summaryrefslogtreecommitdiffstats
path: root/drivers/net/tun.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/tun.c')
-rw-r--r--drivers/net/tun.c84
1 files changed, 57 insertions, 27 deletions
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index af372d0957f..b6f45c5d84d 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -109,11 +109,11 @@ struct tap_filter {
unsigned char addr[FLT_EXACT_COUNT][ETH_ALEN];
};
-/* 1024 is probably a high enough limit: modern hypervisors seem to support on
- * the order of 100-200 CPUs so this leaves us some breathing space if we want
- * to match a queue per guest CPU.
- */
-#define MAX_TAP_QUEUES 1024
+/* DEFAULT_MAX_NUM_RSS_QUEUES were choosed to let the rx/tx queues allocated for
+ * the netdevice to be fit in one page. So we can make sure the success of
+ * memory allocation. TODO: increase the limit. */
+#define MAX_TAP_QUEUES DEFAULT_MAX_NUM_RSS_QUEUES
+#define MAX_TAP_FLOWS 4096
#define TUN_FLOW_EXPIRE (3 * HZ)
@@ -185,6 +185,8 @@ struct tun_struct {
unsigned long ageing_time;
unsigned int numdisabled;
struct list_head disabled;
+ void *security;
+ u32 flow_count;
};
static inline u32 tun_hashfn(u32 rxhash)
@@ -218,6 +220,7 @@ static struct tun_flow_entry *tun_flow_create(struct tun_struct *tun,
e->queue_index = queue_index;
e->tun = tun;
hlist_add_head_rcu(&e->hash_link, head);
+ ++tun->flow_count;
}
return e;
}
@@ -228,6 +231,7 @@ static void tun_flow_delete(struct tun_struct *tun, struct tun_flow_entry *e)
e->rxhash, e->queue_index);
hlist_del_rcu(&e->hash_link);
kfree_rcu(e, rcu);
+ --tun->flow_count;
}
static void tun_flow_flush(struct tun_struct *tun)
@@ -294,11 +298,12 @@ static void tun_flow_cleanup(unsigned long data)
}
static void tun_flow_update(struct tun_struct *tun, u32 rxhash,
- u16 queue_index)
+ struct tun_file *tfile)
{
struct hlist_head *head;
struct tun_flow_entry *e;
unsigned long delay = tun->ageing_time;
+ u16 queue_index = tfile->queue_index;
if (!rxhash)
return;
@@ -307,7 +312,9 @@ static void tun_flow_update(struct tun_struct *tun, u32 rxhash,
rcu_read_lock();
- if (tun->numqueues == 1)
+ /* We may get a very small possibility of OOO during switching, not
+ * worth to optimize.*/
+ if (tun->numqueues == 1 || tfile->detached)
goto unlock;
e = tun_flow_find(head, rxhash);
@@ -317,7 +324,8 @@ static void tun_flow_update(struct tun_struct *tun, u32 rxhash,
e->updated = jiffies;
} else {
spin_lock_bh(&tun->lock);
- if (!tun_flow_find(head, rxhash))
+ if (!tun_flow_find(head, rxhash) &&
+ tun->flow_count < MAX_TAP_FLOWS)
tun_flow_create(tun, head, rxhash, queue_index);
if (!timer_pending(&tun->flow_gc_timer))
@@ -406,21 +414,21 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
tun = rtnl_dereference(tfile->tun);
- if (tun) {
+ if (tun && !tfile->detached) {
u16 index = tfile->queue_index;
BUG_ON(index >= tun->numqueues);
dev = tun->dev;
rcu_assign_pointer(tun->tfiles[index],
tun->tfiles[tun->numqueues - 1]);
- rcu_assign_pointer(tfile->tun, NULL);
ntfile = rtnl_dereference(tun->tfiles[index]);
ntfile->queue_index = index;
--tun->numqueues;
- if (clean)
+ if (clean) {
+ rcu_assign_pointer(tfile->tun, NULL);
sock_put(&tfile->sk);
- else
+ } else
tun_disable_queue(tun, tfile);
synchronize_net();
@@ -434,10 +442,13 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
}
if (clean) {
- if (tun && tun->numqueues == 0 && tun->numdisabled == 0 &&
- !(tun->flags & TUN_PERSIST))
- if (tun->dev->reg_state == NETREG_REGISTERED)
+ if (tun && tun->numqueues == 0 && tun->numdisabled == 0) {
+ netif_carrier_off(tun->dev);
+
+ if (!(tun->flags & TUN_PERSIST) &&
