#include <rte_interrupts.h>
#include <rte_malloc.h>
#include <rte_string_fns.h>
+#include <rte_rwlock.h>
#include "mlx5.h"
#include "mlx5_glue.h"
#include "mlx5_rxtx.h"
#include "mlx5_utils.h"
+/* Supported speed values found in /usr/include/linux/ethtool.h */
+#ifndef HAVE_SUPPORTED_40000baseKR4_Full
+#define SUPPORTED_40000baseKR4_Full (1 << 23)
+#endif
+#ifndef HAVE_SUPPORTED_40000baseCR4_Full
+#define SUPPORTED_40000baseCR4_Full (1 << 24)
+#endif
+#ifndef HAVE_SUPPORTED_40000baseSR4_Full
+#define SUPPORTED_40000baseSR4_Full (1 << 25)
+#endif
+#ifndef HAVE_SUPPORTED_40000baseLR4_Full
+#define SUPPORTED_40000baseLR4_Full (1 << 26)
+#endif
+#ifndef HAVE_SUPPORTED_56000baseKR4_Full
+#define SUPPORTED_56000baseKR4_Full (1 << 27)
+#endif
+#ifndef HAVE_SUPPORTED_56000baseCR4_Full
+#define SUPPORTED_56000baseCR4_Full (1 << 28)
+#endif
+#ifndef HAVE_SUPPORTED_56000baseSR4_Full
+#define SUPPORTED_56000baseSR4_Full (1 << 29)
+#endif
+#ifndef HAVE_SUPPORTED_56000baseLR4_Full
+#define SUPPORTED_56000baseLR4_Full (1 << 30)
+#endif
+
/* Add defines in case the running kernel is not the same as user headers. */
#ifndef ETHTOOL_GLINKSETTINGS
struct ethtool_link_settings {
#endif
/**
- * Get interface name from private structure.
+ * Get master interface name from private structure.
*
* @param[in] dev
* Pointer to Ethernet device.
* 0 on success, a negative errno value otherwise and rte_errno is set.
*/
int
-mlx5_get_ifname(const struct rte_eth_dev *dev, char (*ifname)[IF_NAMESIZE])
+mlx5_get_master_ifname(const struct rte_eth_dev *dev,
+ char (*ifname)[IF_NAMESIZE])
{
struct priv *priv = dev->data->dev_private;
DIR *dir;
if (dev_port == dev_port_prev)
goto try_dev_id;
dev_port_prev = dev_port;
- if (dev_port == (priv->port - 1u))
+ if (dev_port == 0)
strlcpy(match, name, sizeof(match));
}
closedir(dir);
return 0;
}
+/**
+ * Get interface name from private structure.
+ *
+ * This is a port representor-aware version of mlx5_get_master_ifname().
+ *
+ * @param[in] dev
+ * Pointer to Ethernet device.
+ * @param[out] ifname
+ * Interface name output buffer.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_get_ifname(const struct rte_eth_dev *dev, char (*ifname)[IF_NAMESIZE])
+{
+ struct priv *priv = dev->data->dev_private;
+ unsigned int ifindex =
+ priv->nl_socket_rdma >= 0 ?
+ mlx5_nl_ifindex(priv->nl_socket_rdma, priv->ibdev_name) : 0;
+
+ if (!ifindex) {
+ if (!priv->representor)
+ return mlx5_get_master_ifname(dev, ifname);
+ rte_errno = ENXIO;
+ return -rte_errno;
+ }
+ if (if_indextoname(ifindex, &(*ifname)[0]))
+ return 0;
+ rte_errno = errno;
+ return -rte_errno;
+}
+
/**
* Get the interface index from device name.
*
mlx5_ifindex(const struct rte_eth_dev *dev)
{
char ifname[IF_NAMESIZE];
- int ret;
+ unsigned int ret;
ret = mlx5_get_ifname(dev, &ifname);
if (ret)
return ret;
ret = if_nametoindex(ifname);
- if (ret == -1) {
+ if (ret == 0) {
rte_errno = errno;
return -rte_errno;
}
* Request number to pass to ioctl().
