1 files changed, 166 insertions, 100 deletions

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 91b7106a4a73..2a82f49ce16f 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -164,6 +164,7 @@ static const char * const map_type_name[] = {
 	[BPF_MAP_TYPE_TASK_STORAGE]		= "task_storage",
 	[BPF_MAP_TYPE_BLOOM_FILTER]		= "bloom_filter",
 	[BPF_MAP_TYPE_USER_RINGBUF]             = "user_ringbuf",
+	[BPF_MAP_TYPE_CGRP_STORAGE]		= "cgrp_storage",
 };
 
 static const char * const prog_type_name[] = {
@@ -346,7 +347,8 @@ enum sec_def_flags {
 	SEC_ATTACHABLE = 2,
 	SEC_ATTACHABLE_OPT = SEC_ATTACHABLE | SEC_EXP_ATTACH_OPT,
 	/* attachment target is specified through BTF ID in either kernel or
-	 * other BPF program's BTF object */
+	 * other BPF program's BTF object
+	 */
 	SEC_ATTACH_BTF = 4,
 	/* BPF program type allows sleeping/blocking in kernel */
 	SEC_SLEEPABLE = 8,
@@ -487,7 +489,7 @@ struct bpf_map {
 	char *name;
 	/* real_name is defined for special internal maps (.rodata*,
 	 * .data*, .bss, .kconfig) and preserves their original ELF section
-	 * name. This is important to be be able to find corresponding BTF
+	 * name. This is important to be able to find corresponding BTF
 	 * DATASEC information.
 	 */
 	char *real_name;
@@ -597,7 +599,7 @@ struct elf_state {
 	size_t shstrndx; /* section index for section name strings */
 	size_t strtabidx;
 	struct elf_sec_desc *secs;
-	int sec_cnt;
+	size_t sec_cnt;
 	int btf_maps_shndx;
 	__u32 btf_maps_sec_btf_id;
 	int text_shndx;
@@ -1408,6 +1410,10 @@ static int bpf_object__check_endianness(struct bpf_object *obj)
 static int
 bpf_object__init_license(struct bpf_object *obj, void *data, size_t size)
 {
+	if (!data) {
+		pr_warn("invalid license section in %s\n", obj->path);
+		return -LIBBPF_ERRNO__FORMAT;
+	}
 	/* libbpf_strlcpy() only copies first N - 1 bytes, so size + 1 won't
 	 * go over allowed ELF data section buffer
 	 */
@@ -1421,7 +1427,7 @@ bpf_object__init_kversion(struct bpf_object *obj, void *data, size_t size)
 {
 	__u32 kver;
 
-	if (size != sizeof(kver)) {
+	if (!data || size != sizeof(kver)) {
 		pr_warn("invalid kver section in %s\n", obj->path);
 		return -LIBBPF_ERRNO__FORMAT;
 	}
@@ -1457,15 +1463,12 @@ static int find_elf_sec_sz(const struct bpf_object *obj, const char *name, __u32
 	return -ENOENT;
 }
 
-static int find_elf_var_offset(const struct bpf_object *obj, const char *name, __u32 *off)
+static Elf64_Sym *find_elf_var_sym(const struct bpf_object *obj, const char *name)
 {
 	Elf_Data *symbols = obj->efile.symbols;
 	const char *sname;
 	size_t si;
 
-	if (!name || !off)
-		return -EINVAL;
-
 	for (si = 0; si < symbols->d_size / sizeof(Elf64_Sym); si++) {
 		Elf64_Sym *sym = elf_sym_by_idx(obj, si);
 
@@ -1479,15 +1482,13 @@ static int find_elf_var_offset(const struct bpf_object *obj, const char *name, _
 		sname = elf_sym_str(obj, sym->st_name);
 		if (!sname) {
 			pr_warn("failed to get sym name string for var %s\n", name);
-			return -EIO;
-		}
-		if (strcmp(name, sname) == 0) {
-			*off = sym->st_value;
-			return 0;
+			return ERR_PTR(-EIO);
 		}
+		if (strcmp(name, sname) == 0)
+			return sym;
 	}
 
