diff options
26 files changed, 3931 insertions, 567 deletions
diff --git a/Documentation/bpf/kfuncs.rst b/Documentation/bpf/kfuncs.rst index 0f858156371d..3b1501c3b6cd 100644 --- a/Documentation/bpf/kfuncs.rst +++ b/Documentation/bpf/kfuncs.rst @@ -72,6 +72,30 @@ argument as its size. By default, without __sz annotation, the size of the type of the pointer is used. Without __sz annotation, a kfunc cannot accept a void pointer. +2.2.2 __k Annotation +-------------------- + +This annotation is only understood for scalar arguments, where it indicates that +the verifier must check the scalar argument to be a known constant, which does +not indicate a size parameter, and the value of the constant is relevant to the +safety of the program. + +An example is given below:: + + void *bpf_obj_new(u32 local_type_id__k, ...) + { + ... + } + +Here, bpf_obj_new uses local_type_id argument to find out the size of that type +ID in program's BTF and return a sized pointer to it. Each type ID will have a +distinct size, hence it is crucial to treat each such call as distinct when +values don't match during verifier state pruning checks. + +Hence, whenever a constant scalar argument is accepted by a kfunc which is not a +size parameter, and the value of the constant matters for program safety, __k +suffix should be used. + .. _BPF_kfunc_nodef: 2.3 Using an existing kernel function diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e60a5c052473..8b32376ce746 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -54,6 +54,8 @@ struct cgroup; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; extern struct kobject *btf_kobj; +extern struct bpf_mem_alloc bpf_global_ma; +extern bool bpf_global_ma_set; typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64); typedef int (*bpf_iter_init_seq_priv_t)(void *private_data, @@ -177,6 +179,7 @@ enum btf_field_type { BPF_KPTR_REF = (1 << 3), BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF, BPF_LIST_HEAD = (1 << 4), + BPF_LIST_NODE = (1 << 5), }; struct btf_field_kptr { @@ -190,6 +193,7 @@ struct btf_field_list_head { struct btf *btf; u32 value_btf_id; u32 node_offset; + struct btf_record *value_rec; }; struct btf_field { @@ -277,6 +281,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type) return "kptr"; case BPF_LIST_HEAD: return "bpf_list_head"; + case BPF_LIST_NODE: + return "bpf_list_node"; default: WARN_ON_ONCE(1); return "unknown"; @@ -295,6 +301,8 @@ static inline u32 btf_field_type_size(enum btf_field_type type) return sizeof(u64); case BPF_LIST_HEAD: return sizeof(struct bpf_list_head); + case BPF_LIST_NODE: + return sizeof(struct bpf_list_node); default: WARN_ON_ONCE(1); return 0; @@ -313,6 +321,8 @@ static inline u32 btf_field_type_align(enum btf_field_type type) return __alignof__(u64); case BPF_LIST_HEAD: return __alignof__(struct bpf_list_head); + case BPF_LIST_NODE: + return __alignof__(struct bpf_list_node); default: WARN_ON_ONCE(1); return 0; @@ -326,16 +336,19 @@ static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_f return rec->field_mask & type; } -static inline void check_and_init_map_value(struct bpf_map *map, void *dst) +static inline void bpf_obj_init(const struct btf_field_offs *foffs, void *obj) { - if (!IS_ERR_OR_NULL(map->record)) { - struct btf_field *fields = map->record->fields; - u32 cnt = map->record->cnt; - int i; + int i; - for (i = 0; i < cnt; i++) - memset(dst + fields[i].offset, 0, btf_field_type_size(fields[i].type)); - } + if (!foffs) + return; + for (i = 0; i < foffs->cnt; i++) + memset(obj + foffs->field_off[i], 0, foffs->field_sz[i]); +} + +static inline void check_and_init_map_value(struct bpf_map *map, void *dst) +{ + bpf_obj_init(map->field_offs, dst); } /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and @@ -525,6 +538,11 @@ enum bpf_type_flag { /* Size is known at compile time. */ MEM_FIXED_SIZE = BIT(10 + BPF_BASE_TYPE_BITS), + /* MEM is of an allocated object of type in program BTF. This is used to + * tag PTR_TO_BTF_ID allocated using bpf_obj_new. + */ + MEM_ALLOC = BIT(11 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; @@ -2096,22 +2114,11 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, const char *func_name, struct btf_func_model *m); -struct bpf_kfunc_arg_meta { - u64 r0_size; - bool r0_rdonly; - int ref_obj_id; - u32 flags; -}; - struct bpf_reg_state; int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs); int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs); -int btf_check_kfunc_arg_match(struct bpf_verifier_env *env, - const struct btf *btf, u32 func_id, - struct bpf_reg_state *regs, - struct bpf_kfunc_arg_meta *meta); int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *reg); int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, @@ -2792,4 +2799,10 @@ struct bpf_key { bool has_ref; }; #endif /* CONFIG_KEYS */ + +static inline bool type_is_alloc(u32 type) +{ + return type & MEM_ALLOC; +} + #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 1a32baa78ce2..23f30c685f28 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -223,6 +223,11 @@ struct bpf_reference_state { * exiting a callback function. */ int callback_ref; + /* Mark the reference state to release the registers sharing the same id + * on bpf_spin_unlock (for nodes that we will lose ownership to but are + * safe to access inside the critical section). + */ + bool release_on_unlock; }; /* state of the program: @@ -323,7 +328,21 @@ struct bpf_verifier_state { u32 branches; u32 insn_idx; u32 curframe; - u32 active_spin_lock; + /* For every reg representing a map value or allocated object pointer, + * we consider the tuple of (ptr, id) for them to be unique in verifier + * context and conside them to not alias each other for the purposes of + * tracking lock state. + */ + struct { + /* This can either be reg->map_ptr or reg->btf. If ptr is NULL, + * there's no active lock held, and other fields have no + * meaning. If non-NULL, it indicates that a lock is held and + * id member has the reg->id of the register which can be >= 0. + */ + void *ptr; + /* This will be reg->id */ + u32 id; + } active_lock; bool speculative; /* first and last insn idx of this verifier state */ @@ -419,6 +438,8 @@ struct bpf_insn_aux_data { */ struct bpf_loop_inline_state loop_inline_state; }; + u64 obj_new_size; /* remember the size of type passed to bpf_obj_new to rewrite R1 */ + struct btf_struct_meta *kptr_struct_meta; u64 map_key_state; /* constant (32 bit) key tracking for maps */ int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ u32 seen; /* this insn was processed by the verifier at env->pass_cnt */ @@ -589,8 +610,6 @@ int check_ptr_off_reg(struct bpf_verifier_env *env, int check_func_arg_reg_off(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, enum bpf_arg_type arg_type); -int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, - u32 regno); int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size); bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, diff --git a/include/linux/btf.h b/include/linux/btf.h index d80345fa566b..d5b26380a60f 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -6,6 +6,8 @@ #include <linux/types.h> #include <linux/bpfptr.h> +#include <linux/bsearch.h> +#include <linux/btf_ids.h> #include <uapi/linux/btf.h> #include <uapi/linux/bpf.h> @@ -78,6 +80,17 @@ struct btf_id_dtor_kfunc { u32 kfunc_btf_id; }; +struct btf_struct_meta { + u32 btf_id; + struct btf_record *record; + struct btf_field_offs *field_offs; +}; + +struct btf_struct_metas { + u32 cnt; + struct btf_struct_meta types[]; +}; + typedef void (*btf_dtor_kfunc_t)(void *); extern const struct file_operations btf_fops; @@ -165,6 +178,7 @@ int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); int btf_find_timer(const struct btf *btf, const struct btf_type *t); struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t, u32 field_mask, u32 value_size); +int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec); struct btf_field_offs *btf_parse_field_offs(struct btf_record *rec); bool btf_type_is_void(const struct btf_type *t); s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind); @@ -324,6 +338,16 @@ static inline bool btf_type_is_struct(const struct btf_type *t) return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; } +static inline bool __btf_type_is_struct(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT; +} + +static inline bool btf_type_is_array(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY; +} + static inline u16 btf_type_vlen(const struct btf_type *t) { return BTF_INFO_VLEN(t->info); @@ -408,9 +432,27 @@ static inline struct btf_param *btf_params(const struct btf_type *t) return (struct btf_param *)(t + 1); } -#ifdef CONFIG_BPF_SYSCALL +static inline int btf_id_cmp_func(const void *a, const void *b) +{ + const int *pa = a, *pb = b; + + return *pa - *pb; +} + +static inline bool btf_id_set_contains(const struct btf_id_set *set, u32 id) +{ + return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL; +} + +static inline void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id) +{ + return bsearch(&id, set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func); +} + struct bpf_prog; +struct bpf_verifier_log; +#ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); struct btf *btf_parse_vmlinux(void); @@ -423,6 +465,13 @@ int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id); int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt, struct module *owner); +struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id); +const struct btf_member * +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_types_are_same(const struct btf *btf1, u32 id1, + const struct btf *btf2, u32 id2); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) @@ -454,6 +503,22 @@ static inline int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dt { return 0; } +static inline struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id) +{ + return NULL; +} +static inline const struct btf_member * +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) +{ + return NULL; +} +static inline bool btf_types_are_same(const struct btf *btf1, u32 id1, + const struct btf *btf2, u32 id2) +{ + return false; +} #endif static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type *t) diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 672eb17ac421..484706959556 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -430,7 +430,6 @@ static void array_map_free(struct bpf_map *map) for (i = 0; i < array->map.max_entries; i++) bpf_obj_free_fields(map->record, array_map_elem_ptr(array, i)); } - bpf_map_free_record(map); } if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 875355ff3718..f7d5fab61535 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -237,6 +237,7 @@ struct btf { struct rcu_head rcu; struct btf_kfunc_set_tab *kfunc_set_tab; struct btf_id_dtor_kfunc_tab *dtor_kfunc_tab; + struct btf_struct_metas *struct_meta_tab; /* split BTF support */ struct btf *base_btf; @@ -477,16 +478,6 @@ static bool btf_type_nosize_or_null(const struct btf_type *t) return !t || btf_type_nosize(t); } -static bool __btf_type_is_struct(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT; -} - -static bool btf_type_is_array(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY; -} - static bool btf_type_is_datasec(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; @@ -1642,8 +1633,30 @@ static void btf_free_dtor_kfunc_tab(struct btf *btf) btf->dtor_kfunc_tab = NULL; } +static void btf_struct_metas_free(struct btf_struct_metas *tab) +{ + int i; + + if (!tab) + return; + for (i = 0; i < tab->cnt; i++) { + btf_record_free(tab->types[i].record); + kfree(tab->types[i].field_offs); + } + kfree(tab); +} + +static void btf_free_struct_meta_tab(struct btf *btf) +{ + struct btf_struct_metas *tab = btf->struct_meta_tab; + + btf_struct_metas_free(tab); + btf->struct_meta_tab = NULL; +} + static void btf_free(struct btf *btf) { + btf_free_struct_meta_tab(btf); btf_free_dtor_kfunc_tab(btf); btf_free_kfunc_set_tab(btf); kvfree(btf->types); @@ -3353,6 +3366,12 @@ static int btf_get_field_type(const char *name, u32 field_mask, u32 *seen_mask, goto end; } } + if (field_mask & BPF_LIST_NODE) { + if (!strcmp(name, "bpf_list_node")) { + type = BPF_LIST_NODE; + goto end; + } + } /* Only return BPF_KPTR when all other types with matchable names fail */ if (field_mask & BPF_KPTR) { type = BPF_KPTR_REF; @@ -3396,6 +3415,7 @@ static int btf_find_struct_field(const struct btf *btf, switch (field_type) { case BPF_SPIN_LOCK: case BPF_TIMER: + case BPF_LIST_NODE: ret = btf_find_struct(btf, member_type, off, sz, field_type, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) @@ -3456,6 +3476,7 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, switch (field_type) { case BPF_SPIN_LOCK: case BPF_TIMER: + case BPF_LIST_NODE: ret = btf_find_struct(btf, var_type, off, sz, field_type, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) @@ -3627,6 +3648,9 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type return NULL; cnt = ret; + /* This needs to be kzalloc to zero out padding and unused fields, see + * comment in btf_record_equal. + */ rec = kzalloc(offsetof(struct btf_record, fields[cnt]), GFP_KERNEL | __GFP_NOWARN); if (!rec) return ERR_PTR(-ENOMEM); @@ -3671,6 +3695,8 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type if (ret < 0) goto end; break; + case BPF_LIST_NODE: + break; default: ret = -EFAULT; goto end; @@ -3690,6 +3716,67 @@ end: return ERR_PTR(ret); } +int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec) +{ + int i; + + /* There are two owning types, kptr_ref and bpf_list_head. The former + * only supports storing kernel types, which can never store references + * to program allocated local types, atleast not yet. Hence we only need + * to ensure that bpf_list_head ownership does not form cycles. + */ + if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & BPF_LIST_HEAD)) + return 0; + for (i = 0; i < rec->cnt; i++) { + struct btf_struct_meta *meta; + u32 btf_id; + + if (!(rec->fields[i].type & BPF_LIST_HEAD)) + continue; + btf_id = rec->fields[i].list_head.value_btf_id; + meta = btf_find_struct_meta(btf, btf_id); + if (!meta) + return -EFAULT; + rec->fields[i].list_head.value_rec = meta->record; + + if (!(rec->field_mask & BPF_LIST_NODE)) + continue; + + /* We need to ensure ownership acyclicity among all types. The + * proper way to do it would be to topologically sort all BTF + * IDs based on the ownership edges, since there can be multiple + * bpf_list_head in a type. Instead, we use the following + * reasoning: + * + * - A type can only be owned by another type in user BTF if it + * has a bpf_list_node. + * - A type can only _own_ another type in user BTF if it has a + * bpf_list_head. + * + * We ensure that if a type has both bpf_list_head and + * bpf_list_node, its element types cannot be owning types. + * + * To ensure acyclicity: + * + * When A only has bpf_list_head, ownership chain can be: + * A -> B -> C + * Where: + * - B has both bpf_list_head and bpf_list_node. + * - C only has bpf_list_node. + * + * When A has both bpf_list_head and bpf_list_node, some other + * type already owns it in the BTF domain, hence it can not own + * another owning type through any of the bpf_list_head edges. + * A -> B + * Where: + * - B only has bpf_list_node. + */ + if (meta->record->field_mask & BPF_LIST_HEAD) + return -ELOOP; + } + return 0; +} + static int btf_field_offs_cmp(const void *_a, const void *_b, const void *priv) { const u32 a = *(const u32 *)_a; @@ -5141,6 +5228,119 @@ static int btf_parse_hdr(struct btf_verifier_env *env) return btf_check_sec_info(env, btf_data_size); } +static const char *alloc_obj_fields[] = { + "bpf_spin_lock", + "bpf_list_head", + "bpf_list_node", +}; + +static struct btf_struct_metas * +btf_parse_struct_metas(struct bpf_verifier_log *log, struct btf *btf) +{ + union { + struct btf_id_set set; + struct { + u32 _cnt; + u32 _ids[ARRAY_SIZE(alloc_obj_fields)]; + } _arr; + } aof; + struct btf_struct_metas *tab = NULL; + int i, n, id, ret; + + BUILD_BUG_ON(offsetof(struct btf_id_set, cnt) != 0); + BUILD_BUG_ON(sizeof(struct btf_id_set) != sizeof(u32)); + + memset(&aof, 0, sizeof(aof)); + for (i = 0; i < ARRAY_SIZE(alloc_obj_fields); i++) { + /* Try to find whether this special type exists in user BTF, and + * if so remember its ID so we can easily find it among members + * of structs that we iterate in the next loop. + */ + id = btf_find_by_name_kind(btf, alloc_obj_fields[i], BTF_KIND_STRUCT); + if (id < 0) + continue; + aof.set.ids[aof.set.cnt++] = id; + } + + if (!aof.set.cnt) + return NULL; + sort(&aof.set.ids, aof.set.cnt, sizeof(aof.set.ids[0]), btf_id_cmp_func, NULL); + + n = btf_nr_types(btf); + for (i = 1; i < n; i++) { + struct btf_struct_metas *new_tab; + const struct btf_member *member; + struct btf_field_offs *foffs; + struct btf_struct_meta *type; + struct btf_record *record; + const struct btf_type *t; + int j, tab_cnt; + + t = btf_type_by_id(btf, i); + if (!t) { + ret = -EINVAL; + goto free; + } + if (!