[dpdk-dev] [PATCH v1 4/8] net/mlx5: split mlx5 ethdev under Linux directory

Ophir Munk ophirmu at mellanox.com
Wed Jun 10 11:32:29 CEST 2020


File mlx5_ethdev.c is partially moved to linux/mlx5_ethdev_os.c for
functions which are Linux specific. Functions which are Linux agnostics
remain in mlx5_ethdev.c file.

Signed-off-by: Ophir Munk <ophirmu at mellanox.com>
---
 drivers/net/mlx5/Makefile               |    1 +
 drivers/net/mlx5/linux/meson.build      |    1 +
 drivers/net/mlx5/linux/mlx5_ethdev_os.c | 1270 +++++++++++++++++++++++++++++++
 drivers/net/mlx5/mlx5.h                 |   20 +-
 drivers/net/mlx5/mlx5_ethdev.c          | 1257 +-----------------------------
 5 files changed, 1291 insertions(+), 1258 deletions(-)
 create mode 100644 drivers/net/mlx5/linux/mlx5_ethdev_os.c

diff --git a/drivers/net/mlx5/Makefile b/drivers/net/mlx5/Makefile
index 84fc9cc..fada6fb 100644
--- a/drivers/net/mlx5/Makefile
+++ b/drivers/net/mlx5/Makefile
@@ -33,6 +33,7 @@ SRCS-$(CONFIG_RTE_LIBRTE_MLX5_PMD) += mlx5_mp.c
 SRCS-$(CONFIG_RTE_LIBRTE_MLX5_PMD) += mlx5_utils.c
 SRCS-$(CONFIG_RTE_LIBRTE_MLX5_PMD) += linux/mlx5_socket.c
 SRCS-$(CONFIG_RTE_LIBRTE_MLX5_PMD) += linux/mlx5_os.c
+SRCS-$(CONFIG_RTE_LIBRTE_MLX5_PMD) += linux/mlx5_ethdev_os.c
 
 # Basic CFLAGS.
 CFLAGS += -O3
diff --git a/drivers/net/mlx5/linux/meson.build b/drivers/net/mlx5/linux/meson.build
index f8369cc..ad908c4 100644
--- a/drivers/net/mlx5/linux/meson.build
+++ b/drivers/net/mlx5/linux/meson.build
@@ -5,5 +5,6 @@ includes += include_directories('.')
 sources += files(
 	'mlx5_socket.c',
 	'mlx5_os.c',
+	'mlx5_ethdev_os.c',
 )
 
