WSL2-Linux-Kernel/drivers/net/macvtap.c

1163 строки
28 KiB
C
Исходник Обычный вид История

#include <linux/etherdevice.h>
#include <linux/if_macvlan.h>
#include <linux/if_vlan.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 cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 11:04:11 +03:00
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/wait.h>
#include <linux/cdev.h>
#include <linux/idr.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;
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 15:01:49 +04:00
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_protected(vlan->taps[i],
lockdep_is_held(&macvtap_lock)) == 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_INIT_POINTER(vlan->taps[index], NULL);
RCU_INIT_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.
* Cache vlan->numvtaps since it can become zero during the execution
* of this function.
*/
static struct macvtap_queue *macvtap_get_queue(struct net_device *dev,
struct sk_buff *skb)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct macvtap_queue *tap = NULL;
int numvtaps = vlan->numvtaps;
__u32 rxq;
if (!numvtaps)
goto out;
/* Check if we can use flow to select a queue */
rxq = skb_get_rxhash(skb);
if (rxq) {
tap = rcu_dereference(vlan->taps[rxq % numvtaps]);
if (tap)
goto out;
}
if (likely(skb_rx_queue_recorded(skb))) {
rxq = skb_get_rx_queue(skb);
while (unlikely(rxq >= numvtaps))
rxq -= numvtaps;
tap = rcu_dereference(vlan->taps[rxq]);
if (tap)
goto out;
}
/* Everything failed - find first available queue */
for (rxq = 0; rxq < MAX_MACVTAP_QUEUES; rxq++) {
tap = rcu_dereference(vlan->taps[rxq]);
if (tap)
break;
}
out:
return tap;
}
/*
* The net_device is going away, give up the reference
* that it holds on all queues and safely set the pointer
* from the queues to NULL.
*/
static void macvtap_del_queues(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct macvtap_queue *q, *qlist[MAX_MACVTAP_QUEUES];
int i, j = 0;
/* macvtap_put_queue can free some slots, so go through all slots */
spin_lock(&macvtap_lock);
for (i = 0; i < MAX_MACVTAP_QUEUES && vlan->numvtaps; i++) {
q = rcu_dereference_protected(vlan->taps[i],
lockdep_is_held(&macvtap_lock));
if (q) {
qlist[j++] = q;
RCU_INIT_POINTER(vlan->taps[i], NULL);
RCU_INIT_POINTER(q->vlan, NULL);
vlan->numvtaps--;
}
}
BUG_ON(vlan->numvtaps != 0);
/* guarantee that any future macvtap_set_queue will fail */
vlan->numvtaps = MAX_MACVTAP_QUEUES;
spin_unlock(&macvtap_lock);
synchronize_rcu();
for (--j; j >= 0; j--)
sock_put(&qlist[j]->sk);
}
/*
* Forward happens for data that gets sent from one macvlan
* endpoint to another one in bridge mode. We just take
* the skb and put it into the receive queue.
*/
static int macvtap_forward(struct net_device *dev, struct sk_buff *skb)
{
struct macvtap_queue *q = macvtap_get_queue(dev, skb);
if (!q)
macvtap: Limit packet queue length Mark Wagner reported OOM symptoms when sending UDP traffic over a macvtap link to a kvm receiver. This appears to be caused by the fact that macvtap packet queues are unlimited in length. This means that if the receiver can't keep up with the rate of flow, then we will hit OOM. Of course it gets worse if the OOM killer then decides to kill the receiver. This patch imposes a cap on the packet queue length, in the same way as the tuntap driver, using the device TX queue length. Please note that macvtap currently has no way of giving congestion notification, that means the software device TX queue cannot be used and packets will always be dropped once the macvtap driver queue fills up. This shouldn't be a great problem for the scenario where macvtap is used to feed a kvm receiver, as the traffic is most likely external in origin so congestion notification can't be applied anyway. Of course, if anybody decides to complain about guest-to-guest UDP packet loss down the track, then we may have to revisit this. Incidentally, this patch also fixes a real memory leak when macvtap_get_queue fails. Chris Wright noticed that for this patch to work, we need a non-zero TX queue length. This patch includes his work to change the default macvtap TX queue length to 500. Reported-by: Mark Wagner <mwagner@redhat.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Acked-by: Chris Wright <chrisw@sous-sol.org> Acked-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-22 01:44:31 +04:00
