/* After we've used one of their buffers, we tell them about it. We'll then
* want to notify the guest, using eventfd. */
int vhost_add_used(struct vhost_virtqueue *vq, unsigned int head, int len)
{
struct vring_used_elem *used;
/* The virtqueue contains a ring of used buffers. Get a pointer to the
* next entry in that used ring. */
used = &vq->used->ring[vq->last_used_idx % vq->num];
if (put_user(head, &used->id)) {
vq_err(vq, "Failed to write used id");
return -EFAULT;
}
if (put_user(len, &used->len)) {
vq_err(vq, "Failed to write used len");
return -EFAULT;
}
/* Make sure buffer is written before we update index. */
smp_wmb();
if (put_user(vq->last_used_idx + 1, &vq->used->idx)) {
vq_err(vq, "Failed to increment used idx");
return -EFAULT;
}
if (unlikely(vq->log_used)) {
/* Make sure data is seen before log. */
smp_wmb();
/* Log used ring entry write. */
log_write(vq->log_base,
vq->log_addr + ((void *)used - (void *)vq->used),
sizeof *used);
/* Log used index update. */
log_write(vq->log_base,
vq->log_addr + offsetof(struct vring_used, idx),
sizeof vq->used->idx);
if (vq->log_ctx)
eventfd_signal(vq->log_ctx, 1);
}
/* Expects to be always run from workqueue - which acts as
* read-size critical section for our kind of RCU. */
static void handle_rx(struct vhost_net *net)
{
struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_RX];
struct vhost_virtqueue *vq = &nvq->vq;
unsigned uninitialized_var(in), log;
struct vhost_log *vq_log;
struct msghdr msg = {
.msg_name = NULL,
.msg_namelen = 0,
.msg_control = NULL, /* FIXME: get and handle RX aux data. */
.msg_controllen = 0,
.msg_flags = MSG_DONTWAIT,
};
struct virtio_net_hdr_mrg_rxbuf hdr = {
.hdr.flags = 0,
.hdr.gso_type = VIRTIO_NET_HDR_GSO_NONE
};
size_t total_len = 0;
int err, mergeable;
s16 headcount;
size_t vhost_hlen, sock_hlen;
size_t vhost_len, sock_len;
struct socket *sock;
mutex_lock(&vq->mutex);
sock = vq->private_data;
if (!sock)
goto out;
vhost_disable_notify(&net->dev, vq);
vhost_hlen = nvq->vhost_hlen;
sock_hlen = nvq->sock_hlen;
vq_log = unlikely(vhost_has_feature(vq, VHOST_F_LOG_ALL)) ?
vq->log : NULL;
mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF);
while ((sock_len = peek_head_len(sock->sk))) {
sock_len += sock_hlen;
vhost_len = sock_len + vhost_hlen;
headcount = get_rx_bufs(vq, vq->heads, vhost_len,
&in, vq_log, &log,
likely(mergeable) ? UIO_MAXIOV : 1);
/* On error, stop handling until the next kick. */
if (unlikely(headcount < 0))
break;
/* On overrun, truncate and discard */
if (unlikely(headcount > UIO_MAXIOV)) {
iov_iter_init(&msg.msg_iter, READ, vq->iov, 1, 1);
err = sock->ops->recvmsg(NULL, sock, &msg,
1, MSG_DONTWAIT | MSG_TRUNC);
pr_debug("Discarded rx packet: len %zd\n", sock_len);
continue;
}
/* OK, now we need to know about added descriptors. */
if (!headcount) {
if (unlikely(vhost_enable_notify(&net->dev, vq))) {
/* They have slipped one in as we were
* doing that: check again. */
vhost_disable_notify(&net->dev, vq);
continue;
}
/* Nothing new? Wait for eventfd to tell us
* they refilled. */
break;
}
/* We don't need to be notified again. */
if (unlikely((vhost_hlen)))
/* Skip header. TODO: support TSO. */
move_iovec_hdr(vq->iov, nvq->hdr, vhost_hlen, in);
else
/* Copy the header for use in VIRTIO_NET_F_MRG_RXBUF:
* needed because recvmsg can modify msg_iov. */
copy_iovec_hdr(vq->iov, nvq->hdr, sock_hlen, in);
iov_iter_init(&msg.msg_iter, READ, vq->iov, in, sock_len);
err = sock->ops->recvmsg(NULL, sock, &msg,
sock_len, MSG_DONTWAIT | MSG_TRUNC);
/* Userspace might have consumed the packet meanwhile:
* it's not supposed to do this usually, but might be hard
* to prevent. Discard data we got (if any) and keep going. */
if (unlikely(err != sock_len)) {
pr_debug("Discarded rx packet: "
" len %d, expected %zd\n", err, sock_len);
vhost_discard_vq_desc(vq, headcount);
continue;
}
if (unlikely(vhost_hlen) &&
memcpy_toiovecend(nvq->hdr, (unsigned char *)&hdr, 0,
vhost_hlen)) {
vq_err(vq, "Unable to write vnet_hdr at addr %p\n",
vq->iov->iov_base);
break;
}
/* TODO: Should check and handle checksum. */
if (likely(mergeable) &&
memcpy_toiovecend(nvq->hdr, (unsigned char *)&headcount,
offsetof(typeof(hdr), num_buffers),
sizeof hdr.num_buffers)) {
vq_err(vq, "Failed num_buffers write");
vhost_discard_vq_desc(vq, headcount);
break;
}
vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
headcount);
if (unlikely(vq_log))
vhost_log_write(vq, vq_log, log, vhost_len);
total_len += vhost_len;
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
vhost_poll_queue(&vq->poll);
break;
}
}
out:
mutex_unlock(&vq->mutex);
}
static void handle_tx_kick(struct vhost_work *work)
{
struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
poll.work);
struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev);
handle_tx(net);
}
static void handle_rx_kick(struct vhost_work *work)
{
struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
poll.work);
struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev);
handle_rx(net);
}
static void handle_tx_net(struct vhost_work *work)
{
struct vhost_net *net = container_of(work, struct vhost_net,
poll[VHOST_NET_VQ_TX].work);
handle_tx(net);
}
static void handle_rx_net(struct vhost_work *work)
{
struct vhost_net *net = container_of(work, struct vhost_net,
poll[VHOST_NET_VQ_RX].work);
handle_rx(net);
}
static int vhost_net_open(struct inode *inode, struct file *f)
{
struct vhost_net *n;
struct vhost_dev *dev;
struct vhost_virtqueue **vqs;
int i;
n = kmalloc(sizeof *n, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
if (!n) {
n = vmalloc(sizeof *n);
if (!n)
return -ENOMEM;
}
vqs = kmalloc(VHOST_NET_VQ_MAX * sizeof(*vqs), GFP_KERNEL);
if (!vqs) {
kvfree(n);
return -ENOMEM;
}
dev = &n->dev;
vqs[VHOST_NET_VQ_TX] = &n->vqs[VHOST_NET_VQ_TX].vq;
vqs[VHOST_NET_VQ_RX] = &n->vqs[VHOST_NET_VQ_RX].vq;
n->vqs[VHOST_NET_VQ_TX].vq.handle_kick = handle_tx_kick;
