return 0;
}
+static void virtio_queues_unbind_intr(struct rte_eth_dev *dev);
+
static void
virtio_dev_close(struct rte_eth_dev *dev)
{
struct virtio_hw *hw = dev->data->dev_private;
+ struct rte_intr_conf *intr_conf = &dev->data->dev_conf.intr_conf;
PMD_INIT_LOG(DEBUG, "virtio_dev_close");
/* reset the NIC */
if (dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC)
VTPCI_OPS(hw)->set_config_irq(hw, VIRTIO_MSI_NO_VECTOR);
+ if (intr_conf->rxq)
+ virtio_queues_unbind_intr(dev);
+
+ if (intr_conf->lsc || intr_conf->rxq) {
+ rte_intr_disable(dev->intr_handle);
+ rte_intr_efd_disable(dev->intr_handle);
+ rte_free(dev->intr_handle->intr_vec);
+ dev->intr_handle->intr_vec = NULL;
+ }
+
vtpci_reset(hw);
virtio_dev_free_mbufs(dev);
virtio_free_queues(hw);
int ret;
if (!vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_RX)) {
- PMD_INIT_LOG(INFO, "host does not support rx control\n");
+ PMD_INIT_LOG(INFO, "host does not support rx control");
return;
}
int ret;
if (!vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_RX)) {
- PMD_INIT_LOG(INFO, "host does not support rx control\n");
+ PMD_INIT_LOG(INFO, "host does not support rx control");
return;
}
int ret;
if (!vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_RX)) {
- PMD_INIT_LOG(INFO, "host does not support rx control\n");
+ PMD_INIT_LOG(INFO, "host does not support rx control");
return;
}
int ret;
if (!vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_RX)) {
- PMD_INIT_LOG(INFO, "host does not support rx control\n");
+ PMD_INIT_LOG(INFO, "host does not support rx control");
return;
}
uint32_t ether_hdr_len = ETHER_HDR_LEN + VLAN_TAG_LEN +
hw->vtnet_hdr_size;
uint32_t frame_size = mtu + ether_hdr_len;
+ uint32_t max_frame_size = hw->max_mtu + ether_hdr_len;
+
+ max_frame_size = RTE_MIN(max_frame_size, VIRTIO_MAX_RX_PKTLEN);
- if (mtu < ETHER_MIN_MTU || frame_size > VIRTIO_MAX_RX_PKTLEN) {
- PMD_INIT_LOG(ERR, "MTU should be between %d and %d\n",
- ETHER_MIN_MTU, VIRTIO_MAX_RX_PKTLEN - ether_hdr_len);
+ if (mtu < ETHER_MIN_MTU || frame_size > max_frame_size) {
+ PMD_INIT_LOG(ERR, "MTU should be between %d and %d",
+ ETHER_MIN_MTU, max_frame_size - ether_hdr_len);
return -EINVAL;
}
return 0;
}
+static int
+virtio_dev_rx_queue_intr_enable(struct rte_eth_dev *dev, uint16_t queue_id)
+{
+ struct virtnet_rx *rxvq = dev->data->rx_queues[queue_id];
+ struct virtqueue *vq = rxvq->vq;
+
+ virtqueue_enable_intr(vq);
+ return 0;
+}
+
+static int
+virtio_dev_rx_queue_intr_disable(struct rte_eth_dev *dev, uint16_t queue_id)
+{
+ struct virtnet_rx *rxvq = dev->data->rx_queues[queue_id];
+ struct virtqueue *vq = rxvq->vq;
+
+ virtqueue_disable_intr(vq);
+ return 0;
+}
+
/*
* dev_ops for virtio, bare necessities for basic operation
*/
.xstats_reset = virtio_dev_stats_reset,
.link_update = virtio_dev_link_update,
.rx_queue_setup = virtio_dev_rx_queue_setup,
+ .rx_queue_intr_enable = virtio_dev_rx_queue_intr_enable,
+ .rx_queue_intr_disable = virtio_dev_rx_queue_intr_disable,
.rx_queue_release = virtio_dev_queue_release,
+ .rx_descriptor_done = virtio_dev_rx_queue_done,
.tx_queue_setup = virtio_dev_tx_queue_setup,
.tx_queue_release = virtio_dev_queue_release,
/* collect stats per queue */
PMD_INIT_LOG(DEBUG, "host_features before negotiate = %" PRIx64,
host_features);
+ /* If supported, ensure MTU value is valid before acknowledging it. */
+ if (host_features & req_features & (1ULL << VIRTIO_NET_F_MTU)) {
+ struct virtio_net_config config;
+
+ vtpci_read_dev_config(hw,
+ offsetof(struct virtio_net_config, mtu),
+ &config.mtu, sizeof(config.mtu));
+
+ if (config.mtu < ETHER_MIN_MTU)
+ req_features &= ~(1ULL << VIRTIO_NET_F_MTU);
+ }
+
/*
* Negotiate features: Subset of device feature bits are written back
* guest feature bits.
* Process Virtio Config changed interrupt and call the callback
* if link state changed.
