#include <linux/cdev.h>
#include <linux/idr.h>
#include <linux/fs.h>
+#include <linux/uio.h>
#include <net/ipv6.h>
#include <net/net_namespace.h>
struct list_head next;
};
+#define MACVTAP_FEATURES (IFF_VNET_HDR | IFF_MULTI_QUEUE)
+
+#define MACVTAP_VNET_LE 0x80000000
+
+static inline u16 macvtap16_to_cpu(struct macvtap_queue *q, __virtio16 val)
+{
+ return __virtio16_to_cpu(q->flags & MACVTAP_VNET_LE, val);
+}
+
+static inline __virtio16 cpu_to_macvtap16(struct macvtap_queue *q, u16 val)
+{
+ return __cpu_to_virtio16(q->flags & MACVTAP_VNET_LE, val);
+}
+
static struct proto macvtap_proto = {
.name = "macvtap",
.owner = THIS_MODULE,
* 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,
+static int macvtap_skb_from_vnet_hdr(struct macvtap_queue *q,
+ struct sk_buff *skb,
struct virtio_net_hdr *vnet_hdr)
{
unsigned short gso_type = 0;
}
if (vnet_hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
- if (!skb_partial_csum_set(skb, vnet_hdr->csum_start,
- vnet_hdr->csum_offset))
+ if (!skb_partial_csum_set(skb, macvtap16_to_cpu(q, vnet_hdr->csum_start),
+ macvtap16_to_cpu(q, 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_size = macvtap16_to_cpu(q, vnet_hdr->gso_size);
skb_shinfo(skb)->gso_type = gso_type;
/* Header must be checked, and gso_segs computed. */
return 0;
}
-static void macvtap_skb_to_vnet_hdr(const struct sk_buff *skb,
- struct virtio_net_hdr *vnet_hdr)
+static void macvtap_skb_to_vnet_hdr(struct macvtap_queue *q,
+ const struct sk_buff *skb,
+ struct virtio_net_hdr *vnet_hdr)
{
memset(vnet_hdr, 0, sizeof(*vnet_hdr));
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;
+ vnet_hdr->hdr_len = cpu_to_macvtap16(q, skb_headlen(skb));
+ vnet_hdr->gso_size = cpu_to_macvtap16(q, 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)
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;
+ if (vlan_tx_tag_present(skb))
+ vnet_hdr->csum_start = cpu_to_macvtap16(q,
+ skb_checksum_start_offset(skb) + VLAN_HLEN);
+ else
+ vnet_hdr->csum_start = cpu_to_macvtap16(q,
+ skb_checksum_start_offset(skb));
+ vnet_hdr->csum_offset = cpu_to_macvtap16(q, skb->csum_offset);
} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
vnet_hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID;
} /* else everything is zero */
/* 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 iov_iter *from, int noblock)
{
int good_linear = SKB_MAX_HEAD(NET_IP_ALIGN);
struct sk_buff *skb;
struct macvlan_dev *vlan;
+ unsigned long total_len = iov_iter_count(from);
unsigned long len = total_len;
int err;
struct virtio_net_hdr vnet_hdr = { 0 };
int copylen = 0;
bool zerocopy = false;
size_t linear;
+ ssize_t n;
if (q->flags & IFF_VNET_HDR) {
vnet_hdr_len = q->vnet_hdr_sz;
goto err;
len -= vnet_hdr_len;
- err = memcpy_fromiovecend((void *)&vnet_hdr, iv, 0,
- sizeof(vnet_hdr));
- if (err < 0)
+ err = -EFAULT;
+ n = copy_from_iter(&vnet_hdr, sizeof(vnet_hdr), from);
+ if (n != sizeof(vnet_hdr))
goto err;
+ iov_iter_advance(from, vnet_hdr_len - sizeof(vnet_hdr));
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;
+ macvtap16_to_cpu(q, vnet_hdr.csum_start) +
+ macvtap16_to_cpu(q, vnet_hdr.csum_offset) + 2 >
+ macvtap16_to_cpu(q, vnet_hdr.hdr_len))
+ vnet_hdr.hdr_len = cpu_to_macvtap16(q,
+ macvtap16_to_cpu(q, vnet_hdr.csum_start) +
+ macvtap16_to_cpu(q, vnet_hdr.csum_offset) + 2);
err = -EINVAL;
- if (vnet_hdr.hdr_len > len)
+ if (macvtap16_to_cpu(q, vnet_hdr.hdr_len) > len)
goto err;
}
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)) {
- copylen = vnet_hdr.hdr_len ? vnet_hdr.hdr_len : GOODCOPY_LEN;
+ struct iov_iter i;
+
+ copylen = vnet_hdr.hdr_len ?