n->vqs[VHOST_NET_VQ_RX].vq.handle_kick = handle_rx_kick;
for (i = 0; i < VHOST_NET_VQ_MAX; i++) {
n->vqs[i].ubufs = NULL;
n->vqs[i].ubuf_info = NULL;
n->vqs[i].upend_idx = 0;
n->vqs[i].done_idx = 0;
n->vqs[i].vhost_hlen = 0;
n->vqs[i].sock_hlen = 0;
}
vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX);
vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT, dev);
vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN, dev);
f->private_data = n;
return 0;
}
static void vhost_net_disable_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
struct vhost_net_virtqueue *nvq =
container_of(vq, struct vhost_net_virtqueue, vq);
struct vhost_poll *poll = n->poll + (nvq - n->vqs);
if (!vq->private_data)
return;
vhost_poll_stop(poll);
}
static int vhost_net_enable_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
struct vhost_net_virtqueue *nvq =
container_of(vq, struct vhost_net_virtqueue, vq);
struct vhost_poll *poll = n->poll + (nvq - n->vqs);
struct socket *sock;
sock = vq->private_data;
if (!sock)
return 0;
return vhost_poll_start(poll, sock->file);
}
static struct socket *vhost_net_stop_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
struct socket *sock;
mutex_lock(&vq->mutex);
sock = vq->private_data;
vhost_net_disable_vq(n, vq);
vq->private_data = NULL;
mutex_unlock(&vq->mutex);
return sock;
}
static void vhost_net_stop(struct vhost_net *n, struct socket **tx_sock,
struct socket **rx_sock)
{
*tx_sock = vhost_net_stop_vq(n, &n->vqs[VHOST_NET_VQ_TX].vq);
*rx_sock = vhost_net_stop_vq(n, &n->vqs[VHOST_NET_VQ_RX].vq);
}
static void vhost_net_flush_vq(struct vhost_net *n, int index)
{
vhost_poll_flush(n->poll + index);
vhost_poll_flush(&n->vqs[index].vq.poll);
}
/* Expects to be always run from workqueue - which acts as
* read-size critical section for our kind of RCU. */
static void handle_tx(struct vhost_net *net)
{
struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
struct vhost_virtqueue *vq = &nvq->vq;
unsigned out, in, s;
int head;
struct msghdr msg = {
.msg_name = NULL,
.msg_namelen = 0,
.msg_control = NULL,
.msg_controllen = 0,
.msg_flags = MSG_DONTWAIT,
};
size_t len, total_len = 0;
int err;
size_t hdr_size;
struct socket *sock;
struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
bool zcopy, zcopy_used;
mutex_lock(&vq->mutex);
sock = vq->private_data;
if (!sock)
goto out;
vhost_disable_notify(&net->dev, vq);
hdr_size = nvq->vhost_hlen;
zcopy = nvq->ubufs;
for (;;) {
/* Release DMAs done buffers first */
if (zcopy)
vhost_zerocopy_signal_used(net, vq);
/* If more outstanding DMAs, queue the work.
* Handle upend_idx wrap around
*/
if (unlikely((nvq->upend_idx + vq->num - VHOST_MAX_PEND)
% UIO_MAXIOV == nvq->done_idx))
break;
head = vhost_get_vq_desc(vq, vq->iov,
ARRAY_SIZE(vq->iov),
&out, &in,
NULL, NULL);
/* On error, stop handling until the next kick. */
if (unlikely(head < 0))
break;
/* Nothing new? Wait for eventfd to tell us they refilled. */
if (head == vq->num) {
if (unlikely(vhost_enable_notify(&net->dev, vq))) {
vhost_disable_notify(&net->dev, vq);
continue;
}
break;
}
if (in) {
vq_err(vq, "Unexpected descriptor format for TX: "
"out %d, int %d\n", out, in);
break;
}
/* Skip header. TODO: support TSO. */
s = move_iovec_hdr(vq->iov, nvq->hdr, hdr_size, out);
len = iov_length(vq->iov, out);
iov_iter_init(&msg.msg_iter, WRITE, vq->iov, out, len);
/* Sanity check */
if (!len) {
vq_err(vq, "Unexpected header len for TX: "
"%zd expected %zd\n",
iov_length(nvq->hdr, s), hdr_size);
break;
}
zcopy_used = zcopy && len >= VHOST_GOODCOPY_LEN
&& (nvq->upend_idx + 1) % UIO_MAXIOV !=
nvq->done_idx
&& vhost_net_tx_select_zcopy(net);
/* use msg_control to pass vhost zerocopy ubuf info to skb */
if (zcopy_used) {
struct ubuf_info *ubuf;
ubuf = nvq->ubuf_info + nvq->upend_idx;
vq->heads[nvq->upend_idx].id = cpu_to_vhost32(vq, head);
vq->heads[nvq->upend_idx].len = VHOST_DMA_IN_PROGRESS;
ubuf->callback = vhost_zerocopy_callback;
ubuf->ctx = nvq->ubufs;
ubuf->desc = nvq->upend_idx;
msg.msg_control = ubuf;
msg.msg_controllen = sizeof(ubuf);
ubufs = nvq->ubufs;
atomic_inc(&ubufs->refcount);
nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV;
} else {
msg.msg_control = NULL;
ubufs = NULL;
}
/* TODO: Check specific error and bomb out unless ENOBUFS? */
err = sock->ops->sendmsg(NULL, sock, &msg, len);
if (unlikely(err < 0)) {
if (zcopy_used) {
vhost_net_ubuf_put(ubufs);
nvq->upend_idx = ((unsigned)nvq->upend_idx - 1)
% UIO_MAXIOV;
}
vhost_discard_vq_desc(vq, 1);
break;
}
if (err != len)
pr_debug("Truncated TX packet: "
" len %d != %zd\n", err, len);
if (!zcopy_used)
vhost_add_used_and_signal(&net->dev, vq, head, 0);
else
vhost_zerocopy_signal_used(net, vq);
total_len += len;
vhost_net_tx_packet(net);
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
vhost_poll_queue(&vq->poll);
break;
}
}
out:
mutex_unlock(&vq->mutex);
}
static int peek_head_len(struct sock *sk)
{
struct sk_buff *head;
int len = 0;
unsigned long flags;
spin_lock_irqsave(&sk->sk_receive_queue.lock, flags);
head = skb_peek(&sk->sk_receive_queue);
if (likely(head)) {
len = head->len;
if (vlan_tx_tag_present(head))
len += VLAN_HLEN;
}
spin_unlock_irqrestore(&sk->sk_receive_queue.lock, flags);
return len;
}
/* This is a multi-buffer version of vhost_get_desc, that works if
* vq has read descriptors only.
* @vq - the relevant virtqueue
* @datalen - data length we'll be reading
* @iovcount - returned count of io vectors we fill
* @log - vhost log
* @log_num - log offset
* @quota - headcount quota, 1 for big buffer
* returns number of buffer heads allocated, negative on error
*/
static int get_rx_bufs(struct vhost_virtqueue *vq,
struct vring_used_elem *heads,
int datalen,
unsigned *iovcount,
struct vhost_log *log,
unsigned *log_num,
unsigned int quota)
{
unsigned int out, in;
int seg = 0;
int headcount = 0;
unsigned d;
int r, nlogs = 0;
/* len is always initialized before use since we are always called with
* datalen > 0.
