*/
#include <stddef.h>
-#include <assert.h>
-#include <inttypes.h>
#include <unistd.h>
-#include <stdint.h>
-#include <stdio.h>
#include <string.h>
+#include <stdint.h>
#include <stdlib.h>
#include <errno.h>
-#include <dirent.h>
-#include <net/if.h>
-#include <sys/ioctl.h>
-#include <sys/socket.h>
-#include <netinet/in.h>
-#include <linux/ethtool.h>
-#include <linux/sockios.h>
-#include <fcntl.h>
-#include <stdalign.h>
-#include <sys/un.h>
-#include <time.h>
-#include <rte_atomic.h>
-#include <rte_ethdev_driver.h>
+#include <ethdev_driver.h>
#include <rte_bus_pci.h>
#include <rte_mbuf.h>
#include <rte_common.h>
#include <rte_malloc.h>
#include <rte_string_fns.h>
#include <rte_rwlock.h>
+#include <rte_cycles.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 {
- uint32_t cmd;
- uint32_t speed;
- uint8_t duplex;
- uint8_t port;
- uint8_t phy_address;
- uint8_t autoneg;
- uint8_t mdio_support;
- uint8_t eth_to_mdix;
- uint8_t eth_tp_mdix_ctrl;
- int8_t link_mode_masks_nwords;
- uint32_t reserved[8];
- uint32_t link_mode_masks[];
-};
-
-#define ETHTOOL_GLINKSETTINGS 0x0000004c
-#define ETHTOOL_LINK_MODE_1000baseT_Full_BIT 5
-#define ETHTOOL_LINK_MODE_Autoneg_BIT 6
-#define ETHTOOL_LINK_MODE_1000baseKX_Full_BIT 17
-#define ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT 18
-#define ETHTOOL_LINK_MODE_10000baseKR_Full_BIT 19
-#define ETHTOOL_LINK_MODE_10000baseR_FEC_BIT 20
-#define ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT 21
-#define ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT 22
-#define ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT 23
-#define ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT 24
-#define ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT 25
-#define ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT 26
-#define ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT 27
-#define ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT 28
-#define ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT 29
-#define ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT 30
-#endif
-#ifndef HAVE_ETHTOOL_LINK_MODE_25G
-#define ETHTOOL_LINK_MODE_25000baseCR_Full_BIT 31
-#define ETHTOOL_LINK_MODE_25000baseKR_Full_BIT 32
-#define ETHTOOL_LINK_MODE_25000baseSR_Full_BIT 33
-#endif
-#ifndef HAVE_ETHTOOL_LINK_MODE_50G
-#define ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT 34
-#define ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT 35
-#endif
-#ifndef HAVE_ETHTOOL_LINK_MODE_100G
-#define ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT 36
-#define ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT 37
-#define ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT 38
-#define ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT 39
-#endif
-
-/**
- * Get master interface name from private structure.
- *
- * @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_master_ifname(const char *ibdev_path, char (*ifname)[IF_NAMESIZE])
-{
- DIR *dir;
- struct dirent *dent;
- unsigned int dev_type = 0;
- unsigned int dev_port_prev = ~0u;
- char match[IF_NAMESIZE] = "";
-
- assert(ibdev_path);
- {
- MKSTR(path, "%s/device/net", ibdev_path);
-
- dir = opendir(path);
- if (dir == NULL) {
- rte_errno = errno;
- return -rte_errno;
- }
- }
- while ((dent = readdir(dir)) != NULL) {
- char *name = dent->d_name;
- FILE *file;
- unsigned int dev_port;
- int r;
-
- if ((name[0] == '.') &&
- ((name[1] == '\0') ||
- ((name[1] == '.') && (name[2] == '\0'))))
- continue;
-
- MKSTR(path, "%s/device/net/%s/%s",
- ibdev_path, name,
- (dev_type ? "dev_id" : "dev_port"));
-
- file = fopen(path, "rb");
- if (file == NULL) {
- if (errno != ENOENT)
- continue;
- /*
- * Switch to dev_id when dev_port does not exist as
- * is the case with Linux kernel versions < 3.15.
- */
-try_dev_id:
- match[0] = '\0';
- if (dev_type)
- break;
- dev_type = 1;
- dev_port_prev = ~0u;
- rewinddir(dir);
- continue;
- }
- r = fscanf(file, (dev_type ? "%x" : "%u"), &dev_port);
- fclose(file);
- if (r != 1)
- continue;
- /*
- * Switch to dev_id when dev_port returns the same value for
- * all ports. May happen when using a MOFED release older than
- * 3.0 with a Linux kernel >= 3.15.
- */
- if (dev_port == dev_port_prev)
- goto try_dev_id;
- dev_port_prev = dev_port;
- if (dev_port == 0)
- strlcpy(match, name, sizeof(match));
- }
- closedir(dir);
- if (match[0] == '\0') {
- rte_errno = ENOENT;
- return -rte_errno;
- }
- strncpy(*ifname, match, sizeof(*ifname));
- 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 mlx5_priv *priv = dev->data->dev_private;
- unsigned int ifindex;
+#include <mlx5_malloc.h>
- assert(priv);
- assert(priv->sh);
- ifindex = priv->nl_socket_rdma >= 0 ?
- mlx5_nl_ifindex(priv->nl_socket_rdma,
- priv->sh->ibdev_name,
- priv->ibv_port) : 0;
- if (!ifindex) {
- if (!priv->representor)
- return mlx5_get_master_ifname(priv->sh->ibdev_path,
- ifname);
- rte_errno = ENXIO;
- return -rte_errno;
- }
- if (if_indextoname(ifindex, &(*ifname)[0]))
- return 0;
- rte_errno = errno;
- return -rte_errno;
-}
+#include "mlx5_rxtx.h"
+#include "mlx5_rx.h"
+#include "mlx5_tx.h"
+#include "mlx5_autoconf.h"
+#include "mlx5_devx.h"
+#include "rte_pmd_mlx5.h"
/**
* Get the interface index from device name.
unsigned int
mlx5_ifindex(const struct rte_eth_dev *dev)
{
- char ifname[IF_NAMESIZE];
+ struct mlx5_priv *priv = dev->data->dev_private;
unsigned int ifindex;
- if (mlx5_get_ifname(dev, &ifname))
- return 0;
- ifindex = if_nametoindex(ifname);
+ MLX5_ASSERT(priv);
+ MLX5_ASSERT(priv->if_index);
+ if (priv->master && priv->sh->bond.ifindex > 0)
+ ifindex = priv->sh->bond.ifindex;
+ else
+ ifindex = priv->if_index;
if (!ifindex)
- rte_errno = errno;
+ rte_errno = ENXIO;
return ifindex;
}
-/**
- * Perform ifreq ioctl() on associated Ethernet device.
- *
- * @param[in] dev
- * Pointer to Ethernet device.
- * @param req
- * Request number to pass to ioctl().
- * @param[out] ifr
- * Interface request structure output buffer.
- *
- * @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)
-{
- int sock = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP);
- int ret = 0;
-
- if (sock == -1) {
- rte_errno = errno;
- return -rte_errno;
- }
- ret = mlx5_get_ifname(dev, &ifr->ifr_name);
- if (ret)
- goto error;
- ret = ioctl(sock, req, ifr);
- if (ret == -1) {
- rte_errno = errno;
- goto error;
- }
- close(sock);
- return 0;
-error:
- close(sock);
- return -rte_errno;
-}
-
-/**
- * Get device MTU.
- *
- * @param dev
- * Pointer to Ethernet device.
- * @param[out] mtu
- * MTU value output buffer.
- *
- * @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
- */
-int
-mlx5_get_mtu(struct rte_eth_dev *dev, uint16_t *mtu)
-{
- struct ifreq request;
- int ret = mlx5_ifreq(dev, SIOCGIFMTU, &request);
-
- if (ret)
- return ret;
- *mtu = request.ifr_mtu;
- return 0;
-}
-
-/**
- * Set device MTU.
- *
- * @param dev
- * Pointer to Ethernet device.
- * @param mtu
- * MTU value to set.
- *
- * @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
- */
-static int
-mlx5_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
-{
- struct ifreq request = { .ifr_mtu = mtu, };
-
- return mlx5_ifreq(dev, SIOCSIFMTU, &request);
-}
-
-/**
- * Set device flags.
- *
- * @param dev
- * Pointer to Ethernet device.
- * @param keep
- * Bitmask for flags that must remain untouched.
- * @param flags
- * Bitmask for flags to modify.