__btf_type_is_struct(t)) + continue; + + cond_resched(); + + for_each_member(j, t, member) { + if (btf_id_set_contains(&aof.set, member->type)) + goto parse; + } + continue; + parse: + tab_cnt = tab ? tab->cnt : 0; + new_tab = krealloc(tab, offsetof(struct btf_struct_metas, types[tab_cnt + 1]), + GFP_KERNEL | __GFP_NOWARN); + if (!new_tab) { + ret = -ENOMEM; + goto free; + } + if (!tab) + new_tab->cnt = 0; + tab = new_tab; + + type = &tab->types[tab->cnt]; + type->btf_id = i; + record = btf_parse_fields(btf, t, BPF_SPIN_LOCK | BPF_LIST_HEAD | BPF_LIST_NODE, t->size); + /* The record cannot be unset, treat it as an error if so */ + if (IS_ERR_OR_NULL(record)) { + ret = PTR_ERR_OR_ZERO(record) ?: -EFAULT; + goto free; + } + foffs = btf_parse_field_offs(record); + /* We need the field_offs to be valid for a valid record, + * either both should be set or both should be unset. + */ + if (IS_ERR_OR_NULL(foffs)) { + btf_record_free(record); + ret = -EFAULT; + goto free; + } + type->record = record; + type->field_offs = foffs; + tab->cnt++; + } + return tab; +free: + btf_struct_metas_free(tab); + return ERR_PTR(ret); +} + +struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id) +{ + struct btf_struct_metas *tab; + + BUILD_BUG_ON(offsetof(struct btf_struct_meta, btf_id) != 0); + tab = btf->struct_meta_tab; + if (!tab) + return NULL; + return bsearch(&btf_id, tab->types, tab->cnt, sizeof(tab->types[0]), btf_id_cmp_func); +} + static int btf_check_type_tags(struct btf_verifier_env *env, struct btf *btf, int start_id) { @@ -5191,6 +5391,7 @@ static int btf_check_type_tags(struct btf_verifier_env *env, static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, u32 log_level, char __user *log_ubuf, u32 log_size) { + struct btf_struct_metas *struct_meta_tab; struct btf_verifier_env *env = NULL; struct bpf_verifier_log *log; struct btf *btf = NULL; @@ -5259,15 +5460,34 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, if (err) goto errout; + struct_meta_tab = btf_parse_struct_metas(log, btf); + if (IS_ERR(struct_meta_tab)) { + err = PTR_ERR(struct_meta_tab); + goto errout; + } + btf->struct_meta_tab = struct_meta_tab; + + if (struct_meta_tab) { + int i; + + for (i = 0; i < struct_meta_tab->cnt; i++) { + err = btf_check_and_fixup_fields(btf, struct_meta_tab->types[i].record); + if (err < 0) + goto errout_meta; + } + } + if (log->level && bpf_verifier_log_full(log)) { err = -ENOSPC; - goto errout; + goto errout_meta; } btf_verifier_env_free(env); refcount_set(&btf->refcnt, 1); return btf; +errout_meta: + btf_free_struct_meta_tab(btf); errout: btf_verifier_env_free(env); if (btf) @@ -5309,7 +5529,7 @@ static u8 bpf_ctx_convert_map[] = { #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE -static const struct btf_member * +const struct btf_member * 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) @@ -6028,12 +6248,39 @@ int btf_struct_access(struct bpf_verifier_log *log, u32 id = reg->btf_id; int err; + while (type_is_alloc(reg->type)) { + struct btf_struct_meta *meta; + struct btf_record *rec; + int i; + + meta = btf_find_struct_meta(btf, id); + if (!meta) + break; + rec = meta->record; + for (i = 0; i < rec->cnt; i++) { + struct btf_field *field = &rec->fields[i]; + u32 offset = field->offset; + if (off < offset + btf_field_type_size(field->type) && offset < off + size) { + bpf_log(log, + "direct access to %s is disallowed\n", + btf_field_type_name(field->type)); + return -EACCES; + } + } + break; + } + t = btf_type_by_id(btf, id); do { err = btf_struct_walk(log, btf, t, off, size, &id, &tmp_flag); switch (err) { case WALK_PTR: + /* For local types, the destination register cannot + * become a pointer again. + */ + if (type_is_alloc(reg->type)) + return SCALAR_VALUE; /* If we found the pointer or scalar on t+off, * we're done. */ @@ -6068,8 +6315,8 @@ int btf_struct_access(struct bpf_verifier_log *log, * end up with two different module BTFs, but IDs point to the common type in * vmlinux BTF. */ -static bool btf_types_are_same(const struct btf *btf1, u32 id1, - const struct btf *btf2, u32 id2) +bool btf_types_are_same(const struct btf *btf1, u32 id1, + const struct btf *btf2, u32 id2) { if (id1 != id2) return false; @@ -6351,122 +6598,19 @@ int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *pr return btf_check_func_type_match(log, btf1, t1, btf2, t2); } -static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = { -#ifdef CONFIG_NET - [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK], - [PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], - [PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP], -#endif -}; - -/* Returns true if struct is composed of scalars, 4 levels of nesting allowed */ -static bool __btf_type_is_scalar_struct(struct bpf_verifier_log *log, - const struct btf *btf, - const struct btf_type *t, int rec) -{ - const struct btf_type *member_type; - const struct btf_member *member; - u32 i; - - if (!btf_type_is_struct(t)) - return false; - - for_each_member(i, t, member) { - const struct btf_array *array; - - member_type = btf_type_skip_modifiers(btf, member->type, NULL); - if (btf_type_is_struct(member_type)) { - if (rec >= 3) { - bpf_log(log, "max struct nesting depth exceeded\n"); - return false; - } - if (!__btf_type_is_scalar_struct(log, btf, member_type, rec + 1)) - return false; - continue; - } - if (btf_type_is_array(member_type)) { - array = btf_type_array(member_type); - if (!array->nelems) - return false; - member_type = btf_type_skip_modifiers(btf, array->type, NULL); - if (!btf_type_is_scalar(member_type)) - return false; - continue; - } - if (!btf_type_is_scalar(member_type)) - return false; - } - return true; -} - -static bool is_kfunc_arg_mem_size(const struct btf *btf, - const struct btf_param *arg, - const struct bpf_reg_state *reg) -{ - int len, sfx_len = sizeof("__sz") - 1; - const struct btf_type *t; - const char *param_name; - - t = btf_type_skip_modifiers(btf, arg->type, NULL); - if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) - return false; - - /* 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 < sfx_len) - return false; - param_name += len - sfx_len; - if (strncmp(param_name, "__sz", sfx_len)) - return false; - - return true; -} - -static bool btf_is_kfunc_arg_mem_size(const struct btf *btf, - const struct btf_param *arg, - const struct bpf_reg_state *reg, - const char *name) -{ - int len, target_len = strlen(name); - const struct btf_type *t; - const char *param_name; - - t = btf_type_skip_modifiers(btf, arg->type, NULL); - if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) - return false; - - param_name = btf_name_by_offset(btf, arg->name_off); - if (str_is_empty(param_name)) - return false; - len = strlen(param_name); - if (len != target_len) - return false; - if (strcmp(param_name, name)) - return false; - - return true; -} - static int btf_check_func_arg_match(struct bpf_verifier_env *env, const struct btf *btf, u32 func_id, struct bpf_reg_state *regs, bool ptr_to_mem_ok, - struct bpf_kfunc_arg_meta *kfunc_meta, bool processing_call) { enum bpf_prog_type prog_type = resolve_prog_type(env->prog); - bool rel = false, kptr_get = false, trusted_args = false; - bool sleepable = false; struct bpf_verifier_log *log = &env->log; - u32 i, nargs, ref_id, ref_obj_id = 0; - bool is_kfunc = btf_is_kernel(btf); const char *func_name, *ref_tname; const struct btf_type *t, *ref_t; const struct btf_param *args; - int ref_regno = 0, ret; + u32 i, nargs, ref_id; + int ret; t = btf_type_by_id(btf, func_id); if (!t || !btf_type_is_func(t)) { @@ -6492,14 +6636,6 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, return -EINVAL; } - if (is_kfunc && kfunc_meta) { - /* Only kfunc can be release func */ - rel = kfunc_meta->flags & KF_RELEASE; - kptr_get = kfunc_meta->flags & KF_KPTR_GET; - trusted_args = kfunc_meta->flags & KF_TRUSTED_ARGS; - sleepable = kfunc_meta->flags & KF_SLEEPABLE; - } - /* check that BTF function arguments match actual types that the * verifier sees. */ @@ -6507,42 +6643,9 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, enum bpf_arg_type arg_type = ARG_DONTCARE; u32 regno = i + 1; struct bpf_reg_state *reg = ®s[regno]; - bool obj_ptr = false; t = btf_type_skip_modifiers(btf, args[i].type, NULL); if (btf_type_is_scalar(t)) { - if (is_kfunc && kfunc_meta) { - bool is_buf_size = false; - - /* check for any const scalar parameter of name "rdonly_buf_size" - * or "rdwr_buf_size" - */ - if (btf_is_kfunc_arg_mem_size(btf, &args[i], reg, - "rdonly_buf_size")) { - kfunc_meta->r0_rdonly = true; - is_buf_size = true; - } else if (btf_is_kfunc_arg_mem_size(btf, &args[i], reg, - "rdwr_buf_size")) - is_buf_size = true; - - if (is_buf_size) { - if (kfunc_meta->r0_size) { - bpf_log(log, "2 or more rdonly/rdwr_buf_size parameters for kfunc"); - return -EINVAL; - } - - if (!tnum_is_const(reg->var_off)) { - bpf_log(log, "R%d is not a const\n", regno); - return -EINVAL; - } - - kfunc_meta->r0_size = reg->var_off.value; - ret = mark_chain_precision(env, regno); - if (ret) - return ret; - } - } - if (reg->type == SCALAR_VALUE) continue; bpf_log(log, "R%d is not a scalar\n", regno); @@ -6555,88 +6658,14 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, return -EINVAL; } - /* These register types have special constraints wrt ref_obj_id - * and offset checks. The rest of trusted args don't. - */ - obj_ptr = reg->type == PTR_TO_CTX || reg->type == PTR_TO_BTF_ID || - reg2btf_ids[base_type(reg->type)]; - - /* Check if argument must be a referenced pointer, args + i has - * been verified to be a pointer (after skipping modifiers). - * PTR_TO_CTX is ok without having non-zero ref_obj_id. - */ - if (is_kfunc && trusted_args && (obj_ptr && reg->type != PTR_TO_CTX) && !reg->ref_obj_id) { - bpf_log(log, "R%d must be referenced\n", regno); - return -EINVAL; - } - ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id); ref_tname = btf_name_by_offset(btf, ref_t->name_off); - /* Trusted args have the same offset checks as release arguments */ - if ((trusted_args && obj_ptr) || (rel && reg->ref_obj_id)) - arg_type |= OBJ_RELEASE; ret = check_func_arg_reg_off(env, reg, regno, arg_type); if (ret < 0) return ret; - if (is_kfunc && reg->ref_obj_id) { - /* Ensure only one argument is referenced PTR_TO_BTF_ID */ - if (ref_obj_id) { - bpf_log(log, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", - regno, reg->ref_obj_id, ref_obj_id); - return -EFAULT; - } - ref_regno = regno; - ref_obj_id = reg->ref_obj_id; - } - - /* kptr_get is only true for kfunc */ - if (i == 0 && kptr_get) { - struct btf_field *kptr_field; - - if (reg->type != PTR_TO_MAP_VALUE) { - bpf_log(log, "arg#0 expected pointer to map value\n"); - return -EINVAL; - } - - /* check_func_arg_reg_off allows var_off for - * PTR_TO_MAP_VALUE, but we need fixed offset to find - * off_desc. - */ - if (!tnum_is_const(reg->var_off)) { - bpf_log(log, "arg#0 must have constant offset\n"); - return -EINVAL; - } - - kptr_field = btf_record_find(reg->map_ptr->record, reg->off + reg->var_off.value, BPF_KPTR); - if (!kptr_field || kptr_field->type != BPF_KPTR_REF) { - bpf_log(log, "arg#0 no referenced kptr at map value offset=%llu\n", - reg->off + reg->var_off.value); - return -EINVAL; - } - - if (!btf_type_is_ptr(ref_t)) { - bpf_log(log, "arg#0 BTF type must be a double pointer\n"); - return -EINVAL; - } - - ref_t = btf_type_skip_modifiers(btf, ref_t->type, &ref_id); - ref_tname = btf_name_by_offset(btf, ref_t->name_off); - - if (!btf_type_is_struct(ref_t)) { - bpf_log(log, "kernel function %s args#%d pointer type %s %s is not supported\n", - func_name, i, btf_type_str(ref_t), ref_tname); - return -EINVAL; - } - if (!btf_struct_ids_match(log, btf, ref_id, 0, kptr_field->kptr.btf, - kptr_field->kptr.btf_id, true)) { - bpf_log(log, "kernel function %s args#%d expected pointer to %s %s\n", - func_name, i, btf_type_str(ref_t), ref_tname); - return -EINVAL; - } - /* rest of the arguments can be anything, like normal kfunc */ - } else if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { + if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { /* If function expects ctx type in BTF check that caller * is passing PTR_TO_CTX. */ @@ -6646,109 +6675,10 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, i, btf_type_str(t)); return -EINVAL; } - } else if (is_kfunc && (reg->type == PTR_TO_BTF_ID || - (reg2btf_ids[base_type(reg->type)] && !type_flag(reg->type)))) { - const struct btf_type *reg_ref_t; - const struct btf *reg_btf; - const char *reg_ref_tname; - u32 reg_ref_id; - - if (!btf_type_is_struct(ref_t)) { - bpf_log(log, "kernel function %s args#%d pointer type %s %s is not supported\n", - func_name, i, btf_type_str(ref_t), - ref_tname); - return -EINVAL; - } - - if (reg->type == PTR_TO_BTF_ID) { - reg_btf = reg->btf; - reg_ref_id = reg->btf_id; - } else { - reg_btf = btf_vmlinux; - reg_ref_id = *reg2btf_ids[base_type(reg->type)]; - } - - reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id, - ®_ref_id); - reg_ref_tname = btf_name_by_offset(reg_btf, - reg_ref_t->name_off); - if (!btf_struct_ids_match(log, reg_btf, reg_ref_id, - reg->off, btf, ref_id, - trusted_args || (rel && reg->ref_obj_id))) { - bpf_log(log, "kernel function %s args#%d expected pointer to %s %s but R%d has a pointer to %s %s\n", - func_name, i, - btf_type_str(ref_t), ref_tname, - regno, btf_type_str(reg_ref_t), - reg_ref_tname); - return -EINVAL; - } } else if (ptr_to_mem_ok && processing_call) { const struct btf_type *resolve_ret; u32 type_size; - if (is_kfunc) { - bool arg_mem_size = i + 1 < nargs && is_kfunc_arg_mem_size(btf, &args[i + 1], ®s[regno + 1]); - bool arg_dynptr = btf_type_is_struct(ref_t) && - !strcmp(ref_tname, - stringify_struct(bpf_dynptr_kern)); - - /* Permit pointer to mem, but only when argument - * type is pointer to scalar, or struct composed - * (recursively) of scalars. - * When arg_mem_size is true, the pointer can be - * void *. - * Also permit initialized local dynamic pointers. - */ - if (!btf_type_is_scalar(ref_t) && - !__btf_type_is_scalar_struct(log, btf, ref_t, 0) && - !arg_dynptr && - (arg_mem_size ? !btf_type_is_void(ref_t) : 1)) { - bpf_log(log, - "arg#%d pointer type %s %s must point to %sscalar, or struct with scalar\n", - i, btf_type_str(ref_t), ref_tname, arg_mem_size ? "void, " : ""); - return -EINVAL; - } - - if (arg_dynptr) { - if (reg->type != PTR_TO_STACK) { - bpf_log(log, "arg#%d pointer type %s %s not to stack\n", - i, btf_type_str(ref_t), - ref_tname); - return -EINVAL; - } - - if (!is_dynptr_reg_valid_init(env, reg)) { - bpf_log(log, - "arg#%d pointer type %s %s must be valid and initialized\n", - i, btf_type_str(ref_t), - ref_tname); - return -EINVAL; - } - - if (!is_dynptr_type_expected(env, reg, - ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL)) { - bpf_log(log, - "arg#%d pointer type %s %s points to unsupported dynamic pointer type\n", - i, btf_type_str(ref_t), - ref_tname); - return -EINVAL; - } - - continue; - } - - /* Check for mem, len pair */ - if (arg_mem_size) { - if (check_kfunc_mem_size_reg(env, ®s[regno + 1], regno + 1)) { - bpf_log(log, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", - i, i + 1); - return -EINVAL; - } - i++; - continue; - } - } - resolve_ret = btf_resolve_size(btf, ref_t, &type_size); if (IS_ERR(resolve_ret)) { bpf_log(log, @@ -6761,36 +6691,13 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, if (check_mem_reg(env, reg, regno, type_size)) return -EINVAL; } else { - bpf_log(log, "reg type unsupported for arg#%d %sfunction %s#%d\n", i, - is_kfunc ? "kernel " : "", func_name, func_id); + bpf_log(log, "reg type unsupported for arg#%d function %s#%d\n", i, + func_name, func_id); return -EINVAL; } } - /* Either both are set, or neither */ - WARN_ON_ONCE((ref_obj_id && !ref_regno) || (!ref_obj_id && ref_regno)); - /* We already made sure ref_obj_id is set only for one argument. We do - * allow (!rel && ref_obj_id), so that passing such referenced - * PTR_TO_BTF_ID to other kfuncs works. Note that rel is only true when - * is_kfunc is true. - */ - if (rel && !ref_obj_id) { - bpf_log(log, "release kernel function %s expects refcounted PTR_TO_BTF_ID\n", - func_name); - return -EINVAL; - } - - if (sleepable && !env->prog->aux->sleepable) { - bpf_log(log, "kernel function %s is sleepable but the program is not\n", - func_name); - return -EINVAL; - } - - if (kfunc_meta && ref_obj_id) - kfunc_meta->ref_obj_id = ref_obj_id; - - /* returns argument register number > 0 in case of reference release kfunc */ - return rel ? ref_regno : 0; + return 0; } /* Compare BTF of a function declaration with given bpf_reg_state. @@ -6820,7 +6727,7 @@ int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, return -EINVAL; is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL; - err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, NULL, false); + err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, false); /* Compiler optimizations can remove arguments from static functions * or mismatched type can be passed into a global function. @@ -6863,7 +6770,7 @@ int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, return -EINVAL; is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL; - err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, NULL, true); + err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, true); /* Compiler optimizations can remove arguments from static functions * or mismatched type can be passed into a global function. @@ -6874,14 +6781,6 @@ int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, return err; } -int btf_check_kfunc_arg_match(struct bpf_verifier_env *env, - const struct btf *btf, u32 func_id, - struct bpf_reg_state *regs, - struct bpf_kfunc_arg_meta *meta) -{ - return btf_check_func_arg_match(env, btf, func_id, regs, true, meta, true); -} - /* Convert BTF of a function into bpf_reg_state if possible * Returns: * EFAULT - there is a verifier bug. Abort verification. @@ -7264,23 +7163,6 @@ bool btf_is_module(const struct btf *btf) return btf->kernel_btf && strcmp(btf->name, "vmlinux") != 0; } -static int btf_id_cmp_func(const void *a, const void *b) -{ - const int *pa = a, *pb = b; - - return *pa - *pb; -} - -bool btf_id_set_contains(const struct btf_id_set *set, u32 id) -{ - return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL; -} - -static void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id) -{ - return bsearch(&id, set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func); -} - enum { BTF_MODULE_F_LIVE = (1 << 0), }; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9c16338bcbe8..2e57fc839a5c 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -34,6 +34,7 @@ #include <linux/log2.h> #include <linux/bpf_verifier.h> #include <linux/nodemask.h> +#include <linux/bpf_mem_alloc.h> #include <asm/barrier.h> #include <asm/unaligned.h> @@ -60,6 +61,9 @@ #define CTX regs[BPF_REG_CTX] #define IMM insn->imm +struct bpf_mem_alloc bpf_global_ma; +bool bpf_global_ma_set; + /* No hurry in this branch * * Exported for the bpf jit load helper. @@ -2746,6 +2750,18 @@ int __weak bpf_arch_text_invalidate(void *dst, size_t len) return -ENOTSUPP; } +#ifdef CONFIG_BPF_SYSCALL +static int __init bpf_global_ma_init(void) +{ + int ret; + + ret = bpf_mem_alloc_init(&bpf_global_ma, 0, false); + bpf_global_ma_set = !ret; + return ret; +} +late_initcall(bpf_global_ma_init); +#endif + DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key); EXPORT_SYMBOL(bpf_stats_enabled_key); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 50d254cd0709..5aa2b5525f79 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1511,7 +1511,6 @@ static void htab_map_free(struct bpf_map *map) prealloc_destroy(htab); } - bpf_map_free_record(map); free_percpu(htab->extra_elems); bpf_map_area_free(htab->buckets); bpf_mem_alloc_destroy(&htab->pcpu_ma); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 7bc71995f17c..212e791d7452 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -19,6 +19,7 @@ #include <linux/proc_ns.h> #include <linux/security.h> #include <linux/btf_ids.h> +#include <linux/bpf_mem_alloc.h> #include "../../lib/kstrtox.h" @@ -336,6 +337,7 @@ const struct bpf_func_proto bpf_spin_lock_proto = { .gpl_only = false, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_SPIN_LOCK, + .arg1_btf_id = BPF_PTR_POISON, }; static inline void __bpf_spin_unlock_irqrestore(struct bpf_spin_lock *lock) @@ -358,6 +360,7 @@ const struct bpf_func_proto bpf_spin_unlock_proto = { .gpl_only = false, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_SPIN_LOCK, + .arg1_btf_id = BPF_PTR_POISON, }; void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, @@ -1733,25 +1736,121 @@ unlock: obj -= field->list_head.node_offset; head = head->next; - /* TODO: Rework later */ - kfree(obj); + /* The contained type can also have resources, including a + * bpf_list_head which needs to be freed. + */ + bpf_obj_free_fields(field->list_head.value_rec, obj); + /* bpf_mem_free requires migrate_disable(), since we can be + * called from map free path as well apart from BPF program (as + * part of map ops doing bpf_obj_free_fields). + */ + migrate_disable(); + bpf_mem_free(&bpf_global_ma, obj); + migrate_enable(); } } -BTF_SET8_START(tracing_btf_ids) +__diag_push(); +__diag_ignore_all("-Wmissing-prototypes", + "Global functions as their definitions will be in vmlinux BTF"); + +void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign) +{ + struct btf_struct_meta *meta = meta__ign; + u64 size = local_type_id__k; + void *p; + + if (unlikely(!bpf_global_ma_set)) + return NULL; + p = bpf_mem_alloc(&bpf_global_ma, size); + if (!p) + return NULL; + if (meta) + bpf_obj_init(meta->field_offs, p); + return p; +} + +void bpf_obj_drop_impl(void *p__alloc, void *meta__ign) +{ + struct btf_struct_meta *meta = meta__ign; + void *p = p__alloc; + + if (meta) + bpf_obj_free_fields(meta->record, p); + bpf_mem_free(&bpf_global_ma, p); +} + +static void __bpf_list_add(struct bpf_list_node *node, struct bpf_list_head *head, bool tail) +{ + struct list_head *n = (void *)node, *h = (void *)head; + + if (unlikely(!h->next)) + INIT_LIST_HEAD(h); + if (unlikely(!n->next)) + INIT_LIST_HEAD(n); + tail ? list_add_tail(n, h) : list_add(n, h); +} + +void bpf_list_push_front(struct bpf_list_head *head, struct bpf_list_node *node) +{ + return __bpf_list_add(node, head, false); +} + +void bpf_list_push_back(struct bpf_list_head *head, struct bpf_list_node *node) +{ + return __bpf_list_add(node, head, true); +} + +static struct bpf_list_node *__bpf_list_del(struct bpf_list_head *head, bool tail) +{ + struct list_head *n, *h = (void *)head; + + if (unlikely(!h->next)) + INIT_LIST_HEAD(h); + if (list_empty(h)) + return NULL; + n = tail ? h->prev : h->next; + list_del_init(n); + return (struct bpf_list_node *)n; +} + +struct bpf_list_node *bpf_list_pop_front(struct bpf_list_head *head) +{ + return __bpf_list_del(head, false); +} + +struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head) +{ + return __bpf_list_del(head, true); +} + +__diag_pop(); + +BTF_SET8_START(generic_btf_ids) #ifdef CONFIG_KEXEC_CORE BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE) #endif -BTF_SET8_END(tracing_btf_ids) - -static const struct btf_kfunc_id_set tracing_kfunc_set = { +BTF_ID_FLAGS(func, bpf_obj_new_impl, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_obj_drop_impl, KF_RELEASE) +BTF_ID_FLAGS(func, bpf_list_push_front) +BTF_ID_FLAGS(func, bpf_list_push_back) +BTF_ID_FLAGS(func, bpf_list_pop_front, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_list_pop_back, KF_ACQUIRE | KF_RET_NULL) +BTF_SET8_END(generic_btf_ids) + +static const struct btf_kfunc_id_set generic_kfunc_set = { .owner = THIS_MODULE, - .set = &tracing_btf_ids, + .set = &generic_btf_ids, }; static int __init kfunc_init(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &tracing_kfunc_set); + int ret; + + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &generic_kfunc_set); + if (ret) + return ret; + return register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &generic_kfunc_set); } late_initcall(kfunc_init); diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 8ca0cca39d49..38136ec4e095 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -12,6 +12,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) struct bpf_map *inner_map, *inner_map_meta; u32 inner_map_meta_size; struct fd f; + int ret; f = fdget(inner_map_ufd); inner_map = __bpf_map_get(f); @@ -20,18 +21,13 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) /* Does not support >1 level map-in-map */ if (inner_map->inner_map_meta) { - fdput(f); - return ERR_PTR(-EINVAL); + ret = -EINVAL; + goto put; } if (!inner_map->ops->map_meta_equal) { - fdput(f); - return ERR_PTR(-ENOTSUPP); - } - - if (btf_record_has_field(inner_map->record, BPF_SPIN_LOCK)) { - fdput(f); - return ERR_PTR(-ENOTSUPP); + ret = -ENOTSUPP; + goto put; } inner_map_meta_size = sizeof(*inner_map_meta); @@ -41,8 +37,8 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) inner_map_meta = kzalloc(inner_map_meta_size, GFP_USER); if (!inner_map_meta) { - fdput(f); - return ERR_PTR(-ENOMEM); + ret = -ENOMEM; + goto put; } inner_map_meta->map_type = inner_map->map_type; @@ -50,15 +46,33 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) inner_map_meta->value_size = inner_map->value_size; inner_map_meta->map_flags = inner_map->map_flags; inner_map_meta->max_entries = inner_map->max_entries; + inner_map_meta->record = btf_record_dup(inner_map->record); if (IS_ERR(inner_map_meta->record)) { /* btf_record_dup returns NULL or valid pointer in case of * invalid/empty/valid, but ERR_PTR in case of errors. During * equality NULL or IS_ERR is equivalent. */ - fdput(f); - return ERR_CAST(inner_map_meta->record); + ret = PTR_ERR(inner_map_meta->record); + goto free; } + if (inner_map_meta->record) { + struct btf_field_offs *field_offs; + /* If btf_record is !IS_ERR_OR_NULL, then field_offs is always + * valid. + */ + field_offs = kmemdup(inner_map->field_offs, sizeof(*inner_map->field_offs), GFP_KERNEL | __GFP_NOWARN); + if (!field_offs) { + ret = -ENOMEM; + goto free_rec; + } + inner_map_meta->field_offs = field_offs; + } + /* Note: We must use the same BTF, as we also used btf_record_dup above + * which relies on BTF being same for both maps, as some members like + * record->fields.list_head have pointers like value_rec pointing into + * inner_map->btf. + */ if (inner_map->btf) { btf_get(inner_map->btf); inner_map_meta->btf = inner_map->btf; @@ -74,10 +88,18 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) fdput(f); return inner_map_meta; +free_rec: + btf_record_free(inner_map_meta->record); +free: + kfree(inner_map_meta); +put: + fdput(f); + return ERR_PTR(ret); } void bpf_map_meta_free(struct bpf_map *map_meta) { + kfree(map_meta->field_offs); bpf_map_free_record(map_meta); btf_put(map_meta->btf); kfree(map_meta); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b078965999e6..35972afb6850 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -537,6 +537,7 @@ void btf_record_free(struct btf_record *rec) btf_put(rec->fields[i].kptr.btf); break; case BPF_LIST_HEAD: + case BPF_LIST_NODE: /* Nothing to release for bpf_list_head */ break; default: @@ -582,6 +583,7 @@ struct btf_record *btf_record_dup(const struct btf_record *rec) } break; case BPF_LIST_HEAD: + case BPF_LIST_NODE: /* Nothing to acquire for bpf_list_head */ break; default: @@ -609,6 +611,20 @@ bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *r if (rec_a->cnt != rec_b->cnt) return false; size = offsetof(struct btf_record, fields[rec_a->cnt]); + /* btf_parse_fields uses kzalloc to allocate a btf_record, so unused + * members are zeroed out. So memcmp is safe to do without worrying + * about padding/unused fields. + * + * While spin_lock, timer, and kptr have no relation to map BTF, + * list_head metadata is specific to map BTF, the btf and value_rec + * members in particular. btf is the map BTF, while value_rec points to + * btf_record in that map BTF. + * + * So while by default, we don't rely on the map BTF (which the records + * were parsed from) matching for both records, which is not backwards + * compatible, in case list_head is part of it, we implicitly rely on + * that by way of depending on memcmp succeeding for it. + */ return !memcmp(rec_a, rec_b, size); } @@ -648,6 +664,8 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) continue; bpf_list_head_free(field, field_ptr, obj + rec->spin_lock_off); break; + case BPF_LIST_NODE: + break; default: WARN_ON_ONCE(1); continue; @@ -659,14 +677,24 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) static void bpf_map_free_deferred(struct work_struct *work) { struct bpf_map *map = container_of(work, struct bpf_map, work); + struct btf_field_offs *foffs = map->field_offs; + struct btf_record *rec = map->record; security_bpf_map_free(map); - kfree(map->field_offs); bpf_map_release_memcg(map); - /* implementation dependent freeing, map_free callback also does - * bpf_map_free_record, if needed. - */ + /* implementation dependent freeing */ map->ops->map_free(map); + /* Delay freeing of field_offs and btf_record for maps, as map_free + * callback usually needs access to them. It is better to do it here + * than require each callback to do the free itself manually. + * + * Note that the btf_record stashed in map->inner_map_meta->record was + * already freed using the map_free callback for map in map case which + * eventually calls bpf_map_free_meta, since inner_map_meta is only a + * template bpf_map struct used during verification. + */ + kfree(foffs); + btf_record_free(rec); } static void bpf_map_put_uref(struct bpf_map *map) @@ -1010,7 +1038,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY) { - return -EOPNOTSUPP; + ret = -EOPNOTSUPP; goto free_map_tab; } break; @@ -1040,6 +1068,10 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, } } + ret = btf_check_and_fixup_fields(btf, map->record); + if (ret < 0) + goto free_map_tab; + if (map->ops->map_check_btf) { ret = map->ops->map_check_btf(map, btf, key_type, value_type); if (ret < 0) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 0312d9ce292f..195d24316750 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -451,10 +451,24 @@ static bool reg_type_not_null(enum bpf_reg_type type) type == PTR_TO_SOCK_COMMON; } +static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg) +{ + struct btf_record *rec = NULL; + struct btf_struct_meta *meta; + + if (reg->type == PTR_TO_MAP_VALUE) { + rec = reg->map_ptr->record; + } else if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC)) { + meta = btf_find_struct_meta(reg->btf, reg->btf_id); + if (meta) + rec = meta->record; + } + return rec; +} + static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) { - return reg->type == PTR_TO_MAP_VALUE && - btf_record_has_field(reg->map_ptr->record, BPF_SPIN_LOCK); + return btf_record_has_field(reg_btf_record(reg), BPF_SPIN_LOCK); } static bool type_is_rdonly_mem(u32 type) @@ -1207,7 +1221,8 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, } dst_state->speculative = src->speculative; dst_state->curframe = src->curframe; - dst_state->active_spin_lock = src->active_spin_lock; + dst_state->active_lock.ptr = src->active_lock.ptr; + dst_state->active_lock.id = src->active_lock.id; dst_state->branches = src->branches; dst_state->parent = src->parent; dst_state->first_insn_idx = src->first_insn_idx; @@ -4687,14 +4702,27 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, return -EACCES; } - if (env->ops->btf_struct_access) { + if (env->ops->btf_struct_access && !type_is_alloc(reg->type)) { + if (!btf_is_kernel(reg->btf)) { + verbose(env, "verifier internal error: reg->btf must be kernel btf\n"); + return -EFAULT; + } ret = env->ops->btf_struct_access(&env->log, reg, off, size, atype, &btf_id, &flag); } else { - if (atype != BPF_READ) { + /* Writes are permitted with default btf_struct_access for + * program allocated objects (which always have ref_obj_id > 0), + * but not for untrusted PTR_TO_BTF_ID | MEM_ALLOC. + */ + if (atype != BPF_READ && reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { verbose(env, "only read is supported\n"); return -EACCES; } + if (type_is_alloc(reg->type) && !reg->ref_obj_id) { + verbose(env, "verifier internal error: ref_obj_id for allocated object must be non-zero\n"); + return -EFAULT; + } + ret = btf_struct_access(&env->log, reg, off, size, atype, &btf_id, &flag); } @@ -5522,8 +5550,8 @@ int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, return err; } -int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, - u32 regno) +static int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + u32 regno) { struct bpf_reg_state *mem_reg = &cur_regs(env)[regno - 1]; bool may_be_null = type_may_be_null(mem_reg->type); @@ -5551,23 +5579,26 @@ int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state } /* Implementation details: - * bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL + * bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL. + * bpf_obj_new returns PTR_TO_BTF_ID | MEM_ALLOC | PTR_MAYBE_NULL. * Two bpf_map_lookups (even with the same key) will have different reg->id. - * For traditional PTR_TO_MAP_VALUE the verifier clears reg->id after - * value_or_null->value transition, since the verifier only cares about - * the range of access to valid map value pointer and doesn't care about actual - * address of the map element. + * Two separate bpf_obj_new will also have different reg->id. + * For traditional PTR_TO_MAP_VALUE or PTR_TO_BTF_ID | MEM_ALLOC, the verifier + * clears reg->id after value_or_null->value transition, since the verifier only + * cares about the range of access to valid map value pointer and doesn't care + * about actual address of the map element. * For maps with 'struct bpf_spin_lock' inside map value the verifier keeps * reg->id > 0 after value_or_null->value transition. By doing so * two bpf_map_lookups will be considered two different pointers that - * point to different bpf_spin_locks. + * point to different bpf_spin_locks. Likewise for pointers to allocated objects + * returned from bpf_obj_new. * The verifier allows taking only one bpf_spin_lock at a time to avoid * dead-locks. * Since only one bpf_spin_lock is allowed the checks are simpler than * reg_is_refcounted() logic. The verifier needs to remember only * one spin_lock instead of array of acquired_refs. - * cur_state->active_spin_lock remembers which map value element got locked - * and clears it after bpf_spin_unlock. + * cur_state->active_lock remembers which map value element or allocated + * object got locked and clears it after bpf_spin_unlock. */ static int process_spin_lock(struct bpf_verifier_env *env, int regno, bool is_lock) @@ -5575,8 +5606,10 @@ static int process_spin_lock(struct bpf_verifier_env *env, int regno, struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; struct bpf_verifier_state *cur = env->cur_state; bool is_const = tnum_is_const(reg->var_off); - struct bpf_map *map = reg->map_ptr; u64 val = reg->var_off.value; + struct bpf_map *map = NULL; + struct btf *btf = NULL; + struct btf_record *rec; if (!is_const) { verbose(env, @@ -5584,38 +5617,78 @@ static int process_spin_lock(struct bpf_verifier_env *env, int regno, regno); return -EINVAL; } - if (!map->btf) { - verbose(env, - "map '%s' has to have BTF in order to use bpf_spin_lock\n", - map->name); - return -EINVAL; + if (reg->type == PTR_TO_MAP_VALUE) { + map = reg->map_ptr; + if (!map->btf) { + verbose(env, + "map '%s' has to have BTF in order to use bpf_spin_lock\n", + map->name); + return -EINVAL; + } + } else { + btf = reg->btf; } - if (!btf_record_has_field(map->record, BPF_SPIN_LOCK)) { - verbose(env, "map '%s' has no valid bpf_spin_lock\n", map->name); + + rec = reg_btf_record(reg); + if (!btf_record_has_field(rec, BPF_SPIN_LOCK)) { + verbose(env, "%s '%s' has no valid bpf_spin_lock\n", map ? "map" : "local", + map ? map->name : "kptr"); return -EINVAL; } - if (map->record->spin_lock_off != val + reg->off) { + if (rec->spin_lock_off != val + reg->off) { verbose(env, "off %lld doesn't point to 'struct bpf_spin_lock' that is at %d\n", - val + reg->off, map->record->spin_lock_off); + val + reg->off, rec->spin_lock_off); return -EINVAL; } if (is_lock) { - if (cur->active_spin_lock) { + if (cur->active_lock.ptr) { verbose(env, "Locking two bpf_spin_locks are not allowed\n"); return -EINVAL; } - cur->active_spin_lock = reg->id; + if (map) + cur->active_lock.ptr = map; + else + cur->active_lock.ptr = btf; + cur->active_lock.id = reg->id; } else { - if (!cur->active_spin_lock) { + struct bpf_func_state *fstate = cur_func(env); + void *ptr; + int i; + + if (map) + ptr = map; + else + ptr = btf; + + if (!cur->active_lock.ptr) { verbose(env, "bpf_spin_unlock without taking a lock\n"); return -EINVAL; } - if (cur->active_spin_lock != reg->id) { + if (cur->active_lock.ptr != ptr || + cur->active_lock.id != reg->id) { verbose(env, "bpf_spin_unlock of different lock\n"); return -EINVAL; } - cur->active_spin_lock = 0; + cur->active_lock.ptr = NULL; + cur->active_lock.id = 0; + + for (i = 0; i < fstate->acquired_refs; i++) { + int err; + + /* Complain on error because this reference state cannot + * be freed before this point, as bpf_spin_lock critical + * section does not allow functions that release the + * allocated object immediately. + */ + if (!fstate->refs[i].release_on_unlock) + continue; + err = release_reference(env, fstate->refs[i].id); + if (err) { + verbose(env, "failed to release release_on_unlock reference"); + return err; + } + } } return 0; } @@ -5802,13 +5875,19 @@ static const struct bpf_reg_types int_ptr_types = { }, }; +static const struct bpf_reg_types spin_lock_types = { + .types = { + PTR_TO_MAP_VALUE, + PTR_TO_BTF_ID | MEM_ALLOC, + } +}; + static const struct bpf_reg_types fullsock_types = { .types = { PTR_TO_SOCKET } }; static const struct bpf_reg_types scalar_types = { .types = { SCALAR_VALUE } }; static const struct bpf_reg_types context_types = { .types = { PTR_TO_CTX } }; static const struct bpf_reg_types ringbuf_mem_types = { .types = { PTR_TO_MEM | MEM_RINGBUF } }; static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } }; static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID } }; -static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE } }; static const struct bpf_reg_types percpu_btf_ptr_types = { .types = { PTR_TO_BTF_ID | MEM_PERCPU } }; static const struct bpf_reg_types func_ptr_types = { .types = { PTR_TO_FUNC } }; static const struct bpf_reg_types stack_ptr_types = { .types = { PTR_TO_STACK } }; @@ -5933,6 +6012,11 @@ found: return -EACCES; } } + } else if (type_is_alloc(reg->type)) { + if (meta->func_id != BPF_FUNC_spin_lock && meta->func_id != BPF_FUNC_spin_unlock) { + verbose(env, "verifier internal error: unimplemented handling of MEM_ALLOC\n"); + return -EFAULT; + } } return 0; @@ -5973,6 +6057,7 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, * fixed offset. */ case PTR_TO_BTF_ID: + case PTR_TO_BTF_ID | MEM_ALLOC: /* When referenced PTR_TO_BTF_ID is passed to release function, * it's fixed offset must be 0. In the other cases, fixed offset * can be non-zero. @@ -6048,7 +6133,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, goto skip_type_check; /* arg_btf_id and arg_size are in a union. */ - if (base_type(arg_type) == ARG_PTR_TO_BTF_ID) + if (base_type(arg_type) == ARG_PTR_TO_BTF_ID || + base_type(arg_type) == ARG_PTR_TO_SPIN_LOCK) arg_btf_id = fn->arg_btf_id[arg]; err = check_reg_type(env, regno, arg_type, arg_btf_id, meta); @@ -6666,9 +6752,10 @@ static bool check_btf_id_ok(const struct bpf_func_proto *fn) int i; for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++) { - if (base_type(fn->arg_type[i]) == ARG_PTR_TO_BTF_ID && !fn->arg_btf_id[i]) - return false; - + if (base_type(fn->arg_type[i]) == ARG_PTR_TO_BTF_ID) + return !!fn->arg_btf_id[i]; + if (base_type(fn->arg_type[i]) == ARG_PTR_TO_SPIN_LOCK) + return fn->arg_btf_id[i] == BPF_PTR_POISON; if (base_type(fn->arg_type[i]) != ARG_PTR_TO_BTF_ID && fn->arg_btf_id[i] && /* arg_btf_id and arg_size are in a union. */ (base_type(fn->arg_type[i]) != ARG_PTR_TO_MEM || @@ -7795,19 +7882,882 @@ static void mark_btf_func_reg_size(struct bpf_verifier_env *env, u32 regno, } } +struct bpf_kfunc_call_arg_meta { + /* In parameters */ + struct btf *btf; + u32 func_id; + u32 kfunc_flags; + const struct btf_type *func_proto; + const char *func_name; + /* Out parameters */ + u32 ref_obj_id; + u8 release_regno; + bool r0_rdonly; + u64 r0_size; + struct { + u64 value; + bool found; + } arg_constant; + struct { + struct btf *btf; + u32 btf_id; + } arg_obj_drop; + struct { + struct btf_field *field; + } arg_list_head; +}; + +static bool