path: root/drivers/net/macvtap.c

#include <linux/etherdevice.h>
#include <linux/if_macvlan.h>
#include <linux/interrupt.h>
#include <linux/nsproxy.h>
#include <linux/compat.h>
#include <linux/if_tun.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/cache.h>
#include <linux/sched.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/wait.h>
#include <linux/cdev.h>
#include <linux/fs.h>

#include <net/net_namespace.h>
#include <net/rtnetlink.h>
#include <net/sock.h>
#include <linux/virtio_net.h>

/*
 * A macvtap queue is the central object of this driver, it connects
 * an open character device to a macvlan interface. There can be
 * multiple queues on one interface, which map back to queues
 * implemented in hardware on the underlying device.
 *
 * macvtap_proto is used to allocate queues through the sock allocation
 * mechanism.
 *
 * TODO: multiqueue support is currently not implemented, even though
 * macvtap is basically prepared for that. We will need to add this
 * here as well as in virtio-net and qemu to get line rate on 10gbit
 * adapters from a guest.
 */
struct macvtap_queue {
	struct sock sk;
	struct socket sock;
	struct socket_wq wq;
	int vnet_hdr_sz;
	struct macvlan_dev __rcu *vlan;
	struct file *file;
	unsigned int flags;
};

static struct proto macvtap_proto = {
	.name = "macvtap",
	.owner = THIS_MODULE,
	.obj_size = sizeof (struct macvtap_queue),
};

/*
 * Variables for dealing with macvtaps device numbers.
 */
static dev_t macvtap_major;
#define MACVTAP_NUM_DEVS (1U << MINORBITS)
static DEFINE_MUTEX(minor_lock);
static DEFINE_IDR(minor_idr);

#define GOODCOPY_LEN 128
static struct class *macvtap_class;
static struct cdev macvtap_cdev;

static const struct proto_ops macvtap_socket_ops;

/*
 * RCU usage:
 * The macvtap_queue and the macvlan_dev are loosely coupled, the
 * pointers from one to the other can only be read while rcu_read_lock
 * or macvtap_lock is held.
 *
 * Both the file and the macvlan_dev hold a reference on the macvtap_queue
 * through sock_hold(&q->sk). When the macvlan_dev goes away first,
 * q->vlan becomes inaccessible. When the files gets closed,
 * macvtap_get_queue() fails.
 *
 * There may still be references to the struct sock inside of the
 * queue from outbound SKBs, but these never reference back to the
 * file or the dev. The data structure is freed through __sk_free
 * when both our references and any pending SKBs are gone.
 */
static DEFINE_SPINLOCK(macvtap_lock);

/*
 * get_slot: return a [unused/occupied] slot in vlan->taps[]:
 *	- if 'q' is NULL, return the first empty slot;
 *	- otherwise, return the slot this pointer occupies.
 */
static int get_slot(struct macvlan_dev *vlan, struct macvtap_queue *q)
{
	int i;

	for (i = 0; i < MAX_MACVTAP_QUEUES; i++) {
		if (rcu_dereference(vlan->taps[i]) == q)
			return i;
	}

	/* Should never happen */
	BUG_ON(1);
}

static int macvtap_set_queue(struct net_device *dev, struct file *file,
				struct macvtap_queue *q)
{
	struct macvlan_dev *vlan = netdev_priv(dev);
	int index;
	int err = -EBUSY;

	spin_lock(&macvtap_lock);
	if (vlan->numvtaps == MAX_MACVTAP_QUEUES)
		goto out;

	err = 0;
	index = get_slot(vlan, NULL);
	rcu_assign_pointer(q->vlan, vlan);
	rcu_assign_pointer(vlan->taps[index], q);
	sock_hold(&q->sk);

	q->file = file;
	file->private_data = q;

	vlan->numvtaps++;

out:
	spin_unlock(&macvtap_lock);
	return err;
}

/*
 * The file owning the queue got closed, give up both
 * the reference that the files holds as well as the
 * one from the macvlan_dev if that still exists.
 *
 * Using the spinlock makes sure that we don't get
 * to the queue again after destroying it.
 */
static void macvtap_put_queue(struct macvtap_queue *q)
{
	struct macvlan_dev *vlan;

	spin_lock(&macvtap_lock);
	vlan = rcu_dereference_protected(q->vlan,
					 lockdep_is_held(&macvtap_lock));
	if (vlan) {
		int index = get_slot(vlan, q);

		rcu_assign_pointer(vlan->taps[index], NULL);
		rcu_assign_pointer(q->vlan, NULL);
		sock_put(&q->sk);
		--vlan->numvtaps;
	}

	spin_unlock(&macvtap_lock);

	synchronize_rcu();
	sock_put(&q->sk);
}

/*
 * Select a queue based on the rxq of the device on which this packet
 * arrived. If the incoming device is not mq, calculate a flow hash
 * to select a queue. If all fails, find the first available queue.