sec_off(const struct bpf_object *obj, size_t sec_idx,
-			      size_t off, __u32 sym_type, GElf_Sym *sym)
-{
-	Elf_Data *symbols = obj->efile.symbols;
-	size_t n = symbols->d_size / sizeof(GElf_Sym);
-	int i;
-
-	for (i = 0; i < n; i++) {
-		if (!gelf_getsym(symbols, i, sym))
-			continue;
-		if (sym->st_shndx != sec_idx || sym->st_value != off)
-			continue;
-		if (GELF_ST_TYPE(sym->st_info) != sym_type)
-			continue;
-		return 0;
-	}
-
-	return -ENOENT;
-}
-
 static bool is_sec_name_dwarf(const char *name)
 {
 	/* approximation, but the actual list is too long */
@@ -3680,11 +3731,16 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data
 	int err, i, nrels;
 	const char *sym_name;
 	__u32 insn_idx;
+	Elf_Scn *scn;
+	Elf_Data *scn_data;
 	GElf_Sym sym;
 	GElf_Rel rel;
 
+	scn = elf_sec_by_idx(obj, sec_idx);
+	scn_data = elf_sec_data(obj, scn);
+
 	relo_sec_name = elf_sec_str(obj, shdr->sh_name);
-	sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx));
+	sec_name = elf_sec_name(obj, scn);
 	if (!relo_sec_name || !sec_name)
 		return -EINVAL;
 
@@ -3702,7 +3758,8 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data
 				relo_sec_name, (size_t)GELF_R_SYM(rel.r_info), i);
 			return -LIBBPF_ERRNO__FORMAT;
 		}
-		if (rel.r_offset % BPF_INSN_SZ) {
+
+		if (rel.r_offset % BPF_INSN_SZ || rel.r_offset >= scn_data->d_size) {
 			pr_warn("sec '%s': invalid offset 0x%zx for relo #%d\n",
 				relo_sec_name, (size_t)GELF_R_SYM(rel.r_info), i);
 			return -LIBBPF_ERRNO__FORMAT;
@@ -3726,9 +3783,9 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data
 
 		prog = find_prog_by_sec_insn(obj, sec_idx, insn_idx);
 		if (!prog) {
-			pr_warn("sec '%s': relo #%d: program not found in section '%s' for insn #%u\n",
+			pr_debug("sec '%s': relo #%d: couldn't find program in section '%s' for insn #%u, probably overridden weak function, skipping...\n",
 				relo_sec_name, i, sec_name, insn_idx);
-			return -LIBBPF_ERRNO__RELOC;
+			continue;
 		}
 
 		relos = libbpf_reallocarray(prog->reloc_desc,
@@ -6972,7 +7029,7 @@ static bool insn_is_helper_call(struct bpf_insn *insn, enum bpf_func_id *func_id
 	return false;
 }
 
-static int bpf_object__sanitize_prog(struct bpf_object* obj, struct bpf_program *prog)
+static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program *prog)
 {
 	struct bpf_insn *insn = prog->insns;
 	enum bpf_func_id func_id;

tools/lib/bpf/libbpf_internal.h

@@ -19,6 +19,7 @@
 #pragma GCC poison reallocarray
 
 #include "libbpf.h"
+#include "btf.h"
 
 #ifndef EM_BPF
 #define EM_BPF 247
@@ -131,6 +132,50 @@ struct btf;
 struct btf_type;
 
 struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id);
+const char *btf_kind_str(const struct btf_type *t);
+const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id);
+
+static inline enum btf_func_linkage btf_func_linkage(const struct btf_type *t)
+{
+	return (enum btf_func_linkage)(int)btf_vlen(t);
+}
+
+static inline __u32 btf_type_info(int kind, int vlen, int kflag)
+{
+	return (kflag << 31) | (kind << 24) | vlen;
+}
+
+enum map_def_parts {
+	MAP_DEF_MAP_TYPE	= 0x001,
+	MAP_DEF_KEY_TYPE	= 0x002,
+	MAP_DEF_KEY_SIZE	= 0x004,
+	MAP_DEF_VALUE_TYPE	= 0x008,
+	MAP_DEF_VALUE_SIZE	= 0x010,
+	MAP_DEF_MAX_ENTRIES	= 0x020,
+	MAP_DEF_MAP_FLAGS	= 0x040,
+	MAP_DEF_NUMA_NODE	= 0x080,
+	MAP_DEF_PINNING		= 0x100,
+	MAP_DEF_INNER_MAP	= 0x200,
+
+	MAP_DEF_ALL		= 0x3ff, /* combination of all above */
+};
+
+struct btf_map_def {
+	enum map_def_parts parts;
+	__u32 map_type;
+	__u32 key_type_id;
+	__u32 key_size;
+	__u32 value_type_id;
+	__u32 value_size;
+	__u32 max_entries;
+	__u32 map_flags;
+	__u32 numa_node;
+	__u32 pinning;
+};
+
+int parse_btf_map_def(const char *map_name, struct btf *btf,
+		      const struct btf_type *def_t, bool strict,
+		      struct btf_map_def *map_def, struct btf_map_def *inner_def);
 
 void *libbpf_add_mem(void **data, size_t *cap_cnt, size_t elem_sz,
 		     size_t cur_cnt, size_t max_cnt, size_t add_cnt);

tools/lib/bpf/linker.c

@@ -22,6 +22,8 @@
 #include "libbpf_internal.h"
 #include "strset.h"
 
+#define BTF_EXTERN_SEC ".extern"
+
 struct src_sec {
 	const char *sec_name;
 	/* positional (not necessarily ELF) index in an array of sections */
@@ -74,11 +76,36 @@ struct btf_ext_sec_data {
 	void *recs;
 };
 
+struct glob_sym {
+	/* ELF symbol index */
+	int sym_idx;
+	/* associated section id for .ksyms, .kconfig, etc, but not .extern */
+	int sec_id;
+	/* extern name offset in STRTAB */
+	int name_off;
+	/* optional associated BTF type ID */
+	int btf_id;
+	/* BTF type ID to which VAR/FUNC type is pointing to; used for
+	 * rewriting types when extern VAR/FUNC is resolved to a concrete
+	 * definition
+	 */
+	int underlying_btf_id;
+	/* sec_var index in the corresponding dst_sec, if exists */
+	int var_idx;
+
+	/* extern or resolved/global symbol */
+	bool is_extern;
+	/* weak or strong symbol, never goes back from strong to weak */
+	bool is_weak;
+};
+
 struct dst_sec {
 	char *sec_name;
 	/* positional (not necessarily ELF) index in an array of sections */
 	int id;
 
+	bool ephemeral;
+
 	/* ELF info */
 	size_t sec_idx;
 	Elf_Scn *scn;
@@ -120,22 +147,28 @@ struct bpf_linker {
 
 	struct btf *btf;
 	struct btf_ext *btf_ext;
+
+	/* global (including extern) ELF symbols */
+	int glob_sym_cnt;
+	struct glob_sym *glob_syms;
 };
 
 #define pr_warn_elf(fmt, ...)									\
-do {												\
-	libbpf_print(LIBBPF_WARN, "libbpf: " fmt ": %s\n", ##__VA_ARGS__, elf_errmsg(-1));	\
-} while (0)
+	libbpf_print(LIBBPF_WARN, "libbpf: " fmt ": %s\n", ##__VA_ARGS__, elf_errmsg(-1))
 
 static int init_output_elf(struct bpf_linker *linker, const char *file);
 
 static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, struct src_obj *obj);
 static int linker_sanity_check_elf(struct src_obj *obj);
+static int linker_sanity_check_elf_symtab(struct src_obj *obj, struct src_sec *sec);
+static int linker_sanity_check_elf_relos(struct src_obj *obj, struct src_sec *sec);
 static int linker_sanity_check_btf(struct src_obj *obj);
 static int linker_sanity_check_btf_ext(struct src_obj *obj);
 static int linker_fixup_btf(struct src_obj *obj);
 static int linker_append_sec_data(struct bpf_linker *linker, struct src_obj *obj);
 static int linker_append_elf_syms(struct bpf_linker *linker, struct src_obj *obj);
+static int linker_append_elf_sym(struct bpf_linker *linker, struct src_obj *obj,
+				 Elf64_Sym *sym, const char *sym_name, int src_sym_idx);
 static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *obj);
 static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj);
 static int linker_append_btf_ext(struct bpf_linker *linker, struct src_obj *obj);
@@ -282,7 +315,7 @@ static int init_output_elf(struct bpf_linker *linker, const char *file)
 
 	/* ELF header */
 	linker->elf_hdr = elf64_newehdr(linker->elf);
-	if (!linker->elf_hdr){
+	if (!linker->elf_hdr) {
 		pr_warn_elf("failed to create ELF header");
 		return -EINVAL;
 	}
@@ -663,8 +696,8 @@ static bool is_pow_of_2(size_t x)
 
 static int linker_sanity_check_elf(struct src_obj *obj)
 {
-	struct src_sec *sec, *link_sec;
-	int i, j, n;
+	struct src_sec *sec;
+	int i, err;
 
 	if (!obj->symtab_sec_idx) {
 		pr_warn("ELF is missing SYMTAB section in %s\n", obj->filename);
@@ -692,43 +725,11 @@ static int linker_sanity_check_elf(struct src_obj *obj)
 			return -EINVAL;
 
 		switch (sec->shdr->sh_type) {
-		case SHT_SYMTAB: {
-			Elf64_Sym *sym;
-
-			if (sec->shdr->sh_entsize != sizeof(Elf64_Sym))
-				return -EINVAL;
-			if (sec->shdr->sh_size % sec->shdr->sh_entsize != 0)
-				return -EINVAL;
-
-			if (!sec->shdr->sh_link || sec->shdr->sh_link >= obj->sec_cnt) {
-				pr_warn("ELF SYMTAB section #%zu points to missing STRTAB section #%zu in %s\n",
-					sec->sec_idx, (size_t)sec->shdr->sh_link, obj->filename);
-				return -EINVAL;
-			}
-			link_sec = &obj->secs[sec->shdr->sh_link];
-			if (link_sec->shdr->sh_type != SHT_STRTAB) {
-				pr_warn("ELF SYMTAB section #%zu points to invalid STRTAB section #%zu in %s\n",
-					sec->sec_idx, (size_t)sec->shdr->sh_link, obj->filename);
-				return -EINVAL;
-			}
-
-			n = sec->shdr->sh_size / sec->shdr->sh_entsize;
-			sym = sec->data->d_buf;
-			for (j = 0; j < n; j++, sym++) {
-				if (sym->st_shndx
-				    && sym->st_shndx < SHN_LORESERVE
-				    && sym->st_shndx >= obj->sec_cnt) {
-					pr_warn("ELF sym #%d in section #%zu points to missing section #%zu in %s\n",
-						j, sec->sec_idx, (size_t)sym->st_shndx, obj->filename);
-					return -EINVAL;
-				}
-				if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION) {
-					if (sym->st_value != 0)
-						return -EINVAL;
-				}
-			}
+		case SHT_SYMTAB:
+			err = linker_sanity_check_elf_symtab(obj, sec);
+			if (err)
+				return err;
 			break;
-		}
 		case SHT_STRTAB:
 			break;
 		case SHT_PROGBITS:
@@ -739,87 +740,169 @@ static int linker_sanity_check_elf(struct src_obj *obj)
 			break;
 		case SHT_NOBITS:
 			break;
-		case SHT_REL: {
-			Elf64_Rel *relo;
-			struct src_sec *sym_sec;
+		case SHT_REL:
+			err = linker_sanity_check_elf_relos(obj, sec);
+			if (err)
+				return err;
+			break;
+		case SHT_LLVM_ADDRSIG:
+			break;
+		default:
+			pr_warn("ELF section #%zu (%s) has unrecognized type %zu in %s\n",
+				sec->sec_idx, sec->sec_name, (size_t)sec->shdr->sh_type, obj->filename);
+			return -EINVAL;
+		}
+	}
 
