#include <errno.h>
#include <unistd.h>
-#include <rte_ethdev.h>
+#include <rte_ethdev_driver.h>
#include <rte_ethdev_pci.h>
#include <rte_memcpy.h>
#include <rte_string_fns.h>
#include <rte_memzone.h>
#include <rte_malloc.h>
-#include <rte_atomic.h>
#include <rte_branch_prediction.h>
#include <rte_pci.h>
#include <rte_bus_pci.h>
#include <rte_ether.h>
+#include <rte_ip.h>
+#include <rte_arp.h>
#include <rte_common.h>
#include <rte_errno.h>
#include <rte_cpuflags.h>
#include <rte_memory.h>
#include <rte_eal.h>
#include <rte_dev.h>
+#include <rte_cycles.h>
+#include <rte_kvargs.h>
#include "virtio_ethdev.h"
#include "virtio_pci.h"
struct ether_addr *mac_addr,
uint32_t index, uint32_t vmdq);
static void virtio_mac_addr_remove(struct rte_eth_dev *dev, uint32_t index);
-static void virtio_mac_addr_set(struct rte_eth_dev *dev,
+static int virtio_mac_addr_set(struct rte_eth_dev *dev,
struct ether_addr *mac_addr);
static int virtio_intr_enable(struct rte_eth_dev *dev);
uint8_t stat_idx,
uint8_t is_rx);
+int virtio_logtype_init;
+int virtio_logtype_driver;
+
+static void virtio_notify_peers(struct rte_eth_dev *dev);
+static void virtio_ack_link_announce(struct rte_eth_dev *dev);
+
/*
* The set of PCI devices this driver supports
*/
struct virtio_hw_internal virtio_hw_internal[RTE_MAX_ETHPORTS];
+static struct virtio_pmd_ctrl *
+virtio_pq_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl,
+ int *dlen, int pkt_num)
+{
+ struct virtqueue *vq = cvq->vq;
+ int head;
+ struct vring_packed_desc *desc = vq->ring_packed.desc_packed;
+ struct virtio_pmd_ctrl *result;
+ bool avail_wrap_counter, used_wrap_counter;
+ uint16_t flags;
+ int sum = 0;
+ int k;
+
+ /*
+ * Format is enforced in qemu code:
+ * One TX packet for header;
+ * At least one TX packet per argument;
+ * One RX packet for ACK.
+ */
+ head = vq->vq_avail_idx;
+ avail_wrap_counter = vq->avail_wrap_counter;
+ used_wrap_counter = vq->used_wrap_counter;
+ desc[head].flags = VRING_DESC_F_NEXT;
+ desc[head].addr = cvq->virtio_net_hdr_mem;
+ desc[head].len = sizeof(struct virtio_net_ctrl_hdr);
+ vq->vq_free_cnt--;
+ if (++vq->vq_avail_idx >= vq->vq_nentries) {
+ vq->vq_avail_idx -= vq->vq_nentries;
+ vq->avail_wrap_counter ^= 1;
+ }
+
+ for (k = 0; k < pkt_num; k++) {
+ desc[vq->vq_avail_idx].addr = cvq->virtio_net_hdr_mem
+ + sizeof(struct virtio_net_ctrl_hdr)
+ + sizeof(ctrl->status) + sizeof(uint8_t) * sum;
+ desc[vq->vq_avail_idx].len = dlen[k];
+ flags = VRING_DESC_F_NEXT;
+ sum += dlen[k];
+ vq->vq_free_cnt--;
+ flags |= VRING_DESC_F_AVAIL(vq->avail_wrap_counter) |
+ VRING_DESC_F_USED(!vq->avail_wrap_counter);
+ desc[vq->vq_avail_idx].flags = flags;
+ rte_smp_wmb();
+ vq->vq_free_cnt--;
+ if (++vq->vq_avail_idx >= vq->vq_nentries) {
+ vq->vq_avail_idx -= vq->vq_nentries;
+ vq->avail_wrap_counter ^= 1;
+ }
+ }
+
+
+ desc[vq->vq_avail_idx].addr = cvq->virtio_net_hdr_mem
+ + sizeof(struct virtio_net_ctrl_hdr);
+ desc[vq->vq_avail_idx].len = sizeof(ctrl->status);
+ flags = VRING_DESC_F_WRITE;
+ flags |= VRING_DESC_F_AVAIL(vq->avail_wrap_counter) |
+ VRING_DESC_F_USED(!vq->avail_wrap_counter);
+ desc[vq->vq_avail_idx].flags = flags;
+ flags = VRING_DESC_F_NEXT;
+ flags |= VRING_DESC_F_AVAIL(avail_wrap_counter) |
+ VRING_DESC_F_USED(!avail_wrap_counter);
+ desc[head].flags = flags;
+ rte_smp_wmb();
+
+ vq->vq_free_cnt--;
+ if (++vq->vq_avail_idx >= vq->vq_nentries) {
+ vq->vq_avail_idx -= vq->vq_nentries;
+ vq->avail_wrap_counter ^= 1;
+ }
+
+ virtqueue_notify(vq);
+
+ /* wait for used descriptors in virtqueue */
+ do {
+ rte_rmb();
+ usleep(100);
+ } while (!__desc_is_used(&desc[head], used_wrap_counter));
+
+ /* now get used descriptors */
+ while (desc_is_used(&desc[vq->vq_used_cons_idx], vq)) {
+ vq->vq_free_cnt++;
+ if (++vq->vq_used_cons_idx >= vq->vq_nentries) {
+ vq->vq_used_cons_idx -= vq->vq_nentries;
+ vq->used_wrap_counter ^= 1;
+ }
+ }
+
+ result = cvq->virtio_net_hdr_mz->addr;
