#include <unistd.h>
#include <pthread.h>
#include <stdbool.h>
+#include <sys/epoll.h>
#include <rte_mbuf.h>
#include <rte_ethdev_driver.h>
#define ETH_VHOST_IFACE_ARG "iface"
#define ETH_VHOST_QUEUES_ARG "queues"
#define ETH_VHOST_CLIENT_ARG "client"
-#define ETH_VHOST_DEQUEUE_ZERO_COPY "dequeue-zero-copy"
#define ETH_VHOST_IOMMU_SUPPORT "iommu-support"
#define ETH_VHOST_POSTCOPY_SUPPORT "postcopy-support"
#define ETH_VHOST_VIRTIO_NET_F_HOST_TSO "tso"
ETH_VHOST_IFACE_ARG,
ETH_VHOST_QUEUES_ARG,
ETH_VHOST_CLIENT_ARG,
- ETH_VHOST_DEQUEUE_ZERO_COPY,
ETH_VHOST_IOMMU_SUPPORT,
ETH_VHOST_POSTCOPY_SUPPORT,
ETH_VHOST_VIRTIO_NET_F_HOST_TSO,
struct rte_mempool *mb_pool;
uint16_t port;
uint16_t virtqueue_id;
- bool intr_en;
struct vhost_stats stats;
+ int intr_enable;
+ rte_spinlock_t intr_lock;
};
struct pmd_internal {
return list;
}
+static int
+eth_vhost_update_intr(struct rte_eth_dev *eth_dev, uint16_t rxq_idx)
+{
+ struct rte_intr_handle *handle = eth_dev->intr_handle;
+ struct rte_epoll_event rev;
+ int epfd, ret;
+
+ if (!handle)
+ return 0;
+
+ if (handle->efds[rxq_idx] == handle->elist[rxq_idx].fd)
+ return 0;
+
+ VHOST_LOG(INFO, "kickfd for rxq-%d was changed, updating handler.\n",
+ rxq_idx);
+
+ if (handle->elist[rxq_idx].fd != -1)
+ VHOST_LOG(ERR, "Unexpected previous kickfd value (Got %d, expected -1).\n",
+ handle->elist[rxq_idx].fd);
+
+ /*
+ * First remove invalid epoll event, and then install
+ * the new one. May be solved with a proper API in the
+ * future.
+ */
+ epfd = handle->elist[rxq_idx].epfd;
+ rev = handle->elist[rxq_idx];
+ ret = rte_epoll_ctl(epfd, EPOLL_CTL_DEL, rev.fd,
+ &handle->elist[rxq_idx]);
+ if (ret) {
+ VHOST_LOG(ERR, "Delete epoll event failed.\n");
+ return ret;
+ }
+
+ rev.fd = handle->efds[rxq_idx];
+ handle->elist[rxq_idx] = rev;
+ ret = rte_epoll_ctl(epfd, EPOLL_CTL_ADD, rev.fd,
+ &handle->elist[rxq_idx]);
+ if (ret) {
+ VHOST_LOG(ERR, "Add epoll event failed.\n");
+ return ret;
+ }
+
+ return 0;
+}
+
static int
eth_rxq_intr_enable(struct rte_eth_dev *dev, uint16_t qid)
{
struct rte_vhost_vring vring;
struct vhost_queue *vq;
- int ret = 0;
+ int old_intr_enable, ret = 0;
vq = dev->data->rx_queues[qid];
if (!vq) {
return -1;
}
+ rte_spinlock_lock(&vq->intr_lock);
+ old_intr_enable = vq->intr_enable;
+ vq->intr_enable = 1;
+ ret = eth_vhost_update_intr(dev, qid);
+ rte_spinlock_unlock(&vq->intr_lock);
+
+ if (ret < 0) {
+ VHOST_LOG(ERR, "Failed to update rxq%d's intr\n", qid);
+ vq->intr_enable = old_intr_enable;
+ return ret;
+ }
+
ret = rte_vhost_get_vhost_vring(vq->vid, (qid << 1) + 1, &vring);
if (ret < 0) {
VHOST_LOG(ERR, "Failed to get rxq%d's vring\n", qid);
rte_vhost_enable_guest_notification(vq->vid, (qid << 1) + 1, 1);