-			if (sec->shdr->sh_entsize != sizeof(Elf64_Rel))
-				return -EINVAL;
-			if (sec->shdr->sh_size % sec->shdr->sh_entsize != 0)
-				return -EINVAL;
+	return 0;
+}
 
-			/* SHT_REL's sh_link should point to SYMTAB */
-			if (sec->shdr->sh_link != obj->symtab_sec_idx) {
-				pr_warn("ELF relo section #%zu points to invalid SYMTAB section #%zu in %s\n",
-					sec->sec_idx, (size_t)sec->shdr->sh_link, obj->filename);
-				return -EINVAL;
-			}
+static int linker_sanity_check_elf_symtab(struct src_obj *obj, struct src_sec *sec)
+{
+	struct src_sec *link_sec;
+	Elf64_Sym *sym;
+	int i, n;
+
+	if (sec->shdr->sh_entsize != sizeof(Elf64_Sym))
+		return -EINVAL;
+	if (sec->shdr->sh_size % sec->shdr->sh_entsize != 0)
+		return -EINVAL;
+
+	if (!sec->shdr->sh_link || sec->shdr->sh_link >= obj->sec_cnt) {
+		pr_warn("ELF SYMTAB section #%zu points to missing STRTAB section #%zu in %s\n",
+			sec->sec_idx, (size_t)sec->shdr->sh_link, obj->filename);
+		return -EINVAL;
+	}
+	link_sec = &obj->secs[sec->shdr->sh_link];
+	if (link_sec->shdr->sh_type != SHT_STRTAB) {
+		pr_warn("ELF SYMTAB section #%zu points to invalid STRTAB section #%zu in %s\n",
+			sec->sec_idx, (size_t)sec->shdr->sh_link, obj->filename);
+		return -EINVAL;
+	}
 
-			/* SHT_REL's sh_info points to relocated section */
-			if (!sec->shdr->sh_info || sec->shdr->sh_info >= obj->sec_cnt) {
-				pr_warn("ELF relo section #%zu points to missing section #%zu in %s\n",
-					sec->sec_idx, (size_t)sec->shdr->sh_info, obj->filename);
+	n = sec->shdr->sh_size / sec->shdr->sh_entsize;
+	sym = sec->data->d_buf;
+	for (i = 0; i < n; i++, sym++) {
+		int sym_type = ELF64_ST_TYPE(sym->st_info);
+		int sym_bind = ELF64_ST_BIND(sym->st_info);
+		int sym_vis = ELF64_ST_VISIBILITY(sym->st_other);
+
+		if (i == 0) {
+			if (sym->st_name != 0 || sym->st_info != 0
+			    || sym->st_other != 0 || sym->st_shndx != 0
+			    || sym->st_value != 0 || sym->st_size != 0) {
+				pr_warn("ELF sym #0 is invalid in %s\n", obj->filename);
 				return -EINVAL;
 			}
-			link_sec = &obj->secs[sec->shdr->sh_info];
+			continue;
+		}
+		if (sym_bind != STB_LOCAL && sym_bind != STB_GLOBAL && sym_bind != STB_WEAK) {
+			pr_warn("ELF sym #%d in section #%zu has unsupported symbol binding %d\n",
+				i, sec->sec_idx, sym_bind);
+			return -EINVAL;
+		}
+		if (sym_vis != STV_DEFAULT && sym_vis != STV_HIDDEN) {
+			pr_warn("ELF sym #%d in section #%zu has unsupported symbol visibility %d\n",
+				i, sec->sec_idx, sym_vis);
+			return -EINVAL;
+		}
+		if (sym->st_shndx == 0) {
+			if (sym_type != STT_NOTYPE || sym_bind == STB_LOCAL
+			    || sym->st_value != 0 || sym->st_size != 0) {
+				pr_warn("ELF sym #%d is invalid extern symbol in %s\n",
+					i, obj->filename);
 
-			/* .rel<secname> -> <secname> pattern is followed */
-			if (strncmp(sec->sec_name, ".rel", sizeof(".rel") - 1) != 0
-			    || strcmp(sec->sec_name + sizeof(".rel") - 1, link_sec->sec_name) != 0) {
-				pr_warn("ELF relo section #%zu name has invalid name in %s\n",
-					sec->sec_idx, obj->filename);
 				return -EINVAL;
 			}
+			continue;
+		}
+		if (sym->st_shndx < SHN_LORESERVE && sym->st_shndx >= obj->sec_cnt) {
+			pr_warn("ELF sym #%d in section #%zu points to missing section #%zu in %s\n",
+				i, sec->sec_idx, (size_t)sym->st_shndx, obj->filename);
+			return -EINVAL;
+		}
+		if (sym_type == STT_SECTION) {
+			if (sym->st_value != 0)
+				return -EINVAL;
+			continue;
+		}
+	}
 
-			/* don't further validate relocations for ignored sections */
-			if (link_sec->skipped)
-				break;
+	return 0;
+}
 
-			/* relocatable section is data or instructions */
-			if (link_sec->shdr->sh_type != SHT_PROGBITS
-			    && link_sec->shdr->sh_type != SHT_NOBITS) {
-				pr_warn("ELF relo section #%zu points to invalid section #%zu in %s\n",
-					sec->sec_idx, (size_t)sec->shdr->sh_info, obj->filename);
-				return -EINVAL;
-			}
+static int linker_sanity_check_elf_relos(struct src_obj *obj, struct src_sec *sec)
+{
+	struct src_sec *link_sec, *sym_sec;
+	Elf64_Rel *relo;
+	int i, n;
 
-			/* check sanity of each relocation */
-			n = sec->shdr->sh_size / sec->shdr->sh_entsize;
-			relo = sec->data->d_buf;
-			sym_sec = &obj->secs[obj->symtab_sec_idx];
-			for (j = 0; j < n; j++, relo++) {
-				size_t sym_idx = ELF64_R_SYM(relo->r_info);
-				size_t sym_type = ELF64_R_TYPE(relo->r_info);
-
-				if (sym_type != R_BPF_64_64 && sym_type != R_BPF_64_32) {
-					pr_warn("ELF relo #%d in section #%zu has unexpected type %zu in %s\n",
-						j, sec->sec_idx, sym_type, obj->filename);
-					return -EINVAL;
-				}
+	if (sec->shdr->sh_entsize != sizeof(Elf64_Rel))
+		return -EINVAL;
+	if (sec->shdr->sh_size % sec->shdr->sh_entsize != 0)
+		return -EINVAL;
 
-				if (!sym_idx || sym_idx * sizeof(Elf64_Sym) >= sym_sec->shdr->sh_size) {
-					pr_warn("ELF relo #%d in section #%zu points to invalid symbol #%zu in %s\n",
-						j, sec->sec_idx, sym_idx, obj->filename);
-					return -EINVAL;
-				}
+	/* SHT_REL's sh_link should point to SYMTAB */
+	if (sec->shdr->sh_link != obj->symtab_sec_idx) {
+		pr_warn("ELF relo section #%zu points to invalid SYMTAB section #%zu in %s\n",
+			sec->sec_idx, (size_t)sec->shdr->sh_link, obj->filename);
+		return -EINVAL;
+	}
 
-				if (link_sec->shdr->sh_flags & SHF_EXECINSTR) {
-					if (relo->r_offset % sizeof(struct bpf_insn) != 0) {
-						pr_warn("ELF relo #%d in section #%zu points to missing symbol #%zu in %s\n",
-							j, sec->sec_idx, sym_idx, obj->filename);
-						return -EINVAL;
-					}
-				}
-			}
-			break;
+	/* SHT_REL's sh_info points to relocated section */
+	if (!sec->shdr->sh_info || sec->shdr->sh_info >= obj->sec_cnt) {
+		pr_warn("ELF relo section #%zu points to missing section #%zu in %s\n",
+			sec->sec_idx, (size_t)sec->shdr->sh_info, obj->filename);
+		return -EINVAL;
+	}
+	link_sec = &obj->secs[sec->shdr->sh_info];
+
+	/* .rel<secname> -> <secname> pattern is followed */
+	if (strncmp(sec->sec_name, ".rel", sizeof(".rel") - 1) != 0
+	    || strcmp(sec->sec_name + sizeof(".rel") - 1, link_sec->sec_name) != 0) {
+		pr_warn("ELF relo section #%zu name has invalid name in %s\n",
+			sec->sec_idx, obj->filename);
+		return -EINVAL;
+	}
+
+	/* don't further validate relocations for ignored sections */
+	if (link_sec->skipped)
+		return 0;
+
+	/* relocatable section is data or instructions */
+	if (link_sec->shdr->sh_type != SHT_PROGBITS && link_sec->shdr->sh_type != SHT_NOBITS) {
+		pr_warn("ELF relo section #%zu points to invalid section #%zu in %s\n",
+			sec->sec_idx, (size_t)sec->shdr->sh_info, obj->filename);
+		return -EINVAL;
+	}
+
+	/* check sanity of each relocation */
+	n = sec->shdr->sh_size / sec->shdr->sh_entsize;
+	relo = sec->data->d_buf;
+	sym_sec = &obj->secs[obj->symtab_sec_idx];
+	for (i = 0; i < n; i++, relo++) {
+		size_t sym_idx = ELF64_R_SYM(relo->r_info);
+		size_t sym_type = ELF64_R_TYPE(relo->r_info);
+
+		if (sym_type != R_BPF_64_64 && sym_type != R_BPF_64_32) {
+			pr_warn("ELF relo #%d in section #%zu has unexpected type %zu in %s\n",
+				i, sec->sec_idx, sym_type, obj->filename);
+			return -EINVAL;
 		}
-		case SHT_LLVM_ADDRSIG:
-			break;
-		default:
-			pr_warn("ELF section #%zu (%s) has unrecognized type %zu in %s\n",
-				sec->sec_idx, sec->sec_name, (size_t)sec->shdr->sh_type, obj->filename);
+
+		if (!sym_idx || sym_idx * sizeof(Elf64_Sym) >= sym_sec->shdr->sh_size) {
+			pr_warn("ELF relo #%d in section #%zu points to invalid symbol #%zu in %s\n",
+				i, sec->sec_idx, sym_idx, obj->filename);
 			return -EINVAL;
 		}
+
+		if (link_sec->shdr->sh_flags & SHF_EXECINSTR) {
+			if (relo->r_offset % sizeof(struct bpf_insn) != 0) {
+				pr_warn("ELF relo #%d in section #%zu points to missing symbol #%zu in %s\n",
+					i, sec->sec_idx, sym_idx, obj->filename);
+				return -EINVAL;
+			}
+		}
 	}
 
