diff options
Diffstat (limited to 'tools/lib')
-rw-r--r-- | tools/lib/bpf/bpf.c | 25 | ||||
-rw-r--r-- | tools/lib/bpf/bpf.h | 25 | ||||
-rw-r--r-- | tools/lib/bpf/bpf_gen_internal.h | 4 | ||||
-rw-r--r-- | tools/lib/bpf/bpf_helpers.h | 5 | ||||
-rw-r--r-- | tools/lib/bpf/gen_loader.c | 48 | ||||
-rw-r--r-- | tools/lib/bpf/libbpf.c | 245 | ||||
-rw-r--r-- | tools/lib/bpf/libbpf.h | 3 | ||||
-rw-r--r-- | tools/lib/bpf/libbpf.map | 1 | ||||
-rw-r--r-- | tools/lib/bpf/linker.c | 14 | ||||
-rw-r--r-- | tools/lib/bpf/zip.c | 6 |
10 files changed, 278 insertions, 98 deletions
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index e750b6f5fcc3..128ac723c4ea 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -230,9 +230,9 @@ alloc_zero_tailing_info(const void *orecord, __u32 cnt, int bpf_prog_load(enum bpf_prog_type prog_type, const char *prog_name, const char *license, const struct bpf_insn *insns, size_t insn_cnt, - const struct bpf_prog_load_opts *opts) + struct bpf_prog_load_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, fd_array); + const size_t attr_sz = offsetofend(union bpf_attr, log_true_size); void *finfo = NULL, *linfo = NULL; const char *func_info, *line_info; __u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd; @@ -290,10 +290,6 @@ int bpf_prog_load(enum bpf_prog_type prog_type, if (!!log_buf != !!log_size) return libbpf_err(-EINVAL); - if (log_level > (4 | 2 | 1)) - return libbpf_err(-EINVAL); - if (log_level && !log_buf) - return libbpf_err(-EINVAL); func_info_rec_size = OPTS_GET(opts, func_info_rec_size, 0); func_info = OPTS_GET(opts, func_info, NULL); @@ -316,6 +312,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, } fd = sys_bpf_prog_load(&attr, attr_sz, attempts); + OPTS_SET(opts, log_true_size, attr.log_true_size); if (fd >= 0) return fd; @@ -356,6 +353,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, } fd = sys_bpf_prog_load(&attr, attr_sz, attempts); + OPTS_SET(opts, log_true_size, attr.log_true_size); if (fd >= 0) goto done; } @@ -370,6 +368,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, attr.log_level = 1; fd = sys_bpf_prog_load(&attr, attr_sz, attempts); + OPTS_SET(opts, log_true_size, attr.log_true_size); } done: /* free() doesn't affect errno, so we don't need to restore it */ @@ -794,11 +793,17 @@ int bpf_link_update(int link_fd, int new_prog_fd, if (!OPTS_VALID(opts, bpf_link_update_opts)) return libbpf_err(-EINVAL); + if (OPTS_GET(opts, old_prog_fd, 0) && OPTS_GET(opts, old_map_fd, 0)) + return libbpf_err(-EINVAL); + memset(&attr, 0, attr_sz); attr.link_update.link_fd = link_fd; attr.link_update.new_prog_fd = new_prog_fd; attr.link_update.flags = OPTS_GET(opts, flags, 0); - attr.link_update.old_prog_fd = OPTS_GET(opts, old_prog_fd, 0); + if (OPTS_GET(opts, old_prog_fd, 0)) + attr.link_update.old_prog_fd = OPTS_GET(opts, old_prog_fd, 0); + else if (OPTS_GET(opts, old_map_fd, 0)) + attr.link_update.old_map_fd = OPTS_GET(opts, old_map_fd, 0); ret = sys_bpf(BPF_LINK_UPDATE, &attr, attr_sz); return libbpf_err_errno(ret); @@ -1078,9 +1083,9 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd) return libbpf_err_errno(fd); } -int bpf_btf_load(const void *btf_data, size_t btf_size, const struct bpf_btf_load_opts *opts) +int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, btf_log_level); + const size_t attr_sz = offsetofend(union bpf_attr, btf_log_true_size); union bpf_attr attr; char *log_buf; size_t log_size; @@ -1123,6 +1128,8 @@ int bpf_btf_load(const void *btf_data, size_t btf_size, const struct bpf_btf_loa attr.btf_log_level = 1; fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, attr_sz); } + + OPTS_SET(opts, log_true_size, attr.btf_log_true_size); return libbpf_err_errno(fd); } diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index f0f786373238..a2c091389b18 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -96,13 +96,20 @@ struct