diff options
-rw-r--r-- | include/linux/bpf.h | 47 | ||||
-rw-r--r-- | include/linux/bpf_verifier.h | 19 | ||||
-rw-r--r-- | include/linux/btf.h | 1 | ||||
-rw-r--r-- | include/uapi/linux/bpf.h | 73 | ||||
-rw-r--r-- | kernel/bpf/arraymap.c | 21 | ||||
-rw-r--r-- | kernel/bpf/btf.c | 77 | ||||
-rw-r--r-- | kernel/bpf/hashtab.c | 105 | ||||
-rw-r--r-- | kernel/bpf/helpers.c | 340 | ||||
-rw-r--r-- | kernel/bpf/local_storage.c | 4 | ||||
-rw-r--r-- | kernel/bpf/map_in_map.c | 8 | ||||
-rw-r--r-- | kernel/bpf/syscall.c | 53 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 307 | ||||
-rw-r--r-- | kernel/trace/bpf_trace.c | 2 | ||||
-rwxr-xr-x | scripts/bpf_doc.py | 2 | ||||
-rw-r--r-- | tools/include/uapi/linux/bpf.h | 73 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/prog_tests/timer.c | 55 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/prog_tests/timer_mim.c | 69 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/progs/timer.c | 297 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/progs/timer_mim.c | 88 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/progs/timer_mim_reject.c | 74 |
20 files changed, 1651 insertions, 64 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4afbff308ca3..a9a4a480a6d0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -168,6 +168,7 @@ struct bpf_map { u32 max_entries; u32 map_flags; int spin_lock_off; /* >=0 valid offset, <0 error */ + int timer_off; /* >=0 valid offset, <0 error */ u32 id; int numa_node; u32 btf_key_type_id; @@ -197,30 +198,53 @@ static inline bool map_value_has_spin_lock(const struct bpf_map *map) return map->spin_lock_off >= 0; } -static inline void check_and_init_map_lock(struct bpf_map *map, void *dst) +static inline bool map_value_has_timer(const struct bpf_map *map) { - if (likely(!map_value_has_spin_lock(map))) - return; - *(struct bpf_spin_lock *)(dst + map->spin_lock_off) = - (struct bpf_spin_lock){}; + return map->timer_off >= 0; } -/* copy everything but bpf_spin_lock */ +static inline void check_and_init_map_value(struct bpf_map *map, void *dst) +{ + if (unlikely(map_value_has_spin_lock(map))) + *(struct bpf_spin_lock *)(dst + map->spin_lock_off) = + (struct bpf_spin_lock){}; + if (unlikely(map_value_has_timer(map))) + *(struct bpf_timer *)(dst + map->timer_off) = + (struct bpf_timer){}; +} + +/* copy everything but bpf_spin_lock and bpf_timer. There could be one of each. */ static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) { + u32 s_off = 0, s_sz = 0, t_off = 0, t_sz = 0; + if (unlikely(map_value_has_spin_lock(map))) { - u32 off = map->spin_lock_off; + s_off = map->spin_lock_off; + s_sz = sizeof(struct bpf_spin_lock); + } else if (unlikely(map_value_has_timer(map))) { + t_off = map->timer_off; + t_sz = sizeof(struct bpf_timer); + } - memcpy(dst, src, off); - memcpy(dst + off + sizeof(struct bpf_spin_lock), - src + off + sizeof(struct bpf_spin_lock), - map->value_size - off - sizeof(struct bpf_spin_lock)); + if (unlikely(s_sz || t_sz)) { + if (s_off < t_off || !s_sz) { + swap(s_off, t_off); + swap(s_sz, t_sz); + } + memcpy(dst, src, t_off); + memcpy(dst + t_off + t_sz, + src + t_off + t_sz, + s_off - t_off - t_sz); + memcpy(dst + s_off + s_sz, + src + s_off + s_sz, + map->value_size - s_off - s_sz); } else { memcpy(dst, src, map->value_size); } } void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); +void bpf_timer_cancel_and_free(void *timer); int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size); struct bpf_offload_dev; @@ -314,6 +338,7 @@ enum bpf_arg_type { ARG_PTR_TO_FUNC, /* pointer to a bpf program function */ ARG_PTR_TO_STACK_OR_NULL, /* pointer to stack or NULL */ ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ + ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ __BPF_ARG_TYPE_MAX, }; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e774ecc1cd1f..b847e1ccd10f 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -53,7 +53,14 @@ struct bpf_reg_state { /* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE | * PTR_TO_MAP_VALUE_OR_NULL */ - struct bpf_map *map_ptr; + struct { + struct bpf_map *map_ptr; + /* To distinguish map lookups from outer map + * the map_uid is non-zero for registers + * pointing to inner maps. + */ + u32 map_uid; + }; /* for PTR_TO_BTF_ID */ struct { @@ -201,12 +208,19 @@ struct bpf_func_state { * zero == main subprog */ u32 subprogno; + /* Every bpf_timer_start will increment async_entry_cnt. + * It's used to distinguish: + * void foo(void) { for(;;); } + * void foo(void) { bpf_timer_set_callback(,foo); } + */ + u32 async_entry_cnt; + bool in_callback_fn; + bool in_async_callback_fn; /* The following fields should be last. See copy_func_state() */ int acquired_refs; struct bpf_reference_state *refs; int allocated_stack; - bool in_callback_fn; struct bpf_stack_state *stack; }; @@ -392,6 +406,7 @@ struct bpf_subprog_info { bool has_tail_call; bool tail_call_reachable; bool has_ld_abs; + bool is_async_cb; }; /* single container for all structs diff --git a/include/linux/btf.h b/include/linux/btf.h index 94a0c976c90f..214fde93214b 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -99,6 +99,7 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, 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); 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/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bafb6282032b..3544ec5234f0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4777,6 +4777,70 @@ union bpf_attr { * Execute close syscall for given FD. * Return * A syscall result. + * + * long bpf_timer_init(struct bpf_timer *timer, struct bpf_map *map, u64 flags) + * Description + * Initialize the timer. + * First 4 bits of *flags* specify clockid. + * Only CLOCK_MONOTONIC, CLOCK_REALTIME, CLOCK_BOOTTIME are allowed. + * All other bits of *flags* are reserved. + * The verifier will reject the program if *timer* is not from + * the same *map*. + * Return + * 0 on success. + * **-EBUSY** if *timer* is already initialized. + * **-EINVAL** if invalid *flags* are passed. + * **-EPERM** if *timer* is in a map that doesn't have any user references. + * The user space should either hold a file descriptor to a map with timers + * or pin such map in bpffs. When map is unpinned or file descriptor is + * closed all timers in the map will be cancelled and freed. + * + * long bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn) + * Description + * Configure the timer to call *callback_fn* static function. + * Return + * 0 on success. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier. + * **-EPERM** if *timer* is in a map that doesn't have any user references. + * The user space should either hold a file descriptor to a map with timers + * or pin such map in bpffs. When map is unpinned or file descriptor is + * closed all timers in the map will be cancelled and freed. + * + * long bpf_timer_start(struct bpf_timer *timer, u64 nsecs, u64 flags) + * Description + * Set timer expiration N nanoseconds from the current time. The + * configured callback will be invoked in soft irq context on some cpu + * and will not repeat unless another bpf_timer_start() is made. + * In such case the next invocation can migrate to a different cpu. + * Since struct bpf_timer is a field inside map element the map + * owns the timer. The bpf_timer_set_callback() will increment refcnt + * of BPF program to make sure that callback_fn code stays valid. + * When user space reference to a map reaches zero all timers + * in a map are cancelled and corresponding program's refcnts are + * decremented. This is done to make sure that Ctrl-C of a user + * process doesn't leave any timers running. If map is pinned in + * bpffs the callback_fn can re-arm itself indefinitely. + * bpf_map_update/delete_elem() helpers and user space sys_bpf commands + * cancel and free the timer in the given map element. + * The map can contain timers that invoke callback_fn-s from different + * programs. The same callback_fn can serve different timers from + * different maps if key/value layout matches across maps. + * Every bpf_timer_set_callback() can have different callback_fn. + * + * Return + * 0 on success. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier + * or invalid *flags* are passed. + * + * long bpf_timer_cancel(struct bpf_timer *timer) + * Description + * Cancel the timer and wait for callback_fn to finish if it was running. + * Return + * 0 if the timer was not active. + * 1 if the timer was active. