#include <unistd.h>
#include <pthread.h>
#include <stdbool.h>
-#ifdef RTE_LIBRTE_VHOST_NUMA
-#include <numaif.h>
-#endif
#include <rte_mbuf.h>
#include <rte_ethdev.h>
#include <rte_malloc.h>
#include <rte_memcpy.h>
-#include <rte_dev.h>
+#include <rte_vdev.h>
#include <rte_kvargs.h>
#include <rte_virtio_net.h>
#include <rte_spinlock.h>
#include "rte_eth_vhost.h"
+enum {VIRTIO_RXQ, VIRTIO_TXQ, VIRTIO_QNUM};
+
#define ETH_VHOST_IFACE_ARG "iface"
#define ETH_VHOST_QUEUES_ARG "queues"
-
-static const char *drivername = "VHOST PMD";
+#define ETH_VHOST_CLIENT_ARG "client"
+#define ETH_VHOST_DEQUEUE_ZERO_COPY "dequeue-zero-copy"
+#define VHOST_MAX_PKT_BURST 32
static const char *valid_arguments[] = {
ETH_VHOST_IFACE_ARG,
ETH_VHOST_QUEUES_ARG,
+ ETH_VHOST_CLIENT_ARG,
+ ETH_VHOST_DEQUEUE_ZERO_COPY,
NULL
};
}
};
+enum vhost_xstats_pkts {
+ VHOST_UNDERSIZE_PKT = 0,
+ VHOST_64_PKT,
+ VHOST_65_TO_127_PKT,
+ VHOST_128_TO_255_PKT,
+ VHOST_256_TO_511_PKT,
+ VHOST_512_TO_1023_PKT,
+ VHOST_1024_TO_1522_PKT,
+ VHOST_1523_TO_MAX_PKT,
+ VHOST_BROADCAST_PKT,
+ VHOST_MULTICAST_PKT,
+ VHOST_UNICAST_PKT,
+ VHOST_ERRORS_PKT,
+ VHOST_ERRORS_FRAGMENTED,
+ VHOST_ERRORS_JABBER,
+ VHOST_UNKNOWN_PROTOCOL,
+ VHOST_XSTATS_MAX,
+};
+
+struct vhost_stats {
+ uint64_t pkts;
+ uint64_t bytes;
+ uint64_t missed_pkts;
+ uint64_t xstats[VHOST_XSTATS_MAX];
+};
+
struct vhost_queue {
int vid;
rte_atomic32_t allow_queuing;
struct rte_mempool *mb_pool;
uint8_t port;
uint16_t virtqueue_id;
- uint64_t rx_pkts;
- uint64_t tx_pkts;
- uint64_t missed_pkts;
- uint64_t rx_bytes;
- uint64_t tx_bytes;
+ struct vhost_stats stats;
};
struct pmd_internal {
+ rte_atomic32_t dev_attached;
char *dev_name;
char *iface_name;
uint16_t max_queues;
-
- volatile uint16_t once;
+ rte_atomic32_t started;
};
struct internal_list {
static pthread_mutex_t internal_list_lock = PTHREAD_MUTEX_INITIALIZER;
-static rte_atomic16_t nb_started_ports;
-static pthread_t session_th;
-
static struct rte_eth_link pmd_link = {
.link_speed = 10000,
.link_duplex = ETH_LINK_FULL_DUPLEX,
static struct rte_vhost_vring_state *vring_states[RTE_MAX_ETHPORTS];
+#define VHOST_XSTATS_NAME_SIZE 64
+
+struct vhost_xstats_name_off {
+ char name[VHOST_XSTATS_NAME_SIZE];
+ uint64_t offset;
+};
+
+/* [rx]_is prepended to the name string here */
+static const struct vhost_xstats_name_off vhost_rxport_stat_strings[] = {
+ {"good_packets",
+ offsetof(struct vhost_queue, stats.pkts)},
+ {"total_bytes",
+ offsetof(struct vhost_queue, stats.bytes)},
+ {"missed_pkts",
+ offsetof(struct vhost_queue, stats.missed_pkts)},
+ {"broadcast_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_BROADCAST_PKT])},
+ {"multicast_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_MULTICAST_PKT])},
+ {"unicast_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_UNICAST_PKT])},
+ {"undersize_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_UNDERSIZE_PKT])},
+ {"size_64_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_64_PKT])},
+ {"size_65_to_127_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_65_TO_127_PKT])},
+ {"size_128_to_255_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_128_TO_255_PKT])},
+ {"size_256_to_511_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_256_TO_511_PKT])},
+ {"size_512_to_1023_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_512_TO_1023_PKT])},