- *
- * @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
- */
-int
-mlx5_set_flags(struct rte_eth_dev *dev, unsigned int keep, unsigned int flags)
-{
- struct ifreq request;
- int ret = mlx5_ifreq(dev, SIOCGIFFLAGS, &request);
-
- if (ret)
- return ret;
- request.ifr_flags &= keep;
- request.ifr_flags |= flags & ~keep;
- return mlx5_ifreq(dev, SIOCSIFFLAGS, &request);
-}
-
/**
* DPDK callback for Ethernet device configuration.
*
struct mlx5_priv *priv = dev->data->dev_private;
unsigned int rxqs_n = dev->data->nb_rx_queues;
unsigned int txqs_n = dev->data->nb_tx_queues;
- unsigned int i;
- unsigned int j;
- unsigned int reta_idx_n;
const uint8_t use_app_rss_key =
!!dev->data->dev_conf.rx_adv_conf.rss_conf.rss_key;
int ret = 0;
rte_errno = EINVAL;
return -rte_errno;
}
- priv->rss_conf.rss_key =
- rte_realloc(priv->rss_conf.rss_key,
- MLX5_RSS_HASH_KEY_LEN, 0);
+ priv->rss_conf.rss_key = mlx5_realloc(priv->rss_conf.rss_key,
+ MLX5_MEM_RTE,
+ MLX5_RSS_HASH_KEY_LEN, 0,
+ SOCKET_ID_ANY);
if (!priv->rss_conf.rss_key) {
DRV_LOG(ERR, "port %u cannot allocate RSS hash key memory (%u)",
dev->data->port_id, rxqs_n);
rte_errno = ENOMEM;
return -rte_errno;
}
+
+ if ((dev->data->dev_conf.txmode.offloads &
+ RTE_ETH_TX_OFFLOAD_SEND_ON_TIMESTAMP) &&
+ rte_mbuf_dyn_tx_timestamp_register(NULL, NULL) != 0) {
+ DRV_LOG(ERR, "port %u cannot register Tx timestamp field/flag",
+ dev->data->port_id);
+ return -rte_errno;
+ }
memcpy(priv->rss_conf.rss_key,
use_app_rss_key ?
dev->data->dev_conf.rx_adv_conf.rss_conf.rss_key :
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->rxq_privs = mlx5_realloc(priv->rxq_privs,
+ MLX5_MEM_RTE | MLX5_MEM_ZERO,
+ sizeof(void *) * rxqs_n, 0,
+ SOCKET_ID_ANY);
+ if (rxqs_n && priv->rxq_privs == NULL) {
+ DRV_LOG(ERR, "port %u cannot allocate rxq private data",
+ dev->data->port_id);
+ rte_errno = ENOMEM;
+ return -rte_errno;
+ }
priv->txqs = (void *)dev->data->tx_queues;
if (txqs_n != priv->txqs_n) {
DRV_LOG(INFO, "port %u Tx queues number update: %u -> %u",
dev->data->port_id, priv->txqs_n, txqs_n);
priv->txqs_n = txqs_n;
}
- if (rxqs_n > priv->config.ind_table_max_size) {
+ if (rxqs_n > priv->sh->dev_cap.ind_table_max_size) {
DRV_LOG(ERR, "port %u cannot handle this many Rx queues (%u)",
dev->data->port_id, rxqs_n);
rte_errno = EINVAL;
return -rte_errno;
}
+ if (priv->ext_rxqs && rxqs_n >= MLX5_EXTERNAL_RX_QUEUE_ID_MIN) {
+ DRV_LOG(ERR, "port %u cannot handle this many Rx queues (%u), "
+ "the maximal number of internal Rx queues is %u",
+ dev->data->port_id, rxqs_n,
+ MLX5_EXTERNAL_RX_QUEUE_ID_MIN - 1);
+ rte_errno = EINVAL;
+ return -rte_errno;
+ }
if (rxqs_n != priv->rxqs_n) {
DRV_LOG(INFO, "port %u Rx queues number update: %u -> %u",
dev->data->port_id, priv->rxqs_n, rxqs_n);
priv->rxqs_n = rxqs_n;
- /*
- * If the requested number of RX queues is not a power of two,
- * use the maximum indirection table size for better balancing.
- * The result is always rounded to the next power of two.
- */
- reta_idx_n = (1 << log2above((rxqs_n & (rxqs_n - 1)) ?
- priv->config.ind_table_max_size :
- rxqs_n));
- ret = mlx5_rss_reta_index_resize(dev, reta_idx_n);
- if (ret)
- return ret;
- /*
- * When the number of RX queues is not a power of two,
- * the remaining table entries are padded with reused WQs
- * and hashes are not spread uniformly.
- */
- for (i = 0, j = 0; (i != reta_idx_n); ++i) {
- (*priv->reta_idx)[i] = j;
- if (++j == rxqs_n)
- j = 0;
- }
}
+ priv->skip_default_rss_reta = 0;
ret = mlx5_proc_priv_init(dev);
if (ret)
return ret;
return 0;
}
+/**
+ * Configure default RSS reta.
+ *
+ * @param dev
+ * Pointer to Ethernet device structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_dev_configure_rss_reta(struct rte_eth_dev *dev)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ unsigned int rxqs_n = dev->data->nb_rx_queues;
+ unsigned int i;
+ unsigned int j;
+ unsigned int reta_idx_n;
+ int ret = 0;
+ unsigned int *rss_queue_arr = NULL;
+ unsigned int rss_queue_n = 0;
+
+ if (priv->skip_default_rss_reta)
+ return ret;
+ rss_queue_arr = mlx5_malloc(0, rxqs_n * sizeof(unsigned int), 0,
+ SOCKET_ID_ANY);
+ if (!rss_queue_arr) {
+ DRV_LOG(ERR, "port %u cannot allocate RSS queue list (%u)",
+ dev->data->port_id, rxqs_n);
+ rte_errno = ENOMEM;
+ return -rte_errno;
+ }
+ for (i = 0, j = 0; i < rxqs_n; i++) {
+ struct mlx5_rxq_ctrl *rxq_ctrl = mlx5_rxq_ctrl_get(dev, i);
+
+ if (rxq_ctrl && !rxq_ctrl->is_hairpin)
+ rss_queue_arr[j++] = i;
+ }
+ rss_queue_n = j;
+ if (rss_queue_n > priv->sh->dev_cap.ind_table_max_size) {
+ DRV_LOG(ERR, "port %u cannot handle this many Rx queues (%u)",
+ dev->data->port_id, rss_queue_n);
+ rte_errno = EINVAL;
+ mlx5_free(rss_queue_arr);
+ return -rte_errno;
+ }
+ DRV_LOG(INFO, "port %u Rx queues number update: %u -> %u",
+ dev->data->port_id, priv->rxqs_n, rxqs_n);
+ priv->rxqs_n = rxqs_n;
+ /*
+ * If the requested number of RX queues is not a power of two,
+ * use the maximum indirection table size for better balancing.
+ * The result is always rounded to the next power of two.
+ */
+ reta_idx_n = (1 << log2above((rss_queue_n & (rss_queue_n - 1)) ?
+ priv->sh->dev_cap.ind_table_max_size :
+ rss_queue_n));
+ ret = mlx5_rss_reta_index_resize(dev, reta_idx_n);
+ if (ret) {
+ mlx5_free(rss_queue_arr);
+ return ret;
+ }
+ /*
+ * When the number of RX queues is not a power of two,
+ * the remaining table entries are padded with reused WQs
+ * and hashes are not spread uniformly.
+ */
+ for (i = 0, j = 0; (i != reta_idx_n); ++i) {
+ (*priv->reta_idx)[i] = rss_queue_arr[j];
+ if (++j == rss_queue_n)
+ j = 0;
+ }
+ mlx5_free(rss_queue_arr);
+ return ret;
+}
+
/**
* Sets default tuning parameters.
*
/* 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.burst_size = MLX5_RX_DEFAULT_BURST;
+ info->default_txportconf.burst_size = MLX5_TX_DEFAULT_BURST;
+ if ((priv->link_speed_capa & RTE_ETH_LINK_SPEED_200G) |
+ (priv->link_speed_capa & RTE_ETH_LINK_SPEED_100G)) {
info->default_rxportconf.nb_queues = 16;
info->default_txportconf.nb_queues = 16;
if (dev->data->nb_rx_queues > 2 ||
}
}
+/**
+ * Sets tx mbuf limiting parameters.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param[out] info
+ * Info structure output buffer.
+ */
+static void
+mlx5_set_txlimit_params(struct rte_eth_dev *dev, struct rte_eth_dev_info *info)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_port_config *config = &priv->config;
+ unsigned int inlen;
+ uint16_t nb_max;
+
+ inlen = (config->txq_inline_max == MLX5_ARG_UNSET) ?