-	return -ENOENT;
+	return ERR_PTR(-ENOENT);
 }
 
 static struct bpf_map *bpf_object__add_map(struct bpf_object *obj)
@@ -1578,7 +1579,38 @@ static char *internal_map_name(struct bpf_object *obj, const char *real_name)
 }
 
 static int
-bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map);
+map_fill_btf_type_info(struct bpf_object *obj, struct bpf_map *map);
+
+/* Internal BPF map is mmap()'able only if at least one of corresponding
+ * DATASEC's VARs are to be exposed through BPF skeleton. I.e., it's a GLOBAL
+ * variable and it's not marked as __hidden (which turns it into, effectively,
+ * a STATIC variable).
+ */
+static bool map_is_mmapable(struct bpf_object *obj, struct bpf_map *map)
+{
+	const struct btf_type *t, *vt;
+	struct btf_var_secinfo *vsi;
+	int i, n;
+
+	if (!map->btf_value_type_id)
+		return false;
+
+	t = btf__type_by_id(obj->btf, map->btf_value_type_id);
+	if (!btf_is_datasec(t))
+		return false;
+
+	vsi = btf_var_secinfos(t);
+	for (i = 0, n = btf_vlen(t); i < n; i++, vsi++) {
+		vt = btf__type_by_id(obj->btf, vsi->type);
+		if (!btf_is_var(vt))
+			continue;
+
+		if (btf_var(vt)->linkage != BTF_VAR_STATIC)
+			return true;
+	}
+
+	return false;
+}
 
 static int
 bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
@@ -1610,7 +1642,12 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 	def->max_entries = 1;
 	def->map_flags = type == LIBBPF_MAP_RODATA || type == LIBBPF_MAP_KCONFIG
 			 ? BPF_F_RDONLY_PROG : 0;
-	def->map_flags |= BPF_F_MMAPABLE;
+
+	/* failures are fine because of maps like .rodata.str1.1 */
+	(void) map_fill_btf_type_info(obj, map);
+
+	if (map_is_mmapable(obj, map))
+		def->map_flags |= BPF_F_MMAPABLE;
 
 	pr_debug("map '%s' (global data): at sec_idx %d, offset %zu, flags %x.\n",
 		 map->name, map->sec_idx, map->sec_offset, def->map_flags);
@@ -1627,9 +1664,6 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 		return err;
 	}
 
-	/* failures are fine because of maps like .rodata.str1.1 */
-	(void) bpf_map_find_btf_info(obj, map);
-
 	if (data)
 		memcpy(map->mmaped, data, data_sz);
 
@@ -1830,12 +1864,20 @@ static int set_kcfg_value_num(struct extern_desc *ext, void *ext_val,
 		return -ERANGE;
 	}
 	switch (ext->kcfg.sz) {
-		case 1: *(__u8 *)ext_val = value; break;
-		case 2: *(__u16 *)ext_val = value; break;
-		case 4: *(__u32 *)ext_val = value; break;
-		case 8: *(__u64 *)ext_val = value; break;
-		default:
-			return -EINVAL;
+	case 1:
+		*(__u8 *)ext_val = value;
+		break;
+	case 2:
+		*(__u16 *)ext_val = value;
+		break;
+	case 4:
+		*(__u32 *)ext_val = value;
+		break;
+	case 8:
+		*(__u64 *)ext_val = value;
+		break;
+	default:
+		return -EINVAL;
 	}
 	ext->is_set = true;
 	return 0;
@@ -2541,7 +2583,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 		fill_map_from_def(map->inner_map, &inner_def);
 	}
 
-	err = bpf_map_find_btf_info(obj, map);
+	err = map_fill_btf_type_info(obj, map);
 	if (err)
 		return err;
 
@@ -2737,7 +2779,7 @@ static int bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf)
 				m->type = enum64_placeholder_id;
 				m->offset = 0;
 			}
-                }
+		}
 	}
 
 	return 0;
@@ -2846,57 +2888,89 @@ static int compare_vsi_off(const void *_a, const void *_b)
 static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf,
 			     struct btf_type *t)
 {
-	__u32 size = 0, off = 0, i, vars = btf_vlen(t);
-	const char *name = btf__name_by_offset(btf, t->name_off);
-	const struct btf_type *t_var;
+	__u32 size = 0, i, vars = btf_vlen(t);
+	const char *sec_name = btf__name_by_offset(btf, t->name_off);
 	struct btf_var_secinfo *vsi;
-	const struct btf_var *var;
-	int ret;
+	bool fixup_offsets = false;
+	int err;
 
-	if (!name) {
+	if (!sec_name) {
 		pr_debug("No name found in string section for DATASEC kind.\n");
 		return -ENOENT;
 	}
 
-	/* .extern datasec size and var offsets were set correctly during
-	 * extern collection step, so just skip straight to sorting variables
+	/* Extern-backing datasecs (.ksyms, .kconfig) have their size and
+	 * variable offsets set at the previous step. Further, not every
+	 * extern BTF VAR has corresponding ELF symbol preserved, so we skip
+	 * all fixups altogether for such sections and go straight to sorting
+	 * VARs within their DATASEC.
 	 */
-	if (t->size)
+	if (strcmp(sec_name, KCONFIG_SEC) == 0 || strcmp(sec_name, KSYMS_SEC) == 0)
 		goto sort_vars;
 