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier. + * **-EDEADLK** if callback_fn tried to call bpf_timer_cancel() on its + * own timer which would have led to a deadlock otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -4948,6 +5012,10 @@ union bpf_attr { FN(sys_bpf), \ FN(btf_find_by_name_kind), \ FN(sys_close), \ + FN(timer_init), \ + FN(timer_set_callback), \ + FN(timer_start), \ + FN(timer_cancel), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -6074,6 +6142,11 @@ struct bpf_spin_lock { __u32 val; }; +struct bpf_timer { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + struct bpf_sysctl { __u32 write; /* Sysctl is being read (= 0) or written (= 1). * Allows 1,2,4-byte read, but no write. diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 3c4105603f9d..cebd4fb06d19 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -287,6 +287,12 @@ static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key return 0; } +static void check_and_free_timer_in_array(struct bpf_array *arr, void *val) +{ + if (unlikely(map_value_has_timer(&arr->map))) + bpf_timer_cancel_and_free(val + arr->map.timer_off); +} + /* Called from syscall or from eBPF program */ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) @@ -321,6 +327,7 @@ 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_timer_in_array(array, val); } return 0; } @@ -374,6 +381,19 @@ static void *array_map_vmalloc_addr(struct bpf_array *array) return (void *)round_down((unsigned long)array, PAGE_SIZE); } +static void array_map_free_timers(struct bpf_map *map) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + int i; + + if (likely(!map_value_has_timer(map))) + return; + + for (i = 0; i < array->map.max_entries; i++) + bpf_timer_cancel_and_free(array->value + array->elem_size * i + + map->timer_off); +} + /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ static void array_map_free(struct bpf_map *map) { @@ -668,6 +688,7 @@ const struct bpf_map_ops array_map_ops = { .map_alloc = array_map_alloc, .map_free = array_map_free, .map_get_next_key = array_map_get_next_key, + .map_release_uref = array_map_free_timers, .map_lookup_elem = array_map_lookup_elem, .map_update_elem = array_map_update_elem, .map_delete_elem = array_map_delete_elem, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index cb4b72997d9b..7780131f710e 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3046,43 +3046,92 @@ static void btf_struct_log(struct btf_verifier_env *env, btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); } -/* 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_find_struct_field(const struct btf *btf, const struct btf_type *t, + const char *name, int sz, int align) { const struct btf_member *member; u32 i, off = -ENOENT; - if (!__btf_type_is_struct(t)) - return -EINVAL; - for_each_member(i, t, member) { const struct btf_type *member_type = btf_type_by_id(btf, member->type); if (!__btf_type_is_struct(member_type)) continue; - if (member_type->size != sizeof(struct bpf_spin_lock)) + if (member_type->size != sz) continue; - if (strcmp(__btf_name_by_offset(btf, member_type->name_off), - "bpf_spin_lock")) + if (strcmp(__btf_name_by_offset(btf, member_type->name_off), name)) continue; if (off != -ENOENT) - /* only one 'struct bpf_spin_lock' is allowed */ + /* only one such field is allowed */ return -E2BIG; off = btf_member_bit_offset(t, member); if (off % 8) /* valid C code cannot generate such BTF */ return -EINVAL; off /= 8; - if (off % __alignof__(struct bpf_spin_lock)) - /* valid struct bpf_spin_lock will be 4 byte aligned */ + if (off % align) + return -EINVAL; + } + return off; +} + +static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, + const char *name, int sz, int align) +{ + const struct btf_var_secinfo *vsi; + u32 i, off = -ENOENT; + + 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); + + if (!__btf_type_is_struct(var_type)) + continue; + if (var_type->size != sz) + continue; + if (vsi->size != sz) + continue; + if (strcmp(__btf_name_by_offset(btf, var_type->name_off), name)) + continue; + if (off != -ENOENT) + /* only one such field is allowed */ + return -E2BIG; + off = vsi->offset; + if (off % align) return -EINVAL; } return off; } +static int btf_find_field(const struct btf *btf, const struct btf_type *t, + const char *name, int sz, int align) +{ + + if (__btf_type_is_struct(t)) + return btf_find_struct_field(btf, t, name, sz, align); + else if (btf_type_is_datasec(t)) + return btf_find_datasec_var(btf, t, name, sz, align); + 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) +{ + return btf_find_field(btf, t, "bpf_spin_lock", + sizeof(struct bpf_spin_lock), + __alignof__(struct bpf_spin_lock)); +} + +int btf_find_timer(const struct btf *btf, const struct btf_type *t) +{ + return btf_find_field(btf, t, "bpf_timer", + sizeof(struct bpf_timer), + __alignof__(struct bpf_timer)); +} + 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/hashtab.c b/kernel/bpf/hashtab.c index 72c58cc516a3..6dc3fae46a56 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -228,6 +228,32 @@ static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i) return (struct htab_elem *) (htab->elems + i * (u64)htab->elem_size); } +static bool htab_has_extra_elems(struct bpf_htab *htab) +{ + return !htab_is_percpu(htab) && !htab_is_lru(htab); +} + +static void htab_free_prealloced_timers(struct bpf_htab *htab) +{ + u32 num_entries = htab->map.max_entries; + int i; + + if (likely(!map_value_has_timer(&htab->map))) + 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_timer_cancel_and_free(elem->key + + round_up(htab->map.key_size, 8) + + htab->map.timer_off); + cond_resched(); + } +} + static void htab_free_elems(struct bpf_htab *htab) { int i; @@ -265,8 +291,12 @@ static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key, struct htab_elem *l; if (node) { + u32 key_size = htab->map.key_size; + l = container_of(node, struct htab_elem, lru_node); - memcpy(l->key, key, htab->map.key_size); + memcpy(l->key, key, key_size); + check_and_init_map_value(&htab->map, + l->key + round_up(key_size, 8)); return l; } @@ -278,7 +308,7 @@ static int prealloc_init(struct bpf_htab *htab) u32 num_entries = htab->map.max_entries; int err = -ENOMEM, i; - if (!htab_is_percpu(htab) && !htab_is_lru(htab)) + if (htab_has_extra_elems(htab)) num_entries += num_possible_cpus(); htab->elems = bpf_map_area_alloc((u64)htab->elem_size * num_entries, @@ -695,6 +725,14 @@ static int htab_lru_map_gen_lookup(struct bpf_map *map, return insn - insn_buf; } +static void check_and_free_timer(struct bpf_htab *htab, struct htab_elem *elem) +{ + if (unlikely(map_value_has_timer(&htab->map))) + bpf_timer_cancel_and_free(elem->key + + round_up(htab->map.key_size, 8) + + htab->map.timer_off); +} + /* It is called from the bpf_lru_list when the LRU needs to delete * older elements from the htab. */ @@ -719,6 +757,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) if (l == tgt_l) { hlist_nulls_del_rcu(&l->hash_node); + check_and_free_timer(htab, l); break; } @@ -790,6 +829,7 @@ static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l) { if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) free_percpu(htab_elem_get_ptr(l, htab->map.key_size)); + check_and_free_timer(htab, l); kfree(l); } @@ -817,6 +857,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) htab_put_fd_value(htab, l); if (htab_is_prealloc(htab)) { + check_and_free_timer(htab, l); __pcpu_freelist_push(&htab->freelist, &l->fnode); } else { atomic_dec(&htab->count); @@ -920,8 +961,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, l_new = ERR_PTR(-ENOMEM); goto dec_count; } - check_and_init_map_lock(&htab->map, - l_new->key + round_up(key_size, 8)); + check_and_init_map_value(&htab->map, + l_new->key + round_up(key_size, 8)); } memcpy(l_new->key, key, key_size); @@ -1062,6 +1103,8 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, hlist_nulls_del_rcu(&l_old->hash_node); if (!htab_is_prealloc(htab)) free_htab_elem(htab, l_old); + else + check_and_free_timer(htab, l_old); } ret = 0; err: @@ -1069,6 +1112,12 @@ err: return ret; } +static void htab_lru_push_free(struct bpf_htab *htab, struct htab_elem *elem) +{ + check_and_free_timer(htab, elem); + bpf_lru_push_free(&htab->lru, &elem->lru_node); +} + static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { @@ -1102,7 +1151,8 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, l_new = prealloc_lru_pop(htab, key, hash); if (!l_new) return -ENOMEM; - memcpy(l_new->key + round_up(map->key_size, 8), value, map->value_size); + copy_map_value(&htab->map, + l_new->key + round_up(map->key_size, 8), value); ret = htab_lock_bucket(htab, b, hash, &flags); if (ret) @@ -1128,9 +1178,9 @@ err: htab_unlock_bucket(htab, b, hash, flags); if (ret) - bpf_lru_push_free(&htab->lru, &l_new->lru_node); + htab_lru_push_free(htab, l_new); else if (l_old) - bpf_lru_push_free(&htab->lru, &l_old->lru_node); + htab_lru_push_free(htab, l_old); return ret; } @@ -1339,7 +1389,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) htab_unlock_bucket(htab, b, hash, flags); if (l) - bpf_lru_push_free(&htab->lru, &l->lru_node); + htab_lru_push_free(htab, l); return ret; } @@ -1359,6 +1409,35 @@ static void