+ return result;
+}
+
static int
virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl,
int *dlen, int pkt_num)
PMD_INIT_LOG(ERR, "Control queue is not supported.");
return -1;
}
+
+ rte_spinlock_lock(&cvq->lock);
vq = cvq->vq;
head = vq->vq_desc_head_idx;
"vq->hw->cvq = %p vq = %p",
vq->vq_desc_head_idx, status, vq->hw->cvq, vq);
- if ((vq->vq_free_cnt < ((uint32_t)pkt_num + 2)) || (pkt_num < 1))
+ if (vq->vq_free_cnt < pkt_num + 2 || pkt_num < 1) {
+ rte_spinlock_unlock(&cvq->lock);
return -1;
+ }
memcpy(cvq->virtio_net_hdr_mz->addr, ctrl,
sizeof(struct virtio_pmd_ctrl));
+ if (vtpci_packed_queue(vq->hw)) {
+ result = virtio_pq_send_command(cvq, ctrl, dlen, pkt_num);
+ goto out_unlock;
+ }
+
/*
* Format is enforced in qemu code:
* One TX packet for header;
result = cvq->virtio_net_hdr_mz->addr;
+out_unlock:
+ rte_spinlock_unlock(&cvq->lock);
return result->status;
}
/* do nothing */
}
-static int
-virtio_get_queue_type(struct virtio_hw *hw, uint16_t vtpci_queue_idx)
-{
- if (vtpci_queue_idx == hw->max_queue_pairs * 2)
- return VTNET_CQ;
- else if (vtpci_queue_idx % 2 == 0)
- return VTNET_RQ;
- else
- return VTNET_TQ;
-}
-
static uint16_t
virtio_get_nr_vq(struct virtio_hw *hw)
{
PMD_INIT_FUNC_TRACE();
- /*
- * Reinitialise since virtio port might have been stopped and restarted
- */
memset(ring_mem, 0, vq->vq_ring_size);
- vring_init(vr, size, ring_mem, VIRTIO_PCI_VRING_ALIGN);
+
vq->vq_used_cons_idx = 0;
vq->vq_desc_head_idx = 0;
vq->vq_avail_idx = 0;
vq->vq_desc_tail_idx = (uint16_t)(vq->vq_nentries - 1);
vq->vq_free_cnt = vq->vq_nentries;
memset(vq->vq_descx, 0, sizeof(struct vq_desc_extra) * vq->vq_nentries);
-
- vring_desc_init(vr->desc, size);
-
+ if (vtpci_packed_queue(vq->hw)) {
+ vring_init_packed(&vq->ring_packed, ring_mem,
+ VIRTIO_PCI_VRING_ALIGN, size);
+ vring_desc_init_packed(vq, size);
+ } else {
+ vring_init_split(vr, ring_mem, VIRTIO_PCI_VRING_ALIGN, size);
+ vring_desc_init_split(vr->desc, size);
+ }
/*
* Disable device(host) interrupting guest
*/
void *sw_ring = NULL;
int queue_type = virtio_get_queue_type(hw, vtpci_queue_idx);
int ret;
+ int numa_node = dev->device->numa_node;
- PMD_INIT_LOG(DEBUG, "setting up queue: %u", vtpci_queue_idx);
+ PMD_INIT_LOG(INFO, "setting up queue: %u on NUMA node %d",
+ vtpci_queue_idx, numa_node);
/*
* Read the virtqueue size from the Queue Size field
}
vq = rte_zmalloc_socket(vq_name, size, RTE_CACHE_LINE_SIZE,
- SOCKET_ID_ANY);
+ numa_node);
if (vq == NULL) {
PMD_INIT_LOG(ERR, "can not allocate vq");
return -ENOMEM;
vq->hw = hw;
vq->vq_queue_index = vtpci_queue_idx;
vq->vq_nentries = vq_size;
+ vq->event_flags_shadow = 0;
+ if (vtpci_packed_queue(hw)) {
+ vq->avail_wrap_counter = 1;
+ vq->used_wrap_counter = 1;
+ vq->avail_used_flags =
+ VRING_DESC_F_AVAIL(vq->avail_wrap_counter) |
+ VRING_DESC_F_USED(!vq->avail_wrap_counter);
+ }
/*
* Reserve a memzone for vring elements
*/
- size = vring_size(vq_size, VIRTIO_PCI_VRING_ALIGN);
+ size = vring_size(hw, vq_size, VIRTIO_PCI_VRING_ALIGN);
vq->vq_ring_size = RTE_ALIGN_CEIL(size, VIRTIO_PCI_VRING_ALIGN);
PMD_INIT_LOG(DEBUG, "vring_size: %d, rounded_vring_size: %d",
size, vq->vq_ring_size);
mz = rte_memzone_reserve_aligned(vq_name, vq->vq_ring_size,
- SOCKET_ID_ANY,
- 0, VIRTIO_PCI_VRING_ALIGN);
+ numa_node, RTE_MEMZONE_IOVA_CONTIG,
+ VIRTIO_PCI_VRING_ALIGN);
if (mz == NULL) {
if (rte_errno == EEXIST)
mz = rte_memzone_lookup(vq_name);
snprintf(vq_hdr_name, sizeof(vq_hdr_name), "port%d_vq%d_hdr",
dev->data->port_id, vtpci_queue_idx);
hdr_mz = rte_memzone_reserve_aligned(vq_hdr_name, sz_hdr_mz,
- SOCKET_ID_ANY, 0,
- RTE_CACHE_LINE_SIZE);
+ numa_node, RTE_MEMZONE_IOVA_CONTIG,
+ RTE_CACHE_LINE_SIZE);
if (hdr_mz == NULL) {
if (rte_errno == EEXIST)
hdr_mz = rte_memzone_lookup(vq_hdr_name);
sizeof(vq->sw_ring[0]);
sw_ring = rte_zmalloc_socket("sw_ring", sz_sw,
- RTE_CACHE_LINE_SIZE, SOCKET_ID_ANY);
+ RTE_CACHE_LINE_SIZE, numa_node);