diff --git a/drivers/net/mlx5/linux/mlx5_ethdev_os.c b/drivers/net/mlx5/linux/mlx5_ethdev_os.c
new file mode 100644
index 0000000..e4f1516
--- /dev/null
+++ b/drivers/net/mlx5/linux/mlx5_ethdev_os.c
@@ -0,0 +1,1270 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2015 6WIND S.A.
+ * Copyright 2015 Mellanox Technologies, Ltd
+ */
+
+#include <stddef.h>
+#include <inttypes.h>
+#include <unistd.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <string.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 <rte_bus_pci.h>
+#include <rte_mbuf.h>
+#include <rte_common.h>
+#include <rte_interrupts.h>
+#include <rte_malloc.h>
+#include <rte_string_fns.h>
+#include <rte_rwlock.h>
+#include <rte_cycles.h>
+
+#include <mlx5_glue.h>
+#include <mlx5_devx_cmds.h>
+#include <mlx5_common.h>
+
+#include "mlx5.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[];
+};
+
+/* The kernel values can be found in /include/uapi/linux/ethtool.h */
+#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
+#ifndef HAVE_ETHTOOL_LINK_MODE_200G
+#define ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT 62
+#define ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT 63
+#define ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT 0 /* 64 - 64 */
+#define ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT 1 /* 65 - 64 */
+#define ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT 2 /* 66 - 64 */
+#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] = "";
+
+	MLX5_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;
+
+	MLX5_ASSERT(priv);
+	MLX5_ASSERT(priv->sh);
+	ifindex = mlx5_ifindex(dev);
+	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;
+}
+
+/**
+ * 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.
+ */
+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);
+}
+
+/**
+ * Get device current raw clock counter
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param[out] time
+ *   Current raw clock counter of the device.
+ *
+ * @return
+ *   0 if the clock has correctly been read
+ *   The value of errno in case of error
+ */
+int
+mlx5_read_clock(struct rte_eth_dev *dev, uint64_t *clock)
+{
+	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;
+	}
+	*clock = values.raw_clock.tv_nsec;
+	return 0;
+}
+
+/**
+ * Retrieve the master device for representor in the same switch domain.
+ *
+ * @param dev
+ *   Pointer to representor Ethernet device structure.
+ *
+ * @return
+ *   Master device structure  on success, NULL otherwise.
+ */
+static struct rte_eth_dev *
+mlx5_find_master_dev(struct rte_eth_dev *dev)
+{
+	struct mlx5_priv *priv;
+	uint16_t port_id;
+	uint16_t domain_id;
+
+	priv = dev->data->dev_private;
+	domain_id = priv->domain_id;
+	MLX5_ASSERT(priv->representor);
+	MLX5_ETH_FOREACH_DEV(port_id, priv->pci_dev) {
+		struct mlx5_priv *opriv =
+			rte_eth_devices[port_id].data->dev_private;
+		if (opriv &&
+		    opriv->master &&
+		    opriv->domain_id == domain_id &&
+		    opriv->sh == priv->sh)
+			return &rte_eth_devices[port_id];
+	}
+	return NULL;
+}
+
+/**
+ * DPDK callback to retrieve physical link information.
+ *
+ * @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_gset(struct rte_eth_dev *dev,
+			       struct rte_eth_link *link)
+{
+	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;
+
+	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 == UINT32_MAX) ? ETH_SPEED_NUM_NONE :
+							    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;
+	if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT) |
+		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT)))
+		priv->link_speed_capa |= ETH_LINK_SPEED_200G;
+
+	sc = ecmd->link_mode_masks[2] |
+		((uint64_t)ecmd->link_mode_masks[3] << 32);
+	if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT) |
+		  MLX5_BITSHIFT
+		       (ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT) |
+		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT)))
+		priv->link_speed_capa |= ETH_LINK_SPEED_200G;
+	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);
+	int retry = MLX5_GET_LINK_STATUS_RETRY_COUNT;
+
+	do {
+		ret = mlx5_link_update_unlocked_gs(dev, &dev_link);
+		if (ret == -ENOTSUP)
+			ret = mlx5_link_update_unlocked_gset(dev, &dev_link);
+		if (ret == 0)
+			break;
+		/* Handle wait to complete situation. */
+		if ((wait_to_complete || retry) && 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 || retry-- > 0);
+	ret = !!memcmp(&dev->data->dev_link, &dev_link,
+		       sizeof(struct rte_eth_link));
+	dev->data->dev_link = dev_link;
+	return ret;
+}
+
+/**
+ * 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;
+}
+
+/**
+ * Handle asynchronous removal event for entire multiport device.
+ *
+ * @param sh
+ *   Infiniband device shared context.
+ */
+static void
+mlx5_dev_interrupt_device_fatal(struct mlx5_dev_ctx_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];
+		MLX5_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_dev_ctx_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;
+		}
+		MLX5_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];
+		MLX5_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);
+	}
+}
+
+/*
+ * Unregister callback handler safely. The handler may be active
+ * while we are trying to unregister it, in this case code -EAGAIN
+ * is returned by rte_intr_callback_unregister(). This routine checks
+ * the return code and tries to unregister handler again.
+ *
+ * @param handle
