#define REORDER_PERIOD_MS 10
#define DEFAULT_POLLING_INTERVAL_10_MS (10)
+#define BOND_MAX_MAC_ADDRS 16
#define HASH_L4_PORTS(h) ((h)->src_port ^ (h)->dst_port)
{
size_t vlan_offset = 0;
- if (rte_cpu_to_be_16(ETHER_TYPE_VLAN) == *proto) {
+ if (rte_cpu_to_be_16(ETHER_TYPE_VLAN) == *proto ||
+ rte_cpu_to_be_16(ETHER_TYPE_QINQ) == *proto) {
struct vlan_hdr *vlan_hdr = (struct vlan_hdr *)(eth_hdr + 1);
vlan_offset = sizeof(struct vlan_hdr);
{
struct bond_dev_private *internals;
- uint16_t num_rx_slave = 0;
uint16_t num_rx_total = 0;
-
+ uint16_t slave_count;
+ uint16_t active_slave;
int i;
/* Cast to structure, containing bonded device's port id and queue id */
struct bond_rx_queue *bd_rx_q = (struct bond_rx_queue *)queue;
-
internals = bd_rx_q->dev_private;
+ slave_count = internals->active_slave_count;
+ active_slave = internals->active_slave;
+ for (i = 0; i < slave_count && nb_pkts; i++) {
+ uint16_t num_rx_slave;
- for (i = 0; i < internals->active_slave_count && nb_pkts; i++) {
/* Offset of pointer to *bufs increases as packets are received
* from other slaves */
- num_rx_slave = rte_eth_rx_burst(internals->active_slaves[i],
- bd_rx_q->queue_id, bufs + num_rx_total, nb_pkts);
- if (num_rx_slave) {
- num_rx_total += num_rx_slave;
- nb_pkts -= num_rx_slave;
- }
+ num_rx_slave =
+ rte_eth_rx_burst(internals->active_slaves[active_slave],
+ bd_rx_q->queue_id,
+ bufs + num_rx_total, nb_pkts);
+ num_rx_total += num_rx_slave;
+ nb_pkts -= num_rx_slave;
+ if (++active_slave == slave_count)
+ active_slave = 0;
}
+ if (++internals->active_slave == slave_count)
+ internals->active_slave = 0;
return num_rx_total;
}
uint16_t num_rx_total = 0; /* Total number of received packets */
uint16_t slaves[RTE_MAX_ETHPORTS];
uint16_t slave_count;
-
- uint16_t i, idx;
+ uint16_t active_slave;
+ uint16_t i;
/* Copy slave list to protect against slave up/down changes during tx
* bursting */
slave_count = internals->active_slave_count;
+ active_slave = internals->active_slave;
memcpy(slaves, internals->active_slaves,
sizeof(internals->active_slaves[0]) * slave_count);
- for (i = 0, idx = internals->active_slave;
- i < slave_count && num_rx_total < nb_pkts; i++, idx++) {
- idx = idx % slave_count;
+ for (i = 0; i < slave_count && nb_pkts; i++) {
+ uint16_t num_rx_slave;
/* Read packets from this slave */
- num_rx_total += rte_eth_rx_burst(slaves[idx], bd_rx_q->queue_id,
- &bufs[num_rx_total], nb_pkts - num_rx_total);
+ num_rx_slave = rte_eth_rx_burst(slaves[active_slave],
+ bd_rx_q->queue_id,
+ bufs + num_rx_total, nb_pkts);
+ num_rx_total += num_rx_slave;
+ nb_pkts -= num_rx_slave;
+
+ if (++active_slave == slave_count)
+ active_slave = 0;
}
- internals->active_slave = idx;
+ if (++internals->active_slave == slave_count)
+ internals->active_slave = 0;
return num_rx_total;
}
/* Mapping array generated by hash function to map mbufs to slaves */
uint16_t bufs_slave_port_idxs[RTE_MAX_ETHPORTS] = { 0 };
- uint16_t slave_tx_count, slave_tx_fail_count[RTE_MAX_ETHPORTS] = { 0 };
+ uint16_t slave_tx_count;
uint16_t total_tx_count = 0, total_tx_fail_count = 0;
- uint16_t i, j;
+ uint16_t i;
