From 23da464dd6b8935b66f4ee306ad8947fd32ccd75 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Nov 2022 00:39:51 +0530 Subject: bpf: Allow specifying volatile type modifier for kptrs This is useful in particular to mark the pointer as volatile, so that compiler treats each load and store to the field as a volatile access. The alternative is having to define and use READ_ONCE and WRITE_ONCE in the BPF program. Signed-off-by: Kumar Kartikeya Dwivedi Acked-by: David Vernet Link: https://lore.kernel.org/r/20221103191013.1236066-3-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/btf.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/btf.h') diff --git a/include/linux/btf.h b/include/linux/btf.h index f9aababc5d78..86aad9b2ce02 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -288,6 +288,11 @@ static inline bool btf_type_is_typedef(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF; } +static inline bool btf_type_is_volatile(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_VOLATILE; +} + static inline bool btf_type_is_func(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC; -- cgit v1.2.3 From aa3496accc412b3d975e4ee5d06076d73394d8b5 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Nov 2022 00:39:55 +0530 Subject: bpf: Refactor kptr_off_tab into btf_record To prepare the BPF verifier to handle special fields in both map values and program allocated types coming from program BTF, we need to refactor the kptr_off_tab handling code into something more generic and reusable across both cases to avoid code duplication. Later patches also require passing this data to helpers at runtime, so that they can work on user defined types, initialize them, destruct them, etc. The main observation is that both map values and such allocated types point to a type in program BTF, hence they can be handled similarly. We can prepare a field metadata table for both cases and store them in struct bpf_map or struct btf depending on the use case. Hence, refactor the code into generic btf_record and btf_field member structs. The btf_record represents the fields of a specific btf_type in user BTF. The cnt indicates the number of special fields we successfully recognized, and field_mask is a bitmask of fields that were found, to enable quick determination of availability of a certain field. Subsequently, refactor the rest of the code to work with these generic types, remove assumptions about kptr and kptr_off_tab, rename variables to more meaningful names, etc. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221103191013.1236066-7-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 125 +++++++++++++++-------- include/linux/btf.h | 3 +- kernel/bpf/arraymap.c | 13 ++- kernel/bpf/btf.c | 67 ++++++------ kernel/bpf/hashtab.c | 14 ++- kernel/bpf/map_in_map.c | 14 ++- kernel/bpf/syscall.c | 263 +++++++++++++++++++++++++++--------------------- kernel/bpf/verifier.c | 96 +++++++++--------- 8 files changed, 332 insertions(+), 263 deletions(-) (limited to 'include/linux/btf.h') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8d948bfcb984..5f2a42033a37 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -165,35 +165,41 @@ struct bpf_map_ops { }; enum { - /* Support at most 8 pointers in a BPF map value */ - BPF_MAP_VALUE_OFF_MAX = 8, - BPF_MAP_OFF_ARR_MAX = BPF_MAP_VALUE_OFF_MAX + + /* Support at most 8 pointers in a BTF type */ + BTF_FIELDS_MAX = 8, + BPF_MAP_OFF_ARR_MAX = BTF_FIELDS_MAX + 1 + /* for bpf_spin_lock */ 1, /* for bpf_timer */ }; -enum bpf_kptr_type { - BPF_KPTR_UNREF, - BPF_KPTR_REF, +enum btf_field_type { + BPF_KPTR_UNREF = (1 << 2), + BPF_KPTR_REF = (1 << 3), + BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF, }; -struct bpf_map_value_off_desc { +struct btf_field_kptr { + struct btf *btf; + struct module *module; + btf_dtor_kfunc_t dtor; + u32 btf_id; +}; + +struct btf_field { u32 offset; - enum bpf_kptr_type type; - struct { - struct btf *btf; - struct module *module; - btf_dtor_kfunc_t dtor; - u32 btf_id; - } kptr; + enum btf_field_type type; + union { + struct btf_field_kptr kptr; + }; }; -struct bpf_map_value_off { - u32 nr_off; - struct bpf_map_value_off_desc off[]; +struct btf_record { + u32 cnt; + u32 field_mask; + struct btf_field fields[]; }; -struct bpf_map_off_arr { +struct btf_field_offs { u32 cnt; u32 field_off[BPF_MAP_OFF_ARR_MAX]; u8 field_sz[BPF_MAP_OFF_ARR_MAX]; @@ -215,7 +221,7 @@ struct bpf_map { u64 map_extra; /* any per-map-type extra fields */ u32 map_flags; int spin_lock_off; /* >=0 valid offset, <0 error */ - struct bpf_map_value_off *kptr_off_tab; + struct btf_record *record; int timer_off; /* >=0 valid offset, <0 error */ u32 id; int numa_node; @@ -227,7 +233,7 @@ struct bpf_map { struct obj_cgroup *objcg; #endif char name[BPF_OBJ_NAME_LEN]; - struct bpf_map_off_arr *off_arr; + struct btf_field_offs *field_offs; /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. */ @@ -251,6 +257,37 @@ struct bpf_map { bool frozen; /* write-once; write-protected by freeze_mutex */ }; +static inline u32 btf_field_type_size(enum btf_field_type type) +{ + switch (type) { + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: + return sizeof(u64); + default: + WARN_ON_ONCE(1); + return 0; + } +} + +static inline u32 btf_field_type_align(enum btf_field_type type) +{ + switch (type) { + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: + return __alignof__(u64); + default: + WARN_ON_ONCE(1); + return 0; + } +} + +static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_field_type type) +{ + if (IS_ERR_OR_NULL(rec)) + return false; + return rec->field_mask & type; +} + static inline bool map_value_has_spin_lock(const struct bpf_map *map) { return map->spin_lock_off >= 0; @@ -261,23 +298,19 @@ static inline bool map_value_has_timer(const struct bpf_map *map) return map->timer_off >= 0; } -static inline bool map_value_has_kptrs(const struct bpf_map *map) -{ - return !IS_ERR_OR_NULL(map->kptr_off_tab); -} - static inline void check_and_init_map_value(struct bpf_map *map, void *dst) { if (unlikely(map_value_has_spin_lock(map))) memset(dst + map->spin_lock_off, 0, sizeof(struct bpf_spin_lock)); if (unlikely(map_value_has_timer(map))) memset(dst + map->timer_off, 0, sizeof(struct bpf_timer)); - if (unlikely(map_value_has_kptrs(map))) { - struct bpf_map_value_off *tab = map->kptr_off_tab; + if (!IS_ERR_OR_NULL(map->record)) { + struct btf_field *fields = map->record->fields; + u32 cnt = map->record->cnt; int i; - for (i = 0; i < tab->nr_off; i++) - *(u64 *)(dst + tab->off[i].offset) = 0; + for (i = 0; i < cnt; i++) + memset(dst + fields[i].offset, 0, btf_field_type_size(fields[i].type)); } } @@ -303,7 +336,7 @@ static inline void __copy_map_value(struct bpf_map *map, void *dst, void *src, b u32 curr_off = 0; int i; - if (likely(!map->off_arr)) { + if (likely(!map->field_offs)) { if (long_memcpy) bpf_long_memcpy(dst, src, round_up(map->value_size, 8)); else @@ -311,11 +344,12 @@ static inline void __copy_map_value(struct bpf_map *map, void *dst, void *src, b return; } - for (i = 0; i < map->off_arr->cnt; i++) { - u32 next_off = map->off_arr->field_off[i]; + for (i = 0; i < map->field_offs->cnt; i++) { + u32 next_off = map->field_offs->field_off[i]; + u32 sz = next_off - curr_off; - memcpy(dst + curr_off, src + curr_off, next_off - curr_off); - curr_off += map->off_arr->field_sz[i]; + memcpy(dst + curr_off, src + curr_off, sz); + curr_off += map->field_offs->field_sz[i]; } memcpy(dst + curr_off, src + curr_off, map->value_size - curr_off); } @@ -335,16 +369,17 @@ static inline void zero_map_value(struct bpf_map *map, void *dst) u32 curr_off = 0; int i; - if (likely(!map->off_arr)) { + if (likely(!map->field_offs)) { memset(dst, 0, map->value_size); return; } - for (i = 0; i < map->off_arr->cnt; i++) { - u32 next_off = map->off_arr->field_off[i]; + for (i = 0; i < map->field_offs->cnt; i++) { + u32 next_off = map->field_offs->field_off[i]; + u32 sz = next_off - curr_off; - memset(dst + curr_off, 0, next_off - curr_off); - curr_off += map->off_arr->field_sz[i]; + memset(dst + curr_off, 0, sz); + curr_off += map->field_offs->field_sz[i]; } memset(dst + curr_off, 0, map->value_size - curr_off); } @@ -1699,11 +1734,13 @@ void bpf_prog_put(struct bpf_prog *prog); void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock); void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); -struct bpf_map_value_off_desc *bpf_map_kptr_off_contains(struct bpf_map *map, u32 offset); -void bpf_map_free_kptr_off_tab(struct bpf_map *map); -struct bpf_map_value_off *bpf_map_copy_kptr_off_tab(const struct bpf_map *map); -bool bpf_map_equal_kptr_off_tab(const struct bpf_map *map_a, const struct bpf_map *map_b); -void bpf_map_free_kptrs(struct bpf_map *map, void *map_value); +struct btf_field *btf_record_find(const struct btf_record *rec, + u32 offset, enum btf_field_type type); +void btf_record_free(struct btf_record *rec); +void bpf_map_free_record(struct bpf_map *map); +struct btf_record *btf_record_dup(const struct btf_record *rec); +bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b); +void bpf_obj_free_fields(const struct btf_record *rec, void *obj); struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); diff --git a/include/linux/btf.h b/include/linux/btf.h index 86aad9b2ce02..9e62717cdc7a 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -163,8 +163,7 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, u32 expected_offset, u32 expected_size); 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 bpf_map_value_off *btf_parse_kptrs(const struct btf *btf, - const struct btf_type *t); +struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t); 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); const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 832b2659e96e..417f84342e98 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -310,8 +310,7 @@ static void check_and_free_fields(struct bpf_array *arr, void *val) { if (map_value_has_timer(&arr->map)) bpf_timer_cancel_and_free(val + arr->map.timer_off); - if (map_value_has_kptrs(&arr->map)) - bpf_map_free_kptrs(&arr->map, val); + bpf_obj_free_fields(arr->map.record, val); } /* Called from syscall or from eBPF program */ @@ -409,7 +408,7 @@ static void array_map_free_timers(struct bpf_map *map) struct bpf_array *array = container_of(map, struct bpf_array, map); int i; - /* We don't reset or free kptr on uref dropping to zero. */ + /* We don't reset or free fields other than timer on uref dropping to zero. */ if (!map_value_has_timer(map)) return; @@ -423,22 +422,22 @@ static void array_map_free(struct bpf_map *map) struct bpf_array *array = container_of(map, struct bpf_array, map); int i; - if (map_value_has_kptrs(map)) { + if (!IS_ERR_OR_NULL(map->record)) { if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { for (i = 0; i < array->map.max_entries; i++) { void __percpu *pptr = array->pptrs[i & array->index_mask]; int cpu; for_each_possible_cpu(cpu) { - bpf_map_free_kptrs(map, per_cpu_ptr(pptr, cpu)); + bpf_obj_free_fields(map->record, per_cpu_ptr(pptr, cpu)); cond_resched(); } } } else { for (i = 0; i < array->map.max_entries; i++) - bpf_map_free_kptrs(map, array_map_elem_ptr(array, i)); + bpf_obj_free_fields(map->record, array_map_elem_ptr(array, i)); } - bpf_map_free_kptr_off_tab(map); + 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 f4d21eef6ebd..8391a77138ee 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3191,7 +3191,7 @@ static void btf_struct_log(struct btf_verifier_env *env, btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); } -enum btf_field_type { +enum btf_field_info_type { BTF_FIELD_SPIN_LOCK, BTF_FIELD_TIMER, BTF_FIELD_KPTR, @@ -3203,9 +3203,9 @@ enum { }; struct btf_field_info { - u32 type_id; + enum btf_field_type type; u32 off; - enum bpf_kptr_type type; + u32 type_id; }; static int btf_find_struct(const struct btf *btf, const struct btf_type *t, @@ -3222,7 +3222,7 @@ static int btf_find_struct(const struct btf *btf, const struct btf_type *t, static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, u32 off, int sz, struct btf_field_info *info) { - enum bpf_kptr_type type; + enum btf_field_type type; u32 res_id; /* Permit modifiers on the pointer itself */ @@ -3259,7 +3259,7 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t, const char *name, int sz, int align, - enum btf_field_type field_type, + enum btf_field_info_type field_type, struct btf_field_info *info, int info_cnt) { const struct btf_member *member; @@ -3311,7 +3311,7 @@ static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, const char *name, int sz, int align, - enum btf_field_type field_type, + enum btf_field_info_type field_type, struct btf_field_info *info, int info_cnt) { const struct btf_var_secinfo *vsi; @@ -3360,7 +3360,7 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, } static int btf_find_field(const struct btf *btf, const struct btf_type *t, - enum btf_field_type field_type, + enum btf_field_info_type field_type, struct btf_field_info *info, int info_cnt) { const char *name; @@ -3423,14 +3423,13 @@ int btf_find_timer(const struct btf *btf, const struct btf_type *t) return info.off; } -struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf, - const struct btf_type *t) +struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t) { - struct btf_field_info info_arr[BPF_MAP_VALUE_OFF_MAX]; - struct bpf_map_value_off *tab; + struct btf_field_info info_arr[BTF_FIELDS_MAX]; struct btf *kernel_btf = NULL; struct module *mod = NULL; - int ret, i, nr_off; + struct btf_record *rec; + int ret, i, cnt; ret = btf_find_field(btf, t, BTF_FIELD_KPTR, info_arr, ARRAY_SIZE(info_arr)); if (ret < 0) @@ -3438,12 +3437,12 @@ struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf, if (!ret) return NULL; - nr_off = ret; - tab = kzalloc(offsetof(struct bpf_map_value_off, off[nr_off]), GFP_KERNEL | __GFP_NOWARN); - if (!tab) + cnt = ret; + rec = kzalloc(offsetof(struct btf_record, fields[cnt]), GFP_KERNEL | __GFP_NOWARN); + if (!rec) return ERR_PTR(-ENOMEM); - - for (i = 0; i < nr_off; i++) { + rec->cnt = 0; + for (i = 0; i < cnt; i++) { const struct btf_type *t; s32 id; @@ -3500,28 +3499,24 @@ struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf, ret = -EINVAL; goto end_mod; } - tab->off[i].kptr.dtor = (void *)addr; + rec->fields[i].kptr.dtor = (void *)addr; } - tab->off[i].offset = info_arr[i].off; - tab->off[i].type = info_arr[i].type; - tab->off[i].kptr.btf_id = id; - tab->off[i].kptr.btf = kernel_btf; - tab->off[i].kptr.module = mod; + rec->field_mask |= info_arr[i].type; + rec->fields[i].offset = info_arr[i].off; + rec->fields[i].type = info_arr[i].type; + rec->fields[i].kptr.btf_id = id; + rec->fields[i].kptr.btf = kernel_btf; + rec->fields[i].kptr.module = mod; + rec->cnt++; } - tab->nr_off = nr_off; - return tab; + return rec; end_mod: module_put(mod); end_btf: btf_put(kernel_btf); end: - while (i--) { - btf_put(tab->off[i].kptr.btf); - if (tab->off[i].kptr.module) - module_put(tab->off[i].kptr.module); - } - kfree(tab); + btf_record_free(rec); return ERR_PTR(ret); } @@ -6370,7 +6365,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, /* kptr_get is only true for kfunc */ if (i == 0 && kptr_get) { - struct bpf_map_value_off_desc *off_desc; + struct btf_field *kptr_field; if (reg->type != PTR_TO_MAP_VALUE) { bpf_log(log, "arg#0 expected pointer to map value\n"); @@ -6386,8 +6381,8 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, return -EINVAL; } - off_desc = bpf_map_kptr_off_contains(reg->map_ptr, reg->off + reg->var_off.value); - if (!off_desc || off_desc->type != BPF_KPTR_REF) { + 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; @@ -6406,8 +6401,8 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, func_name, i, btf_type_str(ref_t), ref_tname); return -EINVAL; } - if (!btf_struct_ids_match(log, btf, ref_id, 0, off_desc->kptr.btf, - off_desc->kptr.btf_id, true)) { + 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; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index f39ee3e05589..c5ea8f9bb7a9 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -238,21 +238,20 @@ static void htab_free_prealloced_timers(struct bpf_htab *htab) } } -static void htab_free_prealloced_kptrs(struct bpf_htab *htab) +static void htab_free_prealloced_fields(struct bpf_htab *htab) { u32 num_entries = htab->map.max_entries; int i; - if (!map_value_has_kptrs(&htab->map)) + if (IS_ERR_OR_NULL(htab->map.record)) return; if (htab_has_extra_elems(htab)) num_entries += num_possible_cpus(); - for (i = 0; i < num_entries; i++) { struct htab_elem *elem; elem = get_htab_elem(htab, i); - bpf_map_free_kptrs(&htab->map, elem->key + round_up(htab->map.key_size, 8)); + bpf_obj_free_fields(htab->map.record, elem->key + round_up(htab->map.key_size, 8)); cond_resched(); } } @@ -766,8 +765,7 @@ static void check_and_free_fields(struct bpf_htab *htab, if (map_value_has_timer(&htab->map)) bpf_timer_cancel_and_free(map_value + htab->map.timer_off); - if (map_value_has_kptrs(&htab->map)) - bpf_map_free_kptrs(&htab->map, map_value); + bpf_obj_free_fields(htab->map.record, map_value); } /* It is called from the bpf_lru_list when the LRU needs to delete @@ -1517,11 +1515,11 @@ static