 	return 0;
@@ -897,6 +980,7 @@ static int init_sec(struct bpf_linker *linker, struct dst_sec *dst_sec, struct s
 
 	dst_sec->sec_sz = 0;
 	dst_sec->sec_idx = 0;
+	dst_sec->ephemeral = src_sec->ephemeral;
 
 	/* ephemeral sections are just thin section shells lacking most parts */
 	if (src_sec->ephemeral)
@@ -904,13 +988,13 @@ static int init_sec(struct bpf_linker *linker, struct dst_sec *dst_sec, struct s
 
 	scn = elf_newscn(linker->elf);
 	if (!scn)
-		return -1;
+		return -ENOMEM;
 	data = elf_newdata(scn);
 	if (!data)
-		return -1;
+		return -ENOMEM;
 	shdr = elf64_getshdr(scn);
 	if (!shdr)
-		return -1;
+		return -ENOMEM;
 
 	dst_sec->scn = scn;
 	dst_sec->shdr = shdr;
@@ -960,6 +1044,9 @@ static struct dst_sec *find_dst_sec_by_name(struct bpf_linker *linker, const cha
 
 static bool secs_match(struct dst_sec *dst, struct src_sec *src)
 {
+	if (dst->ephemeral || src->ephemeral)
+		return true;
+
 	if (dst->shdr->sh_type != src->shdr->sh_type) {
 		pr_warn("sec %s types mismatch\n", dst->sec_name);
 		return false;
@@ -985,13 +1072,33 @@ static bool sec_content_is_same(struct dst_sec *dst_sec, struct src_sec *src_sec
 	return true;
 }
 
-static int extend_sec(struct dst_sec *dst, struct src_sec *src)
+static int extend_sec(struct bpf_linker *linker, struct dst_sec *dst, struct src_sec *src)
 {
 	void *tmp;
-	size_t dst_align = dst->shdr->sh_addralign;
-	size_t src_align = src->shdr->sh_addralign;
+	size_t dst_align, src_align;
 	size_t dst_align_sz, dst_final_sz;
+	int err;
+
+	/* Ephemeral source section doesn't contribute anything to ELF
+	 * section data.
+	 */
+	if (src->ephemeral)
+		return 0;
+
+	/* Some sections (like .maps) can contain both externs (and thus be
+	 * ephemeral) and non-externs (map definitions). So it's possible that
+	 * it has to be "upgraded" from ephemeral to non-ephemeral when the
+	 * first non-ephemeral entity appears. In such case, we add ELF
+	 * section, data, etc.
+	 */
+	if (dst->ephemeral) {
+		err = init_sec(linker, dst, src);
+		if (err)
+			return err;
+	}
 
+	dst_align = dst->shdr->sh_addralign;
+	src_align = src->shdr->sh_addralign;
 	if (dst_align == 0)
 		dst_align = 1;
 	if (dst_align < src_align)
@@ -1087,10 +1194,7 @@ static int linker_append_sec_data(struct bpf_linker *linker, struct src_obj *obj
 		/* record mapped section index */
 		src_sec->dst_id = dst_sec->id;
 
-		if (src_sec->ephemeral)
-			continue;
-
-		err = extend_sec(dst_sec, src_sec);
+		err = extend_sec(linker, dst_sec, src_sec);
 		if (err)
 			return err;
 	}
@@ -1101,68 +1205,778 @@ static int linker_append_sec_data(struct bpf_linker *linker, struct src_obj *obj
 static int linker_append_elf_syms(struct bpf_linker *linker, struct src_obj *obj)
 {
 	struct src_sec *symtab = &obj->secs[obj->symtab_sec_idx];
-	Elf64_Sym *sym = symtab->data->d_buf, *dst_sym;
-	int i, n = symtab->shdr->sh_size / symtab->shdr->sh_entsize;
+	Elf64_Sym *sym = symtab->data->d_buf;
+	int i, n = symtab->shdr->sh_size / symtab->shdr->sh_entsize, err;
 	int str_sec_idx = symtab->shdr->sh_link;
+	const char *sym_name;
 
 	obj->sym_map = calloc(n + 1, sizeof(*obj->sym_map));
 	if (!obj->sym_map)
 		return -ENOMEM;
 
 	for (i = 0; i < n; i++, sym++) {
-		struct src_sec *src_sec = NULL;
-		struct dst_sec *dst_sec = NULL;
-		const char *sym_name;
-		size_t dst_sym_idx;
-		int name_off;
-
-		/* we already have all-zero initial symbol */
-		if (sym->st_name == 0 && sym->st_info == 0 &&
-		    sym->st_other == 0 && sym->st_shndx == SHN_UNDEF &&
-		    sym->st_value == 0 && sym->st_size ==0)
+		/* We already validated all-zero symbol #0 and we already
+		 * appended it preventively to the final SYMTAB, so skip it.
+		 */
+		if (i == 0)
 			continue;
 