if (unlikely(nb_bufs == 0))
return 0;
/* If tx burst fails move packets to end of bufs */
if (unlikely(slave_tx_count < slave_nb_bufs[i])) {
- slave_tx_fail_count[i] = slave_nb_bufs[i] -
+ int slave_tx_fail_count = slave_nb_bufs[i] -
slave_tx_count;
- total_tx_fail_count += slave_tx_fail_count[i];
-
- /*
- * Shift bufs to beginning of array to allow reordering
- * later
- */
- for (j = 0; j < slave_tx_fail_count[i]; j++) {
- slave_bufs[i][j] =
- slave_bufs[i][(slave_tx_count - 1) + j];
- }
- }
- }
-
- /*
- * If there are tx burst failures we move packets to end of bufs to
- * preserve expected PMD behaviour of all failed transmitted being
- * at the end of the input mbuf array
- */
- if (unlikely(total_tx_fail_count > 0)) {
- int bufs_idx = nb_bufs - total_tx_fail_count - 1;
-
- for (i = 0; i < slave_count; i++) {
- if (slave_tx_fail_count[i] > 0) {
- for (j = 0; j < slave_tx_fail_count[i]; j++)
- bufs[bufs_idx++] = slave_bufs[i][j];
- }
+ total_tx_fail_count += slave_tx_fail_count;
+ memcpy(&bufs[nb_bufs - total_tx_fail_count],
+ &slave_bufs[i][slave_tx_count],
+ slave_tx_fail_count * sizeof(bufs[0]));
}
}
idx = 0;
}
- internals->active_slave = idx;
+ if (++internals->active_slave == slave_count)
+ internals->active_slave = 0;
+
return num_rx_total;
}
tx_fail_total += tx_fail_slave;
memcpy(&bufs[nb_pkts - tx_fail_total],
- &slave_bufs[i][num_tx_slave],
- tx_fail_slave * sizeof(bufs[0]));
+ &slave_bufs[i][num_tx_slave],
+ tx_fail_slave * sizeof(bufs[0]));
}
num_tx_total += num_tx_slave;
}
/* Mapping array generated by hash function to map mbufs to slaves */
uint16_t bufs_slave_port_idxs[nb_bufs];
- uint16_t slave_tx_count, slave_tx_fail_count[RTE_MAX_ETHPORTS] = { 0 };
+ uint16_t slave_tx_count;
uint16_t total_tx_count = 0, total_tx_fail_count = 0;
- uint16_t i, j;
+ uint16_t i;
if (unlikely(nb_bufs == 0))
return 0;
/* If tx burst fails move packets to end of bufs */
if (unlikely(slave_tx_count < slave_nb_bufs[i])) {
- slave_tx_fail_count[i] = slave_nb_bufs[i] -
+ int slave_tx_fail_count = slave_nb_bufs[i] -
slave_tx_count;
- total_tx_fail_count += slave_tx_fail_count[i];
-
- /*
- * Shift bufs to beginning of array to allow reordering
- * later
- */
- for (j = 0; j < slave_tx_fail_count[i]; j++) {
- slave_bufs[i][j] =
- slave_bufs[i][(slave_tx_count - 1) + j];
- }
- }
- }
-
- /*
- * If there are tx burst failures we move packets to end of bufs to
- * preserve expected PMD behaviour of all failed transmitted being
- * at the end of the input mbuf array
- */
- if (unlikely(total_tx_fail_count > 0)) {
- int bufs_idx = nb_bufs - total_tx_fail_count - 1;
-
- for (i = 0; i < slave_count; i++) {
- if (slave_tx_fail_count[i] > 0) {
- for (j = 0; j < slave_tx_fail_count[i]; j++)
- bufs[bufs_idx++] = slave_bufs[i][j];
- }
+ total_tx_fail_count += slave_tx_fail_count;
+ memcpy(&bufs[nb_bufs - total_tx_fail_count],
+ &slave_bufs[i][slave_tx_count],
+ slave_tx_fail_count * sizeof(bufs[0]));
}
}
/* Mapping array generated by hash function to map mbufs to slaves */
uint16_t bufs_slave_port_idxs[RTE_MAX_ETHPORTS] = { 0 };
- uint16_t slave_tx_count, slave_tx_fail_count[RTE_MAX_ETHPORTS] = { 0 };
