diff options
Diffstat (limited to 'kernel/bpf')
-rw-r--r-- | kernel/bpf/Kconfig | 1 | ||||
-rw-r--r-- | kernel/bpf/bpf_local_storage.c | 52 | ||||
-rw-r--r-- | kernel/bpf/bpf_lsm.c | 6 | ||||
-rw-r--r-- | kernel/bpf/bpf_struct_ops.c | 227 | ||||
-rw-r--r-- | kernel/bpf/btf.c | 275 | ||||
-rw-r--r-- | kernel/bpf/cgroup.c | 3 | ||||
-rw-r--r-- | kernel/bpf/cpumask.c | 4 | ||||
-rw-r--r-- | kernel/bpf/helpers.c | 16 | ||||
-rw-r--r-- | kernel/bpf/log.c | 62 | ||||
-rw-r--r-- | kernel/bpf/lpm_trie.c | 20 | ||||
-rw-r--r-- | kernel/bpf/map_iter.c | 4 | ||||
-rw-r--r-- | kernel/bpf/token.c | 16 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 236 |
13 files changed, 681 insertions, 241 deletions
diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig index 6a906ff93006..bc25f5098a25 100644 --- a/kernel/bpf/Kconfig +++ b/kernel/bpf/Kconfig @@ -3,6 +3,7 @@ # BPF interpreter that, for example, classic socket filters depend on. config BPF bool + select CRYPTO_LIB_SHA1 # Used by archs to tell that they support BPF JIT compiler plus which # flavour. Only one of the two can be selected for a specific arch since diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index 146824cc9689..bdea1a459153 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -414,47 +414,21 @@ void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool reuse_now) bpf_selem_unlink_storage(selem, reuse_now); } -/* If cacheit_lockit is false, this lookup function is lockless */ -struct bpf_local_storage_data * -bpf_local_storage_lookup(struct bpf_local_storage *local_storage, - struct bpf_local_storage_map *smap, - bool cacheit_lockit) +void __bpf_local_storage_insert_cache(struct bpf_local_storage *local_storage, + struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem) { - struct bpf_local_storage_data *sdata; - struct bpf_local_storage_elem *selem; - - /* Fast path (cache hit) */ - sdata = rcu_dereference_check(local_storage->cache[smap->cache_idx], - bpf_rcu_lock_held()); - if (sdata && rcu_access_pointer(sdata->smap) == smap) - return sdata; - - /* Slow path (cache miss) */ - hlist_for_each_entry_rcu(selem, &local_storage->list, snode, - rcu_read_lock_trace_held()) - if (rcu_access_pointer(SDATA(selem)->smap) == smap) - break; - - if (!selem) - return NULL; - - sdata = SDATA(selem); - if (cacheit_lockit) { - unsigned long flags; - - /* spinlock is needed to avoid racing with the - * parallel delete. Otherwise, publishing an already - * deleted sdata to the cache will become a use-after-free - * problem in the next bpf_local_storage_lookup(). - */ - raw_spin_lock_irqsave(&local_storage->lock, flags); - if (selem_linked_to_storage(selem)) - rcu_assign_pointer(local_storage->cache[smap->cache_idx], - sdata); - raw_spin_unlock_irqrestore(&local_storage->lock, flags); - } + unsigned long flags; - return sdata; + /* spinlock is needed to avoid racing with the + * parallel delete. Otherwise, publishing an already + * deleted sdata to the cache will become a use-after-free + * problem in the next bpf_local_storage_lookup(). + */ + raw_spin_lock_irqsave(&local_storage->lock, flags); + if (selem_linked_to_storage(selem)) + rcu_assign_pointer(local_storage->cache[smap->cache_idx], SDATA(selem)); + raw_spin_unlock_irqrestore(&local_storage->lock, flags); } static int check_flags(const struct bpf_local_storage_data *old_sdata, diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 63b4dc495125..68240c3c6e7d 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -282,10 +282,6 @@ BTF_ID(func, bpf_lsm_file_lock) BTF_ID(func, bpf_lsm_file_open) BTF_ID(func, bpf_lsm_file_receive) -#ifdef CONFIG_SECURITY_NETWORK -BTF_ID(func, bpf_lsm_inet_conn_established) -#endif /* CONFIG_SECURITY_NETWORK */ - BTF_ID(func, bpf_lsm_inode_create) BTF_ID(func, bpf_lsm_inode_free_security) BTF_ID(func, bpf_lsm_inode_getattr) @@ -336,6 +332,8 @@ BTF_ID(func, bpf_lsm_sb_umount) BTF_ID(func, bpf_lsm_settime) #ifdef CONFIG_SECURITY_NETWORK +BTF_ID(func, bpf_lsm_inet_conn_established) + BTF_ID(func, bpf_lsm_socket_accept) BTF_ID(func, bpf_lsm_socket_bind) BTF_ID(func, bpf_lsm_socket_connect) diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 0decd862dfe0..a6019087b467 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -116,17 +116,183 @@ static bool is_valid_value_type(struct btf *btf, s32 value_id, return true; } +#define MAYBE_NULL_SUFFIX "__nullable" +#define MAX_STUB_NAME 128 + +/* Return the type info of a stub function, if it exists. + * + * The name of a stub function is made up of the name of the struct_ops and + * the name of the function pointer member, separated by "__". For example, + * if the struct_ops type is named "foo_ops" and the function pointer + * member is named "bar", the stub function name would be "foo_ops__bar". + */ +static const struct btf_type * +find_stub_func_proto(const struct btf *btf, const char *st_op_name, + const char *member_name) +{ + char stub_func_name[MAX_STUB_NAME]; + const struct btf_type *func_type; + s32 btf_id; + int cp; + + cp = snprintf(stub_func_name, MAX_STUB_NAME, "%s__%s", + st_op_name, member_name); + if (cp >= MAX_STUB_NAME) { + pr_warn("Stub function name too long\n"); + return NULL; + } + btf_id = btf_find_by_name_kind(btf, stub_func_name, BTF_KIND_FUNC); + if (btf_id < 0) + return NULL; + func_type = btf_type_by_id(btf, btf_id); + if (!func_type) + return NULL; + + return btf_type_by_id(btf, func_type->type); /* FUNC_PROTO */ +} + +/* Prepare argument info for every nullable argument of a member of a + * struct_ops type. + * + * Initialize a struct bpf_struct_ops_arg_info according to type info of + * the arguments of a stub function. (Check kCFI for more information about + * stub functions.) + * + * Each member in the struct_ops type has a struct bpf_struct_ops_arg_info + * to provide an array of struct bpf_ctx_arg_aux, which in turn provides + * the information that used by the verifier to check the arguments of the + * BPF struct_ops program assigned to the member. Here, we only care about + * the arguments that are marked as __nullable. + * + * The array of struct bpf_ctx_arg_aux is eventually assigned to + * prog->aux->ctx_arg_info of BPF struct_ops programs and passed to the + * verifier. (See check_struct_ops_btf_id()) + * + * arg_info->info will be the list of struct bpf_ctx_arg_aux if success. If + * fails, it will be kept untouched. + */ +static int prepare_arg_info(struct btf *btf, + const char *st_ops_name, + const char *member_name, + const struct btf_type *func_proto, + struct bpf_struct_ops_arg_info *arg_info) +{ + const struct btf_type *stub_func_proto, *pointed_type; + const struct btf_param *stub_args, *args; + struct bpf_ctx_arg_aux *info, *info_buf; + u32 nargs, arg_no, info_cnt = 0; + u32 arg_btf_id; + int offset; + + stub_func_proto = find_stub_func_proto(btf, st_ops_name, member_name); + if (!stub_func_proto) + return 0; + + /* Check if the number of