bpf_prog_load_opts { __u32 log_level; __u32 log_size; char *log_buf; + /* output: actual total log contents size (including termintaing zero). + * It could be both larger than original log_size (if log was + * truncated), or smaller (if log buffer wasn't filled completely). + * If kernel doesn't support this feature, log_size is left unchanged. + */ + __u32 log_true_size; + size_t :0; }; -#define bpf_prog_load_opts__last_field log_buf +#define bpf_prog_load_opts__last_field log_true_size LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type, const char *prog_name, const char *license, const struct bpf_insn *insns, size_t insn_cnt, - const struct bpf_prog_load_opts *opts); + struct bpf_prog_load_opts *opts); /* Flags to direct loading requirements */ #define MAPS_RELAX_COMPAT 0x01 @@ -117,11 +124,18 @@ struct bpf_btf_load_opts { char *log_buf; __u32 log_level; __u32 log_size; + /* output: actual total log contents size (including termintaing zero). + * It could be both larger than original log_size (if log was + * truncated), or smaller (if log buffer wasn't filled completely). + * If kernel doesn't support this feature, log_size is left unchanged. + */ + __u32 log_true_size; + size_t :0; }; -#define bpf_btf_load_opts__last_field log_size +#define bpf_btf_load_opts__last_field log_true_size LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size, - const struct bpf_btf_load_opts *opts); + struct bpf_btf_load_opts *opts); LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value, __u64 flags); @@ -336,8 +350,9 @@ struct bpf_link_update_opts { size_t sz; /* size of this struct for forward/backward compatibility */ __u32 flags; /* extra flags */ __u32 old_prog_fd; /* expected old program FD */ + __u32 old_map_fd; /* expected old map FD */ }; -#define bpf_link_update_opts__last_field old_prog_fd +#define bpf_link_update_opts__last_field old_map_fd LIBBPF_API int bpf_link_update(int link_fd, int new_prog_fd, const struct bpf_link_update_opts *opts); diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h index 223308931d55..fdf44403ff36 100644 --- a/tools/lib/bpf/bpf_gen_internal.h +++ b/tools/lib/bpf/bpf_gen_internal.h @@ -11,6 +11,7 @@ struct ksym_relo_desc { int insn_idx; bool is_weak; bool is_typeless; + bool is_ld64; }; struct ksym_desc { @@ -24,6 +25,7 @@ struct ksym_desc { bool typeless; }; int insn; + bool is_ld64; }; struct bpf_gen { @@ -65,7 +67,7 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *value, __u void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx); void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *name, enum bpf_attach_type type); void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak, - bool is_typeless, int kind, int insn_idx); + bool is_typeless, bool is_ld64, int kind, int insn_idx); void bpf_gen__record_relo_core(struct bpf_gen *gen, const struct bpf_core_relo *core_relo); void bpf_gen__populate_outer_map(struct bpf_gen *gen, int outer_map_idx, int key, int inner_map_idx); diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 7d12d3e620cc..e7e1a8acc299 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -177,6 +177,11 @@ enum libbpf_tristate { #define __kptr_untrusted __attribute__((btf_type_tag("kptr_untrusted"))) #define __kptr __attribute__((btf_type_tag("kptr"))) +#define bpf_ksym_exists(sym) ({ \ + _Static_assert(!