#define VIRTIO_NB_TXQ_XSTATS (sizeof(rte_virtio_txq_stat_strings) / \
sizeof(rte_virtio_txq_stat_strings[0]))
+struct virtio_hw_internal virtio_hw_internal[RTE_MAX_ETHPORTS];
+
static int
virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl,
int *dlen, int pkt_num)
* Read the virtqueue size from the Queue Size field
* Always power of 2 and if 0 virtqueue does not exist
*/
- vq_size = hw->vtpci_ops->get_queue_num(hw, vtpci_queue_idx);
+ vq_size = VTPCI_OPS(hw)->get_queue_num(hw, vtpci_queue_idx);
PMD_INIT_LOG(DEBUG, "vq_size: %u", vq_size);
if (vq_size == 0) {
PMD_INIT_LOG(ERR, "virtqueue does not exist");
hw->cvq = cvq;
}
- /* For virtio_user case (that is when dev->pci_dev is NULL), we use
+ /* For virtio_user case (that is when hw->dev is NULL), we use
* virtual address. And we need properly set _offset_, please see
* VIRTIO_MBUF_DATA_DMA_ADDR in virtqueue.h for more information.
*/
- if (dev->pci_dev)
+ if (!hw->virtio_user_dev)
vq->offset = offsetof(struct rte_mbuf, buf_physaddr);
else {
vq->vq_ring_mem = (uintptr_t)mz->addr;
}
}
- if (hw->vtpci_ops->setup_queue(hw, vq) < 0) {
+ if (VTPCI_OPS(hw)->setup_queue(hw, vq) < 0) {
PMD_INIT_LOG(ERR, "setup_queue failed");
return -EINVAL;
}
/* reset the NIC */
if (dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC)
- vtpci_irq_config(hw, VIRTIO_MSI_NO_VECTOR);
+ VTPCI_OPS(hw)->set_config_irq(hw, VIRTIO_MSI_NO_VECTOR);
vtpci_reset(hw);
- hw->started = 0;
virtio_dev_free_mbufs(dev);
virtio_free_queues(hw);
}
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 */
for (t = 0; t < VIRTIO_NB_RXQ_XSTATS; t++) {
xstats[count].value = *(uint64_t *)(((char *)rxvq) +
rte_virtio_rxq_stat_strings[t].offset);
+ xstats[count].id = count;
count++;
}
}
for (t = 0; t < VIRTIO_NB_TXQ_XSTATS; t++) {
xstats[count].value = *(uint64_t *)(((char *)txvq) +
rte_virtio_txq_stat_strings[t].offset);
+ xstats[count].id = count;
count++;
}
}
req_features);
/* Read device(host) feature bits */
- host_features = hw->vtpci_ops->get_features(hw);
+ host_features = VTPCI_OPS(hw)->get_features(hw);
PMD_INIT_LOG(DEBUG, "host_features before negotiate = %" PRIx64,
host_features);
* if link state changed.
*/
static void
-virtio_interrupt_handler(__rte_unused struct rte_intr_handle *handle,
+virtio_interrupt_handler(struct rte_intr_handle *handle,
void *param)
{
struct rte_eth_dev *dev = param;
isr = vtpci_isr(hw);
PMD_DRV_LOG(INFO, "interrupt status = %#x", isr);
- if (rte_intr_enable(&dev->pci_dev->intr_handle) < 0)
+ if (rte_intr_enable(handle) < 0)
PMD_DRV_LOG(ERR, "interrupt enable failed");
if (isr & VIRTIO_PCI_ISR_CONFIG) {
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\n");
+ 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 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)
struct virtio_hw *hw = eth_dev->data->dev_private;
struct virtio_net_config *config;
struct virtio_net_config local_config;
- struct rte_pci_device *pci_dev = eth_dev->pci_dev;
+ struct rte_pci_device *pci_dev = NULL;
int ret;
/* Reset the device although not necessary at startup */
if (virtio_negotiate_features(hw, req_features) < 0)
return -1;
+ if (eth_dev->device) {
+ pci_dev = RTE_DEV_TO_PCI(eth_dev->device);
+ 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
eth_dev->data->dev_flags |= RTE_ETH_DEV_INTR_LSC;
- rte_eth_copy_pci_info(eth_dev, pci_dev);
-
rx_func_get(eth_dev);
/* Setting up rx_header size for the device */
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)
return 0;
}
+/*
+ * Remap the PCI device again (IO port map for legacy device and
+ * memory map for modern device), so that the secondary process
+ * could have the PCI initiated correctly.