+ {"size_1024_to_1522_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_1024_TO_1522_PKT])},
+ {"size_1523_to_max_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_1523_TO_MAX_PKT])},
+ {"errors_with_bad_CRC",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_ERRORS_PKT])},
+ {"fragmented_errors",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_ERRORS_FRAGMENTED])},
+ {"jabber_errors",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_ERRORS_JABBER])},
+ {"unknown_protos_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_UNKNOWN_PROTOCOL])},
+};
+
+/* [tx]_ is prepended to the name string here */
+static const struct vhost_xstats_name_off vhost_txport_stat_strings[] = {
+ {"good_packets",
+ offsetof(struct vhost_queue, stats.pkts)},
+ {"total_bytes",
+ offsetof(struct vhost_queue, stats.bytes)},
+ {"missed_pkts",
+ offsetof(struct vhost_queue, stats.missed_pkts)},
+ {"broadcast_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_BROADCAST_PKT])},
+ {"multicast_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_MULTICAST_PKT])},
+ {"unicast_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_UNICAST_PKT])},
+ {"undersize_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_UNDERSIZE_PKT])},
+ {"size_64_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_64_PKT])},
+ {"size_65_to_127_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_65_TO_127_PKT])},
+ {"size_128_to_255_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_128_TO_255_PKT])},
+ {"size_256_to_511_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_256_TO_511_PKT])},
+ {"size_512_to_1023_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_512_TO_1023_PKT])},
+ {"size_1024_to_1522_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_1024_TO_1522_PKT])},
+ {"size_1523_to_max_packets",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_1523_TO_MAX_PKT])},
+ {"errors_with_bad_CRC",
+ offsetof(struct vhost_queue, stats.xstats[VHOST_ERRORS_PKT])},
+};
+
+#define VHOST_NB_XSTATS_RXPORT (sizeof(vhost_rxport_stat_strings) / \
+ sizeof(vhost_rxport_stat_strings[0]))
+
+#define VHOST_NB_XSTATS_TXPORT (sizeof(vhost_txport_stat_strings) / \
+ sizeof(vhost_txport_stat_strings[0]))
+
+static void
+vhost_dev_xstats_reset(struct rte_eth_dev *dev)
+{
+ struct vhost_queue *vq = NULL;
+ unsigned int i = 0;
+
+ for (i = 0; i < dev->data->nb_rx_queues; i++) {
+ vq = dev->data->rx_queues[i];
+ if (!vq)
+ continue;
+ memset(&vq->stats, 0, sizeof(vq->stats));
+ }
+ for (i = 0; i < dev->data->nb_tx_queues; i++) {
+ vq = dev->data->tx_queues[i];
+ if (!vq)
+ continue;
+ memset(&vq->stats, 0, sizeof(vq->stats));
+ }
+}
+
+static int
+vhost_dev_xstats_get_names(struct rte_eth_dev *dev __rte_unused,
+ struct rte_eth_xstat_name *xstats_names,
+ unsigned int limit __rte_unused)
+{
+ unsigned int t = 0;
+ int count = 0;
+ int nstats = VHOST_NB_XSTATS_RXPORT + VHOST_NB_XSTATS_TXPORT;
+
+ if (!xstats_names)
+ return nstats;
+ for (t = 0; t < VHOST_NB_XSTATS_RXPORT; t++) {
+ snprintf(xstats_names[count].name,
+ sizeof(xstats_names[count].name),
+ "rx_%s", vhost_rxport_stat_strings[t].name);
+ count++;
+ }
+ for (t = 0; t < VHOST_NB_XSTATS_TXPORT; t++) {
+ snprintf(xstats_names[count].name,
+ sizeof(xstats_names[count].name),
+ "tx_%s", vhost_txport_stat_strings[t].name);
+ count++;
+ }
+ return count;
+}
+
+static int
+vhost_dev_xstats_get(struct rte_eth_dev *dev, struct rte_eth_xstat *xstats,
