diff options
Diffstat (limited to 'kernel/bpf/syscall.c')
| -rw-r--r-- | kernel/bpf/syscall.c | 345 |
1 files changed, 297 insertions, 48 deletions
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 8339d81cba1d..b155cd17c1bd 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -30,7 +30,6 @@ #include <linux/cred.h> #include <linux/timekeeping.h> #include <linux/ctype.h> -#include <linux/btf.h> #include <linux/nospec.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \ @@ -80,7 +79,7 @@ int bpf_check_uarg_tail_zero(void __user *uaddr, if (unlikely(actual_size > PAGE_SIZE)) /* silly large */ return -E2BIG; - if (unlikely(!access_ok(VERIFY_READ, uaddr, actual_size))) + if (unlikely(!access_ok(uaddr, actual_size))) return -EFAULT; if (actual_size <= expected_size) @@ -457,6 +456,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src) } int map_check_no_btf(const struct bpf_map *map, + const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { @@ -479,7 +479,7 @@ static int map_check_btf(const struct bpf_map *map, const struct btf *btf, return -EINVAL; if (map->ops->map_check_btf) - ret = map->ops->map_check_btf(map, key_type, value_type); + ret = map->ops->map_check_btf(map, btf, key_type, value_type); return ret; } @@ -652,6 +652,17 @@ int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) return -ENOTSUPP; } +static void *__bpf_copy_key(void __user *ukey, u64 key_size) +{ + if (key_size) + return memdup_user(ukey, key_size); + + if (ukey) + return ERR_PTR(-EINVAL); + + return NULL; +} + /* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value @@ -679,7 +690,7 @@ static int map_lookup_elem(union bpf_attr *attr) goto err_put; } - key = memdup_user(ukey, map->key_size); + key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; @@ -687,7 +698,8 @@ static int map_lookup_elem(union bpf_attr *attr) if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || + map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) value_size = round_up(map->value_size, 8) * num_possible_cpus(); else if (IS_FD_MAP(map)) value_size = sizeof(u32); @@ -706,6 +718,8 @@ static int map_lookup_elem(union bpf_attr *attr) err = bpf_percpu_hash_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { + err = bpf_percpu_cgroup_storage_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { err = bpf_stackmap_copy(map, key, value); } else if (IS_FD_ARRAY(map)) { @@ -714,13 +728,21 @@ static int map_lookup_elem(union bpf_attr *attr) err = bpf_fd_htab_map_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { err = bpf_fd_reuseport_array_lookup_elem(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK) { + err = map->ops->map_peek_elem(map, value); } else { rcu_read_lock(); ptr = map->ops->map_lookup_elem(map, key); - if (ptr) + if (IS_ERR(ptr)) { + err = PTR_ERR(ptr); + } else if (!ptr) { + err = -ENOENT; + } else { + err = 0; memcpy(value, ptr, value_size); + } rcu_read_unlock(); - err = ptr ? 0 : -ENOENT; } if (err) @@ -741,6 +763,17 @@ err_put: return err; } +static void maybe_wait_bpf_programs(struct bpf_map *map) +{ + /* Wait for any running BPF programs to complete so that + * userspace, when we return to it, knows that all programs + * that could be running use the new map value. + */ + if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS || + map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) + synchronize_rcu(); +} + #define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags static int map_update_elem(union bpf_attr *attr) @@ -767,7 +800,7 @@ static int map_update_elem(union