static VubrDev *
vubr_new(const char *path, bool client)
{
VubrDev *dev = (VubrDev *) calloc(1, sizeof(VubrDev));
struct sockaddr_un un;
CallbackFunc cb;
size_t len;
/* Get a UNIX socket. */
dev->sock = socket(AF_UNIX, SOCK_STREAM, 0);
if (dev->sock == -1) {
vubr_die("socket");
}
dev->notifier.fd = -1;
un.sun_family = AF_UNIX;
strcpy(un.sun_path, path);
len = sizeof(un.sun_family) + strlen(path);
if (!client) {
unlink(path);
if (bind(dev->sock, (struct sockaddr *) &un, len) == -1) {
vubr_die("bind");
}
if (listen(dev->sock, 1) == -1) {
vubr_die("listen");
}
cb = vubr_accept_cb;
DPRINT("Waiting for connections on UNIX socket %s ...\n", path);
} else {
if (connect(dev->sock, (struct sockaddr *)&un, len) == -1) {
vubr_die("connect");
}
vu_init(&dev->vudev,
dev->sock,
vubr_panic,
vubr_set_watch,
vubr_remove_watch,
&vuiface);
cb = vubr_receive_cb;
}
dispatcher_init(&dev->dispatcher);
dispatcher_add(&dev->dispatcher, dev->sock, (void *)dev, cb);
return dev;
}
static void
vubr_backend_udp_setup(VubrDev *dev,
const char *local_host,
const char *local_port,
const char *remote_host,
const char *remote_port)
{
int sock;
const char *r;
int lport, rport;
lport = strtol(local_port, (char **)&r, 0);
if (r == local_port) {
fprintf(stderr, "lport parsing failed.\n");
exit(1);
}
rport = strtol(remote_port, (char **)&r, 0);
if (r == remote_port) {
fprintf(stderr, "rport parsing failed.\n");
exit(1);
}
struct sockaddr_in si_local = {
.sin_family = AF_INET,
.sin_port = htons(lport),
};
vubr_set_host(&si_local, local_host);
/* setup destination for sends */
dev->backend_udp_dest = (struct sockaddr_in) {
.sin_family = AF_INET,
.sin_port = htons(rport),
};
vubr_set_host(&dev->backend_udp_dest, remote_host);
sock = socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP);
if (sock == -1) {
vubr_die("socket");
}
if (bind(sock, (struct sockaddr *)&si_local, sizeof(si_local)) == -1) {
vubr_die("bind");
}
dev->backend_udp_sock = sock;
dispatcher_add(&dev->dispatcher, sock, dev, vubr_backend_recv_cb);
DPRINT("Waiting for data from udp backend on %s:%d...\n",
local_host, lport);
}
/* timeout in us */
static int
dispatcher_wait(Dispatcher *dispr, uint32_t timeout)
{
struct timeval tv;
tv.tv_sec = timeout / 1000000;
tv.tv_usec = timeout % 1000000;
fd_set fdset = dispr->fdset;
/* wait until some of sockets become readable. */
int rc = select(dispr->max_sock + 1, &fdset, 0, 0, &tv);
if (rc == -1) {
vubr_die("select");
}
/* Timeout */
if (rc == 0) {
return 0;
}
/* Now call callback for every ready socket. */
int sock;
for (sock = 0; sock < dispr->max_sock + 1; sock++) {
/* The callback on a socket can remove other sockets from the
* dispatcher, thus we have to check that the socket is
* still not removed from dispatcher's list
*/
if (FD_ISSET(sock, &fdset) && FD_ISSET(sock, &dispr->fdset)) {
Event *e = &dispr->events[sock];
e->callback(sock, e->ctx);
}
}
return 0;
}
static void
vubr_accept_cb(int sock, void *ctx)
{
VubrDev *dev = (VubrDev *)ctx;
int conn_fd;
struct sockaddr_un un;
socklen_t len = sizeof(un);
conn_fd = accept(sock, (struct sockaddr *) &un, &len);
if (conn_fd == -1) {
vubr_die("accept()");
}
DPRINT("Got connection from remote peer on sock %d\n", conn_fd);
vu_init(&dev->vudev,
conn_fd,
vubr_panic,
vubr_set_watch,
vubr_remove_watch,
&vuiface);
dispatcher_add(&dev->dispatcher, conn_fd, ctx, vubr_receive_cb);
dispatcher_remove(&dev->dispatcher, sock);
}
static void
vubr_backend_recv_cb(int sock, void *ctx)
{
VubrDev *vubr = (VubrDev *) ctx;
VuDev *dev = &vubr->vudev;
VuVirtq *vq = vu_get_queue(dev, 0);
VuVirtqElement *elem = NULL;
struct iovec mhdr_sg[VIRTQUEUE_MAX_SIZE];
struct virtio_net_hdr_mrg_rxbuf mhdr;
unsigned mhdr_cnt = 0;
int hdrlen = vubr->hdrlen;
int i = 0;
struct virtio_net_hdr hdr = {
.flags = 0,
.gso_type = VIRTIO_NET_HDR_GSO_NONE
};
DPRINT("\n\n *** IN UDP RECEIVE CALLBACK ***\n\n");
DPRINT(" hdrlen = %d\n", hdrlen);
if (!vu_queue_enabled(dev, vq) ||
!vu_queue_started(dev, vq) ||
!vu_queue_avail_bytes(dev, vq, hdrlen, 0)) {