+ MLX5_SEND_DEF_INLINE_LEN :
+ (unsigned int)config->txq_inline_max;
+ MLX5_ASSERT(config->txq_inline_min >= 0);
+ inlen = RTE_MAX(inlen, (unsigned int)config->txq_inline_min);
+ inlen = RTE_MIN(inlen, MLX5_WQE_SIZE_MAX +
+ MLX5_ESEG_MIN_INLINE_SIZE -
+ MLX5_WQE_CSEG_SIZE -
+ MLX5_WQE_ESEG_SIZE -
+ MLX5_WQE_DSEG_SIZE * 2);
+ nb_max = (MLX5_WQE_SIZE_MAX +
+ MLX5_ESEG_MIN_INLINE_SIZE -
+ MLX5_WQE_CSEG_SIZE -
+ MLX5_WQE_ESEG_SIZE -
+ MLX5_WQE_DSEG_SIZE -
+ inlen) / MLX5_WSEG_SIZE;
+ info->tx_desc_lim.nb_seg_max = nb_max;
+ info->tx_desc_lim.nb_mtu_seg_max = nb_max;
+}
+
/**
* DPDK callback to get information about the device.
*
* @param[out] info
* Info structure output buffer.
*/
-void
+int
mlx5_dev_infos_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *info)
{
struct mlx5_priv *priv = dev->data->dev_private;
- struct mlx5_dev_config *config = &priv->config;
unsigned int max;
- char ifname[IF_NAMESIZE];
/* FIXME: we should ask the device for these values. */
info->min_rx_bufsize = 32;
info->max_rx_pktlen = 65536;
+ info->max_lro_pkt_size = MLX5_MAX_LRO_SIZE;
/*
* Since we need one CQ per QP, the limit is the minimum number
* between the two values.
*/
- max = RTE_MIN(priv->sh->device_attr.orig_attr.max_cq,
- priv->sh->device_attr.orig_attr.max_qp);
- /* If max >= 65535 then max = 0, max_rx_queues is uint16_t. */
- if (max >= 65535)
- max = 65535;
+ max = RTE_MIN(priv->sh->dev_cap.max_cq, priv->sh->dev_cap.max_qp);
+ /* max_rx_queues is uint16_t. */
+ max = RTE_MIN(max, (unsigned int)UINT16_MAX);
info->max_rx_queues = max;
info->max_tx_queues = max;
info->max_mac_addrs = MLX5_MAX_UC_MAC_ADDRESSES;
info->rx_queue_offload_capa = mlx5_get_rx_queue_offloads(dev);
+ info->rx_seg_capa.max_nseg = MLX5_MAX_RXQ_NSEG;
+ info->rx_seg_capa.multi_pools = !priv->config.mprq.enabled;
+ info->rx_seg_capa.offset_allowed = !priv->config.mprq.enabled;
+ info->rx_seg_capa.offset_align_log2 = 0;
info->rx_offload_capa = (mlx5_get_rx_port_offloads() |
info->rx_queue_offload_capa);
info->tx_offload_capa = mlx5_get_tx_port_offloads(dev);
- if (mlx5_get_ifname(dev, &ifname) == 0)
- info->if_index = if_nametoindex(ifname);
+ info->dev_capa = RTE_ETH_DEV_CAPA_FLOW_SHARED_OBJECT_KEEP;
+ info->if_index = mlx5_ifindex(dev);
info->reta_size = priv->reta_idx_n ?
- priv->reta_idx_n : config->ind_table_max_size;
+ priv->reta_idx_n : priv->sh->dev_cap.ind_table_max_size;
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);
+ mlx5_set_txlimit_params(dev, info);
+ if (priv->sh->cdev->config.hca_attr.mem_rq_rmp &&
+ priv->obj_ops.rxq_obj_new == devx_obj_ops.rxq_obj_new)
+ info->dev_capa |= RTE_ETH_DEV_CAPA_RXQ_SHARE;
info->switch_info.name = dev->data->name;
info->switch_info.domain_id = priv->domain_id;
info->switch_info.port_id = priv->representor_id;
+ info->switch_info.rx_domain = 0; /* No sub Rx domains. */
if (priv->representor) {
- unsigned int i = mlx5_dev_to_port_id(dev->device, NULL, 0);
- uint16_t port_id[i];
+ uint16_t port_id;
- i = RTE_MIN(mlx5_dev_to_port_id(dev->device, port_id, i), i);
- while (i--) {
+ MLX5_ETH_FOREACH_DEV(port_id, dev->device) {
struct mlx5_priv *opriv =
- rte_eth_devices[port_id[i]].data->dev_private;
+ rte_eth_devices[port_id].data->dev_private;
if (!opriv ||
opriv->representor ||
+ opriv->sh != priv->sh ||
opriv->domain_id != priv->domain_id)
continue;
/*
break;
}
}
+ return 0;
+}
+
+/**
+ * Calculate representor ID from port switch info.
+ *
+ * Uint16 representor ID bits definition:
+ * pf: 2
+ * type: 2
+ * vf/sf: 12
+ *
+ * @param info
+ * Port switch info.
+ * @param hpf_type
+ * Use this type if port is HPF.
+ *
+ * @return
+ * Encoded representor ID.
+ */
+uint16_t
+mlx5_representor_id_encode(const struct mlx5_switch_info *info,
+ enum rte_eth_representor_type hpf_type)
+{
+ enum rte_eth_representor_type type = RTE_ETH_REPRESENTOR_VF;
+ uint16_t repr = info->port_name;
+
+ if (info->representor == 0)
+ return UINT16_MAX;
+ if (info->name_type == MLX5_PHYS_PORT_NAME_TYPE_PFSF)
+ type = RTE_ETH_REPRESENTOR_SF;
+ if (info->name_type == MLX5_PHYS_PORT_NAME_TYPE_PFHPF) {
+ type = hpf_type;
+ repr = UINT16_MAX;
+ }
+ return MLX5_REPRESENTOR_ID(info->pf_num, type, repr);
}
/**
- * Get device current raw clock counter
+ * DPDK callback to get information about representor.
+ *
+ * Representor ID bits definition:
+ * vf/sf: 12
+ * type: 2
+ * pf: 2
*
* @param dev
* Pointer to Ethernet device structure.
- * @param[out] time
- * Current raw clock counter of the device.
+ * @param[out] info
+ * Nullable info structure output buffer.
*
* @return
- * 0 if the clock has correctly been read
- * The value of errno in case of error
+ * negative on error, or the number of representor ranges.
*/
int
-mlx5_read_clock(struct rte_eth_dev *dev, uint64_t *clock)
+mlx5_representor_info_get(struct rte_eth_dev *dev,
+ struct rte_eth_representor_info *info)
{
struct mlx5_priv *priv = dev->data->dev_private;
- struct ibv_context *ctx = priv->sh->ctx;
- struct ibv_values_ex values;
- int err = 0;
-
- values.comp_mask = IBV_VALUES_MASK_RAW_CLOCK;
- err = mlx5_glue->query_rt_values_ex(ctx, &values);
- if (err != 0) {
- DRV_LOG(WARNING, "Could not query the clock !");
- return err;
+ int n_type = 4; /* Representor types, VF, HPF@VF, SF and HPF@SF. */
+ int n_pf = 2; /* Number of PFs. */
+ int i = 0, pf;
+ int n_entries;
+
+ if (info == NULL)
+ goto out;
+
+ n_entries = n_type * n_pf;
+ if ((uint32_t)n_entries > info->nb_ranges_alloc)
+ n_entries = info->nb_ranges_alloc;
+
+ info->controller = 0;
+ info->pf = priv->pf_bond >= 0 ? priv->pf_bond : 0;
+ for (pf = 0; pf < n_pf; ++pf) {
+ /* VF range. */
+ info->ranges[i].type = RTE_ETH_REPRESENTOR_VF;
+ info->ranges[i].controller = 0;
+ info->ranges[i].pf = pf;
+ info->ranges[i].vf = 0;
+ info->ranges[i].id_base =
+ MLX5_REPRESENTOR_ID(pf, info->ranges[i].type, 0);
+ info->ranges[i].id_end =
+ MLX5_REPRESENTOR_ID(pf, info->ranges[i].type, -1);
+ snprintf(info->ranges[i].name,
+ sizeof(info->ranges[i].name), "pf%dvf", pf);
+ i++;
+ if (i == n_entries)
+ break;
+ /* HPF range of VF type. */
+ info->ranges[i].type = RTE_ETH_REPRESENTOR_VF;
+ info->ranges[i].controller = 0;
+ info->ranges[i].pf = pf;
+ info->ranges[i].vf = UINT16_MAX;
+ info->ranges[i].id_base =
+ MLX5_REPRESENTOR_ID(pf, info->ranges[i].type, -1);
+ info->ranges[i].id_end =
+ MLX5_REPRESENTOR_ID(pf, info->ranges[i].type, -1);
+ snprintf(info->ranges[i].name,
+ sizeof(info->ranges[i].name), "pf%dvf", pf);
+ i++;
+ if (i == n_entries)
+ break;
+ /* SF range. */
+ info->ranges[i].type = RTE_ETH_REPRESENTOR_SF;
+ info->ranges[i].controller = 0;
+ info->ranges[i].pf = pf;
+ info->ranges[i].vf = 0;
+ info->ranges[i].id_base =
+ MLX5_REPRESENTOR_ID(pf, info->ranges[i].type, 0);
+ info->ranges[i].id_end =
+ MLX5_REPRESENTOR_ID(pf, info->ranges[i].type, -1);
+ snprintf(info->ranges[i].name,
+ sizeof(info->ranges[i].name), "pf%dsf", pf);
+ i++;
+ if (i == n_entries)
+ break;
+ /* HPF range of SF type. */
+ info->ranges[i].type = RTE_ETH_REPRESENTOR_SF;
+ info->ranges[i].controller = 0;
+ info->ranges[i].pf = pf;
+ info->ranges[i].vf = UINT16_MAX;
+ info->ranges[i].id_base =
+ MLX5_REPRESENTOR_ID(pf, info->ranges[i].type, -1);
+ info->ranges[i].id_end =
+ MLX5_REPRESENTOR_ID(pf, info->ranges[i].type, -1);
+ snprintf(info->ranges[i].name,
+ sizeof(info->ranges[i].name), "pf%dsf", pf);
+ i++;
+ if (i == n_entries)
+ break;
}
- *clock = values.raw_clock.tv_nsec;
- return 0;
+ info->nb_ranges = i;
+out:
+ return n_type * n_pf;
}
/**
* @return
* 0 on success, or the size of the non truncated string if too big.