void htab_map_free(struct bpf_map *map) if (!htab_is_prealloc(htab)) { delete_all_elements(htab); } else { - htab_free_prealloced_kptrs(htab); + htab_free_prealloced_fields(htab); prealloc_destroy(htab); } - bpf_map_free_kptr_off_tab(map); + 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/map_in_map.c b/kernel/bpf/map_in_map.c index 135205d0d560..d6c662183f88 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -52,7 +52,15 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) inner_map_meta->max_entries = inner_map->max_entries; inner_map_meta->spin_lock_off = inner_map->spin_lock_off; inner_map_meta->timer_off = inner_map->timer_off; - inner_map_meta->kptr_off_tab = bpf_map_copy_kptr_off_tab(inner_map); + 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); + } if (inner_map->btf) { btf_get(inner_map->btf); inner_map_meta->btf = inner_map->btf; @@ -72,7 +80,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) void bpf_map_meta_free(struct bpf_map *map_meta) { - bpf_map_free_kptr_off_tab(map_meta); + bpf_map_free_record(map_meta); btf_put(map_meta->btf); kfree(map_meta); } @@ -86,7 +94,7 @@ bool bpf_map_meta_equal(const struct bpf_map *meta0, meta0->value_size == meta1->value_size && meta0->timer_off == meta1->timer_off && meta0->map_flags == meta1->map_flags && - bpf_map_equal_kptr_off_tab(meta0, meta1); + btf_record_equal(meta0->record, meta1->record); } void *bpf_map_fd_get_ptr(struct bpf_map *map, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5887592eeb93..b80c0e2eb73f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -495,114 +495,134 @@ static void bpf_map_release_memcg(struct bpf_map *map) } #endif -static int bpf_map_kptr_off_cmp(const void *a, const void *b) +static int btf_field_cmp(const void *a, const void *b) { - const struct bpf_map_value_off_desc *off_desc1 = a, *off_desc2 = b; + const struct btf_field *f1 = a, *f2 = b; - if (off_desc1->offset < off_desc2->offset) + if (f1->offset < f2->offset) return -1; - else if (off_desc1->offset > off_desc2->offset) + else if (f1->offset > f2->offset) return 1; return 0; } -struct bpf_map_value_off_desc *bpf_map_kptr_off_contains(struct bpf_map *map, u32 offset) +struct btf_field *btf_record_find(const struct btf_record *rec, u32 offset, + enum btf_field_type type) { - /* Since members are iterated in btf_find_field in increasing order, - * offsets appended to kptr_off_tab are in increasing order, so we can - * do bsearch to find exact match. - */ - struct bpf_map_value_off *tab; + struct btf_field *field; - if (!map_value_has_kptrs(map)) + if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & type)) + return NULL; + field = bsearch(&offset, rec->fields, rec->cnt, sizeof(rec->fields[0]), btf_field_cmp); + if (!field || !(field->type & type)) return NULL; - tab = map->kptr_off_tab; - return bsearch(&offset, tab->off, tab->nr_off, sizeof(tab->off[0]), bpf_map_kptr_off_cmp); + return field; } -void bpf_map_free_kptr_off_tab(struct bpf_map *map) +void btf_record_free(struct btf_record *rec) { - struct bpf_map_value_off *tab = map->kptr_off_tab; int i; - if (!map_value_has_kptrs(map)) + if (IS_ERR_OR_NULL(rec)) return; - for (i = 0; i < tab->nr_off; i++) { - if (tab->off[i].kptr.module) - module_put(tab->off[i].kptr.module); - btf_put(tab->off[i].kptr.btf); + for (i = 0; i < rec->cnt; i++) { + switch (rec->fields[i].type) { + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: + if (rec->fields[i].kptr.module) + module_put(rec->fields[i].kptr.module); + btf_put(rec->fields[i].kptr.btf); + break; + default: + WARN_ON_ONCE(1); + continue; + } } - kfree(tab); - map->kptr_off_tab = NULL; + kfree(rec); +} + +void bpf_map_free_record(struct bpf_map *map) +{ + btf_record_free(map->record); + map->record = NULL; } -struct bpf_map_value_off *bpf_map_copy_kptr_off_tab(const struct bpf_map *map) +struct btf_record *btf_record_dup(const struct btf_record *rec) { - struct bpf_map_value_off *tab = map->kptr_off_tab, *new_tab; - int size, i; + const struct btf_field *fields; + struct btf_record *new_rec; + int ret, size, i; - if (!map_value_has_kptrs(map)) - return ERR_PTR(-ENOENT); - size = offsetof(struct bpf_map_value_off, off[tab->nr_off]); - new_tab = kmemdup(tab, size, GFP_KERNEL | __GFP_NOWARN); - if (!new_tab) + if (IS_ERR_OR_NULL(rec)) + return NULL; + size = offsetof(struct btf_record, fields[rec->cnt]); + new_rec = kmemdup(rec, size, GFP_KERNEL | __GFP_NOWARN); + if (!new_rec) return ERR_PTR(-ENOMEM); - /* Do a deep copy of the kptr_off_tab */ - for (i = 0; i < tab->nr_off; i++) { - btf_get(tab->off[i].kptr.btf); - if (tab->off[i].kptr.module && !try_module_get(tab->off[i].kptr.module)) { - while (i--) { - if (tab->off[i].kptr.module) - module_put(tab->off[i].kptr.module); - btf_put(tab->off[i].kptr.btf); + /* Do a deep copy of the btf_record */ + fields = rec->fields; + new_rec->cnt = 0; + for (i = 0; i < rec->cnt; i++) { + switch (fields[i].type) { + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: + btf_get(fields[i].kptr.btf); + if (fields[i].kptr.module && !try_module_get(fields[i].kptr.module)) { + ret = -ENXIO; + goto free; } - kfree(new_tab); - return ERR_PTR(-ENXIO); + break; + default: + ret = -EFAULT; + WARN_ON_ONCE(1); + goto free; } + new_rec->cnt++; } - return new_tab; + return new_rec; +free: + btf_record_free(new_rec); + return ERR_PTR(ret); } -bool bpf_map_equal_kptr_off_tab(const struct bpf_map *map_a, const struct bpf_map *map_b) +bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b) { - struct bpf_map_value_off *tab_a = map_a->kptr_off_tab, *tab_b = map_b->kptr_off_tab; - bool a_has_kptr = map_value_has_kptrs(map_a), b_has_kptr = map_value_has_kptrs(map_b); + bool a_has_fields = !IS_ERR_OR_NULL(rec_a), b_has_fields = !IS_ERR_OR_NULL(rec_b); int size; - if (!a_has_kptr && !b_has_kptr) + if (!a_has_fields && !b_has_fields) return true; - if (a_has_kptr != b_has_kptr) + if (a_has_fields != b_has_fields) return false; - if (tab_a->nr_off != tab_b->nr_off) + if (rec_a->cnt != rec_b->cnt) return false; - size = offsetof(struct bpf_map_value_off, off[tab_a->nr_off]); - return !memcmp(tab_a, tab_b, size); + size = offsetof(struct btf_record, fields[rec_a->cnt]); + return !memcmp(rec_a, rec_b, size); } -/* Caller must ensure map_value_has_kptrs is true. Note that this function can - * be called on a map value while the map_value is visible to BPF programs, as - * it ensures the correct synchronization, and we already enforce the same using - * the bpf_kptr_xchg helper on the BPF program side for referenced kptrs. - */ -void bpf_map_free_kptrs(struct bpf_map *map, void *map_value) +void bpf_obj_free_fields(const struct btf_record *rec, void *obj) { - struct bpf_map_value_off *tab = map->kptr_off_tab; - unsigned long *btf_id_ptr; + const struct btf_field *fields; int i; - for (i = 0; i < tab->nr_off; i++) { - struct bpf_map_value_off_desc *off_desc = &tab->off[i]; - unsigned long old_ptr; - - btf_id_ptr = map_value + off_desc->offset; - if (off_desc->type == BPF_KPTR_UNREF) { - u64 *p = (u64 *)btf_id_ptr; - - WRITE_ONCE(*p, 0); + if (IS_ERR_OR_NULL(rec)) + return; + fields = rec->fields; + for (i = 0; i < rec->cnt; i++) { + const struct btf_field *field = &fields[i]; + void *field_ptr = obj + field->offset; + + switch (fields[i].type) { + case BPF_KPTR_UNREF: + WRITE_ONCE(*(u64 *)field_ptr, 0); + break; + case BPF_KPTR_REF: + field->kptr.dtor((void *)xchg((unsigned long *)field_ptr, 0)); + break; + default: + WARN_ON_ONCE(1); continue; } - old_ptr = xchg(btf_id_ptr, 0); - off_desc->kptr.dtor((void *)old_ptr); } } @@ -612,10 +632,10 @@ static void bpf_map_free_deferred(struct work_struct *work) struct bpf_map *map = container_of(work, struct bpf_map, work); security_bpf_map_free(map); - kfree(map->off_arr); + kfree(map->field_offs); bpf_map_release_memcg(map); /* implementation dependent freeing, map_free callback also does - * bpf_map_free_kptr_off_tab, if needed. + * bpf_map_free_record, if needed. */ map->ops->map_free(map); } @@ -779,7 +799,7 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) int err; if (!map->ops->map_mmap || map_value_has_spin_lock(map) || - map_value_has_timer(map) || map_value_has_kptrs(map)) + map_value_has_timer(map) || !IS_ERR_OR_NULL(map->record)) return -ENOTSUPP; if (!(vma->vm_flags & VM_SHARED)) @@ -906,7 +926,7 @@ int map_check_no_btf(const struct bpf_map *map, return -ENOTSUPP; } -static int map_off_arr_cmp(const void *_a, const void *_b, const void *priv) +static int map_field_offs_cmp(const void *_a, const void *_b, const void *priv) { const u32 a = *(const u32 *)_a; const u32 b = *(const u32 *)_b; @@ -918,15 +938,15 @@ static int map_off_arr_cmp(const void *_a, const void *_b, const void *priv) return 0; } -static void map_off_arr_swap(void *_a, void *_b, int size, const void *priv) +static void map_field_offs_swap(void *_a, void *_b, int size, const void *priv) { struct bpf_map *map = (struct bpf_map *)priv; - u32 *off_base = map->off_arr->field_off; + u32 *off_base = map->field_offs->field_off; u32 *a = _a, *b = _b; u8 *sz_a, *sz_b; - sz_a = map->off_arr->field_sz + (a - off_base); - sz_b = map->off_arr->field_sz + (b - off_base); + sz_a = map->field_offs->field_sz + (a - off_base); + sz_b = map->field_offs->field_sz + (b - off_base); swap(*a, *b); swap(*sz_a, *sz_b); @@ -936,51 +956,51 @@ static int bpf_map_alloc_off_arr(struct bpf_map *map) { bool has_spin_lock = map_value_has_spin_lock(map); bool has_timer = map_value_has_timer(map); - bool has_kptrs = map_value_has_kptrs(map); - struct bpf_map_off_arr *off_arr; + bool has_fields = !IS_ERR_OR_NULL(map->record); + struct btf_field_offs *fo; u32 i; - if (!has_spin_lock && !has_timer && !has_kptrs) { - map->off_arr = NULL; + if (!has_spin_lock && !has_timer && !has_fields) { + map->field_offs = NULL; return 0; } - off_arr = kmalloc(sizeof(*map->off_arr), GFP_KERNEL | __GFP_NOWARN); - if (!off_arr) + fo = kmalloc(sizeof(*map->field_offs), GFP_KERNEL | __GFP_NOWARN); + if (!fo) return -ENOMEM; - map->off_arr = off_arr; + map->field_offs = fo; - off_arr->cnt = 0; + fo->cnt = 0; if (has_spin_lock) { - i = off_arr->cnt; + i = fo->cnt; - off_arr->field_off[i] = map->spin_lock_off; - off_arr->field_sz[i] = sizeof(struct bpf_spin_lock); - off_arr->cnt++; + fo->field_off[i] = map->spin_lock_off; + fo->field_sz[i] = sizeof(struct bpf_spin_lock); + fo->cnt++; } if (has_timer) { - i = off_arr->cnt; + i = fo->cnt; - off_arr->field_off[i] = map->timer_off; - off_arr->field_sz[i] = sizeof(struct bpf_timer); - off_arr->cnt++; + fo->field_off[i] = map->timer_off; + fo->field_sz[i] = sizeof(struct bpf_timer); + fo->cnt++; } - if (has_kptrs) { - struct bpf_map_value_off *tab = map->kptr_off_tab; - u32 *off = &off_arr->field_off[off_arr->cnt]; - u8 *sz = &off_arr->field_sz[off_arr->cnt]; + if (has_fields) { + struct btf_record *rec = map->record; + u32 *off = &fo->field_off[fo->cnt]; + u8 *sz = &fo->field_sz[fo->cnt]; - for (i = 0; i < tab->nr_off; i++) { - *off++ = tab->off[i].offset; - *sz++ = sizeof(u64); + for (i = 0; i < rec->cnt; i++) { + *off++ = rec->fields[i].offset; + *sz++ = btf_field_type_size(rec->fields[i].type); } - off_arr->cnt += tab->nr_off; + fo->cnt += rec->cnt; } - if (off_arr->cnt == 1) + if (fo->cnt == 1) return 0; - sort_r(off_arr->field_off, off_arr->cnt, sizeof(off_arr->field_off[0]), - map_off_arr_cmp, map_off_arr_swap, map); + sort_r(fo->field_off, fo->cnt, sizeof(fo->field_off[0]), + map_field_offs_cmp, map_field_offs_swap, map); return 0; } @@ -1038,8 +1058,10 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, return -EOPNOTSUPP; } - map->kptr_off_tab = btf_parse_kptrs(btf, value_type); - if (map_value_has_kptrs(map)) { + map->record = btf_parse_fields(btf, value_type); + if (!IS_ERR_OR_NULL(map->record)) { + int i; + if (!bpf_capable()) { ret = -EPERM; goto free_map_tab; @@ -1048,12 +1070,25 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, ret = -EACCES; goto free_map_tab; } - if (map->map_type != BPF_MAP_TYPE_HASH && - map->map_type != BPF_MAP_TYPE_LRU_HASH && - map->map_type != BPF_MAP_TYPE_ARRAY && - map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY) { - ret = -EOPNOTSUPP; - goto free_map_tab; + for (i = 0; i < sizeof(map->record->field_mask) * 8; i++) { + switch (map->record->field_mask & (1 << i)) { + case 0: + continue; + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: + if (map->map_type != BPF_MAP_TYPE_HASH && + map->map_type != BPF_MAP_TYPE_LRU_HASH && + map->map_type != BPF_MAP_TYPE_ARRAY && + map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY) { + ret = -EOPNOTSUPP; + goto free_map_tab; + } + break; + default: + /* Fail if map_type checks are missing for a field type */ + ret = -EOPNOTSUPP; + goto free_map_tab; + } } } @@ -1065,7 +1100,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, return ret; free_map_tab: - bpf_map_free_kptr_off_tab(map); + bpf_map_free_record(map); return ret; } @@ -1186,7 +1221,7 @@ static int map_create(union bpf_attr *attr) free_map_sec: security_bpf_map_free(map); free_map_off_arr: - kfree(map->off_arr); + kfree(map->field_offs); free_map: btf_put(map->btf); map->ops->map_free(map); @@ -1883,7 +1918,7 @@ static int map_freeze(const union bpf_attr *attr) return PTR_ERR(map); if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || - map_value_has_timer(map) || map_value_has_kptrs(map)) { + map_value_has_timer(map) || !IS_ERR_OR_NULL(map->record)) { fdput(f); return -ENOTSUPP; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 14d350a25d5d..5ce5364ce898 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -262,7 +262,7 @@ struct bpf_call_arg_meta { struct btf *ret_btf; u32 ret_btf_id; u32 subprogno; - struct bpf_map_value_off_desc *kptr_off_desc; + struct btf_field *kptr_field; u8 uninit_dynptr_regno; }; @@ -3674,15 +3674,15 @@ int check_ptr_off_reg(struct bpf_verifier_env *env, } static int map_kptr_match_type(struct bpf_verifier_env *env, - struct bpf_map_value_off_desc *off_desc, + struct btf_field *kptr_field, struct bpf_reg_state *reg, u32 regno) { - const char *targ_name = kernel_type_name(off_desc->kptr.btf, off_desc->kptr.btf_id); + const char *targ_name = kernel_type_name(kptr_field->kptr.btf, kptr_field->kptr.btf_id); int perm_flags = PTR_MAYBE_NULL; const char *reg_name = ""; /* Only unreferenced case accepts untrusted pointers */ - if (off_desc->type == BPF_KPTR_UNREF) + if (kptr_field->type == BPF_KPTR_UNREF) perm_flags |= PTR_UNTRUSTED; if (base_type(reg->type) != PTR_TO_BTF_ID || (type_flag(reg->type) & ~perm_flags)) @@ -3729,15 +3729,15 @@ static int map_kptr_match_type(struct bpf_verifier_env *env, * strict mode to true for type match. */ if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off, - off_desc->kptr.btf, off_desc->kptr.btf_id, - off_desc->type == BPF_KPTR_REF)) + kptr_field->kptr.btf, kptr_field->kptr.btf_id, + kptr_field->type == BPF_KPTR_REF)) goto bad_type; return 0; bad_type: verbose(env, "invalid kptr access, R%d type=%s%s ", regno, reg_type_str(env, reg->type), reg_name); verbose(env, "expected=%s%s", reg_type_str(env, PTR_TO_BTF_ID), targ_name); - if (off_desc->type == BPF_KPTR_UNREF) + if (kptr_field->type == BPF_KPTR_UNREF) verbose(env, " or %s%s\n", reg_type_str(env, PTR_TO_BTF_ID | PTR_UNTRUSTED), targ_name); else @@ -3747,7 +3747,7 @@ bad_type: static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, int value_regno, int insn_idx, - struct bpf_map_value_off_desc *off_desc) + struct btf_field *kptr_field) { struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; int class = BPF_CLASS(insn->code); @@ -3757,7 +3757,7 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, * - Reject cases where variable offset may touch kptr * - size of access (must be BPF_DW) * - tnum_is_const(reg->var_off) - * - off_desc->offset == off + reg->var_off.value + * - kptr_field->offset == off + reg->var_off.value */ /* Only BPF_[LDX,STX,ST] | BPF_MEM | BPF_DW is supported */ if (BPF_MODE(insn->code) != BPF_MEM) { @@ -3768,7 +3768,7 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, /* We only allow loading referenced kptr, since it will be marked as * untrusted, similar to unreferenced kptr. */ - if (class != BPF_LDX && off_desc->type == BPF_KPTR_REF) { + if (class != BPF_LDX && kptr_field->type == BPF_KPTR_REF) { verbose(env, "store to referenced kptr disallowed\n"); return -EACCES; } @@ -3778,19 +3778,19 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, /* We can simply mark the value_regno receiving the pointer * value from map as PTR_TO_BTF_ID, with the correct type. */ - mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID, off_desc->kptr.btf, - off_desc->kptr.btf_id, PTR_MAYBE_NULL | PTR_UNTRUSTED); + mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID, kptr_field->kptr.btf, + kptr_field->kptr.btf_id, PTR_MAYBE_NULL | PTR_UNTRUSTED); /* For mark_ptr_or_null_reg */ val_reg->id = ++env->id_gen; } else if (class == BPF_STX) { val_reg = reg_state(env, value_regno); if (!register_is_null(val_reg) && - map_kptr_match_type(env, off_desc, val_reg, value_regno)) + map_kptr_match_type(env, kptr_field, val_reg, value_regno)) return -EACCES; } else if (class == BPF_ST) { if (insn->imm) { verbose(env, "BPF_ST imm must be 0 when storing to kptr at