+ macvtap16_to_cpu(q, vnet_hdr.hdr_len) : GOODCOPY_LEN;
if (copylen > good_linear)
copylen = good_linear;
linear = copylen;
- if (iov_pages(iv, vnet_hdr_len + copylen, count)
- <= MAX_SKB_FRAGS)
+ i = *from;
+ iov_iter_advance(&i, copylen);
+ if (iov_iter_npages(&i, INT_MAX) <= MAX_SKB_FRAGS)
zerocopy = true;
}
if (!zerocopy) {
copylen = len;
- if (vnet_hdr.hdr_len > good_linear)
+ if (macvtap16_to_cpu(q, vnet_hdr.hdr_len) > good_linear)
linear = good_linear;
else
- linear = vnet_hdr.hdr_len;
+ linear = macvtap16_to_cpu(q, vnet_hdr.hdr_len);
}
skb = macvtap_alloc_skb(&q->sk, NET_IP_ALIGN, copylen,
goto err;
if (zerocopy)
- err = zerocopy_sg_from_iovec(skb, iv, vnet_hdr_len, count);
+ err = zerocopy_sg_from_iter(skb, from);
else {
- err = skb_copy_datagram_from_iovec(skb, 0, iv, vnet_hdr_len,
- len);
+ err = skb_copy_datagram_from_iter(skb, 0, from, len);
if (!err && m && m->msg_control) {
struct ubuf_info *uarg = m->msg_control;
uarg->callback(uarg, false);
skb->protocol = eth_hdr(skb)->h_proto;
if (vnet_hdr_len) {
- err = macvtap_skb_from_vnet_hdr(skb, &vnet_hdr);
+ err = macvtap_skb_from_vnet_hdr(q, skb, &vnet_hdr);
if (err)
goto err_kfree;
}
return err;
}
-static ssize_t macvtap_aio_write(struct kiocb *iocb, const struct iovec *iv,
- unsigned long count, loff_t pos)
+static ssize_t macvtap_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
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;
+ return macvtap_get_user(q, NULL, from, file->f_flags & O_NONBLOCK);
}
/* 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 iov_iter *iter)
{
int ret;
int vnet_hdr_len = 0;
int vlan_offset = 0;
- int copied, total;
+ int total;
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)
+ if (iov_iter_count(iter) < vnet_hdr_len)
return -EINVAL;
- macvtap_skb_to_vnet_hdr(skb, &vnet_hdr);
+ macvtap_skb_to_vnet_hdr(q, skb, &vnet_hdr);
- if (memcpy_toiovecend(iv, (void *)&vnet_hdr, 0, sizeof(vnet_hdr)))
+ if (copy_to_iter(&vnet_hdr, sizeof(vnet_hdr), iter) !=
+ sizeof(vnet_hdr))
return -EFAULT;
+
+ iov_iter_advance(iter, vnet_hdr_len - sizeof(vnet_hdr));
}
- total = copied = vnet_hdr_len;
+ total = vnet_hdr_len;
total += skb->len;
- if (!vlan_tx_tag_present(skb))
- len = min_t(int, skb->len, len);
- else {
- int copy;
+ if (vlan_tx_tag_present(skb)) {
struct {
__be16 h_vlan_proto;
__be16 h_vlan_TCI;
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)
+ ret = skb_copy_datagram_iter(skb, 0, iter, vlan_offset);
+ if (ret || !iov_iter_count(iter))
goto done;
- copy = min_t(int, sizeof(veth), len);
- ret = memcpy_toiovecend(iv, (void *)&veth, copied, copy);
- len -= copy;
- copied += copy;
- if (ret || !len)
+ ret = copy_to_iter(&veth, sizeof(veth), iter);
+ if (ret != sizeof(veth) || !iov_iter_count(iter))
goto done;
}
- ret = skb_copy_datagram_const_iovec(skb, vlan_offset, iv, copied, len);
+ ret = skb_copy_datagram_iter(skb, vlan_offset, iter,
+ skb->len - vlan_offset);
done:
return ret ? ret : total;
}
static ssize_t macvtap_do_read(struct macvtap_queue *q,
- const struct iovec *iv, unsigned long len,
+ struct iov_iter *to,
int noblock)
{
DEFINE_WAIT(wait);
struct sk_buff *skb;
ssize_t ret = 0;
- while (len) {
