tuntap: choose the txq based on rxq

[deliverable/linux.git] / drivers / net / tun.c

/*
 *  TUN - Universal TUN/TAP device driver.
 *  Copyright (C) 1999-2002 Maxim Krasnyansky <maxk@qualcomm.com>
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; either version 2 of the License, or
 *  (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
 *  GNU General Public License for more details.
 *
 *  $Id: tun.c,v 1.15 2002/03/01 02:44:24 maxk Exp $
 */

/*
 *  Changes:
 *
 *  Mike Kershaw <dragorn@kismetwireless.net> 2005/08/14
 *    Add TUNSETLINK ioctl to set the link encapsulation
 *
 *  Mark Smith <markzzzsmith@yahoo.com.au>
 *    Use eth_random_addr() for tap MAC address.
 *
 *  Harald Roelle <harald.roelle@ifi.lmu.de>  2004/04/20
 *    Fixes in packet dropping, queue length setting and queue wakeup.
 *    Increased default tx queue length.
 *    Added ethtool API.
 *    Minor cleanups
 *
 *  Daniel Podlejski <underley@underley.eu.org>
 *    Modifications for 2.3.99-pre5 kernel.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#define DRV_NAME        "tun"
#define DRV_VERSION     "1.6"
#define DRV_DESCRIPTION "Universal TUN/TAP device driver"
#define DRV_COPYRIGHT   "(C) 1999-2004 Max Krasnyansky <maxk@qualcomm.com>"

#include <linux/module.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/major.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/fcntl.h>
#include <linux/init.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/miscdevice.h>
#include <linux/ethtool.h>
#include <linux/rtnetlink.h>
#include <linux/compat.h>
#include <linux/if.h>
#include <linux/if_arp.h>
#include <linux/if_ether.h>
#include <linux/if_tun.h>
#include <linux/crc32.h>
#include <linux/nsproxy.h>
#include <linux/virtio_net.h>
#include <linux/rcupdate.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
#include <net/sock.h>

#include <asm/uaccess.h>

/* Uncomment to enable debugging */
/* #define TUN_DEBUG 1 */

#ifdef TUN_DEBUG
static int debug;

#define tun_debug(level, tun, fmt, args...)                     \
do {                                                            \
        if (tun->debug)                                         \
                netdev_printk(level, tun->dev, fmt, ##args);    \
} while (0)
#define DBG1(level, fmt, args...)                               \
do {                                                            \
        if (debug == 2)                                         \
                printk(level fmt, ##args);                      \
} while (0)
#else
#define tun_debug(level, tun, fmt, args...)                     \
do {                                                            \
        if (0)                                                  \
                netdev_printk(level, tun->dev, fmt, ##args);    \
} while (0)
#define DBG1(level, fmt, args...)                               \
do {                                                            \
        if (0)                                                  \
                printk(level fmt, ##args);                      \
} while (0)
#endif

#define GOODCOPY_LEN 128

#define FLT_EXACT_COUNT 8
struct tap_filter {
        unsigned int    count;    /* Number of addrs. Zero means disabled */
        u32             mask[2];  /* Mask of the hashed addrs */
        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

#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
 * this).
 *
 * RCU usage:
 * The tun_file and tun_struct are loosely coupled, the pointer from on to the
 * other can only be read while rcu_read_lock or rtnl_lock is held.
 */
struct tun_file {
        struct sock sk;
        struct socket socket;
        struct socket_wq wq;
        struct tun_struct __rcu *tun;
        struct net *net;
        struct fasync_struct *fasync;
        /* only used for fasnyc */
        unsigned int flags;
        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
 * file were attached to a persist device.
 */
struct tun_struct {
        struct tun_file __rcu   *tfiles[MAX_TAP_QUEUES];
        unsigned int            numqueues;
        unsigned int            flags;
        kuid_t                  owner;
        kgid_t                  group;

        struct net_device       *dev;
        netdev_features_t       set_features;
#define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \
                          NETIF_F_TSO6|NETIF_F_UFO)

        int                     vnet_hdr_sz;
        int                     sndbuf;
        struct tap_filter       txflt;
        struct sock_fprog       fprog;
        /* protected by rtnl lock */
        bool                    filter_attached;
#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
 * 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)
{
        struct tun_struct *tun = netdev_priv(dev);
        struct tun_flow_entry *e;
        u32 txq = 0;
        u32 numqueues = 0;

        rcu_read_lock();
        numqueues = tun->numqueues;

        txq = skb_get_rxhash(skb);
        if (txq) {
                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))
                        txq -= numqueues;
        }

        rcu_read_unlock();
        return txq;
}

static inline bool tun_not_capable(struct tun_struct *tun)
{
        const struct cred *cred = current_cred();

        return ((uid_valid(tun->owner) && !uid_eq(cred->euid, tun->owner)) ||
                  (gid_valid(tun->group) && !in_egroup_p(tun->group))) &&
                !capable(CAP_NET_ADMIN);
}

static void tun_set_real_num_queues(struct tun_struct *tun)
{
        netif_set_real_num_tx_queues(tun->dev, tun->numqueues);
        netif_set_real_num_rx_queues(tun->dev, tun->numqueues);
}

static void __tun_detach(struct tun_file *tfile, bool clean)
{
        struct tun_file *ntfile;
        struct tun_struct *tun;
        struct net_device *dev;

        tun = rcu_dereference_protected(tfile->tun,
                                        lockdep_rtnl_is_held());
        if (tun) {
                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 = rcu_dereference_protected(tun->tfiles[index],
                                                   lockdep_rtnl_is_held());
                ntfile->queue_index = index;

                --tun->numqueues;
                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);

                if (tun->numqueues == 0 && !(tun->flags & TUN_PERSIST))
                        if (dev->reg_state == NETREG_REGISTERED)
                                unregister_netdevice(dev);
        }

        if (clean) {
                BUG_ON(!test_bit(SOCK_EXTERNALLY_ALLOCATED,
                                 &tfile->socket.flags));
                sk_release_kernel(&tfile->sk);
        }
}

static void tun_detach(struct tun_file *tfile, bool clean)
{
        rtnl_lock();
        __tun_detach(tfile, clean);
        rtnl_unlock();
}

static void tun_detach_all(struct net_device *dev)
{
        struct tun_struct *tun = netdev_priv(dev);
        struct tun_file *tfile;
        int i, n = tun->numqueues;

        for (i = 0; i < n; i++) {
                tfile = rcu_dereference_protected(tun->tfiles[i],
                                                  lockdep_rtnl_is_held());
                BUG_ON(!tfile);
                wake_up_all(&tfile->wq.wait);
                rcu_assign_pointer(tfile->tun, NULL);
                --tun->numqueues;
        }
        BUG_ON(tun->numqueues != 0);

        synchronize_net();
        for (i = 0; i < n; i++) {
                tfile = rcu_dereference_protected(tun->tfiles[i],
                                                  lockdep_rtnl_is_held());
                /* Drop read queue */
                skb_queue_purge(&tfile->sk.sk_receive_queue);
                sock_put(&tfile->sk);
        }
}

static int tun_attach(struct tun_struct *tun, struct file *file)
{
        struct tun_file *tfile = file->private_data;
        int err;

        err = -EINVAL;
        if (rcu_dereference_protected(tfile->tun, lockdep_rtnl_is_held()))
                goto out;

        err = -EBUSY;
        if (!(tun->flags & TUN_TAP_MQ) && tun->numqueues == 1)
                goto out;

        err = -E2BIG;
        if (tun->numqueues == MAX_TAP_QUEUES)
                goto out;

        err = 0;

