#include <string.h>
#include <errno.h>
+#include <rte_alarm.h>
#include <rte_string_fns.h>
#include <rte_fbarray.h>
#include "vhost.h"
#include "virtio_user_dev.h"
+struct vhost_user_data {
+ int vhostfd;
+ int listenfd;
+ uint64_t protocol_features;
+};
+
+#ifndef VHOST_USER_F_PROTOCOL_FEATURES
+#define VHOST_USER_F_PROTOCOL_FEATURES 30
+#endif
+
+/** Protocol features. */
+#ifndef VHOST_USER_PROTOCOL_F_MQ
+#define VHOST_USER_PROTOCOL_F_MQ 0
+#endif
+
+#ifndef VHOST_USER_PROTOCOL_F_REPLY_ACK
+#define VHOST_USER_PROTOCOL_F_REPLY_ACK 3
+#endif
+
+#ifndef VHOST_USER_PROTOCOL_F_STATUS
+#define VHOST_USER_PROTOCOL_F_STATUS 16
+#endif
+
+#define VHOST_USER_SUPPORTED_PROTOCOL_FEATURES \
+ (1ULL << VHOST_USER_PROTOCOL_F_MQ | \
+ 1ULL << VHOST_USER_PROTOCOL_F_REPLY_ACK | \
+ 1ULL << VHOST_USER_PROTOCOL_F_STATUS)
+
/* The version of the protocol we support */
#define VHOST_USER_VERSION 0x1
int ret, sz_hdr = VHOST_USER_HDR_SIZE, sz_payload;
ret = recv(fd, (void *)msg, sz_hdr, 0);
- if (ret < sz_hdr) {
+ if (ret < 0) {
+ PMD_DRV_LOG(ERR, "Failed to recv msg header: %s", strerror(errno));
+ return -1;
+ } else if (ret < sz_hdr) {
PMD_DRV_LOG(ERR, "Failed to recv msg hdr: %d instead of %d.",
ret, sz_hdr);
- goto fail;
+ return -1;
}
/* validate msg flags */
if (msg->flags != (valid_flags)) {
- PMD_DRV_LOG(ERR, "Failed to recv msg: flags %x instead of %x.",
+ PMD_DRV_LOG(ERR, "Failed to recv msg: flags 0x%x instead of 0x%x.",
msg->flags, valid_flags);
- goto fail;
+ return -1;
}
sz_payload = msg->size;
- if ((size_t)sz_payload > sizeof(msg->payload))
- goto fail;
+ if ((size_t)sz_payload > sizeof(msg->payload)) {
+ PMD_DRV_LOG(ERR, "Payload size overflow, header says %d but max %zu\n",
+ sz_payload, sizeof(msg->payload));
+ return -1;
+ }
if (sz_payload) {
ret = recv(fd, (void *)((char *)msg + sz_hdr), sz_payload, 0);
- if (ret < sz_payload) {
- PMD_DRV_LOG(ERR,
- "Failed to recv msg payload: %d instead of %d.",
+ if (ret < 0) {
+ PMD_DRV_LOG(ERR, "Failed to recv msg payload: %s", strerror(errno));
+ return -1;
+ } else if (ret < sz_payload) {
+ PMD_DRV_LOG(ERR, "Failed to recv msg payload: %d instead of %u.",
ret, msg->size);
- goto fail;
+ return -1;
}
}
return 0;
-
-fail:
- return -1;
}
static int
vhost_user_check_reply_ack(struct virtio_user_dev *dev, struct vhost_user_msg *msg)
{
+ struct vhost_user_data *data = dev->backend_data;
enum vhost_user_request req = msg->request;
int ret;
if (!(msg->flags & VHOST_USER_NEED_REPLY_MASK))
return 0;
- ret = vhost_user_read(dev->vhostfd, msg);
+ ret = vhost_user_read(data->vhostfd, msg);
if (ret < 0) {
PMD_DRV_LOG(ERR, "Failed to read reply-ack");
return -1;
vhost_user_set_owner(struct virtio_user_dev *dev)
{
int ret;
+ struct vhost_user_data *data = dev->backend_data;
struct vhost_user_msg msg = {
.request = VHOST_USER_SET_OWNER,
.flags = VHOST_USER_VERSION,
};
- ret = vhost_user_write(dev->vhostfd, &msg, NULL, 0);
+ ret = vhost_user_write(data->vhostfd, &msg, NULL, 0);
if (ret < 0) {
PMD_DRV_LOG(ERR, "Failed to set owner");
return -1;
}
static int
-vhost_user_get_features(struct virtio_user_dev *dev, uint64_t *features)