 		sym_name = elf_strptr(obj->elf, str_sec_idx, sym->st_name);
 		if (!sym_name) {
 			pr_warn("can't fetch symbol name for symbol #%d in '%s'\n", i, obj->filename);
-			return -1;
+			return -EINVAL;
+		}
+
+		err = linker_append_elf_sym(linker, obj, sym, sym_name, i);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static Elf64_Sym *get_sym_by_idx(struct bpf_linker *linker, size_t sym_idx)
+{
+	struct dst_sec *symtab = &linker->secs[linker->symtab_sec_idx];
+	Elf64_Sym *syms = symtab->raw_data;
+
+	return &syms[sym_idx];
+}
+
+static struct glob_sym *find_glob_sym(struct bpf_linker *linker, const char *sym_name)
+{
+	struct glob_sym *glob_sym;
+	const char *name;
+	int i;
+
+	for (i = 0; i < linker->glob_sym_cnt; i++) {
+		glob_sym = &linker->glob_syms[i];
+		name = strset__data(linker->strtab_strs) + glob_sym->name_off;
+
+		if (strcmp(name, sym_name) == 0)
+			return glob_sym;
+	}
+
+	return NULL;
+}
+
+static struct glob_sym *add_glob_sym(struct bpf_linker *linker)
+{
+	struct glob_sym *syms, *sym;
+
+	syms = libbpf_reallocarray(linker->glob_syms, linker->glob_sym_cnt + 1,
+				   sizeof(*linker->glob_syms));
+	if (!syms)
+		return NULL;
+
+	sym = &syms[linker->glob_sym_cnt];
+	memset(sym, 0, sizeof(*sym));
+	sym->var_idx = -1;
+
+	linker->glob_syms = syms;
+	linker->glob_sym_cnt++;
+
+	return sym;
+}
+
+static bool glob_sym_btf_matches(const char *sym_name, bool exact,
+				 const struct btf *btf1, __u32 id1,
+				 const struct btf *btf2, __u32 id2)
+{
+	const struct btf_type *t1, *t2;
+	bool is_static1, is_static2;
+	const char *n1, *n2;
+	int i, n;
+
+recur:
+	n1 = n2 = NULL;
+	t1 = skip_mods_and_typedefs(btf1, id1, &id1);
+	t2 = skip_mods_and_typedefs(btf2, id2, &id2);
+
+	/* check if only one side is FWD, otherwise handle with common logic */
+	if (!exact && btf_is_fwd(t1) != btf_is_fwd(t2)) {
+		n1 = btf__str_by_offset(btf1, t1->name_off);
+		n2 = btf__str_by_offset(btf2, t2->name_off);
+		if (strcmp(n1, n2) != 0) {
+			pr_warn("global '%s': incompatible forward declaration names '%s' and '%s'\n",
+				sym_name, n1, n2);
+			return false;
 		}
+		/* validate if FWD kind matches concrete kind */
+		if (btf_is_fwd(t1)) {
+			if (btf_kflag(t1) && btf_is_union(t2))
+				return true;
+			if (!btf_kflag(t1) && btf_is_struct(t2))
+				return true;
+			pr_warn("global '%s': incompatible %s forward declaration and concrete kind %s\n",
+				sym_name, btf_kflag(t1) ? "union" : "struct", btf_kind_str(t2));
+		} else {
+			if (btf_kflag(t2) && btf_is_union(t1))
+				return true;
+			if (!btf_kflag(t2) && btf_is_struct(t1))
+				return true;
+			pr_warn("global '%s': incompatible %s forward declaration and concrete kind %s\n",
+				sym_name, btf_kflag(t2) ? "union" : "struct", btf_kind_str(t1));
+		}
+		return false;
+	}
+
+	if (btf_kind(t1) != btf_kind(t2)) {
+		pr_warn("global '%s': incompatible BTF kinds %s and %s\n",
+			sym_name, btf_kind_str(t1), btf_kind_str(t2));
+		return false;
+	}
+
+	switch (btf_kind(t1)) {
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION:
+	case BTF_KIND_ENUM:
+	case BTF_KIND_FWD:
+	case BTF_KIND_FUNC:
+	case BTF_KIND_VAR:
+		n1 = btf__str_by_offset(btf1, t1->name_off);
+		n2 = btf__str_by_offset(btf2, t2->name_off);
+		if (strcmp(n1, n2) != 0) {
+			pr_warn("global '%s': incompatible %s names '%s' and '%s'\n",
+				sym_name, btf_kind_str(t1), n1, n2);
+			return false;
+		}
+		break;
+	default:
+		break;
+	}
+
+	switch (btf_kind(t1)) {
+	case BTF_KIND_UNKN: /* void */
+	case BTF_KIND_FWD:
+		return true;
+	case BTF_KIND_INT:
+	case BTF_KIND_FLOAT:
+	case BTF_KIND_ENUM:
+		/* ignore encoding for int and enum values for enum */
+		if (t1->size != t2->size) {
+			pr_warn("global '%s': incompatible %s '%s' size %u and %u\n",
+				sym_name, btf_kind_str(t1), n1, t1->size, t2->size);
+			return false;
+		}
+		return true;
+	case BTF_KIND_PTR:
+		/* just validate overall shape of the referenced type, so no
+		 * contents comparison for struct/union, and allowd fwd vs
+		 * struct/union
+		 */
+		exact = false;
+		id1 = t1->type;
+		id2 = t2->type;
+		goto recur;
+	case BTF_KIND_ARRAY:
+		/* ignore index type and array size */
+		id1 = btf_array(t1)->type;
+		id2 = btf_array(t2)->type;
+		goto recur;
+	case BTF_KIND_FUNC:
+		/* extern and global linkages are compatible */
+		is_static1 = btf_func_linkage(t1) == BTF_FUNC_STATIC;
+		is_static2 = btf_func_linkage(t2) == BTF_FUNC_STATIC;
+		if (is_static1 != is_static2) {
+			pr_warn("global '%s': incompatible func '%s' linkage\n", sym_name, n1);
+			return false;
+		}
+
+		id1 = t1->type;
+		id2 = t2->type;
+		goto recur;
+	case BTF_KIND_VAR:
+		/* extern and global linkages are compatible */
+		is_static1 = btf_var(t1)->linkage == BTF_VAR_STATIC;
+		is_static2 = btf_var(t2)->linkage == BTF_VAR_STATIC;
+		if (is_static1 != is_static2) {
+			pr_warn("global '%s': incompatible var '%s' linkage\n", sym_name, n1);
+			return false;
+		}
+
+		id1 = t1->type;
+		id2 = t2->type;
+		goto recur;
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION: {
+		const struct btf_member *m1, *m2;
+
+		if (!exact)
+			return true;
+
+		if (btf_vlen(t1) != btf_vlen(t2)) {
+			pr_warn("global '%s': incompatible number of %s fields %u and %u\n",
+				sym_name, btf_kind_str(t1), btf_vlen(t1), btf_vlen(t2));
+			return false;
+		}
+
+		n = btf_vlen(t1);
+		m1 = btf_members(t1);
+		m2 = btf_members(t2);
+		for (i = 0; i < n; i++, m1++, m2++) {
+			n1 = btf__str_by_offset(btf1, m1->name_off);
+			n2 = btf__str_by_offset(btf2, m2->name_off);
+			if (strcmp(n1, n2) != 0) {
+				pr_warn("global '%s': incompatible field #%d names '%s' and '%s'\n",
+					sym_name, i, n1, n2);
+				return false;
+			}
+			if (m1->offset != m2->offset) {
+				pr_warn("global '%s': incompatible field #%d ('%s') offsets\n",
+					sym_name, i, n1);
+				return false;
+			}
+			if (!glob_sym_btf_matches(sym_name, exact, btf1, m1->type, btf2, m2->type))
+				return false;
+		}
+
+		return true;
+	}
+	case BTF_KIND_FUNC_PROTO: {
+		const struct btf_param *m1, *m2;
+
+		if (btf_vlen(t1) != btf_vlen(t2)) {
+			pr_warn("global '%s': incompatible number of %s params %u and %u\n",
+				sym_name, btf_kind_str(t1), btf_vlen(t1), btf_vlen(t2));
+			return false;
+		}
+
+		n = btf_vlen(t1);
+		m1 = btf_params(t1);
+		m2 = btf_params(t2);
+		for (i = 0; i < n; i++, m1++, m2++) {
+			/* ignore func arg names */
+			if (!glob_sym_btf_matches(sym_name, exact, btf1, m1->type, btf2, m2->type))
+				return false;
+		}
+
+		/* now check return type as well */
+		id1 = t1->type;
+		id2 = t2->type;
+		goto recur;
+	}
+
+	/* skip_mods_and_typedefs() make this impossible */
+	case BTF_KIND_TYPEDEF:
+	case BTF_KIND_VOLATILE:
+	case BTF_KIND_CONST:
+	case BTF_KIND_RESTRICT:
+	/* DATASECs are never compared with each other */
+	case BTF_KIND_DATASEC:
+	default:
+		pr_warn("global '%s': unsupported BTF kind %s\n",
+			sym_name, btf_kind_str(t1));
+		return false;
+	}
+}
+
+static bool map_defs_match(const char *sym_name,
+			   const struct btf *main_btf,
+			   const struct btf_map_def *main_def,
+			   const struct btf_map_def *main_inner_def,
+			   const struct btf *extra_btf,
+			   const struct btf_map_def *extra_def,
+			   const struct btf_map_def *extra_inner_def)
+{
+	const char *reason;
+
+	if (main_def->map_type != extra_def->map_type) {
+		reason = "type";
+		goto mismatch;
+	}
+
+	/* check key type/size match */
+	if (main_def->key_size != extra_def->key_size) {
+		reason = "key_size";
+		goto mismatch;
+	}
+	if (!!main_def->key_type_id != !!extra_def->key_type_id) {
+		reason = "key type";
+		goto mismatch;
+	}
+	if ((main_def->parts & MAP_DEF_KEY_TYPE)
+	     && !glob_sym_btf_matches(sym_name, true /*exact*/,
+				      main_btf, main_def->key_type_id,
+				      extra_btf, extra_def->key_type_id)) {
+		reason = "key type";
+		goto mismatch;
+	}
+
+	/* validate value type/size match */
+	if (main_def->value_size != extra_def->value_size) {
+		reason = "value_size";
+		goto mismatch;
+	}
+	if (!!main_def->value_type_id != !!extra_def->value_type_id) {
+		reason = "value type";
+		goto mismatch;
+	}
+	if ((main_def->parts & MAP_DEF_VALUE_TYPE)
+	     && !glob_sym_btf_matches(sym_name, true /*exact*/,
+				      main_btf, main_def->value_type_id,
+				      extra_btf, extra_def->value_type_id)) {
+		reason = "key type";
+		goto mismatch;
+	}
+
+	if (main_def->max_entries != extra_def->max_entries) {
+		reason = "max_entries";
+		goto mismatch;
+	}
+	if (main_def->map_flags != extra_def->map_flags) {
+		reason = "map_flags";
+		goto mismatch;
+	}
+	if (main_def->numa_node != extra_def->numa_node) {
+		reason = "numa_node";
+		goto mismatch;
+	}
+	if (main_def->pinning != extra_def->pinning) {
+		reason = "pinning";
+		goto mismatch;
+	}
+
+	if ((main_def->parts & MAP_DEF_INNER_MAP) != (extra_def->parts & MAP_DEF_INNER_MAP)) {
+		reason = "inner map";
+		goto mismatch;
+	}
 
-		if (sym->st_shndx && sym->st_shndx < SHN_LORESERVE) {
-			src_sec = &obj->secs[sym->st_shndx];
-			if (src_sec->skipped)
+	if (main_def->parts & MAP_DEF_INNER_MAP) {
+		char inner_map_name[128];
+
+		snprintf(inner_map_name, sizeof(inner_map_name), "%s.inner", sym_name);
+
+		return map_defs_match(inner_map_name,
+				      main_btf, main_inner_def, NULL,
+				      extra_btf, extra_inner_def, NULL);
+	}
+
+	return true;
+
+mismatch:
+	pr_warn("global '%s': map %s mismatch\n", sym_name, reason);
+	return false;
+}
+
+static bool glob_map_defs_match(const char *sym_name,
+				struct bpf_linker *linker, struct glob_sym *glob_sym,
+				struct src_obj *obj, Elf64_Sym *sym, int btf_id)
+{
+	struct btf_map_def dst_def = {}, dst_inner_def = {};
+	struct btf_map_def src_def = {}, src_inner_def = {};
+	const struct btf_type *t;
+	int err;
+
+	t = btf__type_by_id(obj->btf, btf_id);
+	if (!btf_is_var(t)) {
+		pr_warn("global '%s': invalid map definition type [%d]\n", sym_name, btf_id);
+		return false;
+	}
+	t = skip_mods_and_typedefs(obj->btf, t->type, NULL);
+
+	err = parse_btf_map_def(sym_name, obj->btf, t, true /*strict*/, &src_def, &src_inner_def);
+	if (err) {
+		pr_warn("global '%s': invalid map definition\n", sym_name);
+		return false;
+	}
+
+	/* re-parse existing map definition */
+	t = btf__type_by_id(linker->btf, glob_sym->btf_id);
+	t = skip_mods_and_typedefs(linker->btf, t->type, NULL);
+	err = parse_btf_map_def(sym_name, linker->btf, t, true /*strict*/, &dst_def, &dst_inner_def);
+	if (err) {
+		/* this should not happen, because we already validated it */
+		pr_warn("global '%s': invalid dst map definition\n", sym_name);
+		return false;
+	}
+
+	/* Currently extern map definition has to be complete and match
+	 * concrete map definition exactly. This restriction might be lifted
+	 * in the future.
+	 */
+	return map_defs_match(sym_name, linker->btf, &dst_def, &dst_inner_def,
+			      obj->btf, &src_def, &src_inner_def);
+}
+
+static bool glob_syms_match(const char *sym_name,
+			    struct bpf_linker *linker, struct glob_sym *glob_sym,
+			    struct src_obj *obj, Elf64_Sym *sym, size_t sym_idx, int btf_id)
+{
+	const struct btf_type *src_t;
+
+	/* if we are dealing with externs, BTF types describing both global
+	 * and extern VARs/FUNCs should be completely present in all files
+	 */
+	if (!glob_sym->btf_id || !btf_id) {
+		pr_warn("BTF info is missing for global symbol '%s'\n", sym_name);
+		return false;
+	}
+
+	src_t = btf__type_by_id(obj->btf, btf_id);
+	if (!btf_is_var(src_t) && !btf_is_func(src_t)) {
+		pr_warn("only extern variables and functions are supported, but got '%s' for '%s'\n",
+			btf_kind_str(src_t), sym_name);
+		return false;
+	}
+
+	/* deal with .maps definitions specially */
+	if (glob_sym->sec_id && strcmp(linker->secs[glob_sym->sec_id].sec_name, MAPS_ELF_SEC) == 0)
+		return glob_map_defs_match(sym_name, linker, glob_sym, obj, sym, btf_id);
+
+	if (!glob_sym_btf_matches(sym_name, true /*exact*/,
+				  linker->btf, glob_sym->btf_id, obj->btf, btf_id))
+		return false;
+
+	return true;
+}
+
+static bool btf_is_non_static(const struct btf_type *t)
+{
+	return (btf_is_var(t) && btf_var(t)->linkage != BTF_VAR_STATIC)
+	       || (btf_is_func(t) && btf_func_linkage(t) != BTF_FUNC_STATIC);
+}
+
+static int find_glob_sym_btf(struct src_obj *obj, Elf64_Sym *sym, const char *sym_name,
+			     int *out_btf_sec_id, int *out_btf_id)
+{
+	int i, j, n = btf__get_nr_types(obj->btf), m, btf_id = 0;
+	const struct btf_type *t;
+	const struct btf_var_secinfo *vi;
+	const char *name;
+
+	for (i = 1; i <= n; i++) {
+		t = btf__type_by_id(obj->btf, i);
+
+		/* some global and extern FUNCs and VARs might not be associated with any
+		 * DATASEC, so try to detect them in the same pass
+		 */
+		if (btf_is_non_static(t)) {
+			name = btf__str_by_offset(obj->btf, t->name_off);
+			if (strcmp(name, sym_name) != 0)
 				continue;
-			dst_sec = &linker->secs[src_sec->dst_id];
 