*/
-int mlx5_fw_version_get(struct rte_eth_dev *dev, char *fw_ver, size_t fw_size)
+int
+mlx5_fw_version_get(struct rte_eth_dev *dev, char *fw_ver, size_t fw_size)
{
struct mlx5_priv *priv = dev->data->dev_private;
- struct ibv_device_attr *attr = &priv->sh->device_attr.orig_attr;
+ struct mlx5_dev_cap *attr = &priv->sh->dev_cap;
size_t size = strnlen(attr->fw_ver, sizeof(attr->fw_ver)) + 1;
if (fw_size < size)
if (dev->rx_pkt_burst == mlx5_rx_burst ||
dev->rx_pkt_burst == mlx5_rx_burst_mprq ||
- dev->rx_pkt_burst == mlx5_rx_burst_vec)
+ dev->rx_pkt_burst == mlx5_rx_burst_vec ||
+ dev->rx_pkt_burst == mlx5_rx_burst_mprq_vec)
return ptypes;
return NULL;
}
/**
- * Retrieve the master device for representor in the same switch domain.
+ * DPDK callback to change the MTU.
*
* @param dev
- * Pointer to representor Ethernet device structure.
+ * Pointer to Ethernet device structure.
+ * @param in_mtu
+ * New MTU.
*
* @return
- * Master device structure on success, NULL otherwise.
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
*/
-
-static struct rte_eth_dev *
-mlx5_find_master_dev(struct rte_eth_dev *dev)
+int
+mlx5_dev_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
{
- struct mlx5_priv *priv;
- uint16_t port_id;
- uint16_t domain_id;
+ struct mlx5_priv *priv = dev->data->dev_private;
+ uint16_t kern_mtu = 0;
+ int ret;
- priv = dev->data->dev_private;
- domain_id = priv->domain_id;
- assert(priv->representor);
- RTE_ETH_FOREACH_DEV_OF(port_id, dev->device) {
- priv = rte_eth_devices[port_id].data->dev_private;
- if (priv &&
- priv->master &&
- priv->domain_id == domain_id)
- return &rte_eth_devices[port_id];
+ ret = mlx5_get_mtu(dev, &kern_mtu);
+ if (ret)
+ return ret;
+ /* Set kernel interface MTU first. */
+ ret = mlx5_set_mtu(dev, mtu);
+ if (ret)
+ return ret;
+ ret = mlx5_get_mtu(dev, &kern_mtu);
+ if (ret)
+ return ret;
+ if (kern_mtu == mtu) {
+ priv->mtu = mtu;
+ DRV_LOG(DEBUG, "port %u adapter MTU set to %u",
+ dev->data->port_id, mtu);
+ return 0;
}
- return NULL;
+ rte_errno = EAGAIN;
+ return -rte_errno;
}
/**
- * DPDK callback to retrieve physical link information.
+ * Configure the RX function to use.
*
* @param dev
- * Pointer to Ethernet device structure.
- * @param[out] link
- * Storage for current link status.
+ * Pointer to private data structure.
*
* @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
+ * Pointer to selected Rx burst function.
*/
-static int
-mlx5_link_update_unlocked_gset(struct rte_eth_dev *dev,
- struct rte_eth_link *link)
+eth_rx_burst_t
+mlx5_select_rx_function(struct rte_eth_dev *dev)
{
- struct mlx5_priv *priv = dev->data->dev_private;
- struct ethtool_cmd edata = {
- .cmd = ETHTOOL_GSET /* Deprecated since Linux v4.5. */
- };
- struct ifreq ifr;
- struct rte_eth_link dev_link;
- int link_speed = 0;
- int ret;
+ eth_rx_burst_t rx_pkt_burst = mlx5_rx_burst;
- ret = mlx5_ifreq(dev, SIOCGIFFLAGS, &ifr);
- if (ret) {
- DRV_LOG(WARNING, "port %u ioctl(SIOCGIFFLAGS) failed: %s",
- dev->data->port_id, strerror(rte_errno));
- return ret;
- }
- dev_link = (struct rte_eth_link) {
- .link_status = ((ifr.ifr_flags & IFF_UP) &&
- (ifr.ifr_flags & IFF_RUNNING)),
- };
- ifr = (struct ifreq) {
- .ifr_data = (void *)&edata,
- };
- ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
- if (ret) {
- if (ret == -ENOTSUP && priv->representor) {
- struct rte_eth_dev *master;
-
- /*
- * For representors we can try to inherit link
- * settings from the master device. Actually
- * link settings do not make a lot of sense
- * for representors due to missing physical
- * link. The old kernel drivers supported
- * emulated settings query for representors,
- * the new ones do not, so we have to add
- * this code for compatibility issues.
- */
- master = mlx5_find_master_dev(dev);
- if (master) {
- ifr = (struct ifreq) {
- .ifr_data = (void *)&edata,
- };
- ret = mlx5_ifreq(master, SIOCETHTOOL, &ifr);
- }
- }
- if (ret) {
- DRV_LOG(WARNING,
- "port %u ioctl(SIOCETHTOOL,"
- " ETHTOOL_GSET) failed: %s",
- dev->data->port_id, strerror(rte_errno));
- return ret;
- }
- }
- link_speed = ethtool_cmd_speed(&edata);
- if (link_speed == -1)
- dev_link.link_speed = ETH_SPEED_NUM_NONE;
- else
- dev_link.link_speed = link_speed;
- priv->link_speed_capa = 0;
- if (edata.supported & SUPPORTED_Autoneg)
- priv->link_speed_capa |= ETH_LINK_SPEED_AUTONEG;
- if (edata.supported & (SUPPORTED_1000baseT_Full |
- SUPPORTED_1000baseKX_Full))
- priv->link_speed_capa |= ETH_LINK_SPEED_1G;
- if (edata.supported & SUPPORTED_10000baseKR_Full)
- priv->link_speed_capa |= ETH_LINK_SPEED_10G;
- if (edata.supported & (SUPPORTED_40000baseKR4_Full |
- SUPPORTED_40000baseCR4_Full |
- SUPPORTED_40000baseSR4_Full |
- SUPPORTED_40000baseLR4_Full))
- priv->link_speed_capa |= ETH_LINK_SPEED_40G;
- dev_link.link_duplex = ((edata.duplex == DUPLEX_HALF) ?
- ETH_LINK_HALF_DUPLEX : ETH_LINK_FULL_DUPLEX);
- dev_link.link_autoneg = !(dev->data->dev_conf.link_speeds &
- ETH_LINK_SPEED_FIXED);
- if (((dev_link.link_speed && !dev_link.link_status) ||
- (!dev_link.link_speed && dev_link.link_status))) {
- rte_errno = EAGAIN;
- return -rte_errno;
- }
- *link = dev_link;
- return 0;
-}
-
-/**
- * Retrieve physical link information (unlocked version using new ioctl).