+vhost_user_get_protocol_features(struct virtio_user_dev *dev, uint64_t *features)
{
int ret;
+ struct vhost_user_data *data = dev->backend_data;
struct vhost_user_msg msg = {
- .request = VHOST_USER_GET_FEATURES,
+ .request = VHOST_USER_GET_PROTOCOL_FEATURES,
.flags = VHOST_USER_VERSION,
};
- ret = vhost_user_write(dev->vhostfd, &msg, NULL, 0);
+ ret = vhost_user_write(data->vhostfd, &msg, NULL, 0);
if (ret < 0)
goto err;
- ret = vhost_user_read(dev->vhostfd, &msg);
+ ret = vhost_user_read(data->vhostfd, &msg);
if (ret < 0)
goto err;
- if (msg.request != VHOST_USER_GET_FEATURES) {
+ if (msg.request != VHOST_USER_GET_PROTOCOL_FEATURES) {
PMD_DRV_LOG(ERR, "Unexpected request type (%d)", msg.request);
goto err;
}
return 0;
err:
- PMD_DRV_LOG(ERR, "Failed to get backend features");
+ PMD_DRV_LOG(ERR, "Failed to get backend protocol features");
return -1;
}
static int
-vhost_user_set_features(struct virtio_user_dev *dev, uint64_t features)
+vhost_user_set_protocol_features(struct virtio_user_dev *dev, uint64_t features)
{
int ret;
+ struct vhost_user_data *data = dev->backend_data;
struct vhost_user_msg msg = {
- .request = VHOST_USER_SET_FEATURES,
+ .request = VHOST_USER_SET_PROTOCOL_FEATURES,
.flags = VHOST_USER_VERSION,
.size = sizeof(features),
.payload.u64 = features,
};
- msg.payload.u64 |= dev->device_features & (1ULL << VHOST_USER_F_PROTOCOL_FEATURES);
-
- ret = vhost_user_write(dev->vhostfd, &msg, NULL, 0);
+ ret = vhost_user_write(data->vhostfd, &msg, NULL, 0);
if (ret < 0) {
- PMD_DRV_LOG(ERR, "Failed to set features");
+ PMD_DRV_LOG(ERR, "Failed to set protocol features");
return -1;
}
}
static int
-vhost_user_get_protocol_features(struct virtio_user_dev *dev, uint64_t *features)
+vhost_user_get_features(struct virtio_user_dev *dev, uint64_t *features)
{
int ret;
+ struct vhost_user_data *data = dev->backend_data;
struct vhost_user_msg msg = {
- .request = VHOST_USER_GET_PROTOCOL_FEATURES,
+ .request = VHOST_USER_GET_FEATURES,
.flags = VHOST_USER_VERSION,
};
- ret = vhost_user_write(dev->vhostfd, &msg, NULL, 0);
+ ret = vhost_user_write(data->vhostfd, &msg, NULL, 0);
if (ret < 0)
goto err;
- ret = vhost_user_read(dev->vhostfd, &msg);
+ ret = vhost_user_read(data->vhostfd, &msg);
if (ret < 0)
goto err;
- if (msg.request != VHOST_USER_GET_PROTOCOL_FEATURES) {
+ if (msg.request != VHOST_USER_GET_FEATURES) {
PMD_DRV_LOG(ERR, "Unexpected request type (%d)", msg.request);
goto err;
}
*features = msg.payload.u64;
+ if (!(*features & (1ULL << VHOST_USER_F_PROTOCOL_FEATURES)))
+ return 0;
+
+ /* Negotiate protocol features */
+ ret = vhost_user_get_protocol_features(dev, &data->protocol_features);
+ if (ret < 0)
+ goto err;
+
+ data->protocol_features &= VHOST_USER_SUPPORTED_PROTOCOL_FEATURES;
+
+ ret = vhost_user_set_protocol_features(dev, data->protocol_features);
+ if (ret < 0)
+ goto err;
+
+ if (!(data->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_MQ)))
+ dev->unsupported_features |= (1ull << VIRTIO_NET_F_MQ);
+
return 0;
err:
- PMD_DRV_LOG(ERR, "Failed to get backend protocol features");
+ PMD_DRV_LOG(ERR, "Failed to get backend features");