+ unsigned int n)
+{
+ unsigned int i;
+ unsigned int t;
+ unsigned int count = 0;
+ struct vhost_queue *vq = NULL;
+ unsigned int nxstats = VHOST_NB_XSTATS_RXPORT + VHOST_NB_XSTATS_TXPORT;
+
+ if (n < nxstats)
+ return nxstats;
+
+ for (i = 0; i < dev->data->nb_rx_queues; i++) {
+ vq = dev->data->rx_queues[i];
+ if (!vq)
+ continue;
+ vq->stats.xstats[VHOST_UNICAST_PKT] = vq->stats.pkts
+ - (vq->stats.xstats[VHOST_BROADCAST_PKT]
+ + vq->stats.xstats[VHOST_MULTICAST_PKT]);
+ }
+ for (i = 0; i < dev->data->nb_tx_queues; i++) {
+ vq = dev->data->tx_queues[i];
+ if (!vq)
+ continue;
+ vq->stats.xstats[VHOST_UNICAST_PKT] = vq->stats.pkts
+ + vq->stats.missed_pkts
+ - (vq->stats.xstats[VHOST_BROADCAST_PKT]
+ + vq->stats.xstats[VHOST_MULTICAST_PKT]);
+ }
+ for (t = 0; t < VHOST_NB_XSTATS_RXPORT; t++) {
+ xstats[count].value = 0;
+ for (i = 0; i < dev->data->nb_rx_queues; i++) {
+ vq = dev->data->rx_queues[i];
+ if (!vq)
+ continue;
+ xstats[count].value +=
+ *(uint64_t *)(((char *)vq)
+ + vhost_rxport_stat_strings[t].offset);
+ }
+ xstats[count].id = count;
+ count++;
+ }
+ for (t = 0; t < VHOST_NB_XSTATS_TXPORT; t++) {
+ xstats[count].value = 0;
+ for (i = 0; i < dev->data->nb_tx_queues; i++) {
+ vq = dev->data->tx_queues[i];
+ if (!vq)
+ continue;
+ xstats[count].value +=
+ *(uint64_t *)(((char *)vq)
+ + vhost_txport_stat_strings[t].offset);
+ }
+ xstats[count].id = count;
+ count++;
+ }
+ return count;
+}
+
+static inline void
+vhost_count_multicast_broadcast(struct vhost_queue *vq,
+ struct rte_mbuf *mbuf)
+{
+ struct ether_addr *ea = NULL;
+ struct vhost_stats *pstats = &vq->stats;
+
+ ea = rte_pktmbuf_mtod(mbuf, struct ether_addr *);
+ if (is_multicast_ether_addr(ea)) {
+ if (is_broadcast_ether_addr(ea))
+ pstats->xstats[VHOST_BROADCAST_PKT]++;
+ else
+ pstats->xstats[VHOST_MULTICAST_PKT]++;
+ }
+}
+
+static void
+vhost_update_packet_xstats(struct vhost_queue *vq,
+ struct rte_mbuf **bufs,
+ uint16_t count)
+{
+ uint32_t pkt_len = 0;
+ uint64_t i = 0;
+ uint64_t index;
+ struct vhost_stats *pstats = &vq->stats;
+
+ for (i = 0; i < count ; i++) {
+ pkt_len = bufs[i]->pkt_len;
+ if (pkt_len == 64) {
+ pstats->xstats[VHOST_64_PKT]++;
+ } else if (pkt_len > 64 && pkt_len < 1024) {
+ index = (sizeof(pkt_len) * 8)
+ - __builtin_clz(pkt_len) - 5;
+ pstats->xstats[index]++;
+ } else {
+ if (pkt_len < 64)
+ pstats->xstats[VHOST_UNDERSIZE_PKT]++;
+ else if (pkt_len <= 1522)
+ pstats->xstats[VHOST_1024_TO_1522_PKT]++;
+ else if (pkt_len > 1522)
+ pstats->xstats[VHOST_1523_TO_MAX_PKT]++;
+ }
+ vhost_count_multicast_broadcast(vq, bufs[i]);
+ }
+}
+
static uint16_t
eth_vhost_rx(void *q, struct rte_mbuf **bufs, uint16_t nb_bufs)
{
struct vhost_queue *r = q;
uint16_t i, nb_rx = 0;
+ uint16_t nb_receive = nb_bufs;
if (unlikely(rte_atomic32_read(&r->allow_queuing) == 0))
return 0;
goto out;
/* Dequeue packets from guest TX queue */
- nb_rx = rte_vhost_dequeue_burst(r->vid,
- r->virtqueue_id, r->mb_pool, bufs, nb_bufs);
+ while (nb_receive) {
+ uint16_t nb_pkts;
+ uint16_t num = (uint16_t)RTE_MIN(nb_receive,
+ VHOST_MAX_PKT_BURST);
+
+ nb_pkts = rte_vhost_dequeue_burst(r->vid, r->virtqueue_id,
+ r->mb_pool, &bufs[nb_rx],
+ num);
+
+ nb_rx += nb_pkts;
+ nb_receive -= nb_pkts;
+ if (nb_pkts < num)
+ break;
+ }
- r->rx_pkts += nb_rx;
+ r->stats.pkts += nb_rx;
for (i = 0; likely(i < nb_rx); i++) {