arguments of the stub function is the same + * as the number of arguments of the function pointer. + */ + nargs = btf_type_vlen(func_proto); + if (nargs != btf_type_vlen(stub_func_proto)) { + pr_warn("the number of arguments of the stub function %s__%s does not match the number of arguments of the member %s of struct %s\n", + st_ops_name, member_name, member_name, st_ops_name); + return -EINVAL; + } + + if (!nargs) + return 0; + + args = btf_params(func_proto); + stub_args = btf_params(stub_func_proto); + + info_buf = kcalloc(nargs, sizeof(*info_buf), GFP_KERNEL); + if (!info_buf) + return -ENOMEM; + + /* Prepare info for every nullable argument */ + info = info_buf; + for (arg_no = 0; arg_no < nargs; arg_no++) { + /* Skip arguments that is not suffixed with + * "__nullable". + */ + if (!btf_param_match_suffix(btf, &stub_args[arg_no], + MAYBE_NULL_SUFFIX)) + continue; + + /* Should be a pointer to struct */ + pointed_type = btf_type_resolve_ptr(btf, + args[arg_no].type, + &arg_btf_id); + if (!pointed_type || + !btf_type_is_struct(pointed_type)) { + pr_warn("stub function %s__%s has %s tagging to an unsupported type\n", + st_ops_name, member_name, MAYBE_NULL_SUFFIX); + goto err_out; + } + + offset = btf_ctx_arg_offset(btf, func_proto, arg_no); + if (offset < 0) { + pr_warn("stub function %s__%s has an invalid trampoline ctx offset for arg#%u\n", + st_ops_name, member_name, arg_no); + goto err_out; + } + + if (args[arg_no].type != stub_args[arg_no].type) { + pr_warn("arg#%u type in stub function %s__%s does not match with its original func_proto\n", + arg_no, st_ops_name, member_name); + goto err_out; + } + + /* Fill the information of the new argument */ + info->reg_type = + PTR_TRUSTED | PTR_TO_BTF_ID | PTR_MAYBE_NULL; + info->btf_id = arg_btf_id; + info->btf = btf; + info->offset = offset; + + info++; + info_cnt++; + } + + if (info_cnt) { + arg_info->info = info_buf; + arg_info->cnt = info_cnt; + } else { + kfree(info_buf); + } + + return 0; + +err_out: + kfree(info_buf); + + return -EINVAL; +} + +/* Clean up the arg_info in a struct bpf_struct_ops_desc. */ +void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_ops_desc) +{ + struct bpf_struct_ops_arg_info *arg_info; + int i; + + arg_info = st_ops_desc->arg_info; + for (i = 0; i < btf_type_vlen(st_ops_desc->type); i++) + kfree(arg_info[i].info); + + kfree(arg_info); +} + int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, struct btf *btf, struct bpf_verifier_log *log) { struct bpf_struct_ops *st_ops = st_ops_desc->st_ops; + struct bpf_struct_ops_arg_info *arg_info; const struct btf_member *member; const struct btf_type *t; s32 type_id, value_id; char value_name[128]; const char *mname; - int i; + int i, err; if (strlen(st_ops->name) + VALUE_PREFIX_LEN >= sizeof(value_name)) { @@ -136,6 +302,11 @@ int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, } sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name); + if (!st_ops->cfi_stubs) { + pr_warn("struct_ops for %s has no cfi_stubs\n", st_ops->name); + return -EINVAL; + } + type_id = btf_find_by_name_kind(btf, st_ops->name, BTF_KIND_STRUCT); if (type_id < 0) { @@ -160,6 +331,17 @@ int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, if (!is_valid_value_type(btf, value_id, t, value_name)) return -EINVAL; + arg_info = kcalloc(btf_type_vlen(t), sizeof(*arg_info), + GFP_KERNEL); + if (!arg_info) + return -ENOMEM; + + st_ops_desc->arg_info = arg_info; + st_ops_desc->type = t; + st_ops_desc->type_id = type_id; + st_ops_desc->value_id = value_id; + st_ops_desc->value_type = btf_type_by_id(btf, value_id); + for_each_member(i, t, member) { const struct btf_type *func_proto; @@ -167,43 +349,52 @@ int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, if (!*mname) { pr_warn("anon member in struct %s is not supported\n", st_ops->name); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto errout; } if (__btf_member_bitfield_size(t, member)) { pr_warn("bit field member %s in struct %s is not supported\n", mname, st_ops->name); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto errout; } func_proto = btf_type_resolve_func_ptr(btf, member->type, NULL); - if (func_proto && - btf_distill_func_proto(log, btf, + if (!func_proto) + continue; + + if (btf_distill_func_proto(log, btf, func_proto, mname, &st_ops->func_models[i])) { pr_warn("Error in parsing func ptr %s in struct %s\n", mname, st_ops->name); - return -EINVAL; + err = -EINVAL; + goto errout; } + + err = prepare_arg_info(btf, st_ops->name, mname, + func_proto, + arg_info + i); + if (err) + goto errout; } - if (i == btf_type_vlen(t)) { - if (st_ops->init(btf)) { - pr_warn("Error in init bpf_struct_ops %s\n", - st_ops->name); - return -EINVAL; - } else { - st_ops_desc->type_id = type_id; - st_ops_desc->type = t; - st_ops_desc->value_id = value_id; - st_ops_desc->value_type = btf_type_by_id(btf, - value_id); - } + if (st_ops->init(btf)) { + pr_warn("Error in init bpf_struct_ops %s\n", + st_ops->name); + err = -EINVAL; + goto errout; } return 0; + +errout: + bpf_struct_ops_desc_release(st_ops_desc); + + return err; } static int bpf_struct_ops_map_get_next_key(struct bpf_map *map, void *key, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index edef96ceffa3..6ff0bd1a91d5 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -1699,6 +1699,13 @@ static void btf_free_struct_meta_tab(struct btf *btf) static void btf_free_struct_ops_tab(struct btf *btf) { struct btf_struct_ops_tab *tab = btf->struct_ops_tab; + u32 i; + + if (!tab) + return; + + for (i = 0; i < tab->cnt; i++) + bpf_struct_ops_desc_release(&tab->ops[i]); kfree(tab); btf->struct_ops_tab = NULL; @@ -5687,15 +5694,29 @@ static int find_kern_ctx_type_id(enum bpf_prog_type prog_type) return ctx_type->type; } -const struct btf_type * -btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, - const struct btf_type *t, enum bpf_prog_type prog_type, - int arg) +bool btf_is_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, enum bpf_prog_type prog_type, + int arg) { const struct btf_type *ctx_type; const char *tname, *ctx_tname; t = btf_type_by_id(btf, t->type); + + /* KPROBE programs allow bpf_user_pt_regs_t typedef, which we need to + * check before we skip all the typedef below. + */ + if (prog_type == BPF_PROG_TYPE_KPROBE) { + while (btf_type_is_modifier(t) && !btf_type_is_typedef(t)) + t = btf_type_by_id(btf, t->type); + + if (btf_type_is_typedef(t)) { + tname = btf_name_by_offset(btf, t->name_off); + if (tname && strcmp(tname, "bpf_user_pt_regs_t") == 0) + return true; + } + } + while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); if (!btf_type_is_struct(t)) { @@ -5704,27 +5725,30 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, * is not supported yet. * BPF_PROG_TYPE_RAW_TRACEPOINT is fine. */ - return NULL; + return false; } tname = btf_name_by_offset(btf, t->name_off); if (!tname) { bpf_log(log, "arg#%d struct doesn't have a