*/
u32 uninitialized_var(len);
while (datalen > 0 && headcount < quota) {
if (unlikely(seg >= UIO_MAXIOV)) {
r = -ENOBUFS;
goto err;
}
r = vhost_get_vq_desc(vq, vq->iov + seg,
ARRAY_SIZE(vq->iov) - seg, &out,
&in, log, log_num);
if (unlikely(r < 0))
goto err;
d = r;
if (d == vq->num) {
r = 0;
goto err;
}
if (unlikely(out || in <= 0)) {
vq_err(vq, "unexpected descriptor format for RX: "
"out %d, in %d\n", out, in);
r = -EINVAL;
goto err;
}
if (unlikely(log)) {
nlogs += *log_num;
log += *log_num;
}
heads[headcount].id = cpu_to_vhost32(vq, d);
len = iov_length(vq->iov + seg, in);
heads[headcount].len = cpu_to_vhost32(vq, len);
datalen -= len;
++headcount;
seg += in;
}
heads[headcount - 1].len = cpu_to_vhost32(vq, len - datalen);
*iovcount = seg;
if (unlikely(log))
*log_num = nlogs;
/* Detect overrun */
if (unlikely(datalen > 0)) {
r = UIO_MAXIOV + 1;
goto err;
}
return headcount;
err:
vhost_discard_vq_desc(vq, headcount);
return r;
}
/* Expects to be always run from workqueue - which acts as
* read-size critical section for our kind of RCU. */
static void handle_tx(struct vhost_net *net)
{
struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_TX];
unsigned out, in, s;
int head;
struct msghdr msg = {
.msg_name = NULL,
.msg_namelen = 0,
.msg_control = NULL,
.msg_controllen = 0,
.msg_iov = vq->iov,
.msg_flags = MSG_DONTWAIT,
};
size_t len, total_len = 0;
int err, wmem;
size_t hdr_size;
struct socket *sock;
struct vhost_ubuf_ref *uninitialized_var(ubufs);
bool zcopy;
/* TODO: check that we are running from vhost_worker? */
sock = rcu_dereference_check(vq->private_data, 1);
if (!sock)
return;
wmem = atomic_read(&sock->sk->sk_wmem_alloc);
if (wmem >= sock->sk->sk_sndbuf) {
mutex_lock(&vq->mutex);
tx_poll_start(net, sock);
mutex_unlock(&vq->mutex);
return;
}
mutex_lock(&vq->mutex);
vhost_disable_notify(&net->dev, vq);
if (wmem < sock->sk->sk_sndbuf / 2)
tx_poll_stop(net);
hdr_size = vq->vhost_hlen;
zcopy = vhost_sock_zcopy(sock);
for (;;) {
/* Release DMAs done buffers first */
if (zcopy)
vhost_zerocopy_signal_used(vq);
head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
ARRAY_SIZE(vq->iov),
&out, &in,
NULL, NULL);
/* On error, stop handling until the next kick. */
if (unlikely(head < 0))
break;
/* Nothing new? Wait for eventfd to tell us they refilled. */
if (head == vq->num) {
int num_pends;
wmem = atomic_read(&sock->sk->sk_wmem_alloc);
if (wmem >= sock->sk->sk_sndbuf * 3 / 4) {
tx_poll_start(net, sock);
set_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
break;
}
/* If more outstanding DMAs, queue the work.
* Handle upend_idx wrap around
*/
num_pends = likely(vq->upend_idx >= vq->done_idx) ?
(vq->upend_idx - vq->done_idx) :
(vq->upend_idx + UIO_MAXIOV - vq->done_idx);
if (unlikely(num_pends > VHOST_MAX_PEND)) {
tx_poll_start(net, sock);
set_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
break;
}
if (unlikely(vhost_enable_notify(&net->dev, vq))) {
vhost_disable_notify(&net->dev, vq);
continue;
}
break;
}
if (in) {
vq_err(vq, "Unexpected descriptor format for TX: "
"out %d, int %d\n", out, in);
break;
}
/* Skip header. TODO: support TSO. */
s = move_iovec_hdr(vq->iov, vq->hdr, hdr_size, out);
msg.msg_iovlen = out;
len = iov_length(vq->iov, out);
/* Sanity check */
if (!len) {
vq_err(vq, "Unexpected header len for TX: "
"%zd expected %zd\n",
iov_length(vq->hdr, s), hdr_size);
break;
}
/* use msg_control to pass vhost zerocopy ubuf info to skb */
if (zcopy) {
vq->heads[vq->upend_idx].id = head;
if (len < VHOST_GOODCOPY_LEN) {
/* copy don't need to wait for DMA done */
vq->heads[vq->upend_idx].len =
VHOST_DMA_DONE_LEN;
msg.msg_control = NULL;
msg.msg_controllen = 0;
ubufs = NULL;
} else {
struct ubuf_info *ubuf = &vq->ubuf_info[head];
vq->heads[vq->upend_idx].len = len;
ubuf->callback = vhost_zerocopy_callback;
ubuf->ctx = vq->ubufs;
ubuf->desc = vq->upend_idx;
msg.msg_control = ubuf;
msg.msg_controllen = sizeof(ubuf);
ubufs = vq->ubufs;
kref_get(&ubufs->kref);
}
vq->upend_idx = (vq->upend_idx + 1) % UIO_MAXIOV;
}
/* TODO: Check specific error and bomb out unless ENOBUFS? */
err = sock->ops->sendmsg(NULL, sock, &msg, len);
if (unlikely(err < 0)) {
if (zcopy) {
if (ubufs)
vhost_ubuf_put(ubufs);
vq->upend_idx = ((unsigned)vq->upend_idx - 1) %
UIO_MAXIOV;
}
vhost_discard_vq_desc(vq, 1);
tx_poll_start(net, sock);
break;
}
if (err != len)
pr_debug("Truncated TX packet: "
" len %d != %zd\n", err, len);
if (!zcopy)
vhost_add_used_and_signal(&net->dev, vq, head, 0);
total_len += len;
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
vhost_poll_queue(&vq->poll);
break;
}
}
mutex_unlock(&vq->mutex);
}
static int peek_head_len(struct sock *sk)
{
struct sk_buff *head;
int len = 0;
unsigned long flags;
spin_lock_irqsave(&sk->sk_receive_queue.lock, flags);
head = skb_peek(&sk->sk_receive_queue);
if (likely(head)) {
len = head->len;
if (vlan_tx_tag_present(head))
len += VLAN_HLEN;
}
spin_unlock_irqrestore(&sk->sk_receive_queue.lock, flags);
return len;
}
/* This is a multi-buffer version of vhost_get_desc, that works if
* vq has read descriptors only.
