size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
struct iov_iter *i)
{
if (i->type & (ITER_BVEC|ITER_KVEC)) {
void *kaddr = kmap_atomic(page);
size_t wanted = copy_to_iter(kaddr + offset, bytes, i);
kunmap_atomic(kaddr);
return wanted;
} else
return copy_page_to_iter_iovec(page, offset, bytes, i);
}
static ssize_t hypfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
char *data = file->private_data;
size_t available = strlen(data);
loff_t pos = iocb->ki_pos;
size_t count;
if (pos < 0)
return -EINVAL;
if (pos >= available || !iov_iter_count(to))
return 0;
count = copy_to_iter(data + pos, available - pos, to);
if (!count)
return -EFAULT;
iocb->ki_pos = pos + count;
file_accessed(file);
return count;
}
static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
loff_t start, loff_t end, get_block_t get_block,
struct buffer_head *bh)
{
loff_t pos = start, max = start, bh_max = start;
bool hole = false, need_wmb = false;
struct block_device *bdev = NULL;
int rw = iov_iter_rw(iter), rc;
long map_len = 0;
struct blk_dax_ctl dax = {
.addr = (void __pmem *) ERR_PTR(-EIO),
};
if (rw == READ)
end = min(end, i_size_read(inode));
while (pos < end) {
size_t len;
if (pos == max) {
unsigned blkbits = inode->i_blkbits;
long page = pos >> PAGE_SHIFT;
sector_t block = page << (PAGE_SHIFT - blkbits);
unsigned first = pos - (block << blkbits);
long size;
if (pos == bh_max) {
bh->b_size = PAGE_ALIGN(end - pos);
bh->b_state = 0;
rc = get_block(inode, block, bh, rw == WRITE);
if (rc)
break;
if (!buffer_size_valid(bh))
bh->b_size = 1 << blkbits;
bh_max = pos - first + bh->b_size;
bdev = bh->b_bdev;
} else {
unsigned done = bh->b_size -
(bh_max - (pos - first));
bh->b_blocknr += done >> blkbits;
bh->b_size -= done;
}
hole = rw == READ && !buffer_written(bh);
if (hole) {
size = bh->b_size - first;
} else {
dax_unmap_atomic(bdev, &dax);
dax.sector = to_sector(bh, inode);
dax.size = bh->b_size;
map_len = dax_map_atomic(bdev, &dax);
if (map_len < 0) {
rc = map_len;
break;
}
if (buffer_unwritten(bh) || buffer_new(bh)) {
dax_new_buf(dax.addr, map_len, first,
pos, end);
need_wmb = true;
}
dax.addr += first;
size = map_len - first;
}
max = min(pos + size, end);
}
if (iov_iter_rw(iter) == WRITE) {
len = copy_from_iter_pmem(dax.addr, max - pos, iter);
need_wmb = true;
} else if (!hole)
len = copy_to_iter((void __force *) dax.addr, max - pos,
iter);
else
len = iov_iter_zero(max - pos, iter);
if (!len) {
rc = -EFAULT;
break;
}
pos += len;
if (!IS_ERR(dax.addr))
dax.addr += len;
}
if (need_wmb)
wmb_pmem();
dax_unmap_atomic(bdev, &dax);
return (pos == start) ? rc : pos - start;
}
static size_t dcssblk_dax_copy_to_iter(struct dax_device *dax_dev,
pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i)
{
return copy_to_iter(addr, bytes, i);
}
static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
loff_t start, loff_t end, get_block_t get_block,
struct buffer_head *bh)
{
loff_t pos = start, max = start, bh_max = start;
bool hole = false, need_wmb = false;
struct block_device *bdev = NULL;
