diff options
Diffstat (limited to 'drivers/net/tun.c')
| -rw-r--r-- | drivers/net/tun.c | 2268 |
1 files changed, 1867 insertions, 401 deletions
diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 7b816a03295..98bad1fb1bf 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -18,15 +18,11 @@ /* * Changes: * - * Brian Braunstein <linuxkernel@bristyle.com> 2007/03/23 - * Fixed hw address handling. Now net_device.dev_addr is kept consistent - * with tun.dev_addr when the address is set by this module. - * * Mike Kershaw <dragorn@kismetwireless.net> 2005/08/14 * Add TUNSETLINK ioctl to set the link encapsulation * * Mark Smith <markzzzsmith@yahoo.com.au> - * Use random_ether_addr() for tap MAC address. + * 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. @@ -38,6 +34,8 @@ * 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" @@ -57,118 +55,778 @@ #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/if_vlan.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 <linux/seq_file.h> -#include <asm/system.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]; +}; + +/* 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 +#define MAX_TAP_FLOWS 4096 + +#define TUN_FLOW_EXPIRE (3 * HZ) + +/* A tun_file connects an open character device to a tuntap netdevice. It + * 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 + * this). + * + * RCU usage: + * The tun_file and tun_struct are loosely coupled, the pointer from one to the + * other can only be read while rcu_read_lock or rtnl_lock is held. + */ +struct tun_file { + 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; + union { + u16 queue_index; + unsigned int ifindex; + }; + struct list_head next; + struct tun_struct *detached; +}; + +struct tun_flow_entry { + struct hlist_node hash_link; + struct rcu_head rcu; + struct tun_struct *tun; + + u32 rxhash; + u32 rps_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 filter, 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 hlist_head flows[TUN_NUM_FLOW_ENTRIES]; + struct timer_list flow_gc_timer; + unsigned long ageing_time; + unsigned int numdisabled; + struct list_head disabled; + void *security; + u32 flow_count; +}; + +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; + + hlist_for_each_entry_rcu(e, 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 = kmalloc(sizeof(*e), 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->rps_rxhash = 0; + e->queue_index = queue_index; + e->tun = tun; + hlist_add_head_rcu(&e->hash_link, head); + ++tun->flow_count; + } + return 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); + sock_rps_reset_flow_hash(e->rps_rxhash); + hlist_del_rcu(&e->hash_link); + kfree_rcu(e, rcu); + --tun->flow_count; +} + +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 *n; + + hlist_for_each_entry_safe(e, 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 *n; + + hlist_for_each_entry_safe(e, 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 *n; + + hlist_for_each_entry_safe(e, 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, u32 rxhash, + 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; + else + head = &tun->flows[tun_hashfn(rxhash)]; + + rcu_read_lock(); + + /* 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); + if (likely(e)) { + /* 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) && + tun->flow_count < MAX_TAP_FLOWS) + 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(); +} + +/** + * 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 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, + void *accel_priv, select_queue_fallback_t fallback) +{ + struct tun_struct *tun = netdev_priv(dev); + struct tun_flow_entry *e; + u32 txq = 0; + u32 numqueues = 0; + + rcu_read_lock(); + numqueues = ACCESS_ONCE(tun->numqueues); + + txq = skb_get_hash(skb); + if (txq) { + e = tun_flow_find(&tun->flows[tun_hashfn(txq)], txq); + if (e) { + tun_flow_save_rps_rxhash(e, txq); + 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(); + struct net *net = dev_net(tun->dev); + + return ((uid_valid(tun->owner) && !uid_eq(cred->euid, tun->owner)) || + (gid_valid(tun->group) && !in_egroup_p(tun->group))) && + !ns_capable(net->user_ns, 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_disable_queue(struct tun_struct *tun, struct tun_file *tfile) +{ + tfile->detached = tun; + list_add_tail(&tfile->next, &tun->disabled); + ++tun->numdisabled; +} + +static struct tun_struct *tun_enable_queue(struct tun_file *tfile) +{ + struct tun_struct *tun = tfile->detached; + + tfile->detached = NULL; + list_del_init(&tfile->next); + --tun->numdisabled; + return tun; +} + +static void tun_queue_purge(struct tun_file *tfile) +{ + skb_queue_purge(&tfile->sk.sk_receive_queue); + skb_queue_purge(&tfile->sk.sk_error_queue); +} + +static