delete_all_elements(struct bpf_htab *htab) } } +static void htab_free_malloced_timers(struct bpf_htab *htab) +{ + int i; + + rcu_read_lock(); + for (i = 0; i < htab->n_buckets; i++) { + struct hlist_nulls_head *head = select_bucket(htab, i); + struct hlist_nulls_node *n; + struct htab_elem *l; + + hlist_nulls_for_each_entry(l, n, head, hash_node) + check_and_free_timer(htab, l); + cond_resched_rcu(); + } + rcu_read_unlock(); +} + +static void htab_map_free_timers(struct bpf_map *map) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + + if (likely(!map_value_has_timer(&htab->map))) + return; + if (!htab_is_prealloc(htab)) + htab_free_malloced_timers(htab); + else + htab_free_prealloced_timers(htab); +} + /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ static void htab_map_free(struct bpf_map *map) { @@ -1456,7 +1535,7 @@ static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key, else copy_map_value(map, value, l->key + roundup_key_size); - check_and_init_map_lock(map, value); + check_and_init_map_value(map, value); } hlist_nulls_del_rcu(&l->hash_node); @@ -1467,7 +1546,7 @@ static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key, htab_unlock_bucket(htab, b, hash, bflags); if (is_lru_map && l) - bpf_lru_push_free(&htab->lru, &l->lru_node); + htab_lru_push_free(htab, l); return ret; } @@ -1645,7 +1724,7 @@ again_nocopy: true); else copy_map_value(map, dst_val, value); - check_and_init_map_lock(map, dst_val); + check_and_init_map_value(map, dst_val); } if (do_delete) { hlist_nulls_del_rcu(&l->hash_node); @@ -1672,7 +1751,7 @@ again_nocopy: while (node_to_free) { l = node_to_free; node_to_free = node_to_free->batch_flink; - bpf_lru_push_free(&htab->lru, &l->lru_node); + htab_lru_push_free(htab, l); } next_batch: @@ -2034,6 +2113,7 @@ const struct bpf_map_ops htab_map_ops = { .map_alloc = htab_map_alloc, .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, + .map_release_uref = htab_map_free_timers, .map_lookup_elem = htab_map_lookup_elem, .map_lookup_and_delete_elem = htab_map_lookup_and_delete_elem, .map_update_elem = htab_map_update_elem, @@ -2055,6 +2135,7 @@ const struct bpf_map_ops htab_lru_map_ops = { .map_alloc = htab_map_alloc, .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, + .map_release_uref = htab_map_free_timers, .map_lookup_elem = htab_lru_map_lookup_elem, .map_lookup_and_delete_elem = htab_lru_map_lookup_and_delete_elem, .map_lookup_elem_sys_only = htab_lru_map_lookup_elem_sys, diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 62cf00383910..9fe846ec6bd1 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -289,13 +289,18 @@ static inline void __bpf_spin_unlock(struct bpf_spin_lock *lock) static DEFINE_PER_CPU(unsigned long, irqsave_flags); -notrace BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) +static inline void __bpf_spin_lock_irqsave(struct bpf_spin_lock *lock) { unsigned long flags; local_irq_save(flags); __bpf_spin_lock(lock); __this_cpu_write(irqsave_flags, flags); +} + +notrace BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) +{ + __bpf_spin_lock_irqsave(lock); return 0; } @@ -306,13 +311,18 @@ const struct bpf_func_proto bpf_spin_lock_proto = { .arg1_type = ARG_PTR_TO_SPIN_LOCK, }; -notrace BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) +static inline void __bpf_spin_unlock_irqrestore(struct bpf_spin_lock *lock) { unsigned long flags; flags = __this_cpu_read(irqsave_flags); __bpf_spin_unlock(lock); local_irq_restore(flags); +} + +notrace BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) +{ + __bpf_spin_unlock_irqrestore(lock); return 0; } @@ -333,9 +343,9 @@ void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, else lock = dst + map->spin_lock_off; preempt_disable(); - ____bpf_spin_lock(lock); + __bpf_spin_lock_irqsave(lock); copy_map_value(map, dst, src); - ____bpf_spin_unlock(lock); + __bpf_spin_unlock_irqrestore(lock); preempt_enable(); } @@ -989,6 +999,320 @@ const struct bpf_func_proto bpf_snprintf_proto = { .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; +/* BPF map elements can contain 'struct bpf_timer'. + * Such map owns all of its BPF timers. + * 'struct bpf_timer' is allocated as part of map element allocation + * and it's zero initialized. + * That space is used to keep 'struct bpf_timer_kern'. + * bpf_timer_init() allocates 'struct bpf_hrtimer', inits hrtimer, and + * remembers 'struct bpf_map *' pointer it's part of. + * bpf_timer_set_callback() increments prog refcnt and assign bpf callback_fn. + * bpf_timer_start() arms the timer. + * If user space reference to a map goes to zero at this point + * ops->map_release_uref callback is responsible for cancelling the timers, + * freeing their memory, and decrementing prog's refcnts. + * bpf_timer_cancel() cancels the timer and decrements prog's refcnt. + * Inner maps can contain bpf timers as well. ops->map_release_uref is + * freeing the timers when inner map is replaced or deleted by user space. + */ +struct bpf_hrtimer { + struct hrtimer timer; + struct bpf_map *map; + struct bpf_prog *prog; + void __rcu *callback_fn; + void *value; +}; + +/* the actual struct hidden inside uapi struct bpf_timer */ +struct bpf_timer_kern { + struct bpf_hrtimer *timer; + /* bpf_spin_lock is used here instead of spinlock_t to make + * sure that it always fits into space resereved by struct bpf_timer + * regardless of LOCKDEP and spinlock debug flags. + */ + struct bpf_spin_lock lock; +} __attribute__((aligned(8))); + +static DEFINE_PER_CPU(struct bpf_hrtimer *, hrtimer_running); + +static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer) +{ + struct bpf_hrtimer *t = container_of(hrtimer, struct bpf_hrtimer, timer); + struct bpf_map *map = t->map; + void *value = t->value; + void *callback_fn; + void *key; + u32 idx; + + callback_fn = rcu_dereference_check(t->callback_fn, rcu_read_lock_bh_held()); + if (!callback_fn) + goto out; + + /* bpf_timer_cb() runs in hrtimer_run_softirq. It doesn't migrate and + * cannot be preempted by another bpf_timer_cb() on the same cpu. + * Remember the timer this callback is servicing to prevent + * deadlock if callback_fn() calls bpf_timer_cancel() or + * bpf_map_delete_elem() on the same timer. + */ + this_cpu_write(hrtimer_running, t); + if (map->map_type == BPF_MAP_TYPE_ARRAY) { + struct bpf_array *array = container_of(map, struct bpf_array, map); + + /* compute the key */ + idx = ((char *)value - array->value) / array->elem_size; + key = &idx; + } else { /* hash or lru */ + key = value - round_up(map->key_size, 8); + } + + BPF_CAST_CALL(callback_fn)((u64)(long)map, (u64)(long)key, + (u64)(long)value, 0, 0); + /* The verifier checked that return value is zero. */ + + this_cpu_write(hrtimer_running, NULL); +out: + return HRTIMER_NORESTART; +} + +BPF_CALL_3(bpf_timer_init, struct bpf_timer_kern *, timer, struct bpf_map *, map, + u64, flags) +{ + clockid_t clockid = flags & (MAX_CLOCKS - 1); + struct bpf_hrtimer *t; + int ret = 0; + + BUILD_BUG_ON(MAX_CLOCKS != 16); + BUILD_BUG_ON(sizeof(struct bpf_timer_kern) > sizeof(struct bpf_timer)); + BUILD_BUG_ON(__alignof__(struct bpf_timer_kern) != __alignof__(struct bpf_timer)); + + if (in_nmi()) + return -EOPNOTSUPP; + + if (flags >= MAX_CLOCKS || + /* similar to timerfd except _ALARM variants are not supported */ + (clockid != CLOCK_MONOTONIC && + clockid != CLOCK_REALTIME && + clockid != CLOCK_BOOTTIME)) + return -EINVAL; + __bpf_spin_lock_irqsave(&timer->lock); + t = timer->timer; + if (t) { + ret = -EBUSY; + goto out; + } + if (!atomic64_read(&map->usercnt)) { + /* maps with timers must be either held by user space + * or pinned in bpffs. + */ + ret = -EPERM; + goto out; + } + /* allocate hrtimer via map_kmalloc to use memcg accounting */ + t = bpf_map_kmalloc_node(map, sizeof(*t), GFP_ATOMIC, map->numa_node); + if (!t) { + ret = -ENOMEM; + goto out; + } + t->value = (void *)timer - map->timer_off; + t->map = map; + t->prog = NULL; + rcu_assign_pointer(t->callback_fn, NULL); + hrtimer_init(&t->timer, clockid, HRTIMER_MODE_REL_SOFT); + t->timer.function = bpf_timer_cb; + timer->timer = t; +out: + __bpf_spin_unlock_irqrestore(&timer->lock); + return ret; +} + +static const struct bpf_func_proto bpf_timer_init_proto = { + .func = bpf_timer_init, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_TIMER, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, +}; + +BPF_CALL_3(bpf_timer_set_callback, struct bpf_timer_kern *, timer, void *, callback_fn, + struct bpf_prog_aux *, aux) +{ + struct bpf_prog *prev, *prog = aux->prog; + struct bpf_hrtimer *t; + int ret = 0; + + if (in_nmi()) + return -EOPNOTSUPP; + __bpf_spin_lock_irqsave(&timer->lock); + t = timer->timer; + if (!t) { + ret = -EINVAL; + goto out; + } + if (!atomic64_read(&t->map->usercnt)) { + /* maps with timers must be either held by user space + * or pinned in bpffs. Otherwise timer might still