+ tun->dev->reg_state == NETREG_REGISTERED)
unregister_netdevice(tun->dev);
+ }
BUG_ON(!test_bit(SOCK_EXTERNALLY_ALLOCATED,
&tfile->socket.flags));
@@ -465,6 +476,10 @@ static void tun_detach_all(struct net_device *dev)
rcu_assign_pointer(tfile->tun, NULL);
--tun->numqueues;
}
+ list_for_each_entry(tfile, &tun->disabled, next) {
+ wake_up_all(&tfile->wq.wait);
+ rcu_assign_pointer(tfile->tun, NULL);
+ }
BUG_ON(tun->numqueues != 0);
synchronize_net();
@@ -490,8 +505,12 @@ static int tun_attach(struct tun_struct *tun, struct file *file)
struct tun_file *tfile = file->private_data;
int err;
+ err = security_tun_dev_attach(tfile->socket.sk, tun->security);
+ if (err < 0)
+ goto out;
+
err = -EINVAL;
- if (rtnl_dereference(tfile->tun))
+ if (rtnl_dereference(tfile->tun) && !tfile->detached)
goto out;
err = -EBUSY;
@@ -1181,6 +1200,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
if (zerocopy) {
skb_shinfo(skb)->destructor_arg = msg_control;
skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
+ skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
}
skb_reset_network_header(skb);
@@ -1190,7 +1210,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
tun->dev->stats.rx_packets++;
tun->dev->stats.rx_bytes += len;
- tun_flow_update(tun, rxhash, tfile->queue_index);
+ tun_flow_update(tun, rxhash, tfile);
return total_len;
}
@@ -1373,6 +1393,7 @@ static void tun_free_netdev(struct net_device *dev)
BUG_ON(!(list_empty(&tun->disabled)));
tun_flow_uninit(tun);
+ security_tun_dev_free_security(tun->security);
free_netdev(dev);
}
@@ -1562,7 +1583,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
if (tun_not_capable(tun))
return -EPERM;
- err = security_tun_dev_attach(tfile->socket.sk);
+ err = security_tun_dev_open(tun->security);
if (err < 0)
return err;
@@ -1577,6 +1598,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
else {
char *name;
unsigned long flags = 0;
+ int queues = ifr->ifr_flags & IFF_MULTI_QUEUE ?
+ MAX_TAP_QUEUES : 1;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
@@ -1600,8 +1623,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
name = ifr->ifr_name;
dev = alloc_netdev_mqs(sizeof(struct tun_struct), name,
- tun_setup,
- MAX_TAP_QUEUES, MAX_TAP_QUEUES);
+ tun_setup, queues, queues);
+
if (!dev)
return -ENOMEM;
@@ -1619,7 +1642,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
spin_lock_init(&tun->lock);
- security_tun_dev_post_create(&tfile->sk);
+ err = security_tun_dev_alloc_security(&tun->security);
+ if (err < 0)
+ goto err_free_dev;
tun_net_init(dev);
@@ -1644,10 +1669,10 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
device_create_file(&tun->dev->dev, &dev_attr_owner) ||
device_create_file(&tun->dev->dev, &dev_attr_group))
pr_err("Failed to create tun sysfs files\n");
-
- netif_carrier_on(tun->dev);
}
+ netif_carrier_on(tun->dev);
+
tun_debug(KERN_INFO, tun, "tun_set_iff\n");
if (ifr->ifr_flags & IFF_NO_PI)
@@ -1789,19 +1814,24 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr)
if (ifr->ifr_flags & IFF_ATTACH_QUEUE) {
tun = tfile->detached;
- if (!tun)
+ if (!tun) {
ret = -EINVAL;
- else
- ret = tun_attach(tun, file);
+ goto unlock;
+ }
+ ret = security_tun_dev_attach_queue(tun->security);
+ if (ret < 0)
+ goto unlock;
+ ret = tun_attach(tun, file);
} else if (ifr->ifr_flags & IFF_DETACH_QUEUE) {
tun = rtnl_dereference(tfile->tun);
- if (!tun || !(tun->flags & TUN_TAP_MQ))
+ if (!tun || !(tun->flags & TUN_TAP_MQ) || tfile->detached)
ret = -EINVAL;
else
__tun_detach(tfile, false);
} else
ret = -EINVAL;
+unlock:
rtnl_unlock();
return ret;
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-11-24 04:29:42 +0000