if (ret)
DRV_LOG(WARNING, "port %u some flows still remain",
dev->data->port_id);
+ if (priv->domain_id != RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID) {
+ unsigned int c = 0;
+ 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->domain_id != priv->domain_id ||
+ &rte_eth_devices[port_id[i]] == dev)
+ continue;
+ ++c;
+ }
+ if (!c)
+ claim_zero(rte_eth_switch_domain_free(priv->domain_id));
+ }
memset(priv, 0, sizeof(*priv));
+ priv->domain_id = RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID;
}
const struct eth_dev_ops mlx5_dev_ops = {
* Verbs device.
* @param vf
* If nonzero, enable VF-specific features.
+ * @param[in] switch_info
+ * Switch properties of Ethernet device.
*
* @return
* A valid Ethernet device object on success, NULL otherwise and rte_errno
static struct rte_eth_dev *
mlx5_dev_spawn(struct rte_device *dpdk_dev,
struct ibv_device *ibv_dev,
- int vf)
+ int vf,
+ const struct mlx5_switch_info *switch_info)
{
struct ibv_context *ctx;
struct ibv_device_attr_ex attr;
#endif
struct ether_addr mac;
char name[RTE_ETH_NAME_MAX_LEN];
+ int own_domain_id = 0;
+ unsigned int i;
/* Prepare shared data between primary and secondary process. */
mlx5_prepare_shared_data();
DEBUG("ibv_query_device_ex() failed");
goto error;
}
- rte_strlcpy(name, dpdk_dev->name, sizeof(name));
+ if (!switch_info->representor)
+ rte_strlcpy(name, dpdk_dev->name, sizeof(name));
+ else
+ snprintf(name, sizeof(name), "%s_representor_%u",
+ dpdk_dev->name, switch_info->port_name);
+ DRV_LOG(DEBUG, "naming Ethernet device \"%s\"", name);
if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
eth_dev = rte_eth_dev_attach_secondary(name);
if (eth_dev == NULL) {
goto error;
}
priv->ctx = ctx;
+ strncpy(priv->ibdev_name, priv->ctx->device->name,
+ sizeof(priv->ibdev_name));
strncpy(priv->ibdev_path, priv->ctx->device->ibdev_path,
sizeof(priv->ibdev_path));
priv->device_attr = attr;
priv->nl_socket_rdma = mlx5_nl_init(0, NETLINK_RDMA);
priv->nl_socket_route = mlx5_nl_init(RTMGRP_LINK, NETLINK_ROUTE);
priv->nl_sn = 0;
+ priv->representor = !!switch_info->representor;
+ priv->domain_id = RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID;
+ priv->representor_id =
+ switch_info->representor ? switch_info->port_name : -1;
+ /*
+ * Look for sibling devices in order to reuse their switch domain
+ * if any, otherwise allocate one.
+ */
+ i = mlx5_dev_to_port_id(dpdk_dev, NULL, 0);
+ if (i > 0) {
+ uint16_t port_id[i];
+
+ i = RTE_MIN(mlx5_dev_to_port_id(dpdk_dev, port_id, i), i);
+ while (i--) {
+ const struct priv *opriv =
+ rte_eth_devices[port_id[i]].data->dev_private;
+
+ if (!opriv ||
+ opriv->domain_id ==
+ RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID)
+ continue;
+ priv->domain_id = opriv->domain_id;
+ break;
+ }
+ }
+ if (priv->domain_id == RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID) {
+ err = rte_eth_switch_domain_alloc(&priv->domain_id);
+ if (err) {
+ err = rte_errno;
+ DRV_LOG(ERR, "unable to allocate switch domain: %s",
+ strerror(rte_errno));
+ goto error;
+ }
+ own_domain_id = 1;
+ }
err = mlx5_args(&config, dpdk_dev->devargs);
if (err) {
err = rte_errno;
err = ENOMEM;
goto error;
}
+ if (priv->representor)
+ eth_dev->data->dev_flags |= RTE_ETH_DEV_REPRESENTOR;
eth_dev->data->dev_private = priv;
priv->dev_data = eth_dev->data;
eth_dev->data->mac_addrs = priv->mac;
close(priv->nl_socket_route);
if (priv->nl_socket_rdma >= 0)
close(priv->nl_socket_rdma);
+ if (own_domain_id)
+ claim_zero(rte_eth_switch_domain_free(priv->domain_id));
rte_free(priv);
}
if (pd)
/**
* DPDK callback to register a PCI device.