name\n", arg); - return NULL; + return false; } ctx_type = find_canonical_prog_ctx_type(prog_type); if (!ctx_type) { bpf_log(log, "btf_vmlinux is malformed\n"); /* should not happen */ - return NULL; + return false; } again: ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off); if (!ctx_tname) { /* should not happen */ bpf_log(log, "Please fix kernel include/linux/bpf_types.h\n"); - return NULL; + return false; } + /* program types without named context types work only with arg:ctx tag */ + if (ctx_tname[0] == '\0') + return false; /* only compare that prog's ctx type name is the same as * kernel expects. No need to compare field by field. * It's ok for bpf prog to do: @@ -5733,20 +5757,20 @@ again: * { // no fields of skb are ever used } */ if (strcmp(ctx_tname, "__sk_buff") == 0 && strcmp(tname, "sk_buff") == 0) - return ctx_type; + return true; if (strcmp(ctx_tname, "xdp_md") == 0 && strcmp(tname, "xdp_buff") == 0) - return ctx_type; + return true; if (strcmp(ctx_tname, tname)) { /* bpf_user_pt_regs_t is a typedef, so resolve it to * underlying struct and check name again */ if (!btf_type_is_modifier(ctx_type)) - return NULL; + return false; while (btf_type_is_modifier(ctx_type)) ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type); goto again; } - return ctx_type; + return true; } /* forward declarations for arch-specific underlying types of @@ -5898,7 +5922,7 @@ static int btf_translate_to_vmlinux(struct bpf_verifier_log *log, enum bpf_prog_type prog_type, int arg) { - if (!btf_get_prog_ctx_type(log, btf, t, prog_type, arg)) + if (!btf_is_prog_ctx_type(log, btf, t, prog_type, arg)) return -ENOENT; return find_kern_ctx_type_id(prog_type); } @@ -6130,6 +6154,26 @@ static bool prog_args_trusted(const struct bpf_prog *prog) } } +int btf_ctx_arg_offset(const struct btf *btf, const struct btf_type *func_proto, + u32 arg_no) +{ + const struct btf_param *args; + const struct btf_type *t; + int off = 0, i; + u32 sz; + + args = btf_params(func_proto); + for (i = 0; i < arg_no; i++) { + t = btf_type_by_id(btf, args[i].type); + t = btf_resolve_size(btf, t, &sz); + if (IS_ERR(t)) + return PTR_ERR(t); + off += roundup(sz, 8); + } + + return off; +} + bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) @@ -6266,7 +6310,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, } info->reg_type = ctx_arg_info->reg_type; - info->btf = btf_vmlinux; + info->btf = ctx_arg_info->btf ? : btf_vmlinux; info->btf_id = ctx_arg_info->btf_id; return true; } @@ -6985,9 +7029,78 @@ static bool btf_is_dynptr_ptr(const struct btf *btf, const struct btf_type *t) return false; } +struct bpf_cand_cache { + const char *name; + u32 name_len; + u16 kind; + u16 cnt; + struct { + const struct btf *btf; + u32 id; + } cands[]; +}; + +static DEFINE_MUTEX(cand_cache_mutex); + +static struct bpf_cand_cache * +bpf_core_find_cands(struct bpf_core_ctx *ctx, u32 local_type_id); + +static int btf_get_ptr_to_btf_id(struct bpf_verifier_log *log, int arg_idx, + const struct btf *btf, const struct btf_type *t) +{ + struct bpf_cand_cache *cc; + struct bpf_core_ctx ctx = { + .btf = btf, + .log = log, + }; + u32 kern_type_id, type_id; + int err = 0; + + /* skip PTR and modifiers */ + type_id = t->type; + t = btf_type_by_id(btf, t->type); + while (btf_type_is_modifier(t)) { + type_id = t->type; + t = btf_type_by_id(btf, t->type); + } + + mutex_lock(&cand_cache_mutex); + cc = bpf_core_find_cands(&ctx, type_id); + if (IS_ERR(cc)) { + err = PTR_ERR(cc); + bpf_log(log, "arg#%d reference type('%s %s') candidate matching error: %d\n", + arg_idx, btf_type_str(t), __btf_name_by_offset(btf, t->name_off), + err); + goto cand_cache_unlock; + } + if (cc->cnt != 1) { + bpf_log(log, "arg#%d reference type('%s %s') %s\n", + arg_idx, btf_type_str(t), __btf_name_by_offset(btf, t->name_off), + cc->cnt == 0 ? "has no matches" : "is ambiguous"); + err = cc->cnt == 0 ? -ENOENT : -ESRCH; + goto cand_cache_unlock; + } + if (btf_is_module(cc->cands[0].btf)) { + bpf_log(log, "arg#%d reference type('%s %s') points to kernel module type (unsupported)\n", + arg_idx, btf_type_str(t), __btf_name_by_offset(btf, t->name_off)); + err = -EOPNOTSUPP; + goto cand_cache_unlock; + } + kern_type_id = cc->cands[0].id; + +cand_cache_unlock: + mutex_unlock(&cand_cache_mutex); + if (err) + return err; + + return kern_type_id; +} + enum btf_arg_tag { ARG_TAG_CTX = 0x1, ARG_TAG_NONNULL = 0x2, + ARG_TAG_TRUSTED = 0x4, + ARG_TAG_NULLABLE = 0x8, }; /* Process BTF of a function to produce high-level expectation of function @@ -7053,6 +7166,8 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) args = (const struct btf_param *)(t + 1); nargs = btf_type_vlen(t); if (nargs > MAX_BPF_FUNC_REG_ARGS) { + if (!is_global) + return -EINVAL; bpf_log(log, "Global function %s() with %d > %d args. Buggy compiler.\n", tname, nargs, MAX_BPF_FUNC_REG_ARGS); return -EINVAL; @@ -7062,6 +7177,8 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); if (!btf_type_is_int(t) && !btf_is_any_enum(t)) { + if (!is_global) + return -EINVAL; bpf_log(log, "Global function %s() doesn't return scalar. Only those are supported.\n", tname); @@ -7089,8 +7206,12 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) if (strcmp(tag, "ctx") == 0) { tags |= ARG_TAG_CTX; + } else if (strcmp(tag, "trusted") == 0) { + tags |= ARG_TAG_TRUSTED; } else if (strcmp(tag, "nonnull") == 0) { tags |= ARG_TAG_NONNULL; + } else if (strcmp(tag, "nullable") == 0) { + tags |= ARG_TAG_NULLABLE; } else { bpf_log(log, "arg#%d has unsupported set of tags\n", i); return -EOPNOTSUPP; @@ -7107,11 +7228,15 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) if (!btf_type_is_ptr(t)) goto skip_pointer; - if ((tags & ARG_TAG_CTX) || btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { + if ((tags & ARG_TAG_CTX) || btf_is_prog_ctx_type(log, btf, t, prog_type, i)) { if (tags & ~ARG_TAG_CTX) { bpf_log(log, "arg#%d has invalid combination of tags\n", i); return -EINVAL; } + if ((tags & ARG_TAG_CTX) && + btf_validate_prog_ctx_type(log, btf, t, i, prog_type, + prog->expected_attach_type)) + return -EINVAL; sub->args[i].arg_type = ARG_PTR_TO_CTX; continue; } @@ -7123,9 +7248,32 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) sub->args[i].arg_type = ARG_PTR_TO_DYNPTR | MEM_RDONLY; continue; } + if (tags & ARG_TAG_TRUSTED) { + int kern_type_id; + + if (tags & ARG_TAG_NONNULL) { + bpf_log(log, "arg#%d has invalid combination of tags\n", i); + return -EINVAL; + } + + kern_type_id = btf_get_ptr_to_btf_id(log, i, btf, t); + if (kern_type_id < 0) + return kern_type_id; + + sub->args[i].arg_type = ARG_PTR_TO_BTF_ID | PTR_TRUSTED; + if (tags & ARG_TAG_NULLABLE) + sub->args[i].arg_type |= PTR_MAYBE_NULL; + sub->args[i].btf_id = kern_type_id; + continue; + } if (is_global) { /* generic user data pointer */ u32 mem_size; + if (tags & ARG_TAG_NULLABLE) { + bpf_log(log, "arg#%d has invalid combination of tags\n", i); + return -EINVAL; + } + t = btf_type_skip_modifiers(btf, t->type, NULL); ref_t = btf_resolve_size(btf, t, &mem_size); if (IS_ERR(ref_t)) { @@ -7151,28 +7299,13 @@ skip_pointer: sub->args[i].arg_type = ARG_ANYTHING; continue; } + if (!is_global) + return -EINVAL; bpf_log(log, "Arg#%d type %s in %s() is not supported yet.