return -1;
}
static int
-vhost_user_set_protocol_features(struct virtio_user_dev *dev, uint64_t features)
+vhost_user_set_features(struct virtio_user_dev *dev, uint64_t features)
{
int ret;
+ struct vhost_user_data *data = dev->backend_data;
struct vhost_user_msg msg = {
- .request = VHOST_USER_SET_PROTOCOL_FEATURES,
+ .request = VHOST_USER_SET_FEATURES,
.flags = VHOST_USER_VERSION,
.size = sizeof(features),
.payload.u64 = features,
};
- ret = vhost_user_write(dev->vhostfd, &msg, NULL, 0);
+ msg.payload.u64 |= dev->device_features & (1ULL << VHOST_USER_F_PROTOCOL_FEATURES);
+
+ ret = vhost_user_write(data->vhostfd, &msg, NULL, 0);
if (ret < 0) {
- PMD_DRV_LOG(ERR, "Failed to set protocol features");
+ PMD_DRV_LOG(ERR, "Failed to set features");
return -1;
}
struct walk_arg wa;
int fds[VHOST_MEMORY_MAX_NREGIONS];
int ret, fd_num;
+ struct vhost_user_data *data = dev->backend_data;
struct vhost_user_msg msg = {
.request = VHOST_USER_SET_MEM_TABLE,
.flags = VHOST_USER_VERSION,
};
- if (dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_REPLY_ACK))
+ if (data->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_REPLY_ACK))
msg.flags |= VHOST_USER_NEED_REPLY_MASK;
wa.region_nr = 0;
msg.size += sizeof(msg.payload.memory.padding);
msg.size += fd_num * sizeof(struct vhost_memory_region);
- ret = vhost_user_write(dev->vhostfd, &msg, fds, fd_num);
+ ret = vhost_user_write(data->vhostfd, &msg, fds, fd_num);
if (ret < 0)
goto err;
struct vhost_vring_state *state)
{
int ret;
+ struct vhost_user_data *data = dev->backend_data;
struct vhost_user_msg msg = {
.request = req,
.flags = VHOST_USER_VERSION,
.payload.state = *state,
};
- ret = vhost_user_write(dev->vhostfd, &msg, NULL, 0);
+ ret = vhost_user_write(data->vhostfd, &msg, NULL, 0);
if (ret < 0) {
PMD_DRV_LOG(ERR, "Failed to set vring state (request %d)", req);
return -1;
{
int ret;
struct vhost_user_msg msg;
+ struct vhost_user_data *data = dev->backend_data;
unsigned int index = state->index;
ret = vhost_user_set_vring(dev, VHOST_USER_GET_VRING_BASE, state);
goto err;
}
- ret = vhost_user_read(dev->vhostfd, &msg);
+ ret = vhost_user_read(data->vhostfd, &msg);
if (ret < 0) {
PMD_DRV_LOG(ERR, "Failed to read reply");
goto err;
int ret;
int fd = file->fd;
int num_fd = 0;
+ struct vhost_user_data *data = dev->backend_data;
struct vhost_user_msg msg = {
.request = req,
.flags = VHOST_USER_VERSION,
else
msg.payload.u64 |= VHOST_USER_VRING_NOFD_MASK;
- ret = vhost_user_write(dev->vhostfd, &msg, &fd, num_fd);
+ ret = vhost_user_write(data->vhostfd, &msg, &fd, num_fd);
if (ret < 0) {
PMD_DRV_LOG(ERR, "Failed to set vring file (request %d)", req);
return -1;
vhost_user_set_vring_addr(struct virtio_user_dev *dev, struct vhost_vring_addr *addr)
{
int ret;
+ struct vhost_user_data *data = dev->backend_data;
struct vhost_user_msg msg = {
.request = VHOST_USER_SET_VRING_ADDR,
.flags = VHOST_USER_VERSION,
.payload.addr = *addr,
};
- ret = vhost_user_write(dev->vhostfd, &msg, NULL, 0);
+ ret = vhost_user_write(data->vhostfd, &msg, NULL, 0);
if (ret < 0) {
PMD_DRV_LOG(ERR, "Failed to send vring addresses");
return -1;