        /* Re-attach the filter to presist device */
        if (tun->filter_attached == true) {
                err = sk_attach_filter(&tun->fprog, tfile->socket.sk);
                if (!err)
                        goto out;
        }
        tfile->queue_index = tun->numqueues;
        rcu_assign_pointer(tfile->tun, tun);
        rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
        sock_hold(&tfile->sk);
        tun->numqueues++;

        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.
         */

out:
        return err;
}

static struct tun_struct *__tun_get(struct tun_file *tfile)
{
        struct tun_struct *tun;

        rcu_read_lock();
        tun = rcu_dereference(tfile->tun);
        if (tun)
                dev_hold(tun->dev);
        rcu_read_unlock();

        return tun;
}

static struct tun_struct *tun_get(struct file *file)
{
        return __tun_get(file->private_data);
}

static void tun_put(struct tun_struct *tun)
{
        dev_put(tun->dev);
}

/* TAP filtering */
static void addr_hash_set(u32 *mask, const u8 *addr)
{
        int n = ether_crc(ETH_ALEN, addr) >> 26;
        mask[n >> 5] |= (1 << (n & 31));
}

static unsigned int addr_hash_test(const u32 *mask, const u8 *addr)
{
        int n = ether_crc(ETH_ALEN, addr) >> 26;
        return mask[n >> 5] & (1 << (n & 31));
}

static int update_filter(struct tap_filter *filter, void __user *arg)
{
        struct { u8 u[ETH_ALEN]; } *addr;
        struct tun_filter uf;
        int err, alen, n, nexact;

        if (copy_from_user(&uf, arg, sizeof(uf)))
                return -EFAULT;

        if (!uf.count) {
                /* Disabled */
                filter->count = 0;
                return 0;
        }

        alen = ETH_ALEN * uf.count;
        addr = kmalloc(alen, GFP_KERNEL);
        if (!addr)
                return -ENOMEM;

        if (copy_from_user(addr, arg + sizeof(uf), alen)) {
                err = -EFAULT;
                goto done;
        }

        /* The filter is updated without holding any locks. Which is
         * perfectly safe. We disable it first and in the worst
         * case we'll accept a few undesired packets. */
        filter->count = 0;
        wmb();

        /* Use first set of addresses as an exact filter */
        for (n = 0; n < uf.count && n < FLT_EXACT_COUNT; n++)
                memcpy(filter->addr[n], addr[n].u, ETH_ALEN);

        nexact = n;

        /* Remaining multicast addresses are hashed,
         * unicast will leave the filter disabled. */
        memset(filter->mask, 0, sizeof(filter->mask));
        for (; n < uf.count; n++) {
                if (!is_multicast_ether_addr(addr[n].u)) {
                        err = 0; /* no filter */
                        goto done;
                }
                addr_hash_set(filter->mask, addr[n].u);
        }

        /* For ALLMULTI just set the mask to all ones.
         * This overrides the mask populated above. */
        if ((uf.flags & TUN_FLT_ALLMULTI))
                memset(filter->mask, ~0, sizeof(filter->mask));

        /* Now enable the filter */
        wmb();
        filter->count = nexact;

        /* Return the number of exact filters */
        err = nexact;

done:
        kfree(addr);
        return err;
}

/* Returns: 0 - drop, !=0 - accept */
static int run_filter(struct tap_filter *filter, const struct sk_buff *skb)
{
        /* Cannot use eth_hdr(skb) here because skb_mac_hdr() is incorrect
         * at this point. */
        struct ethhdr *eh = (struct ethhdr *) skb->data;
        int i;

        /* Exact match */
        for (i = 0; i < filter->count; i++)
                if (ether_addr_equal(eh->h_dest, filter->addr[i]))
                        return 1;

        /* Inexact match (multicast only) */
        if (is_multicast_ether_addr(eh->h_dest))
                return addr_hash_test(filter->mask, eh->h_dest);

        return 0;
}

/*
 * Checks whether the packet is accepted or not.
 * Returns: 0 - drop, !=0 - accept
 */
static int check_filter(struct tap_filter *filter, const struct sk_buff *skb)
{
        if (!filter->count)
                return 1;

        return run_filter(filter, skb);
}

/* Network device part of the driver */

static const struct ethtool_ops tun_ethtool_ops;

/* Net device detach from fd. */
static void tun_net_uninit(struct net_device *dev)
{
        tun_detach_all(dev);
}

/* Net device open. */
static int tun_net_open(struct net_device *dev)
{
        netif_tx_start_all_queues(dev);
        return 0;
}

/* Net device close. */
static int tun_net_close(struct net_device *dev)
{
        netif_tx_stop_all_queues(dev);
        return 0;
}

/* Net device start xmit */
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;

        rcu_read_lock();
        tfile = rcu_dereference(tun->tfiles[txq]);

        /* Drop packet if interface is not attached */
        if (txq >= tun->numqueues)
                goto drop;

        tun_debug(KERN_INFO, tun, "tun_net_xmit %d\n", skb->len);

        BUG_ON(!tfile);

        /* Drop if the filter does not like it.
         * This is a noop if the filter is disabled.
         * Filter can be enabled only for the TAP devices. */
        if (!check_filter(&tun->txflt, skb))
                goto drop;

        if (tfile->socket.sk->sk_filter &&
            sk_filter(tfile->socket.sk, skb))
                goto drop;

        /* Limit the number of packets queued by divining 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;
                }
        }

        /* Orphan the skb - required as we might hang on to it
         * for indefinite time. */
        if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC)))
                goto drop;
        skb_orphan(skb);

        /* Enqueue packet */
        skb_queue_tail(&tfile->socket.sk->sk_receive_queue, skb);

        /* 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);

        rcu_read_unlock();
        return NETDEV_TX_OK;

drop:
        dev->stats.tx_dropped++;
        kfree_skb(skb);
        rcu_read_unlock();
        return NETDEV_TX_OK;
}

static void tun_net_mclist(struct net_device *dev)
{
        /*
         * This callback is supposed to deal with mc filter in
         * _rx_ path and has nothing to do with the _tx_ path.
         * In rx path we always accept everything userspace gives us.
         */
}