void __tun_detach(struct tun_file *tfile, bool clean) +{ + struct tun_file *ntfile; + struct tun_struct *tun; + + tun = rtnl_dereference(tfile->tun); + + if (tun && !tfile->detached) { + u16 index = tfile->queue_index; + BUG_ON(index >= tun->numqueues); + + rcu_assign_pointer(tun->tfiles[index], + tun->tfiles[tun->numqueues - 1]); + ntfile = rtnl_dereference(tun->tfiles[index]); + ntfile->queue_index = index; + + --tun->numqueues; + if (clean) { + RCU_INIT_POINTER(tfile->tun, NULL); + sock_put(&tfile->sk); + } else + tun_disable_queue(tun, tfile); + + synchronize_net(); + tun_flow_delete_by_queue(tun, tun->numqueues + 1); + /* Drop read queue */ + tun_queue_purge(tfile); + tun_set_real_num_queues(tun); + } else if (tfile->detached && clean) { + tun = tun_enable_queue(tfile); + sock_put(&tfile->sk); + } + + if (clean) { + 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)); + 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, *tmp; + int i, n = tun->numqueues; + + for (i = 0; i < n; i++) { + tfile = rtnl_dereference(tun->tfiles[i]); + BUG_ON(!tfile); + 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) { + tfile->socket.sk->sk_data_ready(tfile->socket.sk); + RCU_INIT_POINTER(tfile->tun, NULL); + } + BUG_ON(tun->numqueues != 0); + + synchronize_net(); + for (i = 0; i < n; i++) { + tfile = rtnl_dereference(tun->tfiles[i]); + /* Drop read queue */ + tun_queue_purge(tfile); + sock_put(&tfile->sk); + } + list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) { + tun_enable_queue(tfile); + tun_queue_purge(tfile); + sock_put(&tfile->sk); + } + BUG_ON(tun->numdisabled != 0); + + if (tun->flags & TUN_PERSIST) + module_put(THIS_MODULE); +} + +static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filter) +{ + 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) && !tfile->detached) + goto out; + + err = -EBUSY; + if (!(tun->flags & TUN_TAP_MQ) && tun->numqueues == 1) + goto out; + + err = -E2BIG; + if (!tfile->detached && + tun->numqueues + tun->numdisabled == MAX_TAP_QUEUES) + goto out; + + err = 0; + + /* 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) + goto out; + } + tfile->queue_index = tun->numqueues; + rcu_assign_pointer(tfile->tun, tun); + rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile); + tun->numqueues++; + + if (tfile->detached) + tun_enable_queue(tfile); + else + sock_hold(&tfile->sk); + + tun_set_real_num_queues(tun); + + /* 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 LIST_HEAD(tun_dev_list); 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_start_queue(dev); + netif_tx_start_all_queues(dev); return 0; } /* Net device close. */ static int tun_net_close(struct net_device *dev) { - netif_stop_queue(dev); + netif_tx_stop_all_queues(dev); return 0; } /* Net device start xmit */ -static int tun_net_xmit(struct sk_buff *skb, struct net_device *dev) +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; - DBG(KERN_INFO "%s: tun_net_xmit %d\n", tun->dev->name, skb->len); + rcu_read_lock(); + tfile = rcu_dereference(tun->tfiles[txq]); + numqueues = ACCESS_ONCE(tun->numqueues); /* Drop packet if interface is not attached */ - if (!tun->attached) + if (txq >= numqueues) goto drop; - /* Packet dropping */ - if (skb_queue_len(&tun->readq) >= dev->tx_queue_len) { - if (!(tun->flags & TUN_ONE_QUEUE)) { - /* Normal queueing mode. */ - /* Packet scheduler handles dropping of further packets. */ - netif_stop_queue(dev); - - /* 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; + 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); } } - /* Queue packet */ - skb_queue_tail(&tun->readq, skb); - dev->trans_start = jiffies; + 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 dividing txq length with the + * number of queues. + */ + 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))) + goto drop; + + if (skb->sk) { + sock_tx_timestamp(skb->sk, &skb_shinfo(skb)->tx_flags); + sw_tx_timestamp(skb); + } + + /* Orphan the skb - required as we might hang on to it + * for indefinite time. + */ + skb_orphan(skb); + + nf_reset(skb); + + /* Enqueue packet */ + skb_queue_tail(&tfile->socket.sk->sk_receive_queue, skb); /* Notify and wake up reader process */ - if (tun->flags & TUN_FASYNC) - kill_fasync(&tun->fasync, SIGIO, POLL_IN); - wake_up_interruptible(&tun->read_wait); - return 0; + if (tfile->flags & TUN_FASYNC) + kill_fasync(&tfile->fasync, SIGIO, POLL_IN); + tfile->socket.sk->sk_data_ready(tfile->socket.sk); + + rcu_read_unlock(); + return NETDEV_TX_OK; drop: dev->stats.tx_dropped++; + skb_tx_error(skb); kfree_skb(skb); - return 0; -} - -/** Add the specified Ethernet address to this multicast filter. */ -static void -add_multi(u32* filter, const u8* addr) -{ - int