bufs[i]->port = r->port;
- r->rx_bytes += bufs[i]->pkt_len;
+ r->stats.bytes += bufs[i]->pkt_len;
}
+ vhost_update_packet_xstats(r, bufs, nb_rx);
+
out:
rte_atomic32_set(&r->while_queuing, 0);
{
struct vhost_queue *r = q;
uint16_t i, nb_tx = 0;
+ uint16_t nb_send = nb_bufs;
if (unlikely(rte_atomic32_read(&r->allow_queuing) == 0))
return 0;
goto out;
/* Enqueue packets to guest RX queue */
- nb_tx = rte_vhost_enqueue_burst(r->vid,
- r->virtqueue_id, bufs, nb_bufs);
+ while (nb_send) {
+ uint16_t nb_pkts;
+ uint16_t num = (uint16_t)RTE_MIN(nb_send,
+ VHOST_MAX_PKT_BURST);
+
+ nb_pkts = rte_vhost_enqueue_burst(r->vid, r->virtqueue_id,
+ &bufs[nb_tx], num);
+
+ nb_tx += nb_pkts;
+ nb_send -= nb_pkts;
+ if (nb_pkts < num)
+ break;
+ }
- r->tx_pkts += nb_tx;
- r->missed_pkts += nb_bufs - nb_tx;
+ r->stats.pkts += nb_tx;
+ r->stats.missed_pkts += nb_bufs - nb_tx;
for (i = 0; likely(i < nb_tx); i++)
- r->tx_bytes += bufs[i]->pkt_len;
+ r->stats.bytes += bufs[i]->pkt_len;
+
+ vhost_update_packet_xstats(r, bufs, nb_tx);
+
+ /* According to RFC2863 page42 section ifHCOutMulticastPkts and
+ * ifHCOutBroadcastPkts, the counters "multicast" and "broadcast"
+ * are increased when packets are not transmitted successfully.
+ */
+ for (i = nb_tx; i < nb_bufs; i++)
+ vhost_count_multicast_broadcast(r, bufs[i]);
for (i = 0; likely(i < nb_tx); i++)
rte_pktmbuf_free(bufs[i]);
return list;
}
+static void
+update_queuing_status(struct rte_eth_dev *dev)
+{
+ struct pmd_internal *internal = dev->data->dev_private;
+ struct vhost_queue *vq;
+ unsigned int i;
+ int allow_queuing = 1;
+
+ if (rte_atomic32_read(&internal->started) == 0 ||
+ rte_atomic32_read(&internal->dev_attached) == 0)
+ allow_queuing = 0;
+
+ /* Wait until rx/tx_pkt_burst stops accessing vhost device */
+ for (i = 0; i < dev->data->nb_rx_queues; i++) {
+ vq = dev->data->rx_queues[i];
+ if (vq == NULL)
+ continue;
+ rte_atomic32_set(&vq->allow_queuing, allow_queuing);
+ while (rte_atomic32_read(&vq->while_queuing))
+ rte_pause();
+ }
+
+ for (i = 0; i < dev->data->nb_tx_queues; i++) {
+ vq = dev->data->tx_queues[i];
+ if (vq == NULL)
+ continue;
+ rte_atomic32_set(&vq->allow_queuing, allow_queuing);
+ while (rte_atomic32_read(&vq->while_queuing))
+ rte_pause();
+ }
+}
+
static int
new_device(int vid)
{
vq->port = eth_dev->data->port_id;
}
- for (i = 0; i < rte_vhost_get_queue_num(vid) * VIRTIO_QNUM; i++)
+ for (i = 0; i < rte_vhost_get_vring_num(vid); i++)
rte_vhost_enable_guest_notification(vid, i, 0);
+ rte_vhost_get_mtu(vid, ð_dev->data->mtu);
+
eth_dev->data->dev_link.link_status = ETH_LINK_UP;
- for (i = 0; i < eth_dev->data->nb_rx_queues; i++) {
- vq = eth_dev->data->rx_queues[i];
- if (vq == NULL)
- continue;
- rte_atomic32_set(&vq->allow_queuing, 1);
- }
- for (i = 0; i < eth_dev->data->nb_tx_queues; i++) {
- vq = eth_dev->data->tx_queues[i];
- if (vq == NULL)
- continue;
- rte_atomic32_set(&vq->allow_queuing, 1);
- }
+ rte_atomic32_set(&internal->dev_attached, 1);
+ update_queuing_status(eth_dev);
RTE_LOG(INFO, PMD, "New connection established\n");
- _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_INTR_LSC);
+ _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_INTR_LSC, NULL);
return 0;
}
destroy_device(int vid)
{
struct rte_eth_dev *eth_dev;
+ struct pmd_internal *internal;
struct vhost_queue *vq;
struct internal_list *list;
char ifname[PATH_MAX];