-			/* allow only one STT_SECTION symbol per section */
-			if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION && dst_sec->sec_sym_idx) {
-				obj->sym_map[i] = dst_sec->sec_sym_idx;
+			/* remember and still try to find DATASEC */
+			btf_id = i;
+			continue;
+		}
+
+		if (!btf_is_datasec(t))
+			continue;
+
+		vi = btf_var_secinfos(t);
+		for (j = 0, m = btf_vlen(t); j < m; j++, vi++) {
+			t = btf__type_by_id(obj->btf, vi->type);
+			name = btf__str_by_offset(obj->btf, t->name_off);
+
+			if (strcmp(name, sym_name) != 0)
+				continue;
+			if (btf_is_var(t) && btf_var(t)->linkage == BTF_VAR_STATIC)
 				continue;
+			if (btf_is_func(t) && btf_func_linkage(t) == BTF_FUNC_STATIC)
+				continue;
+
+			if (btf_id && btf_id != vi->type) {
+				pr_warn("global/extern '%s' BTF is ambiguous: both types #%d and #%u match\n",
+					sym_name, btf_id, vi->type);
+				return -EINVAL;
 			}
+
+			*out_btf_sec_id = i;
+			*out_btf_id = vi->type;
+
+			return 0;
 		}
+	}
+
+	/* free-floating extern or global FUNC */
+	if (btf_id) {
+		*out_btf_sec_id = 0;
+		*out_btf_id = btf_id;
+		return 0;
+	}
 
-		name_off = strset__add_str(linker->strtab_strs, sym_name);
-		if (name_off < 0)
-			return name_off;
+	pr_warn("failed to find BTF info for global/extern symbol '%s'\n", sym_name);
+	return -ENOENT;
+}
 
-		dst_sym = add_new_sym(linker, &dst_sym_idx);
-		if (!dst_sym)
-			return -ENOMEM;
+static struct src_sec *find_src_sec_by_name(struct src_obj *obj, const char *sec_name)
+{
+	struct src_sec *sec;
+	int i;
 
-		dst_sym->st_name = name_off;
-		dst_sym->st_info = sym->st_info;
-		dst_sym->st_other = sym->st_other;
-		dst_sym->st_shndx = src_sec ? dst_sec->sec_idx : sym->st_shndx;
-		dst_sym->st_value = (src_sec ? src_sec->dst_off : 0) + sym->st_value;
-		dst_sym->st_size = sym->st_size;
+	for (i = 1; i < obj->sec_cnt; i++) {
+		sec = &obj->secs[i];
+
+		if (strcmp(sec->sec_name, sec_name) == 0)
+			return sec;
+	}
+
+	return NULL;
+}
+
+static int complete_extern_btf_info(struct btf *dst_btf, int dst_id,
+				    struct btf *src_btf, int src_id)
+{
+	struct btf_type *dst_t = btf_type_by_id(dst_btf, dst_id);
+	struct btf_type *src_t = btf_type_by_id(src_btf, src_id);
+	struct btf_param *src_p, *dst_p;
+	const char *s;
+	int i, n, off;
+
+	/* We already made sure that source and destination types (FUNC or
+	 * VAR) match in terms of types and argument names.
+	 */
+	if (btf_is_var(dst_t)) {
+		btf_var(dst_t)->linkage = BTF_VAR_GLOBAL_ALLOCATED;
+		return 0;
+	}
+
+	dst_t->info = btf_type_info(BTF_KIND_FUNC, BTF_FUNC_GLOBAL, 0);
+
+	/* now onto FUNC_PROTO types */
+	src_t = btf_type_by_id(src_btf, src_t->type);
+	dst_t = btf_type_by_id(dst_btf, dst_t->type);
+
+	/* Fill in all the argument names, which for extern FUNCs are missing.
+	 * We'll end up with two copies of FUNCs/VARs for externs, but that
+	 * will be taken care of by BTF dedup at the very end.
+	 * It might be that BTF types for extern in one file has less/more BTF
+	 * information (e.g., FWD instead of full STRUCT/UNION information),
+	 * but that should be (in most cases, subject to BTF dedup rules)
+	 * handled and resolved by BTF dedup algorithm as well, so we won't
+	 * worry about it. Our only job is to make sure that argument names
+	 * are populated on both sides, otherwise BTF dedup will pedantically
+	 * consider them different.
+	 */
+	src_p = btf_params(src_t);
+	dst_p = btf_params(dst_t);
+	for (i = 0, n = btf_vlen(dst_t); i < n; i++, src_p++, dst_p++) {
+		if (!src_p->name_off)
+			continue;
+
+		/* src_btf has more complete info, so add name to dst_btf */
+		s = btf__str_by_offset(src_btf, src_p->name_off);
+		off = btf__add_str(dst_btf, s);
+		if (off < 0)
+			return off;
+		dst_p->name_off = off;
+	}
+	return 0;
+}
+
+static void sym_update_bind(Elf64_Sym *sym, int sym_bind)
+{
+	sym->st_info = ELF64_ST_INFO(sym_bind, ELF64_ST_TYPE(sym->st_info));
+}
+
+static void sym_update_type(Elf64_Sym *sym, int sym_type)
+{
+	sym->st_info = ELF64_ST_INFO(ELF64_ST_BIND(sym->st_info), sym_type);
+}
+
+static void sym_update_visibility(Elf64_Sym *sym, int sym_vis)
+{
+	/* libelf doesn't provide setters for ST_VISIBILITY,
+	 * but it is stored in the lower 2 bits of st_other
+	 */
+	sym->st_other &= 0x03;
+	sym->st_other |= sym_vis;
+}
+
+static int linker_append_elf_sym(struct bpf_linker *linker, struct src_obj *obj,
+				 Elf64_Sym *sym, const char *sym_name, int src_sym_idx)
+{
+	struct src_sec *src_sec = NULL;
+	struct dst_sec *dst_sec = NULL;
+	struct glob_sym *glob_sym = NULL;
+	int name_off, sym_type, sym_bind, sym_vis, err;
+	int btf_sec_id = 0, btf_id = 0;
+	size_t dst_sym_idx;
+	Elf64_Sym *dst_sym;
+	bool sym_is_extern;
+
+	sym_type = ELF64_ST_TYPE(sym->st_info);
+	sym_bind = ELF64_ST_BIND(sym->st_info);
+	sym_vis = ELF64_ST_VISIBILITY(sym->st_other);
+	sym_is_extern = sym->st_shndx == SHN_UNDEF;
+
+	if (sym_is_extern) {
+		if (!obj->btf) {
+			pr_warn("externs without BTF info are not supported\n");
+			return -ENOTSUP;
+		}
+	} else if (sym->st_shndx < SHN_LORESERVE) {
+		src_sec = &obj->secs[sym->st_shndx];
+		if (src_sec->skipped)
+			return 0;
+		dst_sec = &linker->secs[src_sec->dst_id];
+
+		/* allow only one STT_SECTION symbol per section */
+		if (sym_type == STT_SECTION && dst_sec->sec_sym_idx) {
+			obj->sym_map[src_sym_idx] = dst_sec->sec_sym_idx;
+			return 0;
+		}
+	}
+
+	if (sym_bind == STB_LOCAL)
+		goto add_sym;
+
+	/* find matching BTF info */
+	err = find_glob_sym_btf(obj, sym, sym_name, &btf_sec_id, &btf_id);
+	if (err)
+		return err;
+
+	if (sym_is_extern && btf_sec_id) {
+		const char *sec_name = NULL;
+		const struct btf_type *t;
+
+		t = btf__type_by_id(obj->btf, btf_sec_id);
+		sec_name = btf__str_by_offset(obj->btf, t->name_off);
+
+		/* Clang puts unannotated extern vars into
+		 * '.extern' BTF DATASEC. Treat them the same
+		 * as unannotated extern funcs (which are
+		 * currently not put into any DATASECs).
+		 * Those don't have associated src_sec/dst_sec.
+		 */
+		if (strcmp(sec_name, BTF_EXTERN_SEC) != 0) {
+			src_sec = find_src_sec_by_name(obj, sec_name);
+			if (!src_sec) {
+				pr_warn("failed to find matching ELF sec '%s'\n", sec_name);
+				return -ENOENT;
+			}
+			dst_sec = &linker->secs[src_sec->dst_id];
+		}
+	}
+
+	glob_sym = find_glob_sym(linker, sym_name);
+	if (glob_sym) {
+		/* Preventively resolve to existing symbol. This is
+		 * needed for further relocation symbol remapping in
+		 * the next step of linking.
+		 */
+		obj->sym_map[src_sym_idx] = glob_sym->sym_idx;
+
+		/* If both symbols are non-externs, at least one of
+		 * them has to be STB_WEAK, otherwise they are in
+		 * a conflict with each other.
+		 */
+		if (!sym_is_extern && !glob_sym->is_extern
+		    && !glob_sym->is_weak && sym_bind != STB_WEAK) {
+			pr_warn("conflicting non-weak symbol #%d (%s) definition in '%s'\n",
+				src_sym_idx, sym_name, obj->filename);
+			return -EINVAL;
+		}
 