bit_nr = ether_crc(ETH_ALEN, addr) >> 26; - filter[bit_nr >> 5] |= 1 << (bit_nr & 31); + rcu_read_unlock(); + return NETDEV_TX_OK; } -/** Remove the specified Ethernet addres from this multicast filter. */ -static void -del_multi(u32* filter, const u8* addr) +static void tun_net_mclist(struct net_device *dev) { - int bit_nr = ether_crc(ETH_ALEN, addr) >> 26; - filter[bit_nr >> 5] &= ~(1 << (bit_nr & 31)); -} - -/** Update the list of multicast groups to which the network device belongs. - * This list is used to filter packets being sent from the character device to - * the network device. */ -static void -tun_net_mclist(struct net_device *dev) -{ - struct tun_struct *tun = netdev_priv(dev); - const struct dev_mc_list *mclist; - int i; - DECLARE_MAC_BUF(mac); - DBG(KERN_DEBUG "%s: tun_net_mclist: mc_count %d\n", - dev->name, dev->mc_count); - memset(tun->chr_filter, 0, sizeof tun->chr_filter); - for (i = 0, mclist = dev->mc_list; i < dev->mc_count && mclist != NULL; - i++, mclist = mclist->next) { - add_multi(tun->net_filter, mclist->dmi_addr); - DBG(KERN_DEBUG "%s: tun_net_mclist: %s\n", - dev->name, print_mac(mac, mclist->dmi_addr)); - } + /* + * 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 @@ -183,6 +841,78 @@ tun_net_change_mtu(struct net_device *dev, int 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 synchronous operations, we are guaranteed + * never to have pending data when we poll for it + * 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 + */ + 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 void tun_flow_init(struct tun_struct *tun) +{ + int i; + + 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)); +} + +static void tun_flow_uninit(struct tun_struct *tun) +{ + del_timer_sync(&tun->flow_gc_timer); + tun_flow_flush(tun); +} + /* Initialize net device. */ static void tun_net_init(struct net_device *dev) { @@ -190,11 +920,12 @@ static void tun_net_init(struct net_device *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; - dev->change_mtu = tun_net_change_mtu; /* Zero header length */ dev->type = ARPHRD_NONE; @@ -203,14 +934,13 @@ static void tun_net_init(struct net_device *dev) break; case TUN_TAP_DEV: + dev->netdev_ops = &tap_netdev_ops; /* Ethernet TAP Device */ - dev->set_multicast_list = tun_net_mclist; - ether_setup(dev); - dev->change_mtu = tun_net_change_mtu; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; - /* random address already created for us by tun_set_iff, use it */ - memcpy(dev->dev_addr, tun->dev_addr, min(sizeof(tun->dev_addr), sizeof(dev->dev_addr)) ); + eth_hw_addr_random(dev); dev->tx_queue_len = TUN_READQ_SIZE; /* We prefer our own queue length */ break; @@ -220,57 +950,186 @@ static void tun_net_init(struct net_device *dev) /* Character device part */ /* Poll */ -static unsigned int tun_chr_poll(struct file *file, poll_table * wait) +static unsigned int tun_chr_poll(struct file *file, poll_table *wait) { - struct tun_struct *tun = file->private_data; - unsigned int mask = POLLOUT | POLLWRNORM; + struct tun_file *tfile = file->private_data; + struct tun_struct *tun = __tun_get(tfile); + struct sock *sk; + unsigned int mask = 0; if (!tun) - return -EBADFD; + return POLLERR; + + sk = tfile->socket.sk; - DBG(KERN_INFO "%s: tun_chr_poll\n", tun->dev->name); + tun_debug(KERN_INFO, tun, "tun_chr_poll\n"); - poll_wait(file, &tun->read_wait, wait); + poll_wait(file, sk_sleep(sk), wait); - if (!skb_queue_empty(&tun->readq)) + 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, 0); + 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; +} + /* Get packet from user space buffer */ -static __inline__ ssize_t tun_get_user(struct tun_struct *tun, struct iovec *iv, size_t count) +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, __constant_htons(ETH_P_IP) }; + struct tun_pi pi = { 0, cpu_to_be16(ETH_P_IP) }; struct sk_buff *skb; - size_t len = count, align = 0; + 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; + int err; + u32 rxhash; if (!(tun->flags & TUN_NO_PI)) { - if ((len -= sizeof(pi)) > count) + if (len < sizeof(pi)) + return -EINVAL; + len -= sizeof(pi); + + 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) return -EINVAL; + len -= tun->vnet_hdr_sz; - if(memcpy_fromiovec((void *)&pi, iv, sizeof(pi))) + 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 ((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 (!