/* Update device bond info */
static void
dpdk_ethdev_bond_info_update(struct vr_dpdk_ethdev *ethdev)
{
int i, slave_port_id;
int port_id = ethdev->ethdev_port_id;
struct rte_pci_addr *pci_addr;
struct ether_addr bond_mac, mac_addr;
struct ether_addr lacp_mac = { .addr_bytes = {0x01, 0x80, 0xc2, 0, 0, 0x02} };
if (rte_eth_bond_mode_get(port_id) == -1) {
ethdev->ethdev_nb_slaves = -1;
} else {
ethdev->ethdev_nb_slaves = rte_eth_bond_slaves_get(port_id,
ethdev->ethdev_slaves, sizeof(ethdev->ethdev_slaves));
memset(&mac_addr, 0, sizeof(bond_mac));
rte_eth_macaddr_get(port_id, &bond_mac);
RTE_LOG(INFO, VROUTER, " bond eth device %" PRIu8
" configured MAC " MAC_FORMAT "\n",
port_id, MAC_VALUE(bond_mac.addr_bytes));
/* log out and configure bond members */
for (i = 0; i < ethdev->ethdev_nb_slaves; i++) {
slave_port_id = ethdev->ethdev_slaves[i];
memset(&mac_addr, 0, sizeof(mac_addr));
rte_eth_macaddr_get(slave_port_id, &mac_addr);
pci_addr = &rte_eth_devices[slave_port_id].pci_dev->addr;
RTE_LOG(INFO, VROUTER, " bond member eth device %" PRIu8
" PCI " PCI_PRI_FMT " MAC " MAC_FORMAT "\n",
slave_port_id, pci_addr->domain, pci_addr->bus,
pci_addr->devid, pci_addr->function,
MAC_VALUE(mac_addr.addr_bytes));
/* try to add bond mac and LACP multicast MACs */
if (rte_eth_dev_mac_addr_add(slave_port_id, &bond_mac, 0) == 0
&& rte_eth_dev_mac_addr_add(slave_port_id, &lacp_mac, 0) == 0) {
/* disable the promisc mode enabled by default */
rte_eth_promiscuous_disable(ethdev->ethdev_port_id);
RTE_LOG(INFO, VROUTER, " bond member eth device %" PRIu8
" promisc mode disabled\n", slave_port_id);
} else {
RTE_LOG(INFO, VROUTER, " bond member eth device %" PRIu8
": unable to add MAC addresses\n", slave_port_id);
}
}
/* In LACP mode all the bond members are in the promisc mode
* by default (see bond_mode_8023ad_activate_slave()
* But we need also to put the bond interface in promisc to get
* the broadcasts. Seems to be a bug in bond_ethdev_rx_burst_8023ad()?
*/
rte_eth_promiscuous_enable(port_id);
}
}
int
rw_piot_mac_addr_add(rw_piot_api_handle_t api_handle, struct ether_addr *addr, uint32_t pool)
{
rw_piot_device_t *rw_piot_dev = RWPIOT_GET_DEVICE(api_handle);
ASSERT(RWPIOT_VALID_DEVICE(rw_piot_dev));
if (NULL == rw_piot_dev) {
RW_PIOT_LOG(RTE_LOG_ERR, "PIOT Could not find device by handle\n");
return -1;
}
return(rte_eth_dev_mac_addr_add(rw_piot_dev->rte_port_id, addr, pool));
}
/*
* This function registers mac along with a
* vlan tag to a VMDQ.