is_kfunc_acquire(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_ACQUIRE; +} + +static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_RET_NULL; +} + +static bool is_kfunc_release(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_RELEASE; +} + +static bool is_kfunc_trusted_args(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_TRUSTED_ARGS; +} + +static bool is_kfunc_sleepable(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_SLEEPABLE; +} + +static bool is_kfunc_destructive(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_DESTRUCTIVE; +} + +static bool is_kfunc_arg_kptr_get(struct bpf_kfunc_call_arg_meta *meta, int arg) +{ + return arg == 0 && (meta->kfunc_flags & KF_KPTR_GET); +} + +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) +{ + const struct btf_type *t; + + t = btf_type_skip_modifiers(btf, arg->type, NULL); + if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) + return false; + + return __kfunc_param_match_suffix(btf, arg, "__sz"); +} + +static bool is_kfunc_arg_constant(const struct btf *btf, const struct btf_param *arg) +{ + return __kfunc_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"); +} + +static bool is_kfunc_arg_alloc_obj(const struct btf *btf, const struct btf_param *arg) +{ + return __kfunc_param_match_suffix(btf, arg, "__alloc"); +} + +static bool is_kfunc_arg_scalar_with_name(const struct btf *btf, + const struct btf_param *arg, + const char *name) +{ + int len, target_len = strlen(name); + const char *param_name; + + param_name = btf_name_by_offset(btf, arg->name_off); + if (str_is_empty(param_name)) + return false; + len = strlen(param_name); + if (len != target_len) + return false; + if (strcmp(param_name, name)) + return false; + + return true; +} + +enum { + KF_ARG_DYNPTR_ID, + KF_ARG_LIST_HEAD_ID, + KF_ARG_LIST_NODE_ID, +}; + +BTF_ID_LIST(kf_arg_btf_ids) +BTF_ID(struct, bpf_dynptr_kern) +BTF_ID(struct, bpf_list_head) +BTF_ID(struct, bpf_list_node) + +static bool __is_kfunc_ptr_arg_type(const struct btf *btf, + const struct btf_param *arg, int type) +{ + const struct btf_type *t; + u32 res_id; + + t = btf_type_skip_modifiers(btf, arg->type, NULL); + if (!t) + return false; + if (!btf_type_is_ptr(t)) + return false; + t = btf_type_skip_modifiers(btf, t->type, &res_id); + if (!t) + return false; + return btf_types_are_same(btf, res_id, btf_vmlinux, kf_arg_btf_ids[type]); +} + +static bool is_kfunc_arg_dynptr(const struct btf *btf, const struct btf_param *arg) +{ + return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_DYNPTR_ID); +} + +static bool is_kfunc_arg_list_head(const struct btf *btf, const struct btf_param *arg) +{ + return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_LIST_HEAD_ID); +} + +static bool is_kfunc_arg_list_node(const struct btf *btf, const struct btf_param *arg) +{ + return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_LIST_NODE_ID); +} + +/* Returns true if struct is composed of scalars, 4 levels of nesting allowed */ +static bool __btf_type_is_scalar_struct(struct bpf_verifier_env *env, + const struct btf *btf, + const struct btf_type *t, int rec) +{ + const struct btf_type *member_type; + const struct btf_member *member; + u32 i; + + if (!btf_type_is_struct(t)) + return false; + + for_each_member(i, t, member) { + const struct btf_array *array; + + member_type = btf_type_skip_modifiers(btf, member->type, NULL); + if (btf_type_is_struct(member_type)) { + if (rec >= 3) { + verbose(env, "max struct nesting depth exceeded\n"); + return false; + } + if (!__btf_type_is_scalar_struct(env, btf, member_type, rec + 1)) + return false; + continue; + } + if (btf_type_is_array(member_type)) { + array = btf_array(member_type); + if (!array->nelems) + return false; + member_type = btf_type_skip_modifiers(btf, array->type, NULL); + if (!btf_type_is_scalar(member_type)) + return false; + continue; + } + if (!btf_type_is_scalar(member_type)) + return false; + } + return true; +} + + +static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = { +#ifdef CONFIG_NET + [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK], + [PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], + [PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP], +#endif +}; + +enum kfunc_ptr_arg_type { + KF_ARG_PTR_TO_CTX, + KF_ARG_PTR_TO_ALLOC_BTF_ID, /* Allocated object */ + KF_ARG_PTR_TO_KPTR, /* PTR_TO_KPTR but type specific */ + KF_ARG_PTR_TO_DYNPTR, + KF_ARG_PTR_TO_LIST_HEAD, + KF_ARG_PTR_TO_LIST_NODE, + KF_ARG_PTR_TO_BTF_ID, /* Also covers reg2btf_ids conversions */ + KF_ARG_PTR_TO_MEM, + KF_ARG_PTR_TO_MEM_SIZE, /* Size derived from next argument, skip it */ +}; + +enum special_kfunc_type { + KF_bpf_obj_new_impl, + KF_bpf_obj_drop_impl, + KF_bpf_list_push_front, + KF_bpf_list_push_back, + KF_bpf_list_pop_front, + KF_bpf_list_pop_back, +}; + +BTF_SET_START(special_kfunc_set) +BTF_ID(func, bpf_obj_new_impl) +BTF_ID(func, bpf_obj_drop_impl) +BTF_ID(func, bpf_list_push_front) +BTF_ID(func, bpf_list_push_back) +BTF_ID(func, bpf_list_pop_front) +BTF_ID(func, bpf_list_pop_back) +BTF_SET_END(special_kfunc_set) + +BTF_ID_LIST(special_kfunc_list) +BTF_ID(func, bpf_obj_new_impl) +BTF_ID(func, bpf_obj_drop_impl) +BTF_ID(func, bpf_list_push_front) +BTF_ID(func, bpf_list_push_back) +BTF_ID(func, bpf_list_pop_front) +BTF_ID(func, bpf_list_pop_back) + +static enum kfunc_ptr_arg_type +get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, + struct bpf_kfunc_call_arg_meta *meta, + const struct btf_type *t, const struct btf_type *ref_t, + const char *ref_tname, const struct btf_param *args, + int argno, int nargs) +{ + u32 regno = argno + 1; + struct bpf_reg_state *regs = cur_regs(env); + struct bpf_reg_state *reg = ®s[regno]; + bool arg_mem_size = false; + + /* In this function, we verify the kfunc's BTF as per the argument type, + * leaving the rest of the verification with respect to the register + * 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)) + return KF_ARG_PTR_TO_CTX; + + if (is_kfunc_arg_alloc_obj(meta->btf, &args[argno])) + return KF_ARG_PTR_TO_ALLOC_BTF_ID; + + if (is_kfunc_arg_kptr_get(meta, argno)) { + if (!btf_type_is_ptr(ref_t)) { + verbose(env, "arg#0 BTF type must be a double pointer for kptr_get kfunc\n"); + return -EINVAL; + } + ref_t = btf_type_by_id(meta->btf, ref_t->type); + ref_tname = btf_name_by_offset(meta->btf, ref_t->name_off); + if (!btf_type_is_struct(ref_t)) { + verbose(env, "kernel function %s args#0 pointer type %s %s is not supported\n", + meta->func_name, btf_type_str(ref_t), ref_tname); + return -EINVAL; + } + return KF_ARG_PTR_TO_KPTR; + } + + if (is_kfunc_arg_dynptr(meta->btf, &args[argno])) + return KF_ARG_PTR_TO_DYNPTR; + + if (is_kfunc_arg_list_head(meta->btf, &args[argno])) + return KF_ARG_PTR_TO_LIST_HEAD; + + if (is_kfunc_arg_list_node(meta->btf, &args[argno])) + return KF_ARG_PTR_TO_LIST_NODE; + + if ((base_type(reg->type) == PTR_TO_BTF_ID || reg2btf_ids[base_type(reg->type)])) { + if (!btf_type_is_struct(ref_t)) { + verbose(env, "kernel function %s args#%d pointer type %s %s is not supported\n", + meta->func_name, argno, btf_type_str(ref_t), ref_tname); + return -EINVAL; + } + return KF_ARG_PTR_TO_BTF_ID; + } + + if (argno + 1 < nargs && is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], ®s[regno + 1])) + arg_mem_size = true; + + /* This is the catch all argument type of register types supported by + * check_helper_mem_access. However, we only allow when argument type is + * pointer to scalar, or struct composed (recursively) of scalars. When + * arg_mem_size is true, the pointer can be void *. + */ + if (!btf_type_is_scalar(ref_t) && !__btf_type_is_scalar_struct(env, meta->btf, ref_t, 0) && + (arg_mem_size ? !btf_type_is_void(ref_t) : 1)) { + verbose(env, "arg#%d pointer type %s %s must point to %sscalar, or struct with scalar\n", + argno, btf_type_str(ref_t), ref_tname, arg_mem_size ? "void, " : ""); + return -EINVAL; + } + return arg_mem_size ? KF_ARG_PTR_TO_MEM_SIZE : KF_ARG_PTR_TO_MEM; +} + +static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + const struct btf_type *ref_t, + const char *ref_tname, u32 ref_id, + struct bpf_kfunc_call_arg_meta *meta, + int argno) +{ + const struct btf_type *reg_ref_t; + bool strict_type_match = false; + const struct btf *reg_btf; + const char *reg_ref_tname; + u32 reg_ref_id; + + if (reg->type == PTR_TO_BTF_ID) { + reg_btf = reg->btf; + reg_ref_id = reg->btf_id; + } else { + reg_btf = btf_vmlinux; + reg_ref_id = *reg2btf_ids[base_type(reg->type)]; + } + + if (is_kfunc_trusted_args(meta) || (is_kfunc_release(meta) && reg->ref_obj_id)) + strict_type_match = true; + + reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id, ®_ref_id); + reg_ref_tname = btf_name_by_offset(reg_btf, reg_ref_t->name_off); + if (!btf_struct_ids_match(&env->log, reg_btf, reg_ref_id, reg->off, meta->btf, ref_id, strict_type_match)) { + verbose(env, "kernel function %s args#%d expected pointer to %s %s but R%d has a pointer to %s %s\n", + meta->func_name, argno, btf_type_str(ref_t), ref_tname, argno + 1, + btf_type_str(reg_ref_t), reg_ref_tname); + return -EINVAL; + } + return 0; +} + +static int process_kf_arg_ptr_to_kptr(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + const struct btf_type *ref_t, + const char *ref_tname, + struct bpf_kfunc_call_arg_meta *meta, + int argno) +{ + struct btf_field *kptr_field; + + /* check_func_arg_reg_off allows var_off for + * PTR_TO_MAP_VALUE, but we need fixed offset to find + * off_desc. + */ + if (!tnum_is_const(reg->var_off)) { + verbose(env, "arg#0 must have constant offset\n"); + return -EINVAL; + } + + kptr_field = btf_record_find(reg->map_ptr->record, reg->off + reg->var_off.value, BPF_KPTR); + if (!kptr_field || kptr_field->type != BPF_KPTR_REF) { + verbose(env, "arg#0 no referenced kptr at map value offset=%llu\n", + reg->off + reg->var_off.value); + return -EINVAL; + } + + if (!btf_struct_ids_match(&env->log, meta->btf, ref_t->type, 0, kptr_field->kptr.btf, + kptr_field->kptr.btf_id, true)) { + verbose(env, "kernel function %s args#%d expected pointer to %s %s\n", + meta->func_name, argno, btf_type_str(ref_t), ref_tname); + return -EINVAL; + } + return 0; +} + +static int ref_set_release_on_unlock(struct bpf_verifier_env *env, u32 ref_obj_id) +{ + struct bpf_func_state *state = cur_func(env); + struct bpf_reg_state *reg; + int i; + + /* bpf_spin_lock only allows calling list_push and list_pop, no BPF + * subprogs, no global functions. This means that the references would + * not be released inside the critical section but they may be added to + * the reference state, and the acquired_refs are never copied out for a + * different frame as BPF to BPF calls don't work in bpf_spin_lock + * critical sections. + */ + if (!ref_obj_id) { + verbose(env, "verifier internal error: ref_obj_id is zero for release_on_unlock\n"); + return -EFAULT; + } + for (i = 0; i < state->acquired_refs; i++) { + if (state->refs[i].id == ref_obj_id) { + if (state->refs[i].release_on_unlock) { + verbose(env, "verifier internal error: expected false release_on_unlock"); + return -EFAULT; + } + state->refs[i].release_on_unlock = true; + /* Now mark everyone sharing same ref_obj_id as untrusted */ + bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ + if (reg->ref_obj_id == ref_obj_id) + reg->type |= PTR_UNTRUSTED; + })); + return 0; + } + } + verbose(env, "verifier internal error: ref state missing for ref_obj_id\n"); + return -EFAULT; +} + +/* Implementation details: + * + * Each register points to some region of memory, which we define as an + * allocation. Each allocation may embed a bpf_spin_lock which protects any + * special BPF objects (bpf_list_head, bpf_rb_root, etc.) part of the same + * allocation. The lock and the data it protects are colocated in the same + * memory region. + * + * Hence, everytime a register holds a pointer value pointing to such + * allocation, the verifier preserves a unique reg->id for it. + * + * The verifier remembers the lock 'ptr' and the lock 'id' whenever + * bpf_spin_lock is called. + * + * To enable this, lock state in the verifier captures two values: + * active_lock.ptr = Register's type specific pointer + * active_lock.id = A unique ID for each register pointer value + * + * Currently, PTR_TO_MAP_VALUE and PTR_TO_BTF_ID | MEM_ALLOC are the two + * supported register types. + * + * The active_lock.ptr in case of map values is the reg->map_ptr, and in case of + * allocated objects is the reg->btf pointer. + * + * The active_lock.id is non-unique for maps supporting direct_value_addr, as we + * can establish the provenance of the map value statically for each distinct + * lookup into such maps. They always contain a single map value hence unique + * IDs for each pseudo load pessimizes the algorithm and rejects valid programs. + * + * So, in case of global variables, they use array maps with max_entries = 1, + * hence their active_lock.ptr becomes map_ptr and id = 0 (since they all point + * into the same map value as max_entries is 1, as described above). + * + * In case of inner map lookups, the inner map pointer has same map_ptr as the + * outer map pointer (in verifier context), but each lookup into an inner map + * assigns a fresh reg->id to the lookup, so while lookups into distinct inner + * maps from the same outer map share the same map_ptr as active_lock.ptr, they + * will get different reg->id assigned to each lookup, hence different + * active_lock.id. + * + * In case of allocated objects, active_lock.ptr is the reg->btf, and the + * reg->id is a unique ID preserved after the NULL pointer check on the pointer + * returned from bpf_obj_new. Each allocation receives a new reg->id. + */ +static int check_reg_allocation_locked(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + void *ptr; + u32 id; + + switch ((int)reg->type) { + case PTR_TO_MAP_VALUE: + ptr = reg->map_ptr; + break; + case PTR_TO_BTF_ID | MEM_ALLOC: + ptr = reg->btf; + break; + default: + verbose(env, "verifier internal error: unknown reg type for lock check\n"); + return -EFAULT; + } + id = reg->id; + + if (!env->cur_state->active_lock.ptr) + return -EINVAL; + if (env->cur_state->active_lock.ptr != ptr || + env->cur_state->active_lock.id != id) { + verbose(env, "held lock and object are not in the same allocation\n"); + return -EINVAL; + } + return 0; +} + +static bool is_bpf_list_api_kfunc(u32 btf_id) +{ + return btf_id == special_kfunc_list[KF_bpf_list_push_front] || + btf_id == special_kfunc_list[KF_bpf_list_push_back] || + btf_id == special_kfunc_list[KF_bpf_list_pop_front] || + btf_id == special_kfunc_list[KF_bpf_list_pop_back]; +} + +static int process_kf_arg_ptr_to_list_head(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, u32 regno, + struct bpf_kfunc_call_arg_meta *meta) +{ + struct btf_field *field; + struct btf_record *rec; + u32 list_head_off; + + if (meta->btf != btf_vmlinux || !is_bpf_list_api_kfunc(meta->func_id)) { + verbose(env, "verifier internal error: bpf_list_head argument for unknown kfunc\n"); + return -EFAULT; + } + + if (!tnum_is_const(reg->var_off)) { + verbose(env, + "R%d doesn't have constant offset. bpf_list_head has to be at the constant offset\n", + regno); + return -EINVAL; + } + + rec = reg_btf_record(reg); + list_head_off = reg->off + reg->var_off.value; + field = btf_record_find(rec, list_head_off, BPF_LIST_HEAD); + if (!field) { + verbose(env, "bpf_list_head not found at offset=%u\n", list_head_off); + return -EINVAL; + } + + /* All functions require bpf_list_head to be protected using a bpf_spin_lock */ + if (check_reg_allocation_locked(env, reg)) { + verbose(env, "bpf_spin_lock at off=%d must be held for bpf_list_head\n", + rec->spin_lock_off); + return -EINVAL; + } + + if (meta->arg_list_head.field) { + verbose(env, "verifier internal error: repeating bpf_list_head arg\n"); + return -EFAULT; + } + meta->arg_list_head.field = field; + return 0; +} + +static int process_kf_arg_ptr_to_list_node(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, u32 regno, + struct bpf_kfunc_call_arg_meta *meta) +{ + const struct btf_type *et, *t; + struct btf_field *field; + struct btf_record *rec; + u32 list_node_off; + + if (meta->btf != btf_vmlinux || + (meta->func_id != special_kfunc_list[KF_bpf_list_push_front] && + meta->func_id != special_kfunc_list[KF_bpf_list_push_back])) { + verbose(env, "verifier internal error: bpf_list_node argument for unknown kfunc\n"); + return -EFAULT; + } + + if (!tnum_is_const(reg->var_off)) { + verbose(env, + "R%d doesn't have constant offset. bpf_list_node has to be at the constant offset\n", + regno); + return -EINVAL; + } + + rec = reg_btf_record(reg); + list_node_off = reg->off + reg->var_off.value; + field = btf_record_find(rec, list_node_off, BPF_LIST_NODE); + if (!field || field->offset != list_node_off) { + verbose(env, "bpf_list_node not found at offset=%u\n", list_node_off); + return -EINVAL; + } + + field = meta->arg_list_head.field; + + et = btf_type_by_id(field->list_head.btf, field->list_head.value_btf_id); + t = btf_type_by_id(reg->btf, reg->btf_id); + if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, 0, field->list_head.btf, + field->list_head.value_btf_id, true)) { + verbose(env, "operation on bpf_list_head expects arg#1 bpf_list_node at offset=%d " + "in struct %s, but arg is at offset=%d in struct %s\n", + field->list_head.node_offset, btf_name_by_offset(field->list_head.btf, et->name_off), + list_node_off, btf_name_by_offset(reg->btf, t->name_off)); + return -EINVAL; + } + + if (list_node_off != field->list_head.node_offset) { + verbose(env, "arg#1 offset=%d, but expected bpf_list_node at offset=%d in struct %s\n", + list_node_off, field->list_head.node_offset, + btf_name_by_offset(field->list_head.btf, et->name_off)); + return -EINVAL; + } + /* Set arg#1 for expiration after unlock */ + return ref_set_release_on_unlock(env, reg->ref_obj_id); +} + +static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta) +{ + const char *func_name = meta->func_name, *ref_tname; + const struct btf *btf = meta->btf; + const struct btf_param *args; + u32 i, nargs; + int ret; + + args = (const struct btf_param *)(meta->func_proto + 1); + nargs = btf_type_vlen(meta->func_proto); + if (nargs > MAX_BPF_FUNC_REG_ARGS) { + verbose(env, "Function %s has %d > %d args\n", func_name, nargs, + MAX_BPF_FUNC_REG_ARGS); + return -EINVAL; + } + + /* Check that BTF function arguments match actual types that the + * verifier sees. + */ + for (i = 0; i < nargs; i++) { + struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[i + 1]; + const struct btf_type *t, *ref_t, *resolve_ret; + enum bpf_arg_type arg_type = ARG_DONTCARE; + u32 regno = i + 1, ref_id, type_size; + bool is_ret_buf_sz = false; + int kf_arg_type; + + t = btf_type_skip_modifiers(btf, args[i].type, NULL); + + if (is_kfunc_arg_ignore(btf, &args[i])) + continue; + + if (btf_type_is_scalar(t)) { + if (reg->type != SCALAR_VALUE) { + verbose(env, "R%d is not a scalar\n", regno); + return -EINVAL; + } + + if (is_kfunc_arg_constant(meta->btf, &args[i])) { + if (meta->arg_constant.found) { + verbose(env, "verifier internal error: only one constant argument permitted\n"); + return -EFAULT; + } + if (!tnum_is_const(reg->var_off)) { + verbose(env, "R%d must be a known constant\n", regno); + return -EINVAL; + } + ret = mark_chain_precision(env, regno); + if (ret < 0) + return