goto drop;
if (skb_queue_len(&q->sk.sk_receive_queue) >= dev->tx_queue_len)
goto drop;
skb_queue_tail(&q->sk.sk_receive_queue, skb);
wake_up_interruptible_poll(sk_sleep(&q->sk), POLLIN | POLLRDNORM | POLLRDBAND);
macvtap: Limit packet queue length Mark Wagner reported OOM symptoms when sending UDP traffic over a macvtap link to a kvm receiver. This appears to be caused by the fact that macvtap packet queues are unlimited in length. This means that if the receiver can't keep up with the rate of flow, then we will hit OOM. Of course it gets worse if the OOM killer then decides to kill the receiver. This patch imposes a cap on the packet queue length, in the same way as the tuntap driver, using the device TX queue length. Please note that macvtap currently has no way of giving congestion notification, that means the software device TX queue cannot be used and packets will always be dropped once the macvtap driver queue fills up. This shouldn't be a great problem for the scenario where macvtap is used to feed a kvm receiver, as the traffic is most likely external in origin so congestion notification can't be applied anyway. Of course, if anybody decides to complain about guest-to-guest UDP packet loss down the track, then we may have to revisit this. Incidentally, this patch also fixes a real memory leak when macvtap_get_queue fails. Chris Wright noticed that for this patch to work, we need a non-zero TX queue length. This patch includes his work to change the default macvtap TX queue length to 500. Reported-by: Mark Wagner <mwagner@redhat.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Acked-by: Chris Wright <chrisw@sous-sol.org> Acked-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-22 01:44:31 +04:00
return NET_RX_SUCCESS;
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
/*
* Receive is for data from the external interface (lowerdev),
* in case of macvtap, we can treat that the same way as
* forward, which macvlan cannot.
*/
static int macvtap_receive(struct sk_buff *skb)
{
skb_push(skb, ETH_HLEN);
return macvtap_forward(skb->dev, skb);
}
static int macvtap_get_minor(struct macvlan_dev *vlan)
{
int retval = -ENOMEM;
int id;
mutex_lock(&minor_lock);
if (idr_pre_get(&minor_idr, GFP_KERNEL) == 0)
goto exit;
retval = idr_get_new_above(&minor_idr, vlan, 1, &id);
if (retval < 0) {
if (retval == -EAGAIN)
retval = -ENOMEM;
goto exit;
}
if (id < MACVTAP_NUM_DEVS) {
vlan->minor = id;
} else {
printk(KERN_ERR "too many macvtap devices\n");
retval = -EINVAL;
idr_remove(&minor_idr, id);
}
exit:
mutex_unlock(&minor_lock);
return retval;
}
static void macvtap_free_minor(struct macvlan_dev *vlan)
{
mutex_lock(&minor_lock);
if (vlan->minor) {
idr_remove(&minor_idr, vlan->minor);
vlan->minor = 0;
}
mutex_unlock(&minor_lock);
}
static struct net_device *dev_get_by_macvtap_minor(int minor)
{
struct net_device *dev = NULL;
struct macvlan_dev *vlan;
mutex_lock(&minor_lock);
vlan = idr_find(&minor_idr, minor);
if (vlan) {
dev = vlan->dev;
dev_hold(dev);
}
mutex_unlock(&minor_lock);
return dev;
}
static int macvtap_newlink(struct net *src_net,
struct net_device *dev,
struct nlattr *tb[],
struct nlattr *data[])
{
/* Don't put anything that may fail after macvlan_common_newlink
* because we can't undo what it does.