* @vq - the relevant virtqueue
* @datalen - data length we'll be reading
* @iovcount - returned count of io vectors we fill
* @log - vhost log
* @log_num - log offset
* @quota - headcount quota, 1 for big buffer
* returns number of buffer heads allocated, negative on error
*/
static int get_rx_bufs(struct vhost_virtqueue *vq,
struct vring_used_elem *heads,
int datalen,
unsigned *iovcount,
struct vhost_log *log,
unsigned *log_num,
unsigned int quota)
{
unsigned int out, in;
int seg = 0;
int headcount = 0;
unsigned d;
int r, nlogs = 0;
while (datalen > 0 && headcount < quota) {
if (unlikely(seg >= UIO_MAXIOV)) {
r = -ENOBUFS;
goto err;
}
d = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
ARRAY_SIZE(vq->iov) - seg, &out,
&in, log, log_num);
if (d == vq->num) {
r = 0;
goto err;
}
if (unlikely(out || in <= 0)) {
vq_err(vq, "unexpected descriptor format for RX: "
"out %d, in %d\n", out, in);
r = -EINVAL;
goto err;
}
if (unlikely(log)) {
nlogs += *log_num;
log += *log_num;
}
heads[headcount].id = d;
heads[headcount].len = iov_length(vq->iov + seg, in);
datalen -= heads[headcount].len;
++headcount;
seg += in;
}
heads[headcount - 1].len += datalen;
*iovcount = seg;
if (unlikely(log))
*log_num = nlogs;
return headcount;
err:
vhost_discard_vq_desc(vq, headcount);
return r;
}
/* Expects to be always run from workqueue - which acts as
* read-size critical section for our kind of RCU. */
static void handle_tx(struct vhost_net *net)
{
struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_TX];
unsigned out, in, s;
int head;
struct msghdr msg = {
.msg_name = NULL,
.msg_namelen = 0,
.msg_control = NULL,
.msg_controllen = 0,
.msg_iov = vq->iov,
.msg_flags = MSG_DONTWAIT,
};
size_t len, total_len = 0;
int err, wmem;
size_t hdr_size;
struct socket *sock;
/* TODO: check that we are running from vhost_worker? */
sock = rcu_dereference_check(vq->private_data, 1);
if (!sock)
return;
wmem = atomic_read(&sock->sk->sk_wmem_alloc);
if (wmem >= sock->sk->sk_sndbuf) {
mutex_lock(&vq->mutex);
tx_poll_start(net, sock);
mutex_unlock(&vq->mutex);
return;
}
mutex_lock(&vq->mutex);
vhost_disable_notify(vq);
if (wmem < sock->sk->sk_sndbuf / 2)
tx_poll_stop(net);
hdr_size = vq->vhost_hlen;
for (;;) {
head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
ARRAY_SIZE(vq->iov),
&out, &in,
NULL, NULL);
/* On error, stop handling until the next kick. */
if (unlikely(head < 0))
break;
/* Nothing new? Wait for eventfd to tell us they refilled. */
if (head == vq->num) {
wmem = atomic_read(&sock->sk->sk_wmem_alloc);
if (wmem >= sock->sk->sk_sndbuf * 3 / 4) {
tx_poll_start(net, sock);
set_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
break;
}
if (unlikely(vhost_enable_notify(vq))) {
vhost_disable_notify(vq);
continue;
}
break;
}
if (in) {
vq_err(vq, "Unexpected descriptor format for TX: "
"out %d, int %d\n", out, in);
break;
}
/* Skip header. TODO: support TSO. */
s = move_iovec_hdr(vq->iov, vq->hdr, hdr_size, out);
msg.msg_iovlen = out;
len = iov_length(vq->iov, out);
/* Sanity check */
if (!len) {
vq_err(vq, "Unexpected header len for TX: "
"%zd expected %zd\n",
iov_length(vq->hdr, s), hdr_size);
break;
}
/* TODO: Check specific error and bomb out unless ENOBUFS? */
err = sock->ops->sendmsg(NULL, sock, &msg, len);
if (unlikely(err < 0)) {
vhost_discard_vq_desc(vq, 1);
tx_poll_start(net, sock);
break;
}
if (err != len)
pr_debug("Truncated TX packet: "
" len %d != %zd\n", err, len);
vhost_add_used_and_signal(&net->dev, vq, head, 0);
total_len += len;
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
vhost_poll_queue(&vq->poll);
break;
}
}
mutex_unlock(&vq->mutex);
}
static int peek_head_len(struct sock *sk)
{
struct sk_buff *head;
int len = 0;
unsigned long flags;
spin_lock_irqsave(&sk->sk_receive_queue.lock, flags);
head = skb_peek(&sk->sk_receive_queue);
if (likely(head))
len = head->len;
spin_unlock_irqrestore(&sk->sk_receive_queue.lock, flags);
return len;
}
/* This is a multi-buffer version of vhost_get_desc, that works if
* vq has read descriptors only.
* @vq - the relevant virtqueue
* @datalen - data length we'll be reading
* @iovcount - returned count of io vectors we fill
* @log - vhost log
* @log_num - log offset
* @quota - headcount quota, 1 for big buffer
* returns number of buffer heads allocated, negative on error
*/
static int get_rx_bufs(struct vhost_virtqueue *vq,
struct vring_used_elem *heads,
int datalen,
unsigned *iovcount,
struct vhost_log *log,
unsigned *log_num,
unsigned int quota)
{
unsigned int out, in;
int seg = 0;
int headcount = 0;
unsigned d;
int r, nlogs = 0;
while (datalen > 0 && headcount < quota) {
if (unlikely(seg >= UIO_MAXIOV)) {
r = -ENOBUFS;
goto err;
}
d = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
ARRAY_SIZE(vq->iov) - seg, &out,
&in, log, log_num);
if (d == vq->num) {
r = 0;
goto err;
}
if (unlikely(out || in <= 0)) {
vq_err(vq, "unexpected descriptor format for RX: "
"out %d, in %d\n", out, in);
r = -EINVAL;
goto err;
}
if (unlikely(log)) {
nlogs += *log_num;
log += *log_num;
}
heads[headcount].id = d;
heads[headcount].len = iov_length(vq->iov + seg, in);
datalen -= heads[headcount].len;
++headcount;
seg += in;
}
heads[headcount - 1].len += datalen;
*iovcount = seg;
if (unlikely(log))
*log_num = nlogs;
return headcount;
err:
vhost_discard_vq_desc(vq, headcount);
return r;
}
/* This looks in the virtqueue and for the first available buffer, and converts
* it to an iovec for convenient access. Since descriptors consist of some
* number of output then some number of input descriptors, it's actually two
* iovecs, but we pack them into one and note how many of each there were.
