To compile this driver as a module, choose M here: the module
will be called vxlan.
+config GENEVE
+ tristate "Generic Network Virtualization Encapsulation netdev"
+ depends on INET && GENEVE_CORE
+ select NET_IP_TUNNEL
+ ---help---
+ This allows one to create geneve virtual interfaces that provide
+ Layer 2 Networks over Layer 3 Networks. GENEVE is often used
+ to tunnel virtual network infrastructure in virtualized environments.
+ For more information see:
+ http://tools.ietf.org/html/draft-gross-geneve-02
+
+ To compile this driver as a module, choose M here: the module
+ will be called geneve.
+
config NETCONSOLE
tristate "Network console logging support"
---help---
If you don't know what to use this for, you don't need it.
+ config TUN_VNET_CROSS_LE
+ bool "Support for cross-endian vnet headers on little-endian kernels"
+ default n
+ ---help---
+ This option allows TUN/TAP and MACVTAP device drivers in a
+ little-endian kernel to parse vnet headers that come from a
+ big-endian legacy virtio device.
+
+ Userspace programs can control the feature using the TUNSETVNETBE
+ and TUNGETVNETBE ioctls.
+
+ Unless you have a little-endian system hosting a big-endian virtual
+ machine with a legacy virtio NIC, you should say N.
+
config VETH
tristate "Virtual ethernet pair device"
---help---
#define MACVTAP_FEATURES (IFF_VNET_HDR | IFF_MULTI_QUEUE)
#define MACVTAP_VNET_LE 0x80000000
+ #define MACVTAP_VNET_BE 0x40000000
+
+ #ifdef CONFIG_TUN_VNET_CROSS_LE
+ static inline bool macvtap_legacy_is_little_endian(struct macvtap_queue *q)
+ {
+ return q->flags & MACVTAP_VNET_BE ? false :
+ virtio_legacy_is_little_endian();
+ }
+
+ static long macvtap_get_vnet_be(struct macvtap_queue *q, int __user *sp)
+ {
+ int s = !!(q->flags & MACVTAP_VNET_BE);
+
+ if (put_user(s, sp))
+ return -EFAULT;
+
+ return 0;
+ }
+
+ static long macvtap_set_vnet_be(struct macvtap_queue *q, int __user *sp)
+ {
+ int s;
+
+ if (get_user(s, sp))
+ return -EFAULT;
+
+ if (s)
+ q->flags |= MACVTAP_VNET_BE;
+ else
+ q->flags &= ~MACVTAP_VNET_BE;
+
+ return 0;
+ }
+ #else
+ static inline bool macvtap_legacy_is_little_endian(struct macvtap_queue *q)
+ {
+ return virtio_legacy_is_little_endian();
+ }
+
+ static long macvtap_get_vnet_be(struct macvtap_queue *q, int __user *argp)
+ {
+ return -EINVAL;
+ }
+
+ static long macvtap_set_vnet_be(struct macvtap_queue *q, int __user *argp)
+ {
+ return -EINVAL;
+ }
+ #endif /* CONFIG_TUN_VNET_CROSS_LE */
+
+ static inline bool macvtap_is_little_endian(struct macvtap_queue *q)
+ {
+ return q->flags & MACVTAP_VNET_LE ||
+ macvtap_legacy_is_little_endian(q);
+ }
static inline u16 macvtap16_to_cpu(struct macvtap_queue *q, __virtio16 val)
{
- return __virtio16_to_cpu(q->flags & MACVTAP_VNET_LE, val);
+ return __virtio16_to_cpu(macvtap_is_little_endian(q), val);
}
static inline __virtio16 cpu_to_macvtap16(struct macvtap_queue *q, u16 val)
{
- return __cpu_to_virtio16(q->flags & MACVTAP_VNET_LE, val);
+ return __cpu_to_virtio16(macvtap_is_little_endian(q), val);