off=%u\n", - off_desc->offset); + kptr_field->offset); return -EACCES; } } else { @@ -3809,7 +3809,8 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *reg = &state->regs[regno]; struct bpf_map *map = reg->map_ptr; - int err; + struct btf_record *rec; + int err, i; err = check_mem_region_access(env, regno, off, size, map->value_size, zero_size_allowed); @@ -3839,15 +3840,18 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, return -EACCES; } } - if (map_value_has_kptrs(map)) { - struct bpf_map_value_off *tab = map->kptr_off_tab; - int i; - - for (i = 0; i < tab->nr_off; i++) { - u32 p = tab->off[i].offset; - - if (reg->smin_value + off < p + sizeof(u64) && - p < reg->umax_value + off + size) { + if (IS_ERR_OR_NULL(map->record)) + return 0; + rec = map->record; + for (i = 0; i < rec->cnt; i++) { + struct btf_field *field = &rec->fields[i]; + u32 p = field->offset; + + if (reg->smin_value + off < p + btf_field_type_size(field->type) && + p < reg->umax_value + off + size) { + switch (field->type) { + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: if (src != ACCESS_DIRECT) { verbose(env, "kptr cannot be accessed indirectly by helper\n"); return -EACCES; @@ -3866,10 +3870,13 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, return -EACCES; } break; + default: + verbose(env, "field cannot be accessed directly by load/store\n"); + return -EACCES; } } } - return err; + return 0; } #define MAX_PACKET_OFF 0xffff @@ -4742,7 +4749,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_MAP_VALUE) { - struct bpf_map_value_off_desc *kptr_off_desc = NULL; + struct btf_field *kptr_field = NULL; if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { @@ -4756,11 +4763,10 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (err) return err; if (tnum_is_const(reg->var_off)) - kptr_off_desc = bpf_map_kptr_off_contains(reg->map_ptr, - off + reg->var_off.value); - if (kptr_off_desc) { - err = check_map_kptr_access(env, regno, value_regno, insn_idx, - kptr_off_desc); + kptr_field = btf_record_find(reg->map_ptr->record, + off + reg->var_off.value, BPF_KPTR); + if (kptr_field) { + err = check_map_kptr_access(env, regno, value_regno, insn_idx, kptr_field); } else if (t == BPF_READ && value_regno >= 0) { struct bpf_map *map = reg->map_ptr; @@ -5527,10 +5533,9 @@ static int process_kptr_func(struct bpf_verifier_env *env, int regno, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; - struct bpf_map_value_off_desc *off_desc; struct bpf_map *map_ptr = reg->map_ptr; + struct btf_field *kptr_field; u32 kptr_off; - int ret; if (!tnum_is_const(reg->var_off)) { verbose(env, @@ -5543,30 +5548,23 @@ static int process_kptr_func(struct bpf_verifier_env *env, int regno, map_ptr->name); return -EINVAL; } - if (!map_value_has_kptrs(map_ptr)) { - ret = PTR_ERR_OR_ZERO(map_ptr->kptr_off_tab); - if (ret == -E2BIG) - verbose(env, "map '%s' has more than %d kptr\n", map_ptr->name, - BPF_MAP_VALUE_OFF_MAX); - else if (ret == -EEXIST) - verbose(env, "map '%s' has repeating kptr BTF tags\n", map_ptr->name); - else - verbose(env, "map '%s' has no valid kptr\n", map_ptr->name); + if (!btf_record_has_field(map_ptr->record, BPF_KPTR)) { + verbose(env, "map '%s' has no valid kptr\n", map_ptr->name); return -EINVAL; } meta->map_ptr = map_ptr; kptr_off = reg->off + reg->var_off.value; - off_desc = bpf_map_kptr_off_contains(map_ptr, kptr_off); - if (!off_desc) { + kptr_field = btf_record_find(map_ptr->record, kptr_off, BPF_KPTR); + if (!kptr_field) { verbose(env, "off=%d doesn't point to kptr\n", kptr_off); return -EACCES; } - if (off_desc->type != BPF_KPTR_REF) { + if (kptr_field->type != BPF_KPTR_REF) { verbose(env, "off=%d kptr isn't referenced kptr\n", kptr_off); return -EACCES; } - meta->kptr_off_desc = off_desc; + meta->kptr_field = kptr_field; return 0; } @@ -5788,7 +5786,7 @@ found: } if (meta->func_id == BPF_FUNC_kptr_xchg) { - if (map_kptr_match_type(env, meta->kptr_off_desc, reg, regno)) + if (map_kptr_match_type(env, meta->kptr_field, reg, regno)) return -EACCES; } else { if (arg_btf_id == BPF_PTR_POISON) { @@ -7536,8 +7534,8 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag; if (func_id == BPF_FUNC_kptr_xchg) { - ret_btf = meta.kptr_off_desc->kptr.btf; - ret_btf_id = meta.kptr_off_desc->kptr.btf_id; + ret_btf = meta.kptr_field->kptr.btf; + ret_btf_id = meta.kptr_field->kptr.btf_id; } else { if (fn->ret_btf_id == BPF_PTR_POISON) { verbose(env, "verifier internal error:"); -- cgit v1.2.3 From db559117828d2448fe81ada051c60bcf39f822e9 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Nov 2022 00:39:56 +0530 Subject: bpf: Consolidate spin_lock, timer management into btf_record Now that kptr_off_tab has been refactored into btf_record, and can hold more than one specific field type, accomodate bpf_spin_lock and bpf_timer as well. While they don't require any more metadata than offset, having all special fields in one place allows us to share the same code for allocated user defined types and handle both map values and these allocated objects in a similar fashion. As an optimization, we still keep spin_lock_off and timer_off offsets in the btf_record structure, just to avoid having to find the btf_field struct each time their offset is needed. This is mostly needed to manipulate such objects in a map value at runtime. It's ok to hardcode just one offset as more than one field is disallowed. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221103191013.1236066-8-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 53 ++++--- include/linux/btf.h | 3 +- kernel/bpf/arraymap.c | 19 +-- kernel/bpf/bpf_local_storage.c | 2 +- kernel/bpf/btf.c | 323 ++++++++++++++++++++++------------------- kernel/bpf/hashtab.c | 24 +-- kernel/bpf/helpers.c | 6 +- kernel/bpf/local_storage.c | 2 +- kernel/bpf/map_in_map.c | 5 +- kernel/bpf/syscall.c | 135 ++++++++--------- kernel/bpf/verifier.c | 82 +++-------- net/core/bpf_sk_storage.c | 4 +- 12 files changed, 314 insertions(+), 344 deletions(-) (limited to 'include/linux/btf.h') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5f2a42033a37..aae85019abde 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -166,13 +166,13 @@ struct bpf_map_ops { enum { /* Support at most 8 pointers in a BTF type */ - BTF_FIELDS_MAX = 8, - BPF_MAP_OFF_ARR_MAX = BTF_FIELDS_MAX + - 1 + /* for bpf_spin_lock */ - 1, /* for bpf_timer */ + BTF_FIELDS_MAX = 10, + BPF_MAP_OFF_ARR_MAX = BTF_FIELDS_MAX, }; enum btf_field_type { + BPF_SPIN_LOCK = (1 << 0), + BPF_TIMER = (1 << 1), BPF_KPTR_UNREF = (1 << 2), BPF_KPTR_REF = (1 << 3), BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF, @@ -196,6 +196,8 @@ struct btf_field { struct btf_record { u32 cnt; u32 field_mask; + int spin_lock_off; + int timer_off; struct btf_field fields[]; }; @@ -220,10 +222,8 @@ struct bpf_map { u32 max_entries; u64 map_extra; /* any per-map-type extra fields */ u32 map_flags; - int spin_lock_off; /* >=0 valid offset, <0 error */ - struct btf_record *record; - int timer_off; /* >=0 valid offset, <0 error */ u32 id; + struct btf_record *record; int numa_node; u32 btf_key_type_id; u32 btf_value_type_id; @@ -257,9 +257,29 @@ struct bpf_map { bool frozen; /* write-once; write-protected by freeze_mutex */ }; +static inline const char *btf_field_type_name(enum btf_field_type type) +{ + switch (type) { + case BPF_SPIN_LOCK: + return "bpf_spin_lock"; + case BPF_TIMER: + return "bpf_timer"; + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: + return "kptr"; + default: + WARN_ON_ONCE(1); + return "unknown"; + } +} + static inline u32 btf_field_type_size(enum btf_field_type type) { switch (type) { + case BPF_SPIN_LOCK: + return sizeof(struct bpf_spin_lock); + case BPF_TIMER: + return sizeof(struct bpf_timer); case BPF_KPTR_UNREF: case BPF_KPTR_REF: return sizeof(u64); @@ -272,6 +292,10 @@ static inline u32 btf_field_type_size(enum btf_field_type type) static inline u32 btf_field_type_align(enum btf_field_type type) { switch (type) { + case BPF_SPIN_LOCK: + return __alignof__(struct bpf_spin_lock); + case BPF_TIMER: + return __alignof__(struct bpf_timer); case BPF_KPTR_UNREF: case BPF_KPTR_REF: return __alignof__(u64); @@ -288,22 +312,8 @@ static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_f return rec->field_mask & type; } -static inline bool map_value_has_spin_lock(const struct bpf_map *map) -{ - return map->spin_lock_off >= 0; -} - -static inline bool map_value_has_timer(const struct bpf_map *map) -{ - return map->timer_off >= 0; -} - static inline void check_and_init_map_value(struct bpf_map *map, void *dst) { - if (unlikely(map_value_has_spin_lock(map))) - memset(dst + map->spin_lock_off, 0, sizeof(struct bpf_spin_lock)); - if (unlikely(map_value_has_timer(map))) - memset(dst + map->timer_off, 0, sizeof(struct bpf_timer)); if (!IS_ERR_OR_NULL(map->record)) { struct btf_field *fields = map->record->fields; u32 cnt = map->record->cnt; @@ -1740,6 +1750,7 @@ void btf_record_free(struct btf_record *rec); void bpf_map_free_record(struct bpf_map *map); struct btf_record *btf_record_dup(const struct btf_record *rec); bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b); +void bpf_obj_free_timer(const struct btf_record *rec, void *obj); void bpf_obj_free_fields(const struct btf_record *rec, void *obj); struct bpf_map *bpf_map_get(u32 ufd); diff --git a/include/linux/btf.h b/include/linux/btf.h index 9e62717cdc7a..282006abd062 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -163,7 +163,8 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, u32 expected_offset, u32 expected_size); 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); +struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t, + u32 field_mask, u32 value_size); 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); const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 417f84342e98..672eb17ac421 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -306,13 +306,6 @@ static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key return 0; } -static void check_and_free_fields(struct bpf_array *arr, void *val) -{ - if (map_value_has_timer(&arr->map)) - bpf_timer_cancel_and_free(val + arr->map.timer_off); - bpf_obj_free_fields(arr->map.record, val); -} - /* Called from syscall or from eBPF program */ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) @@ -334,13 +327,13 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, return -EEXIST; if (unlikely((map_flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map))) + !btf_record_has_field(map->record, BPF_SPIN_LOCK))) return -EINVAL; if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { val = this_cpu_ptr(array->pptrs[index & array->index_mask]); copy_map_value(map, val, value); - check_and_free_fields(array, val); + bpf_obj_free_fields(array->map.record, val); } else { val = array->value + (u64)array->elem_size * (index & array->index_mask); @@ -348,7 +341,7 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, copy_map_value_locked(map, val, value, false); else copy_map_value(map, val, value); - check_and_free_fields(array, val); + bpf_obj_free_fields(array->map.record, val); } return 0; } @@ -385,7 +378,7 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, pptr = array->pptrs[index & array->index_mask]; for_each_possible_cpu(cpu) { copy_map_value_long(map, per_cpu_ptr(pptr, cpu), value + off); - check_and_free_fields(array, per_cpu_ptr(pptr, cpu)); + bpf_obj_free_fields(array->map.record, per_cpu_ptr(pptr, cpu)); off += size; } rcu_read_unlock(); @@ -409,11 +402,11 @@ static void array_map_free_timers(struct bpf_map *map) int i; /* We don't reset or free fields other than timer on uref dropping to zero. */ - if (!map_value_has_timer(map)) + if (!btf_record_has_field(map->record, BPF_TIMER)) return; for (i = 0; i < array->map.max_entries; i++) - bpf_timer_cancel_and_free(array_map_elem_ptr(array, i) + map->timer_off); + bpf_obj_free_timer(map->record, array_map_elem_ptr(array, i)); } /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index 93d9b1b17bc8..37020078d1c1 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -382,7 +382,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) || /* BPF_F_LOCK can only be used in a value with spin_lock */ unlikely((map_flags & BPF_F_LOCK) && - !map_value_has_spin_lock(&smap->map))) + !btf_record_has_field(smap->map.record, BPF_SPIN_LOCK))) return ERR_PTR(-EINVAL); if (gfp_flags == GFP_KERNEL && (map_flags & ~BPF_F_LOCK) != BPF_NOEXIST) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 8391a77138ee..3dad828db13c 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3205,16 +3205,20 @@ enum { struct btf_field_info { enum btf_field_type type; u32 off; - u32 type_id; + struct { + u32 type_id; + } kptr; }; static int btf_find_struct(const struct btf *btf, const struct btf_type *t, - u32 off, int sz, struct btf_field_info *info) + u32 off, int sz, enum btf_field_type field_type, + struct btf_field_info *info) { if (!__btf_type_is_struct(t)) return BTF_FIELD_IGNORE; if (t->size != sz) return BTF_FIELD_IGNORE; + info->type = field_type; info->off = off; return BTF_FIELD_FOUND; } @@ -3251,28 +3255,66 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, if (!__btf_type_is_struct(t)) return -EINVAL; - info->type_id = res_id; - info->off = off; info->type = type; + info->off = off; + info->kptr.type_id = res_id; return BTF_FIELD_FOUND; } -static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t, - const char *name, int sz, int align, - enum btf_field_info_type field_type, +static int btf_get_field_type(const char *name, u32 field_mask, u32 *seen_mask, + int *align, int *sz) +{ + int type = 0; + + if (field_mask & BPF_SPIN_LOCK) { + if (!strcmp(name, "bpf_spin_lock")) { + if (*seen_mask & BPF_SPIN_LOCK) + return -E2BIG; + *seen_mask |= BPF_SPIN_LOCK; + type = BPF_SPIN_LOCK; + goto end; + } + } + if (field_mask & BPF_TIMER) { + if (!strcmp(name, "bpf_timer")) { + if (*seen_mask & BPF_TIMER) + return -E2BIG; + *seen_mask |= BPF_TIMER; + type = BPF_TIMER; + goto end; + } + } + /* Only return BPF_KPTR when all other types with matchable names fail */ + if (field_mask & BPF_KPTR) { + type = BPF_KPTR_REF; + goto end; + } + return 0; +end: + *sz = btf_field_type_size(type); + *align = btf_field_type_align(type); + return type; +} + +static int btf_find_struct_field(const struct btf *btf, + const struct btf_type *t, u32 field_mask, struct btf_field_info *info, int info_cnt) { + int ret, idx = 0, align, sz, field_type; const struct btf_member *member; struct btf_field_info tmp; - int ret, idx = 0; - u32 i, off; + u32 i, off, seen_mask = 0; for_each_member(i, t, member) { const struct btf_type *member_type = btf_type_by_id(btf, member->type); - if (name && strcmp(__btf_name_by_offset(btf, member_type->name_off), name)) + field_type = btf_get_field_type(__btf_name_by_offset(btf, member_type->name_off), + field_mask, &seen_mask, &align, &sz); + if (field_type == 0) continue; + if (field_type < 0) + return field_type; off = __btf_member_bit_offset(t, member); if (off % 8) @@ -3280,17 +3322,18 @@ static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t return -EINVAL; off /= 8; if (off % align) - return -EINVAL; + continue; switch (field_type) { - case BTF_FIELD_SPIN_LOCK: - case BTF_FIELD_TIMER: - ret = btf_find_struct(btf, member_type, off, sz, + case BPF_SPIN_LOCK: + case BPF_TIMER: + ret = btf_find_struct(btf, member_type, off, sz, field_type, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) return ret; break; - case BTF_FIELD_KPTR: + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: ret = btf_find_kptr(btf, member_type, off, sz, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) @@ -3310,37 +3353,41 @@ static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t } static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, - const char *name, int sz, int align, - enum btf_field_info_type field_type, - struct btf_field_info *info, int info_cnt) + u32 field_mask, struct btf_field_info *info, + int info_cnt) { + int ret, idx = 0, align, sz, field_type; const struct btf_var_secinfo *vsi; struct btf_field_info tmp; - int ret, idx = 0; - u32 i, off; + u32 i, off, seen_mask = 0; for_each_vsi(i, t, vsi) { const struct btf_type *var = btf_type_by_id(btf, vsi->type); const struct btf_type *var_type = btf_type_by_id(btf, var->type); - off = vsi->offset; - - if (name && strcmp(__btf_name_by_offset(btf, var_type->name_off), name)) + field_type = btf_get_field_type(__btf_name_by_offset(btf, var_type->name_off), + field_mask, &seen_mask, &align, &sz); + if (field_type == 0) continue; + if (field_type < 0) + return field_type; + + off = vsi->offset; if (vsi->size != sz) continue; if (off % align) - return -EINVAL; + continue; switch (field_type) { - case BTF_FIELD_SPIN_LOCK: - case BTF_FIELD_TIMER: - ret = btf_find_struct(btf, var_type, off, sz, + case BPF_SPIN_LOCK: + case BPF_TIMER: + ret = btf_find_struct(btf, var_type, off, sz, field_type, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) return ret; break; - case BTF_FIELD_KPTR: + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: ret = btf_find_kptr(btf, var_type, off, sz, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) @@ -3360,78 +3407,98 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, } static