*
* This function returns the descriptor number found, or vq->num (which
* is never a valid descriptor number) if none was found. */
unsigned vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq,
struct iovec iov[], unsigned int iov_size,
unsigned int *out_num, unsigned int *in_num,
struct vhost_log *log, unsigned int *log_num)
{
struct vring_desc desc;
unsigned int i, head, found = 0;
u16 last_avail_idx;
int ret;
/* Check it isn't doing very strange things with descriptor numbers. */
last_avail_idx = vq->last_avail_idx;
if (get_user(vq->avail_idx, &vq->avail->idx)) {
vq_err(vq, "Failed to access avail idx at %p\n",
&vq->avail->idx);
return vq->num;
}
if ((u16)(vq->avail_idx - last_avail_idx) > vq->num) {
vq_err(vq, "Guest moved used index from %u to %u",
last_avail_idx, vq->avail_idx);
return vq->num;
}
/* If there's nothing new since last we looked, return invalid. */
if (vq->avail_idx == last_avail_idx)
return vq->num;
/* Only get avail ring entries after they have been exposed by guest. */
smp_rmb();
/* Grab the next descriptor number they're advertising, and increment
* the index we've seen. */
if (get_user(head, &vq->avail->ring[last_avail_idx % vq->num])) {
vq_err(vq, "Failed to read head: idx %d address %p\n",
last_avail_idx,
&vq->avail->ring[last_avail_idx % vq->num]);
return vq->num;
}
/* If their number is silly, that's an error. */
if (head >= vq->num) {
vq_err(vq, "Guest says index %u > %u is available",
head, vq->num);
return vq->num;
}
/* When we start there are none of either input nor output. */
*out_num = *in_num = 0;
if (unlikely(log))
*log_num = 0;
i = head;
do {
unsigned iov_count = *in_num + *out_num;
if (i >= vq->num) {
vq_err(vq, "Desc index is %u > %u, head = %u",
i, vq->num, head);
return vq->num;
}
if (++found > vq->num) {
vq_err(vq, "Loop detected: last one at %u "
"vq size %u head %u\n",
i, vq->num, head);
return vq->num;
}
ret = copy_from_user(&desc, vq->desc + i, sizeof desc);
if (ret) {
vq_err(vq, "Failed to get descriptor: idx %d addr %p\n",
i, vq->desc + i);
return vq->num;
}
if (desc.flags & VRING_DESC_F_INDIRECT) {
ret = get_indirect(dev, vq, iov, iov_size,
out_num, in_num,
log, log_num, &desc);
if (ret < 0) {
vq_err(vq, "Failure detected "
"in indirect descriptor at idx %d\n", i);
return vq->num;
}
continue;
}
ret = translate_desc(dev, desc.addr, desc.len, iov + iov_count,
iov_size - iov_count);
if (ret < 0) {
vq_err(vq, "Translation failure %d descriptor idx %d\n",
ret, i);
return vq->num;
}
if (desc.flags & VRING_DESC_F_WRITE) {
/* If this is an input descriptor,
* increment that count. */
*in_num += ret;
if (unlikely(log)) {
log[*log_num].addr = desc.addr;
log[*log_num].len = desc.len;
++*log_num;
}
} else {
/* If it's an output descriptor, they're all supposed
* to come before any input descriptors. */
if (*in_num) {
vq_err(vq, "Descriptor has out after in: "
"idx %d\n", i);
return vq->num;
}
*out_num += ret;
}
} while ((i = next_desc(&desc)) != -1);
/* On success, increment avail index. */
vq->last_avail_idx++;
return head;
}
static unsigned get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq,
struct iovec iov[], unsigned int iov_size,
unsigned int *out_num, unsigned int *in_num,
struct vhost_log *log, unsigned int *log_num,
struct vring_desc *indirect)
{
struct vring_desc desc;
unsigned int i = 0, count, found = 0;
int ret;
/* Sanity check */
if (indirect->len % sizeof desc) {
vq_err(vq, "Invalid length in indirect descriptor: "
"len 0x%llx not multiple of 0x%zx\n",
(unsigned long long)indirect->len,
sizeof desc);
return -EINVAL;
}
ret = translate_desc(dev, indirect->addr, indirect->len, vq->indirect,
ARRAY_SIZE(vq->indirect));
if (ret < 0) {
vq_err(vq, "Translation failure %d in indirect.\n", ret);
return ret;
}
/* We will use the result as an address to read from, so most
* architectures only need a compiler barrier here. */
read_barrier_depends();
count = indirect->len / sizeof desc;
/* Buffers are chained via a 16 bit next field, so
* we can have at most 2^16 of these. */
if (count > USHORT_MAX + 1) {
vq_err(vq, "Indirect buffer length too big: %d\n",
indirect->len);
return -E2BIG;
}
do {
unsigned iov_count = *in_num + *out_num;
if (++found > count) {
vq_err(vq, "Loop detected: last one at %u "
"indirect size %u\n",
i, count);
return -EINVAL;
}
if (memcpy_fromiovec((unsigned char *)&desc, vq->indirect,
sizeof desc)) {
vq_err(vq, "Failed indirect descriptor: idx %d, %zx\n",
i, (size_t)indirect->addr + i * sizeof desc);
return -EINVAL;
}
if (desc.flags & VRING_DESC_F_INDIRECT) {
vq_err(vq, "Nested indirect descriptor: idx %d, %zx\n",
i, (size_t)indirect->addr + i * sizeof desc);
return -EINVAL;
}
ret = translate_desc(dev, desc.addr, desc.len, iov + iov_count,
iov_size - iov_count);
if (ret < 0) {
vq_err(vq, "Translation failure %d indirect idx %d\n",
ret, i);
return ret;
}
/* If this is an input descriptor, increment that count. */
if (desc.flags & VRING_DESC_F_WRITE) {
*in_num += ret;
if (unlikely(log)) {
log[*log_num].addr = desc.addr;
log[*log_num].len = desc.len;
++*log_num;
}
} else {
/* If it's an output descriptor, they're all supposed
* to come before any input descriptors. */
if (*in_num) {
vq_err(vq, "Indirect descriptor "
"has out after in: idx %d\n", i);
return -EINVAL;
}
*out_num += ret;
}
} while ((i = next_desc(&desc)) != -1);
return 0;
}
static void handle_tx(struct vhost_net *net)
{
struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_TX];
unsigned out, in, s;
int head;
struct msghdr msg = {
.msg_name = NULL,
.msg_namelen = 0,
.msg_control = NULL,
.msg_controllen = 0,
.msg_iov = vq->iov,
.msg_flags = MSG_DONTWAIT,
};
size_t len, total_len = 0;
int err, wmem;
size_t hdr_size;
struct socket *sock = rcu_dereference(vq->private_data);
if (!sock)
return;
wmem = atomic_read(&sock->sk->sk_wmem_alloc);
if (wmem >= sock->sk->sk_sndbuf) {
mutex_lock(&vq->mutex);
tx_poll_start(net, sock);
mutex_unlock(&vq->mutex);
return;
}
use_mm(net->dev.mm);
mutex_lock(&vq->mutex);
vhost_disable_notify(vq);
if (wmem < sock->sk->sk_sndbuf / 2)
tx_poll_stop(net);
hdr_size = vq->hdr_size;
for (;;) {
head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
ARRAY_SIZE(vq->iov),
&out, &in,
NULL, NULL);
/* On error, stop handling until the next kick. */
if (unlikely(head < 0))
break;
/* Nothing new? Wait for eventfd to tell us they refilled. */
if (head == vq->num) {
wmem = atomic_read(&sock->sk->sk_wmem_alloc);
if (wmem >= sock->sk->sk_sndbuf * 3 / 4) {
tx_poll_start(net, sock);
set_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
break;
}
if (unlikely(vhost_enable_notify(vq))) {
vhost_disable_notify(vq);
continue;
}
break;
}
if (in) {
vq_err(vq, "Unexpected descriptor format for TX: "
"out %d, int %d\n", out, in);
break;
}
/* Skip header. TODO: support TSO. */
s = move_iovec_hdr(vq->iov, vq->hdr, hdr_size, out);
msg.msg_iovlen = out;
len = iov_length(vq->iov, out);
/* Sanity check */
if (!len) {
vq_err(vq, "Unexpected header len for TX: "
"%zd expected %zd\n",
iov_length(vq->hdr, s), hdr_size);
break;
}
/* TODO: Check specific error and bomb out unless ENOBUFS? */
err = sock->ops->sendmsg(NULL, sock, &msg, len);
if (unlikely(err < 0)) {
vhost_discard_vq_desc(vq);
tx_poll_start(net, sock);
break;
}
if (err != len)
pr_debug("Truncated TX packet: "
" len %d != %zd\n", err, len);
vhost_add_used_and_signal(&net->dev, vq, head, 0);
total_len += len;
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
vhost_poll_queue(&vq->poll);
break;
}
}
mutex_unlock(&vq->mutex);
unuse_mm(net->dev.mm);
}
static void handle_rx(struct vhost_net *net)
{
struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX];
unsigned out, in, log, s;
int head;
struct vhost_log *vq_log;
struct msghdr msg = {
.msg_name = NULL,
.msg_namelen = 0,
.msg_control = NULL, /* FIXME: get and handle RX aux data. */
.msg_controllen = 0,
.msg_iov = vq->iov,
.msg_flags = MSG_DONTWAIT,
};
struct virtio_net_hdr hdr = {
.flags = 0,
.gso_type = VIRTIO_NET_HDR_GSO_NONE
};
size_t len, total_len = 0;
int err;
size_t hdr_size;
struct socket *sock = rcu_dereference(vq->private_data);
if (!sock || skb_queue_empty(&sock->sk->sk_receive_queue))
return;
use_mm(net->dev.mm);
mutex_lock(&vq->mutex);
vhost_disable_notify(vq);
hdr_size = vq->hdr_size;
vq_log = unlikely(vhost_has_feature(&net->dev, VHOST_F_LOG_ALL)) ?
