aboutsummaryrefslogtreecommitdiff
path: root/drivers/net/tun.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/tun.c')
-rw-r--r--drivers/net/tun.c192
1 files changed, 122 insertions, 70 deletions
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 7cb105c103f..98bad1fb1bf 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -69,6 +69,7 @@
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
#include <net/sock.h>
+#include <linux/seq_file.h>
#include <asm/uaccess.h>
@@ -110,7 +111,7 @@ struct tap_filter {
unsigned char addr[FLT_EXACT_COUNT][ETH_ALEN];
};
-/* DEFAULT_MAX_NUM_RSS_QUEUES were choosed to let the rx/tx queues allocated for
+/* DEFAULT_MAX_NUM_RSS_QUEUES were chosen 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
@@ -119,7 +120,7 @@ struct tap_filter {
#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)
+ * also contains all socket related structures (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 requirement for
@@ -152,6 +153,7 @@ struct tun_flow_entry {
struct tun_struct *tun;
u32 rxhash;
+ u32 rps_rxhash;
int queue_index;
unsigned long updated;
};
@@ -220,6 +222,7 @@ static struct tun_flow_entry *tun_flow_create(struct tun_struct *tun,
rxhash, queue_index);
e->updated = jiffies;
e->rxhash = rxhash;
+ e->rps_rxhash = 0;
e->queue_index = queue_index;
e->tun = tun;
hlist_add_head_rcu(&e->hash_link, head);
@@ -232,6 +235,7 @@ 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);
+ sock_rps_reset_flow_hash(e->rps_rxhash);
hlist_del_rcu(&e->hash_link);
kfree_rcu(e, rcu);
--tun->flow_count;
@@ -325,6 +329,7 @@ static void tun_flow_update(struct tun_struct *tun, u32 rxhash,
/* TODO: keep queueing to old queue until it's empty? */
e->queue_index = queue_index;
e->updated = jiffies;
+ sock_rps_record_flow_hash(e->rps_rxhash);
} else {
spin_lock_bh(&tun->lock);
if (!tun_flow_find(head, rxhash) &&
@@ -341,14 +346,27 @@ unlock:
rcu_read_unlock();
}
+/**
+ * Save the hash received in the stack receive path and update the
+ * flow_hash table accordingly.
+ */
+static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash)
+{
+ if (unlikely(e->rps_rxhash != hash)) {
+ sock_rps_reset_flow_hash(e->rps_rxhash);
+ e->rps_rxhash = hash;
+ }
+}
+
/* 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
+ * we do not check rxq no. is because some cards(e.g 82599), chooses
* the rxq based on the txq where the last packet of the flow comes. As
* the userspace application move between processors, we may get a
* different rxq no. here. If we could not get rxhash, then we would
* hope the rxq no. may help here.
*/
-static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv, select_queue_fallback_t fallback)
{
struct tun_struct *tun = netdev_priv(dev);
struct tun_flow_entry *e;
@@ -358,12 +376,13 @@ static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb)
rcu_read_lock();
numqueues = ACCESS_ONCE(tun->numqueues);
- txq = skb_get_rxhash(skb);
+ txq = skb_get_hash(skb);
if (txq) {
e = tun_flow_find(&tun->flows[tun_hashfn(txq)], txq);
- if (e)
+ if (e) {
+ tun_flow_save_rps_rxhash(e, txq);
txq = e->queue_index;
- else
+ } else
/* use multiply and shift instead of expensive divide */
txq = ((u64)txq * numqueues) >> 32;
} else if (likely(skb_rx_queue_recorded(skb))) {
@@ -433,7 +452,7 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
--tun->numqueues;
if (clean) {
- rcu_assign_pointer(tfile->tun, NULL);
+ RCU_INIT_POINTER(tfile->tun, NULL);
sock_put(&tfile->sk);
} else
tun_disable_queue(tun, tfile);
@@ -479,13 +498,13 @@ static void tun_detach_all(struct net_device *dev)
for (i = 0; i < n; i++) {