#define MIN_MTU 68
#define MAX_MTU 65535

static int
tun_net_change_mtu(struct net_device *dev, int new_mtu)
{
        if (new_mtu < MIN_MTU || new_mtu + dev->hard_header_len > MAX_MTU)
                return -EINVAL;
        dev->mtu = new_mtu;
        return 0;
}

static netdev_features_t tun_net_fix_features(struct net_device *dev,
        netdev_features_t features)
{
        struct tun_struct *tun = netdev_priv(dev);

        return (features & tun->set_features) | (features & ~TUN_USER_FEATURES);
}
#ifdef CONFIG_NET_POLL_CONTROLLER
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
         * never to have pending data when we poll for it
         * so theres 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
         */
        return;
}
#endif
static const struct net_device_ops tun_netdev_ops = {
        .ndo_uninit             = tun_net_uninit,
        .ndo_open               = tun_net_open,
        .ndo_stop               = tun_net_close,
        .ndo_start_xmit         = tun_net_xmit,
        .ndo_change_mtu         = tun_net_change_mtu,
        .ndo_fix_features       = tun_net_fix_features,
        .ndo_select_queue       = tun_select_queue,
#ifdef CONFIG_NET_POLL_CONTROLLER
        .ndo_poll_controller    = tun_poll_controller,
#endif
};

static const struct net_device_ops tap_netdev_ops = {
        .ndo_uninit             = tun_net_uninit,
        .ndo_open               = tun_net_open,
        .ndo_stop               = tun_net_close,
        .ndo_start_xmit         = tun_net_xmit,
        .ndo_change_mtu         = tun_net_change_mtu,
        .ndo_fix_features       = tun_net_fix_features,
        .ndo_set_rx_mode        = tun_net_mclist,
        .ndo_set_mac_address    = eth_mac_addr,
        .ndo_validate_addr      = eth_validate_addr,
        .ndo_select_queue       = tun_select_queue,
#ifdef CONFIG_NET_POLL_CONTROLLER
        .ndo_poll_controller    = tun_poll_controller,
#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)
{
        struct tun_struct *tun = netdev_priv(dev);

        switch (tun->flags & TUN_TYPE_MASK) {
        case TUN_TUN_DEV:
                dev->netdev_ops = &tun_netdev_ops;

                /* Point-to-Point TUN Device */
                dev->hard_header_len = 0;
                dev->addr_len = 0;
                dev->mtu = 1500;

                /* Zero header length */
                dev->type = ARPHRD_NONE;
                dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
                dev->tx_queue_len = TUN_READQ_SIZE;  /* We prefer our own queue length */
                break;

        case TUN_TAP_DEV:
                dev->netdev_ops = &tap_netdev_ops;
                /* Ethernet TAP Device */
                ether_setup(dev);
                dev->priv_flags &= ~IFF_TX_SKB_SHARING;

                eth_hw_addr_random(dev);

                dev->tx_queue_len = TUN_READQ_SIZE;  /* We prefer our own queue length */
                break;
        }
}

/* Character device part */

/* Poll */
static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
{
        struct tun_file *tfile = file->private_data;
        struct tun_struct *tun = __tun_get(tfile);
        struct sock *sk;
        unsigned int mask = 0;

        if (!tun)
                return POLLERR;

        sk = tfile->socket.sk;

        tun_debug(KERN_INFO, tun, "tun_chr_poll\n");

        poll_wait(file, &tfile->wq.wait, wait);

        if (!skb_queue_empty(&sk->sk_receive_queue))
                mask |= POLLIN | POLLRDNORM;

        if (sock_writeable(sk) ||
            (!test_and_set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
             sock_writeable(sk)))
                mask |= POLLOUT | POLLWRNORM;

        if (tun->dev->reg_state != NETREG_REGISTERED)
                mask = POLLERR;

        tun_put(tun);
        return mask;
}

/* prepad is the amount to reserve at front.  len is length after that.
 * linear is a hint as to how much to copy (usually headers). */
static struct sk_buff *tun_alloc_skb(struct tun_file *tfile,
                                     size_t prepad, size_t len,
                                     size_t linear, int noblock)
{
        struct sock *sk = tfile->socket.sk;
        struct sk_buff *skb;
        int err;

        /* Under a page?  Don't bother with paged skb. */
        if (prepad + len < PAGE_SIZE || !linear)
                linear = len;

        skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock,
                                   &err);
        if (!skb)
                return ERR_PTR(err);

        skb_reserve(skb, prepad);
        skb_put(skb, linear);
        skb->data_len = len - linear;
        skb->len += len - linear;

        return skb;
}

/* set skb frags from iovec, this can move to core network code for reuse */
static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from,
                                  int offset, size_t count)
{
        int len = iov_length(from, count) - offset;
        int copy = skb_headlen(skb);
        int size, offset1 = 0;
        int i = 0;

        /* Skip over from offset */
        while (count && (offset >= from->iov_len)) {
                offset -= from->iov_len;
                ++from;
                --count;
        }

        /* copy up to skb headlen */
        while (count && (copy > 0)) {
                size = min_t(unsigned int, copy, from->iov_len - offset);
                if (copy_from_user(skb->data + offset1, from->iov_base + offset,
                                   size))
                        return -EFAULT;
                if (copy > size) {
                        ++from;
                        --count;
                        offset = 0;
                } else
                        offset += size;
                copy -= size;
                offset1 += size;
        }

        if (len == offset1)
                return 0;

        while (count--) {
                struct page *page[MAX_SKB_FRAGS];
                int num_pages;
                unsigned long base;
                unsigned long truesize;

                len = from->iov_len - offset;
                if (!len) {
                        offset = 0;
                        ++from;
                        continue;
                }
                base = (unsigned long)from->iov_base + offset;
                size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
                if (i + size > MAX_SKB_FRAGS)
                        return -EMSGSIZE;
                num_pages = get_user_pages_fast(base, size, 0, &page[i]);
                if (num_pages != size) {
                        for (i = 0; i < num_pages; i++)
                                put_page(page[i]);
                        return -EFAULT;
                }
                truesize = size * PAGE_SIZE;
                skb->data_len += len;
                skb->len += len;
                skb->truesize += truesize;
                atomic_add(truesize, &skb->sk->sk_wmem_alloc);
                while (len) {
                        int off = base & ~PAGE_MASK;
                        int size = min_t(int, len, PAGE_SIZE - off);
                        __skb_fill_page_desc(skb, i, page[i], off, size);
                        skb_shinfo(skb)->nr_frags++;
                        /* increase sk_wmem_alloc */
                        base += size;
                        len -= size;
                        i++;
                }
                offset = 0;
                ++from;
        }
        return 0;
}

/* Get packet from user space buffer */
static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
                            void *msg_control, const struct iovec *iv,
                            size_t total_len, size_t count, int noblock)
{
        struct tun_pi pi = { 0, cpu_to_be16(ETH_P_IP) };
        struct sk_buff *skb;
        size_t len = total_len, align = NET_SKB_PAD;
        struct virtio_net_hdr gso = { 0 };
        int offset = 0;
        int copylen;
        bool zerocopy = false;
        int err;

        if (!(tun->flags & TUN_NO_PI)) {
                if ((len -= sizeof(pi)) > total_len)
                        return -EINVAL;

                if (memcpy_fromiovecend((void *)&pi, iv, 0, sizeof(pi)))
                        return -EFAULT;
                offset += sizeof(pi);
        }

        if (tun->flags & TUN_VNET_HDR) {
                if ((len -= tun->vnet_hdr_sz) > total_len)
                        return -EINVAL;

                if (memcpy_fromiovecend((void *)&gso, iv, offset, sizeof(gso)))
                        return -EFAULT;