int btf_find_field(const struct btf *btf, const struct btf_type *t, - enum btf_field_info_type field_type, - struct btf_field_info *info, int info_cnt) + u32 field_mask, struct btf_field_info *info, + int info_cnt) { - const char *name; - int sz, align; - - switch (field_type) { - case BTF_FIELD_SPIN_LOCK: - name = "bpf_spin_lock"; - sz = sizeof(struct bpf_spin_lock); - align = __alignof__(struct bpf_spin_lock); - break; - case BTF_FIELD_TIMER: - name = "bpf_timer"; - sz = sizeof(struct bpf_timer); - align = __alignof__(struct bpf_timer); - break; - case BTF_FIELD_KPTR: - name = NULL; - sz = sizeof(u64); - align = 8; - break; - default: - return -EFAULT; - } - if (__btf_type_is_struct(t)) - return btf_find_struct_field(btf, t, name, sz, align, field_type, info, info_cnt); + return btf_find_struct_field(btf, t, field_mask, info, info_cnt); else if (btf_type_is_datasec(t)) - return btf_find_datasec_var(btf, t, name, sz, align, field_type, info, info_cnt); + return btf_find_datasec_var(btf, t, field_mask, info, info_cnt); return -EINVAL; } -/* find 'struct bpf_spin_lock' in map value. - * return >= 0 offset if found - * and < 0 in case of error - */ -int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t) +static int btf_parse_kptr(const struct btf *btf, struct btf_field *field, + struct btf_field_info *info) { - struct btf_field_info info; + struct module *mod = NULL; + const struct btf_type *t; + struct btf *kernel_btf; int ret; + s32 id; - ret = btf_find_field(btf, t, BTF_FIELD_SPIN_LOCK, &info, 1); - if (ret < 0) - return ret; - if (!ret) - return -ENOENT; - return info.off; -} + /* Find type in map BTF, and use it to look up the matching type + * in vmlinux or module BTFs, by name and kind. + */ + t = btf_type_by_id(btf, info->kptr.type_id); + id = bpf_find_btf_id(__btf_name_by_offset(btf, t->name_off), BTF_INFO_KIND(t->info), + &kernel_btf); + if (id < 0) + return id; + + /* Find and stash the function pointer for the destruction function that + * needs to be eventually invoked from the map free path. + */ + if (info->type == BPF_KPTR_REF) { + const struct btf_type *dtor_func; + const char *dtor_func_name; + unsigned long addr; + s32 dtor_btf_id; + + /* This call also serves as a whitelist of allowed objects that + * can be used as a referenced pointer and be stored in a map at + * the same time. + */ + dtor_btf_id = btf_find_dtor_kfunc(kernel_btf, id); + if (dtor_btf_id < 0) { + ret = dtor_btf_id; + goto end_btf; + } -int btf_find_timer(const struct btf *btf, const struct btf_type *t) -{ - struct btf_field_info info; - int ret; + dtor_func = btf_type_by_id(kernel_btf, dtor_btf_id); + if (!dtor_func) { + ret = -ENOENT; + goto end_btf; + } - ret = btf_find_field(btf, t, BTF_FIELD_TIMER, &info, 1); - if (ret < 0) - return ret; - if (!ret) - return -ENOENT; - return info.off; + if (btf_is_module(kernel_btf)) { + mod = btf_try_get_module(kernel_btf); + if (!mod) { + ret = -ENXIO; + goto end_btf; + } + } + + /* We already verified dtor_func to be btf_type_is_func + * in register_btf_id_dtor_kfuncs. + */ + dtor_func_name = __btf_name_by_offset(kernel_btf, dtor_func->name_off); + addr = kallsyms_lookup_name(dtor_func_name); + if (!addr) { + ret = -EINVAL; + goto end_mod; + } + field->kptr.dtor = (void *)addr; + } + + field->kptr.btf_id = id; + field->kptr.btf = kernel_btf; + field->kptr.module = mod; + return 0; +end_mod: + module_put(mod); +end_btf: + btf_put(kernel_btf); + return ret; } -struct btf_record *btf_parse_fields(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) { struct btf_field_info info_arr[BTF_FIELDS_MAX]; - struct btf *kernel_btf = NULL; - struct module *mod = NULL; struct btf_record *rec; int ret, i, cnt; - ret = btf_find_field(btf, t, BTF_FIELD_KPTR, info_arr, ARRAY_SIZE(info_arr)); + ret = btf_find_field(btf, t, field_mask, info_arr, ARRAY_SIZE(info_arr)); if (ret < 0) return ERR_PTR(ret); if (!ret) @@ -3441,80 +3508,44 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type rec = kzalloc(offsetof(struct btf_record, fields[cnt]), GFP_KERNEL | __GFP_NOWARN); if (!rec) return ERR_PTR(-ENOMEM); - rec->cnt = 0; - for (i = 0; i < cnt; i++) { - const struct btf_type *t; - s32 id; - /* Find type in map BTF, and use it to look up the matching type - * in vmlinux or module BTFs, by name and kind. - */ - t = btf_type_by_id(btf, info_arr[i].type_id); - id = bpf_find_btf_id(__btf_name_by_offset(btf, t->name_off), BTF_INFO_KIND(t->info), - &kernel_btf); - if (id < 0) { - ret = id; + rec->spin_lock_off = -EINVAL; + rec->timer_off = -EINVAL; + for (i = 0; i < cnt; i++) { + if (info_arr[i].off + btf_field_type_size(info_arr[i].type) > value_size) { + WARN_ONCE(1, "verifier bug off %d size %d", info_arr[i].off, value_size); + ret = -EFAULT; goto end; } - /* Find and stash the function pointer for the destruction function that - * needs to be eventually invoked from the map free path. - */ - if (info_arr[i].type == BPF_KPTR_REF) { - const struct btf_type *dtor_func; - const char *dtor_func_name; - unsigned long addr; - s32 dtor_btf_id; - - /* This call also serves as a whitelist of allowed objects that - * can be used as a referenced pointer and be stored in a map at - * the same time. - */ - dtor_btf_id = btf_find_dtor_kfunc(kernel_btf, id); - if (dtor_btf_id < 0) { - ret = dtor_btf_id; - goto end_btf; - } - - dtor_func = btf_type_by_id(kernel_btf, dtor_btf_id); - if (!dtor_func) { - ret = -ENOENT; - goto end_btf; - } - - if (btf_is_module(kernel_btf)) { - mod = btf_try_get_module(kernel_btf); - if (!mod) { - ret = -ENXIO; - goto end_btf; - } - } - - /* We already verified dtor_func to be btf_type_is_func - * in register_btf_id_dtor_kfuncs. - */ - dtor_func_name = __btf_name_by_offset(kernel_btf, dtor_func->name_off); - addr = kallsyms_lookup_name(dtor_func_name); - if (!addr) { - ret = -EINVAL; - goto end_mod; - } - rec->fields[i].kptr.dtor = (void *)addr; - } - rec->field_mask |= info_arr[i].type; rec->fields[i].offset = info_arr[i].off; rec->fields[i].type = info_arr[i].type; - rec->fields[i].kptr.btf_id = id; - rec->fields[i].kptr.btf = kernel_btf; - rec->fields[i].kptr.module = mod; + + switch (info_arr[i].type) { + case BPF_SPIN_LOCK: + WARN_ON_ONCE(rec->spin_lock_off >= 0); + /* Cache offset for faster lookup at runtime */ + rec->spin_lock_off = rec->fields[i].offset; + break; + case BPF_TIMER: + WARN_ON_ONCE(rec->timer_off >= 0); + /* Cache offset for faster lookup at runtime */ + rec->timer_off = rec->fields[i].offset; + break; + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: + ret = btf_parse_kptr(btf, &rec->fields[i], &info_arr[i]); + if (ret < 0) + goto end; + break; + default: + ret = -EFAULT; + goto end; + } rec->cnt++; } return rec; -end_mod: - module_put(mod); -end_btf: - btf_put(kernel_btf); end: btf_record_free(rec); return ERR_PTR(ret); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index c5ea8f9bb7a9..50d254cd0709 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -222,7 +222,7 @@ static void htab_free_prealloced_timers(struct bpf_htab *htab) u32 num_entries = htab->map.max_entries; int i; - if (!map_value_has_timer(&htab->map)) + if (!btf_record_has_field(htab->map.record, BPF_TIMER)) return; if (htab_has_extra_elems(htab)) num_entries += num_possible_cpus(); @@ -231,9 +231,7 @@ static void htab_free_prealloced_timers(struct bpf_htab *htab) struct htab_elem *elem; elem = get_htab_elem(htab, i); - bpf_timer_cancel_and_free(elem->key + - round_up(htab->map.key_size, 8) + - htab->map.timer_off); + bpf_obj_free_timer(htab->map.record, elem->key + round_up(htab->map.key_size, 8)); cond_resched(); } } @@ -763,8 +761,6 @@ static void check_and_free_fields(struct bpf_htab *htab, { void *map_value = elem->key + round_up(htab->map.key_size, 8); - if (map_value_has_timer(&htab->map)) - bpf_timer_cancel_and_free(map_value + htab->map.timer_off); bpf_obj_free_fields(htab->map.record, map_value); } @@ -1089,7 +1085,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, head = &b->head; if (unlikely(map_flags & BPF_F_LOCK)) { - if (unlikely(!map_value_has_spin_lock(map))) + if (unlikely(!btf_record_has_field(map->record, BPF_SPIN_LOCK))) return -EINVAL; /* find an element without taking the bucket lock */ l_old = lookup_nulls_elem_raw(head, hash, key, key_size, @@ -1472,12 +1468,8 @@ static void htab_free_malloced_timers(struct bpf_htab *htab) struct htab_elem *l; hlist_nulls_for_each_entry(l, n, head, hash_node) { - /* We don't reset or free kptr on uref dropping to zero, - * hence just free timer. - */ - bpf_timer_cancel_and_free(l->key + - round_up(htab->map.key_size, 8) + - htab->map.timer_off); + /* We only free timer on uref dropping to zero */ + bpf_obj_free_timer(htab->map.record, l->key + round_up(htab->map.key_size, 8)); } cond_resched_rcu(); } @@ -1488,8 +1480,8 @@ static void htab_map_free_timers(struct bpf_map *map) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - /* We don't reset or free kptr on uref dropping to zero. */ - if (!map_value_has_timer(&htab->map)) + /* We only free timer on uref dropping to zero */ + if (!btf_record_has_field(htab->map.record, BPF_TIMER)) return; if (!htab_is_prealloc(htab)) htab_free_malloced_timers(htab); @@ -1673,7 +1665,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map, elem_map_flags = attr->batch.elem_flags; if ((elem_map_flags & ~BPF_F_LOCK) || - ((elem_map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map))) + ((elem_map_flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK))) return -EINVAL; map_flags = attr->batch.flags; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 124fd199ce5c..283f55bbeb70 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -366,9 +366,9 @@ void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, struct bpf_spin_lock *lock; if (lock_src) - lock = src + map->spin_lock_off; + lock = src + map->record->spin_lock_off; else - lock = dst + map->spin_lock_off; + lock = dst + map->record->spin_lock_off; preempt_disable(); __bpf_spin_lock_irqsave(lock); copy_map_value(map, dst, src); @@ -1169,7 +1169,7 @@ BPF_CALL_3(bpf_timer_init, struct bpf_timer_kern *, timer, struct bpf_map *, map ret = -ENOMEM; goto out; } - t->value = (void *)timer - map->timer_off; + t->value = (void *)timer - map->record->timer_off; t->map = map; t->prog = NULL; rcu_assign_pointer(t->callback_fn, NULL); diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 098cf336fae6..e90d9f63edc5 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -151,7 +151,7 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *key, return -EINVAL; if (unlikely((flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map))) + !btf_record_has_field(map->record, BPF_SPIN_LOCK))) return -EINVAL; storage = cgroup_storage_lookup((struct bpf_cgroup_storage_map *)map, diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index d6c662183f88..8ca0cca39d49 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -29,7 +29,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) return ERR_PTR(-ENOTSUPP); } - if (map_value_has_spin_lock(inner_map)) { + if (btf_record_has_field(inner_map->record, BPF_SPIN_LOCK)) { fdput(f); return ERR_PTR(-ENOTSUPP); } @@ -50,8 +50,6 @@ 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->spin_lock_off = inner_map->spin_lock_off; - inner_map_meta->timer_off = inner_map->timer_off; 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 @@ -92,7 +90,6 @@ bool bpf_map_meta_equal(const struct bpf_map *meta0, return meta0->map_type == meta1->map_type && meta0->key_size == meta1->key_size && meta0->value_size == meta1->value_size && - meta0->timer_off == meta1->timer_off && meta0->map_flags == meta1->map_flags && btf_record_equal(meta0->record, meta1->record); } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b80c0e2eb73f..53d6dc5cf0e2 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -527,6 +527,9 @@ void btf_record_free(struct btf_record *rec) return; for (i = 0; i < rec->cnt; i++) { switch (rec->fields[i].type) { + case BPF_SPIN_LOCK: + case BPF_TIMER: + break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: if (rec->fields[i].kptr.module) @@ -564,6 +567,9 @@ struct btf_record *btf_record_dup(const struct btf_record *rec) new_rec->cnt = 0; for (i = 0; i < rec->cnt; i++) { switch (fields[i].type) { + case BPF_SPIN_LOCK: + case BPF_TIMER: + break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: btf_get(fields[i].kptr.btf); @@ -600,6 +606,13 @@ bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *r return !memcmp(rec_a, rec_b, size); } +void bpf_obj_free_timer(const struct btf_record *rec, void *obj) +{ + if (WARN_ON_ONCE(!btf_record_has_field(rec, BPF_TIMER))) + return; + bpf_timer_cancel_and_free(obj + rec->timer_off); +} + void bpf_obj_free_fields(const struct btf_record *rec, void *obj) { const struct btf_field *fields; @@ -613,6 +626,11 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) void *field_ptr = obj + field->offset; switch (fields[i].type) { + case BPF_SPIN_LOCK: + break; + case BPF_TIMER: + bpf_timer_cancel_and_free(field_ptr); + break; case BPF_KPTR_UNREF: WRITE_ONCE(*(u64 *)field_ptr, 0); break; @@ -798,8 +816,7 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) struct bpf_map *map = filp->private_data; int err; - if (!map->ops->map_mmap || map_value_has_spin_lock(map) || - map_value_has_timer(map) || !IS_ERR_OR_NULL(map->record)) + if (!map->ops->map_mmap || !IS_ERR_OR_NULL(map->record)) return -ENOTSUPP; if (!(vma->vm_flags & VM_SHARED)) @@ -954,48 +971,30 @@ static void map_field_offs_swap(void *_a, void *_b, int size, const void *priv) static int bpf_map_alloc_off_arr(struct bpf_map *map) { - bool has_spin_lock = map_value_has_spin_lock(map); - bool has_timer = map_value_has_timer(map); bool has_fields = !IS_ERR_OR_NULL(map->record); struct btf_field_offs *fo; - u32 i; + struct btf_record *rec; + u32 i, *off; + u8 *sz; - if (!has_spin_lock && !has_timer && !has_fields) { + if (!has_fields) { map->field_offs = NULL; return 0; } - fo = kmalloc(sizeof(*map->field_offs), GFP_KERNEL | __GFP_NOWARN); + fo = kzalloc(sizeof(*map->field_offs), GFP_KERNEL | __GFP_NOWARN); if (!fo) return -ENOMEM; map->field_offs = fo; - fo->cnt = 0; - if (has_spin_lock) { - i = fo->cnt; - - fo->field_off[i] = map->spin_lock_off; - fo->field_sz[i] = sizeof(struct bpf_spin_lock); - fo->cnt++; - } - if (has_timer) { - i = fo->cnt; - - fo->field_off[i] = map->timer_off; - fo->field_sz[i] = sizeof(struct bpf_timer); - fo->cnt++; - } - if (has_fields) { - struct btf_record *rec = map->record; - u32 *off = &fo->field_off[fo->cnt]; - u8 *sz = &fo->field_sz[fo->cnt]; - - for (i = 0; i < rec->cnt; i++) { - *off++ = rec->fields[i].offset; - *sz++ = btf_field_type_size(rec->fields[i].type); - } - fo->cnt += rec->cnt; + rec = map->record; + off = fo->field_off; + sz = fo->field_sz; + for (i = 0; i < rec->cnt; i++) { + *off++ = rec->fields[i].offset; + *sz++ = btf_field_type_size(rec->fields[i].type); } + fo->cnt = rec->cnt; if (fo->cnt == 1) return 0; @@ -1026,39 +1025,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, if (!value_type || value_size != map->value_size) return -EINVAL; - map->spin_lock_off = btf_find_spin_lock(btf, value_type); - - if (map_value_has_spin_lock(map)) { - if (map->map_flags & BPF_F_RDONLY_PROG) - return -EACCES; - if (map->map_type != BPF_MAP_TYPE_HASH && - map->map_type != BPF_MAP_TYPE_ARRAY && - map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && - map->map_type != BPF_MAP_TYPE_SK_STORAGE && - map->map_type != BPF_MAP_TYPE_INODE_STORAGE && - map->map_type != BPF_MAP_TYPE_TASK_STORAGE && - map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) - return -ENOTSUPP; - if (map->spin_lock_off + sizeof(struct bpf_spin_lock) > - map->value_size) { - WARN_ONCE(1, - "verifier bug spin_lock_off %d value_size %d\n", - map->spin_lock_off, map->value_size); - return -EFAULT; - } - } - - map->timer_off = btf_find_timer(btf, value_type); - if (map_value_has_timer(map)) { - if (map->map_flags & BPF_F_RDONLY_PROG) - return -EACCES; - 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; - } - - map->record = btf_parse_fields(btf, value_type); + map->record = btf_parse_fields(btf, value_type, BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR, + map->value_size); if (!IS_ERR_OR_NULL(map->record)) { int i; @@ -1074,6 +1042,26 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, switch (map->record->field_mask & (1 << i)) { case 0: continue; + case BPF_SPIN_LOCK: + if (map->map_type != BPF_MAP_TYPE_HASH && + map->map_type != BPF_MAP_TYPE_ARRAY && + map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && + map->map_type != BPF_MAP_TYPE_SK_STORAGE && + map->map_type != BPF_MAP_TYPE_INODE_STORAGE && + map->map_type != BPF_MAP_TYPE_TASK_STORAGE && + map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) { + ret = -EOPNOTSUPP; + goto free_map_tab; + } + break; + case BPF_TIMER: + 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; + goto free_map_tab; + } + break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: if (map->map_type != BPF_MAP_TYPE_HASH && @@ -1153,8 +1141,6 @@ static int map_create(union bpf_attr *attr) mutex_init(&map->freeze_mutex); spin_lock_init(&map->owner.lock); - map->spin_lock_off = -EINVAL; - map->timer_off = -EINVAL; if (attr->btf_key_type_id || attr->btf_value_type_id || /* Even the map's value is a kernel's struct, * the bpf_prog.o must have BTF to begin with @@ -1368,7 +1354,7 @@ static int map_lookup_elem(union bpf_attr *attr) } if ((attr->flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map)) { + !