tfile = rtnl_dereference(tun->tfiles[i]);
BUG_ON(!tfile);
- wake_up_all(&tfile->wq.wait);
- rcu_assign_pointer(tfile->tun, NULL);
+ tfile->socket.sk->sk_data_ready(tfile->socket.sk);
+ RCU_INIT_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);
+ tfile->socket.sk->sk_data_ready(tfile->socket.sk);
+ RCU_INIT_POINTER(tfile->tun, NULL);
}
BUG_ON(tun->numqueues != 0);
@@ -531,7 +550,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte
err = 0;
- /* Re-attach the filter to presist device */
+ /* Re-attach the filter to persist device */
if (!skip_filter && (tun->filter_attached == true)) {
err = sk_attach_filter(&tun->fprog, tfile->socket.sk);
if (!err)
@@ -720,14 +739,32 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
struct tun_struct *tun = netdev_priv(dev);
int txq = skb->queue_mapping;
struct tun_file *tfile;
+ u32 numqueues = 0;
rcu_read_lock();
tfile = rcu_dereference(tun->tfiles[txq]);
+ numqueues = ACCESS_ONCE(tun->numqueues);
/* Drop packet if interface is not attached */
- if (txq >= tun->numqueues)
+ if (txq >= numqueues)
goto drop;
+ if (numqueues == 1) {
+ /* Select queue was not called for the skbuff, so we extract the
+ * RPS hash and save it into the flow_table here.
+ */
+ __u32 rxhash;
+
+ rxhash = skb_get_hash(skb);
+ if (rxhash) {
+ struct tun_flow_entry *e;
+ e = tun_flow_find(&tun->flows[tun_hashfn(rxhash)],
+ rxhash);
+ if (e)
+ tun_flow_save_rps_rxhash(e, rxhash);
+ }
+ }
+
tun_debug(KERN_INFO, tun, "tun_net_xmit %d\n", skb->len);
BUG_ON(!tfile);
@@ -745,8 +782,8 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
/* 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 (skb_queue_len(&tfile->socket.sk->sk_receive_queue) * numqueues
+ >= dev->tx_queue_len)
goto drop;
if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC)))
@@ -770,8 +807,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
/* Notify and wake up reader process */
if (tfile->flags & TUN_FASYNC)
kill_fasync(&tfile->fasync, SIGIO, POLL_IN);
- wake_up_interruptible_poll(&tfile->wq.wait, POLLIN |
- POLLRDNORM | POLLRDBAND);
+ tfile->socket.sk->sk_data_ready(tfile->socket.sk);
rcu_read_unlock();
return NETDEV_TX_OK;
@@ -819,9 +855,9 @@ static void tun_poll_controller(struct net_device *dev)
* Tun only receives frames when:
* 1) the char device endpoint gets data from user space
* 2) the tun socket gets a sendmsg call from user space
- * Since both of those are syncronous operations, we are guaranteed
+ * Since both of those are synchronous operations, we are guaranteed
* never to have pending data when we poll for it
- * so theres nothing to do here but return.
+ * so there is nothing to do here but return.
* We need this though so netpoll recognizes us as an interface that
* supports polling, which enables bridge devices in virt setups to
* still use netconsole
@@ -928,7 +964,7 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
tun_debug(KERN_INFO, tun, "tun_chr_poll\n");
- poll_wait(file, &tfile->wq.wait, wait);
+ poll_wait(file, sk_sleep(sk), wait);
if (!skb_queue_empty(&sk->sk_receive_queue))
mask |= POLLIN | POLLRDNORM;
@@ -981,6 +1017,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
struct sk_buff *skb;
size_t len = total_len, align = NET_SKB_PAD, linear;
struct virtio_net_hdr gso = { 0 };
+ int good_linear;
int offset = 0;
int copylen;
bool zerocopy = false;
@@ -1021,12 +1058,16 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
return -EINVAL;
}
+ good_linear = SKB_MAX_HEAD(align);
+
if (msg_control) {
/* There are 256 bytes to be copied in skb, so there is
* enough room for skb expand head in case it is used.