int rw = iov_iter_rw(iter), rc;
long map_len = 0;
struct blk_dax_ctl dax = {
.addr = (void __pmem *) ERR_PTR(-EIO),
};
unsigned blkbits = inode->i_blkbits;
sector_t file_blks = (i_size_read(inode) + (1 << blkbits) - 1)
>> blkbits;
if (rw == READ)
end = min(end, i_size_read(inode));
while (pos < end) {
size_t len;
if (pos == max) {
long page = pos >> PAGE_SHIFT;
sector_t block = page << (PAGE_SHIFT - blkbits);
unsigned first = pos - (block << blkbits);
long size;
if (pos == bh_max) {
bh->b_size = PAGE_ALIGN(end - pos);
bh->b_state = 0;
rc = get_block(inode, block, bh, rw == WRITE);
if (rc)
break;
if (!buffer_size_valid(bh))
bh->b_size = 1 << blkbits;
bh_max = pos - first + bh->b_size;
bdev = bh->b_bdev;
/*
* We allow uninitialized buffers for writes
* beyond EOF as those cannot race with faults
*/
WARN_ON_ONCE(
(buffer_new(bh) && block < file_blks) ||
(rw == WRITE && buffer_unwritten(bh)));
} else {
unsigned done = bh->b_size -
(bh_max - (pos - first));
bh->b_blocknr += done >> blkbits;
bh->b_size -= done;
}
hole = rw == READ && !buffer_written(bh);
if (hole) {
size = bh->b_size - first;
} else {
dax_unmap_atomic(bdev, &dax);
dax.sector = to_sector(bh, inode);
dax.size = bh->b_size;
map_len = dax_map_atomic(bdev, &dax);
if (map_len < 0) {
rc = map_len;
break;
}
dax.addr += first;
size = map_len - first;
}
/*
* pos + size is one past the last offset for IO,
* so pos + size can overflow loff_t at extreme offsets.
* Cast to u64 to catch this and get the true minimum.
*/
max = min_t(u64, pos + size, end);
}
if (iov_iter_rw(iter) == WRITE) {
len = copy_from_iter_pmem(dax.addr, max - pos, iter);
need_wmb = true;
} else if (!hole)
len = copy_to_iter((void __force *) dax.addr, max - pos,
iter);
else
len = iov_iter_zero(max - pos, iter);
if (!len) {
rc = -EFAULT;
break;
}
pos += len;
if (!IS_ERR(dax.addr))
dax.addr += len;
}
if (need_wmb)
wmb_pmem();
dax_unmap_atomic(bdev, &dax);
return (pos == start) ? rc : pos - start;
}
kni_sock_rcvmsg(struct socket *sock,
struct msghdr *m, size_t len, int flags)
#endif /* HAVE_KIOCB_MSG_PARAM */
{
int vnet_hdr_len = 0;
int pkt_len = 0;
struct kni_vhost_queue *q =
container_of(sock->sk, struct kni_vhost_queue, sk);
static struct virtio_net_hdr
__attribute__ ((unused)) vnet_hdr = {
.flags = 0,
.gso_type = VIRTIO_NET_HDR_GSO_NONE
};
if (unlikely(q == NULL || q->kni == NULL))
return 0;
#ifdef RTE_KNI_VHOST_VNET_HDR_EN
if (likely(q->flags & IFF_VNET_HDR)) {
vnet_hdr_len = q->vnet_hdr_sz;
if ((len -= vnet_hdr_len) < 0)
return -EINVAL;
}
#endif
if (unlikely(0 == (pkt_len = kni_vhost_net_rx(q->kni,
m, vnet_hdr_len, len))))
return 0;
#ifdef RTE_KNI_VHOST_VNET_HDR_EN
/* no need to copy hdr when no pkt received */
#ifdef HAVE_IOV_ITER_MSGHDR
if (unlikely(copy_to_iter((void *)&vnet_hdr, vnet_hdr_len,
&m->msg_iter)))
#else
if (unlikely(memcpy_toiovecend(m->msg_iov,
(void *)&vnet_hdr, 0, vnet_hdr_len)))
#endif /* HAVE_IOV_ITER_MSGHDR */
return -EFAULT;
#endif /* RTE_KNI_VHOST_VNET_HDR_EN */
KNI_DBG_RX("kni_rcvmsg expect_len %ld, flags 0x%08x, pkt_len %d\n",