- *
- * @param dev
- * Pointer to Ethernet device structure.
- * @param[out] link
- * Storage for current link status.
- *
- * @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
- */
-static int
-mlx5_link_update_unlocked_gs(struct rte_eth_dev *dev,
- struct rte_eth_link *link)
-
-{
- struct mlx5_priv *priv = dev->data->dev_private;
- struct ethtool_link_settings gcmd = { .cmd = ETHTOOL_GLINKSETTINGS };
- struct ifreq ifr;
- struct rte_eth_link dev_link;
- struct rte_eth_dev *master = NULL;
- uint64_t sc;
- int ret;
-
- ret = mlx5_ifreq(dev, SIOCGIFFLAGS, &ifr);
- if (ret) {
- DRV_LOG(WARNING, "port %u ioctl(SIOCGIFFLAGS) failed: %s",
- dev->data->port_id, strerror(rte_errno));
- return ret;
- }
- dev_link = (struct rte_eth_link) {
- .link_status = ((ifr.ifr_flags & IFF_UP) &&
- (ifr.ifr_flags & IFF_RUNNING)),
- };
- ifr = (struct ifreq) {
- .ifr_data = (void *)&gcmd,
- };
- ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
- if (ret) {
- if (ret == -ENOTSUP && priv->representor) {
- /*
- * For representors we can try to inherit link
- * settings from the master device. Actually
- * link settings do not make a lot of sense
- * for representors due to missing physical
- * link. The old kernel drivers supported
- * emulated settings query for representors,
- * the new ones do not, so we have to add
- * this code for compatibility issues.
- */
- master = mlx5_find_master_dev(dev);
- if (master) {
- ifr = (struct ifreq) {
- .ifr_data = (void *)&gcmd,
- };
- ret = mlx5_ifreq(master, SIOCETHTOOL, &ifr);
- }
- }
- if (ret) {
- DRV_LOG(DEBUG,
- "port %u ioctl(SIOCETHTOOL,"
- " ETHTOOL_GLINKSETTINGS) failed: %s",
- dev->data->port_id, strerror(rte_errno));
- return ret;
- }
-
- }
- gcmd.link_mode_masks_nwords = -gcmd.link_mode_masks_nwords;
-
- alignas(struct ethtool_link_settings)
- uint8_t data[offsetof(struct ethtool_link_settings, link_mode_masks) +
- sizeof(uint32_t) * gcmd.link_mode_masks_nwords * 3];
- struct ethtool_link_settings *ecmd = (void *)data;
-
- *ecmd = gcmd;
- ifr.ifr_data = (void *)ecmd;
- ret = mlx5_ifreq(master ? master : dev, SIOCETHTOOL, &ifr);
- if (ret) {
- DRV_LOG(DEBUG,
- "port %u ioctl(SIOCETHTOOL,"
- "ETHTOOL_GLINKSETTINGS) failed: %s",
- dev->data->port_id, strerror(rte_errno));
- return ret;
- }
- dev_link.link_speed = ecmd->speed;
- sc = ecmd->link_mode_masks[0] |
- ((uint64_t)ecmd->link_mode_masks[1] << 32);
- priv->link_speed_capa = 0;
- if (sc & MLX5_BITSHIFT(ETHTOOL_LINK_MODE_Autoneg_BIT))
- priv->link_speed_capa |= ETH_LINK_SPEED_AUTONEG;
- if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_1000baseT_Full_BIT) |
- MLX5_BITSHIFT(ETHTOOL_LINK_MODE_1000baseKX_Full_BIT)))
- priv->link_speed_capa |= ETH_LINK_SPEED_1G;
- if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT) |
- MLX5_BITSHIFT(ETHTOOL_LINK_MODE_10000baseKR_Full_BIT) |
- MLX5_BITSHIFT(ETHTOOL_LINK_MODE_10000baseR_FEC_BIT)))
- priv->link_speed_capa |= ETH_LINK_SPEED_10G;
- if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT) |
- MLX5_BITSHIFT(ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT)))
- priv->link_speed_capa |= ETH_LINK_SPEED_20G;
- if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT) |
- MLX5_BITSHIFT(ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT) |
- MLX5_BITSHIFT(ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT) |
- MLX5_BITSHIFT(ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT)))
- priv->link_speed_capa |= ETH_LINK_SPEED_40G;
- if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT) |
- MLX5_BITSHIFT(ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT) |
- MLX5_BITSHIFT(ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT) |
- MLX5_BITSHIFT(ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT)))
- priv->link_speed_capa |= ETH_LINK_SPEED_56G;
- if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_25000baseCR_Full_BIT) |
- MLX5_BITSHIFT(ETHTOOL_LINK_MODE_25000baseKR_Full_BIT) |
- MLX5_BITSHIFT(ETHTOOL_LINK_MODE_25000baseSR_Full_BIT)))
- priv->link_speed_capa |= ETH_LINK_SPEED_25G;
- if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT) |
- MLX5_BITSHIFT(ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT)))
- priv->link_speed_capa |= ETH_LINK_SPEED_50G;
- if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT) |
- MLX5_BITSHIFT(ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT) |
- MLX5_BITSHIFT(ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT) |
- MLX5_BITSHIFT(ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT)))
- priv->link_speed_capa |= ETH_LINK_SPEED_100G;
- dev_link.link_duplex = ((ecmd->duplex == DUPLEX_HALF) ?
- ETH_LINK_HALF_DUPLEX : ETH_LINK_FULL_DUPLEX);
- dev_link.link_autoneg = !(dev->data->dev_conf.link_speeds &
- ETH_LINK_SPEED_FIXED);
- if (((dev_link.link_speed && !dev_link.link_status) ||
- (!dev_link.link_speed && dev_link.link_status))) {
- rte_errno = EAGAIN;
- return -rte_errno;
- }
- *link = dev_link;
- return 0;
-}
-
-/**
- * DPDK callback to retrieve physical link information.
- *
- * @param dev
- * Pointer to Ethernet device structure.
- * @param wait_to_complete
- * Wait for request completion.
- *
- * @return
- * 0 if link status was not updated, positive if it was, a negative errno
- * value otherwise and rte_errno is set.
- */
-int
-mlx5_link_update(struct rte_eth_dev *dev, int wait_to_complete)
-{
- int ret;
- struct rte_eth_link dev_link;
- time_t start_time = time(NULL);
-
- do {
- ret = mlx5_link_update_unlocked_gs(dev, &dev_link);
- if (ret)
- ret = mlx5_link_update_unlocked_gset(dev, &dev_link);
- if (ret == 0)
- break;
- /* Handle wait to complete situation. */
- if (wait_to_complete && ret == -EAGAIN) {
- if (abs((int)difftime(time(NULL), start_time)) <
- MLX5_LINK_STATUS_TIMEOUT) {
- usleep(0);
- continue;
- } else {
- rte_errno = EBUSY;
- return -rte_errno;
- }
- } else if (ret < 0) {
- return ret;
- }
- } while (wait_to_complete);
- ret = !!memcmp(&dev->data->dev_link, &dev_link,
- sizeof(struct rte_eth_link));
- dev->data->dev_link = dev_link;
- return ret;
-}
-
-/**
- * DPDK callback to change the MTU.
- *
- * @param dev
- * Pointer to Ethernet device structure.
- * @param in_mtu
- * New MTU.
- *
- * @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
- */
-int
-mlx5_dev_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
-{
- struct mlx5_priv *priv = dev->data->dev_private;
- uint16_t kern_mtu = 0;
- int ret;
-
- ret = mlx5_get_mtu(dev, &kern_mtu);
- if (ret)
- return ret;
- /* Set kernel interface MTU first. */
- ret = mlx5_set_mtu(dev, mtu);
- if (ret)
- return ret;
- ret = mlx5_get_mtu(dev, &kern_mtu);
- if (ret)
- return ret;
- if (kern_mtu == mtu) {
- priv->mtu = mtu;
- DRV_LOG(DEBUG, "port %u adapter MTU set to %u",
- dev->data->port_id, mtu);
- return 0;
- }
- rte_errno = EAGAIN;
- return -rte_errno;
-}
-
-/**
- * DPDK callback to get flow control status.
- *
- * @param dev
- * Pointer to Ethernet device structure.
- * @param[out] fc_conf
- * Flow control output buffer.