(skb = alloc_skb(len + align, GFP_KERNEL))) { - tun->dev->stats.rx_dropped++; - return -ENOMEM; + 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; + } + + if (!zerocopy) { + copylen = len; + if (gso.hdr_len > good_linear) + linear = good_linear; + else + linear = gso.hdr_len; } - if (align) - skb_reserve(skb, align); - if (memcpy_fromiovec(skb_put(skb, len), iv, len)) { + skb = tun_alloc_skb(tfile, align, copylen, linear, 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 && msg_control) { + struct ubuf_info *uarg = msg_control; + uarg->callback(uarg, false); + } + } + + 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; @@ -278,40 +1137,90 @@ static __inline__ ssize_t tun_get_user(struct tun_struct *tun, struct iovec *iv, 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 (tun->flags & TUN_NOCHECKSUM) - skb->ip_summed = CHECKSUM_UNNECESSARY; + 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; + skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; + } + + skb_reset_network_header(skb); + skb_probe_transport_header(skb, 0); + + rxhash = skb_get_hash(skb); netif_rx_ni(skb); - tun->dev->last_rx = jiffies; tun->dev->stats.rx_packets++; tun->dev->stats.rx_bytes += len; - return count; + tun_flow_update(tun, rxhash, tfile); + return total_len; } static ssize_t tun_chr_aio_write(struct kiocb *iocb, const struct iovec *iv, unsigned long count, loff_t pos) { - struct tun_struct *tun = iocb->ki_filp->private_data; + 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; - DBG(KERN_INFO "%s: tun_chr_write %ld\n", tun->dev->name, count); + 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); - return tun_get_user(tun, (struct iovec *) iv, iov_length(iv, count)); + tun_put(tun); + return result; } /* Put packet to the user space buffer */ -static __inline__ ssize_t tun_put_user(struct tun_struct *tun, - struct sk_buff *skb, - struct iovec *iv, int len) +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; + int vlan_offset = 0, copied; if (!(tun->flags & TUN_NO_PI)) { if ((len -= sizeof(pi)) < 0) @@ -322,163 +1231,391 @@ static __inline__ ssize_t tun_put_user(struct tun_struct *tun, pi.flags |= TUN_PKT_STRIP; } - if (memcpy_toiovec(iv, (void *) &pi, sizeof(pi))) + if (memcpy_toiovecend(iv, (void *) &pi, 0, sizeof(pi))) return -EFAULT; total += sizeof(pi); } - len = min_t(int, skb->len, len); + 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; + } + + copied = total; + total += skb->len; + if (!vlan_tx_tag_present(skb)) { + len = min_t(int, skb->len, len); + } else { + int copy, ret; + struct { + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + } veth; + + veth.h_vlan_proto = skb->vlan_proto; + veth.h_vlan_TCI = htons(vlan_tx_tag_get(skb)); + + 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, copied, copy); + len -= copy; + copied += copy; + if (ret || !len) + goto done; + + copy = min_t(int, sizeof(veth), len); + ret = memcpy_toiovecend(iv, (void *)&veth, copied, copy); + len -= copy; + copied += copy; + if (ret || !len) + goto done; + } - skb_copy_datagram_iovec(skb, 0, iv, len); - total += len; + skb_copy_datagram_const_iovec(skb, vlan_offset, iv, copied, len); +done: 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, + const struct iovec *iv, ssize_t len, int noblock) +{ + struct sk_buff *skb; + ssize_t ret = 0; + int peeked, err, off = 0; + + tun_debug(KERN_INFO, tun, "tun_do_read\n"); + + if (!len) + return ret; + + 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); + } else + ret = err; + + 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_struct *tun = file->private_data; - DECLARE_WAITQUEUE(wait, current); - struct sk_buff *skb; - ssize_t len, ret = 0; - DECLARE_MAC_BUF(mac); + 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; + } - DBG(KERN_INFO "%s: tun_chr_read\n", tun->dev->name); + 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; +} - len = iov_length(iv, count); - if (len < 0) - return -EINVAL; +static void tun_free_netdev(struct net_device *dev) +{ + struct tun_struct *tun = netdev_priv(dev); - add_wait_queue(&tun->read_wait, &wait); - while (len) { - const u8 ones[ ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; - u8 addr[ ETH_ALEN]; - int bit_nr; + BUG_ON(!(list_empty(&tun->disabled))); + tun_flow_uninit(tun); + security_tun_dev_free_security(tun->security); + free_netdev(dev); +} - current->state = TASK_INTERRUPTIBLE; +static void tun_setup(struct net_device *dev) +{ + struct tun_struct *tun = netdev_priv(dev); - /* Read frames from the queue */ - if (!