*/
-static void
+void
virtio_interrupt_handler(struct rte_intr_handle *handle,
void *param)
{
eth_dev->rx_pkt_burst = &virtio_recv_pkts;
}
+/* Only support 1:1 queue/interrupt mapping so far.
+ * TODO: support n:1 queue/interrupt mapping when there are limited number of
+ * interrupt vectors (<N+1).
+ */
+static int
+virtio_queues_bind_intr(struct rte_eth_dev *dev)
+{
+ uint32_t i;
+ struct virtio_hw *hw = dev->data->dev_private;
+
+ PMD_INIT_LOG(INFO, "queue/interrupt binding");
+ for (i = 0; i < dev->data->nb_rx_queues; ++i) {
+ dev->intr_handle->intr_vec[i] = i + 1;
+ if (VTPCI_OPS(hw)->set_queue_irq(hw, hw->vqs[i * 2], i + 1) ==
+ VIRTIO_MSI_NO_VECTOR) {
+ PMD_DRV_LOG(ERR, "failed to set queue vector");
+ return -EBUSY;
+ }
+ }
+
+ return 0;
+}
+
+static void
+virtio_queues_unbind_intr(struct rte_eth_dev *dev)
+{
+ uint32_t i;
+ struct virtio_hw *hw = dev->data->dev_private;
+
+ PMD_INIT_LOG(INFO, "queue/interrupt unbinding");
+ for (i = 0; i < dev->data->nb_rx_queues; ++i)
+ VTPCI_OPS(hw)->set_queue_irq(hw,
+ hw->vqs[i * VTNET_CQ],
+ VIRTIO_MSI_NO_VECTOR);
+}
+
+static int
+virtio_configure_intr(struct rte_eth_dev *dev)
+{
+ struct virtio_hw *hw = dev->data->dev_private;
+
+ if (!rte_intr_cap_multiple(dev->intr_handle)) {
+ PMD_INIT_LOG(ERR, "Multiple intr vector not supported");
+ return -ENOTSUP;
+ }
+
+ if (rte_intr_efd_enable(dev->intr_handle, dev->data->nb_rx_queues)) {
+ PMD_INIT_LOG(ERR, "Fail to create eventfd");
+ return -1;
+ }
+
+ if (!dev->intr_handle->intr_vec) {
+ dev->intr_handle->intr_vec =
+ rte_zmalloc("intr_vec",
+ hw->max_queue_pairs * sizeof(int), 0);
+ if (!dev->intr_handle->intr_vec) {
+ PMD_INIT_LOG(ERR, "Failed to allocate %u rxq vectors",
+ hw->max_queue_pairs);
+ return -ENOMEM;
+ }
+ }
+
+ /* Re-register callback to update max_intr */
+ rte_intr_callback_unregister(dev->intr_handle,
+ virtio_interrupt_handler,
+ dev);
+ rte_intr_callback_register(dev->intr_handle,
+ virtio_interrupt_handler,
+ dev);
+
+ /* DO NOT try to remove this! This function will enable msix, or QEMU
+ * will encounter SIGSEGV when DRIVER_OK is sent.
+ * And for legacy devices, this should be done before queue/vec binding
+ * to change the config size from 20 to 24, or VIRTIO_MSI_QUEUE_VECTOR
+ * (22) will be ignored.
+ */
+ if (rte_intr_enable(dev->intr_handle) < 0) {
+ PMD_DRV_LOG(ERR, "interrupt enable failed");
+ return -1;
+ }
+
+ if (virtio_queues_bind_intr(dev) < 0) {
+ PMD_INIT_LOG(ERR, "Failed to bind queue/interrupt");
+ return -1;
+ }
+
+ return 0;
+}
+
/* reset device and renegotiate features if needed */
static int
virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features)
rte_eth_copy_pci_info(eth_dev, pci_dev);
}
- /* If host does not support status then disable LSC */
- if (!vtpci_with_feature(hw, VIRTIO_NET_F_STATUS))
- eth_dev->data->dev_flags &= ~RTE_ETH_DEV_INTR_LSC;
- else
+ /* If host does not support both status and MSI-X then disable LSC */
+ if (vtpci_with_feature(hw, VIRTIO_NET_F_STATUS) && hw->use_msix)
eth_dev->data->dev_flags |= RTE_ETH_DEV_INTR_LSC;
+ else
+ eth_dev->data->dev_flags &= ~RTE_ETH_DEV_INTR_LSC;
rx_func_get(eth_dev);
hw->max_queue_pairs = config->max_virtqueue_pairs;
+ if (vtpci_with_feature(hw, VIRTIO_NET_F_MTU)) {
+ vtpci_read_dev_config(hw,
+ offsetof(struct virtio_net_config, mtu),
+ &config->mtu,
+ sizeof(config->mtu));
+
+ /*
+ * MTU value has already been checked at negotiation
+ * time, but check again in case it has changed since
+ * then, which should not happen.