+ *   interrupt handle
+ * @param cb_fn
+ *   pointer to callback routine
+ * @cb_arg
+ *   opaque callback parameter
+ */
+void
+mlx5_intr_callback_unregister(const struct rte_intr_handle *handle,
+			      rte_intr_callback_fn cb_fn, void *cb_arg)
+{
+	/*
+	 * Try to reduce timeout management overhead by not calling
+	 * the timer related routines on the first iteration. If the
+	 * unregistering succeeds on first call there will be no
+	 * timer calls at all.
+	 */
+	uint64_t twait = 0;
+	uint64_t start = 0;
+
+	do {
+		int ret;
+
+		ret = rte_intr_callback_unregister(handle, cb_fn, cb_arg);
+		if (ret >= 0)
+			return;
+		if (ret != -EAGAIN) {
+			DRV_LOG(INFO, "failed to unregister interrupt"
+				      " handler (error: %d)", ret);
+			MLX5_ASSERT(false);
+			return;
+		}
+		if (twait) {
+			struct timespec onems;
+
+			/* Wait one millisecond and try again. */
+			onems.tv_sec = 0;
+			onems.tv_nsec = NS_PER_S / MS_PER_S;
+			nanosleep(&onems, 0);
+			/* Check whether one second elapsed. */
+			if ((rte_get_timer_cycles() - start) <= twait)
+				continue;
+		} else {
+			/*
+			 * We get the amount of timer ticks for one second.
+			 * If this amount elapsed it means we spent one
+			 * second in waiting. This branch is executed once
+			 * on first iteration.
+			 */
+			twait = rte_get_timer_hz();
+			MLX5_ASSERT(twait);
+		}
+		/*
+		 * Timeout elapsed, show message (once a second) and retry.
+		 * We have no other acceptable option here, if we ignore
+		 * the unregistering return code the handler will not
+		 * be unregistered, fd will be closed and we may get the
+		 * crush. Hanging and messaging in the loop seems not to be
+		 * the worst choice.
+		 */
+		DRV_LOG(INFO, "Retrying to unregister interrupt handler");
+		start = rte_get_timer_cycles();
+	} while (true);
+}
+
+/**
+ * Handle DEVX interrupts from the NIC.
+ * This function is probably called from the DPDK host thread.
+ *
+ * @param cb_arg
+ *   Callback argument.
+ */
+void
+mlx5_dev_interrupt_handler_devx(void *cb_arg)
+{
+#ifndef HAVE_IBV_DEVX_ASYNC
+	(void)cb_arg;
+	return;
+#else
+	struct mlx5_dev_ctx_shared *sh = cb_arg;
+	union {
+		struct mlx5dv_devx_async_cmd_hdr cmd_resp;
+		uint8_t buf[MLX5_ST_SZ_BYTES(query_flow_counter_out) +
+			    MLX5_ST_SZ_BYTES(traffic_counter) +
+			    sizeof(struct mlx5dv_devx_async_cmd_hdr)];
+	} out;
+	uint8_t *buf = out.buf + sizeof(out.cmd_resp);
+
+	while (!mlx5_glue->devx_get_async_cmd_comp(sh->devx_comp,
+						   &out.cmd_resp,
+						   sizeof(out.buf)))
+		mlx5_flow_async_pool_query_handle
+			(sh, (uint64_t)out.cmd_resp.wr_id,
+			 mlx5_devx_get_out_command_status(buf));
+#endif /* HAVE_IBV_DEVX_ASYNC */
+}
+
+/**
+ * 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);
+}
+
+/**
+ * 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 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;
+	}
+	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;
+	MLX5_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;
+}
+
+/**
+ * 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;
+	}
+}
+
+/**
+ * DPDK callback to retrieve plug-in module EEPROM information (type and size).
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param[out] modinfo
+ *   Storage for plug-in module EEPROM information.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_get_module_info(struct rte_eth_dev *dev,
+		     struct rte_eth_dev_module_info *modinfo)
+{
+	struct ethtool_modinfo info = {
+		.cmd = ETHTOOL_GMODULEINFO,
+	};
+	struct ifreq ifr = (struct ifreq) {
+		.ifr_data = (void *)&info,
+	};
+	int ret = 0;
+
+	if (!dev || !modinfo) {
+		DRV_LOG(WARNING, "missing argument, cannot get module info");
+		rte_errno = EINVAL;
+		return -rte_errno;
+	}
+	ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
+	if (ret) {
+		DRV_LOG(WARNING, "port %u ioctl(SIOCETHTOOL) failed: %s",
+			dev->data->port_id, strerror(rte_errno));
+		return ret;
+	}
+	modinfo->type = info.type;
+	modinfo->eeprom_len = info.eeprom_len;
+	return ret;
+}
+
+/**
+ * DPDK callback to retrieve plug-in module EEPROM data.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param[out] info
+ *   Storage for plug-in module EEPROM data.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int mlx5_get_module_eeprom(struct rte_eth_dev *dev,
+			   struct rte_dev_eeprom_info *info)
+{
+	struct ethtool_eeprom *eeprom;
+	struct ifreq ifr;
+	int ret = 0;
+
+	if (!dev || !info) {
+		DRV_LOG(WARNING, "missing argument, cannot get module eeprom");
+		rte_errno = EINVAL;
+		return -rte_errno;
+	}
+	eeprom = rte_calloc(__func__, 1,
+			    (sizeof(struct ethtool_eeprom) + info->length), 0);
+	if (!eeprom) {
+		DRV_LOG(WARNING, "port %u cannot allocate memory for "
+			"eeprom data", dev->data->port_id);
+		rte_errno = ENOMEM;
+		return -rte_errno;
+	}
+	eeprom->cmd = ETHTOOL_GMODULEEEPROM;
+	eeprom->offset = info->offset;
+	eeprom->len = info->length;
+	ifr = (struct ifreq) {
+		.ifr_data = (void *)eeprom,
+	};
+	ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
+	if (ret)
+		DRV_LOG(WARNING, "port %u ioctl(SIOCETHTOOL) failed: %s",
+			dev->data->port_id, strerror(rte_errno));
+	else
+		rte_memcpy(info->data, eeprom->data, info->length);
+	rte_free(eeprom);
+	return ret;
+}
diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h
index abe5099..8aa8510 100644
--- a/drivers/net/mlx5/mlx5.h
+++ b/drivers/net/mlx5/mlx5.h
@@ -711,6 +711,18 @@ int mlx5_init_once(void);
 
