/*-
* BSD LICENSE
*
- * Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2010-2016 Intel Corporation. All rights reserved.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
#include <rte_malloc.h>
#include <rte_ethdev.h>
#include <rte_tcp.h>
+#include <rte_vdev.h>
#include "rte_eth_bond.h"
#include "rte_eth_bond_private.h"
#define DEFAULT_POLLING_INTERVAL_10_MS (10)
int
-valid_bonded_ethdev(const struct rte_eth_dev *eth_dev)
+check_for_bonded_ethdev(const struct rte_eth_dev *eth_dev)
{
/* Check valid pointer */
- if (eth_dev->driver->pci_drv.name == NULL)
+ if (eth_dev->data->drv_name == NULL)
return -1;
/* return 0 if driver name matches */
- return eth_dev->driver->pci_drv.name != pmd_bond_driver_name;
+ return eth_dev->data->drv_name != pmd_bond_drv.driver.name;
}
int
valid_bonded_port_id(uint8_t port_id)
{
- if (!rte_eth_dev_is_valid_port(port_id))
- return -1;
-
- return valid_bonded_ethdev(&rte_eth_devices[port_id]);
+ RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -1);
+ return check_for_bonded_ethdev(&rte_eth_devices[port_id]);
}
int
valid_slave_port_id(uint8_t port_id)
{
- /* Verify that port id's are valid */
- if (!rte_eth_dev_is_valid_port(port_id))
- return -1;
+ RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -1);
/* Verify that port_id refers to a non bonded port */
- if (!valid_bonded_ethdev(&rte_eth_devices[port_id]))
+ if (check_for_bonded_ethdev(&rte_eth_devices[port_id]) == 0)
return -1;
return 0;
internals->tlb_slaves_order[active_count] = port_id;
}
- RTE_VERIFY(internals->active_slave_count <
+ RTE_ASSERT(internals->active_slave_count <
(RTE_DIM(internals->active_slaves) - 1));
internals->active_slaves[internals->active_slave_count] = port_id;
sizeof(internals->active_slaves[0]));
}
- RTE_VERIFY(active_count < RTE_DIM(internals->active_slaves));
+ RTE_ASSERT(active_count < RTE_DIM(internals->active_slaves));
internals->active_slave_count = active_count;
if (eth_dev->data->dev_started) {
return ++sockets;
}
-const char *pmd_bond_driver_name = "Link Bonding PMD";
-
int
rte_eth_bond_create(const char *name, uint8_t mode, uint8_t socket_id)
{
- struct rte_pci_device *pci_dev = NULL;
struct bond_dev_private *internals = NULL;
struct rte_eth_dev *eth_dev = NULL;
- struct eth_driver *eth_drv = NULL;
- struct rte_pci_driver *pci_drv = NULL;
- struct rte_pci_id *pci_id_table = NULL;
+ uint32_t vlan_filter_bmp_size;
+
/* now do all data allocation - for eth_dev structure, dummy pci driver
* and internal (private) data
*/
goto err;
}
- pci_dev = rte_zmalloc_socket(name, sizeof(*pci_dev), 0, socket_id);
- if (pci_dev == NULL) {
- RTE_BOND_LOG(ERR, "Unable to malloc pci dev on socket");
- goto err;
- }
-
- eth_drv = rte_zmalloc_socket(name, sizeof(*eth_drv), 0, socket_id);
- if (eth_drv == NULL) {
- RTE_BOND_LOG(ERR, "Unable to malloc eth_drv on socket");
- goto err;
- }
-
- pci_drv = ð_drv->pci_drv;
-
- pci_id_table = rte_zmalloc_socket(name, sizeof(*pci_id_table), 0, socket_id);
- if (pci_id_table == NULL) {
- RTE_BOND_LOG(ERR, "Unable to malloc pci_id_table on socket");
- goto err;
- }
- pci_id_table->device_id = PCI_ANY_ID;
- pci_id_table->subsystem_device_id = PCI_ANY_ID;
- pci_id_table->vendor_id = PCI_ANY_ID;
- pci_id_table->subsystem_vendor_id = PCI_ANY_ID;
-
- pci_drv->id_table = pci_id_table;