*/
static int
link_vmdq(struct virtio_net *dev)
{
int ret;
struct virtio_net_data_ll *dev_ll;
dev_ll = ll_root_used;
while (dev_ll != NULL) {
if ((dev != dev_ll->dev) && ether_addr_cmp(&dev->mac_address, &dev_ll->dev->mac_address)) {
RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") WARNING: This device is using an existing MAC address and has not been registered.\n", dev->device_fh);
return -1;
}
dev_ll = dev_ll->next;
}
/* vlan_tag currently uses the device_id. */
dev->vlan_tag = vlan_tags[dev->device_fh];
dev->vmdq_rx_q = dev->device_fh * (num_queues/num_devices);
/* Print out VMDQ registration info. */
RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") MAC_ADDRESS %02x:%02x:%02x:%02x:%02x:%02x and VLAN_TAG %d registered\n",
dev->device_fh,
dev->mac_address.addr_bytes[0], dev->mac_address.addr_bytes[1],
dev->mac_address.addr_bytes[2], dev->mac_address.addr_bytes[3],
dev->mac_address.addr_bytes[4], dev->mac_address.addr_bytes[5],
dev->vlan_tag);
/* Register the MAC address. */
ret = rte_eth_dev_mac_addr_add(ports[0], &dev->mac_address, (uint32_t)dev->device_fh);
if (ret) {
RTE_LOG(ERR, VHOST_DATA, "(%"PRIu64") Failed to add device MAC address to VMDQ\n",
dev->device_fh);
return -1;
}
/* Enable stripping of the vlan tag as we handle routing. */
rte_eth_dev_set_vlan_strip_on_queue(ports[0], dev->vmdq_rx_q, 1);
rte_compiler_barrier();
/* Set device as ready for RX. */
dev->ready = DEVICE_READY;
return 0;
}
/*
* Initialises a given port using global settings and with the rx buffers
* coming from the mbuf_pool passed as parameter
*/
static inline int
port_init(uint8_t port, struct rte_mempool *mbuf_pool)
{
struct rte_eth_dev_info dev_info;
struct rte_eth_rxconf *rxconf;
struct rte_eth_conf port_conf;
uint16_t rxRings, txRings;
const uint16_t rxRingSize = RTE_TEST_RX_DESC_DEFAULT, txRingSize = RTE_TEST_TX_DESC_DEFAULT;
int retval;
uint16_t q;
uint16_t queues_per_pool;
uint32_t max_nb_pools;
/*
* The max pool number from dev_info will be used to validate the pool
* number specified in cmd line
*/
rte_eth_dev_info_get(port, &dev_info);
max_nb_pools = (uint32_t)dev_info.max_vmdq_pools;
/*
* We allow to process part of VMDQ pools specified by num_pools in
* command line.
*/
if (num_pools > max_nb_pools) {
printf("num_pools %d >max_nb_pools %d\n",
num_pools, max_nb_pools);
return -1;
}
retval = get_eth_conf(&port_conf, max_nb_pools);
if (retval < 0)
return retval;
/*
* NIC queues are divided into pf queues and vmdq queues.
*/
/* There is assumption here all ports have the same configuration! */
num_pf_queues = dev_info.max_rx_queues - dev_info.vmdq_queue_num;
queues_per_pool = dev_info.vmdq_queue_num / dev_info.max_vmdq_pools;
num_vmdq_queues = num_pools * queues_per_pool;
num_queues = num_pf_queues + num_vmdq_queues;
vmdq_queue_base = dev_info.vmdq_queue_base;
vmdq_pool_base = dev_info.vmdq_pool_base;
printf("pf queue num: %u, configured vmdq pool num: %u,"
" each vmdq pool has %u queues\n",
num_pf_queues, num_pools, queues_per_pool);
printf("vmdq queue base: %d pool base %d\n",
vmdq_queue_base, vmdq_pool_base);
if (port >= rte_eth_dev_count())
return -1;
/*
* Though in this example, we only receive packets from the first queue
* of each pool and send packets through first rte_lcore_count() tx
* queues of vmdq queues, all queues including pf queues are setup.
* This is because VMDQ queues doesn't always start from zero, and the
* PMD layer doesn't support selectively initialising part of rx/tx
* queues.