-	ret = find_elf_sec_sz(obj, name, &size);
-	if (ret || !size) {
-		pr_debug("Invalid size for section %s: %u bytes\n", name, size);
-		return -ENOENT;
-	}
+	/* Clang leaves DATASEC size and VAR offsets as zeroes, so we need to
+	 * fix this up. But BPF static linker already fixes this up and fills
+	 * all the sizes and offsets during static linking. So this step has
+	 * to be optional. But the STV_HIDDEN handling is non-optional for any
+	 * non-extern DATASEC, so the variable fixup loop below handles both
+	 * functions at the same time, paying the cost of BTF VAR <-> ELF
+	 * symbol matching just once.
+	 */
+	if (t->size == 0) {
+		err = find_elf_sec_sz(obj, sec_name, &size);
+		if (err || !size) {
+			pr_debug("sec '%s': failed to determine size from ELF: size %u, err %d\n",
+				 sec_name, size, err);
+			return -ENOENT;
+		}
 
-	t->size = size;
+		t->size = size;
+		fixup_offsets = true;
+	}
 
 	for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) {
+		const struct btf_type *t_var;
+		struct btf_var *var;
+		const char *var_name;
+		Elf64_Sym *sym;
+
 		t_var = btf__type_by_id(btf, vsi->type);
 		if (!t_var || !btf_is_var(t_var)) {
-			pr_debug("Non-VAR type seen in section %s\n", name);
+			pr_debug("sec '%s': unexpected non-VAR type found\n", sec_name);
 			return -EINVAL;
 		}
 
 		var = btf_var(t_var);
-		if (var->linkage == BTF_VAR_STATIC)
+		if (var->linkage == BTF_VAR_STATIC || var->linkage == BTF_VAR_GLOBAL_EXTERN)
 			continue;
 
-		name = btf__name_by_offset(btf, t_var->name_off);
-		if (!name) {
-			pr_debug("No name found in string section for VAR kind\n");
+		var_name = btf__name_by_offset(btf, t_var->name_off);
+		if (!var_name) {
+			pr_debug("sec '%s': failed to find name of DATASEC's member #%d\n",
+				 sec_name, i);
 			return -ENOENT;
 		}
 
-		ret = find_elf_var_offset(obj, name, &off);
-		if (ret) {
-			pr_debug("No offset found in symbol table for VAR %s\n",
-				 name);
+		sym = find_elf_var_sym(obj, var_name);
+		if (IS_ERR(sym)) {
+			pr_debug("sec '%s': failed to find ELF symbol for VAR '%s'\n",
+				 sec_name, var_name);
 			return -ENOENT;
 		}
 
-		vsi->offset = off;
+		if (fixup_offsets)
+			vsi->offset = sym->st_value;
+
+		/* if variable is a global/weak symbol, but has restricted
+		 * (STV_HIDDEN or STV_INTERNAL) visibility, mark its BTF VAR
+		 * as static. This follows similar logic for functions (BPF
+		 * subprogs) and influences libbpf's further decisions about
+		 * whether to make global data BPF array maps as
+		 * BPF_F_MMAPABLE.
+		 */
+		if (ELF64_ST_VISIBILITY(sym->st_other) == STV_HIDDEN
+		    || ELF64_ST_VISIBILITY(sym->st_other) == STV_INTERNAL)
+			var->linkage = BTF_VAR_STATIC;
 	}
 
 sort_vars:
@@ -2904,13 +2978,16 @@ sort_vars:
 	return 0;
 }
 
-static int btf_finalize_data(struct bpf_object *obj, struct btf *btf)
+static int bpf_object_fixup_btf(struct bpf_object *obj)
 {
-	int err = 0;
-	__u32 i, n = btf__type_cnt(btf);
+	int i, n, err = 0;
+
+	if (!obj->btf)
+		return 0;
 
+	n = btf__type_cnt(obj->btf);
 	for (i = 1; i < n; i++) {
-		struct btf_type *t = btf_type_by_id(btf, i);
+		struct btf_type *t = btf_type_by_id(obj->btf, i);
 
 		/* Loader needs to fix up some of the things compiler
 		 * couldn't get its hands on while emitting BTF. This
@@ -2918,28 +2995,12 @@ static int btf_finalize_data(struct bpf_object *obj, struct btf *btf)
 		 * the info from the ELF itself for this purpose.
 		 */
 		if (btf_is_datasec(t)) {
-			err = btf_fixup_datasec(obj, btf, t);
+			err = btf_fixup_datasec(obj, obj->btf, t);
 			if (err)
-				break;
+				return err;
 		}
 	}
 
