tfile->napi_enabled = napi_en;
tfile->napi_frags_enabled = napi_en && napi_frags;
if (napi_en) {
- netif_napi_add(tun->dev, &tfile->napi, tun_napi_poll,
- NAPI_POLL_WEIGHT);
+ netif_tx_napi_add(tun->dev, &tfile->napi, tun_napi_poll,
+ NAPI_POLL_WEIGHT);
napi_enable(&tfile->napi);
}
}
}
static int tun_attach(struct tun_struct *tun, struct file *file,
- bool skip_filter, bool napi, bool napi_frags)
+ bool skip_filter, bool napi, bool napi_frags,
+ bool publish_tun)
{
struct tun_file *tfile = file->private_data;
struct net_device *dev = tun->dev;
* initialized tfile; otherwise we risk using half-initialized
* object.
*/
- rcu_assign_pointer(tfile->tun, tun);
+ if (publish_tun)
+ rcu_assign_pointer(tfile->tun, tun);
rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
tun->numqueues++;
tun_set_real_num_queues(tun);
/* Net device open. */
static int tun_net_open(struct net_device *dev)
{
- struct tun_struct *tun = netdev_priv(dev);
- int i;
-
netif_tx_start_all_queues(dev);
- for (i = 0; i < tun->numqueues; i++) {
- struct tun_file *tfile;
-
- tfile = rtnl_dereference(tun->tfiles[i]);
- tfile->socket.sk->sk_write_space(tfile->socket.sk);
- }
-
return 0;
}
dev->max_mtu = MAX_MTU - dev->hard_header_len;
}
+static bool tun_sock_writeable(struct tun_struct *tun, struct tun_file *tfile)
+{
+ struct sock *sk = tfile->socket.sk;
+
+ return (tun->dev->flags & IFF_UP) && sock_writeable(sk);
+}
+
/* Character device part */
/* Poll */
if (!skb_array_empty(&tfile->tx_array))
mask |= POLLIN | POLLRDNORM;
- if (tun->dev->flags & IFF_UP &&
- (sock_writeable(sk) ||
- (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
- sock_writeable(sk))))
+ /* Make sure SOCKWQ_ASYNC_NOSPACE is set if not writable to
+ * guarantee EPOLLOUT to be raised by either here or
+ * tun_sock_write_space(). Then process could get notification
+ * after it writes to a down device and meets -EIO.
+ */
+ if (tun_sock_writeable(tun, tfile) ||
+ (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
+ tun_sock_writeable(tun, tfile)))
mask |= POLLOUT | POLLWRNORM;
if (tun->dev->reg_state != NETREG_REGISTERED)
skb_reserve(skb, pad - delta);
skb_put(skb, len + delta);
+ skb_set_owner_w(skb, tfile->socket.sk);
get_page(alloc_frag->page);
alloc_frag->offset += buflen;
if (ret != XDP_PASS) {
rcu_read_unlock();
local_bh_enable();
+ if (frags) {
+ tfile->napi.skb = NULL;
+ mutex_unlock(&tfile->napi_mutex);
+ }
return total_len;
}
}
rcu_read_lock();
if (unlikely(!(tun->dev->flags & IFF_UP))) {
err = -EIO;
+ rcu_read_unlock();
goto drop;
}
err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER,
ifr->ifr_flags & IFF_NAPI,
- ifr->ifr_flags & IFF_NAPI_FRAGS);
+ ifr->ifr_flags & IFF_NAPI_FRAGS, true);
if (err < 0)
return err;
INIT_LIST_HEAD(&tun->disabled);
err = tun_attach(tun, file, false, ifr->ifr_flags & IFF_NAPI,
- ifr->ifr_flags & IFF_NAPI_FRAGS);
+ ifr->ifr_flags & IFF_NAPI_FRAGS, false);
if (err < 0)
goto err_free_flow;
err = register_netdevice(tun->dev);
if (err < 0)
goto err_detach;
+ /* free_netdev() won't check refcnt, to aovid race
+ * with dev_put() we need publish tun after registration.
+ */
+ rcu_assign_pointer(tfile->tun, tun);
}
netif_carrier_on(tun->dev);
if (ret < 0)
goto unlock;
ret = tun_attach(tun, file, false, tun->flags & IFF_NAPI,
- tun->flags & IFF_NAPI_FRAGS);
+ tun->flags & IFF_NAPI_FRAGS, true);
} else if (ifr->ifr_flags & IFF_DETACH_QUEUE) {
tun = rtnl_dereference(tfile->tun);
if (!tun || !(tun->flags & IFF_MULTI_QUEUE) || tfile->detached)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct tun_struct *tun = netdev_priv(dev);
+ int i;
if (dev->rtnl_link_ops != &tun_link_ops)
return NOTIFY_DONE;
if (tun_queue_resize(tun))
return NOTIFY_BAD;
break;
+ case NETDEV_UP:
+ for (i = 0; i < tun->numqueues; i++) {
+ struct tun_file *tfile;
+
+ tfile = rtnl_dereference(tun->tfiles[i]);
+ tfile->socket.sk->sk_write_space(tfile->socket.sk);
+ }
+ break;
default:
break;
}