*
- * This function spawns an Ethernet device out of a given PCI device.
+ * This function spawns Ethernet devices out of a given PCI device.
*
* @param[in] pci_drv
* PCI driver structure (mlx5_driver).
struct rte_pci_device *pci_dev)
{
struct ibv_device **ibv_list;
- struct rte_eth_dev *eth_dev = NULL;
unsigned int n = 0;
int vf;
int ret;
unsigned int ifindex[n];
struct mlx5_switch_info info[n];
+ struct rte_eth_dev *eth_list[n];
int nl_route = n ? mlx5_nl_init(0, NETLINK_ROUTE) : -1;
int nl_rdma = n ? mlx5_nl_init(0, NETLINK_RDMA) : -1;
unsigned int i;
+ unsigned int u;
/*
* The existence of several matching entries (n > 1) means port
close(nl_rdma);
if (nl_route >= 0)
close(nl_route);
- /* Look for master device. */
- for (i = 0; i != n; ++i) {
- if (!info[i].master)
- continue;
- /* Make it the first entry. */
- if (i == 0)
- break;
- ibv_match[n] = ibv_match[0];
- ibv_match[0] = ibv_match[i];
- ibv_match[n] = NULL;
- break;
- }
- if (n && i == n) {
- if (n == 1 && !info[0].representor) {
+ /* Count unidentified devices. */
+ for (u = 0, i = 0; i != n; ++i)
+ if (!info[i].master && !info[i].representor)
+ ++u;
+ if (u) {
+ if (n == 1 && u == 1) {
/* Case #2. */
DRV_LOG(INFO, "no switch support detected");
- } else if (n == 1) {
- /* Case #3. */
- DRV_LOG(ERR,
- "device looks like a port representor, this is"
- " not supported yet");
- n = 0;
} else {
/* Case #3. */
DRV_LOG(ERR,
default:
vf = 0;
}
- if (n)
- eth_dev = mlx5_dev_spawn(&pci_dev->device, ibv_match[0], vf);
+ for (i = 0; i != n; ++i) {
+ uint32_t restore;
+
+ eth_list[i] = mlx5_dev_spawn(&pci_dev->device, ibv_match[i],
+ vf, &info[i]);
+ if (!eth_list[i])
+ break;
+ restore = eth_list[i]->data->dev_flags;
+ rte_eth_copy_pci_info(eth_list[i], pci_dev);
+ /* Restore non-PCI flags cleared by the above call. */
+ eth_list[i]->data->dev_flags |= restore;
+ rte_eth_dev_probing_finish(eth_list[i]);
+ }
mlx5_glue->free_device_list(ibv_list);
if (!n) {
DRV_LOG(WARNING,
pci_dev->addr.devid, pci_dev->addr.function);
rte_errno = ENOENT;
ret = -rte_errno;
- } else if (!eth_dev) {
+ } else if (i != n) {
DRV_LOG(ERR,
"probe of PCI device " PCI_PRI_FMT " aborted after"
" encountering an error: %s",
pci_dev->addr.devid, pci_dev->addr.function,
strerror(rte_errno));
ret = -rte_errno;
+ /* Roll back. */
+ while (i--) {
+ mlx5_dev_close(eth_list[i]);
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY)
+ rte_free(eth_list[i]->data->dev_private);
+ claim_zero(rte_eth_dev_release_port(eth_list[i]));
+ }
+ /* Restore original error. */
+ rte_errno = -ret;
} else {
- rte_eth_copy_pci_info(eth_dev, pci_dev);
- rte_eth_dev_probing_finish(eth_dev);
ret = 0;
}
return ret;
struct ibv_context *ctx; /* Verbs context. */
struct ibv_device_attr_ex device_attr; /* Device properties. */
struct ibv_pd *pd; /* Protection Domain. */
+ char ibdev_name[IBV_SYSFS_NAME_MAX]; /* IB device name. */
char ibdev_path[IBV_SYSFS_PATH_MAX]; /* IB device path for secondary */