be + * running even when bpf prog is detached and user space + * is gone, since map_release_uref won't ever be called. + */ + ret = -EPERM; + goto out; + } + prev = t->prog; + if (prev != prog) { + /* Bump prog refcnt once. Every bpf_timer_set_callback() + * can pick different callback_fn-s within the same prog. + */ + prog = bpf_prog_inc_not_zero(prog); + if (IS_ERR(prog)) { + ret = PTR_ERR(prog); + goto out; + } + if (prev) + /* Drop prev prog refcnt when swapping with new prog */ + bpf_prog_put(prev); + t->prog = prog; + } + rcu_assign_pointer(t->callback_fn, callback_fn); +out: + __bpf_spin_unlock_irqrestore(&timer->lock); + return ret; +} + +static const struct bpf_func_proto bpf_timer_set_callback_proto = { + .func = bpf_timer_set_callback, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_TIMER, + .arg2_type = ARG_PTR_TO_FUNC, +}; + +BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, flags) +{ + struct bpf_hrtimer *t; + int ret = 0; + + if (in_nmi()) + return -EOPNOTSUPP; + if (flags) + return -EINVAL; + __bpf_spin_lock_irqsave(&timer->lock); + t = timer->timer; + if (!t || !t->prog) { + ret = -EINVAL; + goto out; + } + hrtimer_start(&t->timer, ns_to_ktime(nsecs), HRTIMER_MODE_REL_SOFT); +out: + __bpf_spin_unlock_irqrestore(&timer->lock); + return ret; +} + +static const struct bpf_func_proto bpf_timer_start_proto = { + .func = bpf_timer_start, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_TIMER, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + +static void drop_prog_refcnt(struct bpf_hrtimer *t) +{ + struct bpf_prog *prog = t->prog; + + if (prog) { + bpf_prog_put(prog); + t->prog = NULL; + rcu_assign_pointer(t->callback_fn, NULL); + } +} + +BPF_CALL_1(bpf_timer_cancel, struct bpf_timer_kern *, timer) +{ + struct bpf_hrtimer *t; + int ret = 0; + + if (in_nmi()) + return -EOPNOTSUPP; + __bpf_spin_lock_irqsave(&timer->lock); + t = timer->timer; + if (!t) { + ret = -EINVAL; + goto out; + } + if (this_cpu_read(hrtimer_running) == t) { + /* If bpf callback_fn is trying to bpf_timer_cancel() + * its own timer the hrtimer_cancel() will deadlock + * since it waits for callback_fn to finish + */ + ret = -EDEADLK; + goto out; + } + drop_prog_refcnt(t); +out: + __bpf_spin_unlock_irqrestore(&timer->lock); + /* Cancel the timer and wait for associated callback to finish + * if it was running. + */ + ret = ret ?: hrtimer_cancel(&t->timer); + return ret; +} + +static const struct bpf_func_proto bpf_timer_cancel_proto = { + .func = bpf_timer_cancel, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_TIMER, +}; + +/* This function is called by map_delete/update_elem for individual element and + * by ops->map_release_uref when the user space reference to a map reaches zero. + */ +void bpf_timer_cancel_and_free(void *val) +{ + struct bpf_timer_kern *timer = val; + struct bpf_hrtimer *t; + + /* Performance optimization: read timer->timer without lock first. */ + if (!READ_ONCE(timer->timer)) + return; + + __bpf_spin_lock_irqsave(&timer->lock); + /* re-read it under lock */ + t = timer->timer; + if (!t) + goto out; + drop_prog_refcnt(t); + /* The subsequent bpf_timer_start/cancel() helpers won't be able to use + * this timer, since it won't be initialized. + */ + timer->timer = NULL; +out: + __bpf_spin_unlock_irqrestore(&timer->lock); + if (!t) + return; + /* Cancel the timer and wait for callback to complete if it was running. + * If hrtimer_cancel() can be safely called it's safe to call kfree(t) + * right after for both preallocated and non-preallocated maps. + * The timer->timer = NULL was already done and no code path can + * see address 't' anymore. + * + * Check that bpf_map_delete/update_elem() wasn't called from timer + * callback_fn. In such case don't call hrtimer_cancel() (since it will + * deadlock) and don't call hrtimer_try_to_cancel() (since it will just + * return -1). Though callback_fn is still running on this cpu it's + * safe to do kfree(t) because bpf_timer_cb() read everything it needed + * from 't'. The bpf subprog callback_fn won't be able to access 't', + * since timer->timer = NULL was already done. The timer will be + * effectively cancelled because bpf_timer_cb() will return + * HRTIMER_NORESTART. + */ + if (this_cpu_read(hrtimer_running) != t) + hrtimer_cancel(&t->timer); + kfree(t); +} + const struct bpf_func_proto bpf_get_current_task_proto __weak; const struct bpf_func_proto bpf_probe_read_user_proto __weak; const struct bpf_func_proto bpf_probe_read_user_str_proto __weak; @@ -1055,6 +1379,14 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_per_cpu_ptr_proto; case BPF_FUNC_this_cpu_ptr: return &bpf_this_cpu_ptr_proto; + case BPF_FUNC_timer_init: + return &bpf_timer_init_proto; + case BPF_FUNC_timer_set_callback: + return &bpf_timer_set_callback_proto; + case BPF_FUNC_timer_start: + return &bpf_timer_start_proto; + case BPF_FUNC_timer_cancel: + return &bpf_timer_cancel_proto; default: break; } diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index bd11db9774c3..95d70a08325d 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -173,7 +173,7 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *key, return -ENOMEM; memcpy(&new->data[0], value, map->value_size); - check_and_init_map_lock(map, new->data); + check_and_init_map_value(map, new->data); new = xchg(&storage->buf, new); kfree_rcu(new, rcu); @@ -509,7 +509,7 @@ struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, map->numa_node); if (!storage->buf) goto enomem; - check_and_init_map_lock(map, storage->buf->data); + check_and_init_map_value(map, storage->buf->data); } else { storage->percpu_buf = bpf_map_alloc_percpu(map, size, 8, gfp); if (!storage->percpu_buf) diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 39ab0b68cade..5cd8f5277279 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -3,6 +3,7 @@ */ #include <linux/slab.h> #include <linux/bpf.h> +#include <linux/btf.h> #include "map_in_map.h" @@ -50,6 +51,11 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) 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; + if (inner_map->btf) { + btf_get(inner_map->btf); + inner_map_meta->btf = inner_map->btf; + } /* Misc members not needed in bpf_map_meta_equal() check. */ inner_map_meta->ops = inner_map->ops; @@ -65,6 +71,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) void bpf_map_meta_free(struct bpf_map *map_meta) { + btf_put(map_meta->btf); kfree(map_meta); } @@ -75,6 +82,7 @@ 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; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index e343f158e556..9a2068e39d23 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -260,8 +260,8 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, copy_map_value_locked(map, value, ptr, true); else copy_map_value(map, value, ptr); - /* mask lock, since value wasn't zero inited */ - check_and_init_map_lock(map, value); + /* mask lock and timer, since value wasn't zero inited */ + check_and_init_map_value(map, value); } rcu_read_unlock(); } @@ -623,7 +623,8 @@ 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)) + if (!map->ops->map_mmap || map_value_has_spin_lock(map) || + map_value_has_timer(map)) return -ENOTSUPP; if (!(vma->vm_flags & VM_SHARED)) @@ -793,6 +794,16 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, } } + 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; + } + if (map->ops->map_check_btf) ret = map->ops->map_check_btf(map, btf, key_type, value_type); @@ -844,6 +855,7 @@ static int map_create(union bpf_attr *attr) mutex_init(&map->freeze_mutex); 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 @@ -1591,7 +1603,8 @@ 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) { + if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || + map_value_has_timer(map)) { fdput(f); return -ENOTSUPP; } @@ -1699,6 +1712,8 @@ static int bpf_prog_alloc_id(struct bpf_prog *prog) void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock) { + unsigned long flags; + /* cBPF to eBPF migrations are currently not in the idr store. * Offloaded programs are removed from the store when their device * disappears - even if someone grabs an fd to them they are unusable, @@ -1708,7 +1723,7 @@ void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock) return; if (do_idr_lock) - spin_lock_bh(&prog_idr_lock); + spin_lock_irqsave(&prog_idr_lock, flags); else __acquire(&prog_idr_lock); @@ -1716,7 +1731,7 @@ void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock) prog->aux->id = 0; if (do_idr_lock) - spin_unlock_bh(&prog_idr_lock); + spin_unlock_irqrestore(&prog_idr_lock, flags); else __release(&prog_idr_lock); } @@ -1752,14 +1767,32 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) } } +static void bpf_prog_put_deferred(struct work_struct *work) +{ + struct bpf_prog_aux *aux; + struct bpf_prog *prog; + + aux = container_of(work, struct bpf_prog_aux, work); + prog = aux->prog; + perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); + bpf_audit_prog(prog, BPF_AUDIT_UNLOAD); + __bpf_prog_put_noref(prog, true); +} + static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) { - if (atomic64_dec_and_test(&prog->aux->refcnt)) { - perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); - bpf_audit_prog(prog, BPF_AUDIT_UNLOAD); + struct bpf_prog_aux *aux = prog->aux; + + if (atomic64_dec_and_test(&aux->refcnt)) { /* bpf_prog_free_id() must be called first */ bpf_prog_free_id(prog, do_idr_lock); - __bpf_prog_put_noref(prog, true); + + if (in_irq() || irqs_disabled()) { + INIT_WORK(&aux->work, bpf_prog_put_deferred); + schedule_work(&aux->work); + } else { + bpf_prog_put_deferred(&aux->work); + } } } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 3dbb3b40b754..344ee67265cc 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -255,6 +255,7 @@ struct bpf_call_arg_meta { int mem_size; u64 msize_max_value; int ref_obj_id; + int map_uid; int func_id; struct btf *btf; u32 btf_id; @@ -734,6 +735,10 @@ static void print_verifier_state(struct bpf_verifier_env *env, if (state->refs[i].id) verbose(env, ",%d", state->refs[i].id); } + if (state->in_callback_fn) + verbose(env, " cb"); + if (state->in_async_callback_fn) + verbose(env, " async_cb"); verbose(env, "\n"); } @@ -1135,6 +1140,10 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) if (map->inner_map_meta) { reg->type = CONST_PTR_TO_MAP; reg->map_ptr = map->inner_map_meta; + /* transfer reg's id which is unique for every map_lookup_elem + * as UID of the inner map. + */ + reg->map_uid = reg->id; } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { reg->type = PTR_TO_XDP_SOCK; } else if (map->map_type == BPF_MAP_TYPE_SOCKMAP || @@ -1522,6 +1531,54 @@ static void init_func_state(struct bpf_verifier_env *env, init_reg_state(env, state); } +/* Similar to push_stack(), but for async callbacks */ +static struct bpf_verifier_state *push_async_cb(struct bpf_verifier_env *env, + int insn_idx, int prev_insn_idx, + int subprog) +{ + struct bpf_verifier_stack_elem *elem; + struct bpf_func_state *frame; + + elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL); + if (!elem) + goto err; + + elem->insn_idx = insn_idx; + elem->prev_insn_idx = prev_insn_idx; + elem->next = env->head; + elem->log_pos = env->log.len_used; + env->head = elem; + env->stack_size++; + if (env->stack_size > BPF_COMPLEXITY_LIMIT_JMP_SEQ) { + verbose(env, + "The sequence of %d jumps is too complex for async cb.\n", + env->stack_size); + goto err; + } + /* Unlike push_stack() do not copy_verifier_state(). + * The caller state doesn't matter. + * This is async callback. It starts in a fresh stack. + * Initialize it similar to do_check_common(). + */ + elem->st.branches = 1; + frame = kzalloc(sizeof(*frame), GFP_KERNEL); + if (!frame) + goto err; + init_func_state(env, frame, + BPF_MAIN_FUNC /* callsite */, + 0 /* frameno within this callchain */, + subprog /* subprog number within this prog */); + elem->st.frame[0] = frame; + return &elem->st; +err: + free_verifier_state(env->cur_state, true); + env->cur_state = NULL; + /* pop all elements and return */ + while (!pop_stack(env, NULL, NULL, false)); + return NULL; +} + + enum reg_arg_type { SRC_OP, /* register is used as source operand */ DST_OP, /* register is used as destination operand */ @@ -3241,6 +3298,15 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, 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; + } + } return err; } @@ -3643,6 +3709,8 @@ process_func: continue_func: subprog_end = subprog[idx + 1].start; for (; i < subprog_end; i++) { + int next_insn; + if (!bpf_pseudo_call(insn + i) && !bpf_pseudo_func(insn + i)) continue; /* remember insn and function to return to */ @@ -3650,13 +3718,22 @@ continue_func: ret_prog[frame] = idx; /* find the callee */ - i = i + insn[i].imm + 1; - idx = find_subprog(env, i); + next_insn = i + insn[i].imm + 1; + idx = find_subprog(env, next_insn); if (idx < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", - i); + next_insn); return -EFAULT; } + if (subprog[idx].is_async_cb) { + if (subprog[idx].has_tail_call) { + verbose(env, "verifier bug. subprog has tail_call and async cb\n"); + return -EFAULT; + } + /* async callbacks don't increase bpf prog stack size */ + continue; + } + i = next_insn; if (subprog[idx].has_tail_call) tail_call_reachable = true; @@ -4656,6 +4733,54 @@ static int process_spin_lock(struct bpf_verifier_env *env, int regno, return 0; } +static int process_timer_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]; + bool is_const = tnum_is_const(reg->var_off); + struct bpf_map *map = reg->map_ptr; + u64 val = reg->var_off.value; + + if (!is_const) { + verbose(env, + "R%d doesn't have constant offset. bpf_timer has to be at the constant offset\n", + regno); + return -EINVAL; + } + if (!map->btf) { + verbose(env, "map '%s' has to have BTF in order to use bpf_timer\n", + 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); + return -EINVAL; + } + if (map->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); + return -EINVAL; + } + if (meta->map_ptr) { + verbose(env, "verifier bug. Two map pointers in a timer helper\n"); + return -EFAULT; + } + meta->map_uid = reg->map_uid; + meta->map_ptr = map; + return 0; +} + static bool arg_type_is_mem_ptr(enum bpf_arg_type type) { return type == ARG_PTR_TO_MEM || @@ -4788,6 +4913,7 @@ static const struct bpf_reg_types percpu_btf_ptr_types = { .types = { PTR_TO_PER 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 } }; +static const struct bpf_reg_types timer_types = { .types = { PTR_TO_MAP_VALUE } }; static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_PTR_TO_MAP_KEY] = &map_key_value_types, @@ -4819,6 +4945,7 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_PTR_TO_FUNC] = &func_ptr_types, [ARG_PTR_TO_STACK_OR_NULL] = &stack_ptr_types, [ARG_PTR_TO_CONST_STR] = &const_str_ptr_types, + [ARG_PTR_TO_TIMER] = &timer_types, }; static int check_reg_type(struct bpf_verifier_env *env, u32 regno, @@ -4948,7 +5075,29 @@ skip_type_check: if (arg_type == ARG_CONST_MAP_PTR) { /* bpf_map_xxx(map_ptr) call: remember that map_ptr */ + if (meta->map_ptr) { + /* Use map_uid (which is unique id of inner map) to reject: + * inner_map1 = bpf_map_lookup_elem(outer_map, key1) + * inner_map2 = bpf_map_lookup_elem(outer_map, key2) + * if (inner_map1 && inner_map2) { + * timer = bpf_map_lookup_elem(inner_map1); + * if (timer) + * // mismatch would have been allowed + * bpf_timer_init(timer, inner_map2); + * } + * + * Comparing map_ptr is enough to distinguish normal and outer maps. + */ + if (meta->map_ptr != reg->map_ptr || + meta->map_uid != reg->map_uid) { + verbose(env, + "timer pointer in R1 map_uid=%d doesn't match map pointer in R2 map_uid=%d\n", + meta->map_uid, reg->map_uid); + return -EINVAL; + } + } meta->map_ptr = reg->map_ptr; + meta->map_uid = reg->map_uid; } else if (arg_type == ARG_PTR_TO_MAP_KEY) { /* bpf_map_xxx(..., map_ptr, ..., key) call: * check that [key, key + map->key_size) are within @@ -5000,6 +5149,9 @@ skip_type_check: verbose(env, "verifier internal error\n"); return -EFAULT; } + } else if (arg_type == ARG_PTR_TO_TIMER) { + if (process_timer_func(env, regno, meta)) + return -EACCES; } else if (arg_type == ARG_PTR_TO_FUNC) { meta->subprogno = reg->subprogno; } else if (arg_type_is_mem_ptr(arg_type)) { @@ -5615,6 +5767,31 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn } } + if (insn->code == (BPF_JMP | BPF_CALL) && + insn->imm == BPF_FUNC_timer_set_callback) { + struct bpf_verifier_state *async_cb; + + /* there is no real recursion here. timer callbacks are async */ + env->subprog_info[subprog].is_async_cb = true; + async_cb = push_async_cb(env, env->subprog_info[subprog].start, + *insn_idx, subprog); + if (!async_cb) + return -EFAULT; + callee = async_cb->frame[0]; + callee->async_entry_cnt = caller->async_entry_cnt + 1; + + /* Convert bpf_timer_set_callback() args into timer callback args */ + err = set_callee_state_cb(env, caller, callee, *insn_idx); + if (err) + return err; + + clear_caller_saved_regs(env, caller->regs); + mark_reg_unknown(env, caller->regs, BPF_REG_0); + caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; + /* continue with next insn after call */ + return 0; + } + callee = kzalloc(sizeof(*callee), GFP_KERNEL); if (!callee) return -ENOMEM; @@ -5742,6 +5919,35 @@ static int set_map_elem_callback_state(struct bpf_verifier_env *env, return 0; } +static int set_timer_callback_state(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee, + int insn_idx) +{ + struct bpf_map *map_ptr = caller->regs[BPF_REG_1].map_ptr; + + /* bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn); + * callback_fn(struct bpf_map *map, void *key, void *value); + */ + callee->regs[BPF_REG_1].type = CONST_PTR_TO_MAP; + __mark_reg_known_zero(&callee->regs[BPF_REG_1]); + callee->regs[BPF_REG_1].map_ptr = map_ptr; + + callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY; + __mark_reg_known_zero(&callee->regs[BPF_REG_2]); + callee->regs[BPF_REG_2].map_ptr = map_ptr; + + callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE; + __mark_reg_known_zero(&callee->regs[BPF_REG_3]); + callee->regs[BPF_REG_3].map_ptr = map_ptr; + + /* unused */ + __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); + __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); + callee->in_async_callback_fn = true; + return 0; +} + static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) { struct bpf_verifier_state *state = env->cur_state; @@ -6069,6 +6275,13 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EINVAL; } + if (func_id == BPF_FUNC_timer_set_callback) { + err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, + set_timer_callback_state); + if (err < 0) + return -EINVAL; + } + if (func_id == BPF_FUNC_snprintf) { err = check_bpf_snprintf_call(env, regs); if (err < 0) @@ -6104,6 +6317,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EINVAL; } regs[BPF_REG_0].map_ptr = meta.map_ptr; + regs[BPF_REG_0].map_uid = meta.map_uid; if (fn->ret_type == RET_PTR_TO_MAP_VALUE) { regs[BPF_REG_0].type = PTR_TO_MAP_VALUE; if (map_value_has_spin_lock(meta.map_ptr)) @@ -9099,7 +9313,8 @@ static int check_return_code(struct bpf_verifier_env *env) struct tnum range = tnum_range(0, 1); enum bpf_prog_type prog_type = resolve_prog_type(env->prog); int err; - const bool is_subprog = env->cur_state->frame[0]->subprogno; + struct bpf_func_state *frame = env->cur_state->frame[0]; + const bool is_subprog = frame->subprogno; /* LSM and struct_ops func-ptr's return type could be "void" */ if (!is_subprog && @@ -9124,6 +9339,22 @@ static int check_return_code(struct bpf_verifier_env *env) } reg = cur_regs(env) + BPF_REG_0; + + if (frame->in_async_callback_fn) { + /* enforce return zero from async callbacks like timer */ + if (reg->type != SCALAR_VALUE) { + verbose(env, "In async callback the register R0 is not a known value (%s)\n", + reg_type_str[reg->type]); + return -EINVAL; + } + + if (!tnum_in(tnum_const(0), reg->var_off)) { + verbose_invalid_scalar(env, reg, &range, "async callback", "R0"); + return -EINVAL; + } + return 0; + } + if (is_subprog) { if (reg->type != SCALAR_VALUE) { verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n", @@ -9338,8 +9569,12 @@ static int visit_func_call_insn(int t, int insn_cnt, init_explored_state(env, t + 1); if (visit_callee) { init_explored_state(env, t); - ret = push_insn(t, t + insns[t].imm + 1, BRANCH, - env, false); + ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env, + /* It's ok to allow recursion from CFG point of + * view. __check_func_call() will do the actual + * check. + */ + bpf_pseudo_func(insns + t)); } return ret; } @@ -9367,6 +9602,13 @@ static int visit_insn(int t, int insn_cnt, struct bpf_verifier_env *env) return DONE_EXPLORING; case BPF_CALL: + if (insns[t].imm == BPF_FUNC_timer_set_callback) + /* Mark this call insn to trigger is_state_visited() check + * before call itself is processed by __check_func_call(). + * Otherwise new async state will be pushed for further + * exploration. + */ + init_explored_state(env, t); return visit_func_call_insn(t, insn_cnt, insns, env, insns[t].src_reg == BPF_PSEUDO_CALL); @@ -10374,9 +10616,25 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) states_cnt++; if (sl->state.insn_idx != insn_idx) goto next; + if (sl->state.branches) { - if (states_maybe_looping(&sl->state, cur) && - states_equal(env, &sl->state, cur)) { + struct bpf_func_state *frame = sl->state.frame[sl->state.curframe]; + + if (frame->in_async_callback_fn && + frame->async_entry_cnt != cur->frame[cur->curframe]->async_entry_cnt) { + /* Different async_entry_cnt means that the verifier is + * processing another entry into async callback. + * Seeing the same state is not an indication of infinite + * loop or infinite recursion. + * But finding the same state doesn't mean that it's safe + * to stop processing the current state. The previous state + * hasn't yet reached bpf_exit, since state.branches > 0. + * Checking in_async_callback_fn alone is not enough either. + * Since the verifier still needs to catch infinite loops + * inside async callbacks. + */ + } else if (states_maybe_looping(&sl->state, cur) && + states_equal(env, &sl->state, cur)) { verbose_linfo(env, insn_idx, "; "); verbose(env, "infinite loop detected at insn %d\n", insn_idx); return -EINVAL; @@ -12591,6 +12849,39 @@ static int do_misc_fixups(struct bpf_verifier_env *env) continue; } + if (insn->imm == BPF_FUNC_timer_set_callback) { + /* The verifier will process callback_fn as many times as necessary + * with different maps and the register states prepared by + * set_timer_callback_state will be accurate. + * + * The following use case is valid: + * map1 is shared by prog1, prog2, prog3. + * prog1 calls bpf_timer_init for some map1 elements + * prog2 calls bpf_timer_set_callback for some map1 elements. + * Those that were not bpf_timer_init-ed will return -EINVAL. + * prog3 calls bpf_timer_start for some map1 elements. + * Those that were not both bpf_timer_init-ed and + * bpf_timer_set_callback-ed will return -EINVAL. + */ + struct bpf_insn ld_addrs[2] = { + BPF_LD_IMM64(BPF_REG_3, (long)prog->aux), + }; + + insn_buf[0] = ld_addrs[0]; + insn_buf[1] = ld_addrs[1]; + insn_buf[2] = *insn; + cnt = 3; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + goto patch_call_imm; + } + /* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup * and other inlining handlers are currently limited to 64 bit * only. diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 64bd2d84367f..6c77d25137e0 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1059,7 +1059,7 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_snprintf: return &bpf_snprintf_proto; default: - return NULL; + return bpf_base_func_proto(func_id); } } diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index 2d94025b38e9..00ac7b79cddb 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -547,6 +547,7 @@ class PrinterHelpers(Printer): 'struct inode', 'struct socket', 'struct file', + 'struct bpf_timer', ] known_types = { '...', @@ -594,6 +595,7 @@ class PrinterHelpers(Printer): 'struct inode', 'struct socket', 'struct file', + 'struct bpf_timer', } mapped_types = { 'u8': '__u8', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index bafb6282032b..3544ec5234f0 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4777,6 +4777,70 @@ union bpf_attr { * Execute close syscall for given FD. * Return * A syscall result. + * + * long bpf_timer_init(struct bpf_timer *timer, struct bpf_map *map, u64 flags) + * Description + * Initialize the timer. + * First 4 bits of *flags* specify clockid. + * Only CLOCK_MONOTONIC, CLOCK_REALTIME, CLOCK_BOOTTIME are allowed. + * All other bits of *flags* are reserved. + * The verifier will reject the program if *timer* is not from + * the same *map*. + * Return + * 0 on success. + * **-EBUSY** if *timer* is already initialized. + * **-EINVAL** if invalid *flags* are passed. + * **-EPERM** if *timer* is in a map that doesn't have any user references. + * The user space should either hold a file descriptor to a map with timers + * or pin such map in bpffs. When map is unpinned or file descriptor is + * closed all timers in the map will be cancelled and freed. + * + * long bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn) + * Description + * Configure the timer to call *callback_fn* static function. + * Return + * 0 on success. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier. + * **-EPERM** if *timer* is in a map that doesn't have any user references. + * The user space should either hold a file descriptor to a map with timers + * or pin such map in bpffs. When map is unpinned or file descriptor is + * closed all timers in the map will be cancelled and freed. + * + * long bpf_timer_start(struct bpf_timer *timer, u64 nsecs, u64 flags) + * Description + * Set timer expiration N nanoseconds from the current time. The + * configured callback will be invoked in soft irq context on some cpu + * and will not repeat unless another bpf_timer_start() is made. + * In such case the next invocation can migrate to a different cpu. + * Since struct bpf_timer is a field inside map element the map + * owns the timer. The bpf_timer_set_callback() will increment refcnt + * of BPF program to make sure that callback_fn code stays valid. + * When user space reference to a map reaches zero all timers + * in a map are cancelled and corresponding program's refcnts are + * decremented. This is done to make sure that Ctrl-C of a user + * process doesn't leave any timers running. If map is pinned in + * bpffs the callback_fn can re-arm itself indefinitely. + * bpf_map_update/delete_elem() helpers and user space sys_bpf commands + * cancel and free the timer in the given map element. + * The map can contain timers that invoke callback_fn-s from different + * programs. The same callback_fn can serve different timers from + * different maps if key/value layout matches across maps. + * Every bpf_timer_set_callback() can have different callback_fn. + * + * Return + * 0 on success. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier + * or invalid *flags* are passed. + * + * long bpf_timer_cancel(struct bpf_timer *timer) + * Description + * Cancel the timer and wait for callback_fn to finish if it was running. + * Return + * 0 if the timer was not active. + * 1 if the timer was active. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier. + * **-EDEADLK** if callback_fn tried to call bpf_timer_cancel() on its + * own timer which would have led to a deadlock otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -4948,6 +5012,10 @@ union bpf_attr { FN(sys_bpf), \ FN(btf_find_by_name_kind), \ FN(sys_close), \ + FN(timer_init), \ + FN(timer_set_callback), \ + FN(timer_start), \ + FN(timer_cancel), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -6074,6 +6142,11 @@ struct bpf_spin_lock { __u32 val; }; +struct bpf_timer { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + struct bpf_sysctl { __u32 write; /* Sysctl is being read (= 0) or written (= 1). * Allows 1,2,4-byte read, but no write. diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c new file mode 100644 index 000000000000..25f40e1b9967 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/timer.c @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <test_progs.h> +#include "timer.skel.h" + +static int timer(struct timer *timer_skel) +{ + int err, prog_fd; + __u32 duration = 0, retval; + + err = timer__attach(timer_skel); + if (!ASSERT_OK(err, "timer_attach")) + return err; + + ASSERT_EQ(timer_skel->data->callback_check, 52, "callback_check1"); + ASSERT_EQ(timer_skel->data->callback2_check, 52, "callback2_check1"); + + prog_fd = bpf_program__fd(timer_skel->progs.test1); + err = bpf_prog_test_run(prog_fd, 1, NULL, 0, + NULL, NULL, &retval, &duration); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(retval, 0, "test_run"); + timer__detach(timer_skel); + + usleep(50); /* 10 usecs should be enough, but give it extra */ + /* check that timer_cb1() was executed 10+10 times */ + ASSERT_EQ(timer_skel->data->callback_check, 42, "callback_check2"); + ASSERT_EQ(timer_skel->data->callback2_check, 42, "callback2_check2"); + + /* check that timer_cb2() was executed twice */ + ASSERT_EQ(timer_skel->bss->bss_data, 10, "bss_data"); + + /* check that there were no errors in timer execution */ + ASSERT_EQ(timer_skel->bss->err, 0, "err"); + + /* check that code paths completed */ + ASSERT_EQ(timer_skel->bss->ok, 1 | 2 | 4, "ok"); + + return 0; +} + +void test_timer(void) +{ + struct timer *timer_skel = NULL; + int err; + + timer_skel = timer__open_and_load(); + if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load")) + goto cleanup; + + err = timer(timer_skel); + ASSERT_OK(err, "timer"); +cleanup: + timer__destroy(timer_skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/timer_mim.c b/tools/testing/selftests/bpf/prog_tests/timer_mim.c new file mode 100644 index 000000000000..f5acbcbe33a4 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/timer_mim.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <test_progs.h> +#include "timer_mim.skel.h" +#include "timer_mim_reject.skel.h" + +static int timer_mim(struct timer_mim *timer_skel) +{ + __u32 duration = 0, retval; + __u64 cnt1, cnt2; + int err, prog_fd, key1 = 1; + + err = timer_mim__attach(timer_skel); + if (!ASSERT_OK(err, "timer_attach")) + return err; + + prog_fd = bpf_program__fd(timer_skel->progs.test1); + err = bpf_prog_test_run(prog_fd, 1, NULL, 0, + NULL, NULL, &retval, &duration); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(retval, 0, "test_run"); + timer_mim__detach(timer_skel); + + /* check that timer_cb[12] are incrementing 'cnt' */ + cnt1 = READ_ONCE(timer_skel->bss->cnt); + usleep(200); /* 100 times more than interval */ + cnt2 = READ_ONCE(timer_skel->bss->cnt); + ASSERT_GT(cnt2, cnt1, "cnt"); + + ASSERT_EQ(timer_skel->bss->err, 0, "err"); + /* check that code paths completed */ + ASSERT_EQ(timer_skel->bss->ok, 1 | 2, "ok"); + + close(bpf_map__fd(timer_skel->maps.inner_htab)); + err = bpf_map_delete_elem(bpf_map__fd(timer_skel->maps.outer_arr), &key1); + ASSERT_EQ(err, 0, "delete inner map"); + + /* check that timer_cb[12] are no longer running */ + cnt1 = READ_ONCE(timer_skel->bss->cnt); + usleep(200); + cnt2 = READ_ONCE(timer_skel->bss->cnt); + ASSERT_EQ(cnt2, cnt1, "cnt"); + + return 0; +} + +void test_timer_mim(void) +{ + struct timer_mim_reject *timer_reject_skel = NULL; + libbpf_print_fn_t old_print_fn = NULL; + struct timer_mim *timer_skel = NULL; + int err; + + old_print_fn = libbpf_set_print(NULL); + timer_reject_skel = timer_mim_reject__open_and_load(); + libbpf_set_print(old_print_fn); + if (!ASSERT_ERR_PTR(timer_reject_skel, "timer_reject_skel_load")) + goto cleanup; + + timer_skel = timer_mim__open_and_load(); + if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load")) + goto cleanup; + + err = timer_mim(timer_skel); + ASSERT_OK(err, "timer_mim"); +cleanup: + timer_mim__destroy(timer_skel); + timer_mim_reject__destroy(timer_reject_skel); +} diff --git a/tools/testing/selftests/bpf/progs/timer.c b/tools/testing/selftests/bpf/progs/timer.c new file mode 100644 index 000000000000..5f5309791649 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/timer.c @@ -0,0 +1,297 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <linux/bpf.h> +#include <time.h> +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "GPL"; +struct hmap_elem { + int counter; + struct bpf_timer timer; + struct bpf_spin_lock lock; /* unused */ +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1000); + __type(key, int); + __type(value, struct hmap_elem); +} hmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(map_flags, BPF_F_NO_PREALLOC); + __uint(max_entries, 1000); + __type(key, int); + __type(value, struct hmap_elem); +} hmap_malloc SEC(".maps"); + +struct elem { + struct bpf_timer t; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 2); + __type(key, int); + __type(value, struct elem); +} array SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_LRU_HASH); + __uint(max_entries, 4); + __type(key, int); + __type(value, struct elem); +} lru SEC(".maps"); + +__u64 bss_data; +__u64 err; +__u64 ok; +__u64 callback_check = 52; +__u64 callback2_check = 52; + +#define ARRAY 1 +#define HTAB 2 +#define HTAB_MALLOC 3 +#define LRU 4 + +/* callback for array and lru timers */ +static int timer_cb1(void *map, int *key, struct bpf_timer *timer) +{ + /* increment bss variable twice. + * Once via array timer callback and once via lru timer callback + */ + bss_data += 5; + + /* *key == 0 - the callback was called for array timer. + * *key == 4 - the callback was called from lru timer. + */ + if (*key == ARRAY) { + struct bpf_timer *lru_timer; + int lru_key = LRU; + + /* rearm array timer to be called again in ~35 seconds */ + if (bpf_timer_start(timer, 1ull << 35, 0) != 0) + err |= 1; + + lru_timer = bpf_map_lookup_elem(&lru, &lru_key); + if (!lru_timer) + return 0; + bpf_timer_set_callback(lru_timer, timer_cb1); + if (bpf_timer_start(lru_timer, 0, 0) != 0) + err |= 2; + } else if (*key == LRU) { + int lru_key, i; + + for (i = LRU + 1; + i <= 100 /* for current LRU eviction algorithm this number + * should be larger than ~ lru->max_entries * 2 + */; + i++) { + struct elem init = {}; + + /* lru_key cannot be used as loop induction variable + * otherwise the loop will be unbounded. + */ + lru_key = i; + + /* add more elements into lru map to push out current + * element and force deletion of this timer + */ + bpf_map_update_elem(map, &lru_key, &init, 0); + /* look it up to bump it into active list */ + bpf_map_lookup_elem(map, &lru_key); + + /* keep adding until *key changes underneath, + * which means that key/timer memory was reused + */ + if (*key != LRU) + break; + } + + /* check that the timer was removed */ + if (bpf_timer_cancel(timer) != -EINVAL) + err |= 4; + ok |= 1; + } + return 0; +} + +SEC("fentry/bpf_fentry_test1") +int BPF_PROG(test1, int a) +{ + struct bpf_timer *arr_timer, *lru_timer; + struct elem init = {}; + int lru_key = LRU; + int array_key = ARRAY; + + arr_timer = bpf_map_lookup_elem(&array, &array_key); + if (!arr_timer) + return 0; + bpf_timer_init(arr_timer, &array, CLOCK_MONOTONIC); + + bpf_map_update_elem(&lru, &lru_key, &init, 0); + lru_timer = bpf_map_lookup_elem(&lru, &lru_key); + if (!lru_timer) + return 