bpf_attr *attr) goto err_put; } - key = memdup_user(ukey, map->key_size); + key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; @@ -775,7 +808,8 @@ static int map_update_elem(union bpf_attr *attr) if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || + map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) value_size = round_up(map->value_size, 8) * num_possible_cpus(); else value_size = map->value_size; @@ -810,6 +844,9 @@ static int map_update_elem(union bpf_attr *attr) err = bpf_percpu_hash_update(map, key, value, attr->flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_update(map, key, value, attr->flags); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { + err = bpf_percpu_cgroup_storage_update(map, key, value, + attr->flags); } else if (IS_FD_ARRAY(map)) { rcu_read_lock(); err = bpf_fd_array_map_update_elem(map, f.file, key, value, @@ -824,6 +861,9 @@ static int map_update_elem(union bpf_attr *attr) /* rcu_read_lock() is not needed */ err = bpf_fd_reuseport_array_update_elem(map, key, value, attr->flags); + } else if (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK) { + err = map->ops->map_push_elem(map, value, attr->flags); } else { rcu_read_lock(); err = map->ops->map_update_elem(map, key, value, attr->flags); @@ -831,6 +871,7 @@ static int map_update_elem(union bpf_attr *attr) } __this_cpu_dec(bpf_prog_active); preempt_enable(); + maybe_wait_bpf_programs(map); out: free_value: kfree(value); @@ -865,7 +906,7 @@ static int map_delete_elem(union bpf_attr *attr) goto err_put; } - key = memdup_user(ukey, map->key_size); + key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; @@ -883,6 +924,7 @@ static int map_delete_elem(union bpf_attr *attr) rcu_read_unlock(); __this_cpu_dec(bpf_prog_active); preempt_enable(); + maybe_wait_bpf_programs(map); out: kfree(key); err_put: @@ -917,7 +959,7 @@ static int map_get_next_key(union bpf_attr *attr) } if (ukey) { - key = memdup_user(ukey, map->key_size); + key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; @@ -958,6 +1000,69 @@ err_put: return err; } +#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD value + +static int map_lookup_and_delete_elem(union bpf_attr *attr) +{ + void __user *ukey = u64_to_user_ptr(attr->key); + void __user *uvalue = u64_to_user_ptr(attr->value); + int ufd = attr->map_fd; + struct bpf_map *map; + void *key, *value; + u32 value_size; + struct fd f; + int err; + + if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM)) + return -EINVAL; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + if (!(f.file->f_mode & FMODE_CAN_WRITE)) { + err = -EPERM; + goto err_put; + } + + key = __bpf_copy_key(ukey, map->key_size); + if (IS_ERR(key)) { + err = PTR_ERR(key); + goto err_put; + } + + value_size = map->value_size; + + err = -ENOMEM; + value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); + if (!value) + goto free_key; + + if (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK) { + err = map->ops->map_pop_elem(map, value); + } else { + err = -ENOTSUPP; + } + + if (err) + goto free_value; + + if (copy_to_user(uvalue, value, value_size) != 0) + goto free_value; + + err = 0; + +free_value: + kfree(value); +free_key: + kfree(key); +err_put: + fdput(f); + return err; +} + static const struct bpf_prog_ops * const bpf_prog_types[] = { #define BPF_PROG_TYPE(_id, _name) \ [_id] = & _name ## _prog_ops, @@ -989,10 +1094,15 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) /* drop refcnt on maps used by eBPF program and free auxilary data */ static void free_used_maps(struct