if (!sw_ring) {
PMD_INIT_LOG(ERR, "can not allocate RX soft ring");
ret = -ENOMEM;
memset(txr, 0, vq_size * sizeof(*txr));
for (i = 0; i < vq_size; i++) {
struct vring_desc *start_dp = txr[i].tx_indir;
-
- vring_desc_init(start_dp, RTE_DIM(txr[i].tx_indir));
+ struct vring_packed_desc *start_dp_packed =
+ txr[i].tx_indir_pq;
/* first indirect descriptor is always the tx header */
- start_dp->addr = txvq->virtio_net_hdr_mem
- + i * sizeof(*txr)
- + offsetof(struct virtio_tx_region, tx_hdr);
-
- start_dp->len = hw->vtnet_hdr_size;
- start_dp->flags = VRING_DESC_F_NEXT;
+ if (vtpci_packed_queue(hw)) {
+ start_dp_packed->addr = txvq->virtio_net_hdr_mem
+ + i * sizeof(*txr)
+ + offsetof(struct virtio_tx_region,
+ tx_hdr);
+ start_dp_packed->len = hw->vtnet_hdr_size;
+ } else {
+ vring_desc_init_split(start_dp,
+ RTE_DIM(txr[i].tx_indir));
+ start_dp->addr = txvq->virtio_net_hdr_mem
+ + i * sizeof(*txr)
+ + offsetof(struct virtio_tx_region,
+ tx_hdr);
+ start_dp->len = hw->vtnet_hdr_size;
+ start_dp->flags = VRING_DESC_F_NEXT;
+ }
}
}
PMD_INIT_LOG(DEBUG, "virtio_dev_close");
+ if (!hw->opened)
+ return;
+ hw->opened = false;
+
/* reset the NIC */
if (dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC)
VTPCI_OPS(hw)->set_config_irq(hw, VIRTIO_MSI_NO_VECTOR);
.mac_addr_set = virtio_mac_addr_set,
};
-static inline int
-virtio_dev_atomic_read_link_status(struct rte_eth_dev *dev,
- struct rte_eth_link *link)
-{
- struct rte_eth_link *dst = link;
- struct rte_eth_link *src = &(dev->data->dev_link);
-
- if (rte_atomic64_cmpset((uint64_t *)dst, *(uint64_t *)dst,
- *(uint64_t *)src) == 0)
- return -1;
-
- return 0;
-}
-
-/**
- * Atomically writes the link status information into global
- * structure rte_eth_dev.
- *
- * @param dev
- * - Pointer to the structure rte_eth_dev to read from.
- * - Pointer to the buffer to be saved with the link status.
- *
- * @return
- * - On success, zero.
- * - On failure, negative value.
- */
-static inline int
-virtio_dev_atomic_write_link_status(struct rte_eth_dev *dev,
- struct rte_eth_link *link)
-{
- struct rte_eth_link *dst = &(dev->data->dev_link);
- struct rte_eth_link *src = link;
-
- if (rte_atomic64_cmpset((uint64_t *)dst, *(uint64_t *)dst,
- *(uint64_t *)src) == 0)
- return -1;
-
- return 0;
-}
-
static void
virtio_update_stats(struct rte_eth_dev *dev, struct rte_eth_stats *stats)
{
/* Note: limit checked in rte_eth_xstats_names() */
for (i = 0; i < dev->data->nb_rx_queues; i++) {
- struct virtqueue *rxvq = dev->data->rx_queues[i];
+ struct virtnet_rx *rxvq = dev->data->rx_queues[i];
if (rxvq == NULL)
continue;
for (t = 0; t < VIRTIO_NB_RXQ_XSTATS; t++) {
}
for (i = 0; i < dev->data->nb_tx_queues; i++) {
- struct virtqueue *txvq = dev->data->tx_queues[i];
+ struct virtnet_tx *txvq = dev->data->tx_queues[i];
if (txvq == NULL)
continue;
for (t = 0; t < VIRTIO_NB_TXQ_XSTATS; t++) {
virtio_mac_table_set(hw, uc, mc);
}
-static void
+static int
virtio_mac_addr_set(struct rte_eth_dev *dev, struct ether_addr *mac_addr)
{
struct virtio_hw *hw = dev->data->dev_private;
ctrl.hdr.cmd = VIRTIO_NET_CTRL_MAC_ADDR_SET;
memcpy(ctrl.data, mac_addr, ETHER_ADDR_LEN);
- virtio_send_command(hw->cvq, &ctrl, &len, 1);
- } else if (vtpci_with_feature(hw, VIRTIO_NET_F_MAC))
- virtio_set_hwaddr(hw);
+ return virtio_send_command(hw->cvq, &ctrl, &len, 1);
+ }
+
+ if (!vtpci_with_feature(hw, VIRTIO_NET_F_MAC))
+ return -ENOTSUP;
+
+ virtio_set_hwaddr(hw);
+ return 0;
}
static int
return 0;
}
+int
+virtio_dev_pause(struct rte_eth_dev *dev)
+{
+ struct virtio_hw *hw = dev->data->dev_private;
+
+ rte_spinlock_lock(&hw->state_lock);
+
+ if (hw->started == 0) {
+ /* Device is just stopped. */
+ rte_spinlock_unlock(&hw->state_lock);
+ return -1;
+ }
+ hw->started = 0;
+ /*
+ * Prevent the worker threads from touching queues to avoid contention,
+ * 1 ms should be enough for the ongoing Tx function to finish.