* @param[out] ifr
* Interface request structure output buffer.
+ * @param master
+ * When device is a port representor, perform request on master device
+ * instead.
*
* @return
* 0 on success, a negative errno value otherwise and rte_errno is set.
*/
int
-mlx5_ifreq(const struct rte_eth_dev *dev, int req, struct ifreq *ifr)
+mlx5_ifreq(const struct rte_eth_dev *dev, int req, struct ifreq *ifr,
+ int master)
{
int sock = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP);
int ret = 0;
rte_errno = errno;
return -rte_errno;
}
- ret = mlx5_get_ifname(dev, &ifr->ifr_name);
+ if (master)
+ ret = mlx5_get_master_ifname(dev, &ifr->ifr_name);
+ else
+ ret = mlx5_get_ifname(dev, &ifr->ifr_name);
if (ret)
goto error;
ret = ioctl(sock, req, ifr);
mlx5_get_mtu(struct rte_eth_dev *dev, uint16_t *mtu)
{
struct ifreq request;
- int ret = mlx5_ifreq(dev, SIOCGIFMTU, &request);
+ int ret = mlx5_ifreq(dev, SIOCGIFMTU, &request, 0);
if (ret)
return ret;
{
struct ifreq request = { .ifr_mtu = mtu, };
- return mlx5_ifreq(dev, SIOCSIFMTU, &request);
+ return mlx5_ifreq(dev, SIOCSIFMTU, &request, 0);
}
/**
mlx5_set_flags(struct rte_eth_dev *dev, unsigned int keep, unsigned int flags)
{
struct ifreq request;
- int ret = mlx5_ifreq(dev, SIOCGIFFLAGS, &request);
+ int ret = mlx5_ifreq(dev, SIOCGIFFLAGS, &request, 0);
if (ret)
return ret;
request.ifr_flags &= keep;
request.ifr_flags |= flags & ~keep;
- return mlx5_ifreq(dev, SIOCSIFFLAGS, &request);
+ return mlx5_ifreq(dev, SIOCSIFFLAGS, &request, 0);
}
/**
unsigned int reta_idx_n;
const uint8_t use_app_rss_key =
!!dev->data->dev_conf.rx_adv_conf.rss_conf.rss_key;
- uint64_t supp_tx_offloads = mlx5_get_tx_port_offloads(dev);
- uint64_t tx_offloads = dev->data->dev_conf.txmode.offloads;
- uint64_t supp_rx_offloads =
- (mlx5_get_rx_port_offloads() |
- mlx5_get_rx_queue_offloads(dev));
- uint64_t rx_offloads = dev->data->dev_conf.rxmode.offloads;
int ret = 0;
- if ((tx_offloads & supp_tx_offloads) != tx_offloads) {
- DRV_LOG(ERR,
- "port %u some Tx offloads are not supported requested"
- " 0x%" PRIx64 " supported 0x%" PRIx64,
- dev->data->port_id, tx_offloads, supp_tx_offloads);
- rte_errno = ENOTSUP;
- return -rte_errno;
- }
- if ((rx_offloads & supp_rx_offloads) != rx_offloads) {
- DRV_LOG(ERR,
- "port %u some Rx offloads are not supported requested"
- " 0x%" PRIx64 " supported 0x%" PRIx64,
- dev->data->port_id, rx_offloads, supp_rx_offloads);
- rte_errno = ENOTSUP;
- return -rte_errno;
- }
if (use_app_rss_key &&
(dev->data->dev_conf.rx_adv_conf.rss_conf.rss_key_len !=
- rss_hash_default_key_len)) {
- DRV_LOG(ERR, "port %u RSS key len must be %zu Bytes long",
- dev->data->port_id, rss_hash_default_key_len);
+ MLX5_RSS_HASH_KEY_LEN)) {
+ DRV_LOG(ERR, "port %u RSS key len must be %s Bytes long",
+ dev->data->port_id, RTE_STR(MLX5_RSS_HASH_KEY_LEN));
rte_errno = EINVAL;
return -rte_errno;
}
priv->rss_conf.rss_key =
rte_realloc(priv->rss_conf.rss_key,
- rss_hash_default_key_len, 0);
+ MLX5_RSS_HASH_KEY_LEN, 0);
if (!priv->rss_conf.rss_key) {
DRV_LOG(ERR, "port %u cannot allocate RSS hash key memory (%u)",
dev->data->port_id, rxqs_n);
use_app_rss_key ?