bpf_prog_aux *aux) { + enum bpf_cgroup_storage_type stype; int i; - if (aux->cgroup_storage) - bpf_cgroup_storage_release(aux->prog, aux->cgroup_storage); + for_each_cgroup_storage_type(stype) { + if (!aux->cgroup_storage[stype]) + continue; + bpf_cgroup_storage_release(aux->prog, + aux->cgroup_storage[stype]); + } for (i = 0; i < aux->used_map_cnt; i++) bpf_map_put(aux->used_maps[i]); @@ -1104,6 +1214,9 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) /* bpf_prog_free_id() must be called first */ bpf_prog_free_id(prog, do_idr_lock); bpf_prog_kallsyms_del_all(prog); + btf_put(prog->aux->btf); + kvfree(prog->aux->func_info); + bpf_prog_free_linfo(prog); call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); } @@ -1328,9 +1441,9 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type, } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD expected_attach_type +#define BPF_PROG_LOAD_LAST_FIELD line_info_cnt -static int bpf_prog_load(union bpf_attr *attr) +static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog; @@ -1341,9 +1454,14 @@ static int bpf_prog_load(union bpf_attr *attr) if (CHECK_ATTR(BPF_PROG_LOAD)) return -EINVAL; - if (attr->prog_flags & ~BPF_F_STRICT_ALIGNMENT) + if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | BPF_F_ANY_ALIGNMENT)) return -EINVAL; + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && + (attr->prog_flags & BPF_F_ANY_ALIGNMENT) && + !capable(CAP_SYS_ADMIN)) + return -EPERM; + /* copy eBPF program license from user space */ if (strncpy_from_user(license, u64_to_user_ptr(attr->license), sizeof(license) - 1) < 0) @@ -1355,11 +1473,6 @@ static int bpf_prog_load(union bpf_attr *attr) if (attr->insn_cnt == 0 || attr->insn_cnt > BPF_MAXINSNS) return -E2BIG; - - if (type == BPF_PROG_TYPE_KPROBE && - attr->kern_version != LINUX_VERSION_CODE) - return -EINVAL; - if (type != BPF_PROG_TYPE_SOCKET_FILTER && type != BPF_PROG_TYPE_CGROUP_SKB && !capable(CAP_SYS_ADMIN)) @@ -1416,7 +1529,7 @@ static int bpf_prog_load(union bpf_attr *attr) goto free_prog; /* run eBPF verifier */ - err = bpf_check(&prog, attr); + err = bpf_check(&prog, attr, uattr); if (err < 0) goto free_used_maps; @@ -1444,6 +1557,9 @@ static int bpf_prog_load(union bpf_attr *attr) return err; free_used_maps: + bpf_prog_free_linfo(prog); + kvfree(prog->aux->func_info); + btf_put(prog->aux->btf); bpf_prog_kallsyms_del_subprogs(prog); free_used_maps(prog->aux); free_prog: @@ -1488,6 +1604,7 @@ static int bpf_raw_tracepoint_release(struct inode *inode, struct file *filp) bpf_probe_unregister(raw_tp->btp, raw_tp->prog); bpf_prog_put(raw_tp->prog); } + bpf_put_raw_tracepoint(raw_tp->btp); kfree(raw_tp); return 0; } @@ -1513,13 +1630,15 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) return -EFAULT; tp_name[sizeof(tp_name) - 1] = 0; - btp = bpf_find_raw_tracepoint(tp_name); + btp = bpf_get_raw_tracepoint(tp_name); if (!btp) return -ENOENT; raw_tp = kzalloc(sizeof(*raw_tp), GFP_USER); - if (!raw_tp) - return -ENOMEM; + if (!raw_tp) { + err = -ENOMEM; + goto out_put_btp; + } raw_tp->btp = btp; prog = bpf_prog_get_type(attr->raw_tracepoint.prog_fd, @@ -1547,6 +1666,8 @@ out_put_prog: bpf_prog_put(prog); out_free_tp: kfree(raw_tp); +out_put_btp: + bpf_put_raw_tracepoint(btp); return err; } @@ -1616,6 +1737,9 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_LIRC_MODE2: ptype = BPF_PROG_TYPE_LIRC_MODE2; break; + case BPF_FLOW_DISSECTOR: + ptype = BPF_PROG_TYPE_FLOW_DISSECTOR; + break; default: return -EINVAL; } @@ -1632,11 +1756,14 @@ static int bpf_prog_attach(const