+ */
+ rte_delay_ms(1);
+ return 0;
+}
+
/*
- * Process Virtio Config changed interrupt and call the callback
- * if link state changed.
+ * Recover hw state to let the worker threads continue.
+ */
+void
+virtio_dev_resume(struct rte_eth_dev *dev)
+{
+ struct virtio_hw *hw = dev->data->dev_private;
+
+ hw->started = 1;
+ rte_spinlock_unlock(&hw->state_lock);
+}
+
+/*
+ * Should be called only after device is paused.
+ */
+int
+virtio_inject_pkts(struct rte_eth_dev *dev, struct rte_mbuf **tx_pkts,
+ int nb_pkts)
+{
+ struct virtio_hw *hw = dev->data->dev_private;
+ struct virtnet_tx *txvq = dev->data->tx_queues[0];
+ int ret;
+
+ hw->inject_pkts = tx_pkts;
+ ret = dev->tx_pkt_burst(txvq, tx_pkts, nb_pkts);
+ hw->inject_pkts = NULL;
+
+ return ret;
+}
+
+static void
+virtio_notify_peers(struct rte_eth_dev *dev)
+{
+ struct virtio_hw *hw = dev->data->dev_private;
+ struct virtnet_rx *rxvq;
+ struct rte_mbuf *rarp_mbuf;
+
+ if (!dev->data->rx_queues)
+ return;
+
+ rxvq = dev->data->rx_queues[0];
+ if (!rxvq)
+ return;
+
+ rarp_mbuf = rte_net_make_rarp_packet(rxvq->mpool,
+ (struct ether_addr *)hw->mac_addr);
+ if (rarp_mbuf == NULL) {
+ PMD_DRV_LOG(ERR, "failed to make RARP packet.");
+ return;
+ }
+
+ /* If virtio port just stopped, no need to send RARP */
+ if (virtio_dev_pause(dev) < 0) {
+ rte_pktmbuf_free(rarp_mbuf);
+ return;
+ }
+
+ virtio_inject_pkts(dev, &rarp_mbuf, 1);
+ virtio_dev_resume(dev);
+}
+
+static void
+virtio_ack_link_announce(struct rte_eth_dev *dev)
+{
+ struct virtio_hw *hw = dev->data->dev_private;
+ struct virtio_pmd_ctrl ctrl;
+
+ ctrl.hdr.class = VIRTIO_NET_CTRL_ANNOUNCE;
+ ctrl.hdr.cmd = VIRTIO_NET_CTRL_ANNOUNCE_ACK;
+
+ virtio_send_command(hw->cvq, &ctrl, NULL, 0);
+}
+
+/*
+ * Process virtio config changed interrupt. Call the callback
+ * if link state changed, generate gratuitous RARP packet if
+ * the status indicates an ANNOUNCE.
*/
void
virtio_interrupt_handler(void *param)
struct rte_eth_dev *dev = param;
struct virtio_hw *hw = dev->data->dev_private;
uint8_t isr;
+ uint16_t status;
/* Read interrupt status which clears interrupt */
isr = vtpci_isr(hw);
if (virtio_dev_link_update(dev, 0) == 0)
_rte_eth_dev_callback_process(dev,
RTE_ETH_EVENT_INTR_LSC,
- NULL, NULL);
- }
+ NULL);
+ if (vtpci_with_feature(hw, VIRTIO_NET_F_STATUS)) {
+ vtpci_read_dev_config(hw,
+ offsetof(struct virtio_net_config, status),
+ &status, sizeof(status));
+ if (status & VIRTIO_NET_S_ANNOUNCE) {
+ virtio_notify_peers(dev);
+ if (hw->cvq)
+ virtio_ack_link_announce(dev);
+ }
+ }
+ }
}
/* set rx and tx handlers according to what is supported */
{
struct virtio_hw *hw = eth_dev->data->dev_private;
- if (hw->use_simple_rx) {
- PMD_INIT_LOG(INFO, "virtio: using simple Rx path on port %u",
- eth_dev->data->port_id);
- eth_dev->rx_pkt_burst = virtio_recv_pkts_vec;
- } else if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) {
+ if (vtpci_packed_queue(hw)) {
PMD_INIT_LOG(INFO,
- "virtio: using mergeable buffer Rx path on port %u",
+ "virtio: using packed ring standard Tx path on port %u",
eth_dev->data->port_id);
- eth_dev->rx_pkt_burst = &virtio_recv_mergeable_pkts;
+ eth_dev->tx_pkt_burst = virtio_xmit_pkts_packed;
} else {
- PMD_INIT_LOG(INFO, "virtio: using standard Rx path on port %u",
- eth_dev->data->port_id);
- eth_dev->rx_pkt_burst = &virtio_recv_pkts;
+ if (hw->use_inorder_tx) {
+ PMD_INIT_LOG(INFO, "virtio: using inorder Tx path on port %u",
+ eth_dev->data->port_id);
+ eth_dev->tx_pkt_burst = virtio_xmit_pkts_inorder;
+ } else {
+ PMD_INIT_LOG(INFO, "virtio: using standard Tx path on port %u",
+ eth_dev->data->port_id);
+ eth_dev->tx_pkt_burst = virtio_xmit_pkts;
+ }
}
- if (hw->use_simple_tx) {
- PMD_INIT_LOG(INFO, "virtio: using simple Tx path on port %u",
