*/
#define MAX_TAP_QUEUES 1024
+#define TUN_FLOW_EXPIRE (3 * HZ)
+
/* A tun_file connects an open character device to a tuntap netdevice. It
* also contains all socket related strctures (except sock_fprog and tap_filter)
* to serve as one transmit queue for tuntap device. The sock_fprog and
* tap_filter were kept in tun_struct since they were used for filtering for the
- * netdevice not for a specific queue (at least I didn't see the reqirement for
+ * netdevice not for a specific queue (at least I didn't see the requirement for
* this).
*
* RCU usage:
- * The tun_file and tun_struct are loosely coupled, the pointer from on to the
+ * The tun_file and tun_struct are loosely coupled, the pointer from one to the
* other can only be read while rcu_read_lock or rtnl_lock is held.
*/
struct tun_file {
u16 queue_index;
};
+struct tun_flow_entry {
+ struct hlist_node hash_link;
+ struct rcu_head rcu;
+ struct tun_struct *tun;
+
+ u32 rxhash;
+ int queue_index;
+ unsigned long updated;
+};
+
+#define TUN_NUM_FLOW_ENTRIES 1024
+
/* Since the socket were moved to tun_file, to preserve the behavior of persist
- * device, socket fileter, sndbuf and vnet header size were restore when the
+ * device, socket filter, sndbuf and vnet header size were restore when the
* file were attached to a persist device.
*/
struct tun_struct {
#ifdef TUN_DEBUG
int debug;
#endif
+ spinlock_t lock;
+ struct kmem_cache *flow_cache;
+ struct hlist_head flows[TUN_NUM_FLOW_ENTRIES];
+ struct timer_list flow_gc_timer;
+ unsigned long ageing_time;
};
+static inline u32 tun_hashfn(u32 rxhash)
+{
+ return rxhash & 0x3ff;
+}
+
+static struct tun_flow_entry *tun_flow_find(struct hlist_head *head, u32 rxhash)
+{
+ struct tun_flow_entry *e;
+ struct hlist_node *n;
+
+ hlist_for_each_entry_rcu(e, n, head, hash_link) {
+ if (e->rxhash == rxhash)
+ return e;
+ }
+ return NULL;
+}
+
+static struct tun_flow_entry *tun_flow_create(struct tun_struct *tun,
+ struct hlist_head *head,
+ u32 rxhash, u16 queue_index)
+{
+ struct tun_flow_entry *e = kmem_cache_alloc(tun->flow_cache,
+ GFP_ATOMIC);
+ if (e) {
+ tun_debug(KERN_INFO, tun, "create flow: hash %u index %u\n",
+ rxhash, queue_index);
+ e->updated = jiffies;
+ e->rxhash = rxhash;
+ e->queue_index = queue_index;
+ e->tun = tun;
+ hlist_add_head_rcu(&e->hash_link, head);
+ }
+ return e;
+}
+
+static void tun_flow_free(struct rcu_head *head)
+{
+ struct tun_flow_entry *e
+ = container_of(head, struct tun_flow_entry, rcu);
+ kmem_cache_free(e->tun->flow_cache, e);
+}
+
+static void tun_flow_delete(struct tun_struct *tun, struct tun_flow_entry *e)
+{
+ tun_debug(KERN_INFO, tun, "delete flow: hash %u index %u\n",
+ e->rxhash, e->queue_index);
+ hlist_del_rcu(&e->hash_link);
+ call_rcu(&e->rcu, tun_flow_free);
+}
+
+static void tun_flow_flush(struct tun_struct *tun)
+{
+ int i;
+
+ spin_lock_bh(&tun->lock);
+ for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) {
+ struct tun_flow_entry *e;
+ struct hlist_node *h, *n;
+
+ hlist_for_each_entry_safe(e, h, n, &tun->flows[i], hash_link)
+ tun_flow_delete(tun, e);
+ }
+ spin_unlock_bh(&tun->lock);
+}
+
+static void tun_flow_delete_by_queue(struct tun_struct *tun, u16 queue_index)
+{
+ int i;
+
+ spin_lock_bh(&tun->lock);
+ for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) {
+ struct tun_flow_entry *e;
+ struct hlist_node *h, *n;
+
+ hlist_for_each_entry_safe(e, h, n, &tun->flows[i], hash_link) {
+ if (e->queue_index == queue_index)
+ tun_flow_delete(tun, e);
+ }
+ }
+ spin_unlock_bh(&tun->lock);
+}
+
+static void tun_flow_cleanup(unsigned long data)
+{
+ struct tun_struct *tun = (struct tun_struct *)data;
+ unsigned long delay = tun->ageing_time;
+ unsigned long next_timer = jiffies + delay;