- *
- * @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
- */
-int
-mlx5_dev_get_flow_ctrl(struct rte_eth_dev *dev, struct rte_eth_fc_conf *fc_conf)
-{
- struct ifreq ifr;
- struct ethtool_pauseparam ethpause = {
- .cmd = ETHTOOL_GPAUSEPARAM
- };
- int ret;
-
- ifr.ifr_data = (void *)ðpause;
- ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
- if (ret) {
- DRV_LOG(WARNING,
- "port %u ioctl(SIOCETHTOOL, ETHTOOL_GPAUSEPARAM) failed:"
- " %s",
- dev->data->port_id, strerror(rte_errno));
- return ret;
- }
- fc_conf->autoneg = ethpause.autoneg;
- if (ethpause.rx_pause && ethpause.tx_pause)
- fc_conf->mode = RTE_FC_FULL;
- else if (ethpause.rx_pause)
- fc_conf->mode = RTE_FC_RX_PAUSE;
- else if (ethpause.tx_pause)
- fc_conf->mode = RTE_FC_TX_PAUSE;
- else
- fc_conf->mode = RTE_FC_NONE;
- return 0;
-}
-
-/**
- * DPDK callback to modify flow control parameters.
- *
- * @param dev
- * Pointer to Ethernet device structure.
- * @param[in] fc_conf
- * Flow control parameters.
- *
- * @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
- */
-int
-mlx5_dev_set_flow_ctrl(struct rte_eth_dev *dev, struct rte_eth_fc_conf *fc_conf)
-{
- struct ifreq ifr;
- struct ethtool_pauseparam ethpause = {
- .cmd = ETHTOOL_SPAUSEPARAM
- };
- int ret;
-
- ifr.ifr_data = (void *)ðpause;
- ethpause.autoneg = fc_conf->autoneg;
- if (((fc_conf->mode & RTE_FC_FULL) == RTE_FC_FULL) ||
- (fc_conf->mode & RTE_FC_RX_PAUSE))
- ethpause.rx_pause = 1;
- else
- ethpause.rx_pause = 0;
-
- if (((fc_conf->mode & RTE_FC_FULL) == RTE_FC_FULL) ||
- (fc_conf->mode & RTE_FC_TX_PAUSE))
- ethpause.tx_pause = 1;
- else
- ethpause.tx_pause = 0;
- ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
- if (ret) {
- DRV_LOG(WARNING,
- "port %u ioctl(SIOCETHTOOL, ETHTOOL_SPAUSEPARAM)"
- " failed: %s",
- dev->data->port_id, strerror(rte_errno));
- return ret;
- }
- return 0;
-}
-
-/**
- * Get PCI information from struct ibv_device.
- *
- * @param device
- * Pointer to Ethernet device structure.
- * @param[out] pci_addr
- * PCI bus address output buffer.
- *
- * @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
- */
-int
-mlx5_ibv_device_to_pci_addr(const struct ibv_device *device,
- struct rte_pci_addr *pci_addr)
-{
- FILE *file;
- char line[32];
- MKSTR(path, "%s/device/uevent", device->ibdev_path);
-
- file = fopen(path, "rb");
- if (file == NULL) {
- rte_errno = errno;
- return -rte_errno;
- }
- while (fgets(line, sizeof(line), file) == line) {
- size_t len = strlen(line);
- int ret;
-
- /* Truncate long lines. */
- if (len == (sizeof(line) - 1))
- while (line[(len - 1)] != '\n') {
- ret = fgetc(file);
- if (ret == EOF)
- break;
- line[(len - 1)] = ret;
- }
- /* Extract information. */
- if (sscanf(line,
- "PCI_SLOT_NAME="
- "%" SCNx32 ":%" SCNx8 ":%" SCNx8 ".%" SCNx8 "\n",
- &pci_addr->domain,
- &pci_addr->bus,
- &pci_addr->devid,
- &pci_addr->function) == 4) {
- ret = 0;
- break;
- }
- }
- fclose(file);
- return 0;
-}
-
-/**
- * Handle asynchronous removal event for entire multiport device.
- *
- * @param sh
- * Infiniband device shared context.
- */
-static void
-mlx5_dev_interrupt_device_fatal(struct mlx5_ibv_shared *sh)
-{
- uint32_t i;
-
- for (i = 0; i < sh->max_port; ++i) {
- struct rte_eth_dev *dev;
-
- if (sh->port[i].ih_port_id >= RTE_MAX_ETHPORTS) {
- /*
- * Or not existing port either no
- * handler installed for this port.
- */
- continue;
- }
- dev = &rte_eth_devices[sh->port[i].ih_port_id];
- assert(dev);
- if (dev->data->dev_conf.intr_conf.rmv)
- _rte_eth_dev_callback_process
- (dev, RTE_ETH_EVENT_INTR_RMV, NULL);
- }
-}
-
-/**
- * Handle shared asynchronous events the NIC (removal event
- * and link status change). Supports multiport IB device.
- *
- * @param cb_arg
- * Callback argument.
- */
-void
-mlx5_dev_interrupt_handler(void *cb_arg)
-{
- struct mlx5_ibv_shared *sh = cb_arg;
- struct ibv_async_event event;
-
- /* Read all message from the IB device and acknowledge them. */
- for (;;) {
- struct rte_eth_dev *dev;
- uint32_t tmp;
-
- if (mlx5_glue->get_async_event(sh->ctx, &event))
- break;
- /* Retrieve and check IB port index. */
- tmp = (uint32_t)event.element.port_num;
- if (!tmp && event.event_type == IBV_EVENT_DEVICE_FATAL) {
- /*
- * The DEVICE_FATAL event is called once for
- * entire device without port specifying.
- * We should notify all existing ports.
- */
- mlx5_glue->ack_async_event(&event);
- mlx5_dev_interrupt_device_fatal(sh);
- continue;
- }
- assert(tmp && (tmp <= sh->max_port));
- if (!tmp) {
- /* Unsupported devive level event. */
- mlx5_glue->ack_async_event(&event);
- DRV_LOG(DEBUG,
- "unsupported common event (type %d)",
- event.event_type);
- continue;
- }
- if (tmp > sh->max_port) {
- /* Invalid IB port index. */
- mlx5_glue->ack_async_event(&event);
- DRV_LOG(DEBUG,
- "cannot handle an event (type %d)"
- "due to invalid IB port index (%u)",
- event.event_type, tmp);
- continue;
- }
- if (sh->port[tmp - 1].ih_port_id >= RTE_MAX_ETHPORTS) {
- /* No handler installed. */
- mlx5_glue->ack_async_event(&event);
- DRV_LOG(DEBUG,
- "cannot handle an event (type %d)"
- "due to no handler installed for port %u",
- event.event_type, tmp);
- continue;
- }
- /* Retrieve ethernet device descriptor. */
- tmp = sh->port[tmp - 1].ih_port_id;
- dev = &rte_eth_devices[tmp];
- assert(dev);
- if ((event.event_type == IBV_EVENT_PORT_ACTIVE ||
- event.event_type == IBV_EVENT_PORT_ERR) &&
- dev->data->dev_conf.intr_conf.lsc) {
- mlx5_glue->ack_async_event(&event);
- if (mlx5_link_update(dev, 0) == -EAGAIN) {
- usleep(0);
- continue;
- }
- _rte_eth_dev_callback_process
- (dev, RTE_ETH_EVENT_INTR_LSC, NULL);
- continue;
- }
- DRV_LOG(DEBUG,
- "port %u cannot handle an unknown event (type %d)",
- dev->data->port_id, event.event_type);
- mlx5_glue->ack_async_event(&event);
- }
-}
-
-/**
- * Uninstall shared asynchronous device events handler.
- * This function is implemeted to support event sharing
- * between multiple ports of single IB device.
- *
- * @param dev
- * Pointer to Ethernet device.
- */
-static void
-mlx5_dev_shared_handler_uninstall(struct rte_eth_dev *dev)
-{
- struct mlx5_priv *priv = dev->data->dev_private;
- struct mlx5_ibv_shared *sh = priv->sh;
-
- if (rte_eal_process_type() != RTE_PROC_PRIMARY)
- return;
- pthread_mutex_lock(&sh->intr_mutex);
- assert(priv->ibv_port);
- assert(priv->ibv_port <= sh->max_port);
- assert(dev->data->port_id < RTE_MAX_ETHPORTS);
- if (sh->port[priv->ibv_port - 1].ih_port_id >= RTE_MAX_ETHPORTS)
- goto exit;
- assert(sh->port[priv->ibv_port - 1].ih_port_id ==
- (uint32_t)dev->data->port_id);
- assert(sh->intr_cnt);
- sh->port[priv->ibv_port - 1].ih_port_id = RTE_MAX_ETHPORTS;
- if (!sh->intr_cnt || --sh->intr_cnt)
- goto exit;
- rte_intr_callback_unregister(&sh->intr_handle,
- mlx5_dev_interrupt_handler, sh);
- sh->intr_handle.fd = 0;
- sh->intr_handle.type = RTE_INTR_HANDLE_UNKNOWN;
-exit:
- pthread_mutex_unlock(&sh->intr_mutex);
-}
-
-/**
- * Install shared asyncronous device events handler.