- eth_dev->data->port_id);
- eth_dev->tx_pkt_burst = virtio_xmit_pkts_simple;
+ if (vtpci_packed_queue(hw)) {
+ if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) {
+ PMD_INIT_LOG(INFO,
+ "virtio: using packed ring mergeable buffer Rx path on port %u",
+ eth_dev->data->port_id);
+ eth_dev->rx_pkt_burst =
+ &virtio_recv_mergeable_pkts_packed;
+ } else {
+ PMD_INIT_LOG(INFO,
+ "virtio: using packed ring standard Rx path on port %u",
+ eth_dev->data->port_id);
+ eth_dev->rx_pkt_burst = &virtio_recv_pkts_packed;
+ }
} else {
- PMD_INIT_LOG(INFO, "virtio: using standard Tx path on port %u",
- eth_dev->data->port_id);
- eth_dev->tx_pkt_burst = virtio_xmit_pkts;
+ if (hw->use_simple_rx) {
+ PMD_INIT_LOG(INFO, "virtio: using simple Rx path on port %u",
+ eth_dev->data->port_id);
+ eth_dev->rx_pkt_burst = virtio_recv_pkts_vec;
+ } else if (hw->use_inorder_rx) {
+ PMD_INIT_LOG(INFO,
+ "virtio: using inorder Rx path on port %u",
+ eth_dev->data->port_id);
+ eth_dev->rx_pkt_burst = &virtio_recv_pkts_inorder;
+ } else if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) {
+ PMD_INIT_LOG(INFO,
+ "virtio: using mergeable buffer Rx path on port %u",
+ eth_dev->data->port_id);
+ eth_dev->rx_pkt_burst = &virtio_recv_mergeable_pkts;
+ } else {
+ PMD_INIT_LOG(INFO, "virtio: using standard Rx path on port %u",
+ eth_dev->data->port_id);
+ eth_dev->rx_pkt_burst = &virtio_recv_pkts;
+ }
}
+
}
/* Only support 1:1 queue/interrupt mapping so far.
/* Reset the device although not necessary at startup */
vtpci_reset(hw);
+ if (hw->vqs) {
+ virtio_dev_free_mbufs(eth_dev);
+ virtio_free_queues(hw);
+ }
+
/* Tell the host we've noticed this device. */
vtpci_set_status(hw, VIRTIO_CONFIG_STATUS_ACK);
if (virtio_negotiate_features(hw, req_features) < 0)
return -1;
+ hw->weak_barriers = !vtpci_with_feature(hw, VIRTIO_F_ORDER_PLATFORM);
+
if (!hw->virtio_user_dev) {
pci_dev = RTE_ETH_DEV_TO_PCI(eth_dev);
rte_eth_copy_pci_info(eth_dev, pci_dev);
/* Setting up rx_header size for the device */
if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF) ||
- vtpci_with_feature(hw, VIRTIO_F_VERSION_1))
+ vtpci_with_feature(hw, VIRTIO_F_VERSION_1) ||
+ vtpci_with_feature(hw, VIRTIO_F_RING_PACKED))
hw->vtnet_hdr_size = sizeof(struct virtio_net_hdr_mrg_rxbuf);
else
hw->vtnet_hdr_size = sizeof(struct virtio_net_hdr);
} else {
PMD_INIT_LOG(DEBUG, "config->max_virtqueue_pairs=1");
hw->max_queue_pairs = 1;
+ hw->max_mtu = VIRTIO_MAX_RX_PKTLEN - ETHER_HDR_LEN -
+ VLAN_TAG_LEN - hw->vtnet_hdr_size;
}
ret = virtio_alloc_queues(eth_dev);
if (ret < 0)
goto out;
- /* Setup interrupt callback */
- if (eth_dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC)
- rte_intr_callback_register(eth_dev->intr_handle,
- virtio_interrupt_handler, eth_dev);
-
return 0;
out:
PMD_INIT_FUNC_TRACE();
if (rte_eal_process_type() == RTE_PROC_SECONDARY)
- return -EPERM;
+ return 0;
virtio_dev_stop(eth_dev);
virtio_dev_close(eth_dev);
eth_dev->tx_pkt_burst = NULL;
eth_dev->rx_pkt_burst = NULL;
- rte_free(eth_dev->data->mac_addrs);
- eth_dev->data->mac_addrs = NULL;
-
- /* reset interrupt callback */
- if (eth_dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC)
- rte_intr_callback_unregister(eth_dev->intr_handle,
- virtio_interrupt_handler,
- eth_dev);
if (eth_dev->device)
rte_pci_unmap_device(RTE_ETH_DEV_TO_PCI(eth_dev));
return 0;
}
+static int vdpa_check_handler(__rte_unused const char *key,
+ const char *value, __rte_unused void *opaque)
+{
+ if (strcmp(value, "1"))
+ return -1;
+
+ return 0;
+}
+
+static int
+vdpa_mode_selected(struct rte_devargs *devargs)
+{
+ struct rte_kvargs *kvlist;
+ const char *key = "vdpa";
+ int ret = 0;
+
+ if (devargs == NULL)
+ return 0;
+
+ kvlist = rte_kvargs_parse(devargs->args, NULL);