-		obj->sym_map[i] = dst_sym_idx;
+		if (!glob_syms_match(sym_name, linker, glob_sym, obj, sym, src_sym_idx, btf_id))
+			return -EINVAL;
+
+		dst_sym = get_sym_by_idx(linker, glob_sym->sym_idx);
 
-		if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION && dst_sym) {
-			dst_sec->sec_sym_idx = dst_sym_idx;
-			dst_sym->st_value = 0;
+		/* If new symbol is strong, then force dst_sym to be strong as
+		 * well; this way a mix of weak and non-weak extern
+		 * definitions will end up being strong.
+		 */
+		if (sym_bind == STB_GLOBAL) {
+			/* We still need to preserve type (NOTYPE or
+			 * OBJECT/FUNC, depending on whether the symbol is
+			 * extern or not)
+			 */
+			sym_update_bind(dst_sym, STB_GLOBAL);
+			glob_sym->is_weak = false;
 		}
 
+		/* Non-default visibility is "contaminating", with stricter
+		 * visibility overwriting more permissive ones, even if more
+		 * permissive visibility comes from just an extern definition.
+		 * Currently only STV_DEFAULT and STV_HIDDEN are allowed and
+		 * ensured by ELF symbol sanity checks above.
+		 */
+		if (sym_vis > ELF64_ST_VISIBILITY(dst_sym->st_other))
+			sym_update_visibility(dst_sym, sym_vis);
+
+		/* If the new symbol is extern, then regardless if
+		 * existing symbol is extern or resolved global, just
+		 * keep the existing one untouched.
+		 */
+		if (sym_is_extern)
+			return 0;
+
+		/* If existing symbol is a strong resolved symbol, bail out,
+		 * because we lost resolution battle have nothing to
+		 * contribute. We already checked abover that there is no
+		 * strong-strong conflict. We also already tightened binding
+		 * and visibility, so nothing else to contribute at that point.
+		 */
+		if (!glob_sym->is_extern && sym_bind == STB_WEAK)
+			return 0;
+
+		/* At this point, new symbol is strong non-extern,
+		 * so overwrite glob_sym with new symbol information.
+		 * Preserve binding and visibility.
+		 */
+		sym_update_type(dst_sym, sym_type);
+		dst_sym->st_shndx = dst_sec->sec_idx;
+		dst_sym->st_value = src_sec->dst_off + sym->st_value;
+		dst_sym->st_size = sym->st_size;
+
+		/* see comment below about dst_sec->id vs dst_sec->sec_idx */
+		glob_sym->sec_id = dst_sec->id;
+		glob_sym->is_extern = false;
+
+		if (complete_extern_btf_info(linker->btf, glob_sym->btf_id,
+					     obj->btf, btf_id))
+			return -EINVAL;
+
+		/* request updating VAR's/FUNC's underlying BTF type when appending BTF type */
+		glob_sym->underlying_btf_id = 0;
+
+		obj->sym_map[src_sym_idx] = glob_sym->sym_idx;
+		return 0;
+	}
+
+add_sym:
+	name_off = strset__add_str(linker->strtab_strs, sym_name);
+	if (name_off < 0)
+		return name_off;
+
+	dst_sym = add_new_sym(linker, &dst_sym_idx);
+	if (!dst_sym)
+		return -ENOMEM;
+
+	dst_sym->st_name = name_off;
+	dst_sym->st_info = sym->st_info;
+	dst_sym->st_other = sym->st_other;
+	dst_sym->st_shndx = dst_sec ? dst_sec->sec_idx : sym->st_shndx;
+	dst_sym->st_value = (src_sec ? src_sec->dst_off : 0) + sym->st_value;
+	dst_sym->st_size = sym->st_size;
+
+	obj->sym_map[src_sym_idx] = dst_sym_idx;
+
+	if (sym_type == STT_SECTION && dst_sym) {
+		dst_sec->sec_sym_idx = dst_sym_idx;
+		dst_sym->st_value = 0;
+	}
+
+	if (sym_bind != STB_LOCAL) {
+		glob_sym = add_glob_sym(linker);
+		if (!glob_sym)
+			return -ENOMEM;
+
+		glob_sym->sym_idx = dst_sym_idx;
+		/* we use dst_sec->id (and not dst_sec->sec_idx), because
+		 * ephemeral sections (.kconfig, .ksyms, etc) don't have
+		 * sec_idx (as they don't have corresponding ELF section), but
+		 * still have id. .extern doesn't have even ephemeral section
+		 * associated with it, so dst_sec->id == dst_sec->sec_idx == 0.
+		 */
+		glob_sym->sec_id = dst_sec ? dst_sec->id : 0;
+		glob_sym->name_off = name_off;
+		/* we will fill btf_id in during BTF merging step */
+		glob_sym->btf_id = 0;
+		glob_sym->is_extern = sym_is_extern;
+		glob_sym->is_weak = sym_bind == STB_WEAK;
 	}
 
 	return 0;
@@ -1200,7 +2014,7 @@ static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *ob
 				return err;
 			}
 		} else if (!secs_match(dst_sec, src_sec)) {
-			pr_warn("Secs %s are not compatible\n", src_sec->sec_name);
+			pr_warn("sections %s are not compatible\n", src_sec->sec_name);
 			return -1;
 		}
 
@@ -1212,7 +2026,7 @@ static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *ob
 		dst_sec->shdr->sh_info = dst_linked_sec->sec_idx;
 
 		src_sec->dst_id = dst_sec->id;
-		err = extend_sec(dst_sec, src_sec);
+		err = extend_sec(linker, dst_sec, src_sec);
 		if (err)
 			return err;
 
@@ -1265,21 +2079,6 @@ static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *ob
 	return 0;
 }
 
-static struct src_sec *find_src_sec_by_name(struct src_obj *obj, const char *sec_name)
-{
-	struct src_sec *sec;
-	int i;
-
-	for (i = 1; i < obj->sec_cnt; i++) {
-		sec = &obj->secs[i];
-
-		if (strcmp(sec->sec_name, sec_name) == 0)
-			return sec;
-	}
-
-	return NULL;
-}
-
 static Elf64_Sym *find_sym_by_name(struct src_obj *obj, size_t sec_idx,
 				   int sym_type, const char *sym_name)
 {
@@ -1334,12 +2133,32 @@ static int linker_fixup_btf(struct src_obj *obj)
 				t->size = sec->shdr->sh_size;
 		} else {
 			/* BTF can have some sections that are not represented
-			 * in ELF, e.g., .kconfig and .ksyms, which are used
-			 * for special extern variables.  Here we'll
-			 * pre-create "section shells" for them to be able to
-			 * keep track of extra per-section metadata later
-			 * (e.g., BTF variables).
+			 * in ELF, e.g., .kconfig, .ksyms, .extern, which are used
+			 * for special extern variables.
+			 *
+			 * For all but one such special (ephemeral)
+			 * sections, we pre-create "section shells" to be able
+			 * to keep track of extra per-section metadata later
+			 * (e.g., those BTF extern variables).
+			 *
+			 * .extern is even more special, though, because it
+			 * contains extern variables that need to be resolved
+			 * by static linker, not libbpf and kernel. When such
+			 * externs are resolved, we are going to remove them
+			 * from .extern BTF section and might end up not
+			 * needing it at all. Each resolved extern should have
+			 * matching non-extern VAR/FUNC in other sections.
+			 *
+			 * We do support leaving some of the externs
+			 * unresolved, though, to support cases of building
+			 * libraries, which will later be linked against final
+			 * BPF applications. So if at finalization we still
+			 * see unresolved externs, we'll create .extern
+			 * section on our own.
 			 */
+			if (strcmp(sec_name, BTF_EXTERN_SEC) == 0)
+				continue;
+
 			sec = add_src_sec(obj, sec_name);
 			if (!sec)
 				return -ENOMEM;
@@ -1379,6 +2198,13 @@ static int linker_fixup_btf(struct src_obj *obj)
 static int remap_type_id(__u32 *type_id, void *ctx)
 {
 	int *id_map = ctx;
+	int new_id = id_map[*type_id];
+
+	/* Error out if the type wasn't remapped. Ignore VOID which stays VOID. */
+	if (new_id == 0 && *type_id != 0) {
+		pr_warn("failed to find new ID mapping for original BTF type ID %u\n", *type_id);
+		return -EINVAL;
+	}
 
 	*type_id = id_map[*type_id];
 
@@ -1389,6 +2215,7 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
 {
 	const struct btf_type *t;
 	int i, j, n, start_id, id;
+	const char *name;
 
 	if (!obj->btf)
 		return 0;
@@ -1401,12 +2228,44 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
 		return -ENOMEM;
 
 	for (i = 1; i <= n; i++) {
+		struct glob_sym *glob_sym = NULL;
+
 		t = btf__type_by_id(obj->btf, i);
 
 		/* DATASECs are handled specially below */
 		if (btf_kind(t) == BTF_KIND_DATASEC)
 			continue;
 
+		if (btf_is_non_static(t)) {
+			/* there should be glob_sym already */
+			name = btf__str_by_offset(obj->btf, t->name_off);
+			glob_sym = find_glob_sym(linker, name);
+
+			/* VARs without corresponding glob_sym are those that
+			 * belong to skipped/deduplicated sections (i.e.,
+			 * license and version), so just skip them
+			 */
+			if (!glob_sym)
+				continue;
+
+			/* linker_append_elf_sym() might have requested
+			 * updating underlying type ID, if extern was resolved
+			 * to strong symbol or weak got upgraded to non-weak
+			 */
+			if (glob_sym->underlying_btf_id == 0)
+				glob_sym->underlying_btf_id = -t->type;
+
+			/* globals from previous object files that match our
+			 * VAR/FUNC already have a corresponding associated
+			 * BTF type, so just make sure to use it
+			 */
+			if (glob_sym->btf_id) {
+				/* reuse existing BTF type for global var/func */
+				obj->btf_type_map[i] = glob_sym->btf_id;
+				continue;
+			}
+		}
+
 		id = btf__add_type(linker->btf, obj->btf, t);
 		if (id < 0) {
 			pr_warn("failed to append BTF type #%d from file '%s'\n", i, obj->filename);
@@ -1414,6 +2273,12 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
 		}
 
 		obj->btf_type_map[i] = id;
+
+		/* record just appended BTF type for var/func */
+		if (glob_sym) {
+			glob_sym->btf_id = id;
+			glob_sym->underlying_btf_id = -t->type;
+		}
 	}
 
 	/* remap all the types except DATASECs */
@@ -1425,6 +2290,22 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
 			return -EINVAL;
 	}
 
