linux/drivers/net/macvtap.c

829 lines
20 KiB
C
Raw Normal View History

#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 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 08:04:11 +00:00
#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;
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 11:01:49 +00:00
struct socket_wq wq;
int vnet_hdr_sz;
struct macvlan_dev *vlan;
struct file *file;
unsigned int flags;
};
static struct proto macvtap_proto = {
.name = "macvtap",
.owner = THIS_MODULE,
.obj_size = sizeof (struct macvtap_queue),
};
/*
* Minor number matches netdev->ifindex, so need a potentially
* large value. This also makes it possible to split the
* tap functionality out again in the future by offering it
* from other drivers besides macvtap. As long as every device
* only has one tap, the interface numbers assure that the
* device nodes are unique.
*/
static unsigned int macvtap_major;
#define MACVTAP_NUM_DEVS 65536
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);
/*
* Choose the next free queue, for now there is only one
*/
static int macvtap_set_queue(struct net_device *dev, struct file *file,
struct macvtap_queue *q)
{
struct macvlan_dev *vlan = netdev_priv(dev);
int err = -EBUSY;
spin_lock(&macvtap_lock);
if (rcu_dereference(vlan->tap))
goto out;
err = 0;
rcu_assign_pointer(q->vlan, vlan);
rcu_assign_pointer(vlan->tap, q);
sock_hold(&q->sk);
q->file = file;
file->private_data = q;
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(q->vlan);
if (vlan) {
rcu_assign_pointer(vlan->tap, NULL);
rcu_assign_pointer(q->vlan, NULL);
sock_put(&q->sk);
}
spin_unlock(&macvtap_lock);
synchronize_rcu();
sock_put(&q->sk);
}
/*
* Since we only support one queue, just dereference the pointer.
*/
static struct macvtap_queue *macvtap_get_queue(struct net_device *dev,
struct sk_buff *skb)
{
struct macvlan_dev *vlan = netdev_priv(dev);
return rcu_dereference(vlan->tap);
}
/*
* The net_device is going away, give up the reference
* that it holds on the queue (all the queues one day)
* 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;
spin_lock(&macvtap_lock);
q = rcu_dereference(vlan->tap);
if (!q) {
spin_unlock(&macvtap_lock);
return;
}
rcu_assign_pointer(vlan->tap, NULL);
rcu_assign_pointer(q->vlan, NULL);
spin_unlock(&macvtap_lock);
synchronize_rcu();
sock_put(&q->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)
return -ENOLINK;
skb_queue_tail(&q->sk.sk_receive_queue, skb);
wake_up_interruptible_poll(sk_sleep(&q->sk), POLLIN | POLLRDNORM | POLLRDBAND);
return 0;
}
/*
* 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_newlink(struct net *src_net,
struct net_device *dev,
struct nlattr *tb[],
struct nlattr *data[])
{
struct device *classdev;
dev_t devt;
int err;
err = macvlan_common_newlink(src_net, dev, tb, data,
macvtap_receive, macvtap_forward);
if (err)
goto out;
devt = MKDEV(MAJOR(macvtap_major), dev->ifindex);
classdev = device_create(macvtap_class, &dev->dev, devt,
dev, "tap%d", dev->ifindex);
if (IS_ERR(classdev)) {
err = PTR_ERR(classdev);
macvtap_del_queues(dev);
}
out:
return err;
}
static void macvtap_dellink(struct net_device *dev,
struct list_head *head)
{
device_destroy(macvtap_class,
MKDEV(MAJOR(macvtap_major), dev->ifindex));
macvtap_del_queues(dev);
macvlan_dellink(dev, head);
}
static struct rtnl_link_ops macvtap_link_ops __read_mostly = {
.kind = "macvtap",
.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 11:01:49 +00:00
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 11:01:49 +00:00
wqueue = sk_sleep(sk);
if (wqueue && waitqueue_active(wqueue))
wake_up_interruptible_poll(wqueue, POLLOUT | POLLWRNORM | POLLWRBAND);
}
static int macvtap_open(struct inode *inode, struct file *file)
{
struct net *net = current->nsproxy->net_ns;
struct net_device *dev = dev_get_by_index(net, iminor(inode));
struct macvtap_queue *q;
int err;
err = -ENODEV;
if (!dev)
goto out;
/* check if this is a macvtap device */
err = -EINVAL;
if (dev->rtnl_link_ops != &macvtap_link_ops)
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 11:01:49 +00:00
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->flags = IFF_VNET_HDR | IFF_NO_PI | IFF_TAP;
q->vnet_hdr_sz = sizeof(struct virtio_net_hdr);
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 11:01:49 +00:00
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;
}
/*
* 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->csum_start -
skb_headroom(skb);
vnet_hdr->csum_offset = skb->csum_offset;
} /* else everything is zero */
return 0;
}
/* Get packet from user space buffer */
static ssize_t macvtap_get_user(struct macvtap_queue *q,
const struct iovec *iv, size_t count,
int noblock)
{
struct sk_buff *skb;
struct macvlan_dev *vlan;
size_t len = count;
int err;
struct virtio_net_hdr vnet_hdr = { 0 };
int vnet_hdr_len = 0;
if (q->flags & IFF_VNET_HDR) {
vnet_hdr_len = q->vnet_hdr_sz;
err = -EINVAL;
if ((len -= vnet_hdr_len) < 0)
goto err;
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;
skb = macvtap_alloc_skb(&q->sk, NET_IP_ALIGN, len, vnet_hdr.hdr_len,
noblock, &err);
if (!skb)
goto err;
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(q->vlan);
if (vlan)
macvlan_start_xmit(skb, vlan->dev);
else
kfree_skb(skb);
rcu_read_unlock_bh();
return count;
err_kfree:
kfree_skb(skb);
err:
rcu_read_lock_bh();
vlan = rcu_dereference(q->vlan);
if (vlan)
netdev_get_tx_queue(vlan->dev, 0)->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, iv, iov_length(iv, 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;
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;
}
len = min_t(int, skb->len, len);
ret = skb_copy_datagram_const_iovec(skb, 0, iv, vnet_hdr_len, len);
rcu_read_lock_bh();
vlan = rcu_dereference(q->vlan);
if (vlan)
macvlan_count_rx(vlan, len, ret == 0, 0);
rcu_read_unlock_bh();
return ret ? ret : (len + vnet_hdr_len);
}
static ssize_t macvtap_do_read(struct macvtap_queue *q, struct kiocb *iocb,
const struct iovec *iv, unsigned long len,
int noblock)
{
DECLARE_WAITQUEUE(wait, current);
struct sk_buff *skb;
ssize_t ret = 0;
add_wait_queue(sk_sleep(&q->sk), &wait);
while (len) {
current->state = 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;
}
current->state = TASK_RUNNING;
remove_wait_queue(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(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, q->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->msg_iov, total_len,
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_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 = macvlan_link_register(&macvtap_link_ops);
if (err)
goto out4;
return 0;
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);
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");