+ if (kvlist == NULL)
+ return 0;
+
+ if (!rte_kvargs_count(kvlist, key))
+ goto exit;
+
+ /* vdpa mode selected when there's a key-value pair: vdpa=1 */
+ if (rte_kvargs_process(kvlist, key,
+ vdpa_check_handler, NULL) < 0) {
+ goto exit;
+ }
+ ret = 1;
+
+exit:
+ rte_kvargs_free(kvlist);
+ return ret;
+}
+
static int eth_virtio_pci_probe(struct rte_pci_driver *pci_drv __rte_unused,
struct rte_pci_device *pci_dev)
{
+ if (rte_eal_iopl_init() != 0) {
+ PMD_INIT_LOG(ERR, "IOPL call failed - cannot use virtio PMD");
+ return 1;
+ }
+
+ /* virtio pmd skips probe if device needs to work in vdpa mode */
+ if (vdpa_mode_selected(pci_dev->device.devargs))
+ return 1;
+
return rte_eth_dev_pci_generic_probe(pci_dev, sizeof(struct virtio_hw),
eth_virtio_dev_init);
}
.remove = eth_virtio_pci_remove,
};
-RTE_INIT(rte_virtio_pmd_init);
-static void
-rte_virtio_pmd_init(void)
+RTE_INIT(rte_virtio_pmd_init)
{
- if (rte_eal_iopl_init() != 0) {
- PMD_INIT_LOG(ERR, "IOPL call failed - cannot use virtio PMD");
- return;
- }
-
+ rte_eal_iopl_init();
rte_pci_register(&rte_virtio_pmd);
}
+static bool
+rx_offload_enabled(struct virtio_hw *hw)
+{
+ return vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_CSUM) ||
+ vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_TSO4) ||
+ vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_TSO6);
+}
+
+static bool
+tx_offload_enabled(struct virtio_hw *hw)
+{
+ return vtpci_with_feature(hw, VIRTIO_NET_F_CSUM) ||
+ vtpci_with_feature(hw, VIRTIO_NET_F_HOST_TSO4) ||
+ vtpci_with_feature(hw, VIRTIO_NET_F_HOST_TSO6);
+}
+
/*
* Configure virtio device
* It returns 0 on success.
virtio_dev_configure(struct rte_eth_dev *dev)
{
const struct rte_eth_rxmode *rxmode = &dev->data->dev_conf.rxmode;
+ const struct rte_eth_txmode *txmode = &dev->data->dev_conf.txmode;
struct virtio_hw *hw = dev->data->dev_private;
+ uint64_t rx_offloads = rxmode->offloads;
+ uint64_t tx_offloads = txmode->offloads;
uint64_t req_features;
int ret;
return ret;
}
- /* The name hw_ip_checksum is a bit confusing since it can be
- * set by the application to request L3 and/or L4 checksums. In
- * case of virtio, only L4 checksum is supported.
- */
- if (rxmode->hw_ip_checksum)
+ if (rx_offloads & (DEV_RX_OFFLOAD_UDP_CKSUM |
+ DEV_RX_OFFLOAD_TCP_CKSUM))
req_features |= (1ULL << VIRTIO_NET_F_GUEST_CSUM);
- if (rxmode->enable_lro)
+ if (rx_offloads & DEV_RX_OFFLOAD_TCP_LRO)
req_features |=
(1ULL << VIRTIO_NET_F_GUEST_TSO4) |
(1ULL << VIRTIO_NET_F_GUEST_TSO6);
+ if (tx_offloads & (DEV_TX_OFFLOAD_UDP_CKSUM |
+ DEV_TX_OFFLOAD_TCP_CKSUM))
+ req_features |= (1ULL << VIRTIO_NET_F_CSUM);
+
+ if (tx_offloads & DEV_TX_OFFLOAD_TCP_TSO)
+ req_features |=
+ (1ULL << VIRTIO_NET_F_HOST_TSO4) |
+ (1ULL << VIRTIO_NET_F_HOST_TSO6);
+
/* if request features changed, reinit the device */
if (req_features != hw->req_guest_features) {
ret = virtio_init_device(dev, req_features);
return ret;
}
- if (rxmode->hw_ip_checksum &&
+ if ((rx_offloads & (DEV_RX_OFFLOAD_UDP_CKSUM |
+ DEV_RX_OFFLOAD_TCP_CKSUM)) &&
!vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_CSUM)) {
PMD_DRV_LOG(ERR,
"rx checksum not available on this host");
return -ENOTSUP;
}
- if (rxmode->enable_lro &&
+ if ((rx_offloads & DEV_RX_OFFLOAD_TCP_LRO) &&
(!vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_TSO4) ||
- !vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_TSO4))) {
+ !vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_TSO6))) {
PMD_DRV_LOG(ERR,
"Large Receive Offload not available on this host");
return -ENOTSUP;
if (vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VQ))
virtio_dev_cq_start(dev);
- hw->vlan_strip = rxmode->hw_vlan_strip;
+ if (rx_offloads & DEV_RX_OFFLOAD_VLAN_STRIP)
+ hw->vlan_strip = 1;