*/
rxRings = (uint16_t)dev_info.max_rx_queues;
txRings = (uint16_t)dev_info.max_tx_queues;
retval = rte_eth_dev_configure(port, rxRings, txRings, &port_conf);
if (retval != 0)
return retval;
rte_eth_dev_info_get(port, &dev_info);
rxconf = &dev_info.default_rxconf;
rxconf->rx_drop_en = 1;
for (q = 0; q < rxRings; q++) {
retval = rte_eth_rx_queue_setup(port, q, rxRingSize,
rte_eth_dev_socket_id(port),
rxconf,
mbuf_pool);
if (retval < 0) {
printf("initialise rx queue %d failed\n", q);
return retval;
}
}
for (q = 0; q < txRings; q++) {
retval = rte_eth_tx_queue_setup(port, q, txRingSize,
rte_eth_dev_socket_id(port),
NULL);
if (retval < 0) {
printf("initialise tx queue %d failed\n", q);
return retval;
}
}
retval = rte_eth_dev_start(port);
if (retval < 0) {
printf("port %d start failed\n", port);
return retval;
}
rte_eth_macaddr_get(port, &vmdq_ports_eth_addr[port]);
printf("Port %u MAC: %02"PRIx8" %02"PRIx8" %02"PRIx8
" %02"PRIx8" %02"PRIx8" %02"PRIx8"\n",
(unsigned)port,
vmdq_ports_eth_addr[port].addr_bytes[0],
vmdq_ports_eth_addr[port].addr_bytes[1],
vmdq_ports_eth_addr[port].addr_bytes[2],
vmdq_ports_eth_addr[port].addr_bytes[3],
vmdq_ports_eth_addr[port].addr_bytes[4],
vmdq_ports_eth_addr[port].addr_bytes[5]);
/*
* Set mac for each pool.
* There is no default mac for the pools in i40.
* Removes this after i40e fixes this issue.
*/
for (q = 0; q < num_pools; q++) {
struct ether_addr mac;
mac = pool_addr_template;
mac.addr_bytes[4] = port;
mac.addr_bytes[5] = q;
printf("Port %u vmdq pool %u set mac %02x:%02x:%02x:%02x:%02x:%02x\n",
port, q,
mac.addr_bytes[0], mac.addr_bytes[1],
mac.addr_bytes[2], mac.addr_bytes[3],
mac.addr_bytes[4], mac.addr_bytes[5]);
retval = rte_eth_dev_mac_addr_add(port, &mac,
q + vmdq_pool_base);
if (retval) {
printf("mac addr add failed at pool %d\n", q);
return retval;
}
}
return 0;
}
/*
* Initialises a given port using global settings and with the rx buffers
* coming from the mbuf_pool passed as parameter
*/
static inline int
port_init(uint16_t port, struct rte_mempool *mbuf_pool)
{
struct rte_eth_dev_info dev_info;
struct rte_eth_conf port_conf = {0};
uint16_t rxRingSize = RTE_TEST_RX_DESC_DEFAULT;
uint16_t txRingSize = RTE_TEST_TX_DESC_DEFAULT;
int retval;
uint16_t q;
uint16_t queues_per_pool;
uint32_t max_nb_pools;
/*
* The max pool number from dev_info will be used to validate the pool
* number specified in cmd line
*/
rte_eth_dev_info_get(port, &dev_info);
max_nb_pools = (uint32_t)dev_info.max_vmdq_pools;
/*
* We allow to process part of VMDQ pools specified by num_pools in
* command line.
*/
if (num_pools > max_nb_pools) {
printf("num_pools %d >max_nb_pools %d\n",
num_pools, max_nb_pools);
return -1;
}
/*
* NIC queues are divided into pf queues and vmdq queues.
* There is assumption here all ports have the same configuration!