                if ((gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
                    gso.csum_start + gso.csum_offset + 2 > gso.hdr_len)
                        gso.hdr_len = gso.csum_start + gso.csum_offset + 2;

                if (gso.hdr_len > len)
                        return -EINVAL;
                offset += tun->vnet_hdr_sz;
        }

        if ((tun->flags & TUN_TYPE_MASK) == TUN_TAP_DEV) {
                align += NET_IP_ALIGN;
                if (unlikely(len < ETH_HLEN ||
                             (gso.hdr_len && gso.hdr_len < ETH_HLEN)))
                        return -EINVAL;
        }

        if (msg_control)
                zerocopy = true;

        if (zerocopy) {
                /* Userspace may produce vectors with count greater than
                 * MAX_SKB_FRAGS, so we need to linearize parts of the skb
                 * to let the rest of data to be fit in the frags.
                 */
                if (count > MAX_SKB_FRAGS) {
                        copylen = iov_length(iv, count - MAX_SKB_FRAGS);
                        if (copylen < offset)
                                copylen = 0;
                        else
                                copylen -= offset;
                } else
                                copylen = 0;
                /* 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.
                 */
                if (copylen < gso.hdr_len)
                        copylen = gso.hdr_len;
                if (!copylen)
                        copylen = GOODCOPY_LEN;
        } else
                copylen = len;

        skb = tun_alloc_skb(tfile, align, copylen, gso.hdr_len, noblock);
        if (IS_ERR(skb)) {
                if (PTR_ERR(skb) != -EAGAIN)
                        tun->dev->stats.rx_dropped++;
                return PTR_ERR(skb);
        }

        if (zerocopy)
                err = zerocopy_sg_from_iovec(skb, iv, offset, count);
        else
                err = skb_copy_datagram_from_iovec(skb, 0, iv, offset, len);

        if (err) {
                tun->dev->stats.rx_dropped++;
                kfree_skb(skb);
                return -EFAULT;
        }

        if (gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
                if (!skb_partial_csum_set(skb, gso.csum_start,
                                          gso.csum_offset)) {
                        tun->dev->stats.rx_frame_errors++;
                        kfree_skb(skb);
                        return -EINVAL;
                }
        }

        switch (tun->flags & TUN_TYPE_MASK) {
        case TUN_TUN_DEV:
                if (tun->flags & TUN_NO_PI) {
                        switch (skb->data[0] & 0xf0) {
                        case 0x40:
                                pi.proto = htons(ETH_P_IP);
                                break;
                        case 0x60:
                                pi.proto = htons(ETH_P_IPV6);
                                break;
                        default:
                                tun->dev->stats.rx_dropped++;
                                kfree_skb(skb);
                                return -EINVAL;
                        }
                }

                skb_reset_mac_header(skb);
                skb->protocol = pi.proto;
                skb->dev = tun->dev;
                break;
        case TUN_TAP_DEV:
                skb->protocol = eth_type_trans(skb, tun->dev);
                break;
        }

        if (gso.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
                pr_debug("GSO!\n");
                switch (gso.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
                case VIRTIO_NET_HDR_GSO_TCPV4:
                        skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
                        break;
                case VIRTIO_NET_HDR_GSO_TCPV6:
                        skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
                        break;
                case VIRTIO_NET_HDR_GSO_UDP:
                        skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
                        break;
                default:
                        tun->dev->stats.rx_frame_errors++;
                        kfree_skb(skb);
                        return -EINVAL;
                }

                if (gso.gso_type & VIRTIO_NET_HDR_GSO_ECN)
                        skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;

                skb_shinfo(skb)->gso_size = gso.gso_size;
                if (skb_shinfo(skb)->gso_size == 0) {
                        tun->dev->stats.rx_frame_errors++;
                        kfree_skb(skb);
                        return -EINVAL;
                }

                /* Header must be checked, and gso_segs computed. */
                skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
                skb_shinfo(skb)->gso_segs = 0;
        }

        /* copy skb_ubuf_info for callback when skb has no error */
        if (zerocopy) {
                skb_shinfo(skb)->destructor_arg = msg_control;
                skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
        }

        netif_rx_ni(skb);

        tun->dev->stats.rx_packets++;
        tun->dev->stats.rx_bytes += len;

        tun_flow_update(tun, skb, tfile->queue_index);
        return total_len;
}

static ssize_t tun_chr_aio_write(struct kiocb *iocb, const struct iovec *iv,
                              unsigned long count, loff_t pos)
{
        struct file *file = iocb->ki_filp;
        struct tun_struct *tun = tun_get(file);
        struct tun_file *tfile = file->private_data;
        ssize_t result;

        if (!tun)
                return -EBADFD;

        tun_debug(KERN_INFO, tun, "tun_chr_write %ld\n", count);

        result = tun_get_user(tun, tfile, NULL, iv, iov_length(iv, count),
                              count, file->f_flags & O_NONBLOCK);

        tun_put(tun);
        return result;
}

/* Put packet to the user space buffer */
static ssize_t tun_put_user(struct tun_struct *tun,
                            struct tun_file *tfile,
                            struct sk_buff *skb,
                            const struct iovec *iv, int len)
{
        struct tun_pi pi = { 0, skb->protocol };
        ssize_t total = 0;

        if (!(tun->flags & TUN_NO_PI)) {
                if ((len -= sizeof(pi)) < 0)
                        return -EINVAL;

                if (len < skb->len) {
                        /* Packet will be striped */
                        pi.flags |= TUN_PKT_STRIP;
                }

                if (memcpy_toiovecend(iv, (void *) &pi, 0, sizeof(pi)))
                        return -EFAULT;
                total += sizeof(pi);
        }

        if (tun->flags & TUN_VNET_HDR) {
                struct virtio_net_hdr gso = { 0 }; /* no info leak */
                if ((len -= tun->vnet_hdr_sz) < 0)
                        return -EINVAL;

                if (skb_is_gso(skb)) {
                        struct skb_shared_info *sinfo = skb_shinfo(skb);

                        /* This is a hint as to how much should be linear. */
                        gso.hdr_len = skb_headlen(skb);
                        gso.gso_size = sinfo->gso_size;
                        if (sinfo->gso_type & SKB_GSO_TCPV4)
                                gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
                        else if (sinfo->gso_type & SKB_GSO_TCPV6)
                                gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
                        else if (sinfo->gso_type & SKB_GSO_UDP)
                                gso.gso_type = VIRTIO_NET_HDR_GSO_UDP;
                        else {
                                pr_err("unexpected GSO type: "
                                       "0x%x, gso_size %d, hdr_len %d\n",
                                       sinfo->gso_type, gso.gso_size,
                                       gso.hdr_len);
                                print_hex_dump(KERN_ERR, "tun: ",
                                               DUMP_PREFIX_NONE,
                                               16, 1, skb->head,
                                               min((int)gso.hdr_len, 64), true);
                                WARN_ON_ONCE(1);
                                return -EINVAL;
                        }
                        if (sinfo->gso_type & SKB_GSO_TCP_ECN)
                                gso.gso_type |= VIRTIO_NET_HDR_GSO_ECN;
                } else
                        gso.gso_type = VIRTIO_NET_HDR_GSO_NONE;