dev->data->dev_conf.rx_adv_conf.rss_conf.rss_key :
rss_hash_default_key,
- rss_hash_default_key_len);
- priv->rss_conf.rss_key_len = rss_hash_default_key_len;
+ MLX5_RSS_HASH_KEY_LEN);
+ priv->rss_conf.rss_key_len = MLX5_RSS_HASH_KEY_LEN;
priv->rss_conf.rss_hf = dev->data->dev_conf.rx_adv_conf.rss_conf.rss_hf;
priv->rxqs = (void *)dev->data->rx_queues;
priv->txqs = (void *)dev->data->tx_queues;
return 0;
}
+/**
+ * Sets default tuning parameters.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param[out] info
+ * Info structure output buffer.
+ */
+static void
+mlx5_set_default_params(struct rte_eth_dev *dev, struct rte_eth_dev_info *info)
+{
+ struct priv *priv = dev->data->dev_private;
+
+ /* Minimum CPU utilization. */
+ info->default_rxportconf.ring_size = 256;
+ info->default_txportconf.ring_size = 256;
+ info->default_rxportconf.burst_size = 64;
+ info->default_txportconf.burst_size = 64;
+ if (priv->link_speed_capa & ETH_LINK_SPEED_100G) {
+ info->default_rxportconf.nb_queues = 16;
+ info->default_txportconf.nb_queues = 16;
+ if (dev->data->nb_rx_queues > 2 ||
+ dev->data->nb_tx_queues > 2) {
+ /* Max Throughput. */
+ info->default_rxportconf.ring_size = 2048;
+ info->default_txportconf.ring_size = 2048;
+ }
+ } else {
+ info->default_rxportconf.nb_queues = 8;
+ info->default_txportconf.nb_queues = 8;
+ if (dev->data->nb_rx_queues > 2 ||
+ dev->data->nb_tx_queues > 2) {
+ /* Max Throughput. */
+ info->default_rxportconf.ring_size = 4096;
+ info->default_txportconf.ring_size = 4096;
+ }
+ }
+}
+
/**
* DPDK callback to get information about the device.
*
max = 65535;
info->max_rx_queues = max;
info->max_tx_queues = max;
- info->max_mac_addrs = RTE_DIM(priv->mac);
+ info->max_mac_addrs = MLX5_MAX_UC_MAC_ADDRESSES;
info->rx_queue_offload_capa = mlx5_get_rx_queue_offloads(dev);
info->rx_offload_capa = (mlx5_get_rx_port_offloads() |
info->rx_queue_offload_capa);
info->if_index = if_nametoindex(ifname);
info->reta_size = priv->reta_idx_n ?
priv->reta_idx_n : config->ind_table_max_size;
- info->hash_key_size = rss_hash_default_key_len;
+ info->hash_key_size = MLX5_RSS_HASH_KEY_LEN;
info->speed_capa = priv->link_speed_capa;
info->flow_type_rss_offloads = ~MLX5_RSS_HF_MASK;
+ mlx5_set_default_params(dev, info);
+ info->switch_info.name = dev->data->name;
+ info->switch_info.domain_id = priv->domain_id;
+ info->switch_info.port_id = priv->representor_id;
+ if (priv->representor) {
+ unsigned int i = mlx5_dev_to_port_id(dev->device, NULL, 0);
+ uint16_t port_id[i];
+
+ i = RTE_MIN(mlx5_dev_to_port_id(dev->device, port_id, i), i);
+ while (i--) {
+ struct priv *opriv =
+ rte_eth_devices[port_id[i]].data->dev_private;
+
+ if (!opriv ||
+ opriv->representor ||
+ opriv->domain_id != priv->domain_id)
+ continue;
+ /*
+ * Override switch name with that of the master
+ * device.