*/
return macvlan_common_newlink(src_net, dev, tb, data,
macvtap_receive, macvtap_forward);
}
static void macvtap_dellink(struct net_device *dev,
struct list_head *head)
{
macvtap_del_queues(dev);
macvlan_dellink(dev, head);
}
macvtap: Limit packet queue length Mark Wagner reported OOM symptoms when sending UDP traffic over a macvtap link to a kvm receiver. This appears to be caused by the fact that macvtap packet queues are unlimited in length. This means that if the receiver can't keep up with the rate of flow, then we will hit OOM. Of course it gets worse if the OOM killer then decides to kill the receiver. This patch imposes a cap on the packet queue length, in the same way as the tuntap driver, using the device TX queue length. Please note that macvtap currently has no way of giving congestion notification, that means the software device TX queue cannot be used and packets will always be dropped once the macvtap driver queue fills up. This shouldn't be a great problem for the scenario where macvtap is used to feed a kvm receiver, as the traffic is most likely external in origin so congestion notification can't be applied anyway. Of course, if anybody decides to complain about guest-to-guest UDP packet loss down the track, then we may have to revisit this. Incidentally, this patch also fixes a real memory leak when macvtap_get_queue fails. Chris Wright noticed that for this patch to work, we need a non-zero TX queue length. This patch includes his work to change the default macvtap TX queue length to 500. Reported-by: Mark Wagner <mwagner@redhat.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Acked-by: Chris Wright <chrisw@sous-sol.org> Acked-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-22 01:44:31 +04:00
static void macvtap_setup(struct net_device *dev)
{
macvlan_common_setup(dev);
dev->tx_queue_len = TUN_READQ_SIZE;
}
static struct rtnl_link_ops macvtap_link_ops __read_mostly = {
.kind = "macvtap",
macvtap: Limit packet queue length Mark Wagner reported OOM symptoms when sending UDP traffic over a macvtap link to a kvm receiver. This appears to be caused by the fact that macvtap packet queues are unlimited in length. This means that if the receiver can't keep up with the rate of flow, then we will hit OOM. Of course it gets worse if the OOM killer then decides to kill the receiver. This patch imposes a cap on the packet queue length, in the same way as the tuntap driver, using the device TX queue length. Please note that macvtap currently has no way of giving congestion notification, that means the software device TX queue cannot be used and packets will always be dropped once the macvtap driver queue fills up. This shouldn't be a great problem for the scenario where macvtap is used to feed a kvm receiver, as the traffic is most likely external in origin so congestion notification can't be applied anyway. Of course, if anybody decides to complain about guest-to-guest UDP packet loss down the track, then we may have to revisit this. Incidentally, this patch also fixes a real memory leak when macvtap_get_queue fails. Chris Wright noticed that for this patch to work, we need a non-zero TX queue length. This patch includes his work to change the default macvtap TX queue length to 500. Reported-by: Mark Wagner <mwagner@redhat.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Acked-by: Chris Wright <chrisw@sous-sol.org> Acked-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-22 01:44:31 +04:00
.setup = macvtap_setup,
.newlink = macvtap_newlink,
.dellink = macvtap_dellink,
};
static void macvtap_sock_write_space(struct sock *sk)
{
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 15:01:49 +04:00
wait_queue_head_t *wqueue;
if (!sock_writeable(sk) ||
!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags))
return;
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 15:01:49 +04:00
wqueue = sk_sleep(sk);
if (wqueue && waitqueue_active(wqueue))
wake_up_interruptible_poll(wqueue, POLLOUT | POLLWRNORM | POLLWRBAND);
}
static void macvtap_sock_destruct(struct sock *sk)
{
skb_queue_purge(&sk->sk_receive_queue);
}
static int macvtap_open(struct inode *inode, struct file *file)
{
struct net *net = current->nsproxy->net_ns;
struct net_device *dev = dev_get_by_macvtap_minor(iminor(inode));
struct macvtap_queue *q;
int err;
err = -ENODEV;
if (!dev)
goto out;
err = -ENOMEM;
q = (struct macvtap_queue *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL,
&macvtap_proto);
if (!q)
goto out;
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 15:01:49 +04:00
q->sock.wq = &q->wq;
init_waitqueue_head(&q->wq.wait);
q->sock.type = SOCK_RAW;
q->sock.state = SS_CONNECTED;
q->sock.file = file;
q->sock.ops = &macvtap_socket_ops;
sock_init_data(&q->sock, &q->sk);
q->sk.sk_write_space = macvtap_sock_write_space;
q->sk.sk_destruct = macvtap_sock_destruct;
q->flags = IFF_VNET_HDR | IFF_NO_PI | IFF_TAP;
q->vnet_hdr_sz = sizeof(struct virtio_net_hdr);
/*
* so far only KVM virtio_net uses macvtap, enable zero copy between
* guest kernel and host kernel when lower device supports zerocopy
*
* The macvlan supports zerocopy iff the lower device supports zero
* copy so we don't have to look at the lower device directly.