-	return libbpf_err(err);
-}
-
-static int bpf_object__finalize_btf(struct bpf_object *obj)
-{
-	int err;
-
-	if (!obj->btf)
-		return 0;
-
-	err = btf_finalize_data(obj, obj->btf);
-	if (err) {
-		pr_warn("Error finalizing %s: %d.\n", BTF_ELF_SEC, err);
-		return err;
-	}
-
 	return 0;
 }
 
@@ -3312,10 +3373,15 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 	Elf64_Shdr *sh;
 
 	/* ELF section indices are 0-based, but sec #0 is special "invalid"
-	 * section. e_shnum does include sec #0, so e_shnum is the necessary
-	 * size of an array to keep all the sections.
+	 * section. Since section count retrieved by elf_getshdrnum() does
+	 * include sec #0, it is already the necessary size of an array to keep
+	 * all the sections.
 	 */
-	obj->efile.sec_cnt = obj->efile.ehdr->e_shnum;
+	if (elf_getshdrnum(obj->efile.elf, &obj->efile.sec_cnt)) {
+		pr_warn("elf: failed to get the number of sections for %s: %s\n",
+			obj->path, elf_errmsg(-1));
+		return -LIBBPF_ERRNO__FORMAT;
+	}
 	obj->efile.secs = calloc(obj->efile.sec_cnt, sizeof(*obj->efile.secs));
 	if (!obj->efile.secs)
 		return -ENOMEM;
@@ -3445,7 +3511,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 			sec_desc->sec_type = SEC_RELO;
 			sec_desc->shdr = sh;
 			sec_desc->data = data;
-		} else if (sh->sh_type == SHT_NOBITS && strcmp(name, BSS_SEC) == 0) {
+		} else if (sh->sh_type == SHT_NOBITS && (strcmp(name, BSS_SEC) == 0 ||
+							 str_has_pfx(name, BSS_SEC "."))) {
 			sec_desc->sec_type = SEC_BSS;
 			sec_desc->shdr = sh;
 			sec_desc->data = data;
@@ -3461,7 +3528,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 	}
 
 	/* sort BPF programs by section name and in-section instruction offset
-	 * for faster search */
+	 * for faster search
+	 */
 	if (obj->nr_programs)
 		qsort(obj->programs, obj->nr_programs, sizeof(*obj->programs), cmp_progs);
 
@@ -3760,7 +3828,7 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
 				return -EINVAL;
 			}
 			ext->kcfg.type = find_kcfg_type(obj->btf, t->type,
-						        &ext->kcfg.is_signed);
+							&ext->kcfg.is_signed);
 			if (ext->kcfg.type == KCFG_UNKNOWN) {
 				pr_warn("extern (kcfg) '%s': type is unsupported\n", ext_name);
 				return -ENOTSUP;
@@ -4106,6 +4174,9 @@ static struct bpf_program *find_prog_by_sec_insn(const struct bpf_object *obj,
 	int l = 0, r = obj->nr_programs - 1, m;
 	struct bpf_program *prog;
 
+	if (!obj->nr_programs)
+		return NULL;
+
 	while (l < r) {
 		m = l + (r - l + 1) / 2;
 		prog = &obj->programs[m];
@@ -4223,7 +4294,7 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, Elf64_Shdr *shdr, Elf_Dat
 	return 0;
 }
 
-static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map)
+static int map_fill_btf_type_info(struct bpf_object *obj, struct bpf_map *map)
 {
 	int id;
 
@@ -4905,9 +4976,9 @@ bpf_object__reuse_map(struct bpf_map *map)
 
 	err = bpf_map__reuse_fd(map, pin_fd);
 	close(pin_fd);
-	if (err) {
+	if (err)
 		return err;
-	}
+
 	map->pinned = true;
 	pr_debug("reused pinned map at '%s'\n", map->pin_path);
 
@@ -5425,7 +5496,7 @@ static int load_module_btfs(struct bpf_object *obj)
 		}
 
 		err = libbpf_ensure_mem((void **)&obj->btf_modules, &obj->btf_module_cap,
-				        sizeof(*obj->btf_modules), obj->btf_module_cnt + 1);
+					sizeof(*obj->btf_modules), obj->btf_module_cnt + 1);
 		if (err)
 			goto err_out;
 
@@ -5541,21 +5612,16 @@ int bpf_core_types_match(const struct btf *local_btf, __u32 local_id,
 	return __bpf_core_types_match(local_btf, local_id, targ_btf, targ_id, false, 32);
 }
 