\n", i, btf_type_str(t), tname); return -EINVAL; } - for (i = 0; i < nargs; i++) { - const char *tag; - - if (sub->args[i].arg_type != ARG_PTR_TO_CTX) - continue; - - /* check if arg has "arg:ctx" tag */ - t = btf_type_by_id(btf, args[i].type); - tag = btf_find_decl_tag_value(btf, fn_t, i, "arg:"); - if (IS_ERR_OR_NULL(tag) || strcmp(tag, "ctx") != 0) - continue; - - if (btf_validate_prog_ctx_type(log, btf, t, i, prog_type, - prog->expected_attach_type)) - return -EINVAL; - } - sub->arg_cnt = nargs; sub->args_cached = true; @@ -7649,6 +7782,17 @@ static struct btf *btf_get_module_btf(const struct module *module) return btf; } +static int check_btf_kconfigs(const struct module *module, const char *feature) +{ + if (!module && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { + pr_err("missing vmlinux BTF, cannot register %s\n", feature); + return -ENOENT; + } + if (module && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) + pr_warn("missing module BTF, cannot register %s\n", feature); + return 0; +} + BPF_CALL_4(bpf_btf_find_by_name_kind, char *, name, int, name_sz, u32, kind, int, flags) { struct btf *btf = NULL; @@ -8009,15 +8153,8 @@ static int __register_btf_kfunc_id_set(enum btf_kfunc_hook hook, int ret, i; btf = btf_get_module_btf(kset->owner); - if (!btf) { - if (!kset->owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { - pr_err("missing vmlinux BTF, cannot register kfuncs\n"); - return -ENOENT; - } - if (kset->owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) - pr_warn("missing module BTF, cannot register kfuncs\n"); - return 0; - } + if (!btf) + return check_btf_kconfigs(kset->owner, "kfunc"); if (IS_ERR(btf)) return PTR_ERR(btf); @@ -8041,6 +8178,14 @@ int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, { enum btf_kfunc_hook hook; + /* All kfuncs need to be tagged as such in BTF. + * WARN() for initcall registrations that do not check errors. + */ + if (!(kset->set->flags & BTF_SET8_KFUNCS)) { + WARN_ON(!kset->owner); + return -EINVAL; + } + hook = bpf_prog_type_to_kfunc_hook(prog_type); return __register_btf_kfunc_id_set(hook, kset); } @@ -8117,17 +8262,8 @@ int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_c int ret; btf = btf_get_module_btf(owner); - if (!btf) { - if (!owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { - pr_err("missing vmlinux BTF, cannot register dtor kfuncs\n"); - return -ENOENT; - } - if (owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) { - pr_err("missing module BTF, cannot register dtor kfuncs\n"); - return -ENOENT; - } - return 0; - } + if (!btf) + return check_btf_kconfigs(owner, "dtor kfuncs"); if (IS_ERR(btf)) return PTR_ERR(btf); @@ -8242,17 +8378,6 @@ size_t bpf_core_essential_name_len(const char *name) return n; } -struct bpf_cand_cache { - const char *name; - u32 name_len; - u16 kind; - u16 cnt; - struct { - const struct btf *btf; - u32 id; - } cands[]; -}; - static void bpf_free_cands(struct bpf_cand_cache *cands) { if (!cands->cnt) @@ -8273,8 +8398,6 @@ static struct bpf_cand_cache *vmlinux_cand_cache[VMLINUX_CAND_CACHE_SIZE]; #define MODULE_CAND_CACHE_SIZE 31 static struct bpf_cand_cache *module_cand_cache[MODULE_CAND_CACHE_SIZE]; -static DEFINE_MUTEX(cand_cache_mutex); - static void __print_cand_cache(struct bpf_verifier_log *log, struct bpf_cand_cache **cache, int cache_size) @@ -8803,7 +8926,9 @@ int __register_bpf_struct_ops(struct bpf_struct_ops *st_ops) btf = btf_get_module_btf(st_ops->owner); if (!btf) - return -EINVAL; + return check_btf_kconfigs(st_ops->owner, "struct_ops"); + if (IS_ERR(btf)) + return PTR_ERR(btf); log = kzalloc(sizeof(*log), GFP_KERNEL | __GFP_NOWARN); if (!log) { @@ -8823,3 +8948,21 @@ errout: } EXPORT_SYMBOL_GPL(__register_bpf_struct_ops); #endif + +bool btf_param_match_suffix(const struct btf *btf, + const struct btf_param *arg, + const char *suffix) +{ + int suffix_len = strlen(suffix), len; + const char *param_name; + + /* In the future, this can be ported to use BTF tagging */ + param_name = btf_name_by_offset(btf, arg->name_off); + if (str_is_empty(param_name)) + return false; + len = strlen(param_name); + if (len <= suffix_len) + return false; + param_name += len - suffix_len; + return !strncmp(param_name, suffix, suffix_len); +} diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 98e0e3835b28..5a568bbbeaeb 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1364,9 +1364,6 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, struct cgroup *cgrp; int ret; - if (!sk || !sk_fullsock(sk)) - return 0; - if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6) return 0; diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c index 2e73533a3811..dad0fb1c8e87 100644 --- a/kernel/bpf/cpumask.c +++ b/kernel/bpf/cpumask.c @@ -424,7 +424,7 @@ __bpf_kfunc u32 bpf_cpumask_weight(const struct cpumask *cpumask) __bpf_kfunc_end_defs(); -BTF_SET8_START(cpumask_kfunc_btf_ids) +BTF_KFUNCS_START(cpumask_kfunc_btf_ids) BTF_ID_FLAGS(func, bpf_cpumask_create, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_cpumask_release, KF_RELEASE) BTF_ID_FLAGS(func, bpf_cpumask_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS) @@ -450,7 +450,7 @@ BTF_ID_FLAGS(func, bpf_cpumask_copy, KF_RCU) BTF_ID_FLAGS(func, bpf_cpumask_any_distribute, KF_RCU) BTF_ID_FLAGS(func, bpf_cpumask_any_and_distribute, KF_RCU) BTF_ID_FLAGS(func, bpf_cpumask_weight, KF_RCU) -BTF_SET8_END(cpumask_kfunc_btf_ids) +BTF_KFUNCS_END(cpumask_kfunc_btf_ids) static const struct btf_kfunc_id_set cpumask_kfunc_set = { .owner = THIS_MODULE, diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 3da54d0b3469..a89587859571 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -334,7 +334,7 @@ static inline void __bpf_spin_lock_irqsave(struct bpf_spin_lock *lock) __this_cpu_write(irqsave_flags, flags); } -notrace BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) +NOTRACE_BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) { __bpf_spin_lock_irqsave(lock); return 0; @@ -357,7 +357,7 @@ static inline void __bpf_spin_unlock_irqrestore(struct bpf_spin_lock *lock) local_irq_restore(flags); } -notrace BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) +NOTRACE_BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) { __bpf_spin_unlock_irqrestore(lock); return 0; @@ -2487,9 +2487,9 @@ __bpf_kfunc void *bpf_cast_to_kern_ctx(void *obj) return obj; } -__bpf_kfunc void *bpf_rdonly_cast(void *obj__ign, u32 btf_id__k) +__bpf_kfunc void *bpf_rdonly_cast(const void *obj__ign, u32 btf_id__k) { - return obj__ign; + return (void *)obj__ign; } __bpf_kfunc void bpf_rcu_read_lock(void) @@ -2547,7 +2547,7 @@ __bpf_kfunc void