*/
if ((dev->features & NETIF_F_HIGHDMA) && (dev->features & NETIF_F_SG))
sock_set_flag(&q->sk, SOCK_ZEROCOPY);
err = macvtap_set_queue(dev, file, q);
if (err)
sock_put(&q->sk);
out:
if (dev)
dev_put(dev);
return err;
}
static int macvtap_release(struct inode *inode, struct file *file)
{
struct macvtap_queue *q = file->private_data;
macvtap_put_queue(q);
return 0;
}
static unsigned int macvtap_poll(struct file *file, poll_table * wait)
{
struct macvtap_queue *q = file->private_data;
unsigned int mask = POLLERR;
if (!q)
goto out;
mask = 0;
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 15:01:49 +04:00
poll_wait(file, &q->wq.wait, wait);
if (!skb_queue_empty(&q->sk.sk_receive_queue))
mask |= POLLIN | POLLRDNORM;
if (sock_writeable(&q->sk) ||
(!test_and_set_bit(SOCK_ASYNC_NOSPACE, &q->sock.flags) &&
sock_writeable(&q->sk)))
mask |= POLLOUT | POLLWRNORM;
out:
return mask;
}
static inline struct sk_buff *macvtap_alloc_skb(struct sock *sk, size_t prepad,
size_t len, size_t linear,
int noblock, int *err)
{
struct sk_buff *skb;
/* 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 NULL;
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;
}
/*
* macvtap_skb_from_vnet_hdr and macvtap_skb_to_vnet_hdr should
* be shared with the tun/tap driver.
*/
static int macvtap_skb_from_vnet_hdr(struct sk_buff *skb,
struct virtio_net_hdr *vnet_hdr)
{
unsigned short gso_type = 0;
if (vnet_hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
switch (vnet_hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
case VIRTIO_NET_HDR_GSO_TCPV4:
gso_type = SKB_GSO_TCPV4;
break;
case VIRTIO_NET_HDR_GSO_TCPV6:
gso_type = SKB_GSO_TCPV6;
break;
case VIRTIO_NET_HDR_GSO_UDP:
gso_type = SKB_GSO_UDP;
break;
default:
return -EINVAL;
}
if (vnet_hdr->gso_type & VIRTIO_NET_HDR_GSO_ECN)
gso_type |= SKB_GSO_TCP_ECN;
if (vnet_hdr->gso_size == 0)
return -EINVAL;
}
if (vnet_hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
if (!skb_partial_csum_set(skb, vnet_hdr->csum_start,
vnet_hdr->csum_offset))
return -EINVAL;
}
if (vnet_hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
skb_shinfo(skb)->gso_size = vnet_hdr->gso_size;
skb_shinfo(skb)->gso_type = gso_type;
/* Header must be checked, and gso_segs computed. */
skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
skb_shinfo(skb)->gso_segs = 0;
}
return 0;
}
static int macvtap_skb_to_vnet_hdr(const struct sk_buff *skb,
struct virtio_net_hdr *vnet_hdr)
{
memset(vnet_hdr, 0, sizeof(*vnet_hdr));
if (skb_is_gso(skb)) {
struct skb_shared_info *sinfo = skb_shinfo(skb);
/* This is a hint as to how much should be linear. */
vnet_hdr->hdr_len = skb_headlen(skb);
vnet_hdr->gso_size = sinfo->gso_size;
if (sinfo->gso_type & SKB_GSO_TCPV4)
vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
else if (sinfo->gso_type & SKB_GSO_TCPV6)
vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
else if (sinfo->gso_type & SKB_GSO_UDP)
vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP;
else
BUG();
if (sinfo->gso_type & SKB_GSO_TCP_ECN)
vnet_hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN;
} else
vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE;
if (skb->ip_summed == CHECKSUM_PARTIAL) {
vnet_hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
vnet_hdr->csum_start = skb_checksum_start_offset(skb);
vnet_hdr->csum_offset = skb->csum_offset;
} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
vnet_hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID;
} /* else everything is zero */
return 0;
}
/* Get packet from user space buffer */
static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
const struct iovec *iv, unsigned long total_len,
size_t count, int noblock)
{
struct sk_buff *skb;
struct macvlan_dev *vlan;
unsigned long len = total_len;
int err;
struct virtio_net_hdr vnet_hdr = { 0 };
int vnet_hdr_len = 0;
int copylen = 0;
bool zerocopy = false;
if (q->flags & IFF_VNET_HDR) {
vnet_hdr_len = q->vnet_hdr_sz;
err = -EINVAL;
if (len < vnet_hdr_len)
goto err;
len -= vnet_hdr_len;
err = memcpy_fromiovecend((void *)&vnet_hdr, iv, 0,
sizeof(vnet_hdr));
if (err < 0)
goto err;
if ((vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
vnet_hdr.csum_start + vnet_hdr.csum_offset + 2 >
vnet_hdr.hdr_len)
vnet_hdr.hdr_len = vnet_hdr.csum_start +
vnet_hdr.csum_offset + 2;
err = -EINVAL;
if (vnet_hdr.hdr_len > len)
goto err;
}
err = -EINVAL;
if (unlikely(len < ETH_HLEN))
goto err;
err = -EMSGSIZE;
if (unlikely(count > UIO_MAXIOV))
goto err;
if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY))
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 < vnet_hdr_len)
copylen = 0;
else
copylen -= vnet_hdr_len;
}
/* 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 buffer is mapped from userspace.