rte_wmb();
- vq->intr_en = true;
-
return ret;
}
rte_vhost_enable_guest_notification(vq->vid, (qid << 1) + 1, 0);
rte_wmb();
- vq->intr_en = false;
+ vq->intr_enable = 0;
return 0;
}
{
struct rte_vhost_vring vring;
struct vhost_queue *vq;
- int count = 0;
int nb_rxq = dev->data->nb_rx_queues;
int i;
int ret;
VHOST_LOG(INFO, "Prepare intr vec\n");
for (i = 0; i < nb_rxq; i++) {
+ dev->intr_handle->intr_vec[i] = RTE_INTR_VEC_RXTX_OFFSET + i;
+ dev->intr_handle->efds[i] = -1;
vq = dev->data->rx_queues[i];
if (!vq) {
VHOST_LOG(INFO, "rxq-%d not setup yet, skip!\n", i);
"rxq-%d's kickfd is invalid, skip!\n", i);
continue;
}
- dev->intr_handle->intr_vec[i] = RTE_INTR_VEC_RXTX_OFFSET + i;
dev->intr_handle->efds[i] = vring.kickfd;
- count++;
VHOST_LOG(INFO, "Installed intr vec for rxq-%d\n", i);
}
- dev->intr_handle->nb_efd = count;
- dev->intr_handle->max_intr = count + 1;
+ dev->intr_handle->nb_efd = nb_rxq;
+ dev->intr_handle->max_intr = nb_rxq + 1;
dev->intr_handle->type = RTE_INTR_HANDLE_VDEV;
return 0;
VHOST_LOG(INFO, "Vhost device %d created\n", vid);
- _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_INTR_LSC, NULL);
+ rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_INTR_LSC, NULL);
return 0;
}
VHOST_LOG(INFO, "Vhost device %d destroyed\n", vid);
eth_vhost_uninstall_intr(eth_dev);
- _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_INTR_LSC, NULL);
+ rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_INTR_LSC, NULL);
}
static int
{
struct rte_eth_conf *dev_conf = ð_dev->data->dev_conf;
struct pmd_internal *internal = eth_dev->data->dev_private;
- struct rte_vhost_vring vring;
struct vhost_queue *vq;
+ struct rte_vhost_vring vring;
int rx_idx = vring_id % 2 ? (vring_id - 1) >> 1 : -1;
int ret = 0;
rte_atomic32_read(&internal->dev_attached) &&
rte_atomic32_read(&internal->started) &&
dev_conf->intr_conf.rxq) {
- vq = eth_dev->data->rx_queues[rx_idx];
ret = rte_vhost_get_vhost_vring(vid, vring_id, &vring);
- if (!ret) {
- if (vring.kickfd !=
- eth_dev->intr_handle->efds[rx_idx]) {
- VHOST_LOG(INFO,
- "kickfd for rxq-%d was changed.\n",
- rx_idx);
- eth_dev->intr_handle->efds[rx_idx] =
- vring.kickfd;
- }
+ if (ret) {
+ VHOST_LOG(ERR, "Failed to get vring %d information.\n",
+ vring_id);
+ return ret;
+ }
+ eth_dev->intr_handle->efds[rx_idx] = vring.kickfd;
- rte_vhost_enable_guest_notification(vid, vring_id,
- vq->intr_en);
- rte_wmb();
+ vq = eth_dev->data->rx_queues[rx_idx];
+ if (!vq) {
+ VHOST_LOG(ERR, "rxq%d is not setup yet\n", rx_idx);
+ return -1;
}
+
+ rte_spinlock_lock(&vq->intr_lock);
+ if (vq->intr_enable)
+ ret = eth_vhost_update_intr(eth_dev, rx_idx);
+ rte_spinlock_unlock(&vq->intr_lock);
}
return ret;
VHOST_LOG(INFO, "vring%u is %s\n",