+ */
+static int
+virtio_remap_pci(struct rte_pci_device *pci_dev, struct virtio_hw *hw)
+{
+ if (hw->modern) {
+ /*
+ * We don't have to re-parse the PCI config space, since
+ * rte_eal_pci_map_device() makes sure the mapped address
+ * in secondary process would equal to the one mapped in
+ * the primary process: error will be returned if that
+ * requirement is not met.
+ *
+ * That said, we could simply reuse all cap pointers
+ * (such as dev_cfg, common_cfg, etc.) parsed from the
+ * primary process, which is stored in shared memory.
+ */
+ if (rte_eal_pci_map_device(pci_dev)) {
+ PMD_INIT_LOG(DEBUG, "failed to map pci device!");
+ return -1;
+ }
+ } else {
+ if (rte_eal_pci_ioport_map(pci_dev, 0, VTPCI_IO(hw)) < 0)
+ return -1;
+ }
+
+ return 0;
+}
+
+static void
+virtio_set_vtpci_ops(struct virtio_hw *hw)
+{
+ if (hw->virtio_user_dev)
+ VTPCI_OPS(hw) = &virtio_user_ops;
+ else if (hw->modern)
+ VTPCI_OPS(hw) = &modern_ops;
+ else
+ VTPCI_OPS(hw) = &legacy_ops;
+}
+
/*
* This function is based on probe() function in virtio_pci.c
* It returns 0 on success.
eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
{
struct virtio_hw *hw = eth_dev->data->dev_private;
- struct rte_pci_device *pci_dev;
uint32_t dev_flags = RTE_ETH_DEV_DETACHABLE;
int ret;
eth_dev->tx_pkt_burst = &virtio_xmit_pkts;
if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
- rx_func_get(eth_dev);
+ if (!hw->virtio_user_dev) {
+ ret = virtio_remap_pci(RTE_DEV_TO_PCI(eth_dev->device),
+ hw);
+ if (ret)
+ return ret;
+ }
+
+ virtio_set_vtpci_ops(hw);
+ if (hw->use_simple_rxtx) {
+ eth_dev->tx_pkt_burst = virtio_xmit_pkts_simple;
+ eth_dev->rx_pkt_burst = virtio_recv_pkts_vec;
+ } else {
+ rx_func_get(eth_dev);
+ }
return 0;
}
return -ENOMEM;
}
- pci_dev = eth_dev->pci_dev;
-
- if (pci_dev) {
- ret = vtpci_init(pci_dev, hw, &dev_flags);
+ /* For virtio_user case the hw->virtio_user_dev is populated by
+ * virtio_user_eth_dev_alloc() before eth_virtio_dev_init() is called.