}
static struct proto macvtap_proto = {
static void macvtap_del_queues(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
- struct macvtap_queue *q, *tmp, *qlist[MAX_MACVTAP_QUEUES];
- int i, j = 0;
+ struct macvtap_queue *q, *tmp;
ASSERT_RTNL();
list_for_each_entry_safe(q, tmp, &vlan->queue_list, next) {
list_del_init(&q->next);
- qlist[j++] = q;
RCU_INIT_POINTER(q->vlan, NULL);
if (q->enabled)
vlan->numvtaps--;
vlan->numqueues--;
+ sock_put(&q->sk);
}
- for (i = 0; i < vlan->numvtaps; i++)
- RCU_INIT_POINTER(vlan->taps[i], NULL);
BUG_ON(vlan->numvtaps);
BUG_ON(vlan->numqueues);
/* guarantee that any future macvtap_set_queue will fail */
vlan->numvtaps = MAX_MACVTAP_QUEUES;
-
- for (--j; j >= 0; j--)
- sock_put(&qlist[j]->sk);
}
static rx_handler_result_t macvtap_handle_frame(struct sk_buff **pskb)
err = -ENOMEM;
q = (struct macvtap_queue *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL,
- &macvtap_proto);
+ &macvtap_proto, 0);
if (!q)
goto out;
unsigned int __user *up = argp;
unsigned short u;
int __user *sp = argp;
+ struct sockaddr sa;
int s;
int ret;
q->flags &= ~MACVTAP_VNET_LE;
return 0;
+ case TUNGETVNETBE:
+ return macvtap_get_vnet_be(q, sp);
+
+ case TUNSETVNETBE:
+ return macvtap_set_vnet_be(q, sp);
+
case TUNSETOFFLOAD:
/* let the user check for future flags */
if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 |
rtnl_unlock();
return ret;
+ case SIOCGIFHWADDR:
+ rtnl_lock();
+ vlan = macvtap_get_vlan(q);
+ if (!vlan) {
+ rtnl_unlock();
+ return -ENOLINK;
+ }
+ ret = 0;
+ u = vlan->dev->type;
+ if (copy_to_user(&ifr->ifr_name, vlan->dev->name, IFNAMSIZ) ||
+ copy_to_user(&ifr->ifr_hwaddr.sa_data, vlan->dev->dev_addr, ETH_ALEN) ||
+ put_user(u, &ifr->ifr_hwaddr.sa_family))
+ ret = -EFAULT;
+ macvtap_put_vlan(vlan);
+ rtnl_unlock();
+ return ret;
+
+ case SIOCSIFHWADDR:
+ if (copy_from_user(&sa, &ifr->ifr_hwaddr, sizeof(sa)))
+ return -EFAULT;
+ rtnl_lock();
+ vlan = macvtap_get_vlan(q);
+ if (!vlan) {
+ rtnl_unlock();
+ return -ENOLINK;
+ }
+ ret = dev_set_mac_address(vlan->dev, &sa);
+ macvtap_put_vlan(vlan);
+ rtnl_unlock();
+ return ret;
+
default:
return -EINVAL;
}
#define TUN_FASYNC IFF_ATTACH_QUEUE
/* High bits in flags field are unused. */
#define TUN_VNET_LE 0x80000000
+ #define TUN_VNET_BE 0x40000000
#define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \
IFF_MULTI_QUEUE)
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;
u32 flow_count;
};
+ #ifdef CONFIG_TUN_VNET_CROSS_LE
+ static inline bool tun_legacy_is_little_endian(struct tun_struct *tun)
+ {
+ return tun->flags & TUN_VNET_BE ? false :
+ virtio_legacy_is_little_endian();
+ }
+
+ static long tun_get_vnet_be(struct tun_struct *tun, int __user *argp)
+ {
+ int be = !!(tun->flags & TUN_VNET_BE);
+
+ if (put_user(be, argp))
+ return -EFAULT;
+
+ return 0;
+ }
+
+ static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp)
+ {
+ int be;
+
+ if (get_user(be, argp))
+ return -EFAULT;
+
+ if (be)
+ tun->flags |= TUN_VNET_BE;
