On 2/14/24 9:18 AM, Benjamin Tissoires wrote:
+static void bpf_timer_work_cb(struct work_struct *work)
+{
+ struct bpf_hrtimer *t = container_of(work, struct bpf_hrtimer, work);
+ struct bpf_map *map = t->map;
+ void *value = t->value;
+ bpf_callback_t callback_fn;
+ void *key;
+ u32 idx;
+
+ BTF_TYPE_EMIT(struct bpf_timer);
+
+ rcu_read_lock();
+ callback_fn = rcu_dereference(t->sleepable_cb_fn);
+ rcu_read_unlock();
I took a very brief look at patch 2. One thing that may worth to ask here, the
rcu_read_unlock() seems to be done too early. It is protecting the
t->sleepable_cb_fn (?), so should it be done after finished using the callback_fn?
A high level design question. The intention of the new
bpf_timer_set_sleepable_cb() kfunc is actually to delay work to a workqueue. It
is useful to delay work from the bpf_timer_cb and it may also useful to delay
work from other bpf running context (e.g. the networking hooks like "tc"). The
bpf_timer_set_sleepable_cb() seems to be unnecessary forcing delay-work must be
done in a bpf_timer_cb.
Have you thought about if it is possible to create a more generic kfunc like
bpf_schedule_work() to delay work to a workqueue ?
+ if (!callback_fn)
+ return;
+
+ /* FIXME: do we need any locking? */
+ 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);
+ }
+
+ /* FIXME: this crashes the system with
+ * BUG: kernel NULL pointer dereference, address: 000000000000000b
+ */
+ /* callback_fn((u64)(long)map, (u64)(long)key, (u64)(long)value, 0, 0); */
+ /* The verifier checked that return value is zero. */
+}
+
[ ... ]
+/* FIXME: use kernel doc style */
+/* Description
+ * Configure the timer to call *callback_fn* static function in a
+ * sleepable context.
+ * 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.
+ */
+__bpf_kfunc int bpf_timer_set_sleepable_cb(struct bpf_timer_kern *timer,
+ int (callback_fn)(void *map, int *key, struct bpf_timer *timer))
+{
+ struct bpf_throw_ctx ctx = {};
+
+ /* FIXME: definietely not sure this is OK */
+ arch_bpf_stack_walk(bpf_stack_walker, &ctx);
+ WARN_ON_ONCE(!ctx.aux);
+
+ if (!ctx.aux)
+ return -EINVAL;
+
+ return __bpf_timer_set_callback(timer, (void *)callback_fn, ctx.aux, true);
+}
+