 /* mlx5_ethdev.c */
 
+int mlx5_dev_configure(struct rte_eth_dev *dev);
+int mlx5_fw_version_get(struct rte_eth_dev *dev, char *fw_ver,
+			size_t fw_size);
+int mlx5_dev_infos_get(struct rte_eth_dev *dev,
+		       struct rte_eth_dev_info *info);
+const uint32_t *mlx5_dev_supported_ptypes_get(struct rte_eth_dev *dev);
+int mlx5_dev_set_mtu(struct rte_eth_dev *dev, uint16_t mtu);
+int mlx5_hairpin_cap_get(struct rte_eth_dev *dev,
+			 struct rte_eth_hairpin_cap *cap);
+
+/* mlx5_ethdev_os.c */
+
 int mlx5_get_ifname(const struct rte_eth_dev *dev, char (*ifname)[IF_NAMESIZE]);
 int mlx5_get_master_ifname(const char *ibdev_path, char (*ifname)[IF_NAMESIZE]);
 unsigned int mlx5_ifindex(const struct rte_eth_dev *dev);
@@ -718,14 +730,10 @@ int mlx5_ifreq(const struct rte_eth_dev *dev, int req, struct ifreq *ifr);
 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_dev_configure(struct rte_eth_dev *dev);
-int mlx5_dev_infos_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *info);
+int mlx5_set_mtu(struct rte_eth_dev *dev, uint16_t mtu);
 int mlx5_read_clock(struct rte_eth_dev *dev, uint64_t *clock);
-int mlx5_fw_version_get(struct rte_eth_dev *dev, char *fw_ver, size_t fw_size);
-const uint32_t *mlx5_dev_supported_ptypes_get(struct rte_eth_dev *dev);
 int mlx5_link_update(struct rte_eth_dev *dev, int wait_to_complete);
 int mlx5_force_link_status_change(struct rte_eth_dev *dev, int status);
-int mlx5_dev_set_mtu(struct rte_eth_dev *dev, uint16_t mtu);
 int mlx5_dev_get_flow_ctrl(struct rte_eth_dev *dev,
 			   struct rte_eth_fc_conf *fc_conf);
 int mlx5_dev_set_flow_ctrl(struct rte_eth_dev *dev,
@@ -754,8 +762,6 @@ int mlx5_get_module_info(struct rte_eth_dev *dev,
 			 struct rte_eth_dev_module_info *modinfo);
 int mlx5_get_module_eeprom(struct rte_eth_dev *dev,
 			   struct rte_dev_eeprom_info *info);
-int mlx5_hairpin_cap_get(struct rte_eth_dev *dev,
-			 struct rte_eth_hairpin_cap *cap);
 int mlx5_dev_configure_rss_reta(struct rte_eth_dev *dev);
 
 /* mlx5_mac.c */
diff --git a/drivers/net/mlx5/mlx5_ethdev.c b/drivers/net/mlx5/mlx5_ethdev.c
index 6b8b303..6b4efcd 100644
--- a/drivers/net/mlx5/mlx5_ethdev.c
+++ b/drivers/net/mlx5/mlx5_ethdev.c
@@ -4,25 +4,11 @@
  */
 