unsigned i;
+ struct rte_vhost_vring_state *state;
rte_vhost_get_ifname(vid, ifname, sizeof(ifname));
list = find_internal_resource(ifname);
return;
}
eth_dev = list->eth_dev;
+ internal = eth_dev->data->dev_private;
- /* Wait until rx/tx_pkt_burst stops accessing vhost device */
- for (i = 0; i < eth_dev->data->nb_rx_queues; i++) {
- vq = eth_dev->data->rx_queues[i];
- if (vq == NULL)
- continue;
- rte_atomic32_set(&vq->allow_queuing, 0);
- while (rte_atomic32_read(&vq->while_queuing))
- rte_pause();
- }
- for (i = 0; i < eth_dev->data->nb_tx_queues; i++) {
- vq = eth_dev->data->tx_queues[i];
- if (vq == NULL)
- continue;
- rte_atomic32_set(&vq->allow_queuing, 0);
- while (rte_atomic32_read(&vq->while_queuing))
- rte_pause();
- }
+ rte_atomic32_set(&internal->dev_attached, 0);
+ update_queuing_status(eth_dev);
eth_dev->data->dev_link.link_status = ETH_LINK_DOWN;
vq->vid = -1;
}
+ state = vring_states[eth_dev->data->port_id];
+ rte_spinlock_lock(&state->lock);
+ for (i = 0; i <= state->max_vring; i++) {
+ state->cur[i] = false;
+ state->seen[i] = false;
+ }
+ state->max_vring = 0;
+ rte_spinlock_unlock(&state->lock);
+
RTE_LOG(INFO, PMD, "Connection closed\n");
- _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_INTR_LSC);
+ _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_INTR_LSC, NULL);
}
static int
RTE_LOG(INFO, PMD, "vring%u is %s\n",
vring, enable ? "enabled" : "disabled");
- _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_QUEUE_STATE);
+ _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_QUEUE_STATE, NULL);
return 0;
}
+static struct vhost_device_ops vhost_ops = {
+ .new_device = new_device,
+ .destroy_device = destroy_device,
+ .vring_state_changed = vring_state_changed,
+};
+
int
rte_eth_vhost_get_queue_event(uint8_t port_id,
struct rte_eth_vhost_queue_event *event)
return -1;
}
-static void *
-vhost_driver_session(void *param __rte_unused)
+int
+rte_eth_vhost_get_vid_from_port_id(uint8_t port_id)
{
- static struct virtio_net_device_ops vhost_ops;
+ struct internal_list *list;
+ struct rte_eth_dev *eth_dev;
+ struct vhost_queue *vq;
+ int vid = -1;
- /* set vhost arguments */
- vhost_ops.new_device = new_device;
- vhost_ops.destroy_device = destroy_device;
- vhost_ops.vring_state_changed = vring_state_changed;
- if (rte_vhost_driver_callback_register(&vhost_ops) < 0)
- RTE_LOG(ERR, PMD, "Can't register callbacks\n");
+ if (!rte_eth_dev_is_valid_port(port_id))
+ return -1;
- /* start event handling */
- rte_vhost_driver_session_start();
+ pthread_mutex_lock(&internal_list_lock);
- return NULL;
+ TAILQ_FOREACH(list, &internal_list, next) {
+ eth_dev = list->eth_dev;
+ if (eth_dev->data->port_id == port_id) {
+ vq = eth_dev->data->rx_queues[0];
+ if (vq) {
+ vid = vq->vid;
+ }
+ break;
+ }
+ }
+
+ pthread_mutex_unlock(&internal_list_lock);
+
+ return vid;
}
static int
-vhost_driver_session_start(void)
+eth_dev_start(struct rte_eth_dev *dev)
{
- int ret;
+ struct pmd_internal *internal = dev->data->dev_private;
- ret = pthread_create(&session_th,
- NULL, vhost_driver_session, NULL);
- if (ret)
- RTE_LOG(ERR, PMD, "Can't create a thread\n");
+ rte_atomic32_set(&internal->started, 1);
+ update_queuing_status(dev);
- return ret;
+ return 0;
}
static void
-vhost_driver_session_stop(void)
+eth_dev_stop(struct rte_eth_dev *dev)
{
- int ret;
-
- ret = pthread_cancel(session_th);