union bpf_attr *attr) switch (ptype) { case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: - ret = sockmap_get_from_fd(attr, ptype, prog); + ret = sock_map_get_from_fd(attr, prog); break; case BPF_PROG_TYPE_LIRC_MODE2: ret = lirc_prog_attach(attr, prog); break; + case BPF_PROG_TYPE_FLOW_DISSECTOR: + ret = skb_flow_dissector_bpf_prog_attach(attr, prog); + break; default: ret = cgroup_bpf_prog_attach(attr, ptype, prog); } @@ -1683,12 +1810,14 @@ static int bpf_prog_detach(const union bpf_attr *attr) ptype = BPF_PROG_TYPE_CGROUP_DEVICE; break; case BPF_SK_MSG_VERDICT: - return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, NULL); + return sock_map_get_from_fd(attr, NULL); case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, NULL); + return sock_map_get_from_fd(attr, NULL); case BPF_LIRC_MODE2: return lirc_prog_detach(attr); + case BPF_FLOW_DISSECTOR: + return skb_flow_dissector_bpf_prog_detach(attr); default: return -EINVAL; } @@ -1903,18 +2032,42 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog) insns[i + 1].imm = 0; continue; } - - if (!bpf_dump_raw_ok() && - imm == (unsigned long)prog->aux) { - insns[i].imm = 0; - insns[i + 1].imm = 0; - continue; - } } return insns; } +static int set_info_rec_size(struct bpf_prog_info *info) +{ + /* + * Ensure info.*_rec_size is the same as kernel expected size + * + * or + * + * Only allow zero *_rec_size if both _rec_size and _cnt are + * zero. In this case, the kernel will set the expected + * _rec_size back to the info. + */ + + if ((info->nr_func_info || info->func_info_rec_size) && + info->func_info_rec_size != sizeof(struct bpf_func_info)) + return -EINVAL; + + if ((info->nr_line_info || info->line_info_rec_size) && + info->line_info_rec_size != sizeof(struct bpf_line_info)) + return -EINVAL; + + if ((info->nr_jited_line_info || info->jited_line_info_rec_size) && + info->jited_line_info_rec_size != sizeof(__u64)) + return -EINVAL; + + info->func_info_rec_size = sizeof(struct bpf_func_info); + info->line_info_rec_size = sizeof(struct bpf_line_info); + info->jited_line_info_rec_size = sizeof(__u64); + + return 0; +} + static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, const union bpf_attr *attr, union bpf_attr __user *uattr) @@ -1957,10 +2110,18 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, return -EFAULT; } + err = set_info_rec_size(&info); + if (err) + return err; + if (!capable(CAP_SYS_ADMIN)) { info.jited_prog_len = 0; info.xlated_prog_len = 0; info.nr_jited_ksyms = 0; + info.nr_jited_func_lens = 0; + info.nr_func_info = 0; + info.nr_line_info = 0; + info.nr_jited_line_info = 0; goto done; } @@ -2041,11 +2202,11 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, } ulen = info.nr_jited_ksyms; - info.nr_jited_ksyms = prog->aux->func_cnt; - if (info.nr_jited_ksyms && ulen) { + info.nr_jited_ksyms = prog->aux->func_cnt ? : 1; + if (ulen) { if (bpf_dump_raw_ok()) { + unsigned long ksym_addr; u64 __user *user_ksyms; - ulong ksym_addr; u32 i; /* copy the address of the kernel symbol @@ -2053,10 +2214,17 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, */ ulen = min_t(u32, info.nr_jited_ksyms, ulen); user_ksyms = u64_to_user_ptr(info.jited_ksyms); - for (i = 0; i < ulen; i++) { - ksym_addr = (ulong) prog->aux->func[i]->bpf_func; - ksym_addr &= PAGE_MASK; - if (put_user((u64) ksym_addr, &user_ksyms[i])) + if (prog->aux->func_cnt) { + for (i = 0; i < ulen; i++) { + ksym_addr = (unsigned long) + prog->aux->func[i]->bpf_func; + if (put_user((u64) ksym_addr, + &user_ksyms[i])) + return -EFAULT; + } + } else { + ksym_addr = (unsigned long) prog->bpf_func; + if (put_user((u64) ksym_addr, &user_ksyms[0])) return -EFAULT; } } else { @@ -2065,8 +2233,8 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, } ulen = info.nr_jited_func_lens; - info.nr_jited_func_lens = prog->aux->func_cnt; - if (info.nr_jited_func_lens && ulen) { + info.nr_jited_func_lens = prog->aux->func_cnt ? : 1; + if (ulen) { if (bpf_dump_raw_ok()) { u32 __user *user_lens; u32 func_len, i; @@ -2074,9 +2242,16 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, /* copy the JITed image lengths for each function */ ulen = min_t(u32, info.nr_jited_func_lens, ulen); user_lens = u64_to_user_ptr(info.jited_func_lens); - for (i = 0; i < ulen; i++) { - func_len = prog->aux->func[i]->jited_len; - if (put_user(func_len, &user_lens[i])) + if (prog->aux->func_cnt) { + for (i = 0; i < ulen; i++) { + func_len = + prog->aux->func[i]->jited_len; + if (put_user(func_len, &user_lens[i])) + return -EFAULT; + } + } else { + func_len = prog->jited_len; + if (put_user(func_len, &user_lens[0])) return -EFAULT; } } else { @@ -2084,6 +2259,77 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, } } + if (prog->aux->btf) + info.btf_id = btf_id(prog->aux->btf); + + ulen = info.nr_func_info; + info.nr_func_info = prog->aux->func_info_cnt; + if (info.nr_func_info && ulen) { + char __user *user_finfo; + + user_finfo = u64_to_user_ptr(info.func_info); + ulen = min_t(u32, info.nr_func_info, ulen); + if (copy_to_user(user_finfo, prog->aux->func_info, + info.func_info_rec_size * ulen)) + return -EFAULT; + } + + ulen = info.nr_line_info; + info.nr_line_info = prog->aux->nr_linfo; + if (info.nr_line_info && ulen) { + __u8 __user *user_linfo; + + user_linfo = u64_to_user_ptr(info.line_info); + ulen = min_t(u32, info.nr_line_info, ulen); + if (copy_to_user(user_linfo, prog->aux->linfo, + info.line_info_rec_size * ulen)) + return -EFAULT; + } + + ulen = info.nr_jited_line_info; + if (prog->aux->jited_linfo) + info.nr_jited_line_info = prog->aux->nr_linfo; + else + info.nr_jited_line_info = 0; + if (info.nr_jited_line_info && ulen) { + if (bpf_dump_raw_ok()) { + __u64 __user *user_linfo; + u32 i; + + user_linfo = u64_to_user_ptr(info.jited_line_info); + ulen = min_t(u32, info.nr_jited_line_info, ulen); + for (i = 0; i < ulen; i++) { + if (put_user((__u64)(long)prog->aux->jited_linfo[i], + &user_linfo[i])) + return -EFAULT; + } + } else { + info.jited_line_info = 0; + } + } + + ulen = info.nr_prog_tags; + info.nr_prog_tags = prog->aux->func_cnt ? : 1; + if (ulen) { + __u8 __user (*user_prog_tags)[BPF_TAG_SIZE]; + u32 i; + + user_prog_tags = u64_to_user_ptr(info.prog_tags); + ulen = min_t(u32, info.nr_prog_tags, ulen); + if (prog->aux->func_cnt) { + for (i = 0; i < ulen; i++) { + if (copy_to_user(user_prog_tags[i], + prog->aux->func[i]->tag, + BPF_TAG_SIZE)) + return -EFAULT; + } + } else { + if (copy_to_user(user_prog_tags[0], + prog->tag, BPF_TAG_SIZE)) + return -EFAULT; + } + } + done: if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) @@ -2369,7 +2615,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = map_get_next_key(&attr); break; case BPF_PROG_LOAD: - err = bpf_prog_load(&attr); + err = bpf_prog_load(&attr, uattr); break; case BPF_OBJ_PIN: err = bpf_obj_pin(&attr); @@ -2418,6 +2664,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_TASK_FD_QUERY: err = bpf_task_fd_query(&attr, uattr); break; + case BPF_MAP_LOOKUP_AND_DELETE_ELEM: + err = map_lookup_and_delete_elem(&attr); + break; default: err = -EINVAL; break; |