 #include <stddef.h>
-#include <inttypes.h>
 #include <unistd.h>
-#include <stdbool.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>
@@ -35,219 +21,8 @@
 #include <rte_rwlock.h>
 #include <rte_cycles.h>
 
-#include <mlx5_glue.h>
-#include <mlx5_devx_cmds.h>
-#include <mlx5_common.h>
-
-#include "mlx5.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[];
-};
-
-/* The kernel values can be found in /include/uapi/linux/ethtool.h */
-#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
-#ifndef HAVE_ETHTOOL_LINK_MODE_200G
-#define ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT 62
-#define ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT 63
-#define ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT 0 /* 64 - 64 */
-#define ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT 1 /* 65 - 64 */
-#define ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT 2 /* 66 - 64 */
-#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] = "";
-
-	MLX5_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;
-
-	MLX5_ASSERT(priv);
-	MLX5_ASSERT(priv->sh);
-	ifindex = mlx5_ifindex(dev);
-	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_autoconf.h"
 
 /**
  * Get the interface index from device name.
@@ -273,112 +48,6 @@ mlx5_ifindex(const struct rte_eth_dev *dev)
 }
 
 /**
- * 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.
  *
  * @param dev
@@ -691,36 +360,6 @@ mlx5_dev_infos_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *info)
 }
 
 /**
- * Get device current raw clock counter
- *
- * @param dev
- *   Pointer to Ethernet device structure.
- * @param[out] time
- *   Current raw clock counter of the device.
- *
- * @return
- *   0 if the clock has correctly been read
- *   The value of errno in case of error
- */
-int
-mlx5_read_clock(struct rte_eth_dev *dev, uint64_t *clock)
-{
-	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;
-	}
-	*clock = values.raw_clock.tv_nsec;
-	return 0;
-}
-
-/**
  * Get firmware version of a device.
  *
  * @param dev
@@ -733,7 +372,8 @@ mlx5_read_clock(struct rte_eth_dev *dev, uint64_t *clock)
  * @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 mlx5_dev_attr *attr = &priv->sh->device_attr;
@@ -784,330 +424,6 @@ mlx5_dev_supported_ptypes_get(struct rte_eth_dev *dev)
 }
 
 /**
- * Retrieve the master device for representor in the same switch domain.
- *
- * @param dev
- *   Pointer to representor Ethernet device structure.
- *
- * @return
- *   Master device structure  on success, NULL otherwise.
- */
-
-static struct rte_eth_dev *
-mlx5_find_master_dev(struct rte_eth_dev *dev)
-{
-	struct mlx5_priv *priv;
-	uint16_t port_id;
-	uint16_t domain_id;
-
-	priv = dev->data->dev_private;
-	domain_id = priv->domain_id;
-	MLX5_ASSERT(priv->representor);
-	MLX5_ETH_FOREACH_DEV(port_id, priv->pci_dev) {
-		struct mlx5_priv *opriv =
-			rte_eth_devices[port_id].data->dev_private;
-		if (opriv &&
-		    opriv->master &&
-		    opriv->domain_id == domain_id &&
-		    opriv->sh == priv->sh)
-			return &rte_eth_devices[port_id];
-	}
-	return NULL;
-}
-
-/**
- * DPDK callback to retrieve physical link information.
- *
- * @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_gset(struct rte_eth_dev *dev,
-			       struct rte_eth_link *link)
-{
-	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;
-
-	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 == UINT32_MAX) ? ETH_SPEED_NUM_NONE :
-							    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;
-	if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT) |
-		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT)))
-		priv->link_speed_capa |= ETH_LINK_SPEED_200G;
-
-	sc = ecmd->link_mode_masks[2] |
-		((uint64_t)ecmd->link_mode_masks[3] << 32);
-	if (sc & (MLX5_BITSHIFT(ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT) |
-		  MLX5_BITSHIFT(
-			ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT) |
-		  MLX5_BITSHIFT(ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT)))
-		priv->link_speed_capa |= ETH_LINK_SPEED_200G;
-	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);
-	int retry = MLX5_GET_LINK_STATUS_RETRY_COUNT;
-
-	do {
-		ret = mlx5_link_update_unlocked_gs(dev, &dev_link);
-		if (ret == -ENOTSUP)
-			ret = mlx5_link_update_unlocked_gset(dev, &dev_link);
-		if (ret == 0)
-			break;
-		/* Handle wait to complete situation. */
-		if ((wait_to_complete || retry) && 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 || retry-- > 0);
-	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
@@ -1146,335 +462,6 @@ mlx5_dev_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
 }
 