(skb=skb_dequeue(&tun->readq))) { - if (file->f_flags & O_NONBLOCK) { - ret = -EAGAIN; - break; - } - if (signal_pending(current)) { - ret = -ERESTARTSYS; - break; - } + tun->owner = INVALID_UID; + tun->group = INVALID_GID; - /* Nothing to read, let's sleep */ - schedule(); - continue; - } - netif_wake_queue(tun->dev); - - /** Decide whether to accept this packet. This code is designed to - * behave identically to an Ethernet interface. Accept the packet if - * - we are promiscuous. - * - the packet is addressed to us. - * - the packet is broadcast. - * - the packet is multicast and - * - we are multicast promiscous. - * - we belong to the multicast group. - */ - skb_copy_from_linear_data(skb, addr, min_t(size_t, sizeof addr, - skb->len)); - bit_nr = ether_crc(sizeof addr, addr) >> 26; - if ((tun->if_flags & IFF_PROMISC) || - memcmp(addr, tun->dev_addr, sizeof addr) == 0 || - memcmp(addr, ones, sizeof addr) == 0 || - (((addr[0] == 1 && addr[1] == 0 && addr[2] == 0x5e) || - (addr[0] == 0x33 && addr[1] == 0x33)) && - ((tun->if_flags & IFF_ALLMULTI) || - (tun->chr_filter[bit_nr >> 5] & (1 << (bit_nr & 31)))))) { - DBG(KERN_DEBUG "%s: tun_chr_readv: accepted: %s\n", - tun->dev->name, print_mac(mac, addr)); - ret = tun_put_user(tun, skb, (struct iovec *) iv, len); - kfree_skb(skb); - break; - } else { - DBG(KERN_DEBUG "%s: tun_chr_readv: rejected: %s\n", - tun->dev->name, print_mac(mac, addr)); - kfree_skb(skb); - continue; - } - } + dev->ethtool_ops = &tun_ethtool_ops; + dev->destructor = tun_free_netdev; +} - current->state = TASK_RUNNING; - remove_wait_queue(&tun->read_wait, &wait); +/* 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 void tun_setup(struct net_device *dev) +static int tun_recvmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len, + int flags) { - struct tun_struct *tun = netdev_priv(dev); + struct tun_file *tfile = container_of(sock, struct tun_file, socket); + struct tun_struct *tun = __tun_get(tfile); + int ret; - skb_queue_head_init(&tun->readq); - init_waitqueue_head(&tun->read_wait); + if (!tun) + return -EBADFD; - tun->owner = -1; - tun->group = -1; + if (flags & ~(MSG_DONTWAIT|MSG_TRUNC|MSG_ERRQUEUE)) { + ret = -EINVAL; + goto out; + } + if (flags & MSG_ERRQUEUE) { + ret = sock_recv_errqueue(sock->sk, m, total_len, + SOL_PACKET, TUN_TX_TIMESTAMP); + goto out; + } + ret = tun_do_read(tun, tfile, m->msg_iov, total_len, + flags & MSG_DONTWAIT); + if (ret > total_len) { + m->msg_flags |= MSG_TRUNC; + ret = flags & MSG_TRUNC ? ret : total_len; + } +out: + tun_put(tun); + return ret; +} - dev->open = tun_net_open; - dev->hard_start_xmit = tun_net_xmit; - dev->stop = tun_net_close; - dev->ethtool_ops = &tun_ethtool_ops; - dev->destructor = free_netdev; +static int tun_release(struct socket *sock) +{ + if (sock->sk) + sock_put(sock->sk); + return 0; } -static struct tun_struct *tun_get_by_name(const char *name) +/* 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) { - struct tun_struct *tun; + int flags = 0; - ASSERT_RTNL(); - list_for_each_entry(tun, &tun_dev_list, list) { - if (!strncmp(tun->dev->name, name, IFNAMSIZ)) - return tun; - } + if (tun->flags & TUN_TUN_DEV) + flags |= IFF_TUN; + else + flags |= IFF_TAP; - return NULL; + if (tun->flags & TUN_NO_PI) + flags |= IFF_NO_PI; + + /* This flag has no real effect. We track the value for backwards + * compatibility. + */ + if (tun->flags & TUN_ONE_QUEUE) + flags |= IFF_ONE_QUEUE; + + if (tun->flags & TUN_VNET_HDR) + flags |= IFF_VNET_HDR; + + if (tun->flags & TUN_TAP_MQ) + flags |= IFF_MULTI_QUEUE; + + if (tun->flags & TUN_PERSIST) + flags |= IFF_PERSIST; + + 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 int tun_set_iff(struct file *file, struct ifreq *ifr) +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; - tun = tun_get_by_name(ifr->ifr_name); - if (tun) { - if (tun->attached) + if (tfile->detached) + return -EINVAL; + + 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; - /* Check permissions */ - if (((tun->owner != -1 && - current->euid != tun->owner) || - (tun->group != -1 && - current->egid != tun->group)) && - !capable(CAP_NET_ADMIN)) + if (!!(ifr->ifr_flags & IFF_MULTI_QUEUE) != + !!(tun->flags & TUN_TAP_MQ)) + return -EINVAL; + + if (tun_not_capable(tun)) return -EPERM; + err = security_tun_dev_open(tun->security); + if (err < 0) + return err; + + err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER); + if (err < 0) + return err; + + if (tun->flags & TUN_TAP_MQ && + (tun->numqueues + tun->numdisabled > 1)) { + /* One or more queue has already been attached, no need + * to initialize the device again. + */ + return 0; + } } - else if (__dev_get_by_name(&init_net, ifr->ifr_name)) - return -EINVAL; else { char *name; unsigned long flags = 0; + int queues = ifr->ifr_flags & IFF_MULTI_QUEUE ? + MAX_TAP_QUEUES : 1; - err = -EINVAL; - - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; + err = security_tun_dev_create(); + if (err < 0) + return err; /* Set dev type */ if (ifr->ifr_flags & IFF_TUN) { @@ -490,145 +1627,372 @@ static int tun_set_iff(struct file *file, struct ifreq *ifr) flags |= TUN_TAP_DEV; name = "tap%d"; } else - goto failed; + return -EINVAL; if (*ifr->ifr_name) name = ifr->ifr_name; - dev = alloc_netdev(sizeof(struct tun_struct), name, - tun_setup); + dev = alloc_netdev_mqs(sizeof(struct