bpf_throw(u64 cookie) __bpf_kfunc_end_defs(); -BTF_SET8_START(generic_btf_ids) +BTF_KFUNCS_START(generic_btf_ids) #ifdef CONFIG_KEXEC_CORE BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE) #endif @@ -2576,7 +2576,7 @@ BTF_ID_FLAGS(func, bpf_task_get_cgroup1, KF_ACQUIRE | KF_RCU | KF_RET_NULL) #endif BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_throw) -BTF_SET8_END(generic_btf_ids) +BTF_KFUNCS_END(generic_btf_ids) static const struct btf_kfunc_id_set generic_kfunc_set = { .owner = THIS_MODULE, @@ -2592,7 +2592,7 @@ BTF_ID(struct, cgroup) BTF_ID(func, bpf_cgroup_release_dtor) #endif -BTF_SET8_START(common_btf_ids) +BTF_KFUNCS_START(common_btf_ids) BTF_ID_FLAGS(func, bpf_cast_to_kern_ctx) BTF_ID_FLAGS(func, bpf_rdonly_cast) BTF_ID_FLAGS(func, bpf_rcu_read_lock) @@ -2621,7 +2621,7 @@ BTF_ID_FLAGS(func, bpf_dynptr_is_null) BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly) BTF_ID_FLAGS(func, bpf_dynptr_size) BTF_ID_FLAGS(func, bpf_dynptr_clone) -BTF_SET8_END(common_btf_ids) +BTF_KFUNCS_END(common_btf_ids) static const struct btf_kfunc_id_set common_kfunc_set = { .owner = THIS_MODULE, diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c index 594a234f122b..63c34e7b0715 100644 --- a/kernel/bpf/log.c +++ b/kernel/bpf/log.c @@ -9,6 +9,7 @@ #include <linux/bpf.h> #include <linux/bpf_verifier.h> #include <linux/math64.h> +#include <linux/string.h> #define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args) @@ -333,7 +334,8 @@ find_linfo(const struct bpf_verifier_env *env, u32 insn_off) { const struct bpf_line_info *linfo; const struct bpf_prog *prog; - u32 i, nr_linfo; + u32 nr_linfo; + int l, r, m; prog = env->prog; nr_linfo = prog->aux->nr_linfo; @@ -342,11 +344,30 @@ find_linfo(const struct bpf_verifier_env *env, u32 insn_off) return NULL; linfo = prog->aux->linfo; - for (i = 1; i < nr_linfo; i++) - if (insn_off < linfo[i].insn_off) - break; + /* Loop invariant: linfo[l].insn_off <= insns_off. + * linfo[0].insn_off == 0 which always satisfies above condition. + * Binary search is searching for rightmost linfo entry that satisfies + * the above invariant, giving us the desired record that covers given + * instruction offset. + */ + l = 0; + r = nr_linfo - 1; + while (l < r) { + /* (r - l + 1) / 2 means we break a tie to the right, so if: + * l=1, r=2, linfo[l].insn_off <= insn_off, linfo[r].insn_off > insn_off, + * then m=2, we see that linfo[m].insn_off > insn_off, and so + * r becomes 1 and we exit the loop with correct l==1. + * If the tie was broken to the left, m=1 would end us up in + * an endless loop where l and m stay at 1 and r stays at 2. + */ + m = l + (r - l + 1) / 2; + if (linfo[m].insn_off <= insn_off) + l = m; + else + r = m - 1; + } - return &linfo[i - 1]; + return &linfo[l]; } static const char *ltrim(const char *s) @@ -361,13 +382,28 @@ __printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env, u32 insn_off, const char *prefix_fmt, ...) { - const struct bpf_line_info *linfo; + const struct bpf_line_info *linfo, *prev_linfo; + const struct btf *btf; + const char *s, *fname; if (!bpf_verifier_log_needed(&env->log)) return; + prev_linfo = env->prev_linfo; linfo = find_linfo(env, insn_off); - if (!linfo || linfo == env->prev_linfo) + if (!linfo || linfo == prev_linfo) + return; + + /* It often happens that two separate linfo records point to the same + * source code line, but have differing column numbers. Given verifier + * log doesn't emit column information, from user perspective we just + * end up emitting the same source code line twice unnecessarily. + * So instead check that previous and current linfo record point to + * the same file (file_name_offs match) and the same line number, and + * avoid emitting duplicated source code line in such case. + */ + if (prev_linfo && linfo->file_name_off == prev_linfo->file_name_off && + BPF_LINE_INFO_LINE_NUM(linfo->line_col) == BPF_LINE_INFO_LINE_NUM(prev_linfo->line_col)) return; if (prefix_fmt) { @@ -378,9 +414,15 @@ __printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env, va_end(args); } - verbose(env, "%s\n", - ltrim(btf_name_by_offset(env->prog->aux->btf, - linfo->line_off))); + btf = env->prog->aux->btf; + s = ltrim(btf_name_by_offset(btf, linfo->line_off)); + verbose(env, "%s", s); /* source code line */ + + s = btf_name_by_offset(btf, linfo->file_name_off); + /* leave only file name */ + fname = strrchr(s, '/'); + fname = fname ? fname + 1 : s; + verbose(env, " @ %s:%u\n", fname, BPF_LINE_INFO_LINE_NUM(linfo->line_col)); env->prev_linfo = linfo; } diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index b32be680da6c..050fe1ebf0f7 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -164,13 +164,13 @@ static inline int extract_bit(const u8 *data, size_t index) */ static size_t longest_prefix_match(const struct lpm_trie *trie, const struct lpm_trie_node *node, - const struct bpf_lpm_trie_key *key) + const struct bpf_lpm_trie_key_u8 *key) { u32 limit = min(node->prefixlen, key->prefixlen); u32 prefixlen = 0, i = 0; BUILD_BUG_ON(offsetof(struct lpm_trie_node, data) % sizeof(u32)); - BUILD_BUG_ON(offsetof(struct bpf_lpm_trie_key, data) % sizeof(u32)); + BUILD_BUG_ON(offsetof(struct bpf_lpm_trie_key_u8, data) % sizeof(u32)); #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && defined(CONFIG_64BIT) @@ -229,7 +229,7 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node *node, *found = NULL; - struct bpf_lpm_trie_key *key = _key; + struct bpf_lpm_trie_key_u8 *key = _key; if (key->prefixlen > trie->max_prefixlen) return NULL; @@ -309,7 +309,7 @@ static long trie_update_elem(struct bpf_map *map, struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node *node, *im_node = NULL, *new_node = NULL; struct lpm_trie_node __rcu **slot; - struct bpf_lpm_trie_key *key = _key; + struct bpf_lpm_trie_key_u8 *key = _key; unsigned long irq_flags; unsigned int next_bit; size_t matchlen = 0; @@ -437,7 +437,7 @@ out: static long trie_delete_elem(struct bpf_map *map, void *_key) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); - struct bpf_lpm_trie_key *key = _key; + struct bpf_lpm_trie_key_u8 *key = _key; struct lpm_trie_node __rcu **trim, **trim2; struct lpm_trie_node *node, *parent; unsigned long irq_flags; @@ -536,7 +536,7 @@ out: sizeof(struct lpm_trie_node)) #define LPM_VAL_SIZE_MIN 1 -#define LPM_KEY_SIZE(X) (sizeof(struct bpf_lpm_trie_key) + (X)) +#define LPM_KEY_SIZE(X) (sizeof(struct bpf_lpm_trie_key_u8) + (X)) #define LPM_KEY_SIZE_MAX LPM_KEY_SIZE(LPM_DATA_SIZE_MAX) #define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN) @@ -565,7 +565,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) /* copy mandatory map attributes */ bpf_map_init_from_attr(&trie->map, attr); trie->data_size = attr->key_size - - offsetof(struct bpf_lpm_trie_key, data); + offsetof(struct bpf_lpm_trie_key_u8, data); trie->max_prefixlen = trie->data_size * 8; spin_lock_init(&trie->lock); @@ -616,7 +616,7 @@ static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key) { struct lpm_trie_node *node, *next_node = NULL, *parent, *search_root; struct lpm_trie *trie = container_of(map, struct lpm_trie, map); - struct bpf_lpm_trie_key *key = _key, *next_key = _next_key; + struct bpf_lpm_trie_key_u8 *key = _key, *next_key = _next_key; struct lpm_trie_node **node_stack = NULL; int err = 0, stack_ptr = -1; unsigned int next_bit; @@ -703,7 +703,7 @@ find_leftmost: } do_copy: next_key->prefixlen = next_node->prefixlen; - memcpy((void *)next_key + offsetof(struct bpf_lpm_trie_key, data), + memcpy((void *)next_key + offsetof(struct bpf_lpm_trie_key_u8, data), next_node->data, trie->data_size); free_stack: kfree(node_stack); @@ -715,7 +715,7 @@ static int trie_check_btf(const struct bpf_map *map, const struct btf_type *key_type, const struct btf_type *value_type) { - /* Keys must have struct bpf_lpm_trie_key embedded. */ + /* Keys must have struct bpf_lpm_trie_key_u8 embedded. */ return BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ? -EINVAL : 0; } diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c index 6abd7c5df4b3..9575314f40a6 100644 --- a/kernel/bpf/map_iter.c +++ b/kernel/bpf/map_iter.c @@ -213,9 +213,9 @@ __bpf_kfunc s64 bpf_map_sum_elem_count(const struct bpf_map *map) __bpf_kfunc_end_defs(); -BTF_SET8_START(bpf_map_iter_kfunc_ids) +BTF_KFUNCS_START(bpf_map_iter_kfunc_ids) BTF_ID_FLAGS(func, bpf_map_sum_elem_count, KF_TRUSTED_ARGS) -BTF_SET8_END(bpf_map_iter_kfunc_ids) +BTF_KFUNCS_END(bpf_map_iter_kfunc_ids) static const struct btf_kfunc_id_set bpf_map_iter_kfunc_set = { .owner = THIS_MODULE, diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c index 0bca93b60c43..d6ccf8d00eab 100644 --- a/kernel/bpf/token.c +++ b/kernel/bpf/token.c @@ -72,28 +72,28 @@ static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) u64 mask; BUILD_BUG_ON(__MAX_BPF_CMD >= 64); - mask = (1ULL << __MAX_BPF_CMD) - 1; + mask = BIT_ULL(__MAX_BPF_CMD) - 1; if ((token->allowed_cmds & mask) == mask) seq_printf(m, "allowed_cmds:\tany\n"); else seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds); BUILD_BUG_ON(__MAX_BPF_MAP_TYPE >= 64); - mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1; + mask = BIT_ULL(__MAX_BPF_MAP_TYPE) - 1; if ((token->allowed_maps & mask) == mask) seq_printf(m, "allowed_maps:\tany\n"); else seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps); BUILD_BUG_ON(__MAX_BPF_PROG_TYPE >= 64); - mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1; + mask = BIT_ULL(__MAX_BPF_PROG_TYPE) - 1; if ((token->allowed_progs & mask) == mask) seq_printf(m, "allowed_progs:\tany\n"); else seq_printf(m, "allowed_progs:\t0x%llx\n", token->allowed_progs); BUILD_BUG_ON(__MAX_BPF_ATTACH_TYPE >= 64); - mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1; + mask = BIT_ULL(__MAX_BPF_ATTACH_TYPE) - 1; if ((token->allowed_attachs & mask) == mask) seq_printf(m, "allowed_attachs:\tany\n"); else @@ -253,7 +253,7 @@ bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd) { if (!token) return false; - if (!(token->allowed_cmds & (1ULL << cmd))) + if (!(token->allowed_cmds & BIT_ULL(cmd))) return false; return security_bpf_token_cmd(token, cmd) == 0; } @@ -263,7 +263,7 @@ bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type t if (!token || type >= __MAX_BPF_MAP_TYPE) return false; - return token->allowed_maps & (1ULL << type); + return token->allowed_maps & BIT_ULL(type); } bool bpf_token_allow_prog_type(const struct bpf_token *token, @@ -273,6 +273,6 @@ bool bpf_token_allow_prog_type(const struct bpf_token *token, if (!token || prog_type >= __MAX_BPF_PROG_TYPE || attach_type >= __MAX_BPF_ATTACH_TYPE) return false; - return (token->allowed_progs & (1ULL << prog_type)) && - (token->allowed_attachs & (1ULL << attach_type)); + return (token->allowed_progs & BIT_ULL(prog_type)) && + (token->allowed_attachs & BIT_ULL(attach_type)); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 174be4d0e21a..4dd84e13bbfe 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -528,6 +528,11 @@ static bool is_sync_callback_calling_insn(struct bpf_insn *insn) (bpf_pseudo_kfunc_call(insn) && is_sync_callback_calling_kfunc(insn->imm)); } +static bool is_async_callback_calling_insn(struct bpf_insn *insn) +{ + return bpf_helper_call(insn) && is_async_callback_calling_function(insn->imm); +} + static bool is_storage_get_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_sk_storage_get || @@ -1155,6 +1160,12 @@ static bool is_spilled_scalar_reg(const struct bpf_stack_state *stack) stack->spilled_ptr.type == SCALAR_VALUE; } +static bool is_spilled_scalar_reg64(const struct bpf_stack_state *stack) +{ + return stack->slot_type[0] == STACK_SPILL && + stack->spilled_ptr.type == SCALAR_VALUE; +} + /* Mark stack slot as STACK_MISC, unless it is already STACK_INVALID, in which * case they are equivalent, or it's STACK_ZERO, in which case we preserve * more precise STACK_ZERO. @@ -2264,8 +2275,7 @@ static void __reg_assign_32_into_64(struct bpf_reg_state *reg) } /* Mark a register as having a completely unknown (scalar) value. */ -static void __mark_reg_unknown(const struct bpf_verifier_env *env, - struct bpf_reg_state *reg) +static void __mark_reg_unknown_imprecise(struct bpf_reg_state *reg) { /* * Clear type, off, and union(map_ptr, range) and @@ -2277,10 +2287,20 @@ static void __mark_reg_unknown(const struct bpf_verifier_env *env, reg->ref_obj_id = 0; reg->var_off = tnum_unknown; reg->frameno = 0; - reg->precise = !env->bpf_capable; + reg->precise = false; __mark_reg_unbounded(reg); } +/* Mark a register as having a completely unknown (scalar) value, + * initialize .precise as true when not bpf capable. + */ +static void __mark_reg_unknown(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg) +{ + __mark_reg_unknown_imprecise(reg); + reg->precise = !env->bpf_capable; +} + static void mark_reg_unknown(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno) { @@ -4380,20 +4400,6 @@ static u64 reg_const_value(struct bpf_reg_state *reg, bool subreg32) return subreg32 ? tnum_subreg(reg->var_off).value : reg->var_off.value; } -static bool __is_scalar_unbounded(struct bpf_reg_state *reg) -{ - return tnum_is_unknown(reg->var_off) && - reg->smin_value == S64_MIN && reg->smax_value == S64_MAX && - reg->umin_value == 0 && reg->umax_value == U64_MAX && - reg->s32_min_value == S32_MIN && reg->s32_max_value == S32_MAX && - reg->u32_min_value == 0 && reg->u32_max_value == U32_MAX; -} - -static bool register_is_bounded(struct bpf_reg_state *reg) -{ - return reg->type == SCALAR_VALUE && !__is_scalar_unbounded(reg); -} - static bool __is_pointer_value(bool allow_ptr_leaks, const struct bpf_reg_state *reg) { @@ -4504,7 +4510,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, return err; mark_stack_slot_scratched(env, spi); - if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) && env->bpf_capable) { + if (reg && !