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { err = -EINVAL; goto err_put; } @@ -1441,7 +1427,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) } if ((attr->flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map)) { + !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { err = -EINVAL; goto err_put; } @@ -1604,7 +1590,7 @@ int generic_map_delete_batch(struct bpf_map *map, return -EINVAL; if ((attr->batch.elem_flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map)) { + !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { return -EINVAL; } @@ -1661,7 +1647,7 @@ int generic_map_update_batch(struct bpf_map *map, return -EINVAL; if ((attr->batch.elem_flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map)) { + !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { return -EINVAL; } @@ -1724,7 +1710,7 @@ int generic_map_lookup_batch(struct bpf_map *map, return -EINVAL; if ((attr->batch.elem_flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map)) + !btf_record_has_field(map->record, BPF_SPIN_LOCK)) return -EINVAL; value_size = bpf_map_value_size(map); @@ -1846,7 +1832,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) } if ((attr->flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map)) { + !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { err = -EINVAL; goto err_put; } @@ -1917,8 +1903,7 @@ static int map_freeze(const union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); - if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || - map_value_has_timer(map) || !IS_ERR_OR_NULL(map->record)) { + if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || !IS_ERR_OR_NULL(map->record)) { fdput(f); return -ENOTSUPP; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5ce5364ce898..73a3516f1a48 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -454,7 +454,7 @@ static bool reg_type_not_null(enum bpf_reg_type type) static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) { return reg->type == PTR_TO_MAP_VALUE && - map_value_has_spin_lock(reg->map_ptr); + btf_record_has_field(reg->map_ptr->record, BPF_SPIN_LOCK); } static bool type_is_rdonly_mem(u32 type) @@ -1388,7 +1388,7 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) /* transfer reg's id which is unique for every map_lookup_elem * as UID of the inner map. */ - if (map_value_has_timer(map->inner_map_meta)) + if (btf_record_has_field(map->inner_map_meta->record, BPF_TIMER)) reg->map_uid = reg->id; } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { reg->type = PTR_TO_XDP_SOCK; @@ -3817,29 +3817,6 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, if (err) return err; - if (map_value_has_spin_lock(map)) { - u32 lock = map->spin_lock_off; - - /* if any part of struct bpf_spin_lock can be touched by - * load/store reject this program. - * To check that [x1, x2) overlaps with [y1, y2) - * it is sufficient to check x1 < y2 && y1 < x2. - */ - if (reg->smin_value + off < lock + sizeof(struct bpf_spin_lock) && - lock < reg->umax_value + off + size) { - verbose(env, "bpf_spin_lock cannot be accessed directly by load/store\n"); - return -EACCES; - } - } - if (map_value_has_timer(map)) { - u32 t = map->timer_off; - - if (reg->smin_value + off < t + sizeof(struct bpf_timer) && - t < reg->umax_value + off + size) { - verbose(env, "bpf_timer cannot be accessed directly by load/store\n"); - return -EACCES; - } - } if (IS_ERR_OR_NULL(map->record)) return 0; rec = map->record; @@ -3847,6 +3824,10 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, struct btf_field *field = &rec->fields[i]; u32 p = field->offset; + /* If any part of a field can be touched by load/store, reject + * this program. To check that [x1, x2) overlaps with [y1, y2), + * it is sufficient to check x1 < y2 && y1 < x2. + */ if (reg->smin_value + off < p + btf_field_type_size(field->type) && p < reg->umax_value + off + size) { switch (field->type) { @@ -3871,7 +3852,8 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, } break; default: - verbose(env, "field cannot be accessed directly by load/store\n"); + verbose(env, "%s cannot be accessed directly by load/store\n", + btf_field_type_name(field->type)); return -EACCES; } } @@ -5440,24 +5422,13 @@ static int process_spin_lock(struct bpf_verifier_env *env, int regno, map->name); return -EINVAL; } - if (!map_value_has_spin_lock(map)) { - if (map->spin_lock_off == -E2BIG) - verbose(env, - "map '%s' has more than one 'struct bpf_spin_lock'\n", - map->name); - else if (map->spin_lock_off == -ENOENT) - verbose(env, - "map '%s' doesn't have 'struct bpf_spin_lock'\n", - map->name); - else - verbose(env, - "map '%s' is not a struct type or bpf_spin_lock is mangled\n", - map->name); + if (!btf_record_has_field(map->record, BPF_SPIN_LOCK)) { + verbose(env, "map '%s' has no valid bpf_spin_lock\n", map->name); return -EINVAL; } - if (map->spin_lock_off != val + reg->off) { - verbose(env, "off %lld doesn't point to 'struct bpf_spin_lock'\n", - val + reg->off); + if (map->record->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); return -EINVAL; } if (is_lock) { @@ -5500,24 +5471,13 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno, map->name); return -EINVAL; } - if (!map_value_has_timer(map)) { - if (map->timer_off == -E2BIG) - verbose(env, - "map '%s' has more than one 'struct bpf_timer'\n", - map->name); - else if (map->timer_off == -ENOENT) - verbose(env, - "map '%s' doesn't have 'struct bpf_timer'\n", - map->name); - else - verbose(env, - "map '%s' is not a struct type or bpf_timer is mangled\n", - map->name); + if (!btf_record_has_field(map->record, BPF_TIMER)) { + verbose(env, "map '%s' has no valid bpf_timer\n", map->name); return -EINVAL; } - if (map->timer_off != val + reg->off) { + if (map->record->timer_off != val + reg->off) { verbose(env, "off %lld doesn't point to 'struct bpf_timer' that is at %d\n", - val + reg->off, map->timer_off); + val + reg->off, map->record->timer_off); return -EINVAL; } if (meta->map_ptr) { @@ -7470,7 +7430,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn regs[BPF_REG_0].map_uid = meta.map_uid; regs[BPF_REG_0].type = PTR_TO_MAP_VALUE | ret_flag; if (!type_may_be_null(ret_type) && - map_value_has_spin_lock(meta.map_ptr)) { + btf_record_has_field(meta.map_ptr->record, BPF_SPIN_LOCK)) { regs[BPF_REG_0].id = ++env->id_gen; } break; @@ -10381,7 +10341,7 @@ 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 (map_value_has_spin_lock(map)) + if (btf_record_has_field(map->record, BPF_SPIN_LOCK)) dst_reg->id = ++env->id_gen; } else if (insn->src_reg == BPF_PSEUDO_MAP_FD || insn->src_reg == BPF_PSEUDO_MAP_IDX) { @@ -12659,7 +12619,7 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, { enum bpf_prog_type prog_type = resolve_prog_type(prog); - if (map_value_has_spin_lock(map)) { + if (btf_record_has_field(map->record, BPF_SPIN_LOCK)) { if (prog_type == BPF_PROG_TYPE_SOCKET_FILTER) { verbose(env, "socket filter progs cannot use bpf_spin_lock yet\n"); return -EINVAL; @@ -12676,7 +12636,7 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, } } - if (map_value_has_timer(map)) { + if (btf_record_has_field(map->record, BPF_TIMER)) { if (is_tracing_prog_type(prog_type)) { verbose(env, "tracing progs cannot use bpf_timer yet\n"); return -EINVAL; diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 49884e7de080..9d2288c0736e 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -147,7 +147,7 @@ bpf_sk_storage_clone_elem(struct sock *newsk, if (!copy_selem) return NULL; - if (map_value_has_spin_lock(&smap->map)) + if (btf_record_has_field(smap->map.record, BPF_SPIN_LOCK)) copy_map_value_locked(&smap->map, SDATA(copy_selem)->data, SDATA(selem)->data, true); else @@ -566,7 +566,7 @@ static int diag_get(struct bpf_local_storage_data *sdata, struct sk_buff *skb) if (!nla_value) goto errout; - if (map_value_has_spin_lock(&smap->map)) + if (btf_record_has_field(smap->map.record, BPF_SPIN_LOCK)) copy_map_value_locked(&smap->map, nla_data(nla_value), sdata->data, true); else -- cgit v1.2.3 From f71b2f64177a199d5b1d2047e155d45fd98f564a Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Nov 2022 00:39:57 +0530 Subject: bpf: Refactor map->off_arr handling Refactor map->off_arr handling into generic functions that can work on their own without hardcoding map specific code. The btf_fields_offs structure is now returned from btf_parse_field_offs, which can be reused later for types in program BTF. All functions like copy_map_value, zero_map_value call generic underlying functions so that they can also be reused later for copying to values allocated in programs which encode specific fields. Later, some helper functions will also require access to this btf_field_offs structure to be able to skip over special fields at runtime. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221103191013.1236066-9-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 41 +++++++++++++++++------------ include/linux/btf.h | 1 + kernel/bpf/btf.c | 55 +++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 73 +++++++--------------------------------------------- 4 files changed, 89 insertions(+), 81 deletions(-) (limited to 'include/linux/btf.h') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index aae85019abde..798aec816970 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -341,57 +341,64 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) } /* copy everything but bpf_spin_lock, bpf_timer, and kptrs. There could be one of each. */ -static inline void __copy_map_value(struct bpf_map *map, void *dst, void *src, bool long_memcpy) +static inline void bpf_obj_memcpy(struct btf_field_offs *foffs, + void *dst, void *src, u32 size, + bool long_memcpy) { u32 curr_off = 0; int i; - if (likely(!map->field_offs)) { + if (likely(!foffs)) { if (long_memcpy) - bpf_long_memcpy(dst, src, round_up(map->value_size, 8)); + bpf_long_memcpy(dst, src, round_up(size, 8)); else - memcpy(dst, src, map->value_size); + memcpy(dst, src, size); return; } - for (i = 0; i < map->field_offs->cnt; i++) { - u32 next_off = map->field_offs->field_off[i]; + for (i = 0; i < foffs->cnt; i++) { + u32 next_off = foffs->field_off[i]; u32 sz = next_off - curr_off; memcpy(dst + curr_off, src + curr_off, sz); - curr_off += map->field_offs->field_sz[i]; + curr_off += foffs->field_sz[i]; } - memcpy(dst + curr_off, src + curr_off, map->value_size - curr_off); + memcpy(dst + curr_off, src + curr_off, size - curr_off); } static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) { - __copy_map_value(map, dst, src, false); + bpf_obj_memcpy(map->field_offs, dst, src, map->value_size, false); } static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src) { - __copy_map_value(map, dst, src, true); + bpf_obj_memcpy(map->field_offs, dst, src, map->value_size, true); } -static inline void zero_map_value(struct bpf_map *map, void *dst) +static inline void bpf_obj_memzero(struct btf_field_offs *foffs, void *dst, u32 size) { u32 curr_off = 0; int i; - if (likely(!map->field_offs)) { - memset(dst, 0, map->value_size); + if (likely(!foffs)) { + memset(dst, 0, size); return; } - for (i = 0; i < map->field_offs->cnt; i++) { - u32 next_off = map->field_offs->field_off[i]; + for (i = 0; i < foffs->cnt; i++) { + u32 next_off = foffs->field_off[i]; u32 sz = next_off - curr_off; memset(dst + curr_off, 0, sz); - curr_off += map->field_offs->field_sz[i]; + curr_off += foffs->field_sz[i]; } - memset(dst + curr_off, 0, map->value_size - curr_off); + memset(dst + curr_off, 0, size - curr_off); +} + +static inline void zero_map_value(struct bpf_map *map, void *dst) +{ + bpf_obj_memzero(map->field_offs, dst, map->value_size); } void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, diff --git a/include/linux/btf.h b/include/linux/btf.h index 282006abd062..d80345fa566b 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -165,6 +165,7 @@ 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); +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); const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 3dad828db13c..5579ff3a5b54 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3551,6 +3551,61 @@ end: return ERR_PTR(ret); } +static int btf_field_offs_cmp(const void *_a, const void *_b, const void *priv) +{ + const u32 a = *(const u32 *)_a; + const u32 b = *(const u32 *)_b; + + if (a < b) + return -1; + else if (a > b) + return 1; + return 0; +} + +static void btf_field_offs_swap(void *_a, void *_b, int size, const void *priv) +{ + struct btf_field_offs *foffs = (void *)priv; + u32 *off_base = foffs->field_off; + u32 *a = _a, *b = _b; + u8 *sz_a, *sz_b; + + sz_a = foffs->field_sz + (a - off_base); + sz_b = foffs->field_sz + (b - off_base); + + swap(*a, *b); + swap(*sz_a, *sz_b); +} + +struct btf_field_offs *btf_parse_field_offs(struct btf_record *rec) +{ + struct btf_field_offs *foffs; + u32 i, *off; + u8 *sz; + + BUILD_BUG_ON(ARRAY_SIZE(foffs->field_off) != ARRAY_SIZE(foffs->field_sz)); + if (IS_ERR_OR_NULL(rec) || WARN_ON_ONCE(rec->cnt > sizeof(foffs->field_off))) + return NULL; + + foffs = kzalloc(sizeof(*foffs), GFP_KERNEL | __GFP_NOWARN); + if (!foffs) + return ERR_PTR(-ENOMEM); + + off = foffs->field_off; + sz = foffs->field_sz; + for (i = 0; i < rec->cnt; i++) { + off[i] = rec->fields[i].offset; + sz[i] = btf_field_type_size(rec->fields[i].type); + } + foffs->cnt = rec->cnt; + + if (foffs->cnt == 1) + return foffs; + sort_r(foffs->field_off, foffs->cnt, sizeof(foffs->field_off[0]), + btf_field_offs_cmp, btf_field_offs_swap, foffs); + return foffs; +} + static void __btf_struct_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 53d6dc5cf0e2..85532d301124 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -943,66 +943,6 @@ int map_check_no_btf(const struct bpf_map *map, return -ENOTSUPP; } -static int map_field_offs_cmp(const void *_a, const void *_b, const void *priv) -{ - const u32 a = *(const u32 *)_a; - const u32 b = *(const u32 *)_b; - - if (a < b) - return -1; - else if (a > b) - return 1; - return 0; -} - -static void map_field_offs_swap(void *_a, void *_b, int size, const void *priv) -{ - struct bpf_map *map = (struct bpf_map *)priv; - u32 *off_base = map->field_offs->field_off; - u32 *a = _a, *b = _b; - u8 *sz_a, *sz_b; - - sz_a = map->field_offs->field_sz + (a - off_base); - sz_b = map->field_offs->field_sz + (b - off_base); - - swap(*a, *b); - swap(*sz_a, *sz_b); -} - -static int bpf_map_alloc_off_arr(struct bpf_map *map) -{ - bool has_fields = !IS_ERR_OR_NULL(map->record); - struct btf_field_offs *fo; - struct btf_record *rec; - u32 i, *off; - u8 *sz; - - if (!has_fields) { - map->field_offs = NULL; - return 0; - } - - fo = kzalloc(sizeof(*map->field_offs), GFP_KERNEL | __GFP_NOWARN); - if (!fo) - return -ENOMEM; - map->field_offs = fo; - - rec = map->record; - off = fo->field_off; - sz = fo->field_sz; - for (i = 0; i < rec->cnt; i++) { - *off++ = rec->fields[i].offset; - *sz++ = btf_field_type_size(rec->fields[i].type); - } - fo->cnt = rec->cnt; - - if (fo->cnt == 1) - return 0; - sort_r(fo->field_off, fo->cnt, sizeof(fo->field_off[0]), - map_field_offs_cmp, map_field_offs_swap, map); - return 0; -} - static int map_check_btf(struct bpf_map *map, const struct btf *btf, u32 btf_key_id, u32 btf_value_id) { @@ -1097,6 +1037,7 @@ free_map_tab: static int map_create(union bpf_attr *attr) { int numa_node = bpf_map_attr_numa_node(attr); + struct btf_field_offs *foffs; struct bpf_map *map; int f_flags; int err; @@ -1176,13 +1117,17 @@ static int map_create(union bpf_attr *attr) attr->btf_vmlinux_value_type_id; } - err = bpf_map_alloc_off_arr(map); - if (err) + + foffs = btf_parse_field_offs(map->record); + if (IS_ERR(foffs)) { + err = PTR_ERR(foffs); goto free_map; + } + map->field_offs = foffs; err = security_bpf_map_alloc(map); if (err) - goto free_map_off_arr; + goto free_map_field_offs; err = bpf_map_alloc_id(map); if (err) @@ -1206,7 +1151,7 @@ static int map_create(union bpf_attr *attr) free_map_sec: security_bpf_map_free(map); -free_map_off_arr: +free_map_field_offs: kfree(map->field_offs); free_map: btf_put(map->btf); -- cgit v1.2.3 From 8ffa5cc142137a59d6a10eb5273fa2ba5dcd4947 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 18 Nov 2022 07:25:56 +0530 Subject: bpf: Recognize lock and list fields in allocated objects Allow specifying bpf_spin_lock, bpf_list_head, bpf_list_node fields in a allocated object. Also update btf_struct_access to reject direct access to these special fields. A bpf_list_head allows implementing map-in-map style use cases, where an allocated object with bpf_list_head is linked into a list in a map value. This would require embedding a bpf_list_node, support for which is also included. The bpf_spin_lock is used to protect the bpf_list_head and other data. While we strictly don't require to hold a bpf_spin_lock while touching the bpf_list_head in such objects, as when have access to it, we have complete ownership of the object, the locking constraint is still kept and may be conditionally lifted in the future. Note that the specification of such types can be done just like map values, e.g.: struct bar { struct bpf_list_node node; }; struct foo { struct bpf_spin_lock lock; struct bpf_list_head head __contains(bar, node); struct bpf_list_node node; }; struct map_value { struct bpf_spin_lock lock; struct bpf_list_head head __contains(foo, node); }; To recognize such types in user BTF, we build a btf_struct_metas array of metadata items corresponding to each BTF ID. This is done once during the btf_parse stage to avoid having to do it each time during the verification process's requirement to inspect the metadata. Moreover, the computed metadata needs to be passed to some helpers in future patches which requires allocating them and storing them in the BTF that is pinned by the program itself, so that valid access can be assumed to such data during program runtime. A key thing to note is that once a btf_struct_meta is available for a type, both the btf_record and btf_field_offs should be available. It is critical that btf_field_offs is available in case special fields are present, as we extensively rely on special fields being zeroed out in map values and allocated objects in later patches. The code ensures that by bailing out in case of errors and ensuring both are available together. If the record is not available, the special fields won't be recognized, so not having both is also fine (in terms of being a verification error and not a runtime bug). Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221118015614.2013203-7-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 7 ++ include/linux/btf.h | 35 +++++++++ kernel/bpf/btf.c | 197 ++++++++++++++++++++++++++++++++++++++++++++++----- kernel/bpf/syscall.c | 4 ++ 4 files changed, 225 insertions(+), 18 deletions(-) (limited to 'include/linux/btf.h') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7440c20c4192..eb6ea53fa5a2 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -177,6 +177,7 @@ 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 { @@ -277,6 +278,8 @@ 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 +298,8 @@ 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 +318,8 @@ 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; diff --git a/include/linux/btf.h b/include/linux/btf.h index d80345fa566b..a01a8da20021 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -6,6 +6,8 @@ #include #include +#include +#include #include #include @@ -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; @@ -408,6 +421,23 @@ static inline struct btf_param *btf_params(const struct btf_type *t) return (struct btf_param *)(t + 1); } +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); +} + #ifdef CONFIG_BPF_SYSCALL struct bpf_prog; @@ -423,6 +453,7 @@ 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); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) @@ -454,6 +485,10 @@ 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; +} #endif static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type *t) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 9a596f430558..a04e10477567 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; @@ -1642,8 +1643,30 @@ 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 +3376,12 @@ 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 +3425,7 @@ 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 +3486,7 @@ 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) @@ -3671,6 +3702,8 @@ 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; @@ -5141,6 +5174,119 @@ 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 +5337,7 @@ 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 +5406,24 @@ 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 (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) @@ -6028,6 +6184,28 @@ 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); @@ -7269,23 +7447,6 @@ 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/syscall.c b/kernel/bpf/syscall.c index 4c20dcbc6526..56ae97d490f4 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: @@ -648,6 +650,8 @@ 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; -- cgit v1.2.3 From 865ce09a49d79d2b2c1d980f4c05ffc0b3517bdc Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 18 Nov 2022 07:25:57 +0530 Subject: bpf: Verify ownership relationships for user BTF types Ensure that there can be no ownership cycles among different types by way of having owning objects that can hold some other type as their element. For instance, a map value can only hold allocated objects, but these are allowed to have another bpf_list_head. To prevent unbounded recursion while freeing resources, elements of bpf_list_head in local kptrs can never have a bpf_list_head which are part of list in a map value. Later patches will verify this by having dedicated BTF selftests. Also, to make runtime destruction easier, once btf_struct_metas is fully populated, we can stash the metadata of the value type directly in the metadata of the list_head fields, as that allows easier access to the value type's layout to destruct it at runtime from the btf_field entry of the list head itself. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221118015614.2013203-8-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + include/linux/btf.h | 1 + kernel/bpf/btf.c | 71 ++++++++++++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 4 +++ 4 files changed, 77 insertions(+) (limited to 'include/linux/btf.h') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index eb6ea53fa5a2..323985a39ece 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -191,6 +191,7 @@ struct btf_field_list_head { struct btf *btf; u32 value_btf_id; u32 node_offset; + struct btf_record *value_rec; }; struct btf_field { diff --git a/include/linux/btf.h b/include/linux/btf.h index a01a8da20021..42d8f3730a8d 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -178,6 +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); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index a04e10477567..91aa9c96621f 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3723,6 +3723,67 @@ 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; @@ -5413,6 +5474,16 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, } 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_meta; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 56ae97d490f4..6140cbc3ed8a 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1054,6 +1054,10 @@ 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) -- cgit v1.2.3 From 00b85860feb809852af9a88cb4ca8766d7dff6a3 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 18 Nov 2022 07:26:01 +0530 Subject: bpf: Rewrite kfunc argument handling As we continue to add more features, argument types, kfunc flags, and different extensions to kfuncs, the code to verify the correctness of the kfunc prototype wrt the passed in registers has become ad-hoc and ugly to read. To make life easier, and make a very clear split between different stages of argument processing, move all the code into verifier.c and refactor into easier to read helpers and functions. This also makes sharing code within the verifier easier with kfunc argument processing. This will be more and more useful in later patches as we are now moving to implement very core BPF helpers as kfuncs, to keep them experimental before baking into UAPI. Remove all kfunc related bits now from btf_check_func_arg_match, as users have been converted away to refactored kfunc argument handling. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221118015614.2013203-12-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 11 - include/linux/bpf_verifier.h | 2 - include/linux/btf.h | 31 +- kernel/bpf/btf.c | 380 +------------- kernel/bpf/verifier.c | 545 ++++++++++++++++++++- .../selftests/bpf/prog_tests/kfunc_dynptr_param.c | 2 +- tools/testing/selftests/bpf/verifier/calls.c | 2 +- .../testing/selftests/bpf/verifier/ref_tracking.c | 4 +- 8 files changed, 573 insertions(+), 404 deletions(-) (limited to 'include/linux/btf.h') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 323985a39ece..0a74df731eb8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2109,22 +2109,11 @@ 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, diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 1db2b4dc7009..fb146b0ce006 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -603,8 +603,6 @@ 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 42d8f3730a8d..d5b26380a60f 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -338,6 +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); @@ -439,9 +449,10 @@ 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); } -#ifdef CONFIG_BPF_SYSCALL 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); @@ -455,6 +466,12 @@ 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) @@ -490,6 +507,18 @@ static inline struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf { 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/btf.c b/kernel/bpf/btf.c index 91aa9c96621f..4dcda4ae48c1 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -478,16 +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; @@ -5536,7 +5526,7 @@ 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) @@ -6322,8 +6312,8 @@ 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; @@ -6605,122 +6595,19 @@ 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)) { @@ -6746,14 +6633,6 @@ 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. */ @@ -6761,42 +6640,9 @@ 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); @@ -6809,88 +6655,14 @@ 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. */ @@ -6900,109 +6672,10 @@ 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, @@ -7015,36 +6688,13 @@ 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. @@ -7074,7 +6724,7 @@ 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. @@ -7117,7 +6767,7 @@ 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. @@ -7128,14 +6778,6 @@ 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. diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c8f3abe9b08e..7d7a91c54709 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5550,8 +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); @@ -7863,19 +7863,517 @@ 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; +}; + +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 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 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, +}; + +BTF_ID_LIST(kf_arg_btf_ids) +BTF_ID(struct, bpf_dynptr_kern) + +static bool is_kfunc_arg_dynptr(const struct btf *btf, + const struct btf_param *arg) +{ + 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[KF_ARG_DYNPTR_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_KPTR, /* PTR_TO_KPTR but type specific */ + KF_ARG_PTR_TO_DYNPTR, + 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 */ +}; + +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_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 ((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 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 (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_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_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_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_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_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) @@ -7896,24 +8394,34 @@ 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); @@ -7927,7 +8435,7 @@ 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)) { + if (is_kfunc_acquire(&meta) && !btf_type_is_struct_ptr(meta.btf, t)) { verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n"); return -EINVAL; } @@ -7966,20 +8474,23 @@ 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); 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/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 }, -- cgit v1.2.3 From 3f00c52393445ed49aadc1a567aa502c6333b1a1 Mon Sep 17 00:00:00 2001 From: David Vernet Date: Sat, 19 Nov 2022 23:10:02 -0600 Subject: bpf: Allow trusted pointers to be passed to KF_TRUSTED_ARGS kfuncs Kfuncs currently support specifying the KF_TRUSTED_ARGS flag to signal to the verifier that it should enforce that a BPF program passes it a "safe", trusted pointer. Currently, "safe" means that the pointer is either PTR_TO_CTX, or is refcounted. There may be cases, however, where the kernel passes a BPF program a safe / trusted pointer to an object that the BPF program wishes to use as a kptr, but because the object does not yet have a ref_obj_id from the perspective of the verifier, the program would be unable to pass it to a KF_ACQUIRE | KF_TRUSTED_ARGS kfunc. The solution is to expand the set of pointers that are considered trusted according to KF_TRUSTED_ARGS, so that programs can invoke kfuncs with these pointers without getting rejected by the verifier. There is already a PTR_UNTRUSTED flag that is set in some scenarios, such as when a BPF program reads a kptr directly from a map without performing a bpf_kptr_xchg() call. These pointers of course can and should be rejected by the verifier. Unfortunately, however, PTR_UNTRUSTED does not cover all the cases for safety that need to be addressed to adequately protect kfuncs. Specifically, pointers obtained by a BPF program "walking" a struct are _not_ considered PTR_UNTRUSTED according to BPF. For example, say that we were to add a kfunc called bpf_task_acquire(), with KF_ACQUIRE | KF_TRUSTED_ARGS, to acquire a struct task_struct *. If we only used PTR_UNTRUSTED to signal that a task was unsafe to pass to a kfunc, the verifier would mistakenly allow the following unsafe BPF program to be loaded: SEC("tp_btf/task_newtask") int BPF_PROG(unsafe_acquire_task, struct task_struct *task, u64 clone_flags) { struct task_struct *acquired, *nested; nested = task->last_wakee; /* Would not be rejected by the verifier. */ acquired = bpf_task_acquire(nested); if (!acquired) return 0; bpf_task_release(acquired); return 0; } To address this, this patch defines a new type flag called PTR_TRUSTED which tracks whether a PTR_TO_BTF_ID pointer is safe to pass to a KF_TRUSTED_ARGS kfunc or a BPF helper function. PTR_TRUSTED pointers are passed directly from the kernel as a tracepoint or struct_ops callback argument. Any nested pointer that is obtained from walking a PTR_TRUSTED pointer is no longer PTR_TRUSTED. From the example above, the struct task_struct *task argument is PTR_TRUSTED, but the 'nested' pointer obtained from 'task->last_wakee' is not PTR_TRUSTED. A subsequent patch will add kfuncs for storing a task kfunc as a kptr, and then another patch will add selftests to validate. Signed-off-by: David Vernet Link: https://lore.kernel.org/r/20221120051004.3605026-3-void@manifault.com Signed-off-by: Alexei Starovoitov --- Documentation/bpf/kfuncs.rst | 30 +++++----- include/linux/bpf.h | 30 ++++++++++ include/linux/bpf_verifier.h | 7 +++ include/linux/btf.h | 65 ++++++++++++-------- kernel/bpf/btf.c | 8 +++ kernel/bpf/verifier.c | 69 ++++++++++++++++++---- kernel/trace/bpf_trace.c | 2 +- net/ipv4/bpf_tcp_ca.c | 4 +- tools/testing/selftests/bpf/verifier/calls.c | 2 +- .../testing/selftests/bpf/verifier/ref_tracking.c | 4 +- 10 files changed, 164 insertions(+), 57 deletions(-) (limited to 'include/linux/btf.h') diff --git a/Documentation/bpf/kfuncs.rst b/Documentation/bpf/kfuncs.rst index 3b1501c3b6cd..90774479ab7a 100644 --- a/Documentation/bpf/kfuncs.rst +++ b/Documentation/bpf/kfuncs.rst @@ -161,22 +161,20 @@ KF_ACQUIRE and KF_RET_NULL flags. -------------------------- The KF_TRUSTED_ARGS flag is used for kfuncs taking pointer arguments. It -indicates that the all pointer arguments will always have a guaranteed lifetime, -and pointers to kernel objects are always passed to helpers in their unmodified -form (as obtained from acquire kfuncs). - -It can be used to enforce that a pointer to a refcounted object acquired from a -kfunc or BPF helper is passed as an argument to this kfunc without any -modifications (e.g. pointer arithmetic) such that it is trusted and points to -the original object. - -Meanwhile, it is also allowed pass pointers to normal memory to such kfuncs, -but those can have a non-zero offset. - -This flag is often used for kfuncs that operate (change some property, perform -some operation) on an object that was obtained using an acquire kfunc. Such -kfuncs need an unchanged pointer to ensure the integrity of the operation being -performed on the expected object. +indicates that the all pointer arguments are valid, and that all pointers to +BTF objects have been passed in their unmodified form (that is, at a zero +offset, and without having been obtained from walking another pointer). + +There are two types of pointers to kernel objects which are considered "valid": + +1. Pointers which are passed as tracepoint or struct_ops callback arguments. +2. Pointers which were returned from a KF_ACQUIRE or KF_KPTR_GET kfunc. + +Pointers to non-BTF objects (e.g. scalar pointers) may also be passed to +KF_TRUSTED_ARGS kfuncs, and may have a non-zero offset. + +The definition of "valid" pointers is subject to change at any time, and has +absolutely no ABI stability guarantees. 