tun_struct), name, + tun_setup, queues, queues); + if (!dev) return -ENOMEM; + dev_net_set(dev, net); + dev->rtnl_link_ops = &tun_link_ops; + dev->ifindex = tfile->ifindex; + tun = netdev_priv(dev); tun->dev = dev; tun->flags = flags; - /* Be promiscuous by default to maintain previous behaviour. */ - tun->if_flags = IFF_PROMISC; - /* Generate random Ethernet address. */ - *(__be16 *)tun->dev_addr = htons(0x00FF); - get_random_bytes(tun->dev_addr + sizeof(u16), 4); - memset(tun->chr_filter, 0, sizeof tun->chr_filter); + tun->txflt.count = 0; + tun->vnet_hdr_sz = sizeof(struct virtio_net_hdr); - tun_net_init(dev); + tun->filter_attached = false; + tun->sndbuf = tfile->socket.sk->sk_sndbuf; - if (strchr(dev->name, '%')) { - err = dev_alloc_name(dev, dev->name); - if (err < 0) - goto err_free_dev; - } + spin_lock_init(&tun->lock); - err = register_netdevice(tun->dev); + err = security_tun_dev_alloc_security(&tun->security); if (err < 0) goto err_free_dev; - list_add(&tun->list, &tun_dev_list); + tun_net_init(dev); + tun_flow_init(tun); + + dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | + 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 & + ~(NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX); + + INIT_LIST_HEAD(&tun->disabled); + err = tun_attach(tun, file, false); + if (err < 0) + goto err_free_flow; + + err = register_netdevice(tun->dev); + if (err < 0) + goto err_detach; + + 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"); } - DBG(KERN_INFO "%s: tun_set_iff\n", tun->dev->name); + netif_carrier_on(tun->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; + /* This flag has no real effect. We track the value for backwards + * compatibility. + */ if (ifr->ifr_flags & IFF_ONE_QUEUE) tun->flags |= TUN_ONE_QUEUE; else tun->flags &= ~TUN_ONE_QUEUE; - file->private_data = tun; - tun->attached = 1; + 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: +err_detach: + tun_detach_all(dev); +err_free_flow: + tun_flow_uninit(tun); + security_tun_dev_free_security(tun->security); +err_free_dev: free_netdev(dev); - failed: return err; } -static int tun_chr_ioctl(struct inode *inode, struct file *file, - unsigned int cmd, unsigned long arg) +static void tun_get_iff(struct net *net, struct tun_struct *tun, + struct ifreq *ifr) { - struct tun_struct *tun = file->private_data; + tun_debug(KERN_INFO, tun, "tun_get_iff\n"); + + strcpy(ifr->ifr_name, tun->dev->name); + + ifr->ifr_flags = tun_flags(tun); + +} + +/* 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 = rtnl_dereference(tun->tfiles[i]); + 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 = rtnl_dereference(tun->tfiles[i]); + 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 = rtnl_dereference(tun->tfiles[i]); + 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; + int ret = 0; + + rtnl_lock(); + + if (ifr->ifr_flags & IFF_ATTACH_QUEUE) { + tun = tfile->detached; + if (!tun) { + ret = -EINVAL; + goto unlock; + } + ret = security_tun_dev_attach_queue(tun->security); + if (ret < 0) + goto unlock; + ret = tun_attach(tun, file, false); + } else if (ifr->ifr_flags & IFF_DETACH_QUEUE) { + tun = rtnl_dereference(tfile->tun); + if (!tun || !(tun->flags & TUN_TAP_MQ) || tfile->detached) + ret = -EINVAL; + else + __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; - DECLARE_MAC_BUF(mac); + kuid_t owner; + kgid_t group; + int sndbuf; + int vnet_hdr_sz; + unsigned int ifindex; + int ret; - if (cmd == TUNSETIFF || _IOC_TYPE(cmd) == 0x89) - if (copy_from_user(&ifr, argp, sizeof ifr)) + 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) { - int err; - ifr.ifr_name[IFNAMSIZ-1] = '\0'; - rtnl_lock(); - err = tun_set_iff(file, &ifr); - rtnl_unlock(); + ret = tun_set_iff(tfile->net, file, &ifr); - if (err) - return err; + if (ret) + goto unlock; - if (copy_to_user(argp, &ifr, sizeof(ifr))) - return -EFAULT; - return 0; + if (copy_to_user(argp, &ifr, ifreq_len)) + ret = -EFAULT; + goto unlock; + } + if (cmd == TUNSETIFINDEX) { + ret = -EPERM; + if (tun) + goto unlock; + + ret = -EFAULT; + if (copy_from_user(&ifindex, argp, sizeof(ifindex))) + goto unlock; + + ret = 0; + tfile->ifindex = ifindex; + goto unlock; } + ret = -EBADFD; if (!tun) - return -EBADFD; + goto unlock; - DBG(KERN_INFO "%s: tun_chr_ioctl cmd %d\n", tun->dev->name, cmd); + tun_debug(KERN_INFO, tun, "tun_chr_ioctl cmd %u\n", cmd); + ret = 0; switch (cmd) { + case TUNGETIFF: + tun_get_iff(current->nsproxy->net_ns, tun, &ifr); + + if (tfile->detached) + ifr.ifr_flags |= IFF_DETACH_QUEUE; + if (!tfile->socket.sk->sk_filter) + ifr.ifr_flags |= IFF_NOFILTER; + + if (copy_to_user(argp, &ifr, ifreq_len)) + ret = -EFAULT; + break; + case TUNSETNOCSUM: /* Disable/Enable checksum */ - if (arg) - tun->flags |= TUN_NOCHECKSUM; - else - tun->flags &= ~TUN_NOCHECKSUM; - DBG(KERN_INFO "%s: checksum %s\n", - tun->dev->name, arg ? "disabled" : "enabled"); + /* [unimplemented] */ + tun_debug(KERN_INFO, tun, "ignored: set checksum %s\n", + arg ? "disabled" : "enabled"); break; case TUNSETPERSIST: - /* Disable/Enable persist mode */ - if (arg) + /* Disable/Enable persist mode. Keep an extra reference to the + * module to prevent the module being unprobed. + */ + if (arg && !