+ */
+ if (config->mtu < ETHER_MIN_MTU) {
+ PMD_INIT_LOG(ERR, "invalid max MTU value (%u)",
+ config->mtu);
+ return -1;
+ }
+
+ hw->max_mtu = config->mtu;
+ /* Set initial MTU to maximum one supported by vhost */
+ eth_dev->data->mtu = config->mtu;
+
+ } else {
+ hw->max_mtu = VIRTIO_MAX_RX_PKTLEN - ETHER_HDR_LEN -
+ VLAN_TAG_LEN - hw->vtnet_hdr_size;
+ }
+
PMD_INIT_LOG(DEBUG, "config->max_virtqueue_pairs=%d",
config->max_virtqueue_pairs);
PMD_INIT_LOG(DEBUG, "config->status=%d", config->status);
ret = virtio_alloc_queues(eth_dev);
if (ret < 0)
return ret;
+
+ if (eth_dev->data->dev_conf.intr_conf.rxq) {
+ if (virtio_configure_intr(eth_dev) < 0) {
+ PMD_INIT_LOG(ERR, "failed to configure interrupt");
+ return -1;
+ }
+ }
+
vtpci_reinit_complete(hw);
if (pci_dev)
static void
virtio_set_vtpci_ops(struct virtio_hw *hw)
{
+#ifdef RTE_VIRTIO_USER
if (hw->virtio_user_dev)
VTPCI_OPS(hw) = &virtio_user_ops;
- else if (hw->modern)
+ else
+#endif
+ if (hw->modern)
VTPCI_OPS(hw) = &modern_ops;
else
VTPCI_OPS(hw) = &legacy_ops;
return -ENOMEM;
}
+ hw->port_id = eth_dev->data->port_id;
/* For virtio_user case the hw->virtio_user_dev is populated by
* virtio_user_eth_dev_alloc() before eth_virtio_dev_init() is called.
*/
return ret;
}
- hw->port_id = eth_dev->data->port_id;
eth_dev->data->dev_flags = dev_flags;
/* reset device and negotiate default features */
PMD_DRV_LOG(ERR, "link status not supported by host");
return -ENOTSUP;
}
+ }
+
+ /* Enable uio/vfio intr/eventfd mapping: althrough we already did that
+ * in device configure, but it could be unmapped when device is
+ * stopped.
+ */
+ if (dev->data->dev_conf.intr_conf.lsc ||
+ dev->data->dev_conf.intr_conf.rxq) {
+ rte_intr_disable(dev->intr_handle);
if (rte_intr_enable(dev->intr_handle) < 0) {
PMD_DRV_LOG(ERR, "interrupt enable failed");
virtio_dev_stop(struct rte_eth_dev *dev)
{
struct rte_eth_link link;
+ struct rte_intr_conf *intr_conf = &dev->data->dev_conf.intr_conf;
PMD_INIT_LOG(DEBUG, "stop");
- if (dev->data->dev_conf.intr_conf.lsc)
+ if (intr_conf->lsc || intr_conf->rxq)
rte_intr_disable(dev->intr_handle);
memset(&link, 0, sizeof(link));
static void
virtio_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
{
- uint64_t tso_mask;
+ uint64_t tso_mask, host_features;
struct virtio_hw *hw = dev->data->dev_private;
+ dev_info->speed_capa = ETH_LINK_SPEED_10G; /* fake value */
+
dev_info->pci_dev = dev->device ? RTE_DEV_TO_PCI(dev->device) : NULL;
dev_info->max_rx_queues =
RTE_MIN(hw->max_queue_pairs, VIRTIO_MAX_RX_QUEUES);
dev_info->default_txconf = (struct rte_eth_txconf) {
.txq_flags = ETH_TXQ_FLAGS_NOOFFLOADS
};
- dev_info->rx_offload_capa =
- DEV_RX_OFFLOAD_TCP_CKSUM |
- DEV_RX_OFFLOAD_UDP_CKSUM |
- DEV_RX_OFFLOAD_TCP_LRO;
- dev_info->tx_offload_capa = 0;
+ host_features = VTPCI_OPS(hw)->get_features(hw);
+ dev_info->rx_offload_capa = 0;
+ if (host_features & (1ULL << VIRTIO_NET_F_GUEST_CSUM)) {
+ dev_info->rx_offload_capa |=
+ DEV_RX_OFFLOAD_TCP_CKSUM |
+ DEV_RX_OFFLOAD_UDP_CKSUM;
+ }
+ tso_mask = (1ULL << VIRTIO_NET_F_GUEST_TSO4) |
+ (1ULL << VIRTIO_NET_F_GUEST_TSO6);
+ if ((host_features & tso_mask) == tso_mask)
+ dev_info->rx_offload_capa |= DEV_RX_OFFLOAD_TCP_LRO;
+
+ dev_info->tx_offload_capa = 0;
if (hw->guest_features & (1ULL << VIRTIO_NET_F_CSUM)) {
dev_info->tx_offload_capa |=
DEV_TX_OFFLOAD_UDP_CKSUM |
DEV_TX_OFFLOAD_TCP_CKSUM;
}
-
tso_mask = (1ULL << VIRTIO_NET_F_HOST_TSO4) |
(1ULL << VIRTIO_NET_F_HOST_TSO6);
if ((hw->guest_features & tso_mask) == tso_mask)