* The rest of the buffer is mapped from userspace.
*/
copylen = gso.hdr_len ? gso.hdr_len : GOODCOPY_LEN;
+ if (copylen > good_linear)
+ copylen = good_linear;
linear = copylen;
if (iov_pages(iv, offset + copylen, count) <= MAX_SKB_FRAGS)
zerocopy = true;
@@ -1034,7 +1075,10 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
if (!zerocopy) {
copylen = len;
- linear = gso.hdr_len;
+ if (gso.hdr_len > good_linear)
+ linear = good_linear;
+ else
+ linear = gso.hdr_len;
}
skb = tun_alloc_skb(tfile, align, copylen, linear, noblock);
@@ -1138,7 +1182,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
skb_reset_network_header(skb);
skb_probe_transport_header(skb, 0);
- rxhash = skb_get_rxhash(skb);
+ rxhash = skb_get_hash(skb);
netif_rx_ni(skb);
tun->dev->stats.rx_packets++;
@@ -1176,7 +1220,7 @@ static ssize_t tun_put_user(struct tun_struct *tun,
{
struct tun_pi pi = { 0, skb->protocol };
ssize_t total = 0;
- int vlan_offset = 0;
+ int vlan_offset = 0, copied;
if (!(tun->flags & TUN_NO_PI)) {
if ((len -= sizeof(pi)) < 0)
@@ -1240,6 +1284,8 @@ static ssize_t tun_put_user(struct tun_struct *tun,
total += tun->vnet_hdr_sz;
}
+ copied = total;
+ total += skb->len;
if (!vlan_tx_tag_present(skb)) {
len = min_t(int, skb->len, len);
} else {
@@ -1254,24 +1300,24 @@ static ssize_t tun_put_user(struct tun_struct *tun,
vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto);
len = min_t(int, skb->len + VLAN_HLEN, len);
+ total += VLAN_HLEN;
copy = min_t(int, vlan_offset, len);
- ret = skb_copy_datagram_const_iovec(skb, 0, iv, total, copy);
+ ret = skb_copy_datagram_const_iovec(skb, 0, iv, copied, copy);
len -= copy;
- total += copy;
+ copied += copy;
if (ret || !len)
goto done;
copy = min_t(int, sizeof(veth), len);
- ret = memcpy_toiovecend(iv, (void *)&veth, total, copy);
+ ret = memcpy_toiovecend(iv, (void *)&veth, copied, copy);
len -= copy;
- total += copy;
+ copied += copy;
if (ret || !len)
goto done;
}
- skb_copy_datagram_const_iovec(skb, vlan_offset, iv, total, len);
- total += len;
+ skb_copy_datagram_const_iovec(skb, vlan_offset, iv, copied, len);
done:
tun->dev->stats.tx_packets++;
@@ -1281,50 +1327,28 @@ done:
}
static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
- struct kiocb *iocb, const struct iovec *iv,
- ssize_t len, int noblock)
+ const struct iovec *iv, ssize_t len, int noblock)
{
- DECLARE_WAITQUEUE(wait, current);
struct sk_buff *skb;
ssize_t ret = 0;
+ int peeked, err, off = 0;
tun_debug(KERN_INFO, tun, "tun_do_read\n");
- if (unlikely(!noblock))
- add_wait_queue(&tfile->wq.wait, &wait);
- while (len) {
- if (unlikely(!noblock))
- current->state = TASK_INTERRUPTIBLE;
+ if (!len)
+ return ret;
- /* Read frames from the queue */
- if (!(skb = skb_dequeue(&tfile->socket.sk->sk_receive_queue))) {
- if (noblock) {
- ret = -EAGAIN;
- break;
- }
- if (signal_pending(current)) {
- ret = -ERESTARTSYS;
- break;
- }
- if (tun->dev->reg_state != NETREG_REGISTERED) {