0; + bpf_timer_init(lru_timer, &lru, CLOCK_MONOTONIC); + + bpf_timer_set_callback(arr_timer, timer_cb1); + bpf_timer_start(arr_timer, 0 /* call timer_cb1 asap */, 0); + + /* init more timers to check that array destruction + * doesn't leak timer memory. + */ + array_key = 0; + arr_timer = bpf_map_lookup_elem(&array, &array_key); + if (!arr_timer) + return 0; + bpf_timer_init(arr_timer, &array, CLOCK_MONOTONIC); + return 0; +} + +/* callback for prealloc and non-prealloca hashtab timers */ +static int timer_cb2(void *map, int *key, struct hmap_elem *val) +{ + if (*key == HTAB) + callback_check--; + else + callback2_check--; + if (val->counter > 0 && --val->counter) { + /* re-arm the timer again to execute after 1 usec */ + bpf_timer_start(&val->timer, 1000, 0); + } else if (*key == HTAB) { + struct bpf_timer *arr_timer; + int array_key = ARRAY; + + /* cancel arr_timer otherwise bpf_fentry_test1 prog + * will stay alive forever. + */ + arr_timer = bpf_map_lookup_elem(&array, &array_key); + if (!arr_timer) + return 0; + if (bpf_timer_cancel(arr_timer) != 1) + /* bpf_timer_cancel should return 1 to indicate + * that arr_timer was active at this time + */ + err |= 8; + + /* try to cancel ourself. It shouldn't deadlock. */ + if (bpf_timer_cancel(&val->timer) != -EDEADLK) + err |= 16; + + /* delete this key and this timer anyway. + * It shouldn't deadlock either. + */ + bpf_map_delete_elem(map, key); + + /* in preallocated hashmap both 'key' and 'val' could have been + * reused to store another map element (like in LRU above), + * but in controlled test environment the below test works. + * It's not a use-after-free. The memory is owned by the map. + */ + if (bpf_timer_start(&val->timer, 1000, 0) != -EINVAL) + err |= 32; + ok |= 2; + } else { + if (*key != HTAB_MALLOC) + err |= 64; + + /* try to cancel ourself. It shouldn't deadlock. */ + if (bpf_timer_cancel(&val->timer) != -EDEADLK) + err |= 128; + + /* delete this key and this timer anyway. + * It shouldn't deadlock either. + */ + bpf_map_delete_elem(map, key); + + /* in non-preallocated hashmap both 'key' and 'val' are RCU + * protected and still valid though this element was deleted + * from the map. Arm this timer for ~35 seconds. When callback + * finishes the call_rcu will invoke: + * htab_elem_free_rcu + * check_and_free_timer + * bpf_timer_cancel_and_free + * to cancel this 35 second sleep and delete the timer for real. + */ + if (bpf_timer_start(&val->timer, 1ull << 35, 0) != 0) + err |= 256; + ok |= 4; + } + return 0; +} + +int bpf_timer_test(void) +{ + struct hmap_elem *val; + int key = HTAB, key_malloc = HTAB_MALLOC; + + val = bpf_map_lookup_elem(&hmap, &key); + if (val) { + if (bpf_timer_init(&val->timer, &hmap, CLOCK_BOOTTIME) != 0) + err |= 512; + bpf_timer_set_callback(&val->timer, timer_cb2); + bpf_timer_start(&val->timer, 1000, 0); + } + val = bpf_map_lookup_elem(&hmap_malloc, &key_malloc); + if (val) { + if (bpf_timer_init(&val->timer, &hmap_malloc, CLOCK_BOOTTIME) != 0) + err |= 1024; + bpf_timer_set_callback(&val->timer, timer_cb2); + bpf_timer_start(&val->timer, 1000, 0); + } + return 0; +} + +SEC("fentry/bpf_fentry_test2") +int BPF_PROG(test2, int a, int b) +{ + struct hmap_elem init = {}, *val; + int key = HTAB, key_malloc = HTAB_MALLOC; + + init.counter = 10; /* number of times to trigger timer_cb2 */ + bpf_map_update_elem(&hmap, &key, &init, 0); + val = bpf_map_lookup_elem(&hmap, &key); + if (val) + bpf_timer_init(&val->timer, &hmap, CLOCK_BOOTTIME); + /* update the same key to free the timer */ + bpf_map_update_elem(&hmap, &key, &init, 0); + + bpf_map_update_elem(&hmap_malloc, &key_malloc, &init, 0); + val = bpf_map_lookup_elem(&hmap_malloc, &key_malloc); + if (val) + bpf_timer_init(&val->timer, &hmap_malloc, CLOCK_BOOTTIME); + /* update the same key to free the timer */ + bpf_map_update_elem(&hmap_malloc, &key_malloc, &init, 0); + + /* init more timers to check that htab operations + * don't leak timer memory. + */ + key = 0; + bpf_map_update_elem(&hmap, &key, &init, 0); + val = bpf_map_lookup_elem(&hmap, &key); + if (val) + bpf_timer_init(&val->timer, &hmap, CLOCK_BOOTTIME); + bpf_map_delete_elem(&hmap, &key); + bpf_map_update_elem(&hmap, &key, &init, 0); + val = bpf_map_lookup_elem(&hmap, &key); + if (val) + bpf_timer_init(&val->timer, &hmap, CLOCK_BOOTTIME); + + /* and with non-prealloc htab */ + key_malloc = 0; + bpf_map_update_elem(&hmap_malloc, &key_malloc, &init, 0); + val = bpf_map_lookup_elem(&hmap_malloc, &key_malloc); + if (val) + bpf_timer_init(&val->timer, &hmap_malloc, CLOCK_BOOTTIME); + bpf_map_delete_elem(&hmap_malloc, &key_malloc); + bpf_map_update_elem(&hmap_malloc, &key_malloc, &init, 0); + val = bpf_map_lookup_elem(&hmap_malloc, &key_malloc); + if (val) + bpf_timer_init(&val->timer, &hmap_malloc, CLOCK_BOOTTIME); + + return bpf_timer_test(); +} diff --git a/tools/testing/selftests/bpf/progs/timer_mim.c b/tools/testing/selftests/bpf/progs/timer_mim.c new file mode 100644 index 000000000000..2fee7ab105ef --- /dev/null +++ b/tools/testing/selftests/bpf/progs/timer_mim.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <linux/bpf.h> +#include <time.h> +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "GPL"; +struct hmap_elem { + int pad; /* unused */ + struct bpf_timer timer; +}; + +struct inner_map { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1024); + __type(key, int); + __type(value, struct hmap_elem); +} inner_htab SEC(".maps"); + +#define ARRAY_KEY 1 +#define HASH_KEY 1234 + +struct outer_arr { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 2); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); + __array(values, struct inner_map); +} outer_arr SEC(".maps") = { + .values = { [ARRAY_KEY] = &inner_htab }, +}; + +__u64 err; +__u64 ok; +__u64 cnt; + +static int timer_cb1(void *map, int *key, struct hmap_elem *val); + +static int timer_cb2(void *map, int *key, struct hmap_elem *val) +{ + cnt++; + bpf_timer_set_callback(&val->timer, timer_cb1); + if (bpf_timer_start(&val->timer, 1000, 0)) + err |= 1; + ok |= 1; + return 0; +} + +/* callback for inner hash map */ +static int timer_cb1(void *map, int *key, struct hmap_elem *val) +{ + cnt++; + bpf_timer_set_callback(&val->timer, timer_cb2); + if (bpf_timer_start(&val->timer, 1000, 0)) + err |= 2; + /* Do a lookup to make sure 'map' and 'key' pointers are correct */ + bpf_map_lookup_elem(map, key); + ok |= 2; + return 0; +} + +SEC("fentry/bpf_fentry_test1") +int BPF_PROG(test1, int a) +{ + struct hmap_elem init = {}; + struct bpf_map *inner_map; + struct hmap_elem *val; + int array_key = ARRAY_KEY; + int hash_key = HASH_KEY; + + inner_map = bpf_map_lookup_elem(&outer_arr, &array_key); + if (!inner_map) + return 0; + + bpf_map_update_elem(inner_map, &hash_key, &init, 0); + val = bpf_map_lookup_elem(inner_map, &hash_key); + if (!val) + return 0; + + bpf_timer_init(&val->timer, inner_map, CLOCK_MONOTONIC); + if (bpf_timer_set_callback(&val->timer, timer_cb1)) + err |= 4; + if (bpf_timer_start(&val->timer, 0, 0)) + err |= 8; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/timer_mim_reject.c b/tools/testing/selftests/bpf/progs/timer_mim_reject.c new file mode 100644 index 000000000000..5d648e3d8a41 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/timer_mim_reject.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <linux/bpf.h> +#include <time.h> +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "GPL"; +struct hmap_elem { + int pad; /* unused */ + struct bpf_timer timer; +}; + +struct inner_map { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1024); + __type(key, int); + __type(value, struct hmap_elem); +} inner_htab SEC(".maps"); + +#define ARRAY_KEY 1 +#define ARRAY_KEY2 2 +#define HASH_KEY 1234 + +struct outer_arr { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 2); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); + __array(values, struct inner_map); +} outer_arr SEC(".maps") = { + .values = { [ARRAY_KEY] = &inner_htab }, +}; + +__u64 err; +__u64 ok; +__u64 cnt; + +/* callback for inner hash map */ +static int timer_cb(void *map, int *key, struct hmap_elem *val) +{ + return 0; +} + +SEC("fentry/bpf_fentry_test1") +int BPF_PROG(test1, int a) +{ + struct hmap_elem init = {}; + struct bpf_map *inner_map, *inner_map2; + struct hmap_elem *val; + int array_key = ARRAY_KEY; + int array_key2 = ARRAY_KEY2; + int hash_key = HASH_KEY; + + inner_map = bpf_map_lookup_elem(&outer_arr, &array_key); + if (!inner_map) + return 0; + + inner_map2 = bpf_map_lookup_elem(&outer_arr, &array_key2); + if (!inner_map2) + return 0; + bpf_map_update_elem(inner_map, &hash_key, &init, 0); + val = bpf_map_lookup_elem(inner_map, &hash_key); + if (!val) + return 0; + + bpf_timer_init(&val->timer, inner_map2, CLOCK_MONOTONIC); + if (bpf_timer_set_callback(&val->timer, timer_cb)) + err |= 4; + if (bpf_timer_start(&val->timer, 0, 0)) + err |= 8; + return 0; +} |