+ */
+ if (!hw->virtio_user_dev) {
+ ret = vtpci_init(RTE_DEV_TO_PCI(eth_dev->device), hw,
+ &dev_flags);
if (ret)
return ret;
}
+ hw->port_id = eth_dev->data->port_id;
eth_dev->data->dev_flags = dev_flags;
/* reset device and negotiate default features */
/* Setup interrupt callback */
if (eth_dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC)
- rte_intr_callback_register(&pci_dev->intr_handle,
+ rte_intr_callback_register(eth_dev->intr_handle,
virtio_interrupt_handler, eth_dev);
return 0;
static int
eth_virtio_dev_uninit(struct rte_eth_dev *eth_dev)
{
- struct rte_pci_device *pci_dev;
- struct virtio_hw *hw = eth_dev->data->dev_private;
-
PMD_INIT_FUNC_TRACE();
if (rte_eal_process_type() == RTE_PROC_SECONDARY)
return -EPERM;
- if (hw->started == 1) {
- virtio_dev_stop(eth_dev);
- virtio_dev_close(eth_dev);
- }
- pci_dev = eth_dev->pci_dev;
+ virtio_dev_stop(eth_dev);
+ virtio_dev_close(eth_dev);
eth_dev->dev_ops = NULL;
eth_dev->tx_pkt_burst = NULL;
/* reset interrupt callback */
if (eth_dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC)
- rte_intr_callback_unregister(&pci_dev->intr_handle,
+ rte_intr_callback_unregister(eth_dev->intr_handle,
virtio_interrupt_handler,
eth_dev);
- rte_eal_pci_unmap_device(pci_dev);
+ if (eth_dev->device)
+ rte_eal_pci_unmap_device(RTE_DEV_TO_PCI(eth_dev->device));
PMD_INIT_LOG(DEBUG, "dev_uninit completed");
.name = "net_virtio",
},
.id_table = pci_id_virtio_map,
- .drv_flags = RTE_PCI_DRV_DETACHABLE,
+ .drv_flags = 0,
.probe = rte_eth_dev_pci_probe,
.remove = rte_eth_dev_pci_remove,
},
}
if (dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC)
- if (vtpci_irq_config(hw, 0) == VIRTIO_MSI_NO_VECTOR) {
+ /* Enable vector (0) for Link State Intrerrupt */
+ if (VTPCI_OPS(hw)->set_config_irq(hw, 0) ==
+ VIRTIO_MSI_NO_VECTOR) {
PMD_DRV_LOG(ERR, "failed to set config vector");
return -EBUSY;
}
virtio_dev_start(struct rte_eth_dev *dev)
{
uint16_t nb_queues, i;
- struct virtio_hw *hw = dev->data->dev_private;
struct virtnet_rx *rxvq;
struct virtnet_tx *txvq __rte_unused;
+ struct virtio_hw *hw = dev->data->dev_private;
/* check if lsc interrupt feature is enabled */
if (dev->data->dev_conf.intr_conf.lsc) {
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->pci_dev->intr_handle) < 0) {
+ if (rte_intr_enable(dev->intr_handle) < 0) {
PMD_DRV_LOG(ERR, "interrupt enable failed");
return -EIO;
}
/* Initialize Link state */
virtio_dev_link_update(dev, 0);
- /* On restart after stop do not touch queues */
- if (hw->started)
- return 0;
-
- hw->started = 1;
-
/*Notify the backend
*Otherwise the tap backend might already stop its queue due to fullness.
*vhost backend will have no chance to be waked up
*/
- nb_queues = dev->data->nb_rx_queues;
- if (nb_queues > 1) {
+ nb_queues = RTE_MAX(dev->data->nb_rx_queues, dev->data->nb_tx_queues);
+ if (hw->max_queue_pairs > 1) {
if (virtio_set_multiple_queues(dev, nb_queues) != 0)
return -EINVAL;
}
PMD_INIT_LOG(DEBUG, "nb_queues=%d", nb_queues);
- for (i = 0; i < nb_queues; i++) {
+ for (i = 0; i < dev->data->nb_rx_queues; i++) {
rxvq = dev->data->rx_queues[i];
virtqueue_notify(rxvq->vq);
}
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)
- rte_intr_disable(&dev->pci_dev->intr_handle);
+ if (intr_conf->lsc || intr_conf->rxq)
+ rte_intr_disable(dev->intr_handle);
memset(&link, 0, sizeof(link));
virtio_dev_atomic_write_link_status(dev, &link);
uint64_t tso_mask;
struct virtio_hw *hw = dev->data->dev_private;
- if (dev->pci_dev)
- dev_info->driver_name = dev->driver->pci_drv.driver.name;
- else
- dev_info->driver_name = "virtio_user PMD";
+ 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->max_tx_queues =
RTE_PMD_EXPORT_NAME(net_virtio, __COUNTER__);
RTE_PMD_REGISTER_PCI_TABLE(net_virtio, pci_id_virtio_map);
+RTE_PMD_REGISTER_KMOD_DEP(net_virtio, "* igb_uio | uio_pci_generic | vfio");