ret; + meta->arg_constant.found = true; + meta->arg_constant.value = reg->var_off.value; + } else if (is_kfunc_arg_scalar_with_name(btf, &args[i], "rdonly_buf_size")) { + meta->r0_rdonly = true; + is_ret_buf_sz = true; + } else if (is_kfunc_arg_scalar_with_name(btf, &args[i], "rdwr_buf_size")) { + is_ret_buf_sz = true; + } + + if (is_ret_buf_sz) { + if (meta->r0_size) { + verbose(env, "2 or more rdonly/rdwr_buf_size parameters for kfunc"); + return -EINVAL; + } + + if (!tnum_is_const(reg->var_off)) { + verbose(env, "R%d is not a const\n", regno); + return -EINVAL; + } + + meta->r0_size = reg->var_off.value; + ret = mark_chain_precision(env, regno); + if (ret) + return ret; + } + continue; + } + + if (!btf_type_is_ptr(t)) { + verbose(env, "Unrecognized arg#%d type %s\n", i, btf_type_str(t)); + return -EINVAL; + } + + if (reg->ref_obj_id) { + if (is_kfunc_release(meta) && meta->ref_obj_id) { + verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", + regno, reg->ref_obj_id, + meta->ref_obj_id); + return -EFAULT; + } + meta->ref_obj_id = reg->ref_obj_id; + if (is_kfunc_release(meta)) + meta->release_regno = regno; + } + + ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id); + ref_tname = btf_name_by_offset(btf, ref_t->name_off); + + kf_arg_type = get_kfunc_ptr_arg_type(env, meta, t, ref_t, ref_tname, args, i, nargs); + if (kf_arg_type < 0) + return kf_arg_type; + + switch (kf_arg_type) { + case KF_ARG_PTR_TO_ALLOC_BTF_ID: + case KF_ARG_PTR_TO_BTF_ID: + if (!is_kfunc_trusted_args(meta)) + break; + if (!reg->ref_obj_id) { + verbose(env, "R%d must be referenced\n", regno); + return -EINVAL; + } + fallthrough; + case KF_ARG_PTR_TO_CTX: + /* Trusted arguments have the same offset checks as release arguments */ + arg_type |= OBJ_RELEASE; + break; + case KF_ARG_PTR_TO_KPTR: + case KF_ARG_PTR_TO_DYNPTR: + case KF_ARG_PTR_TO_LIST_HEAD: + case KF_ARG_PTR_TO_LIST_NODE: + case KF_ARG_PTR_TO_MEM: + case KF_ARG_PTR_TO_MEM_SIZE: + /* Trusted by default */ + break; + default: + WARN_ON_ONCE(1); + return -EFAULT; + } + + if (is_kfunc_release(meta) && reg->ref_obj_id) + arg_type |= OBJ_RELEASE; + ret = check_func_arg_reg_off(env, reg, regno, arg_type); + if (ret < 0) + return ret; + + switch (kf_arg_type) { + case KF_ARG_PTR_TO_CTX: + if (reg->type != PTR_TO_CTX) { + verbose(env, "arg#%d expected pointer to ctx, but got %s\n", i, btf_type_str(t)); + return -EINVAL; + } + break; + case KF_ARG_PTR_TO_ALLOC_BTF_ID: + if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { + verbose(env, "arg#%d expected pointer to allocated object\n", i); + return -EINVAL; + } + if (!reg->ref_obj_id) { + verbose(env, "allocated object must be referenced\n"); + return -EINVAL; + } + if (meta->btf == btf_vmlinux && + meta->func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) { + meta->arg_obj_drop.btf = reg->btf; + meta->arg_obj_drop.btf_id = reg->btf_id; + } + break; + case KF_ARG_PTR_TO_KPTR: + if (reg->type != PTR_TO_MAP_VALUE) { + verbose(env, "arg#0 expected pointer to map value\n"); + return -EINVAL; + } + ret = process_kf_arg_ptr_to_kptr(env, reg, ref_t, ref_tname, meta, i); + if (ret < 0) + return ret; + break; + case KF_ARG_PTR_TO_DYNPTR: + if (reg->type != PTR_TO_STACK) { + verbose(env, "arg#%d expected pointer to stack\n", i); + return -EINVAL; + } + + if (!is_dynptr_reg_valid_init(env, reg)) { + verbose(env, "arg#%d pointer type %s %s must be valid and initialized\n", + i, btf_type_str(ref_t), ref_tname); + return -EINVAL; + } + + if (!is_dynptr_type_expected(env, reg, ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL)) { + verbose(env, "arg#%d pointer type %s %s points to unsupported dynamic pointer type\n", + i, btf_type_str(ref_t), ref_tname); + return -EINVAL; + } + break; + case KF_ARG_PTR_TO_LIST_HEAD: + if (reg->type != PTR_TO_MAP_VALUE && + reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { + verbose(env, "arg#%d expected pointer to map value or allocated object\n", i); + return -EINVAL; + } + if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC) && !reg->ref_obj_id) { + verbose(env, "allocated object must be referenced\n"); + return -EINVAL; + } + ret = process_kf_arg_ptr_to_list_head(env, reg, regno, meta); + if (ret < 0) + return ret; + break; + case KF_ARG_PTR_TO_LIST_NODE: + if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { + verbose(env, "arg#%d expected pointer to allocated object\n", i); + return -EINVAL; + } + if (!reg->ref_obj_id) { + verbose(env, "allocated object must be referenced\n"); + return -EINVAL; + } + ret = process_kf_arg_ptr_to_list_node(env, reg, regno, meta); + if (ret < 0) + return ret; + break; + case KF_ARG_PTR_TO_BTF_ID: + /* Only base_type is checked, further checks are done here */ + if (reg->type != PTR_TO_BTF_ID && + (!reg2btf_ids[base_type(reg->type)] || type_flag(reg->type))) { + verbose(env, "arg#%d expected pointer to btf or socket\n", i); + return -EINVAL; + } + ret = process_kf_arg_ptr_to_btf_id(env, reg, ref_t, ref_tname, ref_id, meta, i); + if (ret < 0) + return ret; + break; + case KF_ARG_PTR_TO_MEM: + resolve_ret = btf_resolve_size(btf, ref_t, &type_size); + if (IS_ERR(resolve_ret)) { + verbose(env, "arg#%d reference type('%s %s') size cannot be determined: %ld\n", + i, btf_type_str(ref_t), ref_tname, PTR_ERR(resolve_ret)); + return -EINVAL; + } + ret = check_mem_reg(env, reg, regno, type_size); + if (ret < 0) + return ret; + break; + case KF_ARG_PTR_TO_MEM_SIZE: + ret = check_kfunc_mem_size_reg(env, ®s[regno + 1], regno + 1); + if (ret < 0) { + verbose(env, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", i, i + 1); + return ret; + } + /* Skip next '__sz' argument */ + i++; + break; + } + } + + if (is_kfunc_release(meta) && !meta->release_regno) { + verbose(env, "release kernel function %s expects refcounted PTR_TO_BTF_ID\n", + func_name); + return -EINVAL; + } + + return 0; +} + static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx_p) { const struct btf_type *t, *func, *func_proto, *ptr_type; struct bpf_reg_state *regs = cur_regs(env); - struct bpf_kfunc_arg_meta meta = { 0 }; const char *func_name, *ptr_type_name; + struct bpf_kfunc_call_arg_meta meta; u32 i, nargs, func_id, ptr_type_id; int err, insn_idx = *insn_idx_p; const struct btf_param *args; struct btf *desc_btf; u32 *kfunc_flags; - bool acq; /* skip for now, but return error when we find this in fixup_kfunc_call */ if (!insn->imm) @@ -7828,24 +8778,34 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, func_name); return -EACCES; } - if (*kfunc_flags & KF_DESTRUCTIVE && !capable(CAP_SYS_BOOT)) { - verbose(env, "destructive kfunc calls require CAP_SYS_BOOT capabilities\n"); + + /* Prepare kfunc call metadata */ + memset(&meta, 0, sizeof(meta)); + meta.btf = desc_btf; + meta.func_id = func_id; + meta.kfunc_flags = *kfunc_flags; + meta.func_proto = func_proto; + meta.func_name = func_name; + + if (is_kfunc_destructive(&meta) && !capable(CAP_SYS_BOOT)) { + verbose(env, "destructive kfunc calls require CAP_SYS_BOOT capability\n"); return -EACCES; } - acq = *kfunc_flags & KF_ACQUIRE; - - meta.flags = *kfunc_flags; + if (is_kfunc_sleepable(&meta) && !env->prog->aux->sleepable) { + verbose(env, "program must be sleepable to call sleepable kfunc %s\n", func_name); + return -EACCES; + } /* Check the arguments */ - err = btf_check_kfunc_arg_match(env, desc_btf, func_id, regs, &meta); + err = check_kfunc_args(env, &meta); if (err < 0) return err; /* In case of release function, we get register number of refcounted - * PTR_TO_BTF_ID back from btf_check_kfunc_arg_match, do the release now + * PTR_TO_BTF_ID in bpf_kfunc_arg_meta, do the release now. */ - if (err) { - err = release_reference(env, regs[err].ref_obj_id); + if (meta.release_regno) { + err = release_reference(env, regs[meta.release_regno].ref_obj_id); if (err) { verbose(env, "kfunc %s#%d reference has not been acquired before\n", func_name, func_id); @@ -7859,18 +8819,73 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, /* Check return type */ t = btf_type_skip_modifiers(desc_btf, func_proto->type, NULL); - if (acq && !btf_type_is_struct_ptr(desc_btf, t)) { - verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n"); - return -EINVAL; + if (is_kfunc_acquire(&meta) && !btf_type_is_struct_ptr(meta.btf, t)) { + /* Only exception is bpf_obj_new_impl */ + if (meta.btf != btf_vmlinux || meta.func_id != special_kfunc_list[KF_bpf_obj_new_impl]) { + verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n"); + return -EINVAL; + } } if (btf_type_is_scalar(t)) { mark_reg_unknown(env, regs, BPF_REG_0); mark_btf_func_reg_size(env, BPF_REG_0, t->size); } else if (btf_type_is_ptr(t)) { - ptr_type = btf_type_skip_modifiers(desc_btf, t->type, - &ptr_type_id); - if (!btf_type_is_struct(ptr_type)) { + ptr_type = btf_type_skip_modifiers(desc_btf, t->type, &ptr_type_id); + + if (meta.btf == btf_vmlinux && btf_id_set_contains(&special_kfunc_set, meta.func_id)) { + if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl]) { + const struct btf_type *ret_t; + struct btf *ret_btf; + u32 ret_btf_id; + + if (((u64)(u32)meta.arg_constant.value) != meta.arg_constant.value) { + verbose(env, "local type ID argument must be in range [0, U32_MAX]\n"); + return -EINVAL; + } + + ret_btf = env->prog->aux->btf; + ret_btf_id = meta.arg_constant.value; + + /* This may be NULL due to user not supplying a BTF */ + if (!ret_btf) { + verbose(env, "bpf_obj_new requires prog BTF\n"); + return -EINVAL; + } + + ret_t = btf_type_by_id(ret_btf, ret_btf_id); + if (!ret_t || !__btf_type_is_struct(ret_t)) { + verbose(env, "bpf_obj_new type ID argument must be of a struct\n"); + return -EINVAL; + } + + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC; + regs[BPF_REG_0].btf = ret_btf; + regs[BPF_REG_0].btf_id = ret_btf_id; + + env->insn_aux_data[insn_idx].obj_new_size = ret_t->size; + env->insn_aux_data[insn_idx].kptr_struct_meta = + btf_find_struct_meta(ret_btf, ret_btf_id); + } else if (meta.func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) { + env->insn_aux_data[insn_idx].kptr_struct_meta = + btf_find_struct_meta(meta.arg_obj_drop.btf, + meta.arg_obj_drop.btf_id); + } else if (meta.func_id == special_kfunc_list[KF_bpf_list_pop_front] || + meta.func_id == special_kfunc_list[KF_bpf_list_pop_back]) { + struct btf_field *field = meta.arg_list_head.field; + + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC; + regs[BPF_REG_0].btf = field->list_head.btf; + regs[BPF_REG_0].btf_id = field->list_head.value_btf_id; + regs[BPF_REG_0].off = field->list_head.node_offset; + } else { + verbose(env, "kernel function %s unhandled dynamic return type\n", + meta.func_name); + return -EFAULT; + } + } else if (!__btf_type_is_struct(ptr_type)) { if (!meta.r0_size) { ptr_type_name = btf_name_by_offset(desc_btf, ptr_type->name_off); @@ -7898,20 +8913,24 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, regs[BPF_REG_0].type = PTR_TO_BTF_ID; regs[BPF_REG_0].btf_id = ptr_type_id; } - if (*kfunc_flags & KF_RET_NULL) { + + if (is_kfunc_ret_null(&meta)) { regs[BPF_REG_0].type |= PTR_MAYBE_NULL; /* For mark_ptr_or_null_reg, see 93c230e3f5bd6 */ regs[BPF_REG_0].id = ++env->id_gen; } mark_btf_func_reg_size(env, BPF_REG_0, sizeof(void *)); - if (acq) { + if (is_kfunc_acquire(&meta)) { int id = acquire_reference_state(env, insn_idx); if (id < 0) return id; - regs[BPF_REG_0].id = id; + if (is_kfunc_ret_null(&meta)) + regs[BPF_REG_0].id = id; regs[BPF_REG_0].ref_obj_id = id; } + if (reg_may_point_to_spin_lock(®s[BPF_REG_0]) && !regs[BPF_REG_0].id) + regs[BPF_REG_0].id = ++env->id_gen; } /* else { add_kfunc_call() ensures it is btf_type_is_void(t) } */ nargs = btf_type_vlen(func_proto); @@ -10084,16 +11103,19 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state, { if (type_may_be_null(reg->type) && reg->id == id && !WARN_ON_ONCE(!reg->id)) { - if (WARN_ON_ONCE(reg->smin_value || reg->smax_value || - !tnum_equals_const(reg->var_off, 0) || - reg->off)) { - /* Old offset (both fixed and variable parts) should - * have been known-zero, because we don't allow pointer - * arithmetic on pointers that might be NULL. If we - * see this happening, don't convert the register. - */ + /* Old offset (both fixed and variable parts) should have been + * known-zero, because we don't allow pointer arithmetic on + * pointers that might be NULL. If we see this happening, don't + * convert the register. + * + * But in some cases, some helpers that return local kptrs + * advance offset for the returned pointer. In those cases, it + * is fine to expect to see reg->off. + */ + if (WARN_ON_ONCE(reg->smin_value || reg->smax_value || !tnum_equals_const(reg->var_off, 0))) + return; + if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC | PTR_MAYBE_NULL) && WARN_ON_ONCE(reg->off)) return; - } if (is_null) { reg->type = SCALAR_VALUE; /* We don't need id and ref_obj_id from this point @@ -10563,8 +11585,8 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) { dst_reg->type = PTR_TO_MAP_VALUE; dst_reg->off = aux->map_off; - if (btf_record_has_field(map->record, BPF_SPIN_LOCK)) - dst_reg->id = ++env->id_gen; + WARN_ON_ONCE(map->max_entries != 1); + /* We want reg->id to be same (0) as map_value is not distinct */ } else if (insn->src_reg == BPF_PSEUDO_MAP_FD || insn->src_reg == BPF_PSEUDO_MAP_IDX) { dst_reg->type = CONST_PTR_TO_MAP; @@ -10642,7 +11664,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } - if (env->cur_state->active_spin_lock) { + if (env->cur_state->active_lock.ptr) { verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_spin_lock-ed region\n"); return -EINVAL; } @@ -11908,7 +12930,8 @@ static bool states_equal(struct bpf_verifier_env *env, if (old->speculative && !cur->speculative) return false; - if (old->active_spin_lock != cur->active_spin_lock) + if (old->active_lock.ptr != cur->active_lock.ptr || + old->active_lock.id != cur->active_lock.id) return false; /* for states to be equal callsites have to be the same @@ -12553,11 +13576,14 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } - if (env->cur_state->active_spin_lock && - (insn->src_reg == BPF_PSEUDO_CALL || - insn->imm != BPF_FUNC_spin_unlock)) { - verbose(env, "function calls are not allowed while holding a lock\n"); - return -EINVAL; + 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_list_api_kfunc(insn->imm)))) { + verbose(env, "function calls are not allowed while holding a lock\n"); + return -EINVAL; + } } if (insn->src_reg == BPF_PSEUDO_CALL) err = check_func_call(env, insn, &env->insn_idx); @@ -12590,7 +13616,7 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } - if (env->cur_state->active_spin_lock) { + if (env->cur_state->active_lock.ptr) { verbose(env, "bpf_spin_unlock is missing\n"); return -EINVAL; } @@ -13690,6 +14716,13 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) break; case PTR_TO_BTF_ID: case PTR_TO_BTF_ID | PTR_UNTRUSTED: + /* PTR_TO_BTF_ID | MEM_ALLOC always has a valid lifetime, unlike + * PTR_TO_BTF_ID, and an active ref_obj_id, but the same cannot + * be said once it is marked PTR_UNTRUSTED, hence we must handle + * any faults for loads into such types. BPF_WRITE is disallowed + * for this case. + */ + case PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED: if (type == BPF_READ) { insn->code = BPF_LDX | BPF_PROBE_MEM | BPF_SIZE((insn)->code); @@ -14055,8 +15088,8 @@ static int fixup_call_args(struct bpf_verifier_env *env) return err; } -static int fixup_kfunc_call(struct bpf_verifier_env *env, - struct bpf_insn *insn) +static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, + struct bpf_insn *insn_buf, int insn_idx, int *cnt) { const struct bpf_kfunc_desc *desc; @@ -14075,8 +15108,29 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, return -EFAULT; } + *cnt = 0; insn->imm = desc->imm; - + if (insn->off) + return 0; + if (desc->func_id == special_kfunc_list[KF_bpf_obj_new_impl]) { + struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta; + struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) }; + u64 obj_new_size = env->insn_aux_data[insn_idx].obj_new_size; + + insn_buf[0] = BPF_MOV64_IMM(BPF_REG_1, obj_new_size); + insn_buf[1] = addr[0]; + insn_buf[2] = addr[1]; + insn_buf[3] = *insn; + *cnt = 4; + } else if (desc->func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) { + struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta; + struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) }; + + insn_buf[0] = addr[0]; + insn_buf[1] = addr[1]; + insn_buf[2] = *insn; + *cnt = 3; + } return 0; } @@ -14218,9 +15272,19 @@ static int do_misc_fixups(struct bpf_verifier_env *env) if (insn->src_reg == BPF_PSEUDO_CALL) continue; if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { - ret = fixup_kfunc_call(env, insn); + ret = fixup_kfunc_call(env, insn, insn_buf, i + delta, &cnt); if (ret) return ret; + if (cnt == 0) + continue; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; continue; } diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64 index 09416d5d2e33..affc5aebbf0f 100644 --- a/tools/testing/selftests/bpf/DENYLIST.aarch64 +++ b/tools/testing/selftests/bpf/DENYLIST.aarch64 @@ -38,6 +38,7 @@ kprobe_multi_test/skel_api # kprobe_multi__attach unexpect ksyms_module/libbpf # 'bpf_testmod_ksym_percpu': not found in kernel BTF ksyms_module/lskel # test_ksyms_module_lskel__open_and_load unexpected error: -2 libbpf_get_fd_by_id_opts # test_libbpf_get_fd_by_id_opts__attach unexpected error: -524 (errno 524) +linked_list lookup_key # test_lookup_key__attach unexpected error: -524 (errno 524) lru_bug # lru_bug__attach unexpected error: -524 (errno 524) modify_return # modify_return__attach failed unexpected error: -524 (errno 524) diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x index be4e3d47ea3e..072243af93b0 100644 --- a/tools/testing/selftests/bpf/DENYLIST.s390x +++ b/tools/testing/selftests/bpf/DENYLIST.s390x @@ -33,6 +33,7 @@ ksyms_module # test_ksyms_module__open_and_load unex ksyms_module_libbpf # JIT does not support calling kernel function (kfunc) ksyms_module_lskel # test_ksyms_module_lskel__open_and_load unexpected error: -9 (?) libbpf_get_fd_by_id_opts # failed to attach: ERROR: strerror_r(-524)=22 (trampoline) +linked_list # JIT does not support calling kernel function (kfunc) lookup_key # JIT does not support calling kernel function (kfunc) lru_bug # prog 'printk': failed to auto-attach: -524 map_kptr # failed to open_and_load program: -524 (trampoline) diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h new file mode 100644 index 000000000000..424f7bbbfe9b --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_experimental.h @@ -0,0 +1,68 @@ +#ifndef __BPF_EXPERIMENTAL__ +#define __BPF_EXPERIMENTAL__ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +#define __contains(name, node) __attribute__((btf_decl_tag("contains:" #name ":" #node))) + +/* Description + * Allocates an object of the type represented by 'local_type_id' in + * program BTF. User may use the bpf_core_type_id_local macro to pass the + * type ID of a struct in program BTF. + * + * The 'local_type_id' parameter must be a known constant. + * The 'meta' parameter is a hidden argument that is ignored. + * Returns + * A pointer to an object of the type corresponding to the passed in + * 'local_type_id', or NULL on failure. + */ +extern void *bpf_obj_new_impl(__u64 local_type_id, void *meta) __ksym; + +/* Convenience macro to wrap over bpf_obj_new_impl */ +#define bpf_obj_new(type) ((type *)bpf_obj_new_impl(bpf_core_type_id_local(type), NULL)) + +/* Description + * Free an allocated object. All fields of the object that require + * destruction will be destructed before the storage is freed. + * + * The 'meta' parameter is a hidden argument that is ignored. + * Returns + * Void. + */ +extern void bpf_obj_drop_impl(void *kptr, void *meta) __ksym; + +/* Convenience macro to wrap over bpf_obj_drop_impl */ +#define bpf_obj_drop(kptr) bpf_obj_drop_impl(kptr, NULL) + +/* Description + * Add a new entry to the beginning of the BPF linked list. + * Returns + * Void. + */ +extern void bpf_list_push_front(struct bpf_list_head *head, struct bpf_list_node *node) __ksym; + +/* Description + * Add a new entry to the end of the BPF linked list. + * Returns + * Void. + */ +extern void bpf_list_push_back(struct bpf_list_head *head, struct bpf_list_node *node) __ksym; + +/* Description + * Remove the entry at the beginning of the BPF linked list. + * Returns + * Pointer to bpf_list_node of deleted entry, or NULL if list is empty. + */ +extern struct bpf_list_node *bpf_list_pop_front(struct bpf_list_head *head) __ksym; + +/* Description + * Remove the entry at the end of the BPF linked list. + * Returns + * Pointer to bpf_list_node of deleted entry, or NULL if list is empty. + */ +extern struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head) __ksym; + +#endif diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c b/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c index c210657d4d0a..55d641c1f126 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c @@ -22,7 +22,7 @@ static struct { "arg#0 pointer type STRUCT bpf_dynptr_kern points to unsupported dynamic pointer type", 0}, {"not_valid_dynptr", "arg#0 pointer type STRUCT bpf_dynptr_kern must be valid and initialized", 0}, - {"not_ptr_to_stack", "arg#0 pointer type STRUCT bpf_dynptr_kern not to stack", 0}, + {"not_ptr_to_stack", "arg#0 expected pointer to stack", 0}, {"dynptr_data_null", NULL, -EBADMSG}, }; diff --git a/tools/testing/selftests/bpf/prog_tests/linked_list.c b/tools/testing/selftests/bpf/prog_tests/linked_list.c new file mode 100644 index 000000000000..6170d36fe5fc --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/linked_list.c @@ -0,0 +1,747 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <bpf/btf.h> +#include <test_btf.h> +#include <linux/btf.h> +#include <test_progs.h> +#include <network_helpers.h> + +#include "linked_list.skel.h" +#include "linked_list_fail.skel.h" + +static char log_buf[1024 * 1024]; + +static struct { + const char *prog_name; + const char *err_msg; +} linked_list_fail_tests[] = { +#define TEST(test, off) \ + { #test "_missing_lock_push_front", \ + "bpf_spin_lock at off=" #off " must be held for bpf_list_head" }, \ + { #test "_missing_lock_push_back", \ + "bpf_spin_lock at off=" #off " must be held for bpf_list_head" }, \ + { #test "_missing_lock_pop_front", \ + "bpf_spin_lock at off=" #off " must be held for bpf_list_head" }, \ + { #test "_missing_lock_pop_back", \ + "bpf_spin_lock at off=" #off " must be held for bpf_list_head" }, + TEST(kptr, 32) +/* FIXME + TEST(global, 16) +*/ + TEST(map, 0) + TEST(inner_map, 0) +#undef TEST +#define TEST(test, op) \ + { #test "_kptr_incorrect_lock_" #op, \ + "held lock and object are not in the same allocation\n" \ + "bpf_spin_lock at off=32 must be held for bpf_list_head" }, \ + { #test "_map_incorrect_lock_" #op, \ + "held lock and object are not in the same allocation\n" \ + "bpf_spin_lock at off=0 must be held for bpf_list_head" }, \ + { #test "_inner_map_incorrect_lock_" #op, \ + "held lock and object are not in the same allocation\n" \ + "bpf_spin_lock at off=0 must be held for bpf_list_head" }, + TEST(kptr, push_front) + TEST(kptr, push_back) + TEST(kptr, pop_front) + TEST(kptr, pop_back) + TEST(map, push_front) + TEST(map, push_back) + TEST(map, pop_front) + TEST(map, pop_back) + TEST(inner_map, push_front) + TEST(inner_map, push_back) + TEST(inner_map, pop_front) + TEST(inner_map, pop_back) +#undef TEST +/* FIXME + { "map_compat_kprobe", "tracing progs cannot use bpf_list_head yet" }, + { "map_compat_kretprobe", "tracing progs cannot use bpf_list_head yet" }, + { "map_compat_tp", "tracing progs cannot use bpf_list_head yet" }, + { "map_compat_perf", "tracing progs cannot use bpf_list_head yet" }, + { "map_compat_raw_tp", "tracing progs cannot use bpf_list_head yet" }, + { "map_compat_raw_tp_w", "tracing progs cannot use bpf_list_head yet" }, +*/ + { "obj_type_id_oor", "local type ID argument must be in range [0, U32_MAX]" }, + { "obj_new_no_composite", "bpf_obj_new type ID argument must be of a struct" }, + { "obj_new_no_struct", "bpf_obj_new type ID argument must be of a struct" }, + { "obj_drop_non_zero_off", "R1 must have zero offset when passed to release func" }, + { "new_null_ret", "R0 invalid mem access 'ptr_or_null_'" }, + { "obj_new_acq", "Unreleased reference id=" }, + { "use_after_drop", "invalid mem access 'scalar'" }, + { "ptr_walk_scalar", "type=scalar expected=percpu_ptr_" }, + { "direct_read_lock", "direct access to bpf_spin_lock is disallowed" }, + { "direct_write_lock", "direct access to bpf_spin_lock is disallowed" }, + { "direct_read_head", "direct access to bpf_list_head is disallowed" }, + { "direct_write_head", "direct access to bpf_list_head is disallowed" }, + { "direct_read_node", "direct access to bpf_list_node is disallowed" }, + { "direct_write_node", "direct access to bpf_list_node is disallowed" }, +/* FIXME + { "write_after_push_front", "only read is supported" }, + { "write_after_push_back", "only read is supported" }, + { "use_after_unlock_push_front", "invalid mem access 'scalar'" }, + { "use_after_unlock_push_back", "invalid mem access 'scalar'" }, + { "double_push_front", "arg#1 expected pointer to allocated object" }, + { "double_push_back", "arg#1 expected pointer to allocated object" }, + { "no_node_value_type", "bpf_list_node not found at offset=0" }, + { "incorrect_value_type", + "operation on bpf_list_head expects arg#1 bpf_list_node at offset=0 in struct foo, " + "but arg is at offset=0 in struct bar" }, + { "incorrect_node_var_off", "variable ptr_ access var_off=(0x0; 0xffffffff) disallowed" }, + { "incorrect_node_off1", "bpf_list_node not found at offset=1" }, + { "incorrect_node_off2", "arg#1 offset=40, but expected bpf_list_node at offset=0 in struct foo" }, + { "no_head_type", "bpf_list_head not found at offset=0" }, + { "incorrect_head_var_off1", "R1 doesn't have constant offset" }, + { "incorrect_head_var_off2", "variable ptr_ access var_off=(0x0; 0xffffffff) disallowed" }, +*/ + { "incorrect_head_off1", "bpf_list_head not found at offset=17" }, +/* FIXME + { "incorrect_head_off2", "bpf_list_head not found at offset=1" }, +*/ + { "pop_front_off", + "15: (bf) r1 = r6 ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=40,imm=0) " + "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=40,imm=0) refs=2,4\n" + "16: (85) call bpf_this_cpu_ptr#154\nR1 type=ptr_or_null_ expected=percpu_ptr_" }, + { "pop_back_off", + "15: (bf) r1 = r6 ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=40,imm=0) " + "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=40,imm=0) refs=2,4\n" + "16: (85) call bpf_this_cpu_ptr#154\nR1 type=ptr_or_null_ expected=percpu_ptr_" }, +}; + +static void test_linked_list_fail_prog(const char *prog_name, const char *err_msg) +{ + LIBBPF_OPTS(bpf_object_open_opts, opts, .kernel_log_buf = log_buf, + .kernel_log_size = sizeof(log_buf), + .kernel_log_level = 1); + struct linked_list_fail *skel; + struct bpf_program *prog; + int ret; + + skel = linked_list_fail__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "linked_list_fail__open_opts")) + return; + + prog = bpf_object__find_program_by_name(skel->obj, prog_name); + if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name")) + goto end; + + bpf_program__set_autoload(prog, true); + + ret = linked_list_fail__load(skel); + if (!ASSERT_ERR(ret, "linked_list_fail__load must fail")) + goto end; + + if (!ASSERT_OK_PTR(strstr(log_buf, err_msg), "expected error message")) { + fprintf(stderr, "Expected: %s\n", err_msg); + fprintf(stderr, "Verifier: %s\n", log_buf); + } + +end: + linked_list_fail__destroy(skel); +} + +static void clear_fields(struct bpf_map *map) +{ + char buf[24]; + int key = 0; + + memset(buf, 0xff, sizeof(buf)); + ASSERT_OK(bpf_map__update_elem(map, &key, sizeof(key), buf, sizeof(buf), 0), "check_and_free_fields"); +} + +enum { + TEST_ALL, + PUSH_POP, + PUSH_POP_MULT, + LIST_IN_LIST, +}; + +static void test_linked_list_success(int mode, bool leave_in_map) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + struct linked_list *skel; + int ret; + + skel = linked_list__open_and_load(); + if (!ASSERT_OK_PTR(skel, "linked_list__open_and_load")) + return; + + if (mode == LIST_IN_LIST) + goto lil; + if (mode == PUSH_POP_MULT) + goto ppm; + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.map_list_push_pop), &opts); + ASSERT_OK(ret, "map_list_push_pop"); + ASSERT_OK(opts.retval, "map_list_push_pop retval"); + if (!leave_in_map) + clear_fields(skel->maps.array_map); + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.inner_map_list_push_pop), &opts); + ASSERT_OK(ret, "inner_map_list_push_pop"); + ASSERT_OK(opts.retval, "inner_map_list_push_pop retval"); + if (!leave_in_map) + clear_fields(skel->maps.inner_map); + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.global_list_push_pop), &opts); + ASSERT_OK(ret, "global_list_push_pop"); + ASSERT_OK(opts.retval, "global_list_push_pop retval"); + /* FIXME: + if (!leave_in_map) + clear_fields(skel->maps.data_A); + */ + + if (mode == PUSH_POP) + goto end; + +ppm: + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.map_list_push_pop_multiple), &opts); + ASSERT_OK(ret, "map_list_push_pop_multiple"); + ASSERT_OK(opts.retval, "map_list_push_pop_multiple retval"); + if (!leave_in_map) + clear_fields(skel->maps.array_map); + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.inner_map_list_push_pop_multiple), &opts); + ASSERT_OK(ret, "inner_map_list_push_pop_multiple"); + ASSERT_OK(opts.retval, "inner_map_list_push_pop_multiple retval"); + if (!leave_in_map) + clear_fields(skel->maps.inner_map); + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.global_list_push_pop_multiple), &opts); + ASSERT_OK(ret, "global_list_push_pop_multiple"); + ASSERT_OK(opts.retval, "global_list_push_pop_multiple retval"); + /* FIXME: + if (!leave_in_map) + clear_fields(skel->maps.data_A); + */ + + if (mode == PUSH_POP_MULT) + goto end; + +lil: + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.map_list_in_list), &opts); + ASSERT_OK(ret, "map_list_in_list"); + ASSERT_OK(opts.retval, "map_list_in_list retval"); + if (!leave_in_map) + clear_fields(skel->maps.array_map); + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.inner_map_list_in_list), &opts); + ASSERT_OK(ret, "inner_map_list_in_list"); + ASSERT_OK(opts.retval, "inner_map_list_in_list retval"); + if (!leave_in_map) + clear_fields(skel->maps.inner_map); + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.global_list_in_list), &opts); + ASSERT_OK(ret, "global_list_in_list"); + ASSERT_OK(opts.retval, "global_list_in_list retval"); + /* FIXME: + if (!leave_in_map) + clear_fields(skel->maps.data_A); + */ +end: + linked_list__destroy(skel); +} + +#define SPIN_LOCK 2 +#define LIST_HEAD 3 +#define LIST_NODE 4 + +static struct btf *init_btf(void) +{ + int id, lid, hid, nid; + struct btf *btf; + + btf = btf__new_empty(); + if (!ASSERT_OK_PTR(btf, "btf__new_empty")) + return NULL; + id = btf__add_int(btf, "int", 4, BTF_INT_SIGNED); + if (!ASSERT_EQ(id, 1, "btf__add_int")) + goto end; + lid = btf__add_struct(btf, "bpf_spin_lock", 4); + if (!ASSERT_EQ(lid, SPIN_LOCK, "btf__add_struct bpf_spin_lock")) + goto end; + hid = btf__add_struct(btf, "bpf_list_head", 16); + if (!ASSERT_EQ(hid, LIST_HEAD, "btf__add_struct bpf_list_head")) + goto end; + nid = btf__add_struct(btf, "bpf_list_node", 16); + if (!ASSERT_EQ(nid, LIST_NODE, "btf__add_struct bpf_list_node")) + goto end; + return btf; +end: + btf__free(btf); + return NULL; +} + +static void test_btf(void) +{ + struct btf *btf = NULL; + int id, err; + + while (test__start_subtest("btf: too many locks")) { + btf = init_btf(); + if (!ASSERT_OK_PTR(btf, "init_btf")) + break; + id = btf__add_struct(btf, "foo", 24); + if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) + break; + err = btf__add_field(btf, "a", SPIN_LOCK, 0, 0); + if (!ASSERT_OK(err, "btf__add_struct foo::a")) + break; + err = btf__add_field(btf, "b", SPIN_LOCK, 32, 0); + if (!ASSERT_OK(err, "btf__add_struct foo::a")) + break; + err = btf__add_field(btf, "c", LIST_HEAD, 64, 0); + if (!ASSERT_OK(err, "btf__add_struct foo::a")) + break; + + err = btf__load_into_kernel(btf); + ASSERT_EQ(err, -E2BIG, "check btf"); + btf__free(btf); + break; + } + + while (test__start_subtest("btf: missing lock")) { + btf = init_btf(); + if (!ASSERT_OK_PTR(btf, "init_btf")) + break; + id = btf__add_struct(btf, "foo", 16); + if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) + break; + err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); + if (!ASSERT_OK(err, "btf__add_struct foo::a")) + break; + id = btf__add_decl_tag(btf, "contains:baz:a", 5, 0); + if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:baz:a")) + break; + id = btf__add_struct(btf, "baz", 16); + if (!ASSERT_EQ(id, 7, "btf__add_struct baz")) + break; + err = btf__add_field(btf, "a", LIST_NODE, 0, 0); + if (!ASSERT_OK(err, "btf__add_field baz::a")) + break; + + err = btf__load_into_kernel(btf); + ASSERT_EQ(err, -EINVAL, "check btf"); + btf__free(btf); + break; + } + + while (test__start_subtest("btf: bad offset")) { + btf = init_btf(); + if (!ASSERT_OK_PTR(btf, "init_btf")) + break; + id = btf__add_struct(btf, "foo", 36); + if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) + break; + err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); + if (!ASSERT_OK(err, "btf__add_field foo::a")) + break; + err = btf__add_field(btf, "b", LIST_NODE, 0, 0); + if (!ASSERT_OK(err, "btf__add_field foo::b")) + break; + err = btf__add_field(btf, "c", SPIN_LOCK, 0, 0); + if (!ASSERT_OK(err, "btf__add_field foo::c")) + break; + id = btf__add_decl_tag(btf, "contains:foo:b", 5, 0); + if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:foo:b")) + break; + + err = btf__load_into_kernel(btf); + ASSERT_EQ(err, -EEXIST, "check btf"); + btf__free(btf); + break; + } + + while (test__start_subtest("btf: missing contains:")) { + btf = init_btf(); + if (!ASSERT_OK_PTR(btf, "init_btf")) + break; + id = btf__add_struct(btf, "foo", 24); + if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) + break; + err = btf__add_field(btf, "a", SPIN_LOCK, 0, 0); + if (!ASSERT_OK(err, "btf__add_field foo::a")) + break; + err = btf__add_field(btf, "b", LIST_HEAD, 64, 0); + if (!ASSERT_OK(err, "btf__add_field foo::b")) + break; + + err = btf__load_into_kernel(btf); + ASSERT_EQ(err, -EINVAL, "check btf"); + btf__free(btf); + break; + } + + while (test__start_subtest("btf: missing struct")) { + btf = init_btf(); + if (!ASSERT_OK_PTR(btf, "init_btf")) + break; + id = btf__add_struct(btf, "foo", 24); + if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) + break; + err = btf__add_field(btf, "a", SPIN_LOCK, 0, 0); + if (!ASSERT_OK(err, "btf__add_field foo::a")) + break; + err = btf__add_field(btf, "b", LIST_HEAD, 64, 0); + if (!ASSERT_OK(err, "btf__add_field foo::b")) + break; + id = btf__add_decl_tag(btf, "contains:bar:bar", 5, 1); + if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:bar")) + break; + + err = btf__load_into_kernel(btf); + ASSERT_EQ(err, -ENOENT, "check btf"); + btf__free(btf); + break; + } + + while (test__start_subtest("btf: missing node")) { + btf = init_btf(); + if (!ASSERT_OK_PTR(btf, "init_btf")) + break; + id = btf__add_struct(btf, "foo", 24); + if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) + break; + err = btf__add_field(btf, "a", SPIN_LOCK, 0, 0); + if (!ASSERT_OK(err, "btf__add_field foo::a")) + break; + err = btf__add_field(btf, "b", LIST_HEAD, 64, 0); + if (!ASSERT_OK(err, "btf__add_field foo::b")) + break; + id = btf__add_decl_tag(btf, "contains:foo:c", 5, 1); + if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:foo:c")) + break; + + err = btf__load_into_kernel(btf); + btf__free(btf); + ASSERT_EQ(err, -ENOENT, "check btf"); + break; + } + + while (test__start_subtest("btf: node incorrect type")) { + btf = init_btf(); + if (!ASSERT_OK_PTR(btf, "init_btf")) + break; + id = btf__add_struct(btf, "foo", 20); + if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) + break; + err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); + if (!ASSERT_OK(err, "btf__add_field foo::a")) + break; + err = btf__add_field(btf, "b", SPIN_LOCK, 128, 0); + if (!ASSERT_OK(err, "btf__add_field foo::b")) + break; + id = btf__add_decl_tag(btf, "contains:bar:a", 5, 0); + if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:a")) + break; + id = btf__add_struct(btf, "bar", 4); + if (!ASSERT_EQ(id, 7, "btf__add_struct bar")) + break; + err = btf__add_field(btf, "a", SPIN_LOCK, 0, 0); + if (!ASSERT_OK(err, "btf__add_field bar::a")) + break; + + err = btf__load_into_kernel(btf); + ASSERT_EQ(err, -EINVAL, "check btf"); + btf__free(btf); + break; + } + + while (test__start_subtest("btf: multiple bpf_list_node with name b")) { + btf = init_btf(); + if (!ASSERT_OK_PTR(btf, "init_btf")) + break; + id = btf__add_struct(btf, "foo", 52); + if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) + break; + err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); + if (!ASSERT_OK(err, "btf__add_field foo::a")) + break; + err = btf__add_field(btf, "b", LIST_NODE, 128, 0); + if (!ASSERT_OK(err, "btf__add_field foo::b")) + break; + err = btf__add_field(btf, "b", LIST_NODE, 256, 0); + if (!ASSERT_OK(err, "btf__add_field foo::c")) + break; + err = btf__add_field(btf, "d", SPIN_LOCK, 384, 0); + if (!ASSERT_OK(err, "btf__add_field foo::d")) + break; + id = btf__add_decl_tag(btf, "contains:foo:b", 5, 0); + if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:foo:b")) + break; + + err = btf__load_into_kernel(btf); + ASSERT_EQ(err, -EINVAL, "check btf"); + btf__free(btf); + break; + } + + while (test__start_subtest("btf: owning | owned AA cycle")) { + btf = init_btf(); + if (!ASSERT_OK_PTR(btf, "init_btf")) + break; + id = btf__add_struct(btf, "foo", 36); + if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) + break; + err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); + if (!ASSERT_OK(err, "btf__add_field foo::a")) + break; + err = btf__add_field(btf, "b", LIST_NODE, 128, 0); + if (!ASSERT_OK(err, "btf__add_field foo::b")) + break; + err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + if (!ASSERT_OK(err, "btf__add_field foo::c")) + break; + id = btf__add_decl_tag(btf, "contains:foo:b", 5, 0); + if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:foo:b")) + break; + + err = btf__load_into_kernel(btf); + ASSERT_EQ(err, -ELOOP, "check btf"); + btf__free(btf); + break; + } + + while (test__start_subtest("btf: owning | owned ABA cycle")) { + btf = init_btf(); + if (!ASSERT_OK_PTR(btf, "init_btf")) + break; + id = btf__add_struct(btf, "foo", 36); + if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) + break; + err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); + if (!ASSERT_OK(err, "btf__add_field foo::a")) + break; + err = btf__add_field(btf, "b", LIST_NODE, 128, 0); + if (!ASSERT_OK(err, "btf__add_field foo::b")) + break; + err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + if (!ASSERT_OK(err, "btf__add_field foo::c")) + break; + id = btf__add_decl_tag(btf, "contains:bar:b", 5, 0); + if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:b")) + break; + id = btf__add_struct(btf, "bar", 36); + if (!ASSERT_EQ(id, 7, "btf__add_struct bar")) + break; + err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); + if (!ASSERT_OK(err, "btf__add_field bar::a")) + break; + err = btf__add_field(btf, "b", LIST_NODE, 128, 0); + if (!ASSERT_OK(err, "btf__add_field bar::b")) + break; + err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + if (!ASSERT_OK(err, "btf__add_field bar::c")) + break; + id = btf__add_decl_tag(btf, "contains:foo:b", 7, 0); + if (!ASSERT_EQ(id, 8, "btf__add_decl_tag contains:foo:b")) + break; + + err = btf__load_into_kernel(btf); + ASSERT_EQ(err, -ELOOP, "check btf"); + btf__free(btf); + break; + } + + while (test__start_subtest("btf: owning -> owned")) { + btf = init_btf(); + if (!ASSERT_OK_PTR(btf, "init_btf")) + break; + id = btf__add_struct(btf, "foo", 20); + if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) + break; + err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); + if (!ASSERT_OK(err, "btf__add_field foo::a")) + break; + err = btf__add_field(btf, "b", SPIN_LOCK, 128, 0); + if (!ASSERT_OK(err, "btf__add_field foo::b")) + break; + id = btf__add_decl_tag(btf, "contains:bar:a", 5, 0); + if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:a")) + break; + id = btf__add_struct(btf, "bar", 16); + if (!ASSERT_EQ(id, 7, "btf__add_struct bar")) + break; + err = btf__add_field(btf, "a", LIST_NODE, 0, 0); + if (!ASSERT_OK(err, "btf__add_field bar::a")) + break; + + err = btf__load_into_kernel(btf); + ASSERT_EQ(err, 0, "check btf"); + btf__free(btf); + break; + } + + while (test__start_subtest("btf: owning -> owning | owned -> owned")) { + btf = init_btf(); + if (!ASSERT_OK_PTR(btf, "init_btf")) + break; + id = btf__add_struct(btf, "foo", 20); + if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) + break; + err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); + if (!ASSERT_OK(err, "btf__add_field foo::a")) + break; + err = btf__add_field(btf, "b", SPIN_LOCK, 128, 0); + if (!ASSERT_OK(err, "btf__add_field foo::b")) + break; + id = btf__add_decl_tag(btf, "contains:bar:b", 5, 0); + if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:b")) + break; + id = btf__add_struct(btf, "bar", 36); + if (!ASSERT_EQ(id, 7, "btf__add_struct bar")) + break; + err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); + if (!ASSERT_OK(err, "btf__add_field bar::a")) + break; + err = btf__add_field(btf, "b", LIST_NODE, 128, 0); + if (!ASSERT_OK(err, "btf__add_field bar::b")) + break; + err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + if (!ASSERT_OK(err, "btf__add_field bar::c")) + break; + id = btf__add_decl_tag(btf, "contains:baz:a", 7, 0); + if (!ASSERT_EQ(id, 8, "btf__add_decl_tag contains:baz:a")) + break; + id = btf__add_struct(btf, "baz", 16); + if (!ASSERT_EQ(id, 9, "btf__add_struct baz")) + break; + err = btf__add_field(btf, "a", LIST_NODE, 0, 0); + if (!ASSERT_OK(err, "btf__add_field baz:a")) + break; + + err = btf__load_into_kernel(btf); + ASSERT_EQ(err, 0, "check btf"); + btf__free(btf); + break; + } + + while (test__start_subtest("btf: owning | owned -> owning | owned -> owned")) { + btf = init_btf(); + if (!ASSERT_OK_PTR(btf, "init_btf")) + break; + id = btf__add_struct(btf, "foo", 36); + if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) + break; + err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); + if (!ASSERT_OK(err, "btf__add_field foo::a")) + break; + err = btf__add_field(btf, "b", LIST_NODE, 128, 0); + if (!ASSERT_OK(err, "btf__add_field foo::b")) + break; + err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + if (!ASSERT_OK(err, "btf__add_field foo::c")) + break; + id = btf__add_decl_tag(btf, "contains:bar:b", 5, 0); + if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:b")) + break; + id = btf__add_struct(btf, "bar", 36); + if (!ASSERT_EQ(id, 7, "btf__add_struct bar")) + break; + err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); + if (!ASSERT_OK(err, "btf__add_field bar:a")) + break; + err = btf__add_field(btf, "b", LIST_NODE, 128, 0); + if (!ASSERT_OK(err, "btf__add_field bar:b")) + break; + err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + if (!ASSERT_OK(err, "btf__add_field bar:c")) + break; + id = btf__add_decl_tag(btf, "contains:baz:a", 7, 0); + if (!ASSERT_EQ(id, 8, "btf__add_decl_tag contains:baz:a")) + break; + id = btf__add_struct(btf, "baz", 16); + if (!ASSERT_EQ(id, 9, "btf__add_struct baz")) + break; + err = btf__add_field(btf, "a", LIST_NODE, 0, 0); + if (!ASSERT_OK(err, "btf__add_field baz:a")) + break; + + err = btf__load_into_kernel(btf); + ASSERT_EQ(err, -ELOOP, "check btf"); + btf__free(btf); + break; + } + + while (test__start_subtest("btf: owning -> owning | owned -> owning | owned -> owned")) { + btf = init_btf(); + if (!ASSERT_OK_PTR(btf, "init_btf")) + break; + id = btf__add_struct(btf, "foo", 20); + if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) + break; + err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); + if (!ASSERT_OK(err, "btf__add_field foo::a")) + break; + err = btf__add_field(btf, "b", SPIN_LOCK, 128, 0); + if (!ASSERT_OK(err, "btf__add_field foo::b")) + break; + id = btf__add_decl_tag(btf, "contains:bar:b", 5, 0); + if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:b")) + break; + id = btf__add_struct(btf, "bar", 36); + if (!ASSERT_EQ(id, 7, "btf__add_struct bar")) + break; + err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); + if (!ASSERT_OK(err, "btf__add_field bar::a")) + break; + err = btf__add_field(btf, "b", LIST_NODE, 128, 0); + if (!ASSERT_OK(err, "btf__add_field bar::b")) + break; + err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + if (!ASSERT_OK(err, "btf__add_field bar::c")) + break; + id = btf__add_decl_tag(btf, "contains:baz:b", 7, 0); + if (!ASSERT_EQ(id, 8, "btf__add_decl_tag")) + break; + id = btf__add_struct(btf, "baz", 36); + if (!ASSERT_EQ(id, 9, "btf__add_struct baz")) + break; + err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); + if (!ASSERT_OK(err, "btf__add_field bar::a")) + break; + err = btf__add_field(btf, "b", LIST_NODE, 128, 0); + if (!ASSERT_OK(err, "btf__add_field bar::b")) + break; + err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + if (!ASSERT_OK(err, "btf__add_field bar::c")) + break; + id = btf__add_decl_tag(btf, "contains:bam:a", 9, 0); + if (!ASSERT_EQ(id, 10, "btf__add_decl_tag contains:bam:a")) + break; + id = btf__add_struct(btf, "bam", 16); + if (!ASSERT_EQ(id, 11, "btf__add_struct bam")) + break; + err = btf__add_field(btf, "a", LIST_NODE, 0, 0); + if (!ASSERT_OK(err, "btf__add_field bam::a")) + break; + + err = btf__load_into_kernel(btf); + ASSERT_EQ(err, -ELOOP, "check btf"); + btf__free(btf); + break; + } +} + +void test_linked_list(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(linked_list_fail_tests); i++) { + if (!test__start_subtest(linked_list_fail_tests[i].prog_name)) + continue; + test_linked_list_fail_prog(linked_list_fail_tests[i].prog_name, + linked_list_fail_tests[i].err_msg); + } + test_btf(); + test_linked_list_success(PUSH_POP, false); + test_linked_list_success(PUSH_POP, true); + test_linked_list_success(PUSH_POP_MULT, false); + test_linked_list_success(PUSH_POP_MULT, true); + test_linked_list_success(LIST_IN_LIST, false); + test_linked_list_success(LIST_IN_LIST, true); + test_linked_list_success(TEST_ALL, false); +} diff --git a/tools/testing/selftests/bpf/prog_tests/spin_lock.c b/tools/testing/selftests/bpf/prog_tests/spin_lock.c new file mode 100644 index 000000000000..72282e92a78a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/spin_lock.c @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <network_helpers.h> + +#include "test_spin_lock.skel.h" +#include "test_spin_lock_fail.skel.h" + +static char log_buf[1024 * 1024]; + +static struct { + const char *prog_name; + const char *err_msg; +} spin_lock_fail_tests[] = { + { "lock_id_kptr_preserve", + "5: (bf) r1 = r0 ; R0_w=ptr_foo(id=2,ref_obj_id=2,off=0,imm=0) " + "R1_w=ptr_foo(id=2,ref_obj_id=2,off=0,imm=0) refs=2\n6: (85) call bpf_this_cpu_ptr#154\n" + "R1 type=ptr_ expected=percpu_ptr_" }, + { "lock_id_global_zero", + "; R1_w=map_value(off=0,ks=4,vs=4,imm=0)\n2: (85) call bpf_this_cpu_ptr#154\n" + "R1 type=map_value expected=percpu_ptr_" }, + { "lock_id_mapval_preserve", + "8: (bf) r1 = r0 ; R0_w=map_value(id=1,off=0,ks=4,vs=8,imm=0) " + "R1_w=map_value(id=1,off=0,ks=4,vs=8,imm=0)\n9: (85) call bpf_this_cpu_ptr#154\n" + "R1 type=map_value expected=percpu_ptr_" }, + { "lock_id_innermapval_preserve", + "13: (bf) r1 = r0 ; R0=map_value(id=2,off=0,ks=4,vs=8,imm=0) " + "R1_w=map_value(id=2,off=0,ks=4,vs=8,imm=0)\n14: (85) call bpf_this_cpu_ptr#154\n" + "R1 type=map_value expected=percpu_ptr_" }, + { "lock_id_mismatch_kptr_kptr", "bpf_spin_unlock of different lock" }, + { "lock_id_mismatch_kptr_global", "bpf_spin_unlock of different lock" }, + { "lock_id_mismatch_kptr_mapval", "bpf_spin_unlock of different lock" }, + { "lock_id_mismatch_kptr_innermapval", "bpf_spin_unlock of different lock" }, + { "lock_id_mismatch_global_global", "bpf_spin_unlock of different lock" }, + { "lock_id_mismatch_global_kptr", "bpf_spin_unlock of different lock" }, + { "lock_id_mismatch_global_mapval", "bpf_spin_unlock of different lock" }, + { "lock_id_mismatch_global_innermapval", "bpf_spin_unlock of different lock" }, + { "lock_id_mismatch_mapval_mapval", "bpf_spin_unlock of different lock" }, + { "lock_id_mismatch_mapval_kptr", "bpf_spin_unlock of different lock" }, + { "lock_id_mismatch_mapval_global", "bpf_spin_unlock of different lock" }, + { "lock_id_mismatch_mapval_innermapval", "bpf_spin_unlock of different lock" }, + { "lock_id_mismatch_innermapval_innermapval1", "bpf_spin_unlock of different lock" }, + { "lock_id_mismatch_innermapval_innermapval2", "bpf_spin_unlock of different lock" }, + { "lock_id_mismatch_innermapval_kptr", "bpf_spin_unlock of different lock" }, + { "lock_id_mismatch_innermapval_global", "bpf_spin_unlock of different lock" }, + { "lock_id_mismatch_innermapval_mapval", "bpf_spin_unlock of different lock" }, +}; + +static void test_spin_lock_fail_prog(const char *prog_name, const char *err_msg) +{ + LIBBPF_OPTS(bpf_object_open_opts, opts, .kernel_log_buf = log_buf, + .kernel_log_size = sizeof(log_buf), + .kernel_log_level = 1); + struct test_spin_lock_fail *skel; + struct bpf_program *prog; + int ret; + + skel = test_spin_lock_fail__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "test_spin_lock_fail__open_opts")) + return; + + prog = bpf_object__find_program_by_name(skel->obj, prog_name); + if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name")) + goto end; + + bpf_program__set_autoload(prog, true); + + ret = test_spin_lock_fail__load(skel); + if (!ASSERT_ERR(ret, "test_spin_lock_fail__load must fail")) + goto end; + + if (!ASSERT_OK_PTR(strstr(log_buf, err_msg), "expected error message")) { + fprintf(stderr, "Expected: %s\n", err_msg); + fprintf(stderr, "Verifier: %s\n", log_buf); + } + +end: + test_spin_lock_fail__destroy(skel); +} + +static void *spin_lock_thread(void *arg) +{ + int err, prog_fd = *(u32 *) arg; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 10000, + ); + + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_OK(topts.retval, "test_run retval"); + pthread_exit(arg); +} + +void test_spin_lock_success(void) +{ + struct test_spin_lock *skel; + pthread_t thread_id[4]; + int prog_fd, i; + void *ret; + + skel = test_spin_lock__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_spin_lock__open_and_load")) + return; + prog_fd = bpf_program__fd(skel->progs.bpf_spin_lock_test); + for (i = 0; i < 4; i++) { + int err; + + err = pthread_create(&thread_id[i], NULL, &spin_lock_thread, &prog_fd); + if (!ASSERT_OK(err, "pthread_create")) + goto end; + } + + for (i = 0; i < 4; i++) { + if (!ASSERT_OK(pthread_join(thread_id[i], &ret), "pthread_join")) + goto end; + if (!ASSERT_EQ(ret, &prog_fd, "ret == prog_fd")) + goto end; + } +end: + test_spin_lock__destroy(skel); +} + +void test_spin_lock(void) +{ + int i; + + test_spin_lock_success(); + + for (i = 0; i < ARRAY_SIZE(spin_lock_fail_tests); i++) { + if (!test__start_subtest(spin_lock_fail_tests[i].prog_name)) + continue; + test_spin_lock_fail_prog(spin_lock_fail_tests[i].prog_name, + spin_lock_fail_tests[i].err_msg); + } +} diff --git a/tools/testing/selftests/bpf/prog_tests/spinlock.c b/tools/testing/selftests/bpf/prog_tests/spinlock.c deleted file mode 100644 index 15eb1372d771..000000000000 --- a/tools/testing/selftests/bpf/prog_tests/spinlock.c +++ /dev/null @@ -1,45 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <test_progs.h> -#include <network_helpers.h> - -static void *spin_lock_thread(void *arg) -{ - int err, prog_fd = *(u32 *) arg; - LIBBPF_OPTS(bpf_test_run_opts, topts, - .data_in = &pkt_v4, - .data_size_in = sizeof(pkt_v4), - .repeat = 10000, - ); - - err = bpf_prog_test_run_opts(prog_fd, &topts); - ASSERT_OK(err, "test_run"); - ASSERT_OK(topts.retval, "test_run retval"); - pthread_exit(arg); -} - -void test_spinlock(void) -{ - const char *file = "./test_spin_lock.bpf.o"; - pthread_t thread_id[4]; - struct bpf_object *obj = NULL; - int prog_fd; - int err = 0, i; - void *ret; - - err = bpf_prog_test_load(file, BPF_PROG_TYPE_CGROUP_SKB, &obj, &prog_fd); - if (CHECK_FAIL(err)) { - printf("test_spin_lock:bpf_prog_test_load errno %d\n", errno); - goto close_prog; - } - for (i = 0; i < 4; i++) - if (CHECK_FAIL(pthread_create(&thread_id[i], NULL, - &spin_lock_thread, &prog_fd))) - goto close_prog; - - for (i = 0; i < 4; i++) - if (CHECK_FAIL(pthread_join(thread_id[i], &ret) || - ret != (void *)&prog_fd)) - goto close_prog; -close_prog: - bpf_object__close(obj); -} diff --git a/tools/testing/selftests/bpf/progs/linked_list.c b/tools/testing/selftests/bpf/progs/linked_list.c new file mode 100644 index 000000000000..a99103c86e48 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/linked_list.c @@ -0,0 +1,379 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_experimental.h" + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +#include "linked_list.h" + +static __always_inline +int list_push_pop(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool leave_in_map) +{ + struct bpf_list_node *n; + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 2; + + bpf_spin_lock(lock); + n = bpf_list_pop_front(head); + bpf_spin_unlock(lock); + if (n) { + bpf_obj_drop(container_of(n, struct foo, node)); + bpf_obj_drop(f); + return 3; + } + + bpf_spin_lock(lock); + n = bpf_list_pop_back(head); + bpf_spin_unlock(lock); + if (n) { + bpf_obj_drop(container_of(n, struct foo, node)); + bpf_obj_drop(f); + return 4; + } + + + bpf_spin_lock(lock); + f->data = 42; + bpf_list_push_front(head, &f->node); + bpf_spin_unlock(lock); + if (leave_in_map) + return 0; + bpf_spin_lock(lock); + n = bpf_list_pop_back(head); + bpf_spin_unlock(lock); + if (!n) + return 5; + f = container_of(n, struct foo, node); + if (f->data != 42) { + bpf_obj_drop(f); + return 6; + } + + bpf_spin_lock(lock); + f->data = 13; + bpf_list_push_front(head, &f->node); + bpf_spin_unlock(lock); + bpf_spin_lock(lock); + n = bpf_list_pop_front(head); + bpf_spin_unlock(lock); + if (!n) + return 7; + f = container_of(n, struct foo, node); + if (f->data != 13) { + bpf_obj_drop(f); + return 8; + } + bpf_obj_drop(f); + + bpf_spin_lock(lock); + n = bpf_list_pop_front(head); + bpf_spin_unlock(lock); + if (n) { + bpf_obj_drop(container_of(n, struct foo, node)); + return 9; + } + + bpf_spin_lock(lock); + n = bpf_list_pop_back(head); + bpf_spin_unlock(lock); + if (n) { + bpf_obj_drop(container_of(n, struct foo, node)); + return 10; + } + return 0; +} + + +static __always_inline +int list_push_pop_multiple(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool leave_in_map) +{ + struct bpf_list_node *n; + struct foo *f[8], *pf; + int i; + + for (i = 0; i < ARRAY_SIZE(f); i++) { + f[i] = bpf_obj_new(typeof(**f)); + if (!f[i]) + return 2; + f[i]->data = i; + bpf_spin_lock(lock); + bpf_list_push_front(head, &f[i]->node); + bpf_spin_unlock(lock); + } + + for (i = 0; i < ARRAY_SIZE(f); i++) { + bpf_spin_lock(lock); + n = bpf_list_pop_front(head); + bpf_spin_unlock(lock); + if (!n) + return 3; + pf = container_of(n, struct foo, node); + if (pf->data != (ARRAY_SIZE(f) - i - 1)) { + bpf_obj_drop(pf); + return 4; + } + bpf_spin_lock(lock); + bpf_list_push_back(head, &pf->node); + bpf_spin_unlock(lock); + } + + if (leave_in_map) + return 0; + + for (i = 0; i < ARRAY_SIZE(f); i++) { + bpf_spin_lock(lock); + n = bpf_list_pop_back(head); + bpf_spin_unlock(lock); + if (!n) + return 5; + pf = container_of(n, struct foo, node); + if (pf->data != i) { + bpf_obj_drop(pf); + return 6; + } + bpf_obj_drop(pf); + } + bpf_spin_lock(lock); + n = bpf_list_pop_back(head); + bpf_spin_unlock(lock); + if (n) { + bpf_obj_drop(container_of(n, struct foo, node)); + return 7; + } + + bpf_spin_lock(lock); + n = bpf_list_pop_front(head); + bpf_spin_unlock(lock); + if (n) { + bpf_obj_drop(container_of(n, struct foo, node)); + return 8; + } + return 0; +} + +static __always_inline +int list_in_list(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool leave_in_map) +{ + struct bpf_list_node *n; + struct bar *ba[8], *b; + struct foo *f; + int i; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 2; + for (i = 0; i < ARRAY_SIZE(ba); i++) { + b = bpf_obj_new(typeof(*b)); + if (!b) { + bpf_obj_drop(f); + return 3; + } + b->data = i; + bpf_spin_lock(&f->lock); + bpf_list_push_back(&f->head, &b->node); + bpf_spin_unlock(&f->lock); + } + + bpf_spin_lock(lock); + f->data = 42; + bpf_list_push_front(head, &f->node); + bpf_spin_unlock(lock); + + if (leave_in_map) + return 0; + + bpf_spin_lock(lock); + n = bpf_list_pop_front(head); + bpf_spin_unlock(lock); + if (!n) + return 4; + f = container_of(n, struct foo, node); + if (f->data != 42) { + bpf_obj_drop(f); + return 5; + } + + for (i = 0; i < ARRAY_SIZE(ba); i++) { + bpf_spin_lock(&f->lock); + n = bpf_list_pop_front(&f->head); + bpf_spin_unlock(&f->lock); + if (!n) { + bpf_obj_drop(f); + return 6; + } + b = container_of(n, struct bar, node); + if (b->data != i) { + bpf_obj_drop(f); + bpf_obj_drop(b); + return 7; + } + bpf_obj_drop(b); + } + bpf_spin_lock(&f->lock); + n = bpf_list_pop_front(&f->head); + bpf_spin_unlock(&f->lock); + if (n) { + bpf_obj_drop(f); + bpf_obj_drop(container_of(n, struct bar, node)); + return 8; + } + bpf_obj_drop(f); + return 0; +} + +static __always_inline +int test_list_push_pop(struct bpf_spin_lock *lock, struct bpf_list_head *head) +{ + int ret; + + ret = list_push_pop(lock, head, false); + if (ret) + return ret; + return list_push_pop(lock, head, true); +} + +static __always_inline +int test_list_push_pop_multiple(struct