vhost_user_get_status(struct virtio_user_dev *dev, uint8_t *status)
{
int ret;
+ struct vhost_user_data *data = dev->backend_data;
struct vhost_user_msg msg = {
.request = VHOST_USER_GET_STATUS,
.flags = VHOST_USER_VERSION,
if (!(dev->device_features & (1ULL << VHOST_USER_F_PROTOCOL_FEATURES)))
return -ENOTSUP;
- if (!(dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_STATUS)))
+ if (!(data->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_STATUS)))
return -ENOTSUP;
- ret = vhost_user_write(dev->vhostfd, &msg, NULL, 0);
+ ret = vhost_user_write(data->vhostfd, &msg, NULL, 0);
if (ret < 0) {
PMD_DRV_LOG(ERR, "Failed to send request");
goto err;
}
- ret = vhost_user_read(dev->vhostfd, &msg);
+ ret = vhost_user_read(data->vhostfd, &msg);
if (ret < 0) {
PMD_DRV_LOG(ERR, "Failed to recv request");
goto err;
vhost_user_set_status(struct virtio_user_dev *dev, uint8_t status)
{
int ret;
+ struct vhost_user_data *data = dev->backend_data;
struct vhost_user_msg msg = {
.request = VHOST_USER_SET_STATUS,
.flags = VHOST_USER_VERSION,
if (!(dev->device_features & (1ULL << VHOST_USER_F_PROTOCOL_FEATURES)))
return -ENOTSUP;
- if (!(dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_STATUS)))
+ if (!(data->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_STATUS)))
return -ENOTSUP;
- if (dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_REPLY_ACK))
+ if (data->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_REPLY_ACK))
msg.flags |= VHOST_USER_NEED_REPLY_MASK;
- ret = vhost_user_write(dev->vhostfd, &msg, NULL, 0);
+ ret = vhost_user_write(data->vhostfd, &msg, NULL, 0);
if (ret < 0) {
PMD_DRV_LOG(ERR, "Failed to send get status request");
return -1;
#define MAX_VIRTIO_USER_BACKLOG 1
static int
-virtio_user_start_server(struct virtio_user_dev *dev, struct sockaddr_un *un)
+vhost_user_start_server(struct virtio_user_dev *dev, struct sockaddr_un *un)
{
int ret;
int flag;
- int fd = dev->listenfd;
+ struct vhost_user_data *data = dev->backend_data;
+ int fd = data->listenfd;
ret = bind(fd, (struct sockaddr *)un, sizeof(*un));
if (ret < 0) {
if (ret < 0)
return -1;
+ PMD_DRV_LOG(NOTICE, "(%s) waiting for client connection...", dev->path);
+ data->vhostfd = accept(fd, NULL, NULL);
+ if (data->vhostfd < 0) {
+ PMD_DRV_LOG(ERR, "Failed to accept initial client connection (%s)",
+ strerror(errno));
+ return -1;
+ }
+
flag = fcntl(fd, F_GETFL);
if (fcntl(fd, F_SETFL, flag | O_NONBLOCK) < 0) {
PMD_DRV_LOG(ERR, "fcntl failed, %s", strerror(errno));
return 0;
}
+static int
+vhost_user_server_disconnect(struct virtio_user_dev *dev)
+{
+ struct vhost_user_data *data = dev->backend_data;
+
+ if (data->vhostfd < 0) {
+ PMD_DRV_LOG(ERR, "(%s) Expected valid Vhost FD", dev->path);
+ return -1;
+ }
+
+ close(data->vhostfd);
+ data->vhostfd = -1;
+
+ return 0;
+}
+
+static int
+vhost_user_server_reconnect(struct virtio_user_dev *dev)
+{
+ struct vhost_user_data *data = dev->backend_data;
+ int fd;
+
+ fd = accept(data->listenfd, NULL, NULL);
+ if (fd < 0)
+ return -1;
+
+ data->vhostfd = fd;
+
+ return 0;
+}
+
/**
* Set up environment to talk with a vhost user backend.