+ uint16_t slave_tx_count;
uint16_t total_tx_count = 0, total_tx_fail_count = 0;
- uint16_t i, j;
+ uint16_t i;
if (unlikely(nb_bufs == 0))
return 0;
/* If tx burst fails move packets to end of bufs */
if (unlikely(slave_tx_count < slave_nb_bufs[i])) {
- slave_tx_fail_count[i] = slave_nb_bufs[i] -
+ int slave_tx_fail_count = slave_nb_bufs[i] -
slave_tx_count;
- total_tx_fail_count += slave_tx_fail_count[i];
-
- /*
- * Shift bufs to beginning of array to allow
- * reordering later
- */
- for (j = 0; j < slave_tx_fail_count[i]; j++)
- slave_bufs[i][j] =
- slave_bufs[i]
- [(slave_tx_count - 1)
- + j];
- }
- }
+ total_tx_fail_count += slave_tx_fail_count;
- /*
- * If there are tx burst failures we move packets to end of
- * bufs to preserve expected PMD behaviour of all failed
- * transmitted being at the end of the input mbuf array
- */
- if (unlikely(total_tx_fail_count > 0)) {
- int bufs_idx = nb_bufs - total_tx_fail_count - 1;
-
- for (i = 0; i < slave_count; i++) {
- if (slave_tx_fail_count[i] > 0) {
- for (j = 0;
- j < slave_tx_fail_count[i];
- j++) {
- bufs[bufs_idx++] =
- slave_bufs[i][j];
- }
- }
+ memcpy(&bufs[nb_bufs - total_tx_fail_count],
+ &slave_bufs[i][slave_tx_count],
+ slave_tx_fail_count * sizeof(bufs[0]));
}
}
}
return 0;
}
+static const struct ether_addr null_mac_addr;
+
+/*
+ * Add additional MAC addresses to the slave
+ */
+int
+slave_add_mac_addresses(struct rte_eth_dev *bonded_eth_dev,
+ uint16_t slave_port_id)
+{
+ int i, ret;
+ struct ether_addr *mac_addr;
+
+ for (i = 1; i < BOND_MAX_MAC_ADDRS; i++) {
+ mac_addr = &bonded_eth_dev->data->mac_addrs[i];
+ if (is_same_ether_addr(mac_addr, &null_mac_addr))
+ break;
+
+ ret = rte_eth_dev_mac_addr_add(slave_port_id, mac_addr, 0);
+ if (ret < 0) {
+ /* rollback */
+ for (i--; i > 0; i--)
+ rte_eth_dev_mac_addr_remove(slave_port_id,
+ &bonded_eth_dev->data->mac_addrs[i]);
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * Remove additional MAC addresses from the slave
+ */
+int
+slave_remove_mac_addresses(struct rte_eth_dev *bonded_eth_dev,
+ uint16_t slave_port_id)
+{
+ int i, rc, ret;
+ struct ether_addr *mac_addr;
+
+ rc = 0;
+ for (i = 1; i < BOND_MAX_MAC_ADDRS; i++) {
+ mac_addr = &bonded_eth_dev->data->mac_addrs[i];
+ if (is_same_ether_addr(mac_addr, &null_mac_addr))
+ break;
+
+ ret = rte_eth_dev_mac_addr_remove(slave_port_id, mac_addr);
+ /* save only the first error */
+ if (ret < 0 && rc == 0)
+ rc = ret;
+ }
+
+ return rc;
+}
+
int
mac_address_slaves_update(struct rte_eth_dev *bonded_eth_dev)
{
/* If RSS is enabled for bonding, try to enable it for slaves */
if (bonded_eth_dev->data->dev_conf.rxmode.mq_mode & ETH_MQ_RX_RSS_FLAG) {
- if (bonded_eth_dev->data->dev_conf.rx_adv_conf.rss_conf.rss_key_len
- != 0) {
+ if (internals->rss_key_len != 0) {
slave_eth_dev->data->dev_conf.rx_adv_conf.rss_conf.rss_key_len =
- bonded_eth_dev->data->dev_conf.rx_adv_conf.rss_conf.rss_key_len;
+ internals->rss_key_len;
slave_eth_dev->data->dev_conf.rx_adv_conf.rss_conf.rss_key =
- bonded_eth_dev->data->dev_conf.rx_adv_conf.rss_conf.rss_key;
+ internals->rss_key;
} else {