- if (rxmode->hw_vlan_filter
+ if ((rx_offloads & DEV_RX_OFFLOAD_VLAN_FILTER)
&& !vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VLAN)) {
PMD_DRV_LOG(ERR,
"vlan filtering not available on this host");
return -ENOTSUP;
}
+ hw->has_tx_offload = tx_offload_enabled(hw);
+ hw->has_rx_offload = rx_offload_enabled(hw);
+
if (dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC)
/* Enable vector (0) for Link State Intrerrupt */
if (VTPCI_OPS(hw)->set_config_irq(hw, 0) ==
return -EBUSY;
}
+ rte_spinlock_init(&hw->state_lock);
+
hw->use_simple_rx = 1;
- hw->use_simple_tx = 1;
-#if defined RTE_ARCH_ARM64 || defined CONFIG_RTE_ARCH_ARM
+ if (vtpci_with_feature(hw, VIRTIO_F_IN_ORDER)) {
+ hw->use_inorder_tx = 1;
+ hw->use_inorder_rx = 1;
+ hw->use_simple_rx = 0;
+ }
+
+ if (vtpci_packed_queue(hw)) {
+ hw->use_simple_rx = 0;
+ hw->use_inorder_rx = 0;
+ hw->use_inorder_tx = 0;
+ }
+
+#if defined RTE_ARCH_ARM64 || defined RTE_ARCH_ARM
if (!rte_cpu_get_flag_enabled(RTE_CPUFLAG_NEON)) {
hw->use_simple_rx = 0;
- hw->use_simple_tx = 0;
}
#endif
if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) {
- hw->use_simple_rx = 0;
- hw->use_simple_tx = 0;
+ hw->use_simple_rx = 0;
}
- if (rxmode->hw_ip_checksum)
+ if (rx_offloads & (DEV_RX_OFFLOAD_UDP_CKSUM |
+ DEV_RX_OFFLOAD_TCP_CKSUM |
+ DEV_RX_OFFLOAD_TCP_LRO |
+ DEV_RX_OFFLOAD_VLAN_STRIP))
hw->use_simple_rx = 0;
+ hw->opened = true;
+
return 0;
}
dev->data->dev_conf.intr_conf.rxq) {
virtio_intr_disable(dev);
+ /* Setup interrupt callback */
+ if (dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC)
+ rte_intr_callback_register(dev->intr_handle,
+ virtio_interrupt_handler,
+ dev);
+
if (virtio_intr_enable(dev) < 0) {
PMD_DRV_LOG(ERR, "interrupt enable failed");
return -EIO;
for (i = 0; i < dev->data->nb_rx_queues; i++) {
rxvq = dev->data->rx_queues[i];
/* Flush the old packets */
- virtqueue_flush(rxvq->vq);
+ virtqueue_rxvq_flush(rxvq->vq);
virtqueue_notify(rxvq->vq);
}
}
set_rxtx_funcs(dev);
- hw->started = 1;
+ hw->started = true;
/* Initialize Link state */
virtio_dev_link_update(dev, 0);
static void virtio_dev_free_mbufs(struct rte_eth_dev *dev)
{
+ struct virtio_hw *hw = dev->data->dev_private;
+ uint16_t nr_vq = virtio_get_nr_vq(hw);
+ const char *type __rte_unused;
+ unsigned int i, mbuf_num = 0;
+ struct virtqueue *vq;
struct rte_mbuf *buf;
- int i, mbuf_num = 0;
-
- for (i = 0; i < dev->data->nb_rx_queues; i++) {
- struct virtnet_rx *rxvq = dev->data->rx_queues[i];
-
- PMD_INIT_LOG(DEBUG,
- "Before freeing rxq[%d] used and unused buf", i);
- VIRTQUEUE_DUMP(rxvq->vq);
+ int queue_type;
- PMD_INIT_LOG(DEBUG, "rx_queues[%d]=%p", i, rxvq);
- while ((buf = virtqueue_detatch_unused(rxvq->vq)) != NULL) {
- rte_pktmbuf_free(buf);
- mbuf_num++;
- }
+ if (hw->vqs == NULL)
+ return;
- PMD_INIT_LOG(DEBUG, "free %d mbufs", mbuf_num);
- PMD_INIT_LOG(DEBUG,
- "After freeing rxq[%d] used and unused buf", i);
- VIRTQUEUE_DUMP(rxvq->vq);
- }
+ for (i = 0; i < nr_vq; i++) {
+ vq = hw->vqs[i];
+ if (!vq)
+ continue;
- for (i = 0; i < dev->data->nb_tx_queues; i++) {
- struct virtnet_tx *txvq = dev->data->tx_queues[i];
+ queue_type = virtio_get_queue_type(hw, i);
+ if (queue_type == VTNET_RQ)
+ type = "rxq";
+ else if (queue_type == VTNET_TQ)
+ type = "txq";
+ else
+ continue;
PMD_INIT_LOG(DEBUG,
- "Before freeing txq[%d] used and unused bufs",
- i);
- VIRTQUEUE_DUMP(txvq->vq);
+ "Before freeing %s[%d] used and unused buf",
+ type, i);
+ VIRTQUEUE_DUMP(vq);
- mbuf_num = 0;
- while ((buf = virtqueue_detatch_unused(txvq->vq)) != NULL) {
+ while ((buf = virtqueue_detach_unused(vq)) != NULL) {
rte_pktmbuf_free(buf);
mbuf_num++;
}
- PMD_INIT_LOG(DEBUG, "free %d mbufs", mbuf_num);
PMD_INIT_LOG(DEBUG,
- "After freeing txq[%d] used and unused buf", i);