+ unsigned long count = 0;
+ int i;
+
+ tun_debug(KERN_INFO, tun, "tun_flow_cleanup\n");
+
+ spin_lock_bh(&tun->lock);
+ for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) {
+ struct tun_flow_entry *e;
+ struct hlist_node *h, *n;
+
+ hlist_for_each_entry_safe(e, h, n, &tun->flows[i], hash_link) {
+ unsigned long this_timer;
+ count++;
+ this_timer = e->updated + delay;
+ if (time_before_eq(this_timer, jiffies))
+ tun_flow_delete(tun, e);
+ else if (time_before(this_timer, next_timer))
+ next_timer = this_timer;
+ }
+ }
+
+ if (count)
+ mod_timer(&tun->flow_gc_timer, round_jiffies_up(next_timer));
+ spin_unlock_bh(&tun->lock);
+}
+
+static void tun_flow_update(struct tun_struct *tun, struct sk_buff *skb,
+ u16 queue_index)
+{
+ struct hlist_head *head;
+ struct tun_flow_entry *e;
+ unsigned long delay = tun->ageing_time;
+ u32 rxhash = skb_get_rxhash(skb);
+
+ if (!rxhash)
+ return;
+ else
+ head = &tun->flows[tun_hashfn(rxhash)];
+
+ rcu_read_lock();
+
+ if (tun->numqueues == 1)
+ goto unlock;
+
+ e = tun_flow_find(head, rxhash);
+ if (likely(e)) {
+ /* TODO: keep queueing to old queue until it's empty? */
+ e->queue_index = queue_index;
+ e->updated = jiffies;
+ } else {
+ spin_lock_bh(&tun->lock);
+ if (!tun_flow_find(head, rxhash))
+ tun_flow_create(tun, head, rxhash, queue_index);
+
+ if (!timer_pending(&tun->flow_gc_timer))
+ mod_timer(&tun->flow_gc_timer,
+ round_jiffies_up(jiffies + delay));
+ spin_unlock_bh(&tun->lock);
+ }
+
+unlock:
+ rcu_read_unlock();
+}
+
/* We try to identify a flow through its rxhash first. The reason that
* we do not check rxq no. is becuase some cards(e.g 82599), chooses
* the rxq based on the txq where the last packet of the flow comes. As
static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb)
{
struct tun_struct *tun = netdev_priv(dev);
+ struct tun_flow_entry *e;
u32 txq = 0;
u32 numqueues = 0;
txq = skb_get_rxhash(skb);
if (txq) {
- /* use multiply and shift instead of expensive divide */
- txq = ((u64)txq * numqueues) >> 32;
+ e = tun_flow_find(&tun->flows[tun_hashfn(txq)], txq);
+ if (e)
+ txq = e->queue_index;
+ else
+ /* use multiply and shift instead of expensive divide */
+ txq = ((u64)txq * numqueues) >> 32;
} else if (likely(skb_rx_queue_recorded(skb))) {
txq = skb_get_rx_queue(skb);
while (unlikely(txq >= numqueues))
static inline bool tun_not_capable(struct tun_struct *tun)
{
const struct cred *cred = current_cred();
+ struct net *net = dev_net(tun->dev);
return ((uid_valid(tun->owner) && !uid_eq(cred->euid, tun->owner)) ||
(gid_valid(tun->group) && !in_egroup_p(tun->group))) &&
- !capable(CAP_NET_ADMIN);
+ !ns_capable(net->user_ns, CAP_NET_ADMIN);
}
static void tun_set_real_num_queues(struct tun_struct *tun)
sock_put(&tfile->sk);
synchronize_net();
+ tun_flow_delete_by_queue(tun, tun->numqueues + 1);
/* Drop read queue */
skb_queue_purge(&tfile->sk.sk_receive_queue);
tun_set_real_num_queues(tun);
tun_set_real_num_queues(tun);
- if (tun->numqueues == 1)
- netif_carrier_on(tun->dev);
-
/* device is allowed to go away first, so no need to hold extra
* refcnt.
*/
sk_filter(tfile->socket.sk, skb))
goto drop;
- /* Limit the number of packets queued by divining txq length with the
+ /* Limit the number of packets queued by dividing txq length with the
* number of queues.
*/
if (skb_queue_len(&tfile->socket.sk->sk_receive_queue)
- >= dev->tx_queue_len / tun->numqueues){
- if (!(tun->flags & TUN_ONE_QUEUE)) {
- /* Normal queueing mode. */
- /* Packet scheduler handles dropping of further packets. */
- netif_stop_subqueue(dev, txq);
-
- /* We won't see all dropped packets individually, so overrun
- * error is more appropriate. */
- dev->stats.tx_fifo_errors++;
- } else {
- /* Single queue mode.