- pci_drv->drv_flags = RTE_PCI_DRV_INTR_LSC;
-
internals = rte_zmalloc_socket(name, sizeof(*internals), 0, socket_id);
if (internals == NULL) {
RTE_BOND_LOG(ERR, "Unable to malloc internals on socket");
}
/* reserve an ethdev entry */
- eth_dev = rte_eth_dev_allocate(name, RTE_ETH_DEV_VIRTUAL);
+ eth_dev = rte_eth_dev_allocate(name);
if (eth_dev == NULL) {
RTE_BOND_LOG(ERR, "Unable to allocate rte_eth_dev");
goto err;
}
- pci_dev->numa_node = socket_id;
- pci_drv->name = pmd_bond_driver_name;
- pci_dev->driver = pci_drv;
-
- eth_dev->driver = eth_drv;
eth_dev->data->dev_private = internals;
eth_dev->data->nb_rx_queues = (uint16_t)1;
eth_dev->data->nb_tx_queues = (uint16_t)1;
- TAILQ_INIT(&(eth_dev->link_intr_cbs));
-
- eth_dev->data->dev_link.link_status = 0;
-
eth_dev->data->mac_addrs = rte_zmalloc_socket(name, ETHER_ADDR_LEN, 0,
socket_id);
-
- eth_dev->data->dev_started = 0;
- eth_dev->data->promiscuous = 0;
- eth_dev->data->scattered_rx = 0;
- eth_dev->data->all_multicast = 0;
+ if (eth_dev->data->mac_addrs == NULL) {
+ RTE_BOND_LOG(ERR, "Unable to malloc mac_addrs");
+ goto err;
+ }
eth_dev->dev_ops = &default_dev_ops;
- eth_dev->pci_dev = pci_dev;
+ eth_dev->data->dev_flags = RTE_ETH_DEV_INTR_LSC |
+ RTE_ETH_DEV_DETACHABLE;
+ eth_dev->driver = NULL;
+ eth_dev->data->kdrv = RTE_KDRV_NONE;
+ eth_dev->data->drv_name = pmd_bond_drv.driver.name;
+ eth_dev->data->numa_node = socket_id;
rte_spinlock_init(&internals->lock);
internals->port_id = eth_dev->data->port_id;
internals->mode = BONDING_MODE_INVALID;
- internals->current_primary_port = 0;
+ internals->current_primary_port = RTE_MAX_ETHPORTS + 1;
internals->balance_xmit_policy = BALANCE_XMIT_POLICY_LAYER2;
internals->xmit_hash = xmit_l2_hash;
internals->user_defined_mac = 0;
internals->active_slave_count = 0;
internals->rx_offload_capa = 0;
internals->tx_offload_capa = 0;
+ internals->candidate_max_rx_pktlen = 0;
+ internals->max_rx_pktlen = 0;
+
+ /* Initially allow to choose any offload type */
+ internals->flow_type_rss_offloads = ETH_RSS_PROTO_MASK;
memset(internals->active_slaves, 0, sizeof(internals->active_slaves));
memset(internals->slaves, 0, sizeof(internals->slaves));
goto err;
}
+ vlan_filter_bmp_size =
+ rte_bitmap_get_memory_footprint(ETHER_MAX_VLAN_ID + 1);
+ internals->vlan_filter_bmpmem = rte_malloc(name, vlan_filter_bmp_size,
+ RTE_CACHE_LINE_SIZE);
+ if (internals->vlan_filter_bmpmem == NULL) {
+ RTE_BOND_LOG(ERR,
+ "Failed to allocate vlan bitmap for bonded device %u\n",
+ eth_dev->data->port_id);
+ goto err;
+ }
+
+ internals->vlan_filter_bmp = rte_bitmap_init(ETHER_MAX_VLAN_ID + 1,
+ internals->vlan_filter_bmpmem, vlan_filter_bmp_size);
+ if (internals->vlan_filter_bmp == NULL) {
+ RTE_BOND_LOG(ERR,
+ "Failed to init vlan bitmap for bonded device %u\n",
+ eth_dev->data->port_id);
+ rte_free(internals->vlan_filter_bmpmem);
+ goto err;
+ }
+
return eth_dev->data->port_id;
err:
- rte_free(pci_dev);
- rte_free(pci_id_table);
- rte_free(eth_drv);
rte_free(internals);
-
+ if (eth_dev != NULL) {
+ rte_free(eth_dev->data->mac_addrs);
+ rte_eth_dev_release_port(eth_dev);
+ }
return -1;
}
+int
+rte_eth_bond_free(const char *name)
+{
+ struct rte_eth_dev *eth_dev = NULL;
+ struct bond_dev_private *internals;
+
+ /* now free all data allocation - for eth_dev structure,
+ * dummy pci driver and internal (private) data