- * This function is implemeted to support event sharing
- * between multiple ports of single IB device.
- *
- * @param dev
- * Pointer to Ethernet device.
- */
-static void
-mlx5_dev_shared_handler_install(struct rte_eth_dev *dev)
-{
- struct mlx5_priv *priv = dev->data->dev_private;
- struct mlx5_ibv_shared *sh = priv->sh;
- int ret;
- int flags;
-
- if (rte_eal_process_type() != RTE_PROC_PRIMARY)
- return;
- pthread_mutex_lock(&sh->intr_mutex);
- assert(priv->ibv_port);
- assert(priv->ibv_port <= sh->max_port);
- assert(dev->data->port_id < RTE_MAX_ETHPORTS);
- if (sh->port[priv->ibv_port - 1].ih_port_id < RTE_MAX_ETHPORTS) {
- /* The handler is already installed for this port. */
- assert(sh->intr_cnt);
- goto exit;
- }
- sh->port[priv->ibv_port - 1].ih_port_id = (uint32_t)dev->data->port_id;
- if (sh->intr_cnt) {
- sh->intr_cnt++;
- goto exit;
- }
- /* No shared handler installed. */
- assert(sh->ctx->async_fd > 0);
- flags = fcntl(sh->ctx->async_fd, F_GETFL);
- ret = fcntl(sh->ctx->async_fd, F_SETFL, flags | O_NONBLOCK);
- if (ret) {
- DRV_LOG(INFO, "failed to change file descriptor"
- " async event queue");
- /* Indicate there will be no interrupts. */
- dev->data->dev_conf.intr_conf.lsc = 0;
- dev->data->dev_conf.intr_conf.rmv = 0;
- sh->port[priv->ibv_port - 1].ih_port_id = RTE_MAX_ETHPORTS;
- goto exit;
- }
- sh->intr_handle.fd = sh->ctx->async_fd;
- sh->intr_handle.type = RTE_INTR_HANDLE_EXT;
- rte_intr_callback_register(&sh->intr_handle,
- mlx5_dev_interrupt_handler, sh);
- sh->intr_cnt++;
-exit:
- pthread_mutex_unlock(&sh->intr_mutex);
-}
-
-/**
- * Uninstall interrupt handler.
- *
- * @param dev
- * Pointer to Ethernet device.
- */
-void
-mlx5_dev_interrupt_handler_uninstall(struct rte_eth_dev *dev)
-{
- mlx5_dev_shared_handler_uninstall(dev);
-}
-
-/**
- * Install interrupt handler.
- *
- * @param dev
- * Pointer to Ethernet device.
- */
-void
-mlx5_dev_interrupt_handler_install(struct rte_eth_dev *dev)
-{
- mlx5_dev_shared_handler_install(dev);
-}
-
-/**
- * DPDK callback to bring the link DOWN.
- *
- * @param dev
- * Pointer to Ethernet device structure.
- *
- * @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
- */
-int
-mlx5_set_link_down(struct rte_eth_dev *dev)
-{
- return mlx5_set_flags(dev, ~IFF_UP, ~IFF_UP);
-}
-
-/**
- * DPDK callback to bring the link UP.
- *
- * @param dev
- * Pointer to Ethernet device structure.
- *
- * @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
- */
-int
-mlx5_set_link_up(struct rte_eth_dev *dev)
-{
- return mlx5_set_flags(dev, ~IFF_UP, IFF_UP);
-}
-
-/**
- * Configure the TX function to use.
- *
- * @param dev
- * Pointer to private data structure.
- *
- * @return
- * Pointer to selected Tx burst function.
- */
-eth_tx_burst_t
-mlx5_select_tx_function(struct rte_eth_dev *dev)
-{
- struct mlx5_priv *priv = dev->data->dev_private;
- eth_tx_burst_t tx_pkt_burst = mlx5_tx_burst;
- struct mlx5_dev_config *config = &priv->config;
- 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_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 || swp)
- return tx_pkt_burst;
- if (config->mps == MLX5_MPW_ENHANCED) {
- if (mlx5_check_vec_tx_support(dev) > 0) {
- if (mlx5_check_raw_vec_tx_support(dev) > 0)
- tx_pkt_burst = mlx5_tx_burst_raw_vec;
- else
- tx_pkt_burst = mlx5_tx_burst_vec;
- DRV_LOG(DEBUG,
- "port %u selected enhanced MPW Tx vectorized"
- " function",
- dev->data->port_id);
+ MLX5_ASSERT(dev != NULL);
+ if (mlx5_check_vec_rx_support(dev) > 0) {
+ if (mlx5_mprq_enabled(dev)) {
+ rx_pkt_burst = mlx5_rx_burst_mprq_vec;
+ DRV_LOG(DEBUG, "port %u selected vectorized"
+ " MPRQ Rx function", dev->data->port_id);
} else {
- tx_pkt_burst = mlx5_tx_burst_empw;
- DRV_LOG(DEBUG,
- "port %u selected enhanced MPW Tx function",
- dev->data->port_id);
+ rx_pkt_burst = mlx5_rx_burst_vec;
+ DRV_LOG(DEBUG, "port %u selected vectorized"
+ " SPRQ Rx function", dev->data->port_id);
}
- } else if (config->mps && (config->txq_inline > 0)) {
- tx_pkt_burst = mlx5_tx_burst_mpw_inline;
- DRV_LOG(DEBUG, "port %u selected MPW inline Tx function",
- dev->data->port_id);
- } else if (config->mps) {
- tx_pkt_burst = mlx5_tx_burst_mpw;
- DRV_LOG(DEBUG, "port %u selected MPW Tx function",
- dev->data->port_id);
- }
- return tx_pkt_burst;
-}
-
-/**
- * Configure the RX function to use.
- *
- * @param dev
- * Pointer to private data structure.
- *
- * @return
- * Pointer to selected Rx burst function.
- */
-eth_rx_burst_t
-mlx5_select_rx_function(struct rte_eth_dev *dev)
-{
- eth_rx_burst_t rx_pkt_burst = mlx5_rx_burst;
-
- assert(dev != NULL);
- if (mlx5_check_vec_rx_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;
+ DRV_LOG(DEBUG, "port %u selected MPRQ Rx function",
+ dev->data->port_id);
+ } else {
+ DRV_LOG(DEBUG, "port %u selected SPRQ Rx function",
+ dev->data->port_id);
}
return rx_pkt_burst;
}
/**
- * Check if mlx5 device was removed.
- *
- * @param dev
- * Pointer to Ethernet device structure.
- *
- * @return
- * 1 when device is removed, otherwise 0.
- */
-int
-mlx5_is_removed(struct rte_eth_dev *dev)
-{
- struct ibv_device_attr device_attr;
- struct mlx5_priv *priv = dev->data->dev_private;
-
- if (mlx5_glue->query_device(priv->sh->ctx, &device_attr) == EIO)
- 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_OF(id, dev) {
- if (n < port_list_n)
- port_list[n] = id;
- n++;
- }
- return n;
-}
-
-/**
- * Get the E-Switch domain id this port belongs to.
+ * Get the E-Switch parameters by port id.
*
* @param[in] port
* Device port id.
+ * @param[in] valid
+ * Device port id is valid, skip check. This flag is useful
+ * when trials are performed from probing and device is not
+ * flagged as valid yet (in attaching process).
* @param[out] es_domain_id
* E-Switch domain id.
* @param[out] es_port_id
* The port id of the port in the E-Switch.
*
* @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
+ * pointer to device private data structure containing data needed
+ * on success, NULL otherwise and rte_errno is set.