                if (skb->ip_summed == CHECKSUM_PARTIAL) {
                        gso.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
                        gso.csum_start = skb_checksum_start_offset(skb);
                        gso.csum_offset = skb->csum_offset;
                } else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
                        gso.flags = VIRTIO_NET_HDR_F_DATA_VALID;
                } /* else everything is zero */

                if (unlikely(memcpy_toiovecend(iv, (void *)&gso, total,
                                               sizeof(gso))))
                        return -EFAULT;
                total += tun->vnet_hdr_sz;
        }

        len = min_t(int, skb->len, len);

        skb_copy_datagram_const_iovec(skb, 0, iv, total, len);
        total += skb->len;

        tun->dev->stats.tx_packets++;
        tun->dev->stats.tx_bytes += len;

        return total;
}

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)
{
        DECLARE_WAITQUEUE(wait, current);
        struct sk_buff *skb;
        ssize_t ret = 0;

        tun_debug(KERN_INFO, tun, "tun_chr_read\n");

        if (unlikely(!noblock))
                add_wait_queue(&tfile->wq.wait, &wait);
        while (len) {
                current->state = TASK_INTERRUPTIBLE;

                /* 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;
                }
                netif_wake_subqueue(tun->dev, tfile->queue_index);

                ret = tun_put_user(tun, tfile, skb, iv, len);
                kfree_skb(skb);
                break;
        }

        current->state = TASK_RUNNING;
        if (unlikely(!noblock))
                remove_wait_queue(&tfile->wq.wait, &wait);

        return ret;
}

static ssize_t tun_chr_aio_read(struct kiocb *iocb, const struct iovec *iv,
                            unsigned long count, loff_t pos)
{
        struct file *file = iocb->ki_filp;
        struct tun_file *tfile = file->private_data;
        struct tun_struct *tun = __tun_get(tfile);
        ssize_t len, ret;

        if (!tun)
                return -EBADFD;
        len = iov_length(iv, count);
        if (len < 0) {
                ret = -EINVAL;
                goto out;
        }

        ret = tun_do_read(tun, tfile, iocb, iv, len,
                          file->f_flags & O_NONBLOCK);
        ret = min_t(ssize_t, ret, len);
out:
        tun_put(tun);
        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->owner = INVALID_UID;
        tun->group = INVALID_GID;

        dev->ethtool_ops = &tun_ethtool_ops;
        dev->destructor = tun_free_netdev;
}

/* Trivial set of netlink ops to allow deleting tun or tap
 * device with netlink.
 */
static int tun_validate(struct nlattr *tb[], struct nlattr *data[])
{
        return -EINVAL;
}

static struct rtnl_link_ops tun_link_ops __read_mostly = {
        .kind           = DRV_NAME,
        .priv_size      = sizeof(struct tun_struct),
        .setup          = tun_setup,
        .validate       = tun_validate,
};

static void tun_sock_write_space(struct sock *sk)
{
        struct tun_file *tfile;
        wait_queue_head_t *wqueue;

        if (!sock_writeable(sk))
                return;

        if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags))
                return;

        wqueue = sk_sleep(sk);
        if (wqueue && waitqueue_active(wqueue))
                wake_up_interruptible_sync_poll(wqueue, POLLOUT |
                                                POLLWRNORM | POLLWRBAND);

        tfile = container_of(sk, struct tun_file, sk);
        kill_fasync(&tfile->fasync, SIGIO, POLL_OUT);
}

static int tun_sendmsg(struct kiocb *iocb, struct socket *sock,
                       struct msghdr *m, size_t total_len)
{
        int ret;
        struct tun_file *tfile = container_of(sock, struct tun_file, socket);
        struct tun_struct *tun = __tun_get(tfile);

        if (!tun)
                return -EBADFD;
        ret = tun_get_user(tun, tfile, m->msg_control, m->msg_iov, total_len,
                           m->msg_iovlen, m->msg_flags & MSG_DONTWAIT);
        tun_put(tun);
        return ret;
}


static int tun_recvmsg(struct kiocb *iocb, struct socket *sock,
                       struct msghdr *m, size_t total_len,
                       int flags)
{
        struct tun_file *tfile = container_of(sock, struct tun_file, socket);
        struct tun_struct *tun = __tun_get(tfile);
        int ret;

        if (!tun)
                return -EBADFD;

        if (flags & ~(MSG_DONTWAIT|MSG_TRUNC))
                return -EINVAL;
        ret = tun_do_read(tun, tfile, iocb, m->msg_iov, total_len,
                          flags & MSG_DONTWAIT);
        if (ret > total_len) {
                m->msg_flags |= MSG_TRUNC;
                ret = flags & MSG_TRUNC ? ret : total_len;
        }
        tun_put(tun);
        return ret;
}

static int tun_release(struct socket *sock)
{
        if (sock->sk)
                sock_put(sock->sk);
        return 0;
}

/* Ops structure to mimic raw sockets with tun */
static const struct proto_ops tun_socket_ops = {
        .sendmsg = tun_sendmsg,
        .recvmsg = tun_recvmsg,
        .release = tun_release,
};

static struct proto tun_proto = {
        .name           = "tun",
        .owner          = THIS_MODULE,
        .obj_size       = sizeof(struct tun_file),
};

static int tun_flags(struct tun_struct *tun)
{
        int flags = 0;

        if (tun->flags & TUN_TUN_DEV)
                flags |= IFF_TUN;
        else
                flags |= IFF_TAP;

        if (tun->flags & TUN_NO_PI)
                flags |= IFF_NO_PI;

        if (tun->flags & TUN_ONE_QUEUE)
                flags |= IFF_ONE_QUEUE;

        if (tun->flags & TUN_VNET_HDR)
                flags |= IFF_VNET_HDR;

        if (tun->flags & TUN_TAP_MQ)
                flags |= IFF_MULTI_QUEUE;

        return flags;
}

static ssize_t tun_show_flags(struct device *dev, struct device_attribute *attr,
                              char *buf)
{
        struct tun_struct *tun = netdev_priv(to_net_dev(dev));
        return sprintf(buf, "0x%x\n", tun_flags(tun));
}

static ssize_t tun_show_owner(struct device *dev, struct device_attribute *attr,
                              char *buf)
{
        struct tun_struct *tun = netdev_priv(to_net_dev(dev));
        return uid_valid(tun->owner)?
                sprintf(buf, "%u\n",
                        from_kuid_munged(current_user_ns(), tun->owner)):
                sprintf(buf, "-1\n");
}

static ssize_t tun_show_group(struct device *dev, struct device_attribute *attr,
                              char *buf)
{
        struct tun_struct *tun = netdev_priv(to_net_dev(dev));
        return gid_valid(tun->group) ?
                sprintf(buf, "%u\n",
                        from_kgid_munged(current_user_ns(), tun->group)):
                sprintf(buf, "-1\n");
}

static DEVICE_ATTR(tun_flags, 0444, tun_show_flags, NULL);
static DEVICE_ATTR(owner, 0444, tun_show_owner, NULL);
static DEVICE_ATTR(group, 0444, tun_show_group, NULL);

static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
{
        struct tun_struct *tun;
        struct tun_file *tfile = file->private_data;
        struct net_device *dev;
        int err;

        dev = __dev_get_by_name(net, ifr->ifr_name);
        if (dev) {
                if (ifr->ifr_flags & IFF_TUN_EXCL)
                        return -EBUSY;
                if ((ifr->ifr_flags & IFF_TUN) && dev->netdev_ops == &tun_netdev_ops)
                        tun = netdev_priv(dev);
                else if ((ifr->ifr_flags & IFF_TAP) && dev->netdev_ops == &tap_netdev_ops)
                        tun = netdev_priv(dev);
                else
                        return -EINVAL;

                if (tun_not_capable(tun))
                        return -EPERM;
                err = security_tun_dev_attach(tfile->socket.sk);
                if (err < 0)
                        return err;

                err = tun_attach(tun, file);
                if (err < 0)
                        return err;
        }
        else {
                char *name;
                unsigned long flags = 0;

                if (!capable(CAP_NET_ADMIN))
                        return -EPERM;
                err = security_tun_dev_create();
                if (err < 0)
                        return err;