DPRINT("Got UDP packet, but no available descriptors on RX virtq.\n");
return;
}
while (1) {
struct iovec *sg;
ssize_t ret, total = 0;
unsigned int num;
elem = vu_queue_pop(dev, vq, sizeof(VuVirtqElement));
if (!elem) {
break;
}
if (elem->in_num < 1) {
fprintf(stderr, "virtio-net contains no in buffers\n");
break;
}
sg = elem->in_sg;
num = elem->in_num;
if (i == 0) {
if (hdrlen == 12) {
mhdr_cnt = iov_copy(mhdr_sg, ARRAY_SIZE(mhdr_sg),
sg, elem->in_num,
offsetof(typeof(mhdr), num_buffers),
sizeof(mhdr.num_buffers));
}
iov_from_buf(sg, elem->in_num, 0, &hdr, sizeof hdr);
total += hdrlen;
ret = iov_discard_front(&sg, &num, hdrlen);
assert(ret == hdrlen);
}
struct msghdr msg = {
.msg_name = (struct sockaddr *) &vubr->backend_udp_dest,
.msg_namelen = sizeof(struct sockaddr_in),
.msg_iov = sg,
.msg_iovlen = num,
.msg_flags = MSG_DONTWAIT,
};
do {
ret = recvmsg(vubr->backend_udp_sock, &msg, 0);
} while (ret == -1 && (errno == EINTR));
if (i == 0) {
iov_restore_front(elem->in_sg, sg, hdrlen);
}
if (ret == -1) {
if (errno == EWOULDBLOCK) {
vu_queue_rewind(dev, vq, 1);
break;
}
vubr_die("recvmsg()");
}
total += ret;
iov_truncate(elem->in_sg, elem->in_num, total);
vu_queue_fill(dev, vq, elem, total, i++);
free(elem);
elem = NULL;
break; /* could loop if DONTWAIT worked? */
}
if (mhdr_cnt) {
mhdr.num_buffers = i;
iov_from_buf(mhdr_sg, mhdr_cnt,
0,
&mhdr.num_buffers, sizeof mhdr.num_buffers);
}
vu_queue_flush(dev, vq, i);
vu_queue_notify(dev, vq);
free(elem);
}
static void
vubr_receive_cb(int sock, void *ctx)
{
VubrDev *vubr = (VubrDev *)ctx;
if (!vu_dispatch(&vubr->vudev)) {
fprintf(stderr, "Error while dispatching\n");
}
}
typedef struct WatchData {
VuDev *dev;
vu_watch_cb cb;
void *data;
} WatchData;
static void
watch_cb(int sock, void *ctx)
{
struct WatchData *wd = ctx;
wd->cb(wd->dev, VU_WATCH_IN, wd->data);
}
static void
vubr_set_watch(VuDev *dev, int fd, int condition,
vu_watch_cb cb, void *data)
{
VubrDev *vubr = container_of(dev, VubrDev, vudev);
static WatchData watches[FD_SETSIZE];
struct WatchData *wd = &watches[fd];
wd->cb = cb;
wd->data = data;
wd->dev = dev;
dispatcher_add(&vubr->dispatcher, fd, wd, watch_cb);
}
static void
vubr_handle_tx(VuDev *dev, int qidx)
{
VuVirtq *vq = vu_get_queue(dev, qidx);
VubrDev *vubr = container_of(dev, VubrDev, vudev);
int hdrlen = vubr->hdrlen;
VuVirtqElement *elem = NULL;
assert(qidx % 2);
for (;;) {
ssize_t ret;
unsigned int out_num;
struct iovec sg[VIRTQUEUE_MAX_SIZE], *out_sg;
elem = vu_queue_pop(dev, vq, sizeof(VuVirtqElement));
if (!elem) {
break;
}
out_num = elem->out_num;
out_sg = elem->out_sg;
if (out_num < 1) {
fprintf(stderr, "virtio-net header not in first element\n");
break;
}
if (VHOST_USER_BRIDGE_DEBUG) {
iov_hexdump(out_sg, out_num, stderr, "TX:", 1024);
}
if (hdrlen) {
unsigned sg_num = iov_copy(sg, ARRAY_SIZE(sg),
out_sg, out_num,
hdrlen, -1);
out_num = sg_num;
out_sg = sg;
}
struct msghdr msg = {
.msg_name = (struct sockaddr *) &vubr->backend_udp_dest,
.msg_namelen = sizeof(struct sockaddr_in),
.msg_iov = out_sg,
.msg_iovlen = out_num,
};
do {
ret = sendmsg(vubr->backend_udp_sock, &msg, 0);
} while (ret == -1 && (errno == EAGAIN || errno == EINTR));
if (ret == -1) {
vubr_die("sendmsg()");
}
vu_queue_push(dev, vq, elem, 0);
vu_queue_notify(dev, vq);
free(elem);
elem = NULL;
}
free(elem);
}
/* this function reverse the effect of iov_discard_front() it must be
* called with 'front' being the original struct iovec and 'bytes'
* being the number of bytes you shaved off
*/
static void
iov_restore_front(struct iovec *front, struct iovec *iov, size_t bytes)
{
struct iovec *cur;
for (cur = front; cur != iov; cur++) {
assert(bytes >= cur->iov_len);
bytes -= cur->iov_len;
}
cur->iov_base -= bytes;
cur->iov_len += bytes;
}
static void
iov_truncate(struct iovec *iov, unsigned iovc, size_t bytes)
{
unsigned i;
for (i = 0; i < iovc; i++, iov++) {
if (bytes < iov->iov_len) {
iov->iov_len = bytes;
return;
}
bytes -= iov->iov_len;
}
assert(!"couldn't truncate iov");
}