__builtin_constant_p(!!sym), #sym " should be marked as __weak"); \ + !!sym; \ +}) + #ifndef ___bpf_concat #define ___bpf_concat(a, b) a ## b #endif diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c index 23f5c46708f8..83e8e3bfd8ff 100644 --- a/tools/lib/bpf/gen_loader.c +++ b/tools/lib/bpf/gen_loader.c @@ -560,7 +560,7 @@ static void emit_find_attach_target(struct bpf_gen *gen) } void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak, - bool is_typeless, int kind, int insn_idx) + bool is_typeless, bool is_ld64, int kind, int insn_idx) { struct ksym_relo_desc *relo; @@ -574,6 +574,7 @@ void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak, relo->name = name; relo->is_weak = is_weak; relo->is_typeless = is_typeless; + relo->is_ld64 = is_ld64; relo->kind = kind; relo->insn_idx = insn_idx; gen->relo_cnt++; @@ -586,9 +587,11 @@ static struct ksym_desc *get_ksym_desc(struct bpf_gen *gen, struct ksym_relo_des int i; for (i = 0; i < gen->nr_ksyms; i++) { - if (!strcmp(gen->ksyms[i].name, relo->name)) { - gen->ksyms[i].ref++; - return &gen->ksyms[i]; + kdesc = &gen->ksyms[i]; + if (kdesc->kind == relo->kind && kdesc->is_ld64 == relo->is_ld64 && + !strcmp(kdesc->name, relo->name)) { + kdesc->ref++; + return kdesc; } } kdesc = libbpf_reallocarray(gen->ksyms, gen->nr_ksyms + 1, sizeof(*kdesc)); @@ -603,6 +606,7 @@ static struct ksym_desc *get_ksym_desc(struct bpf_gen *gen, struct ksym_relo_des kdesc->ref = 1; kdesc->off = 0; kdesc->insn = 0; + kdesc->is_ld64 = relo->is_ld64; return kdesc; } @@ -804,11 +808,13 @@ static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, return; /* try to copy from existing ldimm64 insn */ if (kdesc->ref > 1) { - move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4, - kdesc->insn + offsetof(struct bpf_insn, imm)); move_blob2blob(gen, insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 4, kdesc->insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm)); - /* jump over src_reg adjustment if imm is not 0, reuse BPF_REG_0 from move_blob2blob */ + move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4, + kdesc->insn + offsetof(struct bpf_insn, imm)); + /* jump over src_reg adjustment if imm (btf_id) is not 0, reuse BPF_REG_0 from move_blob2blob + * If btf_id is zero, clear BPF_PSEUDO_BTF_ID flag in src_reg of ld_imm64 insn + */ emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3)); goto clear_src_reg; } @@ -831,7 +837,7 @@ static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm))); /* skip src_reg adjustment */ - emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3)); + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 3)); clear_src_reg: /* clear bpf_object__relocate_data's src_reg assignment, otherwise we get a verifier failure */ reg_mask = src_reg_mask(); @@ -862,23 +868,17 @@ static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insn { int insn; - pr_debug("gen: emit_relo (%d): %s at %d\n", relo->kind, relo->name, relo->insn_idx); + pr_debug("gen: emit_relo (%d): %s at %d %s\n", + relo->kind, relo->name, relo->insn_idx, relo->is_ld64 ? "ld64" : "call"); insn = insns + sizeof(struct bpf_insn) * relo->insn_idx; emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_8, BPF_PSEUDO_MAP_IDX_VALUE, 0, 0, 0, insn)); - switch (relo->kind) { - case BTF_KIND_VAR: + if (relo->is_ld64) { if (relo->is_typeless) emit_relo_ksym_typeless(gen, relo, insn); else emit_relo_ksym_btf(gen, relo, insn); - break; - case BTF_KIND_FUNC: + } else { emit_relo_kfunc_btf(gen, relo, insn); - break; - default: - pr_warn("Unknown relocation kind '%d'\n", relo->kind); - gen->error = -EDOM; - return; } } @@ -901,18 +901,20 @@ static void cleanup_core_relo(struct bpf_gen *gen) static void cleanup_relos(struct bpf_gen *gen, int insns) { + struct ksym_desc *kdesc; int i, insn; for (i = 0; i < gen->nr_ksyms; i++) { + kdesc = &gen->ksyms[i]; /* only close fds for typed ksyms and kfuncs */ - if (gen->ksyms[i].kind == BTF_KIND_VAR && !gen->ksyms[i].typeless) { + if (kdesc->is_ld64 && !kdesc->typeless) { /* close fd recorded in insn[insn_idx + 1].imm */ - insn = gen->ksyms[i].insn; + insn = kdesc->insn; insn += sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm); emit_sys_close_blob(gen, insn); - } else if (gen->ksyms[i].kind == BTF_KIND_FUNC) { - emit_sys_close_blob(gen, blob_fd_array_off(gen, gen->ksyms[i].off)); - if (gen->ksyms[i].off < MAX_FD_ARRAY_SZ) + } else if (!kdesc->is_ld64) { + emit_sys_close_blob(gen, blob_fd_array_off(gen, kdesc->off)); + if (kdesc->off < MAX_FD_ARRAY_SZ) gen->nr_fd_array--; } } diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index a557718401e4..49cd304ae3bc 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -116,6 +116,7 @@ static const char * const attach_type_name[] = { [BPF_SK_REUSEPORT_SELECT_OR_MIGRATE] = "sk_reuseport_select_or_migrate", [BPF_PERF_EVENT] = "perf_event", [BPF_TRACE_KPROBE_MULTI] = "trace_kprobe_multi", + [BPF_STRUCT_OPS] = "struct_ops", }; static const char * const link_type_name[] = { @@ -215,9 +216,10 @@ static libbpf_print_fn_t __libbpf_pr = __base_pr; libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn) { - libbpf_print_fn_t old_print_fn = __libbpf_pr; + libbpf_print_fn_t old_print_fn; + + old_print_fn = __atomic_exchange_n(&__libbpf_pr, fn, __ATOMIC_RELAXED); - __libbpf_pr = fn; return old_print_fn; } @@ -226,8 +228,10 @@ void libbpf_print(enum libbpf_print_level level, const char *format, ...) { va_list args; int old_errno; + libbpf_print_fn_t print_fn; - if (!__libbpf_pr) + print_fn = __atomic_load_n(&__libbpf_pr, __ATOMIC_RELAXED); + if (!print_fn) return; old_errno = errno; @@ -315,8 +319,8 @@ enum reloc_type { RELO_LD64, RELO_CALL, RELO_DATA, - RELO_EXTERN_VAR, - RELO_EXTERN_FUNC, + RELO_EXTERN_LD64, + RELO_EXTERN_CALL, RELO_SUBPROG_ADDR, RELO_CORE, }; @@ -467,6 +471,7 @@ struct bpf_struct_ops { #define KCONFIG_SEC ".kconfig" #define KSYMS_SEC ".ksyms" #define STRUCT_OPS_SEC ".struct_ops" +#define STRUCT_OPS_LINK_SEC ".struct_ops.link" enum libbpf_map_type { LIBBPF_MAP_UNSPEC, @@ -596,6 +601,7 @@ struct elf_state { Elf64_Ehdr *ehdr; Elf_Data *symbols; Elf_Data *st_ops_data; + Elf_Data *st_ops_link_data; size_t shstrndx; /* section index for section name strings */ size_t strtabidx; struct elf_sec_desc *secs; @@ -605,6 +611,7 @@ struct elf_state { int text_shndx; int symbols_shndx; int st_ops_shndx; + int st_ops_link_shndx; }; struct usdt_manager; @@ -1118,7 +1125,8 @@ static int bpf_object__init_kern_struct_ops_maps(struct bpf_object *obj) return 0; } -static int bpf_object__init_struct_ops_maps(struct bpf_object *obj) +static int init_struct_ops_maps(struct bpf_object *obj, const char *sec_name, + int shndx, Elf_Data *data, __u32 map_flags) { const struct btf_type *type, *datasec; const struct btf_var_secinfo *vsi; @@ -1129,15 +1137,15 @@ static int bpf_object__init_struct_ops_maps(struct bpf_object *obj) struct bpf_map *map; __u32 i; - if (obj->efile.st_ops_shndx == -1) + if (shndx == -1) return 0; btf = obj->btf; - datasec_id = btf__find_by_name_kind(btf, STRUCT_OPS_SEC, + datasec_id = btf__find_by_name_kind(btf, sec_name, BTF_KIND_DATASEC); if (datasec_id < 0) { pr_warn("struct_ops init: DATASEC %s not found\n", - STRUCT_OPS_SEC); + sec_name); return -EINVAL; } @@ -1150,7 +1158,7 @@ static int bpf_object__init_struct_ops_maps(struct bpf_object *obj) type_id = btf__resolve_type(obj->btf, vsi->type); if (type_id < 0) { pr_warn("struct_ops init: Cannot resolve var type_id %u in DATASEC %s\n", - vsi->type, STRUCT_OPS_SEC); + vsi->type, sec_name); return -EINVAL; } @@ -1169,7 +1177,7 @@ static int bpf_object__init_struct_ops_maps(struct bpf_object *obj) if (IS_ERR(map)) return PTR_ERR(map); - map->sec_idx = obj->efile.st_ops_shndx; + map->sec_idx = shndx; map->sec_offset = vsi->offset; map->name = strdup(var_name); if (!map->name) @@ -1179,6 +1187,7 @@ static int bpf_object__init_struct_ops_maps(struct bpf_object *obj) map->def.key_size = sizeof(int); map->def.value_size = type->size; map->def.max_entries = 1; + map->def.map_flags = map_flags; map->st_ops = calloc(1, sizeof(*map->st_ops)); if (!map->st_ops) @@ -1191,14 +1200,14 @@ static int bpf_object__init_struct_ops_maps(struct bpf_object *obj) if (!st_ops->data || !st_ops->progs || !st_ops->kern_func_off) return -ENOMEM; - if (vsi->offset + type->size > obj->efile.st_ops_data->d_size) { + if (vsi->offset + type->size > data->d_size) { pr_warn("struct_ops init: var %s is beyond the end of DATASEC %s\n", - var_name, STRUCT_OPS_SEC); + var_name, sec_name); return -EINVAL; } memcpy(st_ops->data, - obj->efile.st_ops_data->d_buf + vsi->offset, + data->d_buf + vsi->offset, type->size); st_ops->tname = tname; st_ops->type = type; @@ -1211,6 +1220,19 @@ static int bpf_object__init_struct_ops_maps(struct bpf_object *obj) return 0; } +static int bpf_object_init_struct_ops(struct bpf_object *obj) +{ + int err; + + err = init_struct_ops_maps(obj, STRUCT_OPS_SEC, obj->efile.st_ops_shndx, + obj->efile.st_ops_data, 0); + err = err ?: init_struct_ops_maps(obj, STRUCT_OPS_LINK_SEC, + obj->efile.st_ops_link_shndx, + obj->efile.st_ops_link_data, + BPF_F_LINK); + return err; +} + static struct bpf_object *bpf_object__new(const char *path, const void *obj_buf, size_t obj_buf_sz, @@ -1247,6 +1269,7 @@ static struct bpf_object *bpf_object__new(const char *path, obj->efile.obj_buf_sz = obj_buf_sz; obj->efile.btf_maps_shndx = -1; obj->efile.st_ops_shndx = -1; + obj->efile.st_ops_link_shndx = -1; obj->kconfig_map_idx = -1; obj->kern_version = get_kernel_version(); @@ -1264,6 +1287,7 @@ static void bpf_object__elf_finish(struct bpf_object *obj) obj->efile.elf = NULL; obj->efile.symbols = NULL; obj->efile.st_ops_data = NULL; + obj->efile.st_ops_link_data = NULL; zfree(&obj->efile.secs); obj->efile.sec_cnt = 0; @@ -2618,7 +2642,7 @@ static int bpf_object__init_maps(struct bpf_object *obj, err = bpf_object__init_user_btf_maps(obj, strict, pin_root_path); err = err ?: bpf_object__init_global_data_maps(obj); err = err ?: bpf_object__init_kconfig_map(obj); - err = err ?: bpf_object__init_struct_ops_maps(obj); + err = err ?: bpf_object_init_struct_ops(obj); return err; } @@ -2752,12 +2776,13 @@ static bool libbpf_needs_btf(const struct bpf_object *obj) { return obj->efile.btf_maps_shndx >= 0 || obj->efile.st_ops_shndx >= 0 || + obj->efile.st_ops_link_shndx >= 0 || obj->nr_extern > 0; } static bool kernel_needs_btf(const struct bpf_object *obj) { - return obj->efile.st_ops_shndx >= 0; + return obj->efile.st_ops_shndx >= 0 || obj->efile.st_ops_link_shndx >= 0; } static int bpf_object__init_btf(struct bpf_object *obj, @@ -3450,6 +3475,9 @@ static int bpf_object__elf_collect(struct bpf_object *obj) } else if (strcmp(name, STRUCT_OPS_SEC) == 0) { obj->efile.st_ops_data = data; obj->efile.st_ops_shndx = idx; + } else if (strcmp(name, STRUCT_OPS_LINK_SEC) == 0) { + obj->efile.st_ops_link_data = data; + obj->efile.st_ops_link_shndx = idx; } else { pr_info("elf: skipping unrecognized data section(%d) %s\n", idx, name); @@ -3464,6 +3492,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj) /* Only do relo for section with exec instructions */ if (!section_have_execinstr(obj, targ_sec_idx) && strcmp(name, ".rel" STRUCT_OPS_SEC) && + strcmp(name, ".rel" STRUCT_OPS_LINK_SEC) && strcmp(name, ".rel" MAPS_ELF_SEC)) { pr_info("elf: skipping relo section(%d) %s for section(%d) %s\n", idx, name, targ_sec_idx, @@ -4009,9 +4038,9 @@ static int bpf_program__record_reloc(struct bpf_program *prog, pr_debug("prog '%s': found extern #%d '%s' (sym %d) for insn #%u\n", prog->name, i, ext->name, ext->sym_idx, insn_idx); if (insn->code == (BPF_JMP | BPF_CALL)) - reloc_desc->type = RELO_EXTERN_FUNC; + reloc_desc->type = RELO_EXTERN_CALL; else - reloc_desc->type = RELO_EXTERN_VAR; + reloc_desc->type = RELO_EXTERN_LD64; reloc_desc->insn_idx = insn_idx; reloc_desc->sym_off = i; /* sym_off stores extern index */ return 0; @@ -5855,7 +5884,7 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) relo->map_idx, map); } break; - case RELO_EXTERN_VAR: + case RELO_EXTERN_LD64: ext = &obj->externs[relo->sym_off]; if (ext->type == EXT_KCFG) { if (obj->gen_loader) { @@ -5877,7 +5906,7 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) } } break; - case RELO_EXTERN_FUNC: + case