+ */
+ info->switch_info.name = opriv->dev_data->name;
+ break;
+ }
+ }
}
/**
};
if (dev->rx_pkt_burst == mlx5_rx_burst ||
+ dev->rx_pkt_burst == mlx5_rx_burst_mprq ||
dev->rx_pkt_burst == mlx5_rx_burst_vec)
return ptypes;
return NULL;
int link_speed = 0;
int ret;
- ret = mlx5_ifreq(dev, SIOCGIFFLAGS, &ifr);
+ ret = mlx5_ifreq(dev, SIOCGIFFLAGS, &ifr, 1);
if (ret) {
DRV_LOG(WARNING, "port %u ioctl(SIOCGIFFLAGS) failed: %s",
dev->data->port_id, strerror(rte_errno));
dev_link.link_status = ((ifr.ifr_flags & IFF_UP) &&
(ifr.ifr_flags & IFF_RUNNING));
ifr.ifr_data = (void *)&edata;
- ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
+ ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr, 1);
if (ret) {
DRV_LOG(WARNING,
"port %u ioctl(SIOCETHTOOL, ETHTOOL_GSET) failed: %s",
uint64_t sc;
int ret;
- ret = mlx5_ifreq(dev, SIOCGIFFLAGS, &ifr);
+ ret = mlx5_ifreq(dev, SIOCGIFFLAGS, &ifr, 1);
if (ret) {
DRV_LOG(WARNING, "port %u ioctl(SIOCGIFFLAGS) failed: %s",
dev->data->port_id, strerror(rte_errno));
dev_link.link_status = ((ifr.ifr_flags & IFF_UP) &&
(ifr.ifr_flags & IFF_RUNNING));
ifr.ifr_data = (void *)&gcmd;
- ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
+ ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr, 1);
if (ret) {
DRV_LOG(DEBUG,
"port %u ioctl(SIOCETHTOOL, ETHTOOL_GLINKSETTINGS)"
*ecmd = gcmd;
ifr.ifr_data = (void *)ecmd;
- ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
+ ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr, 1);
if (ret) {
DRV_LOG(DEBUG,
"port %u ioctl(SIOCETHTOOL, ETHTOOL_GLINKSETTINGS)"
time_t start_time = time(NULL);
do {
- ret = mlx5_link_update_unlocked_gset(dev, &dev_link);
+ ret = mlx5_link_update_unlocked_gs(dev, &dev_link);
if (ret)
- ret = mlx5_link_update_unlocked_gs(dev, &dev_link);
+ ret = mlx5_link_update_unlocked_gset(dev, &dev_link);
if (ret == 0)
break;
/* Handle wait to complete situation. */
int ret;
ifr.ifr_data = (void *)ðpause;
- ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
+ ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr, 1);
if (ret) {
DRV_LOG(WARNING,
"port %u ioctl(SIOCETHTOOL, ETHTOOL_GPAUSEPARAM) failed:"
ethpause.tx_pause = 1;
else
ethpause.tx_pause = 0;
- ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
+ ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr, 0);
if (ret) {
DRV_LOG(WARNING,
"port %u ioctl(SIOCETHTOOL, ETHTOOL_SPAUSEPARAM)"
uint64_t tx_offloads = dev->data->dev_conf.txmode.offloads;
int tso = !!(tx_offloads & (DEV_TX_OFFLOAD_TCP_TSO |
DEV_TX_OFFLOAD_VXLAN_TNL_TSO |
- DEV_TX_OFFLOAD_GRE_TNL_TSO));
+ DEV_TX_OFFLOAD_GRE_TNL_TSO |
+ DEV_TX_OFFLOAD_IP_TNL_TSO |
+ DEV_TX_OFFLOAD_UDP_TNL_TSO));
+ int swp = !!(tx_offloads & (DEV_TX_OFFLOAD_IP_TNL_TSO |