bpf_spin_lock *lock, struct bpf_list_head *head) +{ + int ret; + + ret = list_push_pop_multiple(lock ,head, false); + if (ret) + return ret; + return list_push_pop_multiple(lock, head, true); +} + +static __always_inline +int test_list_in_list(struct bpf_spin_lock *lock, struct bpf_list_head *head) +{ + int ret; + + ret = list_in_list(lock, head, false); + if (ret) + return ret; + return list_in_list(lock, head, true); +} + +SEC("tc") +int map_list_push_pop(void *ctx) +{ + struct map_value *v; + + v = bpf_map_lookup_elem(&array_map, &(int){0}); + if (!v) + return 1; + return test_list_push_pop(&v->lock, &v->head); +} + +SEC("tc") +int inner_map_list_push_pop(void *ctx) +{ + struct map_value *v; + void *map; + + map = bpf_map_lookup_elem(&map_of_maps, &(int){0}); + if (!map) + return 1; + v = bpf_map_lookup_elem(map, &(int){0}); + if (!v) + return 1; + return test_list_push_pop(&v->lock, &v->head); +} + +SEC("tc") +int global_list_push_pop(void *ctx) +{ + /* FIXME: + * return test_list_push_pop(&glock, &ghead); + */ + return 0; +} + +SEC("tc") +int map_list_push_pop_multiple(void *ctx) +{ + struct map_value *v; + int ret; + + v = bpf_map_lookup_elem(&array_map, &(int){0}); + if (!v) + return 1; + return test_list_push_pop_multiple(&v->lock, &v->head); +} + +SEC("tc") +int inner_map_list_push_pop_multiple(void *ctx) +{ + struct map_value *v; + void *map; + int ret; + + map = bpf_map_lookup_elem(&map_of_maps, &(int){0}); + if (!map) + return 1; + v = bpf_map_lookup_elem(map, &(int){0}); + if (!v) + return 1; + return test_list_push_pop_multiple(&v->lock, &v->head); +} + +SEC("tc") +int global_list_push_pop_multiple(void *ctx) +{ + int ret; + + /* FIXME: + ret = list_push_pop_multiple(&glock, &ghead, false); + if (ret) + return ret; + return list_push_pop_multiple(&glock, &ghead, true); + */ + return 0; +} + +SEC("tc") +int map_list_in_list(void *ctx) +{ + struct map_value *v; + int ret; + + v = bpf_map_lookup_elem(&array_map, &(int){0}); + if (!v) + return 1; + return test_list_in_list(&v->lock, &v->head); +} + +SEC("tc") +int inner_map_list_in_list(void *ctx) +{ + struct map_value *v; + void *map; + int ret; + + map = bpf_map_lookup_elem(&map_of_maps, &(int){0}); + if (!map) + return 1; + v = bpf_map_lookup_elem(map, &(int){0}); + if (!v) + return 1; + return test_list_in_list(&v->lock, &v->head); +} + +SEC("tc") +int global_list_in_list(void *ctx) +{ + /* FIXME + return test_list_in_list(&glock, &ghead); + */ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/linked_list.h b/tools/testing/selftests/bpf/progs/linked_list.h new file mode 100644 index 000000000000..93157efc2d04 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/linked_list.h @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef LINKED_LIST_H +#define LINKED_LIST_H + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "bpf_experimental.h" + +struct bar { + struct bpf_list_node node; + int data; +}; + +struct foo { + struct bpf_list_node node; + struct bpf_list_head head __contains(bar, node); + struct bpf_spin_lock lock; + int data; + struct bpf_list_node node2; +}; + +struct map_value { + struct bpf_spin_lock lock; + int data; + struct bpf_list_head head __contains(foo, node); +}; + +struct array_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 1); +}; + +struct array_map array_map SEC(".maps"); +struct array_map inner_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); + __array(values, struct array_map); +} map_of_maps SEC(".maps") = { + .values = { + [0] = &inner_map, + }, +}; + +/* FIXME +#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8))) + +private(A) struct bpf_spin_lock glock; +private(A) struct bpf_list_head ghead __contains(foo, node); +private(B) struct bpf_spin_lock glock2; + +*/ +#endif diff --git a/tools/testing/selftests/bpf/progs/linked_list_fail.c b/tools/testing/selftests/bpf/progs/linked_list_fail.c new file mode 100644 index 000000000000..1b7ed1d3a9bb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/linked_list_fail.c @@ -0,0 +1,581 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_experimental.h" + +#include "linked_list.h" + +#define INIT \ + struct map_value *v, *v2, *iv, *iv2; \ + struct foo *f, *f1, *f2; \ + struct bar *b; \ + void *map; \ + \ + map = bpf_map_lookup_elem(&map_of_maps, &(int){ 0 }); \ + if (!map) \ + return 0; \ + v = bpf_map_lookup_elem(&array_map, &(int){ 0 }); \ + if (!v) \ + return 0; \ + v2 = bpf_map_lookup_elem(&array_map, &(int){ 0 }); \ + if (!v2) \ + return 0; \ + iv = bpf_map_lookup_elem(map, &(int){ 0 }); \ + if (!iv) \ + return 0; \ + iv2 = bpf_map_lookup_elem(map, &(int){ 0 }); \ + if (!iv2) \ + return 0; \ + f = bpf_obj_new(typeof(*f)); \ + if (!f) \ + return 0; \ + f1 = f; \ + f2 = bpf_obj_new(typeof(*f2)); \ + if (!f2) { \ + bpf_obj_drop(f1); \ + return 0; \ + } \ + b = bpf_obj_new(typeof(*b)); \ + if (!b) { \ + bpf_obj_drop(f2); \ + bpf_obj_drop(f1); \ + return 0; \ + } + +#define CHECK(test, op, hexpr) \ + SEC("?tc") \ + int test##_missing_lock_##op(void *ctx) \ + { \ + INIT; \ + void (*p)(void *) = (void *)&bpf_list_##op; \ + p(hexpr); \ + return 0; \ + } + +CHECK(kptr, push_front, &f->head); +CHECK(kptr, push_back, &f->head); +CHECK(kptr, pop_front, &f->head); +CHECK(kptr, pop_back, &f->head); + +/* FIXME +CHECK(global, push_front, &ghead); +CHECK(global, push_back, &ghead); +CHECK(global, pop_front, &ghead); +CHECK(global, pop_back, &ghead); +*/ + +CHECK(map, push_front, &v->head); +CHECK(map, push_back, &v->head); +CHECK(map, pop_front, &v->head); +CHECK(map, pop_back, &v->head); + +CHECK(inner_map, push_front, &iv->head); +CHECK(inner_map, push_back, &iv->head); +CHECK(inner_map, pop_front, &iv->head); +CHECK(inner_map, pop_back, &iv->head); + +#undef CHECK + +#define CHECK(test, op, lexpr, hexpr) \ + SEC("?tc") \ + int test##_incorrect_lock_##op(void *ctx) \ + { \ + INIT; \ + void (*p)(void *) = (void *)&bpf_list_##op; \ + bpf_spin_lock(lexpr); \ + p(hexpr); \ + return 0; \ + } + +#define CHECK_OP(op) \ + CHECK(kptr_kptr, op, &f1->lock, &f2->head); \ + CHECK(kptr_map, op, &f1->lock, &v->head); \ + CHECK(kptr_inner_map, op, &f1->lock, &iv->head); \ + \ + CHECK(map_map, op, &v->lock, &v2->head); \ + CHECK(map_kptr, op, &v->lock, &f2->head); \ + CHECK(map_inner_map, op, &v->lock, &iv->head); \ + \ + CHECK(inner_map_inner_map, op, &iv->lock, &iv2->head); \ + CHECK(inner_map_kptr, op, &iv->lock, &f2->head); \ + CHECK(inner_map_map, op, &iv->lock, &v->head); + +CHECK_OP(push_front); +CHECK_OP(push_back); +CHECK_OP(pop_front); +CHECK_OP(pop_back); + +#undef CHECK +#undef CHECK_OP +#undef INIT + +/* FIXME +SEC("?kprobe/xyz") +int map_compat_kprobe(void *ctx) +{ + bpf_list_push_front(&ghead, NULL); + return 0; +} + +SEC("?kretprobe/xyz") +int map_compat_kretprobe(void *ctx) +{ + bpf_list_push_front(&ghead, NULL); + return 0; +} + +SEC("?tracepoint/xyz") +int map_compat_tp(void *ctx) +{ + bpf_list_push_front(&ghead, NULL); + return 0; +} + +SEC("?perf_event") +int map_compat_perf(void *ctx) +{ + bpf_list_push_front(&ghead, NULL); + return 0; +} + +SEC("?raw_tp/xyz") +int map_compat_raw_tp(void *ctx) +{ + bpf_list_push_front(&ghead, NULL); + return 0; +} + +SEC("?raw_tp.w/xyz") +int map_compat_raw_tp_w(void *ctx) +{ + bpf_list_push_front(&ghead, NULL); + return 0; +} +*/ + +SEC("?tc") +int obj_type_id_oor(void *ctx) +{ + bpf_obj_new_impl(~0UL, NULL); + return 0; +} + +SEC("?tc") +int obj_new_no_composite(void *ctx) +{ + bpf_obj_new_impl(bpf_core_type_id_local(int), (void *)42); + return 0; +} + +SEC("?tc") +int obj_new_no_struct(void *ctx) +{ + + bpf_obj_new(union { int data; unsigned udata; }); + return 0; +} + +SEC("?tc") +int obj_drop_non_zero_off(void *ctx) +{ + void *f; + + f = bpf_obj_new(struct foo); + if (!f) + return 0; + bpf_obj_drop(f+1); + return 0; +} + +SEC("?tc") +int new_null_ret(void *ctx) +{ + return bpf_obj_new(struct foo)->data; +} + +SEC("?tc") +int obj_new_acq(void *ctx) +{ + bpf_obj_new(struct foo); + return 0; +} + +SEC("?tc") +int use_after_drop(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_obj_drop(f); + return f->data; +} + +SEC("?tc") +int ptr_walk_scalar(void *ctx) +{ + struct test1 { + struct test2 { + struct test2 *next; + } *ptr; + } *p; + + p = bpf_obj_new(typeof(*p)); + if (!p) + return 0; + bpf_this_cpu_ptr(p->ptr); + return 0; +} + +SEC("?tc") +int direct_read_lock(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + return *(int *)&f->lock; +} + +SEC("?tc") +int direct_write_lock(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + *(int *)&f->lock = 0; + return 0; +} + +SEC("?tc") +int direct_read_head(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + return *(int *)&f->head; +} + +SEC("?tc") +int direct_write_head(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + *(int *)&f->head = 0; + return 0; +} + +SEC("?tc") +int direct_read_node(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + return *(int *)&f->node; +} + +SEC("?tc") +int direct_write_node(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + *(int *)&f->node = 0; + return 0; +} + +/* FIXME +static __always_inline +int write_after_op(void (*push_op)(void *head, void *node)) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_spin_lock(&glock); + push_op(&ghead, &f->node); + f->data = 42; + bpf_spin_unlock(&glock); + + return 0; +} + +SEC("?tc") +int write_after_push_front(void *ctx) +{ + return write_after_op((void *)bpf_list_push_front); +} + +SEC("?tc") +int write_after_push_back(void *ctx) +{ + return write_after_op((void *)bpf_list_push_back); +} + +static __always_inline +int use_after_unlock(void (*op)(void *head, void *node)) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_spin_lock(&glock); + f->data = 42; + op(&ghead, &f->node); + bpf_spin_unlock(&glock); + + return f->data; +} + +SEC("?tc") +int use_after_unlock_push_front(void *ctx) +{ + return use_after_unlock((void *)bpf_list_push_front); +} + +SEC("?tc") +int use_after_unlock_push_back(void *ctx) +{ + return use_after_unlock((void *)bpf_list_push_back); +} + +static __always_inline +int list_double_add(void (*op)(void *head, void *node)) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_spin_lock(&glock); + op(&ghead, &f->node); + op(&ghead, &f->node); + bpf_spin_unlock(&glock); + + return 0; +} + +SEC("?tc") +int double_push_front(void *ctx) +{ + return list_double_add((void *)bpf_list_push_front); +} + +SEC("?tc") +int double_push_back(void *ctx) +{ + return list_double_add((void *)bpf_list_push_back); +} + +SEC("?tc") +int no_node_value_type(void *ctx) +{ + void *p; + + p = bpf_obj_new(struct { int data; }); + if (!p) + return 0; + bpf_spin_lock(&glock); + bpf_list_push_front(&ghead, p); + bpf_spin_unlock(&glock); + + return 0; +} + +SEC("?tc") +int incorrect_value_type(void *ctx) +{ + struct bar *b; + + b = bpf_obj_new(typeof(*b)); + if (!b) + return 0; + bpf_spin_lock(&glock); + bpf_list_push_front(&ghead, &b->node); + bpf_spin_unlock(&glock); + + return 0; +} + +SEC("?tc") +int incorrect_node_var_off(struct __sk_buff *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_spin_lock(&glock); + bpf_list_push_front(&ghead, (void *)&f->node + ctx->protocol); + bpf_spin_unlock(&glock); + + return 0; +} + +SEC("?tc") +int incorrect_node_off1(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_spin_lock(&glock); + bpf_list_push_front(&ghead, (void *)&f->node + 1); + bpf_spin_unlock(&glock); + + return 0; +} + +SEC("?tc") +int incorrect_node_off2(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_spin_lock(&glock); + bpf_list_push_front(&ghead, &f->node2); + bpf_spin_unlock(&glock); + + return 0; +} + +SEC("?tc") +int no_head_type(void *ctx) +{ + void *p; + + p = bpf_obj_new(typeof(struct { int data; })); + if (!p) + return 0; + bpf_spin_lock(&glock); + bpf_list_push_front(p, NULL); + bpf_spin_lock(&glock); + + return 0; +} + +SEC("?tc") +int incorrect_head_var_off1(struct __sk_buff *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_spin_lock(&glock); + bpf_list_push_front((void *)&ghead + ctx->protocol, &f->node); + bpf_spin_unlock(&glock); + + return 0; +} + +SEC("?tc") +int incorrect_head_var_off2(struct __sk_buff *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_spin_lock(&glock); + bpf_list_push_front((void *)&f->head + ctx->protocol, &f->node); + bpf_spin_unlock(&glock); + + return 0; +} +*/ + +SEC("?tc") +int incorrect_head_off1(void *ctx) +{ + struct foo *f; + struct bar *b; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + b = bpf_obj_new(typeof(*b)); + if (!b) { + bpf_obj_drop(f); + return 0; + } + + bpf_spin_lock(&f->lock); + bpf_list_push_front((void *)&f->head + 1, &b->node); + bpf_spin_unlock(&f->lock); + + return 0; +} + +/* FIXME +SEC("?tc") +int incorrect_head_off2(void *ctx) +{ + struct foo *f; + struct bar *b; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + + bpf_spin_lock(&glock); + bpf_list_push_front((void *)&ghead + 1, &f->node); + bpf_spin_unlock(&glock); + + return 0; +} +*/ + +static __always_inline +int pop_ptr_off(void *(*op)(void *head)) +{ + struct { + struct bpf_list_head head __contains(foo, node2); + struct bpf_spin_lock lock; + } *p; + struct bpf_list_node *n; + + p = bpf_obj_new(typeof(*p)); + if (!p) + return 0; + bpf_spin_lock(&p->lock); + n = op(&p->head); + bpf_spin_unlock(&p->lock); + + bpf_this_cpu_ptr(n); + return 0; +} + +SEC("?tc") +int pop_front_off(void *ctx) +{ + return pop_ptr_off((void *)bpf_list_pop_front); +} + +SEC("?tc") +int pop_back_off(void *ctx) +{ + return pop_ptr_off((void *)bpf_list_pop_back); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock.c b/tools/testing/selftests/bpf/progs/test_spin_lock.c index 7e88309d3229..5bd10409285b 100644 --- a/tools/testing/selftests/bpf/progs/test_spin_lock.c +++ b/tools/testing/selftests/bpf/progs/test_spin_lock.c @@ -45,8 +45,8 @@ struct { #define CREDIT_PER_NS(delta, rate) (((delta) * rate) >> 20) -SEC("tc") -int bpf_sping_lock_test(struct __sk_buff *skb) +SEC("cgroup_skb/ingress") +int bpf_spin_lock_test(struct __sk_buff *skb) { volatile int credit = 0, max_credit = 100, pkt_len = 64; struct hmap_elem zero = {}, *val; diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c b/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c new file mode 100644 index 000000000000..86cd183ef6dc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c @@ -0,0 +1,204 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include "bpf_experimental.h" + +struct foo { + struct bpf_spin_lock lock; + int data; +}; + +struct array_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct foo); + __uint(max_entries, 1); +} array_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); + __array(values, struct array_map); +} map_of_maps SEC(".maps") = { + .values = { + [0] = &array_map, + }, +}; + +SEC(".data.A") struct bpf_spin_lock lockA; +SEC(".data.B") struct bpf_spin_lock lockB; + +SEC("?tc") +int lock_id_kptr_preserve(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_this_cpu_ptr(f); + return 0; +} + +SEC("?tc") +int lock_id_global_zero(void *ctx) +{ + bpf_this_cpu_ptr(&lockA); + return 0; +} + +SEC("?tc") +int lock_id_mapval_preserve(void *ctx) +{ + struct foo *f; + int key = 0; + + f = bpf_map_lookup_elem(&array_map, &key); + if (!f) + return 0; + bpf_this_cpu_ptr(f); + return 0; +} + +SEC("?tc") +int lock_id_innermapval_preserve(void *ctx) +{ + struct foo *f; + int key = 0; + void *map; + + map = bpf_map_lookup_elem(&map_of_maps, &key); + if (!map) + return 0; + f = bpf_map_lookup_elem(map, &key); + if (!f) + return 0; + bpf_this_cpu_ptr(f); + return 0; +} + +#define CHECK(test, A, B) \ + SEC("?tc") \ + int lock_id_mismatch_##test(void *ctx) \ + { \ + struct foo *f1, *f2, *v, *iv; \ + int key = 0; \ + void *map; \ + \ + map = bpf_map_lookup_elem(&map_of_maps, &key); \ + if (!map) \ + return 0; \ + iv = bpf_map_lookup_elem(map, &key); \ + if (!iv) \ + return 0; \ + v = bpf_map_lookup_elem(&array_map, &key); \ + if (!v) \ + return 0; \ + f1 = bpf_obj_new(typeof(*f1)); \ + if (!f1) \ + return 0; \ + f2 = bpf_obj_new(typeof(*f2)); \ + if (!f2) { \ + bpf_obj_drop(f1); \ + return 0; \ + } \ + bpf_spin_lock(A); \ + bpf_spin_unlock(B); \ + return 0; \ + } + +CHECK(kptr_kptr, &f1->lock, &f2->lock); +CHECK(kptr_global, &f1->lock, &lockA); +CHECK(kptr_mapval, &f1->lock, &v->lock); +CHECK(kptr_innermapval, &f1->lock, &iv->lock); + +CHECK(global_global, &lockA, &lockB); +CHECK(global_kptr, &lockA, &f1->lock); +CHECK(global_mapval, &lockA, &v->lock); +CHECK(global_innermapval, &lockA, &iv->lock); + +SEC("?tc") +int lock_id_mismatch_mapval_mapval(void *ctx) +{ + struct foo *f1, *f2; + int key = 0; + + f1 = bpf_map_lookup_elem(&array_map, &key); + if (!f1) + return 0; + f2 = bpf_map_lookup_elem(&array_map, &key); + if (!f2) + return 0; + + bpf_spin_lock(&f1->lock); + f1->data = 42; + bpf_spin_unlock(&f2->lock); + + return 0; +} + +CHECK(mapval_kptr, &v->lock, &f1->lock); +CHECK(mapval_global, &v->lock, &lockB); +CHECK(mapval_innermapval, &v->lock, &iv->lock); + +SEC("?tc") +int lock_id_mismatch_innermapval_innermapval1(void *ctx) +{ + struct foo *f1, *f2; + int key = 0; + void *map; + + map = bpf_map_lookup_elem(&map_of_maps, &key); + if (!map) + return 0; + f1 = bpf_map_lookup_elem(map, &key); + if (!f1) + return 0; + f2 = bpf_map_lookup_elem(map, &key); + if (!f2) + return 0; + + bpf_spin_lock(&f1->lock); + f1->data = 42; + bpf_spin_unlock(&f2->lock); + + return 0; +} + +SEC("?tc") +int lock_id_mismatch_innermapval_innermapval2(void *ctx) +{ + struct foo *f1, *f2; + int key = 0; + void *map; + + map = bpf_map_lookup_elem(&map_of_maps, &key); + if (!map) + return 0; + f1 = bpf_map_lookup_elem(map, &key); + if (!f1) + return 0; + map = bpf_map_lookup_elem(&map_of_maps, &key); + if (!map) + return 0; + f2 = bpf_map_lookup_elem(map, &key); + if (!f2) + return 0; + + bpf_spin_lock(&f1->lock); + f1->data = 42; + bpf_spin_unlock(&f2->lock); + + return 0; +} + +CHECK(innermapval_kptr, &iv->lock, &f1->lock); +CHECK(innermapval_global, &iv->lock, &lockA); +CHECK(innermapval_mapval, &iv->lock, &v->lock); + +#undef CHECK + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index e1a937277b54..86d6fef2e3b4 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -109,7 +109,7 @@ }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, - .errstr = "arg#0 pointer type STRUCT prog_test_ref_kfunc must point", + .errstr = "arg#0 expected pointer to btf or socket", .fixup_kfunc_btf_id = { { "bpf_kfunc_call_test_acquire", 3 }, { "bpf_kfunc_call_test_release", 5 }, diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c index fd683a32a276..55cba01c99d5 100644 --- a/tools/testing/selftests/bpf/verifier/ref_tracking.c +++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c @@ -142,7 +142,7 @@ .kfunc = "bpf", .expected_attach_type = BPF_LSM_MAC, .flags = BPF_F_SLEEPABLE, - .errstr = "arg#0 pointer type STRUCT bpf_key must point to scalar, or struct with scalar", + .errstr = "arg#0 expected pointer to btf or socket", .fixup_kfunc_btf_id = { { "bpf_lookup_user_key", 2 }, { "bpf_key_put", 4 }, @@ -163,7 +163,7 @@ .kfunc = "bpf", .expected_attach_type = BPF_LSM_MAC, .flags = BPF_F_SLEEPABLE, - .errstr = "arg#0 pointer type STRUCT bpf_key must point to scalar, or struct with scalar", + .errstr = "arg#0 expected pointer to btf or socket", .fixup_kfunc_btf_id = { { "bpf_lookup_system_key", 1 }, { "bpf_key_put", 3 }, |