- VIRTQUEUE_DUMP(txvq->vq);
+ "After freeing %s[%d] used and unused buf",
+ type, i);
+ VIRTQUEUE_DUMP(vq);
}
+
+ PMD_INIT_LOG(DEBUG, "%d mbufs freed", mbuf_num);
}
/*
PMD_INIT_LOG(DEBUG, "stop");
- if (intr_conf->lsc || intr_conf->rxq)
+ rte_spinlock_lock(&hw->state_lock);
+ if (!hw->started)
+ goto out_unlock;
+ hw->started = false;
+
+ if (intr_conf->lsc || intr_conf->rxq) {
virtio_intr_disable(dev);
- hw->started = 0;
+ /* Reset interrupt callback */
+ if (dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC) {
+ rte_intr_callback_unregister(dev->intr_handle,
+ virtio_interrupt_handler,
+ dev);
+ }
+ }
+
memset(&link, 0, sizeof(link));
- virtio_dev_atomic_write_link_status(dev, &link);
+ rte_eth_linkstatus_set(dev, &link);
+out_unlock:
+ rte_spinlock_unlock(&hw->state_lock);
}
static int
virtio_dev_link_update(struct rte_eth_dev *dev, __rte_unused int wait_to_complete)
{
- struct rte_eth_link link, old;
+ struct rte_eth_link link;
uint16_t status;
struct virtio_hw *hw = dev->data->dev_private;
+
memset(&link, 0, sizeof(link));
- virtio_dev_atomic_read_link_status(dev, &link);
- old = link;
link.link_duplex = ETH_LINK_FULL_DUPLEX;
- link.link_speed = SPEED_10G;
+ link.link_speed = ETH_SPEED_NUM_10G;
+ link.link_autoneg = ETH_LINK_FIXED;
- if (hw->started == 0) {
+ if (!hw->started) {
link.link_status = ETH_LINK_DOWN;
} else if (vtpci_with_feature(hw, VIRTIO_NET_F_STATUS)) {
PMD_INIT_LOG(DEBUG, "Get link status from hw");
} else {
link.link_status = ETH_LINK_UP;
}
- virtio_dev_atomic_write_link_status(dev, &link);
- return (old.link_status == link.link_status) ? -1 : 0;
+ return rte_eth_linkstatus_set(dev, &link);
}
static int
{
const struct rte_eth_rxmode *rxmode = &dev->data->dev_conf.rxmode;
struct virtio_hw *hw = dev->data->dev_private;
+ uint64_t offloads = rxmode->offloads;
if (mask & ETH_VLAN_FILTER_MASK) {
- if (rxmode->hw_vlan_filter &&
+ if ((offloads & DEV_RX_OFFLOAD_VLAN_FILTER) &&
!vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VLAN)) {
PMD_DRV_LOG(NOTICE,
}
if (mask & ETH_VLAN_STRIP_MASK)
- hw->vlan_strip = rxmode->hw_vlan_strip;
+ hw->vlan_strip = !!(offloads & DEV_RX_OFFLOAD_VLAN_STRIP);
return 0;
}
dev_info->speed_capa = ETH_LINK_SPEED_10G; /* fake value */
- dev_info->pci_dev = dev->device ? RTE_ETH_DEV_TO_PCI(dev) : NULL;
dev_info->max_rx_queues =
RTE_MIN(hw->max_queue_pairs, VIRTIO_MAX_RX_QUEUES);
dev_info->max_tx_queues =
dev_info->min_rx_bufsize = VIRTIO_MIN_RX_BUFSIZE;
dev_info->max_rx_pktlen = VIRTIO_MAX_RX_PKTLEN;
dev_info->max_mac_addrs = VIRTIO_MAX_MAC_ADDRS;
- dev_info->default_txconf = (struct rte_eth_txconf) {
- .txq_flags = ETH_TXQ_FLAGS_NOOFFLOADS
- };
host_features = VTPCI_OPS(hw)->get_features(hw);
- dev_info->rx_offload_capa = 0;
+ dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP;
if (host_features & (1ULL << VIRTIO_NET_F_GUEST_CSUM)) {
dev_info->rx_offload_capa |=
DEV_RX_OFFLOAD_TCP_CKSUM |
DEV_RX_OFFLOAD_UDP_CKSUM;
}
+ if (host_features & (1ULL << VIRTIO_NET_F_CTRL_VLAN))
+ dev_info->rx_offload_capa |= DEV_RX_OFFLOAD_VLAN_FILTER;
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_MULTI_SEGS |
+ DEV_TX_OFFLOAD_VLAN_INSERT;
+ if (host_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)
+ if ((host_features & tso_mask) == tso_mask)
dev_info->tx_offload_capa |= DEV_TX_OFFLOAD_TCP_TSO;
}
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-pci");
+
+RTE_INIT(virtio_init_log)
+{
+ virtio_logtype_init = rte_log_register("pmd.net.virtio.init");
+ if (virtio_logtype_init >= 0)
+ rte_log_set_level(virtio_logtype_init, RTE_LOG_NOTICE);
+ virtio_logtype_driver = rte_log_register("pmd.net.virtio.driver");
+ if (virtio_logtype_driver >= 0)
+ rte_log_set_level(virtio_logtype_driver, RTE_LOG_NOTICE);
+}