RELO_EXTERN_CALL: ext = &obj->externs[relo->sym_off]; insn[0].src_reg = BPF_PSEUDO_KFUNC_CALL; if (ext->is_set) { @@ -6115,7 +6144,7 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog, continue; relo = find_prog_insn_relo(prog, insn_idx); - if (relo && relo->type == RELO_EXTERN_FUNC) + if (relo && relo->type == RELO_EXTERN_CALL) /* kfunc relocations will be handled later * in bpf_object__relocate_data() */ @@ -6610,7 +6639,7 @@ static int bpf_object__collect_relos(struct bpf_object *obj) return -LIBBPF_ERRNO__INTERNAL; } - if (idx == obj->efile.st_ops_shndx) + if (idx == obj->efile.st_ops_shndx || idx == obj->efile.st_ops_link_shndx) err = bpf_object__collect_st_ops_relos(obj, shdr, data); else if (idx == obj->efile.btf_maps_shndx) err = bpf_object__collect_map_relos(obj, shdr, data); @@ -7070,18 +7099,21 @@ static int bpf_program_record_relos(struct bpf_program *prog) for (i = 0; i < prog->nr_reloc; i++) { struct reloc_desc *relo = &prog->reloc_desc[i]; struct extern_desc *ext = &obj->externs[relo->sym_off]; + int kind; switch (relo->type) { - case RELO_EXTERN_VAR: + case RELO_EXTERN_LD64: if (ext->type != EXT_KSYM) continue; + kind = btf_is_var(btf__type_by_id(obj->btf, ext->btf_id)) ? + BTF_KIND_VAR : BTF_KIND_FUNC; bpf_gen__record_extern(obj->gen_loader, ext->name, ext->is_weak, !ext->ksym.type_id, - BTF_KIND_VAR, relo->insn_idx); + true, kind, relo->insn_idx); break; - case RELO_EXTERN_FUNC: + case RELO_EXTERN_CALL: bpf_gen__record_extern(obj->gen_loader, ext->name, - ext->is_weak, false, BTF_KIND_FUNC, + ext->is_weak, false, false, BTF_KIND_FUNC, relo->insn_idx); break; case RELO_CORE: { @@ -7533,6 +7565,12 @@ static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj, ext->is_set = true; ext->ksym.kernel_btf_id = kfunc_id; ext->ksym.btf_fd_idx = mod_btf ? mod_btf->fd_array_idx : 0; + /* Also set kernel_btf_obj_fd to make sure that bpf_object__relocate_data() + * populates FD into ld_imm64 insn when it's used to point to kfunc. + * {kernel_btf_id, btf_fd_idx} -> fixup bpf_call. + * {kernel_btf_id, kernel_btf_obj_fd} -> fixup ld_imm64. + */ + ext->ksym.kernel_btf_obj_fd = mod_btf ? mod_btf->fd : 0; pr_debug("extern (func ksym) '%s': resolved to kernel [%d]\n", ext->name, kfunc_id); @@ -7677,6 +7715,37 @@ static int bpf_object__resolve_externs(struct bpf_object *obj, return 0; } +static void bpf_map_prepare_vdata(const struct bpf_map *map) +{ + struct bpf_struct_ops *st_ops; + __u32 i; + + st_ops = map->st_ops; + for (i = 0; i < btf_vlen(st_ops->type); i++) { + struct bpf_program *prog = st_ops->progs[i]; + void *kern_data; + int prog_fd; + + if (!prog) + continue; + + prog_fd = bpf_program__fd(prog); + kern_data = st_ops->kern_vdata + st_ops->kern_func_off[i]; + *(unsigned long *)kern_data = prog_fd; + } +} + +static int bpf_object_prepare_struct_ops(struct bpf_object *obj) +{ + int i; + + for (i = 0; i < obj->nr_maps; i++) + if (bpf_map__is_struct_ops(&obj->maps[i])) + bpf_map_prepare_vdata(&obj->maps[i]); + + return 0; +} + static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const char *target_btf_path) { int err, i; @@ -7702,6 +7771,7 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch err = err ? : bpf_object__relocate(obj, obj->btf_custom_path ? : target_btf_path); err = err ? : bpf_object__load_progs(obj, extra_log_level); err = err ? : bpf_object_init_prog_arrays(obj); + err = err ? : bpf_object_prepare_struct_ops(obj); if (obj->gen_loader) { /* reset FDs */ @@ -8398,6 +8468,7 @@ int bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type) return libbpf_err(-EBUSY); prog->type = type; + prog->sec_def = NULL; return 0; } @@ -8811,6 +8882,7 @@ const char *libbpf_bpf_prog_type_str(enum bpf_prog_type t) } static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj, + int sec_idx, size_t offset) { struct bpf_map *map; @@ -8820,7 +8892,8 @@ static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj, map = &obj->maps[i]; if (!bpf_map__is_struct_ops(map)) continue; - if (map->sec_offset <= offset && + if (map->sec_idx == sec_idx && + map->sec_offset <= offset && offset - map->sec_offset < map->def.value_size) return map; } @@ -8862,7 +8935,7 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, } name = elf_sym_str(obj, sym->st_name) ?: "<?