*/
vmdq_queue_base = dev_info.vmdq_queue_base;
vmdq_pool_base = dev_info.vmdq_pool_base;
printf("vmdq queue base: %d pool base %d\n",
vmdq_queue_base, vmdq_pool_base);
if (vmdq_pool_base == 0) {
num_vmdq_queues = dev_info.max_rx_queues;
num_queues = dev_info.max_rx_queues;
if (num_tcs != num_vmdq_queues / num_pools) {
printf("nb_tcs %d is invalid considering with"
" nb_pools %d, nb_tcs * nb_pools should = %d\n",
num_tcs, num_pools, num_vmdq_queues);
return -1;
}
} else {
queues_per_pool = dev_info.vmdq_queue_num /
dev_info.max_vmdq_pools;
if (num_tcs > queues_per_pool) {
printf("num_tcs %d > num of queues per pool %d\n",
num_tcs, queues_per_pool);
return -1;
}
num_vmdq_queues = num_pools * queues_per_pool;
num_queues = vmdq_queue_base + num_vmdq_queues;
printf("Configured vmdq pool num: %u,"
" each vmdq pool has %u queues\n",
num_pools, queues_per_pool);
}
if (port >= rte_eth_dev_count())
return -1;
retval = get_eth_conf(&port_conf);
if (retval < 0)
return retval;
/*
* Though in this example, all queues including pf queues are setup.
* This is because VMDQ queues doesn't always start from zero, and the
* PMD layer doesn't support selectively initialising part of rx/tx
* queues.
*/
retval = rte_eth_dev_configure(port, num_queues, num_queues, &port_conf);
if (retval != 0)
return retval;
retval = rte_eth_dev_adjust_nb_rx_tx_desc(port, &rxRingSize,
&txRingSize);
if (retval != 0)
return retval;
if (RTE_MAX(rxRingSize, txRingSize) >
RTE_MAX(RTE_TEST_RX_DESC_DEFAULT, RTE_TEST_TX_DESC_DEFAULT)) {
printf("Mbuf pool has an insufficient size for port %u.\n",
port);
return -1;
}
for (q = 0; q < num_queues; q++) {
retval = rte_eth_rx_queue_setup(port, q, rxRingSize,
rte_eth_dev_socket_id(port),
NULL,
mbuf_pool);
if (retval < 0) {
printf("initialize rx queue %d failed\n", q);
return retval;
}
}
for (q = 0; q < num_queues; q++) {
retval = rte_eth_tx_queue_setup(port, q, txRingSize,
rte_eth_dev_socket_id(port),
NULL);
if (retval < 0) {
printf("initialize tx queue %d failed\n", q);
return retval;
}
}
retval = rte_eth_dev_start(port);
if (retval < 0) {
printf("port %d start failed\n", port);
return retval;
}
rte_eth_macaddr_get(port, &vmdq_ports_eth_addr[port]);
printf("Port %u MAC: %02"PRIx8" %02"PRIx8" %02"PRIx8
" %02"PRIx8" %02"PRIx8" %02"PRIx8"\n",
(unsigned)port,
vmdq_ports_eth_addr[port].addr_bytes[0],
vmdq_ports_eth_addr[port].addr_bytes[1],
vmdq_ports_eth_addr[port].addr_bytes[2],
vmdq_ports_eth_addr[port].addr_bytes[3],
vmdq_ports_eth_addr[port].addr_bytes[4],
vmdq_ports_eth_addr[port].addr_bytes[5]);
/* Set mac for each pool.*/
for (q = 0; q < num_pools; q++) {
struct ether_addr mac;
mac = pool_addr_template;
mac.addr_bytes[4] = port;
mac.addr_bytes[5] = q;
printf("Port %u vmdq pool %u set mac %02x:%02x:%02x:%02x:%02x:%02x\n",
port, q,
mac.addr_bytes[0], mac.addr_bytes[1],
mac.addr_bytes[2], mac.addr_bytes[3],
mac.addr_bytes[4], mac.addr_bytes[5]);
retval = rte_eth_dev_mac_addr_add(port, &mac,
q + vmdq_pool_base);
if (retval) {
printf("mac addr add failed at pool %d\n", q);
return retval;
}
}
return 0;
}