*/
if (copylen < vnet_hdr.hdr_len)
copylen = vnet_hdr.hdr_len;
if (!copylen)
copylen = GOODCOPY_LEN;
} else
copylen = len;
skb = macvtap_alloc_skb(&q->sk, NET_IP_ALIGN, copylen,
vnet_hdr.hdr_len, noblock, &err);
if (!skb)
goto err;
if (zerocopy)
err = zerocopy_sg_from_iovec(skb, iv, vnet_hdr_len, count);
else
err = skb_copy_datagram_from_iovec(skb, 0, iv, vnet_hdr_len,
len);
if (err)
goto err_kfree;
skb_set_network_header(skb, ETH_HLEN);
skb_reset_mac_header(skb);
skb->protocol = eth_hdr(skb)->h_proto;
if (vnet_hdr_len) {
err = macvtap_skb_from_vnet_hdr(skb, &vnet_hdr);
if (err)
goto err_kfree;
}
rcu_read_lock_bh();
vlan = rcu_dereference_bh(q->vlan);
/* copy skb_ubuf_info for callback when skb has no error */
if (zerocopy) {
skb_shinfo(skb)->destructor_arg = m->msg_control;
skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
}
if (vlan)
macvlan_start_xmit(skb, vlan->dev);
else
kfree_skb(skb);
rcu_read_unlock_bh();
return total_len;
err_kfree:
kfree_skb(skb);
err:
rcu_read_lock_bh();
vlan = rcu_dereference_bh(q->vlan);
if (vlan)
vlan->dev->stats.tx_dropped++;
rcu_read_unlock_bh();
return err;
}
static ssize_t macvtap_aio_write(struct kiocb *iocb, const struct iovec *iv,
unsigned long count, loff_t pos)
{
struct file *file = iocb->ki_filp;
ssize_t result = -ENOLINK;
struct macvtap_queue *q = file->private_data;
result = macvtap_get_user(q, NULL, iv, iov_length(iv, count), count,
file->f_flags & O_NONBLOCK);
return result;
}
/* Put packet to the user space buffer */
static ssize_t macvtap_put_user(struct macvtap_queue *q,
const struct sk_buff *skb,
const struct iovec *iv, int len)
{
struct macvlan_dev *vlan;
int ret;
int vnet_hdr_len = 0;
int vlan_offset = 0;
int copied;
if (q->flags & IFF_VNET_HDR) {
struct virtio_net_hdr vnet_hdr;
vnet_hdr_len = q->vnet_hdr_sz;
if ((len -= vnet_hdr_len) < 0)
return -EINVAL;
ret = macvtap_skb_to_vnet_hdr(skb, &vnet_hdr);
if (ret)
return ret;
if (memcpy_toiovecend(iv, (void *)&vnet_hdr, 0, sizeof(vnet_hdr)))
return -EFAULT;
}
copied = vnet_hdr_len;
if (!vlan_tx_tag_present(skb))
len = min_t(int, skb->len, len);
else {
int copy;
struct {
__be16 h_vlan_proto;
__be16 h_vlan_TCI;
} veth;
veth.h_vlan_proto = htons(ETH_P_8021Q);
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);
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;
}
ret = skb_copy_datagram_const_iovec(skb, vlan_offset, iv, copied, len);
copied += len;
done:
rcu_read_lock_bh();
vlan = rcu_dereference_bh(q->vlan);
if (vlan)
macvlan_count_rx(vlan, copied - vnet_hdr_len, ret == 0, 0);
rcu_read_unlock_bh();
return ret ? ret : copied;
}
static ssize_t macvtap_do_read(struct macvtap_queue *q, struct kiocb *iocb,
const struct iovec *iv, unsigned long len,
int noblock)
{
DEFINE_WAIT(wait);
struct sk_buff *skb;
ssize_t ret = 0;
while (len) {
prepare_to_wait(sk_sleep(&q->sk), &wait, TASK_INTERRUPTIBLE);
/* Read frames from the queue */
skb = skb_dequeue(&q->sk.sk_receive_queue);
if (!skb) {
if (noblock) {
ret = -EAGAIN;
break;
}
if (signal_pending(current)) {
ret = -ERESTARTSYS;
break;
}