*
int fd;
int flag;
struct sockaddr_un un;
+ struct vhost_user_data *data;
+
+ data = malloc(sizeof(*data));
+ if (!data) {
+ PMD_DRV_LOG(ERR, "(%s) Failed to allocate Vhost-user data\n", dev->path);
+ return -1;
+ }
+
+ memset(data, 0, sizeof(*data));
+
+ dev->backend_data = data;
+
+ data->vhostfd = -1;
fd = socket(AF_UNIX, SOCK_STREAM, 0);
if (fd < 0) {
PMD_DRV_LOG(ERR, "socket() error, %s", strerror(errno));
- return -1;
+ goto err_data;
}
flag = fcntl(fd, F_GETFD);
strlcpy(un.sun_path, dev->path, sizeof(un.sun_path));
if (dev->is_server) {
- dev->listenfd = fd;
- if (virtio_user_start_server(dev, &un) < 0) {
+ data->listenfd = fd;
+ if (vhost_user_start_server(dev, &un) < 0) {
PMD_DRV_LOG(ERR, "virtio-user startup fails in server mode");
- close(fd);
- return -1;
+ goto err_socket;
}
- dev->vhostfd = -1;
} else {
if (connect(fd, (struct sockaddr *)&un, sizeof(un)) < 0) {
PMD_DRV_LOG(ERR, "connect error, %s", strerror(errno));
- close(fd);
- return -1;
+ goto err_socket;
}
- dev->vhostfd = fd;
+ data->vhostfd = fd;
+ }
+
+ return 0;
+
+err_socket:
+ close(fd);
+err_data:
+ free(data);
+ dev->backend_data = NULL;
+
+ return -1;
+}
+
+static int
+vhost_user_destroy(struct virtio_user_dev *dev)
+{
+ struct vhost_user_data *data = dev->backend_data;
+
+ if (!data)
+ return 0;
+
+ if (data->vhostfd >= 0) {
+ close(data->vhostfd);
+ data->vhostfd = -1;
+ }
+
+ if (data->listenfd >= 0) {
+ close(data->listenfd);
+ data->listenfd = -1;
}
+ free(data);
+ dev->backend_data = NULL;
+
return 0;
}
uint16_t pair_idx,
int enable)
{
+ struct vhost_user_data *data = dev->backend_data;
int i;
+ if (data->vhostfd < 0)
+ return 0;
+
if (dev->qp_enabled[pair_idx] == enable)
return 0;
return 0;
}
+static int
+vhost_user_get_backend_features(uint64_t *features)
+{
+ *features = 1ULL << VHOST_USER_F_PROTOCOL_FEATURES;
+
+ return 0;
+}
+
+static int
+vhost_user_update_link_state(struct virtio_user_dev *dev)
+{
+ struct vhost_user_data *data = dev->backend_data;
+ char buf[128];
+
+ if (data->vhostfd >= 0) {
+ int r;
+ int flags;
+
+ flags = fcntl(data->vhostfd, F_GETFL);
+ if (fcntl(data->vhostfd, F_SETFL, flags | O_NONBLOCK) == -1) {
+ PMD_DRV_LOG(ERR, "error setting O_NONBLOCK flag");
+ return -1;
+ }
+
+ r = recv(data->vhostfd, buf, 128, MSG_PEEK);
+ if (r == 0 || (r < 0 && errno != EAGAIN)) {
+ dev->net_status &= (~VIRTIO_NET_S_LINK_UP);
+ PMD_DRV_LOG(ERR, "virtio-user port %u is down", dev->port_id);
+
+ /* This function could be called in the process
+ * of interrupt handling, callback cannot be
+ * unregistered here, set an alarm to do it.
+ */
+ rte_eal_alarm_set(1, virtio_user_dev_delayed_handler, (void *)dev);
+ } else {
+ dev->net_status |= VIRTIO_NET_S_LINK_UP;
+ }
+
+ if (fcntl(data->vhostfd, F_SETFL,
+ flags & ~O_NONBLOCK) == -1) {
+ PMD_DRV_LOG(ERR, "error clearing O_NONBLOCK flag");
+ return -1;
+ }
+ } else if (dev->is_server) {
+ dev->net_status &= (~VIRTIO_NET_S_LINK_UP);
+ if (virtio_user_dev_server_reconnect(dev) >= 0)
+ dev->net_status |= VIRTIO_NET_S_LINK_UP;
+ }
+
+ return 0;
+}
+
+static int
+vhost_user_get_intr_fd(struct virtio_user_dev *dev)
+{
+ struct vhost_user_data *data = dev->backend_data;
+
+ if (dev->is_server && data->vhostfd == -1)
+ return data->listenfd;
+
+ return data->vhostfd;
+}
+
struct virtio_user_backend_ops virtio_ops_user = {
.setup = vhost_user_setup,
+ .destroy = vhost_user_destroy,
+ .get_backend_features = vhost_user_get_backend_features,
.set_owner = vhost_user_set_owner,
.get_features = vhost_user_get_features,
.set_features = vhost_user_set_features,
- .get_protocol_features = vhost_user_get_protocol_features,
- .set_protocol_features = vhost_user_set_protocol_features,
.set_memory_table = vhost_user_set_memory_table,
.set_vring_num = vhost_user_set_vring_num,
.set_vring_base = vhost_user_set_vring_base,
.set_vring_addr = vhost_user_set_vring_addr,
.get_status = vhost_user_get_status,
.set_status = vhost_user_set_status,
- .enable_qp = vhost_user_enable_queue_pair
+ .enable_qp = vhost_user_enable_queue_pair,
+ .update_link_state = vhost_user_update_link_state,
+ .server_disconnect = vhost_user_server_disconnect,
+ .server_reconnect = vhost_user_server_reconnect,
+ .get_intr_fd = vhost_user_get_intr_fd,
};