*/
-int
-mlx5_port_to_eswitch_info(uint16_t port,
- uint16_t *es_domain_id, uint16_t *es_port_id)
+struct mlx5_priv *
+mlx5_port_to_eswitch_info(uint16_t port, bool valid)
{
struct rte_eth_dev *dev;
struct mlx5_priv *priv;
if (port >= RTE_MAX_ETHPORTS) {
rte_errno = EINVAL;
- return -rte_errno;
+ return NULL;
}
- if (!rte_eth_dev_is_valid_port(port)) {
+ if (!valid && !rte_eth_dev_is_valid_port(port)) {
rte_errno = ENODEV;
- return -rte_errno;
+ return NULL;
}
dev = &rte_eth_devices[port];
priv = dev->data->dev_private;
- if (!(priv->representor || priv->master)) {
+ if (!priv->sh->esw_mode) {
rte_errno = EINVAL;
- return -rte_errno;
- }
- if (es_domain_id)
- *es_domain_id = priv->domain_id;
- if (es_port_id)
- *es_port_id = priv->vport_id;
- return 0;
-}
-
-/**
- * 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];
- char port_name[IF_NAMESIZE];
- FILE *file;
- struct mlx5_switch_info data = {
- .master = 0,
- .representor = 0,
- .name_type = MLX5_PHYS_PORT_NAME_TYPE_NOTSET,
- .port_name = 0,
- .switch_id = 0,
- };
- DIR *dir;
- bool port_switch_id_set = false;
- bool device_dir = false;
- char c;
- int ret;
-
- 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);
- MKSTR(pci_device, "/sys/class/net/%s/device",
- ifname);
-
- file = fopen(phys_port_name, "rb");
- if (file != NULL) {
- ret = fscanf(file, "%s", port_name);
- fclose(file);
- if (ret == 1)
- mlx5_translate_port_name(port_name, &data);
- }
- file = fopen(phys_switch_id, "rb");
- if (file == NULL) {
- rte_errno = errno;
- return -rte_errno;
+ return NULL;
}
- port_switch_id_set =
- fscanf(file, "%" SCNx64 "%c", &data.switch_id, &c) == 2 &&
- c == '\n';
- fclose(file);
- dir = opendir(pci_device);
- if (dir != NULL) {
- closedir(dir);
- device_dir = true;
- }
- if (port_switch_id_set) {
- /* We have some E-Switch configuration. */
- mlx5_sysfs_check_switch_info(device_dir, &data);
- }
- *info = data;
- assert(!(data.master && data.representor));
- if (data.master && data.representor) {
- DRV_LOG(ERR, "ifindex %u device is recognized as master"
- " and as representor", ifindex);
- rte_errno = ENODEV;
- return -rte_errno;
- }
- return 0;
+ return priv;
}
/**
- * Analyze gathered port parameters via Netlink to recognize master
- * and representor devices for E-Switch configuration.
+ * Get the E-Switch parameters by device instance.
*
- * @param[in] num_vf_set
- * flag of presence of number of VFs port attribute.
- * @param[inout] switch_info
- * Port information, including port name as a number and port name
- * type if recognized
+ * @param[in] port
+ * Device port id.
+ * @param[out] es_domain_id
+ * E-Switch domain id.
+ * @param[out] es_port_id
+ * The port id of the port in the E-Switch.
*
* @return
- * master and representor flags are set in switch_info according to
- * recognized parameters (if any).
+ * pointer to device private data structure containing data needed
+ * on success, NULL otherwise and rte_errno is set.
*/
-void
-mlx5_nl_check_switch_info(bool num_vf_set,
- struct mlx5_switch_info *switch_info)
+struct mlx5_priv *
+mlx5_dev_to_eswitch_info(struct rte_eth_dev *dev)
{
- switch (switch_info->name_type) {
- case MLX5_PHYS_PORT_NAME_TYPE_UNKNOWN:
- /*
- * Name is not recognized, assume the master,
- * check the number of VFs key presence.
- */
- switch_info->master = num_vf_set;
- break;
- case MLX5_PHYS_PORT_NAME_TYPE_NOTSET:
- /*
- * Name is not set, this assumes the legacy naming
- * schema for master, just check if there is a
- * number of VFs key.
- */
- switch_info->master = num_vf_set;
- break;
- case MLX5_PHYS_PORT_NAME_TYPE_UPLINK:
- /* New uplink naming schema recognized. */
- switch_info->master = 1;
- break;
- case MLX5_PHYS_PORT_NAME_TYPE_LEGACY:
- /* Legacy representors naming schema. */
- switch_info->representor = !num_vf_set;
- break;
- case MLX5_PHYS_PORT_NAME_TYPE_PFVF:
- /* New representors naming schema. */
- switch_info->representor = 1;
- break;
- }
-}
+ struct mlx5_priv *priv;
-/**
- * Analyze gathered port parameters via sysfs to recognize master
- * and representor devices for E-Switch configuration.
- *
- * @param[in] device_dir
- * flag of presence of "device" directory under port device key.
- * @param[inout] switch_info
- * Port information, including port name as a number and port name
- * type if recognized
- *
- * @return
- * master and representor flags are set in switch_info according to
- * recognized parameters (if any).
- */
-void
-mlx5_sysfs_check_switch_info(bool device_dir,
- struct mlx5_switch_info *switch_info)
-{
- switch (switch_info->name_type) {
- case MLX5_PHYS_PORT_NAME_TYPE_UNKNOWN:
- /*
- * Name is not recognized, assume the master,
- * check the device directory presence.
- */
- switch_info->master = device_dir;
- break;
- case MLX5_PHYS_PORT_NAME_TYPE_NOTSET:
- /*
- * Name is not set, this assumes the legacy naming
- * schema for master, just check if there is
- * a device directory.
- */
- switch_info->master = device_dir;
- break;
- case MLX5_PHYS_PORT_NAME_TYPE_UPLINK:
- /* New uplink naming schema recognized. */
- switch_info->master = 1;
- break;
- case MLX5_PHYS_PORT_NAME_TYPE_LEGACY:
- /* Legacy representors naming schema. */
- switch_info->representor = !device_dir;
- break;
- case MLX5_PHYS_PORT_NAME_TYPE_PFVF:
- /* New representors naming schema. */
- switch_info->representor = 1;
- break;
+ priv = dev->data->dev_private;
+ if (!priv->sh->esw_mode) {
+ rte_errno = EINVAL;
+ return NULL;
}
+ return priv;
}
/**
- * Extract port name, as a number, from sysfs or netlink information.
+ * DPDK callback to retrieve hairpin capabilities.
*
- * @param[in] port_name_in
- * String representing the port name.
- * @param[out] port_info_out
- * Port information, including port name as a number and port name
- * type if recognized
+ * @param dev
+ * Pointer to Ethernet device structure.
+ * @param[out] cap
+ * Storage for hairpin capability data.
*
* @return
- * port_name field set according to recognized name format.
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
*/
-void
-mlx5_translate_port_name(const char *port_name_in,
- struct mlx5_switch_info *port_info_out)
+int
+mlx5_hairpin_cap_get(struct rte_eth_dev *dev, struct rte_eth_hairpin_cap *cap)
{
- char pf_c1, pf_c2, vf_c1, vf_c2;
- char *end;
- int sc_items;
+ struct mlx5_priv *priv = dev->data->dev_private;
- /*
- * Check for port-name as a string of the form pf0vf0
- * (support kernel ver >= 5.0 or OFED ver >= 4.6).
- */
- sc_items = sscanf(port_name_in, "%c%c%d%c%c%d",
- &pf_c1, &pf_c2, &port_info_out->pf_num,
- &vf_c1, &vf_c2, &port_info_out->port_name);
- if (sc_items == 6 &&
- pf_c1 == 'p' && pf_c2 == 'f' &&
- vf_c1 == 'v' && vf_c2 == 'f') {
- port_info_out->name_type = MLX5_PHYS_PORT_NAME_TYPE_PFVF;
- return;
- }
- /*
- * Check for port-name as a string of the form p0
- * (support kernel ver >= 5.0, or OFED ver >= 4.6).
- */
- sc_items = sscanf(port_name_in, "%c%d",
- &pf_c1, &port_info_out->port_name);
- if (sc_items == 2 && pf_c1 == 'p') {
- port_info_out->name_type = MLX5_PHYS_PORT_NAME_TYPE_UPLINK;
- return;
- }
- /* Check for port-name as a number (support kernel ver < 5.0 */
- errno = 0;
- port_info_out->port_name = strtol(port_name_in, &end, 0);
- if (!errno &&
- (size_t)(end - port_name_in) == strlen(port_name_in)) {
- port_info_out->name_type = MLX5_PHYS_PORT_NAME_TYPE_LEGACY;
- return;
+ if (!mlx5_devx_obj_ops_en(priv->sh)) {
+ rte_errno = ENOTSUP;
+ return -rte_errno;
}
- port_info_out->name_type = MLX5_PHYS_PORT_NAME_TYPE_UNKNOWN;
- return;
+ cap->max_nb_queues = UINT16_MAX;
+ cap->max_rx_2_tx = 1;
+ cap->max_tx_2_rx = 1;
+ cap->max_nb_desc = 8192;
+ return 0;
}