                /* Set dev type */
                if (ifr->ifr_flags & IFF_TUN) {
                        /* TUN device */
                        flags |= TUN_TUN_DEV;
                        name = "tun%d";
                } else if (ifr->ifr_flags & IFF_TAP) {
                        /* TAP device */
                        flags |= TUN_TAP_DEV;
                        name = "tap%d";
                } else
                        return -EINVAL;

                if (*ifr->ifr_name)
                        name = ifr->ifr_name;

                dev = alloc_netdev_mqs(sizeof(struct tun_struct), name,
                                       tun_setup,
                                       MAX_TAP_QUEUES, MAX_TAP_QUEUES);
                if (!dev)
                        return -ENOMEM;

                dev_net_set(dev, net);
                dev->rtnl_link_ops = &tun_link_ops;

                tun = netdev_priv(dev);
                tun->dev = dev;
                tun->flags = flags;
                tun->txflt.count = 0;
                tun->vnet_hdr_sz = sizeof(struct virtio_net_hdr);

                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 = register_netdevice(tun->dev);
                if (err < 0)
                        goto err_free_dev;

                if (device_create_file(&tun->dev->dev, &dev_attr_tun_flags) ||
                    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");

                err = tun_attach(tun, file);
                if (err < 0)
                        goto err_free_dev;
        }

        tun_debug(KERN_INFO, tun, "tun_set_iff\n");

        if (ifr->ifr_flags & IFF_NO_PI)
                tun->flags |= TUN_NO_PI;
        else
                tun->flags &= ~TUN_NO_PI;

        if (ifr->ifr_flags & IFF_ONE_QUEUE)
                tun->flags |= TUN_ONE_QUEUE;
        else
                tun->flags &= ~TUN_ONE_QUEUE;

        if (ifr->ifr_flags & IFF_VNET_HDR)
                tun->flags |= TUN_VNET_HDR;
        else
                tun->flags &= ~TUN_VNET_HDR;

        if (ifr->ifr_flags & IFF_MULTI_QUEUE)
                tun->flags |= TUN_TAP_MQ;
        else
                tun->flags &= ~TUN_TAP_MQ;

        /* Make sure persistent devices do not get stuck in
         * xoff state.
         */
        if (netif_running(tun->dev))
                netif_tx_wake_all_queues(tun->dev);

        strcpy(ifr->ifr_name, tun->dev->name);
        return 0;

 err_free_dev:
        free_netdev(dev);
        return err;
}

static int tun_get_iff(struct net *net, struct tun_struct *tun,
                       struct ifreq *ifr)
{
        tun_debug(KERN_INFO, tun, "tun_get_iff\n");

        strcpy(ifr->ifr_name, tun->dev->name);

        ifr->ifr_flags = tun_flags(tun);

        return 0;
}

/* This is like a cut-down ethtool ops, except done via tun fd so no
 * privs required. */
static int set_offload(struct tun_struct *tun, unsigned long arg)
{
        netdev_features_t features = 0;

        if (arg & TUN_F_CSUM) {
                features |= NETIF_F_HW_CSUM;
                arg &= ~TUN_F_CSUM;

                if (arg & (TUN_F_TSO4|TUN_F_TSO6)) {
                        if (arg & TUN_F_TSO_ECN) {
                                features |= NETIF_F_TSO_ECN;
                                arg &= ~TUN_F_TSO_ECN;
                        }
                        if (arg & TUN_F_TSO4)
                                features |= NETIF_F_TSO;
                        if (arg & TUN_F_TSO6)
                                features |= NETIF_F_TSO6;
                        arg &= ~(TUN_F_TSO4|TUN_F_TSO6);
                }

                if (arg & TUN_F_UFO) {
                        features |= NETIF_F_UFO;
                        arg &= ~TUN_F_UFO;
                }
        }

        /* This gives the user a way to test for new features in future by
         * trying to set them. */
        if (arg)
                return -EINVAL;

        tun->set_features = features;
        netdev_update_features(tun->dev);

        return 0;
}

static void tun_detach_filter(struct tun_struct *tun, int n)
{
        int i;
        struct tun_file *tfile;

        for (i = 0; i < n; i++) {
                tfile = rcu_dereference_protected(tun->tfiles[i],
                                                  lockdep_rtnl_is_held());
                sk_detach_filter(tfile->socket.sk);
        }

        tun->filter_attached = false;
}

static int tun_attach_filter(struct tun_struct *tun)
{
        int i, ret = 0;
        struct tun_file *tfile;

        for (i = 0; i < tun->numqueues; i++) {
                tfile = rcu_dereference_protected(tun->tfiles[i],
                                                  lockdep_rtnl_is_held());
                ret = sk_attach_filter(&tun->fprog, tfile->socket.sk);
                if (ret) {
                        tun_detach_filter(tun, i);
                        return ret;
                }
        }

        tun->filter_attached = true;
        return ret;
}

static void tun_set_sndbuf(struct tun_struct *tun)
{
        struct tun_file *tfile;
        int i;

        for (i = 0; i < tun->numqueues; i++) {
                tfile = rcu_dereference_protected(tun->tfiles[i],
                                                lockdep_rtnl_is_held());
                tfile->socket.sk->sk_sndbuf = tun->sndbuf;
        }
}

static int tun_set_queue(struct file *file, struct ifreq *ifr)
{
        struct tun_file *tfile = file->private_data;
        struct tun_struct *tun;
        struct net_device *dev;
        int ret = 0;

        rtnl_lock();

        if (ifr->ifr_flags & IFF_ATTACH_QUEUE) {
                dev = __dev_get_by_name(tfile->net, ifr->ifr_name);
                if (!dev) {
                        ret = -EINVAL;
                        goto unlock;
                }

                tun = netdev_priv(dev);
                if (dev->netdev_ops != &tap_netdev_ops &&
                        dev->netdev_ops != &tun_netdev_ops)
                        ret = -EINVAL;
                else if (tun_not_capable(tun))
                        ret = -EPERM;
                else
                        ret = tun_attach(tun, file);
        } else if (ifr->ifr_flags & IFF_DETACH_QUEUE)
                __tun_detach(tfile, false);
        else
                ret = -EINVAL;