+ if (!iov_iter_count(to))
+ return 0;
+
+ while (1) {
if (!noblock)
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;
+ if (skb)
+ break;
+ if (noblock) {
+ ret = -EAGAIN;
+ break;
}
- ret = macvtap_put_user(q, skb, iv, len);
- kfree_skb(skb);
- break;
+ if (signal_pending(current)) {
+ ret = -ERESTARTSYS;
+ break;
+ }
+ /* Nothing to read, let's sleep */
+ schedule();
+ }
+ if (skb) {
+ ret = macvtap_put_user(q, skb, to);
+ if (unlikely(ret < 0))
+ kfree_skb(skb);
+ else
+ consume_skb(skb);
}
-
if (!noblock)
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)
+static ssize_t macvtap_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct macvtap_queue *q = file->private_data;
- ssize_t len, ret = 0;
+ ssize_t len = iov_iter_count(to), ret;
- len = iov_length(iv, count);
- if (len < 0) {
- ret = -EINVAL;
- goto out;
- }
-
- ret = macvtap_do_read(q, iv, len, file->f_flags & O_NONBLOCK);
+ ret = macvtap_do_read(q, to, file->f_flags & O_NONBLOCK);
ret = min_t(ssize_t, ret, len);
if (ret > 0)
iocb->ki_pos = ret;
-out:
return ret;
}
void __user *argp = (void __user *)arg;
struct ifreq __user *ifr = argp;
unsigned int __user *up = argp;
- unsigned int u;
+ unsigned short u;
int __user *sp = argp;
int s;
int ret;
return -EFAULT;
ret = 0;
- if ((u & ~(IFF_VNET_HDR | IFF_MULTI_QUEUE)) !=
- (IFF_NO_PI | IFF_TAP))
+ if ((u & ~MACVTAP_FEATURES) != (IFF_NO_PI | IFF_TAP))
ret = -EINVAL;
else
- q->flags = u;
+ q->flags = (q->flags & ~MACVTAP_FEATURES) | u;
return ret;
}
ret = 0;
+ u = q->flags;
if (copy_to_user(&ifr->ifr_name, vlan->dev->name, IFNAMSIZ) ||
- put_user(q->flags, &ifr->ifr_flags))
+ put_user(u, &ifr->ifr_flags))
ret = -EFAULT;
macvtap_put_vlan(vlan);
rtnl_unlock();
return ret;
case TUNGETFEATURES:
- if (put_user(IFF_TAP | IFF_NO_PI | IFF_VNET_HDR |
- IFF_MULTI_QUEUE, up))
+ if (put_user(IFF_TAP | IFF_NO_PI | MACVTAP_FEATURES, up))
return -EFAULT;
return 0;
q->vnet_hdr_sz = s;
return 0;
+ case TUNGETVNETLE:
+ s = !!(q->flags & MACVTAP_VNET_LE);
+ if (put_user(s, sp))
+ return -EFAULT;
+ return 0;
+
+ case TUNSETVNETLE:
+ if (get_user(s, sp))
+ return -EFAULT;
+ if (s)
+ q->flags |= MACVTAP_VNET_LE;
+ else
+ q->flags &= ~MACVTAP_VNET_LE;
+ return 0;
+
case TUNSETOFFLOAD:
/* let the user check for future flags */
if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 |
.owner = THIS_MODULE,
.open = macvtap_open,
.release = macvtap_release,
- .aio_read = macvtap_aio_read,
- .aio_write = macvtap_aio_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = macvtap_read_iter,
+ .write_iter = macvtap_write_iter,
.poll = macvtap_poll,
.llseek = no_llseek,
.unlocked_ioctl = macvtap_ioctl,
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);
+ return macvtap_get_user(q, m, &m->msg_iter, m->msg_flags & MSG_DONTWAIT);
}
static int macvtap_recvmsg(struct kiocb *iocb, struct socket *sock,
int ret;
if (flags & ~(MSG_DONTWAIT|MSG_TRUNC))
return -EINVAL;
- ret = macvtap_do_read(q, m->msg_iov, total_len,
- flags & MSG_DONTWAIT);
+ ret = macvtap_do_read(q, &m->msg_iter, flags & MSG_DONTWAIT);
if (ret > total_len) {
m->msg_flags |= MSG_TRUNC;
ret = flags & MSG_TRUNC ? ret : total_len;
projects / cascardo / linux.git / blobdiff