+	/* Rewrite VAR/FUNC underlying types (i.e., FUNC's FUNC_PROTO and VAR's
+	 * actual type), if necessary
+	 */
+	for (i = 0; i < linker->glob_sym_cnt; i++) {
+		struct glob_sym *glob_sym = &linker->glob_syms[i];
+		struct btf_type *glob_t;
+
+		if (glob_sym->underlying_btf_id >= 0)
+			continue;
+
+		glob_sym->underlying_btf_id = obj->btf_type_map[-glob_sym->underlying_btf_id];
+
+		glob_t = btf_type_by_id(linker->btf, glob_sym->btf_id);
+		glob_t->type = glob_sym->underlying_btf_id;
+	}
+
 	/* append DATASEC info */
 	for (i = 1; i < obj->sec_cnt; i++) {
 		struct src_sec *src_sec;
@@ -1452,6 +2333,42 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
 		n = btf_vlen(t);
 		for (j = 0; j < n; j++, src_var++) {
 			void *sec_vars = dst_sec->sec_vars;
+			int new_id = obj->btf_type_map[src_var->type];
+			struct glob_sym *glob_sym = NULL;
+
+			t = btf_type_by_id(linker->btf, new_id);
+			if (btf_is_non_static(t)) {
+				name = btf__str_by_offset(linker->btf, t->name_off);
+				glob_sym = find_glob_sym(linker, name);
+				if (glob_sym->sec_id != dst_sec->id) {
+					pr_warn("global '%s': section mismatch %d vs %d\n",
+						name, glob_sym->sec_id, dst_sec->id);
+					return -EINVAL;
+				}
+			}
+
+			/* If there is already a member (VAR or FUNC) mapped
+			 * to the same type, don't add a duplicate entry.
+			 * This will happen when multiple object files define
+			 * the same extern VARs/FUNCs.
+			 */
+			if (glob_sym && glob_sym->var_idx >= 0) {
+				__s64 sz;
+
+				dst_var = &dst_sec->sec_vars[glob_sym->var_idx];
+				/* Because underlying BTF type might have
+				 * changed, so might its size have changed, so
+				 * re-calculate and update it in sec_var.
+				 */
+				sz = btf__resolve_size(linker->btf, glob_sym->underlying_btf_id);
+				if (sz < 0) {
+					pr_warn("global '%s': failed to resolve size of underlying type: %d\n",
+						name, (int)sz);
+					return -EINVAL;
+				}
+				dst_var->size = sz;
+				continue;
+			}
 
 			sec_vars = libbpf_reallocarray(sec_vars,
 						       dst_sec->sec_var_cnt + 1,
@@ -1466,6 +2383,9 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
 			dst_var->type = obj->btf_type_map[src_var->type];
 			dst_var->size = src_var->size;
 			dst_var->offset = src_sec->dst_off + src_var->offset;
+
+			if (glob_sym)
+				glob_sym->var_idx = dst_sec->sec_var_cnt - 1;
 		}
 	}
 

tools/testing/selftests/bpf/Makefile

@@ -21,7 +21,7 @@ endif
 
 BPF_GCC		?= $(shell command -v bpf-gcc;)
 SAN_CFLAGS	?=
-CFLAGS += -g -Og -rdynamic -Wall $(GENFLAGS) $(SAN_CFLAGS)		\
+CFLAGS += -g -O0 -rdynamic -Wall $(GENFLAGS) $(SAN_CFLAGS)		\
 	  -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR)		\
 	  -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT)			\
 	  -Dbpf_prog_load=bpf_prog_test_load				\
@@ -205,7 +205,7 @@ $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)    \
 		    $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool
 	$(Q)$(MAKE) $(submake_extras)  -C $(BPFTOOLDIR)			       \
 		    CC=$(HOSTCC) LD=$(HOSTLD)				       \
-		    EXTRA_CFLAGS='-g -Og'				       \
+		    EXTRA_CFLAGS='-g -O0'				       \
 		    OUTPUT=$(HOST_BUILD_DIR)/bpftool/			       \
 		    prefix= DESTDIR=$(HOST_SCRATCH_DIR)/ install
 
@@ -225,7 +225,7 @@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)		       \
 	   ../../../include/uapi/linux/bpf.h                                   \
 	   | $(INCLUDE_DIR) $(BUILD_DIR)/libbpf
 	$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \
-		    EXTRA_CFLAGS='-g -Og'					       \
+		    EXTRA_CFLAGS='-g -O0'				       \
 		    DESTDIR=$(SCRATCH_DIR) prefix= all install_headers
 
 ifneq ($(BPFOBJ),$(HOST_BPFOBJ))
@@ -233,7 +233,7 @@ $(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)                \
 	   ../../../include/uapi/linux/bpf.h                                   \
 	   | $(INCLUDE_DIR) $(HOST_BUILD_DIR)/libbpf
 	$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR)                             \
-		    EXTRA_CFLAGS='-g -Og'					       \
+		    EXTRA_CFLAGS='-g -O0'				       \
 		    OUTPUT=$(HOST_BUILD_DIR)/libbpf/ CC=$(HOSTCC) LD=$(HOSTLD) \
 		    DESTDIR=$(HOST_SCRATCH_DIR)/ prefix= all install_headers
 endif
@@ -309,9 +309,15 @@ endef
 
 SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c
 
-LINKED_SKELS := test_static_linked.skel.h
+LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h		\
+		linked_vars.skel.h linked_maps.skel.h
 
 test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o
+linked_funcs.skel.h-deps := linked_funcs1.o linked_funcs2.o
+linked_vars.skel.h-deps := linked_vars1.o linked_vars2.o
+linked_maps.skel.h-deps := linked_maps1.o linked_maps2.o
+
+LINKED_BPF_SRCS := $(patsubst %.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
 
 # Set up extra TRUNNER_XXX "temporary" variables in the environment (relies on
 # $eval()) and pass control to DEFINE_TEST_RUNNER_RULES.
@@ -331,7 +337,7 @@ TRUNNER_TESTS_HDR := $(TRUNNER_TESTS_DIR)/tests.h
 TRUNNER_BPF_SRCS := $$(notdir $$(wildcard $(TRUNNER_BPF_PROGS_DIR)/*.c))
 TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, $$(TRUNNER_BPF_SRCS))
 TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h,	\
-				 $$(filter-out $(SKEL_BLACKLIST),	\
+				 $$(filter-out $(SKEL_BLACKLIST) $(LINKED_BPF_SRCS),\
 					       $$(TRUNNER_BPF_SRCS)))
 TRUNNER_BPF_SKELS_LINKED := $$(addprefix $$(TRUNNER_OUTPUT)/,$(LINKED_SKELS))
 TEST_GEN_FILES += $$(TRUNNER_BPF_OBJS)

tools/testing/selftests/bpf/README.rst

@@ -193,3 +193,12 @@ Without it, the error from compiling bpf selftests looks like:
   libbpf: failed to find BTF for extern 'tcp_slow_start' [25] section: -2
 
 __ https://reviews.llvm.org/D93563
+
+Clang dependencies for static linking tests
+===========================================
+
+linked_vars, linked_maps, and linked_funcs tests depend on `Clang fix`__ to
+generate valid BTF information for weak variables. Please make sure you use
+Clang that contains the fix.
+
+__ https://reviews.llvm.org/D100362

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

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <test_progs.h>
+#include <sys/syscall.h>
+#include "linked_funcs.skel.h"
+
+void test_linked_funcs(void)
+{
+	int err;
+	struct linked_funcs *skel;
+
+	skel = linked_funcs__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	skel->rodata->my_tid = syscall(SYS_gettid);
+	skel->bss->syscall_id = SYS_getpgid;
+
+	err = linked_funcs__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	err = linked_funcs__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	/* trigger */
+	syscall(SYS_getpgid);
+
+	ASSERT_EQ(skel->bss->output_val1, 2000 + 2000, "output_val1");
+	ASSERT_EQ(skel->bss->output_ctx1, SYS_getpgid, "output_ctx1");
+	ASSERT_EQ(skel->bss->output_weak1, 42, "output_weak1");
+
+	ASSERT_EQ(skel->bss->output_val2, 2 * 1000 + 2 * (2 * 1000), "output_val2");
+	ASSERT_EQ(skel->bss->output_ctx2, SYS_getpgid, "output_ctx2");
+	/* output_weak2 should never be updated */
+	ASSERT_EQ(skel->bss->output_weak2, 0, "output_weak2");
+
+cleanup:
+	linked_funcs__destroy(skel);
+}

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

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <test_progs.h>
+#include <sys/syscall.h>
+#include "linked_maps.skel.h"
+
+void test_linked_maps(void)
+{
+	int err;
+	struct linked_maps *skel;
+
+	skel = linked_maps__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	err = linked_maps__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	/* trigger */
+	syscall(SYS_getpgid);
+
+	ASSERT_EQ(skel->bss->output_first1, 2000, "output_first1");
+	ASSERT_EQ(skel->bss->output_second1, 2, "output_second1");
+	ASSERT_EQ(skel->bss->output_weak1, 2, "output_weak1");
+
+cleanup:
+	linked_maps__destroy(skel);
+}