>"; - map = find_struct_ops_map_by_offset(obj, rel->r_offset); + map = find_struct_ops_map_by_offset(obj, shdr->sh_info, rel->r_offset); if (!map) { pr_warn("struct_ops reloc: cannot find map at rel->r_offset %zu\n", (size_t)rel->r_offset); @@ -8929,8 +9002,9 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, } /* struct_ops BPF prog can be re-used between multiple - * .struct_ops as long as it's the same struct_ops struct - * definition and the same function pointer field + * .struct_ops & .struct_ops.link as long as it's the + * same struct_ops struct definition and the same + * function pointer field */ if (prog->attach_btf_id != st_ops->type_id || prog->expected_attach_type != member_idx) { @@ -9912,16 +9986,20 @@ static int append_to_file(const char *file, const char *fmt, ...) { int fd, n, err = 0; va_list ap; + char buf[1024]; + + va_start(ap, fmt); + n = vsnprintf(buf, sizeof(buf), fmt, ap); + va_end(ap); + + if (n < 0 || n >= sizeof(buf)) + return -EINVAL; fd = open(file, O_WRONLY | O_APPEND | O_CLOEXEC, 0); if (fd < 0) return -errno; - va_start(ap, fmt); - n = vdprintf(fd, fmt, ap); - va_end(ap); - - if (n < 0) + if (write(fd, buf, n) < 0) err = -errno; close(fd); @@ -11566,22 +11644,30 @@ struct bpf_link *bpf_program__attach(const struct bpf_program *prog) return link; } +struct bpf_link_struct_ops { + struct bpf_link link; + int map_fd; +}; + static int bpf_link__detach_struct_ops(struct bpf_link *link) { + struct bpf_link_struct_ops *st_link; __u32 zero = 0; - if (bpf_map_delete_elem(link->fd, &zero)) - return -errno; + st_link = container_of(link, struct bpf_link_struct_ops, link); - return 0; + if (st_link->map_fd < 0) + /* w/o a real link */ + return bpf_map_delete_elem(link->fd, &zero); + + return close(link->fd); } struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map) { - struct bpf_struct_ops *st_ops; - struct bpf_link *link; - __u32 i, zero = 0; - int err; + struct bpf_link_struct_ops *link; + __u32 zero = 0; + int err, fd; if (!bpf_map__is_struct_ops(map) || map->fd == -1) return libbpf_err_ptr(-EINVAL); @@ -11590,31 +11676,72 @@ struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map) if (!link) return libbpf_err_ptr(-EINVAL); - st_ops = map->st_ops; - for (i = 0; i < btf_vlen(st_ops->type); i++) { - struct bpf_program *prog = st_ops->progs[i]; - void *kern_data; - int prog_fd; + /* kern_vdata should be prepared during the loading phase. */ + err = bpf_map_update_elem(map->fd, &zero, map->st_ops->kern_vdata, 0); + /* It can be EBUSY if the map has been used to create or + * update a link before. We don't allow updating the value of + * a struct_ops once it is set. That ensures that the value + * never changed. So, it is safe to skip EBUSY. + */ + if (err && (!(map->def.map_flags & BPF_F_LINK) || err != -EBUSY)) { + free(link); + return libbpf_err_ptr(err); + } - if (!prog) - continue; + link->link.detach = bpf_link__detach_struct_ops; - prog_fd = bpf_program__fd(prog); - kern_data = st_ops->kern_vdata + st_ops->kern_func_off[i]; - *(unsigned long *)kern_data = prog_fd; + if (!