+ */
+
+ /* find an ethdev entry */
+ eth_dev = rte_eth_dev_allocated(name);
+ if (eth_dev == NULL)
+ return -ENODEV;
+
+ internals = eth_dev->data->dev_private;
+ if (internals->slave_count != 0)
+ return -EBUSY;
+
+ if (eth_dev->data->dev_started == 1) {
+ bond_ethdev_stop(eth_dev);
+ bond_ethdev_close(eth_dev);
+ }
+
+ eth_dev->dev_ops = NULL;
+ eth_dev->rx_pkt_burst = NULL;
+ eth_dev->tx_pkt_burst = NULL;
+
+ internals = eth_dev->data->dev_private;
+ rte_bitmap_free(internals->vlan_filter_bmp);
+ rte_free(internals->vlan_filter_bmpmem);
+ rte_free(eth_dev->data->dev_private);
+ rte_free(eth_dev->data->mac_addrs);
+
+ rte_eth_dev_release_port(eth_dev);
+
+ return 0;
+}
+
+static int
+slave_vlan_filter_set(uint8_t bonded_port_id, uint8_t slave_port_id)
+{
+ struct rte_eth_dev *bonded_eth_dev;
+ struct bond_dev_private *internals;
+ int found;
+ int res = 0;
+ uint64_t slab = 0;
+ uint32_t pos = 0;
+ uint16_t first;
+
+ bonded_eth_dev = &rte_eth_devices[bonded_port_id];
+ if (bonded_eth_dev->data->dev_conf.rxmode.hw_vlan_filter == 0)
+ return 0;
+
+ internals = bonded_eth_dev->data->dev_private;
+ found = rte_bitmap_scan(internals->vlan_filter_bmp, &pos, &slab);
+ first = pos;
+
+ if (!found)
+ return 0;
+
+ do {
+ uint32_t i;
+ uint64_t mask;
+
+ for (i = 0, mask = 1;
+ i < RTE_BITMAP_SLAB_BIT_SIZE;
+ i ++, mask <<= 1) {
+ if (unlikely(slab & mask))
+ res = rte_eth_dev_vlan_filter(slave_port_id,
+ (uint16_t)pos, 1);
+ }
+ found = rte_bitmap_scan(internals->vlan_filter_bmp,
+ &pos, &slab);
+ } while (found && first != pos && res == 0);
+
+ return res;
+}
+
static int
__eth_bond_slave_add_lock_free(uint8_t bonded_port_id, uint8_t slave_port_id)
{
struct rte_eth_dev *bonded_eth_dev, *slave_eth_dev;
struct bond_dev_private *internals;
- struct bond_dev_private *temp_internals;
struct rte_eth_link link_props;
struct rte_eth_dev_info dev_info;
- int i, j;
-
if (valid_slave_port_id(slave_port_id) != 0)
return -1;
bonded_eth_dev = &rte_eth_devices[bonded_port_id];
internals = bonded_eth_dev->data->dev_private;
- /* Verify that new slave device is not already a slave of another
- * bonded device */
- for (i = rte_eth_dev_count()-1; i >= 0; i--) {
- if (valid_bonded_ethdev(&rte_eth_devices[i]) == 0) {
- temp_internals = rte_eth_devices[i].data->dev_private;
-
- for (j = 0; j < temp_internals->slave_count; j++) {
- /* Device already a slave of a bonded device */
- if (temp_internals->slaves[j].port_id == slave_port_id) {
- RTE_BOND_LOG(ERR, "Slave port %d is already a slave",
- slave_port_id);
- return -1;
- }
- }
- }
- }
-
slave_eth_dev = &rte_eth_devices[slave_port_id];
+ if (slave_eth_dev->data->dev_flags & RTE_ETH_DEV_BONDED_SLAVE) {
+ RTE_BOND_LOG(ERR, "Slave device is already a slave of a bonded device");
+ return -1;
+ }
/* Add slave details to bonded device */
- slave_add(internals, slave_eth_dev);
+ slave_eth_dev->data->dev_flags |= RTE_ETH_DEV_BONDED_SLAVE;
rte_eth_dev_info_get(slave_port_id, &dev_info);
+ if (dev_info.max_rx_pktlen < internals->max_rx_pktlen) {
+ RTE_BOND_LOG(ERR, "Slave (port %u) max_rx_pktlen too small",
+ slave_port_id);
+ return -1;
+ }
+
+ slave_add(internals, slave_eth_dev);
+
+ /* We need to store slaves reta_size to be able to synchronize RETA for all
+ * slave devices even if its sizes are different.