vq->log : NULL;
for (;;) {
head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
ARRAY_SIZE(vq->iov),
&out, &in,
vq_log, &log);
/* On error, stop handling until the next kick. */
if (unlikely(head < 0))
break;
/* OK, now we need to know about added descriptors. */
if (head == vq->num) {
if (unlikely(vhost_enable_notify(vq))) {
/* They have slipped one in as we were
* doing that: check again. */
vhost_disable_notify(vq);
continue;
}
/* Nothing new? Wait for eventfd to tell us
* they refilled. */
break;
}
/* We don't need to be notified again. */
if (out) {
vq_err(vq, "Unexpected descriptor format for RX: "
"out %d, int %d\n",
out, in);
break;
}
/* Skip header. TODO: support TSO/mergeable rx buffers. */
s = move_iovec_hdr(vq->iov, vq->hdr, hdr_size, in);
msg.msg_iovlen = in;
len = iov_length(vq->iov, in);
/* Sanity check */
if (!len) {
vq_err(vq, "Unexpected header len for RX: "
"%zd expected %zd\n",
iov_length(vq->hdr, s), hdr_size);
break;
}
err = sock->ops->recvmsg(NULL, sock, &msg,
len, MSG_DONTWAIT | MSG_TRUNC);
/* TODO: Check specific error and bomb out unless EAGAIN? */
if (err < 0) {
vhost_discard_vq_desc(vq);
break;
}
/* TODO: Should check and handle checksum. */
if (err > len) {
pr_debug("Discarded truncated rx packet: "
" len %d > %zd\n", err, len);
vhost_discard_vq_desc(vq);
continue;
}
len = err;
err = memcpy_toiovec(vq->hdr, (unsigned char *)&hdr, hdr_size);
if (err) {
vq_err(vq, "Unable to write vnet_hdr at addr %p: %d\n",
vq->iov->iov_base, err);
break;
}
len += hdr_size;
vhost_add_used_and_signal(&net->dev, vq, head, len);
if (unlikely(vq_log))
vhost_log_write(vq, vq_log, log, len);
total_len += len;
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
vhost_poll_queue(&vq->poll);
break;
}
}
mutex_unlock(&vq->mutex);
unuse_mm(net->dev.mm);
}
static void handle_tx_kick(struct work_struct *work)
{
struct vhost_virtqueue *vq;
struct vhost_net *net;
vq = container_of(work, struct vhost_virtqueue, poll.work);
net = container_of(vq->dev, struct vhost_net, dev);
handle_tx(net);
}
static void handle_rx_kick(struct work_struct *work)
{
struct vhost_virtqueue *vq;
struct vhost_net *net;
vq = container_of(work, struct vhost_virtqueue, poll.work);
net = container_of(vq->dev, struct vhost_net, dev);
handle_rx(net);
}
static void handle_tx_net(struct work_struct *work)
{
struct vhost_net *net;
net = container_of(work, struct vhost_net, poll[VHOST_NET_VQ_TX].work);
handle_tx(net);
}
static void handle_rx_net(struct work_struct *work)
{
struct vhost_net *net;
net = container_of(work, struct vhost_net, poll[VHOST_NET_VQ_RX].work);
handle_rx(net);
}
static int vhost_net_open(struct inode *inode, struct file *f)
{
struct vhost_net *n = kmalloc(sizeof *n, GFP_KERNEL);
int r;
if (!n)
return -ENOMEM;
n->vqs[VHOST_NET_VQ_TX].handle_kick = handle_tx_kick;
n->vqs[VHOST_NET_VQ_RX].handle_kick = handle_rx_kick;
r = vhost_dev_init(&n->dev, n->vqs, VHOST_NET_VQ_MAX);
if (r < 0) {
kfree(n);
return r;
}
vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT);
vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN);
n->tx_poll_state = VHOST_NET_POLL_DISABLED;
f->private_data = n;
return 0;
}
static void vhost_net_disable_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
if (!vq->private_data)
return;
if (vq == n->vqs + VHOST_NET_VQ_TX) {
tx_poll_stop(n);
n->tx_poll_state = VHOST_NET_POLL_DISABLED;
} else
vhost_poll_stop(n->poll + VHOST_NET_VQ_RX);
}
static void vhost_net_enable_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
struct socket *sock = vq->private_data;
if (!sock)
return;
if (vq == n->vqs + VHOST_NET_VQ_TX) {
n->tx_poll_state = VHOST_NET_POLL_STOPPED;
tx_poll_start(n, sock);
} else
vhost_poll_start(n->poll + VHOST_NET_VQ_RX, sock->file);
}
static struct socket *vhost_net_stop_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
struct socket *sock;
mutex_lock(&vq->mutex);
sock = vq->private_data;
vhost_net_disable_vq(n, vq);
rcu_assign_pointer(vq->private_data, NULL);
mutex_unlock(&vq->mutex);
return sock;
}
static void vhost_net_stop(struct vhost_net *n, struct socket **tx_sock,
struct socket **rx_sock)
{
*tx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_TX);
*rx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_RX);
}
static void vhost_net_flush_vq(struct vhost_net *n, int index)
{
vhost_poll_flush(n->poll + index);
vhost_poll_flush(&n->dev.vqs[index].poll);
}
static void vhost_net_flush(struct vhost_net *n)
{
vhost_net_flush_vq(n, VHOST_NET_VQ_TX);
vhost_net_flush_vq(n, VHOST_NET_VQ_RX);
}
/* Expects to be always run from workqueue - which acts as
* read-size critical section for our kind of RCU. */
static void handle_rx_big(struct vhost_net *net)
{
struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX];
unsigned out, in, log, s;
int head;
struct vhost_log *vq_log;
struct msghdr msg = {
.msg_name = NULL,
.msg_namelen = 0,
.msg_control = NULL, /* FIXME: get and handle RX aux data. */
.msg_controllen = 0,
.msg_iov = vq->iov,
.msg_flags = MSG_DONTWAIT,
};
struct virtio_net_hdr hdr = {
.flags = 0,
.gso_type = VIRTIO_NET_HDR_GSO_NONE
};
size_t len, total_len = 0;
int err;
size_t hdr_size;
struct socket *sock = rcu_dereference(vq->private_data);
if (!sock || skb_queue_empty(&sock->sk->sk_receive_queue))
return;
use_mm(net->dev.mm);
mutex_lock(&vq->mutex);
vhost_disable_notify(vq);
hdr_size = vq->vhost_hlen;
vq_log = unlikely(vhost_has_feature(&net->dev, VHOST_F_LOG_ALL)) ?