slave_eth_dev->data->dev_conf.rx_adv_conf.rss_conf.rss_key = NULL;
}
}
}
- /* Update all slave devices MACs*/
- if (mac_address_slaves_update(eth_dev) != 0)
- goto out_err;
-
/* If bonded device is configure in promiscuous mode then re-apply config */
if (internals->promiscuous_en)
bond_ethdev_promiscuous_enable(eth_dev);
(void *)&rte_eth_devices[internals->port_id]);
}
+ /* Update all slave devices MACs*/
+ if (mac_address_slaves_update(eth_dev) != 0)
+ goto out_err;
+
if (internals->user_defined_primary_port)
bond_ethdev_primary_set(internals, internals->primary_port);
tlb_last_obytets[internals->active_slaves[i]] = 0;
}
- internals->active_slave_count = 0;
internals->link_status_polling_enabled = 0;
for (i = 0; i < internals->slave_count; i++)
internals->slaves[i].last_link_status = 0;
uint16_t max_nb_rx_queues = UINT16_MAX;
uint16_t max_nb_tx_queues = UINT16_MAX;
- dev_info->max_mac_addrs = 1;
+ dev_info->max_mac_addrs = BOND_MAX_MAC_ADDRS;
dev_info->max_rx_pktlen = internals->candidate_max_rx_pktlen ?
internals->candidate_max_rx_pktlen :
mac_address_slaves_update(bonded_eth_dev);
}
+ /* check link state properties if bonded link is up*/
+ if (bonded_eth_dev->data->dev_link.link_status == ETH_LINK_UP) {
+ if (link_properties_valid(bonded_eth_dev, &link) != 0)
+ RTE_BOND_LOG(ERR, "Invalid link properties "
+ "for slave %d in bonding mode %d",
+ port_id, internals->mode);
+ } else {
+ /* inherit slave link properties */
+ link_properties_set(bonded_eth_dev, &link);
+ }
+
activate_slave(bonded_eth_dev, port_id);
/* If user has defined the primary port then default to using it */
return -ENOTSUP;
}
+static int
+bond_ethdev_mac_addr_add(struct rte_eth_dev *dev, struct ether_addr *mac_addr,
+ __rte_unused uint32_t index, uint32_t vmdq)
+{
+ struct rte_eth_dev *slave_eth_dev;
+ struct bond_dev_private *internals = dev->data->dev_private;
+ int ret, i;
+
+ rte_spinlock_lock(&internals->lock);
+
+ for (i = 0; i < internals->slave_count; i++) {
+ slave_eth_dev = &rte_eth_devices[internals->slaves[i].port_id];
+ if (*slave_eth_dev->dev_ops->mac_addr_add == NULL ||
+ *slave_eth_dev->dev_ops->mac_addr_remove == NULL) {
+ ret = -ENOTSUP;
+ goto end;
+ }
+ }
+
+ for (i = 0; i < internals->slave_count; i++) {
+ ret = rte_eth_dev_mac_addr_add(internals->slaves[i].port_id,
+ mac_addr, vmdq);
+ if (ret < 0) {
+ /* rollback */
+ for (i--; i >= 0; i--)
+ rte_eth_dev_mac_addr_remove(
+ internals->slaves[i].port_id, mac_addr);
+ goto end;
+ }
+ }
+
+ ret = 0;
+end:
+ rte_spinlock_unlock(&internals->lock);
+ return ret;
+}
+
+static void
+bond_ethdev_mac_addr_remove(struct rte_eth_dev *dev, uint32_t index)
+{
+ struct rte_eth_dev *slave_eth_dev;
+ struct bond_dev_private *internals = dev->data->dev_private;
+ int i;
+
+ rte_spinlock_lock(&internals->lock);
+
+ for (i = 0; i < internals->slave_count; i++) {
+ slave_eth_dev = &rte_eth_devices[internals->slaves[i].port_id];
+ if (*slave_eth_dev->dev_ops->mac_addr_remove == NULL)
+ goto end;
+ }
+
+ struct ether_addr *mac_addr = &dev->data->mac_addrs[index];
+
+ for (i = 0; i < internals->slave_count; i++)
+ rte_eth_dev_mac_addr_remove(internals->slaves[i].port_id,