- if (ret)
- RTE_LOG(ERR, PMD, "Can't cancel the thread\n");
+ struct pmd_internal *internal = dev->data->dev_private;
- ret = pthread_join(session_th, NULL);
- if (ret)
- RTE_LOG(ERR, PMD, "Can't join the thread\n");
+ rte_atomic32_set(&internal->started, 0);
+ update_queuing_status(dev);
}
-static int
-eth_dev_start(struct rte_eth_dev *dev)
+static void
+eth_dev_close(struct rte_eth_dev *dev)
{
- struct pmd_internal *internal = dev->data->dev_private;
- int ret = 0;
-
- if (rte_atomic16_cmpset(&internal->once, 0, 1)) {
- ret = rte_vhost_driver_register(internal->iface_name);
- if (ret)
- return ret;
- }
+ struct pmd_internal *internal;
+ struct internal_list *list;
- /* We need only one message handling thread */
- if (rte_atomic16_add_return(&nb_started_ports, 1) == 1)
- ret = vhost_driver_session_start();
+ internal = dev->data->dev_private;
+ if (!internal)
+ return;
- return ret;
-}
+ rte_vhost_driver_unregister(internal->iface_name);
-static void
-eth_dev_stop(struct rte_eth_dev *dev)
-{
- struct pmd_internal *internal = dev->data->dev_private;
+ list = find_internal_resource(internal->iface_name);
+ if (!list)
+ return;
- if (rte_atomic16_cmpset(&internal->once, 1, 0))
- rte_vhost_driver_unregister(internal->iface_name);
+ pthread_mutex_lock(&internal_list_lock);
+ TAILQ_REMOVE(&internal_list, list, next);
+ pthread_mutex_unlock(&internal_list_lock);
+ rte_free(list);
- if (rte_atomic16_sub_return(&nb_started_ports, 1) == 0)
- vhost_driver_session_stop();
+ free(internal->dev_name);
+ free(internal->iface_name);
+ rte_free(internal);
}
static int
return;
}
- dev_info->driver_name = drivername;
dev_info->max_mac_addrs = 1;
dev_info->max_rx_pktlen = (uint32_t)-1;
dev_info->max_rx_queues = internal->max_queues;
if (dev->data->rx_queues[i] == NULL)
continue;
vq = dev->data->rx_queues[i];
- stats->q_ipackets[i] = vq->rx_pkts;
+ stats->q_ipackets[i] = vq->stats.pkts;
rx_total += stats->q_ipackets[i];
- stats->q_ibytes[i] = vq->rx_bytes;
+ stats->q_ibytes[i] = vq->stats.bytes;
rx_total_bytes += stats->q_ibytes[i];
}
if (dev->data->tx_queues[i] == NULL)
continue;
vq = dev->data->tx_queues[i];
- stats->q_opackets[i] = vq->tx_pkts;
- tx_missed_total += vq->missed_pkts;
+ stats->q_opackets[i] = vq->stats.pkts;
+ tx_missed_total += vq->stats.missed_pkts;
tx_total += stats->q_opackets[i];
- stats->q_obytes[i] = vq->tx_bytes;
+ stats->q_obytes[i] = vq->stats.bytes;
tx_total_bytes += stats->q_obytes[i];
}
stats->ipackets = rx_total;
stats->opackets = tx_total;
- stats->imissed = tx_missed_total;
+ stats->oerrors = tx_missed_total;
stats->ibytes = rx_total_bytes;
stats->obytes = tx_total_bytes;
}
if (dev->data->rx_queues[i] == NULL)
continue;
vq = dev->data->rx_queues[i];
- vq->rx_pkts = 0;
- vq->rx_bytes = 0;
+ vq->stats.pkts = 0;
+ vq->stats.bytes = 0;
}
for (i = 0; i < dev->data->nb_tx_queues; i++) {
if (dev->data->tx_queues[i] == NULL)
continue;
vq = dev->data->tx_queues[i];
- vq->tx_pkts = 0;
- vq->tx_bytes = 0;
- vq->missed_pkts = 0;
+ vq->stats.pkts = 0;
+ vq->stats.bytes = 0;
+ vq->stats.missed_pkts = 0;
}
}
}
static int
-eth_link_update(struct rte_eth_dev *dev __rte_unused,
- int wait_to_complete __rte_unused)
+eth_tx_done_cleanup(void *txq __rte_unused, uint32_t free_cnt __rte_unused)
{
+ /*
+ * vHost does not hang onto mbuf. eth_vhost_tx() copies packet data
+ * and releases mbuf, so nothing to cleanup.