(off % BPF_REG_SIZE) && reg->type == SCALAR_VALUE && env->bpf_capable) { bool reg_value_fits; reg_value_fits = get_reg_width(reg) <= BITS_PER_BYTE * size; @@ -4792,7 +4798,8 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, if (dst_regno < 0) return 0; - if (!(off % BPF_REG_SIZE) && size == spill_size) { + if (size <= spill_size && + bpf_stack_narrow_access_ok(off, size, spill_size)) { /* The earlier check_reg_arg() has decided the * subreg_def for this insn. Save it first. */ @@ -4800,6 +4807,12 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, copy_register_state(&state->regs[dst_regno], reg); state->regs[dst_regno].subreg_def = subreg_def; + + /* Break the relation on a narrowing fill. + * coerce_reg_to_size will adjust the boundaries. + */ + if (get_reg_width(reg) > size * BITS_PER_BYTE) + state->regs[dst_regno].id = 0; } else { int spill_cnt = 0, zero_cnt = 0; @@ -5247,6 +5260,11 @@ bad_type: return -EINVAL; } +static bool in_sleepable(struct bpf_verifier_env *env) +{ + return env->prog->aux->sleepable; +} + /* The non-sleepable programs and sleepable programs with explicit bpf_rcu_read_lock() * can dereference RCU protected pointers and result is PTR_TRUSTED. */ @@ -5254,7 +5272,7 @@ static bool in_rcu_cs(struct bpf_verifier_env *env) { return env->cur_state->active_rcu_lock || env->cur_state->active_lock.ptr || - !env->prog->aux->sleepable; + !in_sleepable(env); } /* Once GCC supports btf_type_tag the following mechanism will be replaced with tag check */ @@ -5806,6 +5824,17 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, strict); } +static int round_up_stack_depth(struct bpf_verifier_env *env, int stack_depth) +{ + if (env->prog->jit_requested) + return round_up(stack_depth, 16); + + /* round up to 32-bytes, since this is granularity + * of interpreter stack size + */ + return round_up(max_t(u32, stack_depth, 1), 32); +} + /* starting from main bpf function walk all instructions of the function * and recursively walk all callees that given function can call. * Ignore jump and exit insns. @@ -5849,10 +5878,7 @@ process_func: depth); return -EACCES; } - /* round up to 32-bytes, since this is granularity - * of interpreter stack size - */ - depth += round_up(max_t(u32, subprog[idx].stack_depth, 1), 32); + depth += round_up_stack_depth(env, subprog[idx].stack_depth); if (depth > MAX_BPF_STACK) { verbose(env, "combined stack size of %d calls is %d. Too large\n", frame + 1, depth); @@ -5946,7 +5972,7 @@ continue_func: */ if (frame == 0) return 0; - depth -= round_up(max_t(u32, subprog[idx].stack_depth, 1), 32); + depth -= round_up_stack_depth(env, subprog[idx].stack_depth); frame--; i = ret_insn[frame]; idx = ret_prog[frame]; @@ -6077,10 +6103,10 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) * values are also truncated so we push 64-bit bounds into * 32-bit bounds. Above were truncated < 32-bits already. */ - if (size < 4) { + if (size < 4) __mark_reg32_unbounded(reg); - reg_bounds_sync(reg); - } + + reg_bounds_sync(reg); } static void set_sext64_default_val(struct bpf_reg_state *reg, int size) @@ -8236,6 +8262,7 @@ found: switch ((int)reg->type) { case PTR_TO_BTF_ID: case PTR_TO_BTF_ID | PTR_TRUSTED: + case PTR_TO_BTF_ID | PTR_TRUSTED | PTR_MAYBE_NULL: case PTR_TO_BTF_ID | MEM_RCU: case PTR_TO_BTF_ID | PTR_MAYBE_NULL: case PTR_TO_BTF_ID | PTR_MAYBE_NULL | MEM_RCU: @@ -9338,6 +9365,18 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog, ret = process_dynptr_func(env, regno, -1, arg->arg_type, 0); if (ret) return ret; + } else if (base_type(arg->arg_type) == ARG_PTR_TO_BTF_ID) { + struct bpf_call_arg_meta meta; + int err; + + if (register_is_null(reg) && type_may_be_null(arg->arg_type)) + continue; + + memset(&meta, 0, sizeof(meta)); /* leave func_id as zero */ + err = check_reg_type(env, regno, arg->arg_type, &arg->btf_id, &meta); + err = err ?: check_func_arg_reg_off(env, reg, regno, arg->arg_type); + if (err) + return err; } else { bpf_log(log, "verifier bug: unrecognized arg#%d type %d\n", i, arg->arg_type); @@ -9413,9 +9452,7 @@ static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *ins return -EFAULT; } - if (insn->code == (BPF_JMP | BPF_CALL) && - insn->src_reg == 0 && - insn->imm == BPF_FUNC_timer_set_callback) { + if (is_async_callback_calling_insn(insn)) { struct bpf_verifier_state *async_cb; /* there is no real recursion here. timer callbacks are async */ @@ -9474,6 +9511,13 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, if (subprog_is_global(env, subprog)) { const char *sub_name = subprog_name(env, subprog); + /* Only global subprogs cannot be called with a lock held. */ + if (env->cur_state->active_lock.ptr) { + verbose(env, "global function calls are not allowed while holding a lock,\n" + "use static function instead\n"); + return -EINVAL; + } + if (err) { verbose(env, "Caller passes invalid args into func#%d ('%s')\n", subprog, sub_name); @@ -10130,7 +10174,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EINVAL; } - if (!env->prog->aux->sleepable && fn->might_sleep) { + if (!in_sleepable(env) && fn->might_sleep) { verbose(env, "helper call might sleep in a non-sleepable prog\n"); return -EINVAL; } @@ -10160,7 +10204,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EINVAL; } - if (env->prog->aux->sleepable && is_storage_get_function(func_id)) + if (in_sleepable(env) && is_storage_get_function(func_id)) env->insn_aux_data[insn_idx].storage_get_func_atomic = true; } @@ -10656,24 +10700,6 @@ static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta) return meta->kfunc_flags & KF_RCU_PROTECTED; } -static bool __kfunc_param_match_suffix(const struct btf *btf, - const struct btf_param *arg, - const char *suffix) -{ - int suffix_len = strlen(suffix), len; - const char *param_name; - - /* In the future, this can be ported to use BTF tagging */ - param_name = btf_name_by_offset(btf, arg->name_off); - if (str_is_empty(param_name)) - return false; - len = strlen(param_name); - if (len < suffix_len) - return false; - param_name += len - suffix_len; - return !strncmp(param_name, suffix, suffix_len); -} - static bool is_kfunc_arg_mem_size(const struct btf *btf, const struct btf_param *arg, const struct bpf_reg_state *reg) @@ -10684,7 +10710,7 @@ static bool is_kfunc_arg_mem_size(const struct btf *btf, if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) return false; - return __kfunc_param_match_suffix(btf, arg, "__sz"); + return btf_param_match_suffix(btf, arg, "__sz"); } static bool is_kfunc_arg_const_mem_size(const struct btf *btf, @@ -10697,47 +10723,47 @@ static bool is_kfunc_arg_const_mem_size(const struct btf *btf, if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) return false; - return __kfunc_param_match_suffix(btf, arg, "__szk"); + return btf_param_match_suffix(btf, arg, "__szk"); } static bool is_kfunc_arg_optional(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__opt"); + return