struct ether_addr mac[MLX5_MAX_MAC_ADDRESSES]; /* MAC addresses. */
BITFIELD_DECLARE(mac_own, uint64_t, MLX5_MAX_MAC_ADDRESSES);
/* Device properties. */
uint16_t mtu; /* Configured MTU. */
unsigned int isolated:1; /* Whether isolated mode is enabled. */
+ unsigned int representor:1; /* Device is a port representor. */
+ uint16_t domain_id; /* Switch domain identifier. */
+ int32_t representor_id; /* Port representor identifier. */
/* RX/TX queues. */
unsigned int rxqs_n; /* RX queues array size. */
unsigned int txqs_n; /* TX queues array size. */
/* mlx5_ethdev.c */
+int mlx5_get_master_ifname(const struct rte_eth_dev *dev,
+ char (*ifname)[IF_NAMESIZE]);
int mlx5_get_ifname(const struct rte_eth_dev *dev, char (*ifname)[IF_NAMESIZE]);
int mlx5_ifindex(const struct rte_eth_dev *dev);
-int mlx5_ifreq(const struct rte_eth_dev *dev, int req, struct ifreq *ifr);
+int mlx5_ifreq(const struct rte_eth_dev *dev, int req, struct ifreq *ifr,
+ int master);
int mlx5_get_mtu(struct rte_eth_dev *dev, uint16_t *mtu);
int mlx5_set_flags(struct rte_eth_dev *dev, unsigned int keep,
unsigned int flags);
int mlx5_is_removed(struct rte_eth_dev *dev);
eth_tx_burst_t mlx5_select_tx_function(struct rte_eth_dev *dev);
eth_rx_burst_t mlx5_select_rx_function(struct rte_eth_dev *dev);
+unsigned int mlx5_dev_to_port_id(const struct rte_device *dev,
+ uint16_t *port_list,
+ unsigned int port_list_n);
/* mlx5_mac.c */
#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;
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.
*
* 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);
}
/**
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;
+ }
+ }
}
/**
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)"
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)"
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;
+}
struct ifreq request;
int ret;
- ret = mlx5_ifreq(dev, SIOCGIFHWADDR, &request);
+ ret = mlx5_ifreq(dev, SIOCGIFHWADDR, &request, 0);
if (ret)
return ret;
memcpy(mac, request.ifr_hwaddr.sa_data, ETHER_ADDR_LEN);
et_stats->cmd = ETHTOOL_GSTATS;
et_stats->n_stats = xstats_ctrl->stats_n;
ifr.ifr_data = (caddr_t)et_stats;
- ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
+ ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr, 1);
if (ret) {
DRV_LOG(WARNING,
"port %u unable to read statistic values from device",
drvinfo.cmd = ETHTOOL_GDRVINFO;
ifr.ifr_data = (caddr_t)&drvinfo;
- ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
+ ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr, 1);
if (ret) {
DRV_LOG(WARNING, "port %u unable to query number of statistics",
dev->data->port_id);
strings->string_set = ETH_SS_STATS;
strings->len = dev_stats_n;
ifr.ifr_data = (caddr_t)strings;
- ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
+ ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr, 1);
if (ret) {
DRV_LOG(WARNING, "port %u unable to get statistic names",
dev->data->port_id);