+ */
+ internals->slaves[internals->slave_count].reta_size = dev_info.reta_size;
if (internals->slave_count < 1) {
/* if MAC is not user defined then use MAC of first slave add to
/* Make primary slave */
internals->primary_port = slave_port_id;
+ internals->current_primary_port = slave_port_id;
+
+ /* Inherit queues settings from first slave */
+ internals->nb_rx_queues = slave_eth_dev->data->nb_rx_queues;
+ internals->nb_tx_queues = slave_eth_dev->data->nb_tx_queues;
+
+ internals->reta_size = dev_info.reta_size;
/* Take the first dev's offload capabilities */
internals->rx_offload_capa = dev_info.rx_offload_capa;
internals->tx_offload_capa = dev_info.tx_offload_capa;
+ internals->flow_type_rss_offloads = dev_info.flow_type_rss_offloads;
+
+ /* Inherit first slave's max rx packet size */
+ internals->candidate_max_rx_pktlen = dev_info.max_rx_pktlen;
} else {
- /* Check slave link properties are supported if props are set,
- * all slaves must be the same */
- if (internals->link_props_set) {
- if (link_properties_valid(&(bonded_eth_dev->data->dev_link),
- &(slave_eth_dev->data->dev_link))) {
- RTE_BOND_LOG(ERR,
- "Slave port %d link speed/duplex not supported",
- slave_port_id);
- return -1;
- }
- } else {
- link_properties_set(bonded_eth_dev,
- &(slave_eth_dev->data->dev_link));
- }
internals->rx_offload_capa &= dev_info.rx_offload_capa;
internals->tx_offload_capa &= dev_info.tx_offload_capa;
+ internals->flow_type_rss_offloads &= dev_info.flow_type_rss_offloads;
+
+ /* RETA size is GCD of all slaves RETA sizes, so, if all sizes will be
+ * the power of 2, the lower one is GCD
+ */
+ if (internals->reta_size > dev_info.reta_size)
+ internals->reta_size = dev_info.reta_size;
+
+ if (!internals->max_rx_pktlen &&
+ dev_info.max_rx_pktlen < internals->candidate_max_rx_pktlen)
+ internals->candidate_max_rx_pktlen = dev_info.max_rx_pktlen;
}
+ bonded_eth_dev->data->dev_conf.rx_adv_conf.rss_conf.rss_hf &=
+ internals->flow_type_rss_offloads;
+
internals->slave_count++;
/* Update all slave devices MACs*/
if (bonded_eth_dev->data->dev_started) {
if (slave_configure(bonded_eth_dev, slave_eth_dev) != 0) {
+ slave_eth_dev->data->dev_flags &= (~RTE_ETH_DEV_BONDED_SLAVE);
RTE_BOND_LOG(ERR, "rte_bond_slaves_configure: port=%d",
slave_port_id);
return -1;
if (bonded_eth_dev->data->dev_started) {
rte_eth_link_get_nowait(slave_port_id, &link_props);
- if (link_props.link_status == 1)
- activate_slave(bonded_eth_dev, slave_port_id);
+ if (link_props.link_status == ETH_LINK_UP) {
+ if (internals->active_slave_count == 0 &&
+ !internals->user_defined_primary_port)
+ bond_ethdev_primary_set(internals,
+ slave_port_id);
+
+ if (find_slave_by_id(internals->active_slaves,
+ internals->active_slave_count,
+ slave_port_id) == internals->active_slave_count)
+ activate_slave(bonded_eth_dev, slave_port_id);
+ }
}
+
+ slave_vlan_filter_set(bonded_port_id, slave_port_id);
+
return 0;
}
{
struct rte_eth_dev *bonded_eth_dev;
struct bond_dev_private *internals;
-
+ struct rte_eth_dev *slave_eth_dev;
int i, slave_idx;
if (valid_slave_port_id(slave_port_id) != 0)
mac_address_set(&rte_eth_devices[slave_port_id],
&(internals->slaves[slave_idx].persisted_mac_addr));
- slave_remove(internals, &rte_eth_devices[slave_port_id]);
+ slave_eth_dev = &rte_eth_devices[slave_port_id];
+ slave_remove(internals, slave_eth_dev);
+ slave_eth_dev->data->dev_flags &= (~RTE_ETH_DEV_BONDED_SLAVE);
/* first slave in the active list will be the primary by default,
* otherwise use first device in list */
if (internals->slave_count == 0) {
internals->rx_offload_capa = 0;
internals->tx_offload_capa = 0;
+ internals->flow_type_rss_offloads = ETH_RSS_PROTO_MASK;
+ internals->reta_size = 0;
+ internals->candidate_max_rx_pktlen = 0;
+ internals->max_rx_pktlen = 0;
}
return 0;
}