+ */
return 0;
}
-/**
- * Disable features in feature_mask. Returns 0 on success.
- */
-int
-rte_eth_vhost_feature_disable(uint64_t feature_mask)
-{
- return rte_vhost_feature_disable(feature_mask);
-}
-
-/**
- * Enable features in feature_mask. Returns 0 on success.
- */
-int
-rte_eth_vhost_feature_enable(uint64_t feature_mask)
-{
- return rte_vhost_feature_enable(feature_mask);
-}
-
-/* Returns currently supported vhost features */
-uint64_t
-rte_eth_vhost_feature_get(void)
+static int
+eth_link_update(struct rte_eth_dev *dev __rte_unused,
+ int wait_to_complete __rte_unused)
{
- return rte_vhost_feature_get();
+ return 0;
}
static const struct eth_dev_ops ops = {
.dev_start = eth_dev_start,
.dev_stop = eth_dev_stop,
+ .dev_close = eth_dev_close,
.dev_configure = eth_dev_configure,
.dev_infos_get = eth_dev_info,
.rx_queue_setup = eth_rx_queue_setup,
.tx_queue_setup = eth_tx_queue_setup,
.rx_queue_release = eth_queue_release,
.tx_queue_release = eth_queue_release,
+ .tx_done_cleanup = eth_tx_done_cleanup,
.link_update = eth_link_update,
.stats_get = eth_stats_get,
.stats_reset = eth_stats_reset,
+ .xstats_reset = vhost_dev_xstats_reset,
+ .xstats_get = vhost_dev_xstats_get,
+ .xstats_get_names = vhost_dev_xstats_get_names,
};
+static struct rte_vdev_driver pmd_vhost_drv;
+
static int
eth_dev_vhost_create(const char *name, char *iface_name, int16_t queues,
- const unsigned numa_node)
+ const unsigned numa_node, uint64_t flags)
{
struct rte_eth_dev_data *data = NULL;
struct pmd_internal *internal = NULL;
goto error;
/* reserve an ethdev entry */
- eth_dev = rte_eth_dev_allocate(name, RTE_ETH_DEV_VIRTUAL);
+ eth_dev = rte_eth_dev_allocate(name);
if (eth_dev == NULL)
goto error;
if (vring_state == NULL)
goto error;
- TAILQ_INIT(ð_dev->link_intr_cbs);
-
/* now put it all together
* - store queue data in internal,
* - store numa_node info in ethdev data
data->dev_flags =
RTE_ETH_DEV_DETACHABLE | RTE_ETH_DEV_INTR_LSC;
data->kdrv = RTE_KDRV_NONE;
- data->drv_name = internal->dev_name;
+ data->drv_name = pmd_vhost_drv.driver.name;
data->numa_node = numa_node;
/* finally assign rx and tx ops */
eth_dev->rx_pkt_burst = eth_vhost_rx;
eth_dev->tx_pkt_burst = eth_vhost_tx;
+ if (rte_vhost_driver_register(iface_name, flags))
+ goto error;
+
+ if (rte_vhost_driver_callback_register(iface_name, &vhost_ops) < 0) {
+ RTE_LOG(ERR, PMD, "Can't register callbacks\n");
+ goto error;
+ }
+
+ if (rte_vhost_driver_start(iface_name) < 0) {
+ RTE_LOG(ERR, PMD, "Failed to start driver for %s\n",
+ iface_name);
+ goto error;
+ }
+
return data->port_id;
error:
}
static inline int
-open_queues(const char *key __rte_unused, const char *value, void *extra_args)
+open_int(const char *key __rte_unused, const char *value, void *extra_args)
{
- uint16_t *q = extra_args;
+ uint16_t *n = extra_args;
if (value == NULL || extra_args == NULL)
return -EINVAL;
- *q = (uint16_t)strtoul(value, NULL, 0);
- if (*q == USHRT_MAX && errno == ERANGE)
- return -1;
-
- if (*q > RTE_MAX_QUEUES_PER_PORT)
+ *n = (uint16_t)strtoul(value, NULL, 0);