(tun->flags & TUN_PERSIST)) { tun->flags |= TUN_PERSIST; - else + __module_get(THIS_MODULE); + } + if (!arg && (tun->flags & TUN_PERSIST)) { tun->flags &= ~TUN_PERSIST; + module_put(THIS_MODULE); + } - DBG(KERN_INFO "%s: persist %s\n", - tun->dev->name, arg ? "enabled" : "disabled"); + tun_debug(KERN_INFO, tun, "persist %s\n", + arg ? "enabled" : "disabled"); break; case TUNSETOWNER: /* Set owner of the device */ - tun->owner = (uid_t) arg; - - DBG(KERN_INFO "%s: owner set to %d\n", tun->dev->name, tun->owner); + 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 */ - tun->group= (gid_t) arg; - - DBG(KERN_INFO "%s: group set to %d\n", tun->dev->name, tun->group); + 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) { - DBG(KERN_INFO "%s: Linktype set failed because interface is up\n", - tun->dev->name); - return -EBUSY; + tun_debug(KERN_INFO, tun, + "Linktype set failed because interface is up\n"); + ret = -EBUSY; } else { tun->dev->type = (int) arg; - DBG(KERN_INFO "%s: linktype set to %d\n", tun->dev->name, tun->dev->type); + tun_debug(KERN_INFO, tun, "linktype set to %d\n", + tun->dev->type); + ret = 0; } break; @@ -637,136 +2001,234 @@ static int tun_chr_ioctl(struct inode *inode, struct file *file, tun->debug = arg; break; #endif + case TUNSETOFFLOAD: + ret = set_offload(tun, arg); + break; - case SIOCGIFFLAGS: - ifr.ifr_flags = tun->if_flags; - if (copy_to_user( argp, &ifr, sizeof ifr)) - return -EFAULT; - return 0; - - case SIOCSIFFLAGS: - /** Set the character device's interface flags. Currently only - * IFF_PROMISC and IFF_ALLMULTI are used. */ - tun->if_flags = ifr.ifr_flags; - DBG(KERN_INFO "%s: interface flags 0x%lx\n", - tun->dev->name, tun->if_flags); - return 0; + 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: - /* Note: the actual net device's address may be different */ - memcpy(ifr.ifr_hwaddr.sa_data, tun->dev_addr, - min(sizeof ifr.ifr_hwaddr.sa_data, sizeof tun->dev_addr)); - if (copy_to_user( argp, &ifr, sizeof ifr)) - return -EFAULT; - return 0; + /* 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: - { - /* try to set the actual net device's hw address */ - int ret; + /* Set hw address */ + tun_debug(KERN_DEBUG, tun, "set hw address: %pM\n", + ifr.ifr_hwaddr.sa_data); - rtnl_lock(); ret = dev_set_mac_address(tun->dev, &ifr.ifr_hwaddr); - rtnl_unlock(); - - if (ret == 0) { - /** Set the character device's hardware address. This is used when - * filtering packets being sent from the network device to the character - * device. */ - memcpy(tun->dev_addr, ifr.ifr_hwaddr.sa_data, - min(sizeof ifr.ifr_hwaddr.sa_data, sizeof tun->dev_addr)); - DBG(KERN_DEBUG "%s: set hardware address: %x:%x:%x:%x:%x:%x\n", - tun->dev->name, - tun->dev_addr[0], tun->dev_addr[1], tun->dev_addr[2], - tun->dev_addr[3], tun->dev_addr[4], tun->dev_addr[5]); + 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; } - return ret; + 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; + + case TUNGETFILTER: + ret = -EINVAL; + if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV) + break; + ret = -EFAULT; + if (copy_to_user(argp, &tun->fprog, sizeof(tun->fprog))) + break; + ret = 0; + break; + + default: + ret = -EINVAL; + break; } - case SIOCADDMULTI: - /** Add the specified group to the character device's multicast filter - * list. */ - add_multi(tun->chr_filter, ifr.ifr_hwaddr.sa_data); - DBG(KERN_DEBUG "%s: add multi: %s\n", - tun->dev->name, print_mac(mac, ifr.ifr_hwaddr.sa_data)); - return 0; +unlock: + rtnl_unlock(); + if (tun) + tun_put(tun); + return ret; +} - case SIOCDELMULTI: - /** Remove the specified group from the character device's multicast - * filter list. */ - del_multi(tun->chr_filter, ifr.ifr_hwaddr.sa_data); - DBG(KERN_DEBUG "%s: del multi: %s\n", - tun->dev->name, print_mac(mac, ifr.ifr_hwaddr.sa_data)); - return 0; +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: - return -EINVAL; - }; + arg = (compat_ulong_t)arg; + break; + } - return 0; + /* + * 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_struct *tun = file->private_data; + struct tun_file *tfile = file->private_data; int ret; - if (!tun) - return -EBADFD; - - DBG(KERN_INFO "%s: tun_chr_fasync %d\n", tun->dev->name, on); - - if ((ret = fasync_helper(fd, file, on, &tun->fasync)) < 