vring, enable ? "enabled" : "disabled");
- _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_QUEUE_STATE, NULL);
+ rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_QUEUE_STATE, NULL);
return 0;
}
return 0;
}
-static void
+static int
eth_dev_stop(struct rte_eth_dev *dev)
{
struct pmd_internal *internal = dev->data->dev_private;
+ dev->data->dev_started = 0;
rte_atomic32_set(&internal->started, 0);
update_queuing_status(dev);
+
+ return 0;
}
-static void
+static int
eth_dev_close(struct rte_eth_dev *dev)
{
struct pmd_internal *internal;
struct internal_list *list;
- unsigned int i;
+ unsigned int i, ret;
+
+ if (rte_eal_process_type() != RTE_PROC_PRIMARY)
+ return 0;
internal = dev->data->dev_private;
if (!internal)
- return;
+ return 0;
- eth_dev_stop(dev);
+ ret = eth_dev_stop(dev);
list = find_internal_resource(internal->iface_name);
if (list) {
rte_free(vring_states[dev->data->port_id]);
vring_states[dev->data->port_id] = NULL;
+
+ return ret;
}
static int
vq->mb_pool = mb_pool;
vq->virtqueue_id = rx_queue_id * VIRTIO_QNUM + VIRTIO_TXQ;
+ rte_spinlock_init(&vq->intr_lock);
dev->data->rx_queues[rx_queue_id] = vq;
return 0;
}
vq->virtqueue_id = tx_queue_id * VIRTIO_QNUM + VIRTIO_RXQ;
+ rte_spinlock_init(&vq->intr_lock);
dev->data->tx_queues[tx_queue_id] = vq;
return 0;
.rx_queue_release = eth_queue_release,
.tx_queue_release = eth_queue_release,
.tx_done_cleanup = eth_tx_done_cleanup,
- .rx_queue_count = eth_rx_queue_count,
.link_update = eth_link_update,
.stats_get = eth_stats_get,
.stats_reset = eth_stats_reset,
internal->flags = flags;
internal->disable_flags = disable_flags;
data->dev_link = pmd_link;
- data->dev_flags = RTE_ETH_DEV_INTR_LSC | RTE_ETH_DEV_CLOSE_REMOVE;
+ data->dev_flags = RTE_ETH_DEV_INTR_LSC |
+ RTE_ETH_DEV_AUTOFILL_QUEUE_XSTATS;
data->promiscuous = 1;
data->all_multicast = 1;
eth_dev->dev_ops = &ops;
+ eth_dev->rx_queue_count = eth_rx_queue_count;
/* finally assign rx and tx ops */
eth_dev->rx_pkt_burst = eth_vhost_rx;
uint64_t flags = 0;
uint64_t disable_flags = 0;
int client_mode = 0;
- int dequeue_zero_copy = 0;
int iommu_support = 0;
int postcopy_support = 0;
int tso = 0;
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;
- }
-
if (rte_kvargs_count(kvlist, ETH_VHOST_IOMMU_SUPPORT) == 1) {
ret = rte_kvargs_process(kvlist, ETH_VHOST_IOMMU_SUPPORT,
&open_int, &iommu_support);
if (eth_dev == NULL)
return 0;
- if (rte_eal_process_type() != RTE_PROC_PRIMARY)
- return rte_eth_dev_release_port(eth_dev);
-
eth_dev_close(eth_dev);
-
rte_eth_dev_release_port(eth_dev);
return 0;
"iface=<ifc> "
"queues=<int> "
"client=<0|1> "
- "dequeue-zero-copy=<0|1> "
"iommu-support=<0|1> "
"postcopy-support=<0|1> "
"tso=<0|1> "