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

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <test_progs.h>
+#include <sys/syscall.h>
+#include "linked_vars.skel.h"
+
+void test_linked_vars(void)
+{
+	int err;
+	struct linked_vars *skel;
+
+	skel = linked_vars__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	skel->bss->input_bss1 = 1000;
+	skel->bss->input_bss2 = 2000;
+	skel->bss->input_bss_weak = 3000;
+
+	err = linked_vars__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	err = linked_vars__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	/* trigger */
+	syscall(SYS_getpgid);
+
+	ASSERT_EQ(skel->bss->output_bss1, 1000 + 2000 + 3000, "output_bss1");
+	ASSERT_EQ(skel->bss->output_bss2, 1000 + 2000 + 3000, "output_bss2");
+	/* 10 comes from "winner" input_data_weak in first obj file */
+	ASSERT_EQ(skel->bss->output_data1, 1 + 2 + 10, "output_bss1");
+	ASSERT_EQ(skel->bss->output_data2, 1 + 2 + 10, "output_bss2");
+	/* 100 comes from "winner" input_rodata_weak in first obj file */
+	ASSERT_EQ(skel->bss->output_rodata1, 11 + 22 + 100, "output_weak1");
+	ASSERT_EQ(skel->bss->output_rodata2, 11 + 22 + 100, "output_weak2");
+
+cleanup:
+	linked_vars__destroy(skel);
+}

tools/testing/selftests/bpf/progs/linked_funcs1.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+/* weak and shared between two files */
+const volatile int my_tid __weak;
+long syscall_id __weak;
+
+int output_val1;
+int output_ctx1;
+int output_weak1;
+
+/* same "subprog" name in all files, but it's ok because they all are static */
+static __noinline int subprog(int x)
+{
+	/* but different formula */
+	return x * 1;
+}
+
+/* Global functions can't be void */
+int set_output_val1(int x)
+{
+	output_val1 = x + subprog(x);
+	return x;
+}
+
+/* This function can't be verified as global, as it assumes raw_tp/sys_enter
+ * context and accesses syscall id (second argument). So we mark it as
+ * __hidden, so that libbpf will mark it as static in the final object file,
+ * right before verifying it in the kernel.
+ *
+ * But we don't mark it as __hidden here, rather at extern site. __hidden is
+ * "contaminating" visibility, so it will get propagated from either extern or
+ * actual definition (including from the losing __weak definition).
+ */
+void set_output_ctx1(__u64 *ctx)
+{
+	output_ctx1 = ctx[1]; /* long id, same as in BPF_PROG below */
+}
+
+/* this weak instance should win because it's the first one */
+__weak int set_output_weak(int x)
+{
+	output_weak1 = x;
+	return x;
+}
+
+extern int set_output_val2(int x);
+
+/* here we'll force set_output_ctx2() to be __hidden in the final obj file */
+__hidden extern void set_output_ctx2(__u64 *ctx);
+
+SEC("raw_tp/sys_enter")
+int BPF_PROG(handler1, struct pt_regs *regs, long id)
+{
+	if (my_tid != (u32)bpf_get_current_pid_tgid() || id != syscall_id)
+		return 0;
+
+	set_output_val2(1000);
+	set_output_ctx2(ctx); /* ctx definition is hidden in BPF_PROG macro */
+
+	/* keep input value the same across both files to avoid dependency on
+	 * handler call order; differentiate by output_weak1 vs output_weak2.
+	 */
+	set_output_weak(42);
+
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/linked_funcs2.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+/* weak and shared between both files */
+const volatile int my_tid __weak;
+long syscall_id __weak;
+
+int output_val2;
+int output_ctx2;
+int output_weak2; /* should stay zero */
+
+/* same "subprog" name in all files, but it's ok because they all are static */
+static __noinline int subprog(int x)
+{
+	/* but different formula */
+	return x * 2;
+}
+
+/* Global functions can't be void */
+int set_output_val2(int x)
+{
+	output_val2 = 2 * x + 2 * subprog(x);
+	return 2 * x;
+}
+
+/* This function can't be verified as global, as it assumes raw_tp/sys_enter
+ * context and accesses syscall id (second argument). So we mark it as
+ * __hidden, so that libbpf will mark it as static in the final object file,
+ * right before verifying it in the kernel.
+ *
+ * But we don't mark it as __hidden here, rather at extern site. __hidden is
+ * "contaminating" visibility, so it will get propagated from either extern or
+ * actual definition (including from the losing __weak definition).
+ */
+void set_output_ctx2(__u64 *ctx)
+{
+	output_ctx2 = ctx[1]; /* long id, same as in BPF_PROG below */
+}
+
+/* this weak instance should lose, because it will be processed second */
+__weak int set_output_weak(int x)
+{
+	output_weak2 = x;
+	return 2 * x;
+}
+
+extern int set_output_val1(int x);
+
+/* here we'll force set_output_ctx1() to be __hidden in the final obj file */
+__hidden extern void set_output_ctx1(__u64 *ctx);
+
+SEC("raw_tp/sys_enter")
+int BPF_PROG(handler2, struct pt_regs *regs, long id)
+{
+	if (my_tid != (u32)bpf_get_current_pid_tgid() || id != syscall_id)
+		return 0;
+
+	set_output_val1(2000);
+	set_output_ctx1(ctx); /* ctx definition is hidden in BPF_PROG macro */
+
+	/* keep input value the same across both files to avoid dependency on
+	 * handler call order; differentiate by output_weak1 vs output_weak2.
+	 */
+	set_output_weak(42);
+
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/linked_maps1.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+struct my_key { long x; };
+struct my_value { long x; };
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, struct my_key);
+	__type(value, struct my_value);
+	__uint(max_entries, 16);
+} map1 SEC(".maps");
+
+ /* Matches map2 definition in linked_maps2.c. Order of the attributes doesn't
+  * matter.
+  */
+typedef struct {
+	__uint(max_entries, 8);
+	__type(key, int);
+	__type(value, int);
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+} map2_t;
+
+extern map2_t map2 SEC(".maps");
+
+/* This should be the winning map definition, but we have no way of verifying,
+ * so we just make sure that it links and works without errors
+ */
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 16);
+} map_weak __weak SEC(".maps");
+
+int output_first1;
+int output_second1;
+int output_weak1;
+
+SEC("raw_tp/sys_enter")
+int BPF_PROG(handler_enter1)
+{
+	/* update values with key = 1 */
+	int key = 1, val = 1;
+	struct my_key key_struct = { .x = 1 };
+	struct my_value val_struct = { .x = 1000 };
+
+	bpf_map_update_elem(&map1, &key_struct, &val_struct, 0);
+	bpf_map_update_elem(&map2, &key, &val, 0);
+	bpf_map_update_elem(&map_weak, &key, &val, 0);
+
+	return 0;
+}
+
+SEC("raw_tp/sys_exit")
+int BPF_PROG(handler_exit1)
+{
+	/* lookup values with key = 2, set in another file */
+	int key = 2, *val;
+	struct my_key key_struct = { .x = 2 };
+	struct my_value *value_struct;
+
+	value_struct = bpf_map_lookup_elem(&map1, &key_struct);
+	if (value_struct)
+		output_first1 = value_struct->x;
+
+	val = bpf_map_lookup_elem(&map2, &key);
+	if (val)
+		output_second1 = *val;
+
+	val = bpf_map_lookup_elem(&map_weak, &key);
+	if (val)
+		output_weak1 = *val;
+	
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/linked_maps2.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+/* modifiers and typedefs are ignored when comparing key/value types */
+typedef struct my_key { long x; } key_type;
+typedef struct my_value { long x; } value_type;
+
+extern struct {
+	__uint(max_entries, 16);
+	__type(key, key_type);
+	__type(value, value_type);
+	__uint(type, BPF_MAP_TYPE_HASH);
+} map1 SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 8);
+} map2 SEC(".maps");
+
+/* this definition will lose, but it has to exactly match the winner */
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 16);
+} map_weak __weak SEC(".maps");
+
+int output_first2;
+int output_second2;
+int output_weak2;
+
+SEC("raw_tp/sys_enter")
+int BPF_PROG(handler_enter2)
+{
+	/* update values with key = 2 */
+	int key = 2, val = 2;
+	key_type key_struct = { .x = 2 };
+	value_type val_struct = { .x = 2000 };
+
+	bpf_map_update_elem(&map1, &key_struct, &val_struct, 0);
+	bpf_map_update_elem(&map2, &key, &val, 0);
+	bpf_map_update_elem(&map_weak, &key, &val, 0);
+
+	return 0;
+}
+
+SEC("raw_tp/sys_exit")
+int BPF_PROG(handler_exit2)
+{
+	/* lookup values with key = 1, set in another file */
+	int key = 1, *val;
+	key_type key_struct = { .x = 1 };
+	value_type *value_struct;
+
+	value_struct = bpf_map_lookup_elem(&map1, &key_struct);
+	if (value_struct)
+		output_first2 = value_struct->x;
+
+	val = bpf_map_lookup_elem(&map2, &key);
+	if (val)
+		output_second2 = *val;
+
+	val = bpf_map_lookup_elem(&map_weak, &key);
+	if (val)
+		output_weak2 = *val;
+
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/linked_vars1.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+extern int LINUX_KERNEL_VERSION __kconfig;
+/* this weak extern will be strict due to the other file's strong extern */
+extern bool CONFIG_BPF_SYSCALL __kconfig __weak;
+extern const void bpf_link_fops __ksym __weak;
+
+int input_bss1;
+int input_data1 = 1;
+const volatile int input_rodata1 = 11;
+
+int input_bss_weak __weak;
+/* these two definitions should win */
+int input_data_weak __weak = 10;
+const volatile int input_rodata_weak __weak = 100;
+
+extern int input_bss2;
+extern int input_data2;
+extern const int input_rodata2;
+
+int output_bss1;
+int output_data1;
+int output_rodata1;
+
+long output_sink1;
+
+static __noinline int get_bss_res(void)
+{
+	/* just make sure all the relocations work against .text as well */
+	return input_bss1 + input_bss2 + input_bss_weak;
+}
+
+SEC("raw_tp/sys_enter")
+int BPF_PROG(handler1)
+{
+	output_bss1 = get_bss_res();
+	output_data1 = input_data1 + input_data2 + input_data_weak;
+	output_rodata1 = input_rodata1 + input_rodata2 + input_rodata_weak;
+
+	/* make sure we actually use above special externs, otherwise compiler
+	 * will optimize them out
+	 */
+	output_sink1 = LINUX_KERNEL_VERSION
+		       + CONFIG_BPF_SYSCALL
+		       + (long)&bpf_link_fops;
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/linked_vars2.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+extern int LINUX_KERNEL_VERSION __kconfig;
+/* when an extern is defined as both strong and weak, resulting symbol will be strong */
+extern bool CONFIG_BPF_SYSCALL __kconfig;
+extern const void __start_BTF __ksym;
+
+int input_bss2;
+int input_data2 = 2;
+const volatile int input_rodata2 = 22;
+
+int input_bss_weak __weak;
+/* these two weak variables should lose */
+int input_data_weak __weak = 20;
+const volatile int input_rodata_weak __weak = 200;
+
+extern int input_bss1;
+extern int input_data1;
+extern const int input_rodata1;
+
+int output_bss2;
+int output_data2;
+int output_rodata2;
+
+int output_sink2;
+
+static __noinline int get_data_res(void)
+{
+	/* just make sure all the relocations work against .text as well */
+	return input_data1 + input_data2 + input_data_weak;
+}
+
+SEC("raw_tp/sys_enter")
+int BPF_PROG(handler2)
+{
+	output_bss2 = input_bss1 + input_bss2 + input_bss_weak;
+	output_data2 = get_data_res();
+	output_rodata2 = input_rodata1 + input_rodata2 + input_rodata_weak;
+
+	/* make sure we actually use above special externs, otherwise compiler
+	 * will optimize them out
+	 */
+	output_sink2 = LINUX_KERNEL_VERSION
+		       + CONFIG_BPF_SYSCALL
+		       + (long)&__start_BTF;
+
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";