+ else
+ tun->flags &= ~TUN_VNET_BE;
+
+ return 0;
+ }
+ #else
+ static inline bool tun_legacy_is_little_endian(struct tun_struct *tun)
+ {
+ return virtio_legacy_is_little_endian();
+ }
+
+ static long tun_get_vnet_be(struct tun_struct *tun, int __user *argp)
+ {
+ return -EINVAL;
+ }
+
+ static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp)
+ {
+ return -EINVAL;
+ }
+ #endif /* CONFIG_TUN_VNET_CROSS_LE */
+
+ static inline bool tun_is_little_endian(struct tun_struct *tun)
+ {
+ return tun->flags & TUN_VNET_LE ||
+ tun_legacy_is_little_endian(tun);
+ }
+
static inline u16 tun16_to_cpu(struct tun_struct *tun, __virtio16 val)
{
- return __virtio16_to_cpu(tun->flags & TUN_VNET_LE, val);
+ return __virtio16_to_cpu(tun_is_little_endian(tun), val);
}
static inline __virtio16 cpu_to_tun16(struct tun_struct *tun, u16 val)
{
- return __cpu_to_virtio16(tun->flags & TUN_VNET_LE, val);
+ return __cpu_to_virtio16(tun_is_little_endian(tun), val);
}
static inline u32 tun_hashfn(u32 rxhash)
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);
+ sock_put(&tfile->sk);
}
}
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 = {
if (cmd == TUNSETIFF && !tun) {
ifr.ifr_name[IFNAMSIZ-1] = '\0';
- ret = tun_set_iff(tfile->net, file, &ifr);
+ ret = tun_set_iff(sock_net(&tfile->sk), file, &ifr);
if (ret)
goto unlock;
tun->flags &= ~TUN_VNET_LE;
break;
+ case TUNGETVNETBE:
+ ret = tun_get_vnet_be(tun, argp);
+ break;
+
+ case TUNSETVNETBE:
+ ret = tun_set_vnet_be(tun, argp);
+ break;
+
case TUNATTACHFILTER:
/* Can be set only for TAPs */
ret = -EINVAL;
static int tun_chr_open(struct inode *inode, struct file * file)
{
+ struct net *net = current->nsproxy->net_ns;
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);
+ tfile = (struct tun_file *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL,
+ &tun_proto, 0);
if (!tfile)
return -ENOMEM;
RCU_INIT_POINTER(tfile->tun, NULL);
- tfile->net = get_net(current->nsproxy->net_ns);
tfile->flags = 0;
tfile->ifindex = 0;
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);
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;
}
if (cpu == -1)
irq_set_affinity_hint(irq, NULL);
else {
+ cpumask_clear(mask);
cpumask_set_cpu(cpu, mask);
irq_set_affinity_hint(irq, mask);
}
INIT_LIST_HEAD(&vp_dev->virtqueues);
spin_lock_init(&vp_dev->lock);
- /* Disable MSI/MSIX to bring device to a known good state. */
- pci_msi_off(pci_dev);
-
/* enable the device */
rc = pci_enable_device(pci_dev);
if (rc)
goto err_enable_device;
- rc = pci_request_regions(pci_dev, "virtio-pci");
- if (rc)
- goto err_request_regions;
-
if (force_legacy) {
rc = virtio_pci_legacy_probe(vp_dev);
/* Also try modern mode if we can't map BAR0 (no IO space). */
else
virtio_pci_modern_remove(vp_dev);
err_probe:
- pci_release_regions(pci_dev);
- err_request_regions:
pci_disable_device(pci_dev);
err_enable_device:
kfree(vp_dev);
else
virtio_pci_modern_remove(vp_dev);
- pci_release_regions(pci_dev);
pci_disable_device(pci_dev);
}