btf_param_match_suffix(btf, arg, "__opt"); } static bool is_kfunc_arg_constant(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__k"); + return btf_param_match_suffix(btf, arg, "__k"); } static bool is_kfunc_arg_ignore(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__ign"); + return btf_param_match_suffix(btf, arg, "__ign"); } static bool is_kfunc_arg_alloc_obj(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__alloc"); + return btf_param_match_suffix(btf, arg, "__alloc"); } static bool is_kfunc_arg_uninit(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__uninit"); + return btf_param_match_suffix(btf, arg, "__uninit"); } static bool is_kfunc_arg_refcounted_kptr(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__refcounted_kptr"); + return btf_param_match_suffix(btf, arg, "__refcounted_kptr"); } static bool is_kfunc_arg_nullable(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__nullable"); + return btf_param_match_suffix(btf, arg, "__nullable"); } static bool is_kfunc_arg_const_str(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__str"); + return btf_param_match_suffix(btf, arg, "__str"); } static bool is_kfunc_arg_scalar_with_name(const struct btf *btf, @@ -11007,7 +11033,7 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, * type to our caller. When a set of conditions hold in the BTF type of * arguments, we resolve it to a known kfunc_ptr_arg_type. */ - if (btf_get_prog_ctx_type(&env->log, meta->btf, t, resolve_prog_type(env->prog), argno)) + if (btf_is_prog_ctx_type(&env->log, meta->btf, t, resolve_prog_type(env->prog), argno)) return KF_ARG_PTR_TO_CTX; if (is_kfunc_arg_alloc_obj(meta->btf, &args[argno])) @@ -11519,7 +11545,7 @@ static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env) return true; fallthrough; default: - return env->prog->aux->sleepable; + return in_sleepable(env); } } @@ -12040,7 +12066,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, } sleepable = is_kfunc_sleepable(&meta); - if (sleepable && !env->prog->aux->sleepable) { + if (sleepable && !in_sleepable(env)) { verbose(env, "program must be sleepable to call sleepable kfunc %s\n", func_name); return -EACCES; } @@ -15567,7 +15593,7 @@ static int visit_insn(int t, struct bpf_verifier_env *env) return DONE_EXPLORING; case BPF_CALL: - if (insn->src_reg == 0 && insn->imm == BPF_FUNC_timer_set_callback) + if (is_async_callback_calling_insn(insn)) /* Mark this call insn as a prune point to trigger * is_state_visited() check before call itself is * processed by __check_func_call(). Otherwise new @@ -16483,6 +16509,43 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, } } +static struct bpf_reg_state unbound_reg; + +static __init int unbound_reg_init(void) +{ + __mark_reg_unknown_imprecise(&unbound_reg); + unbound_reg.live |= REG_LIVE_READ; + return 0; +} +late_initcall(unbound_reg_init); + +static bool is_stack_all_misc(struct bpf_verifier_env *env, + struct bpf_stack_state *stack) +{ + u32 i; + + for (i = 0; i < ARRAY_SIZE(stack->slot_type); ++i) { + if ((stack->slot_type[i] == STACK_MISC) || + (stack->slot_type[i] == STACK_INVALID && env->allow_uninit_stack)) + continue; + return false; + } + + return true; +} + +static struct bpf_reg_state *scalar_reg_for_stack(struct bpf_verifier_env *env, + struct bpf_stack_state *stack) +{ + if (is_spilled_scalar_reg64(stack)) + return &stack->spilled_ptr; + + if (is_stack_all_misc(env, stack)) + return &unbound_reg; + + return NULL; +} + static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, struct bpf_func_state *cur, struct bpf_idmap *idmap, bool exact) { @@ -16521,6 +16584,20 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, if (i >= cur->allocated_stack) return false; + /* 64-bit scalar spill vs all slots MISC and vice versa. + * Load from all slots MISC produces unbound scalar. + * Construct a fake register for such stack and call + * regsafe() to ensure scalar ids are compared. + */ + old_reg = scalar_reg_for_stack(env, &old->stack[spi]); + cur_reg = scalar_reg_for_stack(env, &cur->stack[spi]); + if (old_reg && cur_reg) { + if (!regsafe(env, old_reg, cur_reg, idmap, exact)) + return false; + i += BPF_REG_SIZE - 1; + continue; + } + /* if old state was safe with misc data in the stack * it will be safe with zero-initialized stack. * The opposite is not true @@ -17574,7 +17651,6 @@ static int do_check(struct bpf_verifier_env *env) if (env->cur_state->active_lock.ptr) { if ((insn->src_reg == BPF_REG_0 && insn->imm != BPF_FUNC_spin_unlock) || - (insn->src_reg == BPF_PSEUDO_CALL) || (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && (insn->off != 0 || !is_bpf_graph_api_kfunc(insn->imm)))) { verbose(env, "function calls are not allowed while holding a lock\n"); @@ -17622,14 +17698,12 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } process_bpf_exit_full: - if (env->cur_state->active_lock.ptr && - !in_rbtree_lock_required_cb(env)) { + if (env->cur_state->active_lock.ptr && !env->cur_state->curframe) { verbose(env, "bpf_spin_unlock is missing\n"); return -EINVAL; } - if (env->cur_state->active_rcu_lock && - !in_rbtree_lock_required_cb(env)) { + if (env->cur_state->active_rcu_lock && !env->cur_state->curframe) { verbose(env, "bpf_rcu_read_unlock is missing\n"); return -EINVAL; } @@ -17958,6 +18032,8 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_SK_STORAGE: case BPF_MAP_TYPE_TASK_STORAGE: case BPF_MAP_TYPE_CGRP_STORAGE: + case BPF_MAP_TYPE_QUEUE: + case BPF_MAP_TYPE_STACK: break; default: verbose(env, @@ -19603,7 +19679,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) } if (is_storage_get_function(insn->imm)) { - if (!env->prog->aux->sleepable || + if (!in_sleepable(env) || env->insn_aux_data[i + delta].storage_get_func_atomic) insn_buf[0] = BPF_MOV64_IMM(BPF_REG_5, (__force __s32)GFP_ATOMIC); else @@ -20139,6 +20215,18 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) mark_reg_known_zero(env, regs, i); reg->mem_size = arg->mem_size; reg->id = ++env->id_gen; + } else if (base_type(arg->arg_type) == ARG_PTR_TO_BTF_ID) { + reg->type = PTR_TO_BTF_ID; + if (arg->arg_type & PTR_MAYBE_NULL) + reg->type |= PTR_MAYBE_NULL; + if (arg->arg_type & PTR_UNTRUSTED) + reg->type |= PTR_UNTRUSTED; + if (arg->arg_type & PTR_TRUSTED) + reg->type |= PTR_TRUSTED; + mark_reg_known_zero(env, regs, i); + reg->btf = bpf_get_btf_vmlinux(); /* can't fail at this point */ + reg->btf_id = arg->btf_id; + reg->id = ++env->id_gen; } else { WARN_ONCE(1, "BUG: unhandled arg#%d type %d\n", i - BPF_REG_1, arg->arg_type); @@ -20351,6 +20439,12 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } } + /* btf_ctx_access() used this to provide argument type info */ + prog->aux->ctx_arg_info = + st_ops_desc->arg_info[member_idx].info; + prog->aux->ctx_arg_info_size = + st_ops_desc->arg_info[member_idx].cnt; + prog->aux->attach_func_proto = func_proto; prog->aux->attach_func_name = mname; env->ops = st_ops->verifier_ops; |