- ret = -EIO;
- break;
- }
-
- /* Nothing to read, let's sleep */
- schedule();
- continue;
- }
+ if (tun->dev->reg_state != NETREG_REGISTERED)
+ return -EIO;
+ /* Read frames from queue */
+ skb = __skb_recv_datagram(tfile->socket.sk, noblock ? MSG_DONTWAIT : 0,
+ &peeked, &off, &err);
+ if (skb) {
ret = tun_put_user(tun, tfile, skb, iv, len);
kfree_skb(skb);
- break;
- }
-
- if (unlikely(!noblock)) {
- current->state = TASK_RUNNING;
- remove_wait_queue(&tfile->wq.wait, &wait);
- }
+ } else
+ ret = err;
return ret;
}
@@ -1345,9 +1369,11 @@ static ssize_t tun_chr_aio_read(struct kiocb *iocb, const struct iovec *iv,
goto out;
}
- ret = tun_do_read(tun, tfile, iocb, iv, len,
+ ret = tun_do_read(tun, tfile, iv, len,
file->f_flags & O_NONBLOCK);
ret = min_t(ssize_t, ret, len);
+ if (ret > 0)
+ iocb->ki_pos = ret;
out:
tun_put(tun);
return ret;
@@ -1444,7 +1470,7 @@ static int tun_recvmsg(struct kiocb *iocb, struct socket *sock,
SOL_PACKET, TUN_TX_TIMESTAMP);
goto out;
}
- ret = tun_do_read(tun, tfile, iocb, m->msg_iov, total_len,
+ ret = tun_do_read(tun, tfile, m->msg_iov, total_len,
flags & MSG_DONTWAIT);
if (ret > total_len) {
m->msg_flags |= MSG_TRUNC;
@@ -1638,7 +1664,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX;
dev->features = dev->hw_features;
- dev->vlan_features = dev->features;
+ dev->vlan_features = dev->features &
+ ~(NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_STAG_TX);
INIT_LIST_HEAD(&tun->disabled);
err = tun_attach(tun, file, false);
@@ -2144,13 +2172,13 @@ static int tun_chr_open(struct inode *inode, struct file * file)
&tun_proto);
if (!tfile)
return -ENOMEM;
- rcu_assign_pointer(tfile->tun, NULL);
+ RCU_INIT_POINTER(tfile->tun, NULL);
tfile->net = get_net(current->nsproxy->net_ns);
tfile->flags = 0;
tfile->ifindex = 0;
- rcu_assign_pointer(tfile->socket.wq, &tfile->wq);
init_waitqueue_head(&tfile->wq.wait);
+ RCU_INIT_POINTER(tfile->socket.wq, &tfile->wq);
tfile->socket.file = file;
tfile->socket.ops = &tun_socket_ops;
@@ -2181,6 +2209,27 @@ static int tun_chr_close(struct inode *inode, struct file *file)
return 0;
}
+#ifdef CONFIG_PROC_FS
+static int tun_chr_show_fdinfo(struct seq_file *m, struct file *f)
+{
+ struct tun_struct *tun;
+ struct ifreq ifr;
+
+ memset(&ifr, 0, sizeof(ifr));
+
+ rtnl_lock();
+ tun = tun_get(f);
+ if (tun)
+ tun_get_iff(current->nsproxy->net_ns, tun, &ifr);
+ rtnl_unlock();
+
+ if (tun)
+ tun_put(tun);
+
+ return seq_printf(m, "iff:\t%s\n", ifr.ifr_name);
+}
+#endif
+
static const struct file_operations tun_fops = {
.owner = THIS_MODULE,
.llseek = no_llseek,
@@ -2195,7 +2244,10 @@ static const struct file_operations tun_fops = {
#endif
.open = tun_chr_open,
.release = tun_chr_close,
- .fasync = tun_chr_fasync
+ .fasync = tun_chr_fasync,
+#ifdef CONFIG_PROC_FS
+ .show_fdinfo = tun_chr_show_fdinfo,
+#endif
};
static struct miscdevice tun_miscdev = {
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-04 12:54:18 +0000