+ DEV_TX_OFFLOAD_UDP_TNL_TSO |
+ DEV_TX_OFFLOAD_OUTER_IPV4_CKSUM));
int vlan_insert = !!(tx_offloads & DEV_TX_OFFLOAD_VLAN_INSERT);
assert(priv != NULL);
/* Select appropriate TX function. */
- if (vlan_insert || tso)
+ if (vlan_insert || tso || swp)
return tx_pkt_burst;
if (config->mps == MLX5_MPW_ENHANCED) {
if (mlx5_check_vec_tx_support(dev) > 0) {
rx_pkt_burst = mlx5_rx_burst_vec;
DRV_LOG(DEBUG, "port %u selected Rx vectorized function",
dev->data->port_id);
+ } else if (mlx5_mprq_enabled(dev)) {
+ rx_pkt_burst = mlx5_rx_burst_mprq;
}
return rx_pkt_burst;
}
return 1;
return 0;
}
+
+/**
+ * Get port ID list of mlx5 instances sharing a common device.
+ *
+ * @param[in] dev
+ * Device to look for.
+ * @param[out] port_list
+ * Result buffer for collected port IDs.
+ * @param port_list_n
+ * Maximum number of entries in result buffer. If 0, @p port_list can be
+ * NULL.
+ *
+ * @return
+ * Number of matching instances regardless of the @p port_list_n
+ * parameter, 0 if none were found.
+ */
+unsigned int
+mlx5_dev_to_port_id(const struct rte_device *dev, uint16_t *port_list,
+ unsigned int port_list_n)
+{
+ uint16_t id;
+ unsigned int n = 0;
+
+ RTE_ETH_FOREACH_DEV(id) {
+ struct rte_eth_dev *ldev = &rte_eth_devices[id];
+
+ if (!ldev->device ||
+ !ldev->device->driver ||
+ strcmp(ldev->device->driver->name, MLX5_DRIVER_NAME) ||
+ ldev->device != dev)
+ continue;
+ if (n < port_list_n)
+ port_list[n] = id;
+ n++;
+ }
+ return n;
+}
+
+/**
+ * Get switch information associated with network interface.
+ *
+ * @param ifindex
+ * Network interface index.
+ * @param[out] info
+ * Switch information object, populated in case of success.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_sysfs_switch_info(unsigned int ifindex, struct mlx5_switch_info *info)
+{
+ char ifname[IF_NAMESIZE];
+ FILE *file;
+ struct mlx5_switch_info data = { .master = 0, };
+ bool port_name_set = false;
+ bool port_switch_id_set = false;
+ char c;
+
+ if (!if_indextoname(ifindex, ifname)) {
+ rte_errno = errno;
+ return -rte_errno;
+ }
+
+ MKSTR(phys_port_name, "/sys/class/net/%s/phys_port_name",
+ ifname);
+ MKSTR(phys_switch_id, "/sys/class/net/%s/phys_switch_id",
+ ifname);
+
+ file = fopen(phys_port_name, "rb");
+ if (file != NULL) {
+ port_name_set =
+ fscanf(file, "%d%c", &data.port_name, &c) == 2 &&
+ c == '\n';
+ fclose(file);
+ }
+ file = fopen(phys_switch_id, "rb");
+ if (file == NULL) {
+ rte_errno = errno;
+ return -rte_errno;
+ }
+ port_switch_id_set =
+ fscanf(file, "%" SCNx64 "%c", &data.switch_id, &c) == 2 &&
+ c == '\n';
+ fclose(file);
+ data.master = port_switch_id_set && !port_name_set;
+ data.representor = port_switch_id_set && port_name_set;
+ *info = data;
+ return 0;
+}