+/*
+ * watch/notify callback event infrastructure
+ *
+ * These callbacks are used both for watch and notify operations.
+ */
+static void __release_event(struct kref *kref)
+{
+ struct ceph_osd_event *event =
+ container_of(kref, struct ceph_osd_event, kref);
+
+ dout("__release_event %p\n", event);
+ kfree(event);
+}
+
+static void get_event(struct ceph_osd_event *event)
+{
+ kref_get(&event->kref);
+}
+
+void ceph_osdc_put_event(struct ceph_osd_event *event)
+{
+ kref_put(&event->kref, __release_event);
+}
+EXPORT_SYMBOL(ceph_osdc_put_event);
+
+static void __insert_event(struct ceph_osd_client *osdc,
+ struct ceph_osd_event *new)
+{
+ struct rb_node **p = &osdc->event_tree.rb_node;
+ struct rb_node *parent = NULL;
+ struct ceph_osd_event *event = NULL;
+
+ while (*p) {
+ parent = *p;
+ event = rb_entry(parent, struct ceph_osd_event, node);
+ if (new->cookie < event->cookie)
+ p = &(*p)->rb_left;
+ else if (new->cookie > event->cookie)
+ p = &(*p)->rb_right;
+ else
+ BUG();
+ }
+
+ rb_link_node(&new->node, parent, p);
+ rb_insert_color(&new->node, &osdc->event_tree);
+}
+
+static struct ceph_osd_event *__find_event(struct ceph_osd_client *osdc,
+ u64 cookie)
+{
+ struct rb_node **p = &osdc->event_tree.rb_node;
+ struct rb_node *parent = NULL;
+ struct ceph_osd_event *event = NULL;
+
+ while (*p) {
+ parent = *p;
+ event = rb_entry(parent, struct ceph_osd_event, node);
+ if (cookie < event->cookie)
+ p = &(*p)->rb_left;
+ else if (cookie > event->cookie)
+ p = &(*p)->rb_right;
+ else
+ return event;
+ }
+ return NULL;
+}
+
+static void __remove_event(struct ceph_osd_event *event)
+{
+ struct ceph_osd_client *osdc = event->osdc;
+
+ if (!RB_EMPTY_NODE(&event->node)) {
+ dout("__remove_event removed %p\n", event);
+ rb_erase(&event->node, &osdc->event_tree);
+ ceph_osdc_put_event(event);
+ } else {
+ dout("__remove_event didn't remove %p\n", event);
+ }
+}
+
+int ceph_osdc_create_event(struct ceph_osd_client *osdc,
+ void (*event_cb)(u64, u64, u8, void *),
+ int one_shot, void *data,
+ struct ceph_osd_event **pevent)
+{
+ struct ceph_osd_event *event;
+
+ event = kmalloc(sizeof(*event), GFP_NOIO);
+ if (!event)
+ return -ENOMEM;
+
+ dout("create_event %p\n", event);
+ event->cb = event_cb;
+ event->one_shot = one_shot;
+ event->data = data;
+ event->osdc = osdc;
+ INIT_LIST_HEAD(&event->osd_node);
+ kref_init(&event->kref); /* one ref for us */
+ kref_get(&event->kref); /* one ref for the caller */
+ init_completion(&event->completion);
+
+ spin_lock(&osdc->event_lock);
+ event->cookie = ++osdc->event_count;
+ __insert_event(osdc, event);
+ spin_unlock(&osdc->event_lock);
+
+ *pevent = event;
+ return 0;
+}
+EXPORT_SYMBOL(ceph_osdc_create_event);
+
+void ceph_osdc_cancel_event(struct ceph_osd_event *event)
+{
+ struct ceph_osd_client *osdc = event->osdc;
+
+ dout("cancel_event %p\n", event);
+ spin_lock(&osdc->event_lock);
+ __remove_event(event);
+ spin_unlock(&osdc->event_lock);
+ ceph_osdc_put_event(event); /* caller's */
+}
+EXPORT_SYMBOL(ceph_osdc_cancel_event);
+
+
+static void do_event_work(struct work_struct *work)
+{
+ struct ceph_osd_event_work *event_work =
+ container_of(work, struct ceph_osd_event_work, work);
+ struct ceph_osd_event *event = event_work->event;
+ u64 ver = event_work->ver;
+ u64 notify_id = event_work->notify_id;
+ u8 opcode = event_work->opcode;
+
+ dout("do_event_work completing %p\n", event);
+ event->cb(ver, notify_id, opcode, event->data);
+ complete(&event->completion);
+ dout("do_event_work completed %p\n", event);
+ ceph_osdc_put_event(event);
+ kfree(event_work);
+}
+
+
+/*
+ * Process osd watch notifications
+ */
+void handle_watch_notify(struct ceph_osd_client *osdc, struct ceph_msg *msg)
+{
+ void *p, *end;
+ u8 proto_ver;
+ u64 cookie, ver, notify_id;
+ u8 opcode;
+ struct ceph_osd_event *event;
+ struct ceph_osd_event_work *event_work;
+
+ p = msg->front.iov_base;
+ end = p + msg->front.iov_len;
+
+ ceph_decode_8_safe(&p, end, proto_ver, bad);
+ ceph_decode_8_safe(&p, end, opcode, bad);
+ ceph_decode_64_safe(&p, end, cookie, bad);
+ ceph_decode_64_safe(&p, end, ver, bad);
+ ceph_decode_64_safe(&p, end, notify_id, bad);
+
+ spin_lock(&osdc->event_lock);
+ event = __find_event(osdc, cookie);
+ if (event) {
+ get_event(event);
+ if (event->one_shot)
+ __remove_event(event);
+ }
+ spin_unlock(&osdc->event_lock);
+ dout("handle_watch_notify cookie %lld ver %lld event %p\n",
+ cookie, ver, event);
+ if (event) {
+ event_work = kmalloc(sizeof(*event_work), GFP_NOIO);
+ INIT_WORK(&event_work->work, do_event_work);
+ if (!event_work) {
+ dout("ERROR: could not allocate event_work\n");
+ goto done_err;
+ }
+ event_work->event = event;
+ event_work->ver = ver;
+ event_work->notify_id = notify_id;
+ event_work->opcode = opcode;
+ if (!queue_work(osdc->notify_wq, &event_work->work)) {
+ dout("WARNING: failed to queue notify event work\n");
+ goto done_err;
+ }
+ }
+
+ return;
+
+done_err:
+ complete(&event->completion);
+ ceph_osdc_put_event(event);
+ return;
+
+bad:
+ pr_err("osdc handle_watch_notify corrupt msg\n");
+ return;
+}
+
+int ceph_osdc_wait_event(struct ceph_osd_event *event, unsigned long timeout)
+{
+ int err;
+
+ dout("wait_event %p\n", event);
+ err = wait_for_completion_interruptible_timeout(&event->completion,
+ timeout * HZ);
+ ceph_osdc_put_event(event);
+ if (err > 0)
+ err = 0;
+ dout("wait_event %p returns %d\n", event, err);
+ return err;
+}
+EXPORT_SYMBOL(ceph_osdc_wait_event);
+