+ if (*n == USHRT_MAX && errno == ERANGE)
return -1;
return 0;
}
static int
-rte_pmd_vhost_devinit(const char *name, const char *params)
+rte_pmd_vhost_probe(const char *name, const char *params)
{
struct rte_kvargs *kvlist = NULL;
int ret = 0;
char *iface_name;
uint16_t queues;
+ uint64_t flags = 0;
+ int client_mode = 0;
+ int dequeue_zero_copy = 0;
RTE_LOG(INFO, PMD, "Initializing pmd_vhost for %s\n", name);
if (rte_kvargs_count(kvlist, ETH_VHOST_QUEUES_ARG) == 1) {
ret = rte_kvargs_process(kvlist, ETH_VHOST_QUEUES_ARG,
- &open_queues, &queues);
- if (ret < 0)
+ &open_int, &queues);
+ if (ret < 0 || queues > RTE_MAX_QUEUES_PER_PORT)
goto out_free;
} else
queues = 1;
- eth_dev_vhost_create(name, iface_name, queues, rte_socket_id());
+ if (rte_kvargs_count(kvlist, ETH_VHOST_CLIENT_ARG) == 1) {
+ ret = rte_kvargs_process(kvlist, ETH_VHOST_CLIENT_ARG,
+ &open_int, &client_mode);
+ if (ret < 0)
+ goto out_free;
+
+ if (client_mode)
+ flags |= RTE_VHOST_USER_CLIENT;
+ }
+
+ if (rte_kvargs_count(kvlist, ETH_VHOST_DEQUEUE_ZERO_COPY) == 1) {
+ ret = rte_kvargs_process(kvlist, ETH_VHOST_DEQUEUE_ZERO_COPY,
+ &open_int, &dequeue_zero_copy);
+ if (ret < 0)
+ goto out_free;
+
+ if (dequeue_zero_copy)
+ flags |= RTE_VHOST_USER_DEQUEUE_ZERO_COPY;
+ }
+
+ eth_dev_vhost_create(name, iface_name, queues, rte_socket_id(), flags);
out_free:
rte_kvargs_free(kvlist);
}
static int
-rte_pmd_vhost_devuninit(const char *name)
+rte_pmd_vhost_remove(const char *name)
{
struct rte_eth_dev *eth_dev = NULL;
- struct pmd_internal *internal;
- struct internal_list *list;
unsigned int i;
RTE_LOG(INFO, PMD, "Un-Initializing pmd_vhost for %s\n", name);
if (eth_dev == NULL)
return -ENODEV;
- internal = eth_dev->data->dev_private;
- if (internal == NULL)
- return -ENODEV;
-
- list = find_internal_resource(internal->iface_name);
- if (list == NULL)
- return -ENODEV;
-
- pthread_mutex_lock(&internal_list_lock);
- TAILQ_REMOVE(&internal_list, list, next);
- pthread_mutex_unlock(&internal_list_lock);
- rte_free(list);
-
eth_dev_stop(eth_dev);
+ eth_dev_close(eth_dev);
+
rte_free(vring_states[eth_dev->data->port_id]);
vring_states[eth_dev->data->port_id] = NULL;
- free(internal->dev_name);
- free(internal->iface_name);
-
for (i = 0; i < eth_dev->data->nb_rx_queues; i++)
rte_free(eth_dev->data->rx_queues[i]);
for (i = 0; i < eth_dev->data->nb_tx_queues; i++)
rte_free(eth_dev->data->mac_addrs);
rte_free(eth_dev->data);
- rte_free(internal);
rte_eth_dev_release_port(eth_dev);
return 0;
}
-static struct rte_driver pmd_vhost_drv = {
- .name = "eth_vhost",
- .type = PMD_VDEV,
- .init = rte_pmd_vhost_devinit,
- .uninit = rte_pmd_vhost_devuninit,
+static struct rte_vdev_driver pmd_vhost_drv = {
+ .probe = rte_pmd_vhost_probe,
+ .remove = rte_pmd_vhost_remove,
};
-PMD_REGISTER_DRIVER(pmd_vhost_drv);
+RTE_PMD_REGISTER_VDEV(net_vhost, pmd_vhost_drv);
+RTE_PMD_REGISTER_ALIAS(net_vhost, eth_vhost);
+RTE_PMD_REGISTER_PARAM_STRING(net_vhost,
+ "iface=<ifc> "
+ "queues=<int>");
git.droids-corp.org / dpdk.git / blobdiff