0) - return 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) - return ret; - tun->flags |= TUN_FASYNC; + goto out; + tfile->flags |= TUN_FASYNC; } else - tun->flags &= ~TUN_FASYNC; - - return 0; + tfile->flags &= ~TUN_FASYNC; + ret = 0; +out: + return ret; } static int tun_chr_open(struct inode *inode, struct file * file) { - DBG1(KERN_INFO "tunX: tun_chr_open\n"); - file->private_data = NULL; + 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_INIT_POINTER(tfile->tun, NULL); + tfile->net = get_net(current->nsproxy->net_ns); + tfile->flags = 0; + tfile->ifindex = 0; + + init_waitqueue_head(&tfile->wq.wait); + RCU_INIT_POINTER(tfile->socket.wq, &tfile->wq); + + 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); + INIT_LIST_HEAD(&tfile->next); + + sock_set_flag(&tfile->sk, SOCK_ZEROCOPY); + return 0; } static int tun_chr_close(struct inode *inode, struct file *file) { - struct tun_struct *tun = file->private_data; - - if (!tun) - return 0; - - DBG(KERN_INFO "%s: tun_chr_close\n", tun->dev->name); - - tun_chr_fasync(-1, file, 0); + struct tun_file *tfile = file->private_data; + struct net *net = tfile->net; - rtnl_lock(); + tun_detach(tfile, true); + put_net(net); - /* Detach from net device */ - file->private_data = NULL; - tun->attached = 0; + return 0; +} - /* Drop read queue */ - skb_queue_purge(&tun->readq); +#ifdef CONFIG_PROC_FS +static int tun_chr_show_fdinfo(struct seq_file *m, struct file *f) +{ + struct tun_struct *tun; + struct ifreq ifr; - if (!(tun->flags & TUN_PERSIST)) { - list_del(&tun->list); - unregister_netdevice(tun->dev); - } + memset(&ifr, 0, sizeof(ifr)); + rtnl_lock(); + tun = tun_get(f); + if (tun) + tun_get_iff(current->nsproxy->net_ns, tun, &ifr); rtnl_unlock(); - return 0; + 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, @@ -776,15 +2238,22 @@ static const struct file_operations tun_fops = { .write = do_sync_write, .aio_write = tun_chr_aio_write, .poll = tun_chr_poll, - .ioctl = tun_chr_ioctl, + .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 + .fasync = tun_chr_fasync, +#ifdef CONFIG_PROC_FS + .show_fdinfo = tun_chr_show_fdinfo, +#endif }; static struct miscdevice tun_miscdev = { .minor = TUN_MINOR, .name = "tun", + .nodename = "net/tun", .fops = &tun_fops, }; @@ -794,7 +2263,7 @@ static int tun_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) { cmd->supported = 0; cmd->advertising = 0; - cmd->speed = SPEED_10; + ethtool_cmd_speed_set(cmd, SPEED_10); cmd->duplex = DUPLEX_FULL; cmd->port = PORT_TP; cmd->phy_address = 0; @@ -809,16 +2278,15 @@ static void tun_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info { struct tun_struct *tun = netdev_priv(dev); - strcpy(info->driver, DRV_NAME); - strcpy(info->version, DRV_VERSION); - strcpy(info->fw_version, "N/A"); + 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: - strcpy(info->bus_info, "tun"); + strlcpy(info->bus_info, "tun", sizeof(info->bus_info)); break; case TUN_TAP_DEV: - strcpy(info->bus_info, "tap"); + strlcpy(info->bus_info, "tap", sizeof(info->bus_info)); break; } } @@ -841,65 +2309,62 @@ static void tun_set_msglevel(struct net_device *dev, u32 value) #endif } -static u32 tun_get_link(struct net_device *dev) -{ - struct tun_struct *tun = netdev_priv(dev); - return tun->attached; -} - -static u32 tun_get_rx_csum(struct net_device *dev) -{ - struct tun_struct *tun = netdev_priv(dev); - return (tun->flags & TUN_NOCHECKSUM) == 0; -} - -static int tun_set_rx_csum(struct net_device *dev, u32 data) -{ - struct tun_struct *tun = netdev_priv(dev); - if (data) - tun->flags &= ~TUN_NOCHECKSUM; - else - tun->flags |= TUN_NOCHECKSUM; - return 0; -} - 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 = tun_get_link, - .get_rx_csum = tun_get_rx_csum, - .set_rx_csum = tun_set_rx_csum + .get_link = ethtool_op_get_link, + .get_ts_info = ethtool_op_get_ts_info, }; + static int __init tun_init(void) { int ret = 0; - printk(KERN_INFO "tun: %s, %s\n", DRV_DESCRIPTION, DRV_VERSION); - printk(KERN_INFO "tun: %s\n", DRV_COPYRIGHT); + 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) - printk(KERN_ERR "tun: Can't register misc device %d\n", TUN_MINOR); + 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) { - struct tun_struct *tun, *nxt; - misc_deregister(&tun_miscdev); + rtnl_link_unregister(&tun_link_ops); +} - rtnl_lock(); - list_for_each_entry_safe(tun, nxt, &tun_dev_list, list) { - DBG(KERN_INFO "%s cleaned up\n", tun->dev->name); - unregister_netdevice(tun->dev); - } - rtnl_unlock(); - +/* 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); @@ -907,3 +2372,4 @@ MODULE_DESCRIPTION(DRV_DESCRIPTION); MODULE_AUTHOR(DRV_COPYRIGHT); MODULE_LICENSE("GPL"); MODULE_ALIAS_MISCDEV(TUN_MINOR); +MODULE_ALIAS("devname:net/tun"); |