(unsigned long)len, q->flags, pkt_len);
return (pkt_len + vnet_hdr_len);
}
/* dummy tap like ioctl */
static int
kni_sock_ioctl(struct socket *sock, unsigned int cmd,
unsigned long arg)
{
void __user *argp = (void __user *)arg;
struct ifreq __user *ifr = argp;
unsigned int __user *up = argp;
struct kni_vhost_queue *q =
container_of(sock->sk, struct kni_vhost_queue, sk);
struct kni_dev *kni;
unsigned int u;
int __user *sp = argp;
int s;
int ret;
KNI_DBG("tap ioctl cmd 0x%08x\n", cmd);
switch (cmd) {
case TUNSETIFF:
KNI_DBG("TUNSETIFF\n");
/* 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:
KNI_DBG("TUNGETIFF\n");
rcu_read_lock_bh();
kni = rcu_dereference_bh(q->kni);
if (kni)
dev_hold(kni->net_dev);
rcu_read_unlock_bh();
if (!kni)
return -ENOLINK;
ret = 0;
if (copy_to_user(&ifr->ifr_name, kni->net_dev->name, IFNAMSIZ) ||
put_user(q->flags, &ifr->ifr_flags))
ret = -EFAULT;
dev_put(kni->net_dev);
return ret;
case TUNGETFEATURES:
KNI_DBG("TUNGETFEATURES\n");
u = IFF_TAP | IFF_NO_PI;
#ifdef RTE_KNI_VHOST_VNET_HDR_EN
u |= IFF_VNET_HDR;
#endif
if (put_user(u, up))
return -EFAULT;
return 0;
case TUNSETSNDBUF:
KNI_DBG("TUNSETSNDBUF\n");
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;
KNI_DBG("TUNGETVNETHDRSZ %d\n", s);
return 0;
case TUNSETVNETHDRSZ:
if (get_user(s, sp))
return -EFAULT;
if (s < (int)sizeof(struct virtio_net_hdr))
return -EINVAL;
KNI_DBG("TUNSETVNETHDRSZ %d\n", s);
q->vnet_hdr_sz = s;
return 0;
case TUNSETOFFLOAD:
KNI_DBG("TUNSETOFFLOAD %lx\n", arg);
#ifdef RTE_KNI_VHOST_VNET_HDR_EN
/* not support any offload yet */
if (!(q->flags & IFF_VNET_HDR))
return -EINVAL;
return 0;
#else
return -EINVAL;
#endif
default:
KNI_DBG("NOT SUPPORT\n");
return -EINVAL;
}
}
static inline int
kni_vhost_net_rx(struct kni_dev *kni, struct msghdr *m,
unsigned offset, unsigned len)
{
uint32_t pkt_len;
struct rte_kni_mbuf *kva;
struct rte_kni_mbuf *va;
void * data_kva;
struct sk_buff *skb;
struct kni_vhost_queue *q = kni->vhost_queue;
if (unlikely(q == NULL))
return 0;
/* ensure at least one entry in free_q */
if (unlikely(kni_fifo_free_count(kni->free_q) == 0))
return 0;
skb = skb_dequeue(&q->sk.sk_receive_queue);
if (unlikely(skb == NULL))
return 0;
kva = (struct rte_kni_mbuf*)skb->data;
/* free skb to cache */
skb->data = NULL;
if (unlikely(1 != kni_fifo_put(q->fifo, (void **)&skb, 1)))
/* Failing should not happen */
KNI_ERR("Fail to enqueue entries into rx cache fifo\n");
pkt_len = kva->data_len;
if (unlikely(pkt_len > len))
goto drop;
KNI_DBG_RX("rx offset=%d, len=%d, pkt_len=%d, iovlen=%d\n",
#ifdef HAVE_IOV_ITER_MSGHDR
offset, len, pkt_len, (int)m->msg_iter.iov->iov_len);
#else
offset, len, pkt_len, (int)m->msg_iov->iov_len);
#endif
data_kva = kva->buf_addr + kva->data_off - kni->mbuf_va + kni->mbuf_kva;
#ifdef HAVE_IOV_ITER_MSGHDR
if (unlikely(copy_to_iter(data_kva, pkt_len, &m->msg_iter)))
#else
if (unlikely(memcpy_toiovecend(m->msg_iov, data_kva, offset, pkt_len)))
#endif
goto drop;
/* Update statistics */
kni->stats.rx_bytes += pkt_len;
kni->stats.rx_packets++;
/* enqueue mbufs into free_q */