vq->log : NULL;
for (;;) {
head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
ARRAY_SIZE(vq->iov),
&out, &in,
vq_log, &log);
/* On error, stop handling until the next kick. */
if (unlikely(head < 0))
break;
/* OK, now we need to know about added descriptors. */
if (head == vq->num) {
if (unlikely(vhost_enable_notify(vq))) {
/* They have slipped one in as we were
* doing that: check again. */
vhost_disable_notify(vq);
continue;
}
/* Nothing new? Wait for eventfd to tell us
* they refilled. */
break;
}
/* We don't need to be notified again. */
if (out) {
vq_err(vq, "Unexpected descriptor format for RX: "
"out %d, int %d\n",
out, in);
break;
}
/* Skip header. TODO: support TSO/mergeable rx buffers. */
s = move_iovec_hdr(vq->iov, vq->hdr, hdr_size, in);
msg.msg_iovlen = in;
len = iov_length(vq->iov, in);
/* Sanity check */
if (!len) {
vq_err(vq, "Unexpected header len for RX: "
"%zd expected %zd\n",
iov_length(vq->hdr, s), hdr_size);
break;
}
err = sock->ops->recvmsg(NULL, sock, &msg,
len, MSG_DONTWAIT | MSG_TRUNC);
/* TODO: Check specific error and bomb out unless EAGAIN? */
if (err < 0) {
vhost_discard_vq_desc(vq, 1);
break;
}
/* TODO: Should check and handle checksum. */
if (err > len) {
pr_debug("Discarded truncated rx packet: "
" len %d > %zd\n", err, len);
vhost_discard_vq_desc(vq, 1);
continue;
}
len = err;
err = memcpy_toiovec(vq->hdr, (unsigned char *)&hdr, hdr_size);
if (err) {
vq_err(vq, "Unable to write vnet_hdr at addr %p: %d\n",
vq->iov->iov_base, err);
break;
}
len += hdr_size;
vhost_add_used_and_signal(&net->dev, vq, head, len);
if (unlikely(vq_log))
vhost_log_write(vq, vq_log, log, len);
total_len += len;
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
vhost_poll_queue(&vq->poll);
break;
}
}
mutex_unlock(&vq->mutex);
unuse_mm(net->dev.mm);
}
/* Expects to be always run from workqueue - which acts as
* read-size critical section for our kind of RCU. */
static void handle_rx_mergeable(struct vhost_net *net)
{
struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX];
unsigned uninitialized_var(in), log;
struct vhost_log *vq_log;
struct msghdr msg = {
.msg_name = NULL,
.msg_namelen = 0,
.msg_control = NULL, /* FIXME: get and handle RX aux data. */
.msg_controllen = 0,
.msg_iov = vq->iov,
.msg_flags = MSG_DONTWAIT,
};
struct virtio_net_hdr_mrg_rxbuf hdr = {
.hdr.flags = 0,
.hdr.gso_type = VIRTIO_NET_HDR_GSO_NONE
};
size_t total_len = 0;
int err, headcount;
size_t vhost_hlen, sock_hlen;
size_t vhost_len, sock_len;
struct socket *sock = rcu_dereference(vq->private_data);
if (!sock || skb_queue_empty(&sock->sk->sk_receive_queue))
return;
use_mm(net->dev.mm);
mutex_lock(&vq->mutex);
vhost_disable_notify(vq);
vhost_hlen = vq->vhost_hlen;
sock_hlen = vq->sock_hlen;
vq_log = unlikely(vhost_has_feature(&net->dev, VHOST_F_LOG_ALL)) ?
vq->log : NULL;
while ((sock_len = peek_head_len(sock->sk))) {
sock_len += sock_hlen;
vhost_len = sock_len + vhost_hlen;
headcount = get_rx_bufs(vq, vq->heads, vhost_len,
&in, vq_log, &log);
/* On error, stop handling until the next kick. */
if (unlikely(headcount < 0))
break;
/* OK, now we need to know about added descriptors. */
if (!headcount) {
if (unlikely(vhost_enable_notify(vq))) {
/* They have slipped one in as we were
* doing that: check again. */
vhost_disable_notify(vq);
continue;
}
/* Nothing new? Wait for eventfd to tell us
* they refilled. */
break;
}
/* We don't need to be notified again. */
if (unlikely((vhost_hlen)))
/* Skip header. TODO: support TSO. */
move_iovec_hdr(vq->iov, vq->hdr, vhost_hlen, in);
else
/* Copy the header for use in VIRTIO_NET_F_MRG_RXBUF:
* needed because sendmsg can modify msg_iov. */
copy_iovec_hdr(vq->iov, vq->hdr, sock_hlen, in);
msg.msg_iovlen = in;
err = sock->ops->recvmsg(NULL, sock, &msg,
sock_len, MSG_DONTWAIT | MSG_TRUNC);
/* Userspace might have consumed the packet meanwhile:
* it's not supposed to do this usually, but might be hard
* to prevent. Discard data we got (if any) and keep going. */
if (unlikely(err != sock_len)) {
pr_debug("Discarded rx packet: "
" len %d, expected %zd\n", err, sock_len);
vhost_discard_vq_desc(vq, headcount);
continue;
}
if (unlikely(vhost_hlen) &&
memcpy_toiovecend(vq->hdr, (unsigned char *)&hdr, 0,
vhost_hlen)) {
vq_err(vq, "Unable to write vnet_hdr at addr %p\n",
vq->iov->iov_base);
break;
}
/* TODO: Should check and handle checksum. */
if (vhost_has_feature(&net->dev, VIRTIO_NET_F_MRG_RXBUF) &&
memcpy_toiovecend(vq->hdr, (unsigned char *)&headcount,
offsetof(typeof(hdr), num_buffers),
sizeof hdr.num_buffers)) {
vq_err(vq, "Failed num_buffers write");
vhost_discard_vq_desc(vq, headcount);
break;
}
vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
headcount);
if (unlikely(vq_log))
vhost_log_write(vq, vq_log, log, vhost_len);
total_len += vhost_len;
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
vhost_poll_queue(&vq->poll);
break;
}
}
mutex_unlock(&vq->mutex);
unuse_mm(net->dev.mm);
}
static void handle_rx(struct vhost_net *net)
{
if (vhost_has_feature(&net->dev, VIRTIO_NET_F_MRG_RXBUF))
handle_rx_mergeable(net);
else
handle_rx_big(net);
}
static void handle_tx_kick(struct vhost_work *work)
{
struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
poll.work);
struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev);
handle_tx(net);
}
static void handle_rx_kick(struct vhost_work *work)
{
struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
poll.work);
struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev);
handle_rx(net);
}
static void handle_tx_net(struct vhost_work *work)
{
struct vhost_net *net = container_of(work, struct vhost_net,
poll[VHOST_NET_VQ_TX].work);
handle_tx(net);
}
static void handle_rx_net(struct vhost_work *work)
{
struct vhost_net *net = container_of(work, struct vhost_net,
poll[VHOST_NET_VQ_RX].work);
handle_rx(net);
}