-static size_t bpf_core_hash_fn(const void *key, void *ctx)
+static size_t bpf_core_hash_fn(const long key, void *ctx)
 {
-	return (size_t)key;
+	return key;
 }
 
-static bool bpf_core_equal_fn(const void *k1, const void *k2, void *ctx)
+static bool bpf_core_equal_fn(const long k1, const long k2, void *ctx)
 {
 	return k1 == k2;
 }
 
-static void *u32_as_hash_key(__u32 x)
-{
-	return (void *)(uintptr_t)x;
-}
-
 static int record_relo_core(struct bpf_program *prog,
 			    const struct bpf_core_relo *core_relo, int insn_idx)
 {
@@ -5598,7 +5664,6 @@ static int bpf_core_resolve_relo(struct bpf_program *prog,
 				 struct bpf_core_relo_res *targ_res)
 {
 	struct bpf_core_spec specs_scratch[3] = {};
-	const void *type_key = u32_as_hash_key(relo->type_id);
 	struct bpf_core_cand_list *cands = NULL;
 	const char *prog_name = prog->name;
 	const struct btf_type *local_type;
@@ -5615,7 +5680,7 @@ static int bpf_core_resolve_relo(struct bpf_program *prog,
 		return -EINVAL;
 
 	if (relo->kind != BPF_CORE_TYPE_ID_LOCAL &&
-	    !hashmap__find(cand_cache, type_key, (void **)&cands)) {
+	    !hashmap__find(cand_cache, local_id, &cands)) {
 		cands = bpf_core_find_cands(prog->obj, local_btf, local_id);
 		if (IS_ERR(cands)) {
 			pr_warn("prog '%s': relo #%d: target candidate search failed for [%d] %s %s: %ld\n",
@@ -5623,7 +5688,7 @@ static int bpf_core_resolve_relo(struct bpf_program *prog,
 				local_name, PTR_ERR(cands));
 			return PTR_ERR(cands);
 		}
-		err = hashmap__set(cand_cache, type_key, cands, NULL, NULL);
+		err = hashmap__set(cand_cache, local_id, cands, NULL, NULL);
 		if (err) {
 			bpf_core_free_cands(cands);
 			return err;
@@ -5746,7 +5811,7 @@ out:
 
 	if (!IS_ERR_OR_NULL(cand_cache)) {
 		hashmap__for_each_entry(cand_cache, entry, i) {
-			bpf_core_free_cands(entry->value);
+			bpf_core_free_cands(entry->pvalue);
 		}
 		hashmap__free(cand_cache);
 	}
@@ -6183,7 +6248,8 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog,
 		 * prog; each main prog can have a different set of
 		 * subprograms appended (potentially in different order as
 		 * well), so position of any subprog can be different for
-		 * different main programs */
+		 * different main programs
+		 */
 		insn->imm = subprog->sub_insn_off - (prog->sub_insn_off + insn_idx) - 1;
 
 		pr_debug("prog '%s': insn #%zu relocated, imm %d points to subprog '%s' (now at %zu offset)\n",
@@ -7221,7 +7287,7 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf,
 	err = err ? : bpf_object__check_endianness(obj);
 	err = err ? : bpf_object__elf_collect(obj);
 	err = err ? : bpf_object__collect_externs(obj);
-	err = err ? : bpf_object__finalize_btf(obj);
+	err = err ? : bpf_object_fixup_btf(obj);
 	err = err ? : bpf_object__init_maps(obj, opts);
 	err = err ? : bpf_object_init_progs(obj, opts);
 	err = err ? : bpf_object__collect_relos(obj);
@@ -10941,7 +11007,7 @@ struct bpf_link *bpf_program__attach_usdt(const struct bpf_program *prog,
 
 	usdt_cookie = OPTS_GET(opts, usdt_cookie, 0);
 	link = usdt_manager_attach_usdt(obj->usdt_man, prog, pid, binary_path,
-				        usdt_provider, usdt_name, usdt_cookie);
+					usdt_provider, usdt_name, usdt_cookie);
 	err = libbpf_get_error(link);
 	if (err)
 		return libbpf_err_ptr(err);
@@ -12250,7 +12316,7 @@ int bpf_object__open_subskeleton(struct bpf_object_subskeleton *s)
 	btf = bpf_object__btf(s->obj);
 	if (!btf) {
 		pr_warn("subskeletons require BTF at runtime (object %s)\n",
-		        bpf_object__name(s->obj));
+			bpf_object__name(s->obj));
 		return libbpf_err(-errno);
 	}