- * Driver handles dropping of all packets itself. */
- goto drop;
- }
- }
+ >= dev->tx_queue_len / tun->numqueues)
+ goto drop;
/* Orphan the skb - required as we might hang on to it
* for indefinite time. */
drop:
dev->stats.tx_dropped++;
+ skb_tx_error(skb);
kfree_skb(skb);
rcu_read_unlock();
return NETDEV_TX_OK;
#endif
};
+static int tun_flow_init(struct tun_struct *tun)
+{
+ int i;
+
+ tun->flow_cache = kmem_cache_create("tun_flow_cache",
+ sizeof(struct tun_flow_entry), 0, 0,
+ NULL);
+ if (!tun->flow_cache)
+ return -ENOMEM;
+
+ for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++)
+ INIT_HLIST_HEAD(&tun->flows[i]);
+
+ tun->ageing_time = TUN_FLOW_EXPIRE;
+ setup_timer(&tun->flow_gc_timer, tun_flow_cleanup, (unsigned long)tun);
+ mod_timer(&tun->flow_gc_timer,
+ round_jiffies_up(jiffies + tun->ageing_time));
+
+ return 0;
+}
+
+static void tun_flow_uninit(struct tun_struct *tun)
+{
+ del_timer_sync(&tun->flow_gc_timer);
+ tun_flow_flush(tun);
+
+ /* Wait for completion of call_rcu()'s */
+ rcu_barrier();
+ kmem_cache_destroy(tun->flow_cache);
+}
+
/* Initialize net device. */
static void tun_net_init(struct net_device *dev)
{
tun->dev->stats.rx_packets++;
tun->dev->stats.rx_bytes += len;
+ tun_flow_update(tun, skb, tfile->queue_index);
return total_len;
}
struct sk_buff *skb;
ssize_t ret = 0;
- tun_debug(KERN_INFO, tun, "tun_chr_read\n");
+ tun_debug(KERN_INFO, tun, "tun_do_read\n");
if (unlikely(!noblock))
add_wait_queue(&tfile->wq.wait, &wait);
schedule();
continue;
}
- netif_wake_subqueue(tun->dev, tfile->queue_index);
ret = tun_put_user(tun, tfile, skb, iv, len);
kfree_skb(skb);
return ret;
}
+static void tun_free_netdev(struct net_device *dev)
+{
+ struct tun_struct *tun = netdev_priv(dev);
+
+ tun_flow_uninit(tun);
+ free_netdev(dev);
+}
+
static void tun_setup(struct net_device *dev)
{
struct tun_struct *tun = netdev_priv(dev);
tun->group = INVALID_GID;
dev->ethtool_ops = &tun_ethtool_ops;
- dev->destructor = free_netdev;
+ dev->destructor = tun_free_netdev;
}
/* Trivial set of netlink ops to allow deleting tun or tap
if (tun->flags & TUN_NO_PI)
flags |= IFF_NO_PI;
+ /* This flag has no real effect. We track the value for backwards
+ * compatibility.
+ */
if (tun->flags & TUN_ONE_QUEUE)
flags |= IFF_ONE_QUEUE;
char *name;
unsigned long flags = 0;
- if (!capable(CAP_NET_ADMIN))
+ if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
err = security_tun_dev_create();
if (err < 0)
tun->filter_attached = false;
tun->sndbuf = tfile->socket.sk->sk_sndbuf;
+ spin_lock_init(&tun->lock);
+
security_tun_dev_post_create(&tfile->sk);
tun_net_init(dev);
+ if (tun_flow_init(tun))
+ goto err_free_dev;
+
dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST |
TUN_USER_FEATURES;
dev->features = dev->hw_features;
+ err = tun_attach(tun, file);
+ if (err < 0)
+ goto err_free_dev;
+
err = register_netdevice(tun->dev);
if (err < 0)
goto err_free_dev;
device_create_file(&tun->dev->dev, &dev_attr_group))
pr_err("Failed to create tun sysfs files\n");
- err = tun_attach(tun, file);
- if (err < 0)
- goto err_free_dev;
+ netif_carrier_on(tun->dev);
}
tun_debug(KERN_INFO, tun, "tun_set_iff\n");
else
tun->flags &= ~TUN_NO_PI;
+ /* This flag has no real effect. We track the value for backwards
+ * compatibility.
+ */
if (ifr->ifr_flags & IFF_ONE_QUEUE)
tun->flags |= TUN_ONE_QUEUE;
else
return err;
}
-static int tun_get_iff(struct net *net, struct tun_struct *tun,
+static void tun_get_iff(struct net *net, struct tun_struct *tun,
struct ifreq *ifr)
{
tun_debug(KERN_INFO, tun, "tun_get_iff\n");
ifr->ifr_flags = tun_flags(tun);
- return 0;
}
/* This is like a cut-down ethtool ops, except done via tun fd so no
ret = 0;
switch (cmd) {
case TUNGETIFF:
- ret = tun_get_iff(current->nsproxy->net_ns, tun, &ifr);
- if (ret)
- break;
+ tun_get_iff(current->nsproxy->net_ns, tun, &ifr);
if (copy_to_user(argp, &ifr, ifreq_len))
ret = -EFAULT;