/* Nothing to read, let's sleep */
schedule();
continue;
}
ret = macvtap_put_user(q, skb, iv, len);
kfree_skb(skb);
break;
}
finish_wait(sk_sleep(&q->sk), &wait);
return ret;
}
static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv,
unsigned long count, loff_t pos)
{
struct file *file = iocb->ki_filp;
struct macvtap_queue *q = file->private_data;
ssize_t len, ret = 0;
len = iov_length(iv, count);
if (len < 0) {
ret = -EINVAL;
goto out;
}
ret = macvtap_do_read(q, iocb, iv, len, file->f_flags & O_NONBLOCK);
ret = min_t(ssize_t, ret, len); /* XXX copied from tun.c. Why? */
out:
return ret;
}
/*
* provide compatibility with generic tun/tap interface
*/
static long macvtap_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
struct macvtap_queue *q = file->private_data;
struct macvlan_dev *vlan;
void __user *argp = (void __user *)arg;
struct ifreq __user *ifr = argp;
unsigned int __user *up = argp;
unsigned int u;
int __user *sp = argp;
int s;
int ret;
switch (cmd) {
case TUNSETIFF:
/* ignore the name, just look at flags */
if (get_user(u, &ifr->ifr_flags))
return -EFAULT;
ret = 0;
if ((u & ~IFF_VNET_HDR) != (IFF_NO_PI | IFF_TAP))
ret = -EINVAL;
else
q->flags = u;
return ret;
case TUNGETIFF:
rcu_read_lock_bh();
vlan = rcu_dereference_bh(q->vlan);
if (vlan)
dev_hold(vlan->dev);
rcu_read_unlock_bh();
if (!vlan)
return -ENOLINK;
ret = 0;
if (copy_to_user(&ifr->ifr_name, vlan->dev->name, IFNAMSIZ) ||
put_user(q->flags, &ifr->ifr_flags))
ret = -EFAULT;
dev_put(vlan->dev);
return ret;
case TUNGETFEATURES:
if (put_user(IFF_TAP | IFF_NO_PI | IFF_VNET_HDR, up))
return -EFAULT;
return 0;
case TUNSETSNDBUF:
if (get_user(u, up))
return -EFAULT;
q->sk.sk_sndbuf = u;
return 0;
case TUNGETVNETHDRSZ:
s = q->vnet_hdr_sz;
if (put_user(s, sp))
return -EFAULT;
return 0;
case TUNSETVNETHDRSZ:
if (get_user(s, sp))
return -EFAULT;
if (s < (int)sizeof(struct virtio_net_hdr))
return -EINVAL;
q->vnet_hdr_sz = s;
return 0;
case TUNSETOFFLOAD:
/* let the user check for future flags */
if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 |
TUN_F_TSO_ECN | TUN_F_UFO))
return -EINVAL;
/* TODO: only accept frames with the features that
got enabled for forwarded frames */
if (!(q->flags & IFF_VNET_HDR))
return -EINVAL;
return 0;
default:
return -EINVAL;
}
}
#ifdef CONFIG_COMPAT
static long macvtap_compat_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
return macvtap_ioctl(file, cmd, (unsigned long)compat_ptr(arg));
}
#endif
static const struct file_operations macvtap_fops = {
.owner = THIS_MODULE,
.open = macvtap_open,
.release = macvtap_release,
.aio_read = macvtap_aio_read,
.aio_write = macvtap_aio_write,
.poll = macvtap_poll,
.llseek = no_llseek,
.unlocked_ioctl = macvtap_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = macvtap_compat_ioctl,
#endif
};
static int macvtap_sendmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *m, size_t total_len)
{
struct macvtap_queue *q = container_of(sock, struct macvtap_queue, sock);
return macvtap_get_user(q, m, m->msg_iov, total_len, m->msg_iovlen,