+ mac_addr);
+
+end:
+ rte_spinlock_unlock(&internals->lock);
+}
+
const struct eth_dev_ops default_dev_ops = {
.dev_start = bond_ethdev_start,
.dev_stop = bond_ethdev_stop,
.rss_hash_conf_get = bond_ethdev_rss_hash_conf_get,
.mtu_set = bond_ethdev_mtu_set,
.mac_addr_set = bond_ethdev_mac_address_set,
+ .mac_addr_add = bond_ethdev_mac_addr_add,
+ .mac_addr_remove = bond_ethdev_mac_addr_remove,
.filter_ctrl = bond_filter_ctrl
};
eth_dev->data->nb_rx_queues = (uint16_t)1;
eth_dev->data->nb_tx_queues = (uint16_t)1;
- eth_dev->data->mac_addrs = rte_zmalloc_socket(name, ETHER_ADDR_LEN, 0,
- socket_id);
+ /* Allocate memory for storing MAC addresses */
+ eth_dev->data->mac_addrs = rte_zmalloc_socket(name, ETHER_ADDR_LEN *
+ BOND_MAX_MAC_ADDRS, 0, socket_id);
if (eth_dev->data->mac_addrs == NULL) {
- RTE_BOND_LOG(ERR, "Unable to malloc mac_addrs");
+ RTE_BOND_LOG(ERR,
+ "Failed to allocate %u bytes needed to store MAC addresses",
+ ETHER_ADDR_LEN * BOND_MAX_MAC_ADDRS);
goto err;
}
}
/* TODO: request info from primary to set up Rx and Tx */
eth_dev->dev_ops = &default_dev_ops;
+ eth_dev->device = &dev->device;
rte_eth_dev_probing_finish(eth_dev);
return 0;
}
internals = rte_eth_devices[port_id].data->dev_private;
internals->kvlist = kvlist;
+ rte_eth_dev_probing_finish(&rte_eth_devices[port_id]);
if (rte_kvargs_count(kvlist, PMD_BOND_AGG_MODE_KVARG) == 1) {
if (rte_kvargs_process(kvlist,
rte_eth_bond_8023ad_agg_selection_set(port_id, AGG_STABLE);
}
- rte_eth_dev_probing_finish(&rte_eth_devices[port_id]);
RTE_BOND_LOG(INFO, "Create bonded device %s on port %d in mode %u on "
"socket %u.", name, port_id, bonding_mode, socket_id);
return 0;
unsigned i, j;
- /* If RSS is enabled, fill table and key with default values */
+ /*
+ * If RSS is enabled, fill table with default values and
+ * set key to the the value specified in port RSS configuration.
+ * Fall back to default RSS key if the key is not specified
+ */
if (dev->data->dev_conf.rxmode.mq_mode & ETH_MQ_RX_RSS) {
- dev->data->dev_conf.rx_adv_conf.rss_conf.rss_key = internals->rss_key;
- dev->data->dev_conf.rx_adv_conf.rss_conf.rss_key_len = 0;
- memcpy(internals->rss_key, default_rss_key, 40);
+ if (dev->data->dev_conf.rx_adv_conf.rss_conf.rss_key != NULL) {
+ internals->rss_key_len =
+ dev->data->dev_conf.rx_adv_conf.rss_conf.rss_key_len;
+ memcpy(internals->rss_key,
+ dev->data->dev_conf.rx_adv_conf.rss_conf.rss_key,
+ internals->rss_key_len);
+ } else {
+ internals->rss_key_len = sizeof(default_rss_key);
+ memcpy(internals->rss_key, default_rss_key,
+ internals->rss_key_len);
+ }
for (i = 0; i < RTE_DIM(internals->reta_conf); i++) {
internals->reta_conf[i].mask = ~0LL;
for (j = 0; j < RTE_RETA_GROUP_SIZE; j++)
- internals->reta_conf[i].reta[j] = j % dev->data->nb_rx_queues;
+ internals->reta_conf[i].reta[j] =
+ (i * RTE_RETA_GROUP_SIZE + j) %
+ dev->data->nb_rx_queues;
}
}
int bond_logtype;
-RTE_INIT(bond_init_log);
-static void
-bond_init_log(void)
+RTE_INIT(bond_init_log)
{
bond_logtype = rte_log_register("pmd.net.bon");
if (bond_logtype >= 0)
git.droids-corp.org / dpdk.git / blobdiff