va = (void*)kva - kni->mbuf_kva + kni->mbuf_va;
if (unlikely(1 != kni_fifo_put(kni->free_q, (void **)&va, 1)))
/* Failing should not happen */
KNI_ERR("Fail to enqueue entries into free_q\n");
KNI_DBG_RX("receive done %d\n", pkt_len);
return pkt_len;
drop:
/* Update drop statistics */
kni->stats.rx_dropped++;
return 0;
}
/* 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 hdr = {
.flags = 0,
.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;
struct iov_iter fixup;
__virtio16 num_buffers;
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(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. */
iov_iter_init(&msg.msg_iter, READ, vq->iov, in, vhost_len);
fixup = msg.msg_iter;
if (unlikely((vhost_hlen))) {
/* We will supply the header ourselves
* TODO: support TSO.
*/
iov_iter_advance(&msg.msg_iter, vhost_hlen);
}
err = sock->ops->recvmsg(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;
}
/* Supply virtio_net_hdr if VHOST_NET_F_VIRTIO_NET_HDR */
if (unlikely(vhost_hlen)) {
if (copy_to_iter(&hdr, sizeof(hdr),
&fixup) != sizeof(hdr)) {
vq_err(vq, "Unable to write vnet_hdr "
"at addr %p\n", vq->iov->iov_base);
break;
}
} else {
/* Header came from socket; we'll need to patch
* ->num_buffers over if VIRTIO_NET_F_MRG_RXBUF
*/
iov_iter_advance(&fixup, sizeof(hdr));
}
/* TODO: Should check and handle checksum. */
num_buffers = cpu_to_vhost16(vq, headcount);
if (likely(mergeable) &&
copy_to_iter(&num_buffers, sizeof num_buffers,
&fixup) != sizeof 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);
}
/**
* skb_copy_datagram_iter - Copy a datagram to an iovec iterator.
* @skb: buffer to copy
* @offset: offset in the buffer to start copying from
* @to: iovec iterator to copy to
* @len: amount of data to copy from buffer to iovec
*/
int skb_copy_datagram_iter(const struct sk_buff *skb, int offset,
struct iov_iter *to, int len)
{
int start = skb_headlen(skb);
int i, copy = start - offset, start_off = offset, n;
struct sk_buff *frag_iter;
trace_skb_copy_datagram_iovec(skb, len);
/* Copy header. */
if (copy > 0) {
if (copy > len)
copy = len;
n = copy_to_iter(skb->data + offset, copy, to);
offset += n;
if (n != copy)
goto short_copy;
if ((len -= copy) == 0)
return 0;
}
/* Copy paged appendix. Hmm... why does this look so complicated? */
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int end;
const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
WARN_ON(start > offset + len);
end = start + skb_frag_size(frag);
if ((copy = end - offset) > 0) {
if (copy > len)
copy = len;
n = copy_page_to_iter(skb_frag_page(frag),
frag->page_offset + offset -
start, copy, to);
offset += n;
if (n != copy)
goto short_copy;
if (!(len -= copy))
return 0;
}
start = end;
}
skb_walk_frags(skb, frag_iter) {
int end;
WARN_ON(start > offset + len);
end = start + frag_iter->len;
if ((copy = end - offset) > 0) {
if (copy > len)
copy = len;
if (skb_copy_datagram_iter(frag_iter, offset - start,
to, copy))
goto fault;
if ((len -= copy) == 0)
return 0;
offset += copy;
}
start = end;
}