unlock:
        rtnl_unlock();
        return ret;
}

static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
                            unsigned long arg, int ifreq_len)
{
        struct tun_file *tfile = file->private_data;
        struct tun_struct *tun;
        void __user* argp = (void __user*)arg;
        struct ifreq ifr;
        kuid_t owner;
        kgid_t group;
        int sndbuf;
        int vnet_hdr_sz;
        int ret;

        if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == 0x89) {
                if (copy_from_user(&ifr, argp, ifreq_len))
                        return -EFAULT;
        } else {
                memset(&ifr, 0, sizeof(ifr));
        }
        if (cmd == TUNGETFEATURES) {
                /* Currently this just means: "what IFF flags are valid?".
                 * This is needed because we never checked for invalid flags on
                 * TUNSETIFF. */
                return put_user(IFF_TUN | IFF_TAP | IFF_NO_PI | IFF_ONE_QUEUE |
                                IFF_VNET_HDR | IFF_MULTI_QUEUE,
                                (unsigned int __user*)argp);
        } else if (cmd == TUNSETQUEUE)
                return tun_set_queue(file, &ifr);

        ret = 0;
        rtnl_lock();

        tun = __tun_get(tfile);
        if (cmd == TUNSETIFF && !tun) {
                ifr.ifr_name[IFNAMSIZ-1] = '\0';

                ret = tun_set_iff(tfile->net, file, &ifr);

                if (ret)
                        goto unlock;

                if (copy_to_user(argp, &ifr, ifreq_len))
                        ret = -EFAULT;
                goto unlock;
        }

        ret = -EBADFD;
        if (!tun)
                goto unlock;

        tun_debug(KERN_INFO, tun, "tun_chr_ioctl cmd %u\n", cmd);

        ret = 0;
        switch (cmd) {
        case TUNGETIFF:
                ret = tun_get_iff(current->nsproxy->net_ns, tun, &ifr);
                if (ret)
                        break;

                if (copy_to_user(argp, &ifr, ifreq_len))
                        ret = -EFAULT;
                break;

        case TUNSETNOCSUM:
                /* Disable/Enable checksum */

                /* [unimplemented] */
                tun_debug(KERN_INFO, tun, "ignored: set checksum %s\n",
                          arg ? "disabled" : "enabled");
                break;

        case TUNSETPERSIST:
                /* Disable/Enable persist mode. Keep an extra reference to the
                 * module to prevent the module being unprobed.
                 */
                if (arg) {
                        tun->flags |= TUN_PERSIST;
                        __module_get(THIS_MODULE);
                } else {
                        tun->flags &= ~TUN_PERSIST;
                        module_put(THIS_MODULE);
                }

                tun_debug(KERN_INFO, tun, "persist %s\n",
                          arg ? "enabled" : "disabled");
                break;

        case TUNSETOWNER:
                /* Set owner of the device */
                owner = make_kuid(current_user_ns(), arg);
                if (!uid_valid(owner)) {
                        ret = -EINVAL;
                        break;
                }
                tun->owner = owner;
                tun_debug(KERN_INFO, tun, "owner set to %u\n",
                          from_kuid(&init_user_ns, tun->owner));
                break;

        case TUNSETGROUP:
                /* Set group of the device */
                group = make_kgid(current_user_ns(), arg);
                if (!gid_valid(group)) {
                        ret = -EINVAL;
                        break;
                }
                tun->group = group;
                tun_debug(KERN_INFO, tun, "group set to %u\n",
                          from_kgid(&init_user_ns, tun->group));
                break;

        case TUNSETLINK:
                /* Only allow setting the type when the interface is down */
                if (tun->dev->flags & IFF_UP) {
                        tun_debug(KERN_INFO, tun,
                                  "Linktype set failed because interface is up\n");
                        ret = -EBUSY;
                } else {
                        tun->dev->type = (int) arg;
                        tun_debug(KERN_INFO, tun, "linktype set to %d\n",
                                  tun->dev->type);
                        ret = 0;
                }
                break;

#ifdef TUN_DEBUG
        case TUNSETDEBUG:
                tun->debug = arg;
                break;
#endif
        case TUNSETOFFLOAD:
                ret = set_offload(tun, arg);
                break;

        case TUNSETTXFILTER:
                /* Can be set only for TAPs */
                ret = -EINVAL;
                if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
                        break;
                ret = update_filter(&tun->txflt, (void __user *)arg);
                break;

        case SIOCGIFHWADDR:
                /* Get hw address */
                memcpy(ifr.ifr_hwaddr.sa_data, tun->dev->dev_addr, ETH_ALEN);
                ifr.ifr_hwaddr.sa_family = tun->dev->type;
                if (copy_to_user(argp, &ifr, ifreq_len))
                        ret = -EFAULT;
                break;

        case SIOCSIFHWADDR:
                /* Set hw address */
                tun_debug(KERN_DEBUG, tun, "set hw address: %pM\n",
                          ifr.ifr_hwaddr.sa_data);

                ret = dev_set_mac_address(tun->dev, &ifr.ifr_hwaddr);
                break;

        case TUNGETSNDBUF:
                sndbuf = tfile->socket.sk->sk_sndbuf;
                if (copy_to_user(argp, &sndbuf, sizeof(sndbuf)))
                        ret = -EFAULT;
                break;

        case TUNSETSNDBUF:
                if (copy_from_user(&sndbuf, argp, sizeof(sndbuf))) {
                        ret = -EFAULT;
                        break;
                }

                tun->sndbuf = sndbuf;
                tun_set_sndbuf(tun);
                break;

        case TUNGETVNETHDRSZ:
                vnet_hdr_sz = tun->vnet_hdr_sz;
                if (copy_to_user(argp, &vnet_hdr_sz, sizeof(vnet_hdr_sz)))
                        ret = -EFAULT;
                break;

        case TUNSETVNETHDRSZ:
                if (copy_from_user(&vnet_hdr_sz, argp, sizeof(vnet_hdr_sz))) {
                        ret = -EFAULT;
                        break;
                }
                if (vnet_hdr_sz < (int)sizeof(struct virtio_net_hdr)) {
                        ret = -EINVAL;
                        break;
                }

                tun->vnet_hdr_sz = vnet_hdr_sz;
                break;

        case TUNATTACHFILTER:
                /* Can be set only for TAPs */
                ret = -EINVAL;
                if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
                        break;
                ret = -EFAULT;
                if (copy_from_user(&tun->fprog, argp, sizeof(tun->fprog)))
                        break;

                ret = tun_attach_filter(tun);
                break;

        case TUNDETACHFILTER:
                /* Can be set only for TAPs */
                ret = -EINVAL;
                if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
                        break;
                ret = 0;
                tun_detach_filter(tun, tun->numqueues);
                break;

        default:
                ret = -EINVAL;
                break;
        }

unlock:
        rtnl_unlock();
        if (tun)
                tun_put(tun);
        return ret;
}

static long tun_chr_ioctl(struct file *file,
                          unsigned int cmd, unsigned long arg)
{
        return __tun_chr_ioctl(file, cmd, arg, sizeof (struct ifreq));
}