m->msg_flags & MSG_DONTWAIT);
}
static int macvtap_recvmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *m, size_t total_len,
int flags)
{
struct macvtap_queue *q = container_of(sock, struct macvtap_queue, sock);
int ret;
if (flags & ~(MSG_DONTWAIT|MSG_TRUNC))
return -EINVAL;
ret = macvtap_do_read(q, 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;
}
return ret;
}
/* Ops structure to mimic raw sockets with tun */
static const struct proto_ops macvtap_socket_ops = {
.sendmsg = macvtap_sendmsg,
.recvmsg = macvtap_recvmsg,
};
/* 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 *macvtap_get_socket(struct file *file)
{
struct macvtap_queue *q;
if (file->f_op != &macvtap_fops)
return ERR_PTR(-EINVAL);
q = file->private_data;
if (!q)
return ERR_PTR(-EBADFD);
return &q->sock;
}
EXPORT_SYMBOL_GPL(macvtap_get_socket);
static int macvtap_device_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
struct net_device *dev = ptr;
struct macvlan_dev *vlan;
struct device *classdev;
dev_t devt;
int err;
if (dev->rtnl_link_ops != &macvtap_link_ops)
return NOTIFY_DONE;
vlan = netdev_priv(dev);
switch (event) {
case NETDEV_REGISTER:
/* Create the device node here after the network device has
* been registered but before register_netdevice has
* finished running.
*/
err = macvtap_get_minor(vlan);
if (err)
return notifier_from_errno(err);
devt = MKDEV(MAJOR(macvtap_major), vlan->minor);
classdev = device_create(macvtap_class, &dev->dev, devt,
dev, "tap%d", dev->ifindex);
if (IS_ERR(classdev)) {
macvtap_free_minor(vlan);
return notifier_from_errno(PTR_ERR(classdev));
}
break;
case NETDEV_UNREGISTER:
devt = MKDEV(MAJOR(macvtap_major), vlan->minor);
device_destroy(macvtap_class, devt);
macvtap_free_minor(vlan);
break;
}
return NOTIFY_DONE;
}
static struct notifier_block macvtap_notifier_block __read_mostly = {
.notifier_call = macvtap_device_event,
};
static int macvtap_init(void)
{
int err;
err = alloc_chrdev_region(&macvtap_major, 0,
MACVTAP_NUM_DEVS, "macvtap");
if (err)
goto out1;
cdev_init(&macvtap_cdev, &macvtap_fops);
err = cdev_add(&macvtap_cdev, macvtap_major, MACVTAP_NUM_DEVS);
if (err)
goto out2;
macvtap_class = class_create(THIS_MODULE, "macvtap");
if (IS_ERR(macvtap_class)) {
err = PTR_ERR(macvtap_class);
goto out3;
}
err = register_netdevice_notifier(&macvtap_notifier_block);
if (err)
goto out4;
err = macvlan_link_register(&macvtap_link_ops);
if (err)
goto out5;
return 0;
out5:
unregister_netdevice_notifier(&macvtap_notifier_block);
out4:
class_unregister(macvtap_class);
out3:
cdev_del(&macvtap_cdev);
out2:
unregister_chrdev_region(macvtap_major, MACVTAP_NUM_DEVS);
out1:
return err;
}
module_init(macvtap_init);
static void macvtap_exit(void)
{
rtnl_link_unregister(&macvtap_link_ops);
unregister_netdevice_notifier(&macvtap_notifier_block);
class_unregister(macvtap_class);
cdev_del(&macvtap_cdev);
unregister_chrdev_region(macvtap_major, MACVTAP_NUM_DEVS);
}
module_exit(macvtap_exit);
MODULE_ALIAS_RTNL_LINK("macvtap");
MODULE_AUTHOR("Arnd Bergmann <arnd@arndb.de>");
MODULE_LICENSE("GPL");