static int vhost_net_open(struct inode *inode, struct file *f)
{
struct vhost_net *n = kmalloc(sizeof *n, GFP_KERNEL);
struct vhost_dev *dev;
int r;
if (!n)
return -ENOMEM;
dev = &n->dev;
n->vqs[VHOST_NET_VQ_TX].handle_kick = handle_tx_kick;
n->vqs[VHOST_NET_VQ_RX].handle_kick = handle_rx_kick;
r = vhost_dev_init(dev, n->vqs, VHOST_NET_VQ_MAX);
if (r < 0) {
kfree(n);
return r;
}
vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT, dev);
vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN, dev);
n->tx_poll_state = VHOST_NET_POLL_DISABLED;
f->private_data = n;
return 0;
}
static void vhost_net_disable_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
if (!vq->private_data)
return;
if (vq == n->vqs + VHOST_NET_VQ_TX) {
tx_poll_stop(n);
n->tx_poll_state = VHOST_NET_POLL_DISABLED;
} else
vhost_poll_stop(n->poll + VHOST_NET_VQ_RX);
}
static void vhost_net_enable_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
struct socket *sock;
sock = rcu_dereference_protected(vq->private_data,
lockdep_is_held(&vq->mutex));
if (!sock)
return;
if (vq == n->vqs + VHOST_NET_VQ_TX) {
n->tx_poll_state = VHOST_NET_POLL_STOPPED;
tx_poll_start(n, sock);
} else
vhost_poll_start(n->poll + VHOST_NET_VQ_RX, sock->file);
}
static struct socket *vhost_net_stop_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
struct socket *sock;
mutex_lock(&vq->mutex);
sock = rcu_dereference_protected(vq->private_data,
lockdep_is_held(&vq->mutex));
vhost_net_disable_vq(n, vq);
rcu_assign_pointer(vq->private_data, NULL);
mutex_unlock(&vq->mutex);
return sock;
}
static void vhost_net_stop(struct vhost_net *n, struct socket **tx_sock,
struct socket **rx_sock)
{
*tx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_TX);
*rx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_RX);
}
static void vhost_net_flush_vq(struct vhost_net *n, int index)
{
vhost_poll_flush(n->poll + index);
vhost_poll_flush(&n->dev.vqs[index].poll);
}
static void vhost_net_flush(struct vhost_net *n)
{
vhost_net_flush_vq(n, VHOST_NET_VQ_TX);
vhost_net_flush_vq(n, VHOST_NET_VQ_RX);
}
static int vhost_net_release(struct inode *inode, struct file *f)
{
struct vhost_net *n = f->private_data;
struct socket *tx_sock;
struct socket *rx_sock;
vhost_net_stop(n, &tx_sock, &rx_sock);
vhost_net_flush(n);
vhost_dev_cleanup(&n->dev);
if (tx_sock)
fput(tx_sock->file);
if (rx_sock)
fput(rx_sock->file);
/* We do an extra flush before freeing memory,
* since jobs can re-queue themselves. */
vhost_net_flush(n);
kfree(n);
return 0;
}
static struct socket *get_raw_socket(int fd)
{
struct {
struct sockaddr_ll sa;
char buf[MAX_ADDR_LEN];
} uaddr;
int uaddr_len = sizeof uaddr, r;
struct socket *sock = sockfd_lookup(fd, &r);
if (!sock)
return ERR_PTR(-ENOTSOCK);
/* Parameter checking */
if (sock->sk->sk_type != SOCK_RAW) {
r = -ESOCKTNOSUPPORT;
goto err;
}
r = sock->ops->getname(sock, (struct sockaddr *)&uaddr.sa,
&uaddr_len, 0);
if (r)
goto err;
if (uaddr.sa.sll_family != AF_PACKET) {
r = -EPFNOSUPPORT;
goto err;
}
return sock;
err:
fput(sock->file);
return ERR_PTR(r);
}
static struct socket *get_tap_socket(int fd)
{
struct file *file = fget(fd);
struct socket *sock;
if (!file)
return ERR_PTR(-EBADF);
sock = tun_get_socket(file);
if (!IS_ERR(sock))
return sock;
sock = macvtap_get_socket(file);
if (IS_ERR(sock))
fput(file);
return sock;
}
static struct socket *get_socket(int fd)
{
struct socket *sock;
/* special case to disable backend */
if (fd == -1)
return NULL;
sock = get_raw_socket(fd);
if (!IS_ERR(sock))
return sock;
sock = get_tap_socket(fd);
if (!IS_ERR(sock))
return sock;
return ERR_PTR(-ENOTSOCK);
}
static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
{
struct socket *sock, *oldsock;
struct vhost_virtqueue *vq;
int r;
mutex_lock(&n->dev.mutex);
r = vhost_dev_check_owner(&n->dev);
if (r)
goto err;
if (index >= VHOST_NET_VQ_MAX) {
r = -ENOBUFS;
goto err;
}
vq = n->vqs + index;
mutex_lock(&vq->mutex);
/* Verify that ring has been setup correctly. */
if (!vhost_vq_access_ok(vq)) {
r = -EFAULT;
goto err_vq;
}
sock = get_socket(fd);
if (IS_ERR(sock)) {
r = PTR_ERR(sock);
goto err_vq;
}
/* start polling new socket */
oldsock = rcu_dereference_protected(vq->private_data,
lockdep_is_held(&vq->mutex));
if (sock != oldsock) {
vhost_net_disable_vq(n, vq);
rcu_assign_pointer(vq->private_data, sock);
vhost_net_enable_vq(n, vq);
}
mutex_unlock(&vq->mutex);
if (oldsock) {
vhost_net_flush_vq(n, index);
fput(oldsock->file);
}
mutex_unlock(&n->dev.mutex);
return 0;
err_vq:
mutex_unlock(&vq->mutex);
err:
mutex_unlock(&n->dev.mutex);
return r;
}
static long vhost_net_reset_owner(struct vhost_net *n)
{
struct socket *tx_sock = NULL;
struct socket *rx_sock = NULL;
long err;
mutex_lock(&n->dev.mutex);
err = vhost_dev_check_owner(&n->dev);
if (err)
goto done;
vhost_net_stop(n, &tx_sock, &rx_sock);
vhost_net_flush(n);
err = vhost_dev_reset_owner(&n->dev);
done:
mutex_unlock(&n->dev.mutex);
if (tx_sock)
fput(tx_sock->file);
if (rx_sock)
fput(rx_sock->file);
return err;
}
static int vhost_net_set_features(struct vhost_net *n, u64 features)
{
size_t vhost_hlen, sock_hlen, hdr_len;
int i;
hdr_len = (features & (1 << VIRTIO_NET_F_MRG_RXBUF)) ?
sizeof(struct virtio_net_hdr_mrg_rxbuf) :
sizeof(struct virtio_net_hdr);
if (features & (1 << VHOST_NET_F_VIRTIO_NET_HDR)) {
/* vhost provides vnet_hdr */
vhost_hlen = hdr_len;
sock_hlen = 0;
} else {
/* socket provides vnet_hdr */
vhost_hlen = 0;
sock_hlen = hdr_len;
}
mutex_lock(&n->dev.mutex);
if ((features & (1 << VHOST_F_LOG_ALL)) &&
!vhost_log_access_ok(&n->dev)) {
mutex_unlock(&n->dev.mutex);
return -EFAULT;
}
n->dev.acked_features = features;
smp_wmb();
for (i = 0; i < VHOST_NET_VQ_MAX; ++i) {
mutex_lock(&n->vqs[i].mutex);
n->vqs[i].vhost_hlen = vhost_hlen;
n->vqs[i].sock_hlen = sock_hlen;
mutex_unlock(&n->vqs[i].mutex);
}
vhost_net_flush(n);
mutex_unlock(&n->dev.mutex);
return 0;
}