(map->def.map_flags & BPF_F_LINK)) { + /* w/o a real link */ + link->link.fd = map->fd; + link->map_fd = -1; + return &link->link; } - err = bpf_map_update_elem(map->fd, &zero, st_ops->kern_vdata, 0); - if (err) { - err = -errno; + fd = bpf_link_create(map->fd, 0, BPF_STRUCT_OPS, NULL); + if (fd < 0) { free(link); - return libbpf_err_ptr(err); + return libbpf_err_ptr(fd); } - link->detach = bpf_link__detach_struct_ops; - link->fd = map->fd; + link->link.fd = fd; + link->map_fd = map->fd; - return link; + return &link->link; +} + +/* + * Swap the back struct_ops of a link with a new struct_ops map. + */ +int bpf_link__update_map(struct bpf_link *link, const struct bpf_map *map) +{ + struct bpf_link_struct_ops *st_ops_link; + __u32 zero = 0; + int err; + + if (!bpf_map__is_struct_ops(map) || map->fd < 0) + return -EINVAL; + + st_ops_link = container_of(link, struct bpf_link_struct_ops, link); + /* Ensure the type of a link is correct */ + if (st_ops_link->map_fd < 0) + return -EINVAL; + + err = bpf_map_update_elem(map->fd, &zero, map->st_ops->kern_vdata, 0); + /* It can be EBUSY if the map has been used to create or + * update a link before. We don't allow updating the value of + * a struct_ops once it is set. That ensures that the value + * never changed. So, it is safe to skip EBUSY. + */ + if (err && err != -EBUSY) + return err; + + err = bpf_link_update(link->fd, map->fd, NULL); + if (err < 0) + return err; + + st_ops_link->map_fd = map->fd; + + return 0; } typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(struct perf_event_header *hdr, diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index db4992a036f8..0b7362397ea3 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -101,6 +101,8 @@ typedef int (*libbpf_print_fn_t)(enum libbpf_print_level level, * be used for libbpf warnings and informational messages. * @param fn The log print function. If NULL, libbpf won't print anything. * @return Pointer to old print function. + * + * This function is thread-safe. */ LIBBPF_API libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn); @@ -719,6 +721,7 @@ bpf_program__attach_freplace(const struct bpf_program *prog, struct bpf_map; LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map); +LIBBPF_API int bpf_link__update_map(struct bpf_link *link, const struct bpf_map *map); struct bpf_iter_attach_opts { size_t sz; /* size of this struct for forward/backward compatibility */ diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 50dde1f6521e..a5aa3a383d69 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -386,6 +386,7 @@ LIBBPF_1.1.0 { LIBBPF_1.2.0 { global: bpf_btf_get_info_by_fd; + bpf_link__update_map; bpf_link_get_info_by_fd; bpf_map_get_info_by_fd; bpf_prog_get_info_by_fd; diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index d7069780984a..5ced96d99f8c 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -1115,7 +1115,19 @@ static int extend_sec(struct bpf_linker *linker, struct dst_sec *dst, struct src if (src->shdr->sh_type != SHT_NOBITS) { tmp = realloc(dst->raw_data, dst_final_sz); - if (!tmp) + /* If dst_align_sz == 0, realloc() behaves in a special way: + * 1. When dst->raw_data is NULL it returns: + * "either NULL or a pointer suitable to be passed to free()" [1]. + * 2. When dst->raw_data is not-NULL it frees dst->raw_data and returns NULL, + * thus invalidating any "pointer suitable to be passed to free()" obtained + * at step (1). + * + * The dst_align_sz > 0 check avoids error exit after (2), otherwise + * dst->raw_data would be freed again in bpf_linker__free(). + * + * [1] man 3 realloc + */ + if (!tmp && dst_align_sz > 0) return -ENOMEM; dst->raw_data = tmp; diff --git a/tools/lib/bpf/zip.c b/tools/lib/bpf/zip.c index f561aa07438f..3f26d629b2b4 100644 --- a/tools/lib/bpf/zip.c +++ b/tools/lib/bpf/zip.c @@ -16,6 +16,10 @@ #include "libbpf_internal.h" #include "zip.h" +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wpacked" +#pragma GCC diagnostic ignored "-Wattributes" + /* Specification of ZIP file format can be found here: * https://pkware.cachefly.net/webdocs/casestudies/APPNOTE.TXT * For a high level overview of the structure of a ZIP file see @@ -119,6 +123,8 @@ struct local_file_header { __u16 extra_field_length; } __attribute__((packed)); +#pragma GCC diagnostic pop + struct zip_archive { void *data; __u32 size; |