2.4.6 KF_SLEEPABLE flag ----------------------- diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8b32376ce746..c9eafa67f2a2 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -543,6 +543,35 @@ enum bpf_type_flag { */ MEM_ALLOC = BIT(11 + BPF_BASE_TYPE_BITS), + /* PTR was passed from the kernel in a trusted context, and may be + * passed to KF_TRUSTED_ARGS kfuncs or BPF helper functions. + * Confusingly, this is _not_ the opposite of PTR_UNTRUSTED above. + * PTR_UNTRUSTED refers to a kptr that was read directly from a map + * without invoking bpf_kptr_xchg(). What we really need to know is + * whether a pointer is safe to pass to a kfunc or BPF helper function. + * While PTR_UNTRUSTED pointers are unsafe to pass to kfuncs and BPF + * helpers, they do not cover all possible instances of unsafe + * pointers. For example, a pointer that was obtained from walking a + * struct will _not_ get the PTR_UNTRUSTED type modifier, despite the + * fact that it may be NULL, invalid, etc. This is due to backwards + * compatibility requirements, as this was the behavior that was first + * introduced when kptrs were added. The behavior is now considered + * deprecated, and PTR_UNTRUSTED will eventually be removed. + * + * PTR_TRUSTED, on the other hand, is a pointer that the kernel + * guarantees to be valid and safe to pass to kfuncs and BPF helpers. + * For example, pointers passed to tracepoint arguments are considered + * PTR_TRUSTED, as are pointers that are passed to struct_ops + * callbacks. As alluded to above, pointers that are obtained from + * walking PTR_TRUSTED pointers are _not_ trusted. For example, if a + * struct task_struct *task is PTR_TRUSTED, then accessing + * task->last_wakee will lose the PTR_TRUSTED modifier when it's stored + * in a BPF register. Similarly, pointers passed to certain programs + * types such as kretprobes are not guaranteed to be valid, as they may + * for example contain an object that was recently freed. + */ + PTR_TRUSTED = BIT(12 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; @@ -636,6 +665,7 @@ enum bpf_return_type { RET_PTR_TO_RINGBUF_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_RINGBUF | RET_PTR_TO_MEM, RET_PTR_TO_DYNPTR_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_MEM, RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID, + RET_PTR_TO_BTF_ID_TRUSTED = PTR_TRUSTED | RET_PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 608dde740fef..545152ac136c 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -680,4 +680,11 @@ static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) } } +#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | PTR_TRUSTED) + +static inline bool bpf_type_has_unsafe_modifiers(u32 type) +{ + return type_flag(type) & ~BPF_REG_TRUSTED_MODIFIERS; +} + #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/btf.h b/include/linux/btf.h index d5b26380a60f..d38aa4251c28 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -19,36 +19,53 @@ #define KF_RELEASE (1 << 1) /* kfunc is a release function */ #define KF_RET_NULL (1 << 2) /* kfunc returns a pointer that may be NULL */ #define KF_KPTR_GET (1 << 3) /* kfunc returns reference to a kptr */ -/* Trusted arguments are those which are meant to be referenced arguments with - * unchanged offset. It is used to enforce that pointers obtained from acquire - * kfuncs remain unmodified when being passed to helpers taking trusted args. +/* Trusted arguments are those which are guaranteed to be valid when passed to + * the kfunc. It is used to enforce that pointers obtained from either acquire + * kfuncs, or from the main kernel on a tracepoint or struct_ops callback + * invocation, remain unmodified when being passed to helpers taking trusted + * args. * - * Consider - * struct foo { - * int data; - * struct foo *next; - * }; + * Consider, for example, the following new task tracepoint: * - * struct bar { - * int data; - * struct foo f; - * }; + * SEC("tp_btf/task_newtask") + * int BPF_PROG(new_task_tp, struct task_struct *task, u64 clone_flags) + * { + * ... + * } * - * struct foo *f = alloc_foo(); // Acquire kfunc - * struct bar *b = alloc_bar(); // Acquire kfunc + * And the following kfunc: * - * If a kfunc set_foo_data() wants to operate only on the allocated object, it - * will set the KF_TRUSTED_ARGS flag, which will prevent unsafe usage like: + * BTF_ID_FLAGS(func, bpf_task_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS) * - * set_foo_data(f, 42); // Allowed - * set_foo_data(f->next, 42); // Rejected, non-referenced pointer - * set_foo_data(&f->next, 42);// Rejected, referenced, but wrong type - * set_foo_data(&b->f, 42); // Rejected, referenced, but bad offset + * All invocations to the kfunc must pass the unmodified, unwalked task: * - * In the final case, usually for the purposes of type matching, it is deduced - * by looking at the type of the member at the offset, but due to the - * requirement of trusted argument, this deduction will be strict and not done - * for this case. + * bpf_task_acquire(task); // Allowed + * bpf_task_acquire(task->last_wakee); // Rejected, walked task + * + * Programs may also pass referenced tasks directly to the kfunc: + * + * struct task_struct *acquired; + * + * acquired = bpf_task_acquire(task); // Allowed, same as above + * bpf_task_acquire(acquired); // Allowed + * bpf_task_acquire(task); // Allowed + * bpf_task_acquire(acquired->last_wakee); // Rejected, walked task + * + * Programs may _not_, however, pass a task from an arbitrary fentry/fexit, or + * kprobe/kretprobe to the kfunc, as BPF cannot guarantee that all of these + * pointers are guaranteed to be safe. For example, the following BPF program + * would be rejected: + * + * SEC("kretprobe/free_task") + * int BPF_PROG(free_task_probe, struct task_struct *tsk) + * { + * struct task_struct *acquired; + * + * acquired = bpf_task_acquire(acquired); // Rejected, not a trusted pointer + * bpf_task_release(acquired); + * + * return 0; + * } */ #define KF_TRUSTED_ARGS (1 << 4) /* kfunc only takes trusted pointer arguments */ #define KF_SLEEPABLE (1 << 5) /* kfunc may sleep */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index f7d5fab61535..d52054ec69c9 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5799,6 +5799,11 @@ static u32 get_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto, return nr_args + 1; } +static bool prog_type_args_trusted(enum bpf_prog_type prog_type) +{ + return prog_type == BPF_PROG_TYPE_TRACING || prog_type == BPF_PROG_TYPE_STRUCT_OPS; +} + bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) @@ -5942,6 +5947,9 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, } info->reg_type = PTR_TO_BTF_ID; + if (prog_type_args_trusted(prog->type)) + info->reg_type |= PTR_TRUSTED; + if (tgt_prog) { enum bpf_prog_type tgt_type; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 67a6f11d953c..5bc9d84d7924 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -589,12 +589,13 @@ static const char *reg_type_str(struct bpf_verifier_env *env, strncpy(postfix, "_or_null", 16); } - snprintf(prefix, sizeof(prefix), "%s%s%s%s%s", + snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s", type & MEM_RDONLY ? "rdonly_" : "", type & MEM_RINGBUF ? "ringbuf_" : "", type & MEM_USER ? "user_" : "", type & MEM_PERCPU ? "percpu_" : "", - type & PTR_UNTRUSTED ? "untrusted_" : "" + type & PTR_UNTRUSTED ? "untrusted_" : "", + type & PTR_TRUSTED ? "trusted_" : "" ); snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s", @@ -3856,7 +3857,7 @@ static int map_kptr_match_type(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno) { const char *targ_name = kernel_type_name(kptr_field->kptr.btf, kptr_field->kptr.btf_id); - int perm_flags = PTR_MAYBE_NULL; + int perm_flags = PTR_MAYBE_NULL | PTR_TRUSTED; const char *reg_name = ""; /* Only unreferenced case accepts untrusted pointers */ @@ -4732,6 +4733,9 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, if (type_flag(reg->type) & PTR_UNTRUSTED) flag |= PTR_UNTRUSTED; + /* Any pointer obtained from walking a trusted pointer is no longer trusted. */ + flag &= ~PTR_TRUSTED; + if (atype == BPF_READ && value_regno >= 0) mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id, flag); @@ -5844,6 +5848,7 @@ static const struct bpf_reg_types btf_id_sock_common_types = { PTR_TO_TCP_SOCK, PTR_TO_XDP_SOCK, PTR_TO_BTF_ID, + PTR_TO_BTF_ID | PTR_TRUSTED, }, .btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], }; @@ -5884,8 +5889,18 @@ 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 percpu_btf_ptr_types = { .types = { PTR_TO_BTF_ID | MEM_PERCPU } }; +static const struct bpf_reg_types btf_ptr_types = { + .types = { + PTR_TO_BTF_ID, + PTR_TO_BTF_ID | PTR_TRUSTED, + }, +}; +static const struct bpf_reg_types percpu_btf_ptr_types = { + .types = { + PTR_TO_BTF_ID | MEM_PERCPU, + PTR_TO_BTF_ID | MEM_PERCPU | PTR_TRUSTED, + } +}; 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 } }; static const struct bpf_reg_types const_str_ptr_types = { .types = { PTR_TO_MAP_VALUE } }; @@ -5973,7 +5988,7 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno, return -EACCES; found: - if (reg->type == PTR_TO_BTF_ID) { + if (reg->type == PTR_TO_BTF_ID || reg->type & PTR_TRUSTED) { /* For bpf_sk_release, it needs to match against first member * 'struct sock_common', hence make an exception for it. This * allows bpf_sk_release to work for multiple socket types. @@ -6055,6 +6070,8 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, */ case PTR_TO_BTF_ID: case PTR_TO_BTF_ID | MEM_ALLOC: + case PTR_TO_BTF_ID | PTR_TRUSTED: + case PTR_TO_BTF_ID | MEM_ALLOC | PTR_TRUSTED: /* 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. @@ -7939,6 +7956,25 @@ 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 is_trusted_reg(const struct bpf_reg_state *reg) +{ + /* A referenced register is always trusted. */ + if (reg->ref_obj_id) + return true; + + /* If a register is not referenced, it is trusted if it has either the + * MEM_ALLOC or PTR_TRUSTED type modifiers, and no others. Some of the + * other type modifiers may be safe, but we elect to take an opt-in + * approach here as some (e.g. PTR_UNTRUSTED and PTR_MAYBE_NULL) are + * not. + * + * Eventually, we should make PTR_TRUSTED the single source of truth + * for whether a register is trusted. + */ + return type_flag(reg->type) & BPF_REG_TRUSTED_MODIFIERS && + !bpf_type_has_unsafe_modifiers(reg->type); +} + static bool __kfunc_param_match_suffix(const struct btf *btf, const struct btf_param *arg, const char *suffix) @@ -8220,7 +8256,7 @@ static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env, const char *reg_ref_tname; u32 reg_ref_id; - if (reg->type == PTR_TO_BTF_ID) { + if (base_type(reg->type) == PTR_TO_BTF_ID) { reg_btf = reg->btf; reg_ref_id = reg->btf_id; } else { @@ -8366,6 +8402,7 @@ static int check_reg_allocation_locked(struct bpf_verifier_env *env, struct bpf_ ptr = reg->map_ptr; break; case PTR_TO_BTF_ID | MEM_ALLOC: + case PTR_TO_BTF_ID | MEM_ALLOC | PTR_TRUSTED: ptr = reg->btf; break; default: @@ -8596,8 +8633,9 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ 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); + + if (!is_trusted_reg(reg)) { + verbose(env, "R%d must be referenced or trusted\n", regno); return -EINVAL; } fallthrough; @@ -8702,9 +8740,13 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ 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); + if ((base_type(reg->type) != PTR_TO_BTF_ID || + bpf_type_has_unsafe_modifiers(reg->type)) && + !reg2btf_ids[base_type(reg->type)]) { + verbose(env, "arg#%d is %s ", i, reg_type_str(env, reg->type)); + verbose(env, "expected %s or socket\n", + reg_type_str(env, base_type(reg->type) | + (type_flag(reg->type) & BPF_REG_TRUSTED_MODIFIERS))); return -EINVAL; } ret = process_kf_arg_ptr_to_btf_id(env, reg, ref_t, ref_tname, ref_id, meta, i); @@ -14713,6 +14755,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) break; case PTR_TO_BTF_ID: case PTR_TO_BTF_ID | PTR_UNTRUSTED: + case PTR_TO_BTF_ID | PTR_TRUSTED: /* 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 @@ -14720,6 +14763,8 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) * for this case. */ case PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED: + case PTR_TO_BTF_ID | PTR_UNTRUSTED | PTR_TRUSTED: + case PTR_TO_BTF_ID | PTR_UNTRUSTED | MEM_ALLOC | PTR_TRUSTED: if (type == BPF_READ) { insn->code = BPF_LDX | BPF_PROBE_MEM | BPF_SIZE((insn)->code); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index f2d8d070d024..5b9008bc597b 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -774,7 +774,7 @@ BPF_CALL_0(bpf_get_current_task_btf) const struct bpf_func_proto bpf_get_current_task_btf_proto = { .func = bpf_get_current_task_btf, .gpl_only = true, - .ret_type = RET_PTR_TO_BTF_ID, + .ret_type = RET_PTR_TO_BTF_ID_TRUSTED, .ret_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], }; diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index d15c91de995f..4517d2bd186a 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -61,7 +61,9 @@ static bool bpf_tcp_ca_is_valid_access(int off, int size, if (!bpf_tracing_btf_ctx_access(off, size, type, prog, info)) return false; - if (info->reg_type == PTR_TO_BTF_ID && info->btf_id == sock_id) + if (base_type(info->reg_type) == PTR_TO_BTF_ID && + !bpf_type_has_unsafe_modifiers(info->reg_type) && + info->btf_id == sock_id) /* promote it to tcp_sock */ info->btf_id = tcp_sock_id; diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index 86d6fef2e3b4..3193915c5ee6 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 expected pointer to btf or socket", + .errstr = "arg#0 is ptr_or_null_ expected ptr_ 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 55cba01c99d5..9540164712b7 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 expected pointer to btf or socket", + .errstr = "arg#0 is ptr_or_null_ expected ptr_ 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 expected pointer to btf or socket", + .errstr = "arg#0 is ptr_or_null_ expected ptr_ or socket", .fixup_kfunc_btf_id = { { "bpf_lookup_system_key", 1 }, { "bpf_key_put", 3 }, -- cgit v1.2.3 From fd264ca020948a743e4c36731dfdecc4a812153c Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sun, 20 Nov 2022 11:54:32 -0800 Subject: bpf: Add a kfunc to type cast from bpf uapi ctx to kernel ctx Implement bpf_cast_to_kern_ctx() kfunc which does a type cast of a uapi ctx object to the corresponding kernel ctx. Previously if users want to access some data available in kctx but not in uapi ctx, bpf_probe_read_kernel() helper is needed. The introduction of bpf_cast_to_kern_ctx() allows direct memory access which makes code simpler and easier to understand. Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20221120195432.3113982-1-yhs@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/btf.h | 5 +++++ kernel/bpf/btf.c | 20 ++++++++++++++++++++ kernel/bpf/helpers.c | 6 ++++++ kernel/bpf/verifier.c | 22 ++++++++++++++++++++++ 4 files changed, 53 insertions(+) (limited to 'include/linux/btf.h') diff --git a/include/linux/btf.h b/include/linux/btf.h index d38aa4251c28..9ed00077db6e 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -487,6 +487,7 @@ 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); +int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type); bool btf_types_are_same(const struct btf *btf1, u32 id1, const struct btf *btf2, u32 id2); #else @@ -531,6 +532,10 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, { return NULL; } +static inline int get_kern_ctx_btf_id(struct bpf_verifier_log *log, + enum bpf_prog_type prog_type) { + return -EINVAL; +} static inline bool btf_types_are_same(const struct btf *btf1, u32 id1, const struct btf *btf2, u32 id2) { diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 1c78d4df9e18..1a59cc7ad730 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5603,6 +5603,26 @@ static int btf_translate_to_vmlinux(struct bpf_verifier_log *log, return kern_ctx_type->type; } +int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type) +{ + const struct btf_member *kctx_member; + const struct btf_type *conv_struct; + const struct btf_type *kctx_type; + u32 kctx_type_id; + + conv_struct = bpf_ctx_convert.t; + /* get member for kernel ctx type */ + kctx_member = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2 + 1; + kctx_type_id = kctx_member->type; + kctx_type = btf_type_by_id(btf_vmlinux, kctx_type_id); + if (!btf_type_is_struct(kctx_type)) { + bpf_log(log, "kern ctx type id %u is not a struct\n", kctx_type_id); + return -EINVAL; + } + + return kctx_type_id; +} + BTF_ID_LIST(bpf_ctx_convert_btf_id) BTF_ID(struct, bpf_ctx_convert) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 8e0d80b6bf09..e45e72676f5a 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1879,6 +1879,11 @@ void bpf_task_release(struct task_struct *p) put_task_struct_rcu_user(p); } +void *bpf_cast_to_kern_ctx(void *obj) +{ + return obj; +} + __diag_pop(); BTF_SET8_START(generic_btf_ids) @@ -1907,6 +1912,7 @@ BTF_ID(struct, task_struct) BTF_ID(func, bpf_task_release) BTF_SET8_START(common_btf_ids) +BTF_ID_FLAGS(func, bpf_cast_to_kern_ctx) BTF_SET8_END(common_btf_ids) static const struct btf_kfunc_id_set common_kfunc_set = { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index eb090af35477..d63cc0fb0a9c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -7907,6 +7907,7 @@ struct bpf_kfunc_call_arg_meta { u32 ref_obj_id; u8 release_regno; bool r0_rdonly; + u32 ret_btf_id; u64 r0_size; struct { u64 value; @@ -8151,6 +8152,7 @@ enum special_kfunc_type { KF_bpf_list_push_back, KF_bpf_list_pop_front, KF_bpf_list_pop_back, + KF_bpf_cast_to_kern_ctx, }; BTF_SET_START(special_kfunc_set) @@ -8160,6 +8162,7 @@ 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_ID(func, bpf_cast_to_kern_ctx) BTF_SET_END(special_kfunc_set) BTF_ID_LIST(special_kfunc_list) @@ -8169,6 +8172,7 @@ 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_ID(func, bpf_cast_to_kern_ctx) static enum kfunc_ptr_arg_type get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, @@ -8182,6 +8186,9 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, struct bpf_reg_state *reg = ®s[regno]; bool arg_mem_size = false; + if (meta->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) + return KF_ARG_PTR_TO_CTX; + /* 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 @@ -8668,6 +8675,13 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ verbose(env, "arg#%d expected pointer to ctx, but got %s\n", i, btf_type_str(t)); return -EINVAL; } + + if (meta->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) { + ret = get_kern_ctx_btf_id(&env->log, resolve_prog_type(env->prog)); + if (ret < 0) + return -EINVAL; + meta->ret_btf_id = ret; + } break; case KF_ARG_PTR_TO_ALLOC_BTF_ID: if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { @@ -8922,6 +8936,11 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, 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 if (meta.func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) { + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_TRUSTED; + regs[BPF_REG_0].btf = desc_btf; + regs[BPF_REG_0].btf_id = meta.ret_btf_id; } else { verbose(env, "kernel function %s unhandled dynamic return type\n", meta.func_name); @@ -15175,6 +15194,9 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, insn_buf[1] = addr[1]; insn_buf[2] = *insn; *cnt = 3; + } else if (desc->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) { + insn_buf[0] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_1); + *cnt = 1; } return 0; } -- cgit v1.2.3 From fca1aa75518c03b04c3c249e9a9134faf9ca18c5 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 3 Dec 2022 10:46:02 -0800 Subject: bpf: Handle MEM_RCU type properly Commit 9bb00b2895cb ("bpf: Add kfunc bpf_rcu_read_lock/unlock()") introduced MEM_RCU and bpf_rcu_read_lock/unlock() support. In that commit, a rcu pointer is tagged with both MEM_RCU and PTR_TRUSTED so that it can be passed into kfuncs or helpers as an argument. Martin raised a good question in [1] such that the rcu pointer, although being able to accessing the object, might have reference count of 0. This might cause a problem if the rcu pointer is passed to a kfunc which expects trusted arguments where ref count should be greater than 0. This patch makes the following changes related to MEM_RCU pointer: - MEM_RCU pointer might be NULL (PTR_MAYBE_NULL). - Introduce KF_RCU so MEM_RCU ptr can be acquired with a KF_RCU tagged kfunc which assumes ref count of rcu ptr could be zero. - For mem access 'b = ptr->a', say 'ptr' is a MEM_RCU ptr, and 'a' is tagged with __rcu as well. Let us mark 'b' as MEM_RCU | PTR_MAYBE_NULL. [1] https://lore.kernel.org/bpf/ac70f574-4023-664e-b711-e0d3b18117fd@linux.dev/ Fixes: 9bb00b2895cb ("bpf: Add kfunc bpf_rcu_read_lock/unlock()") Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20221203184602.477272-1-yhs@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 2 +- include/linux/btf.h | 1 + kernel/bpf/helpers.c | 14 ++++++++++++++ kernel/bpf/verifier.c | 45 +++++++++++++++++++++++++++++++------------- 4 files changed, 48 insertions(+), 14 deletions(-) (limited to 'include/linux/btf.h') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index b5090e89cb3f..c07b351a5bc7 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -682,7 +682,7 @@ static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) } } -#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | MEM_RCU | PTR_TRUSTED) +#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | PTR_TRUSTED) static inline bool bpf_type_has_unsafe_modifiers(u32 type) { diff --git a/include/linux/btf.h b/include/linux/btf.h index 9ed00077db6e..cbd6e4096f8c 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -70,6 +70,7 @@ #define KF_TRUSTED_ARGS (1 << 4) /* kfunc only takes trusted pointer arguments */ #define KF_SLEEPABLE (1 << 5) /* kfunc may sleep */ #define KF_DESTRUCTIVE (1 << 6) /* kfunc performs destructive actions */ +#define KF_RCU (1 << 7) /* kfunc only takes rcu pointer arguments */ /* * Return the name of the passed struct, if exists, or halt the build if for diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index a5a511430f2a..cca642358e80 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1837,6 +1837,19 @@ struct task_struct *bpf_task_acquire(struct task_struct *p) return p; } +/** + * bpf_task_acquire_not_zero - Acquire a reference to a rcu task object. A task + * acquired by this kfunc which is not stored in a map as a kptr, must be + * released by calling bpf_task_release(). + * @p: The task on which a reference is being acquired. + */ +struct task_struct *bpf_task_acquire_not_zero(struct task_struct *p) +{ + if (!refcount_inc_not_zero(&p->rcu_users)) + return NULL; + return p; +} + /** * bpf_task_kptr_get - Acquire a reference on a struct task_struct kptr. A task * kptr acquired by this kfunc which is not subsequently stored in a map, must @@ -2013,6 +2026,7 @@ 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_ID_FLAGS(func, bpf_task_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_task_acquire_not_zero, KF_ACQUIRE | KF_RCU | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_task_kptr_get, KF_ACQUIRE | KF_KPTR_GET | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_task_release, KF_RELEASE) #ifdef CONFIG_CGROUPS diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b0db9c10567b..66b82f52b5bc 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4275,7 +4275,7 @@ static bool is_trusted_reg(const struct bpf_reg_state *reg) return true; /* If a register is not referenced, it is trusted if it has the - * MEM_ALLOC, MEM_RCU or PTR_TRUSTED type modifiers, and no others. Some of the + * MEM_ALLOC or PTR_TRUSTED type modifiers, and no others. Some of the * other type modifiers may be safe, but we elect to take an opt-in * approach here as some (e.g. PTR_UNTRUSTED and PTR_MAYBE_NULL) are * not. @@ -4287,6 +4287,11 @@ static bool is_trusted_reg(const struct bpf_reg_state *reg) !bpf_type_has_unsafe_modifiers(reg->type); } +static bool is_rcu_reg(const struct bpf_reg_state *reg) +{ + return reg->type & MEM_RCU; +} + static int check_pkt_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int off, int size, bool strict) @@ -4785,14 +4790,16 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, if (flag & MEM_RCU) { /* Mark value register as MEM_RCU only if it is protected by - * bpf_rcu_read_lock() and the ptr reg is trusted. MEM_RCU + * bpf_rcu_read_lock() and the ptr reg is rcu or trusted. MEM_RCU * itself can already indicate trustedness inside the rcu - * read lock region. Also mark it as PTR_TRUSTED. + * read lock region. Also mark rcu pointer as PTR_MAYBE_NULL since + * it could be null in some cases. */ - if (!env->cur_state->active_rcu_lock || !is_trusted_reg(reg)) + if (!env->cur_state->active_rcu_lock || + !(is_trusted_reg(reg) || is_rcu_reg(reg))) flag &= ~MEM_RCU; else - flag |= PTR_TRUSTED; + flag |= PTR_MAYBE_NULL; } else if (reg->type & MEM_RCU) { /* ptr (reg) is marked as MEM_RCU, but the struct field is not tagged * with __rcu. Mark the flag as PTR_UNTRUSTED conservatively. @@ -5957,7 +5964,7 @@ static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID, PTR_TO_BTF_ID | PTR_TRUSTED, - PTR_TO_BTF_ID | MEM_RCU | PTR_TRUSTED, + PTR_TO_BTF_ID | MEM_RCU, }, }; static const struct bpf_reg_types percpu_btf_ptr_types = { @@ -6136,7 +6143,7 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, case PTR_TO_BTF_ID: case PTR_TO_BTF_ID | MEM_ALLOC: case PTR_TO_BTF_ID | PTR_TRUSTED: - case PTR_TO_BTF_ID | MEM_RCU | PTR_TRUSTED: + case PTR_TO_BTF_ID | MEM_RCU: case PTR_TO_BTF_ID | MEM_ALLOC | PTR_TRUSTED: /* When referenced PTR_TO_BTF_ID is passed to release function, * it's fixed offset must be 0. In the other cases, fixed offset @@ -8038,6 +8045,11 @@ static bool is_kfunc_destructive(struct bpf_kfunc_call_arg_meta *meta) return meta->kfunc_flags & KF_DESTRUCTIVE; } +static bool is_kfunc_rcu(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_RCU; +} + 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); @@ -8722,13 +8734,20 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ 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)) + if (!is_kfunc_trusted_args(meta) && !is_kfunc_rcu(meta)) break; if (!is_trusted_reg(reg)) { - verbose(env, "R%d must be referenced or trusted\n", regno); - return -EINVAL; + if (!is_kfunc_rcu(meta)) { + verbose(env, "R%d must be referenced or trusted\n", regno); + return -EINVAL; + } + if (!is_rcu_reg(reg)) { + verbose(env, "R%d must be a rcu pointer\n", regno); + return -EINVAL; + } } + fallthrough; case KF_ARG_PTR_TO_CTX: /* Trusted arguments have the same offset checks as release arguments */ @@ -8839,7 +8858,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ case KF_ARG_PTR_TO_BTF_ID: /* Only base_type is checked, further checks are done here */ if ((base_type(reg->type) != PTR_TO_BTF_ID || - bpf_type_has_unsafe_modifiers(reg->type)) && + (bpf_type_has_unsafe_modifiers(reg->type) && !is_rcu_reg(reg))) && !reg2btf_ids[base_type(reg->type)]) { verbose(env, "arg#%d is %s ", i, reg_type_str(env, reg->type)); verbose(env, "expected %s or socket\n", @@ -8954,7 +8973,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, } else if (rcu_unlock) { bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ if (reg->type & MEM_RCU) { - reg->type &= ~(MEM_RCU | PTR_TRUSTED); + reg->type &= ~(MEM_RCU | PTR_MAYBE_NULL); reg->type |= PTR_UNTRUSTED; } })); @@ -11294,7 +11313,7 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state, bool is_null) { if (type_may_be_null(reg->type) && reg->id == id && - !WARN_ON_ONCE(!reg->id)) { + (is_rcu_reg(reg) || !WARN_ON_ONCE(!reg->id))) { /* 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 -- cgit v1.2.3 From 5b481acab4ce017fda8166fa9428511da41109e5 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Tue, 6 Dec 2022 15:59:32 +0100 Subject: bpf: do not rely on ALLOW_ERROR_INJECTION for fmod_ret The current way of expressing that a non-bpf kernel component is willing to accept that bpf programs can be attached to it and that they can change the return value is to abuse ALLOW_ERROR_INJECTION. This is debated in the link below, and the result is that it is not a reasonable thing to do. Reuse the kfunc declaration structure to also tag the kernel functions we want to be fmodret. This way we can control from any subsystem which functions are being modified by bpf without touching the verifier. Link: https://lore.kernel.org/all/20221121104403.1545f9b5@gandalf.local.home/ Suggested-by: Alexei Starovoitov Signed-off-by: Benjamin Tissoires Acked-by: Alexei Starovoitov Link: https://lore.kernel.org/r/20221206145936.922196-2-benjamin.tissoires@redhat.com --- include/linux/btf.h | 2 ++ kernel/bpf/btf.c | 30 +++++++++++++++++++++++++----- kernel/bpf/verifier.c | 17 +++++++++++++++-- net/bpf/test_run.c | 14 +++++++++++--- 4 files changed, 53 insertions(+), 10 deletions(-) (limited to 'include/linux/btf.h') diff --git a/include/linux/btf.h b/include/linux/btf.h index f9aababc5d78..6a0808e7845c 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -412,8 +412,10 @@ struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog); u32 *btf_kfunc_id_set_contains(const struct btf *btf, enum bpf_prog_type prog_type, u32 kfunc_btf_id); +u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id); int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, const struct btf_kfunc_id_set *s); +int register_btf_fmodret_id_set(const struct btf_kfunc_id_set *kset); 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); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 35c07afac924..c1df506293e4 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -204,6 +204,7 @@ enum btf_kfunc_hook { BTF_KFUNC_HOOK_STRUCT_OPS, BTF_KFUNC_HOOK_TRACING, BTF_KFUNC_HOOK_SYSCALL, + BTF_KFUNC_HOOK_FMODRET, BTF_KFUNC_HOOK_MAX, }; @@ -7448,11 +7449,14 @@ u32 *btf_kfunc_id_set_contains(const struct btf *btf, return __btf_kfunc_id_set_contains(btf, hook, kfunc_btf_id); } -/* This function must be invoked only from initcalls/module init functions */ -int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, - const struct btf_kfunc_id_set *kset) +u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id) +{ + return __btf_kfunc_id_set_contains(btf, BTF_KFUNC_HOOK_FMODRET, kfunc_btf_id); +} + +static int __register_btf_kfunc_id_set(enum btf_kfunc_hook hook, + const struct btf_kfunc_id_set *kset) { - enum btf_kfunc_hook hook; struct btf *btf; int ret; @@ -7471,13 +7475,29 @@ int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, if (IS_ERR(btf)) return PTR_ERR(btf); - hook = bpf_prog_type_to_kfunc_hook(prog_type); ret = btf_populate_kfunc_set(btf, hook, kset->set); btf_put(btf); return ret; } + +/* This function must be invoked only from initcalls/module init functions */ +int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, + const struct btf_kfunc_id_set *kset) +{ + enum btf_kfunc_hook hook; + + hook = bpf_prog_type_to_kfunc_hook(prog_type); + return __register_btf_kfunc_id_set(hook, kset); +} EXPORT_SYMBOL_GPL(register_btf_kfunc_id_set); +/* This function must be invoked only from initcalls/module init functions */ +int register_btf_fmodret_id_set(const struct btf_kfunc_id_set *kset) +{ + return __register_btf_kfunc_id_set(BTF_KFUNC_HOOK_FMODRET, kset); +} +EXPORT_SYMBOL_GPL(register_btf_fmodret_id_set); + s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id) { struct btf_id_dtor_kfunc_tab *tab = btf->dtor_kfunc_tab; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 225666307bba..ec2e6ec7309e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -15021,12 +15021,22 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, ret = -EINVAL; switch (prog->type) { case BPF_PROG_TYPE_TRACING: - /* fentry/fexit/fmod_ret progs can be sleepable only if they are + + /* fentry/fexit/fmod_ret progs can be sleepable if they are * attached to ALLOW_ERROR_INJECTION and are not in denylist. */ if (!check_non_sleepable_error_inject(btf_id) && within_error_injection_list(addr)) ret = 0; + /* fentry/fexit/fmod_ret progs can also be sleepable if they are + * in the fmodret id set with the KF_SLEEPABLE flag. + */ + else { + u32 *flags = btf_kfunc_is_modify_return(btf, btf_id); + + if (flags && (*flags & KF_SLEEPABLE)) + ret = 0; + } break; case BPF_PROG_TYPE_LSM: /* LSM progs check that they are attached to bpf_lsm_*() funcs. @@ -15047,7 +15057,10 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, bpf_log(log, "can't modify return codes of BPF programs\n"); return -EINVAL; } - ret = check_attach_modify_return(addr, tname); + ret = -EINVAL; + if (btf_kfunc_is_modify_return(btf, btf_id) || + !check_attach_modify_return(addr, tname)) + ret = 0; if (ret) { bpf_log(log, "%s() is not modifiable\n", tname); return ret; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 13d578ce2a09..5079fb089b5f 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -489,7 +489,6 @@ int noinline bpf_fentry_test1(int a) return a + 1; } EXPORT_SYMBOL_GPL(bpf_fentry_test1); -ALLOW_ERROR_INJECTION(bpf_fentry_test1, ERRNO); int noinline bpf_fentry_test2(int a, u64 b) { @@ -733,7 +732,15 @@ noinline void bpf_kfunc_call_test_destructive(void) __diag_pop(); -ALLOW_ERROR_INJECTION(bpf_modify_return_test, ERRNO); +BTF_SET8_START(bpf_test_modify_return_ids) +BTF_ID_FLAGS(func, bpf_modify_return_test) +BTF_ID_FLAGS(func, bpf_fentry_test1, KF_SLEEPABLE) +BTF_SET8_END(bpf_test_modify_return_ids) + +static const struct btf_kfunc_id_set bpf_test_modify_return_set = { + .owner = THIS_MODULE, + .set = &bpf_test_modify_return_ids, +}; BTF_SET8_START(test_sk_check_kfunc_ids) BTF_ID_FLAGS(func, bpf_kfunc_call_test1) @@ -1668,7 +1675,8 @@ static int __init bpf_prog_test_run_init(void) }; int ret; - ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_prog_test_kfunc_set); + ret = register_btf_fmodret_id_set(&bpf_test_modify_return_set); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_prog_test_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_prog_test_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &bpf_prog_test_kfunc_set); return ret ?: register_btf_id_dtor_kfuncs(bpf_prog_test_dtor_kfunc, -- cgit v1.2.3