#ifdef CONFIG_COMPAT
static long tun_chr_compat_ioctl(struct file *file,
                         unsigned int cmd, unsigned long arg)
{
        switch (cmd) {
        case TUNSETIFF:
        case TUNGETIFF:
        case TUNSETTXFILTER:
        case TUNGETSNDBUF:
        case TUNSETSNDBUF:
        case SIOCGIFHWADDR:
        case SIOCSIFHWADDR:
                arg = (unsigned long)compat_ptr(arg);
                break;
        default:
                arg = (compat_ulong_t)arg;
                break;
        }

        /*
         * compat_ifreq is shorter than ifreq, so we must not access beyond
         * the end of that structure. All fields that are used in this
         * driver are compatible though, we don't need to convert the
         * contents.
         */
        return __tun_chr_ioctl(file, cmd, arg, sizeof(struct compat_ifreq));
}
#endif /* CONFIG_COMPAT */

static int tun_chr_fasync(int fd, struct file *file, int on)
{
        struct tun_file *tfile = file->private_data;
        int ret;

        if ((ret = fasync_helper(fd, file, on, &tfile->fasync)) < 0)
                goto out;

        if (on) {
                ret = __f_setown(file, task_pid(current), PIDTYPE_PID, 0);
                if (ret)
                        goto out;
                tfile->flags |= TUN_FASYNC;
        } else
                tfile->flags &= ~TUN_FASYNC;
        ret = 0;
out:
        return ret;
}

static int tun_chr_open(struct inode *inode, struct file * file)
{
        struct tun_file *tfile;

        DBG1(KERN_INFO, "tunX: tun_chr_open\n");

        tfile = (struct tun_file *)sk_alloc(&init_net, AF_UNSPEC, GFP_KERNEL,
                                            &tun_proto);
        if (!tfile)
                return -ENOMEM;
        rcu_assign_pointer(tfile->tun, NULL);
        tfile->net = get_net(current->nsproxy->net_ns);
        tfile->flags = 0;

        rcu_assign_pointer(tfile->socket.wq, &tfile->wq);
        init_waitqueue_head(&tfile->wq.wait);

        tfile->socket.file = file;
        tfile->socket.ops = &tun_socket_ops;

        sock_init_data(&tfile->socket, &tfile->sk);
        sk_change_net(&tfile->sk, tfile->net);

        tfile->sk.sk_write_space = tun_sock_write_space;
        tfile->sk.sk_sndbuf = INT_MAX;

        file->private_data = tfile;
        set_bit(SOCK_EXTERNALLY_ALLOCATED, &tfile->socket.flags);

        return 0;
}

static int tun_chr_close(struct inode *inode, struct file *file)
{
        struct tun_file *tfile = file->private_data;
        struct net *net = tfile->net;

        tun_detach(tfile, true);
        put_net(net);

        return 0;
}

static const struct file_operations tun_fops = {
        .owner  = THIS_MODULE,
        .llseek = no_llseek,
        .read  = do_sync_read,
        .aio_read  = tun_chr_aio_read,
        .write = do_sync_write,
        .aio_write = tun_chr_aio_write,
        .poll   = tun_chr_poll,
        .unlocked_ioctl = tun_chr_ioctl,
#ifdef CONFIG_COMPAT
        .compat_ioctl = tun_chr_compat_ioctl,
#endif
        .open   = tun_chr_open,
        .release = tun_chr_close,
        .fasync = tun_chr_fasync
};

static struct miscdevice tun_miscdev = {
        .minor = TUN_MINOR,
        .name = "tun",
        .nodename = "net/tun",
        .fops = &tun_fops,
};

/* ethtool interface */

static int tun_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
{
        cmd->supported          = 0;
        cmd->advertising        = 0;
        ethtool_cmd_speed_set(cmd, SPEED_10);
        cmd->duplex             = DUPLEX_FULL;
        cmd->port               = PORT_TP;
        cmd->phy_address        = 0;
        cmd->transceiver        = XCVR_INTERNAL;
        cmd->autoneg            = AUTONEG_DISABLE;
        cmd->maxtxpkt           = 0;
        cmd->maxrxpkt           = 0;
        return 0;
}

static void tun_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
        struct tun_struct *tun = netdev_priv(dev);

        strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
        strlcpy(info->version, DRV_VERSION, sizeof(info->version));

        switch (tun->flags & TUN_TYPE_MASK) {
        case TUN_TUN_DEV:
                strlcpy(info->bus_info, "tun", sizeof(info->bus_info));
                break;
        case TUN_TAP_DEV:
                strlcpy(info->bus_info, "tap", sizeof(info->bus_info));
                break;
        }
}

static u32 tun_get_msglevel(struct net_device *dev)
{
#ifdef TUN_DEBUG
        struct tun_struct *tun = netdev_priv(dev);
        return tun->debug;
#else
        return -EOPNOTSUPP;
#endif
}

static void tun_set_msglevel(struct net_device *dev, u32 value)
{
#ifdef TUN_DEBUG
        struct tun_struct *tun = netdev_priv(dev);
        tun->debug = value;
#endif
}

static const struct ethtool_ops tun_ethtool_ops = {
        .get_settings   = tun_get_settings,
        .get_drvinfo    = tun_get_drvinfo,
        .get_msglevel   = tun_get_msglevel,
        .set_msglevel   = tun_set_msglevel,
        .get_link       = ethtool_op_get_link,
};


static int __init tun_init(void)
{
        int ret = 0;

        pr_info("%s, %s\n", DRV_DESCRIPTION, DRV_VERSION);
        pr_info("%s\n", DRV_COPYRIGHT);

        ret = rtnl_link_register(&tun_link_ops);
        if (ret) {
                pr_err("Can't register link_ops\n");
                goto err_linkops;
        }

        ret = misc_register(&tun_miscdev);
        if (ret) {
                pr_err("Can't register misc device %d\n", TUN_MINOR);
                goto err_misc;
        }
        return  0;
err_misc:
        rtnl_link_unregister(&tun_link_ops);
err_linkops:
        return ret;
}

static void tun_cleanup(void)
{
        misc_deregister(&tun_miscdev);
        rtnl_link_unregister(&tun_link_ops);
}

/* Get an underlying socket object from tun file.  Returns error unless file is
 * attached to a device.  The returned object works like a packet socket, it
 * can be used for sock_sendmsg/sock_recvmsg.  The caller is responsible for
 * holding a reference to the file for as long as the socket is in use. */
struct socket *tun_get_socket(struct file *file)
{
        struct tun_file *tfile;
        if (file->f_op != &tun_fops)
                return ERR_PTR(-EINVAL);
        tfile = file->private_data;
        if (!tfile)
                return ERR_PTR(-EBADFD);
        return &tfile->socket;
}
EXPORT_SYMBOL_GPL(tun_get_socket);

module_init(tun_init);
module_exit(tun_cleanup);
MODULE_DESCRIPTION(DRV_DESCRIPTION);
MODULE_AUTHOR(DRV_COPYRIGHT);
MODULE_LICENSE("GPL");
MODULE_ALIAS_MISCDEV(TUN_MINOR);
MODULE_ALIAS("devname:net/tun");