 /**
- * 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;
-}
-
-/**
- * Handle asynchronous removal event for entire multiport device.
- *
- * @param sh
- *   Infiniband device shared context.
- */
-static void
-mlx5_dev_interrupt_device_fatal(struct mlx5_dev_ctx_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];
-		MLX5_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_dev_ctx_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;
-		}
-		MLX5_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];
-		MLX5_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);
-	}
-}
-
-/*
- * Unregister callback handler safely. The handler may be active
- * while we are trying to unregister it, in this case code -EAGAIN
- * is returned by rte_intr_callback_unregister(). This routine checks
- * the return code and tries to unregister handler again.
- *
- * @param handle
- *   interrupt handle
- * @param cb_fn
- *   pointer to callback routine
- * @cb_arg
- *   opaque callback parameter
- */
-void
-mlx5_intr_callback_unregister(const struct rte_intr_handle *handle,
-			      rte_intr_callback_fn cb_fn, void *cb_arg)
-{
-	/*
-	 * Try to reduce timeout management overhead by not calling
-	 * the timer related routines on the first iteration. If the
-	 * unregistering succeeds on first call there will be no
-	 * timer calls at all.
-	 */
-	uint64_t twait = 0;
-	uint64_t start = 0;
-
-	do {
-		int ret;
-
-		ret = rte_intr_callback_unregister(handle, cb_fn, cb_arg);
-		if (ret >= 0)
-			return;
-		if (ret != -EAGAIN) {
-			DRV_LOG(INFO, "failed to unregister interrupt"
-				      " handler (error: %d)", ret);
-			MLX5_ASSERT(false);
-			return;
-		}
-		if (twait) {
-			struct timespec onems;
-
-			/* Wait one millisecond and try again. */
-			onems.tv_sec = 0;
-			onems.tv_nsec = NS_PER_S / MS_PER_S;
-			nanosleep(&onems, 0);
-			/* Check whether one second elapsed. */
-			if ((rte_get_timer_cycles() - start) <= twait)
-				continue;
-		} else {
-			/*
-			 * We get the amount of timer ticks for one second.
-			 * If this amount elapsed it means we spent one
-			 * second in waiting. This branch is executed once
-			 * on first iteration.
-			 */
-			twait = rte_get_timer_hz();
-			MLX5_ASSERT(twait);
-		}
-		/*
-		 * Timeout elapsed, show message (once a second) and retry.
-		 * We have no other acceptable option here, if we ignore
-		 * the unregistering return code the handler will not
-		 * be unregistered, fd will be closed and we may get the
-		 * crush. Hanging and messaging in the loop seems not to be
-		 * the worst choice.
-		 */
-		DRV_LOG(INFO, "Retrying to unregister interrupt handler");
-		start = rte_get_timer_cycles();
-	} while (true);
-}
-
-/**
- * Handle DEVX interrupts from the NIC.
- * This function is probably called from the DPDK host thread.
- *
- * @param cb_arg
- *   Callback argument.
- */
-void
-mlx5_dev_interrupt_handler_devx(void *cb_arg)
-{
-#ifndef HAVE_IBV_DEVX_ASYNC
-	(void)cb_arg;
-	return;
-#else
-	struct mlx5_dev_ctx_shared *sh = cb_arg;
-	union {
-		struct mlx5dv_devx_async_cmd_hdr cmd_resp;
-		uint8_t buf[MLX5_ST_SZ_BYTES(query_flow_counter_out) +
-			    MLX5_ST_SZ_BYTES(traffic_counter) +
-			    sizeof(struct mlx5dv_devx_async_cmd_hdr)];
-	} out;
-	uint8_t *buf = out.buf + sizeof(out.cmd_resp);
-
-	while (!mlx5_glue->devx_get_async_cmd_comp(sh->devx_comp,
-						   &out.cmd_resp,
-						   sizeof(out.buf)))
-		mlx5_flow_async_pool_query_handle
-			(sh, (uint64_t)out.cmd_resp.wr_id,
-			 mlx5_devx_get_out_command_status(buf));
-#endif /* HAVE_IBV_DEVX_ASYNC */
-}
-
-/**
- * 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 RX function to use.
  *
  * @param dev
@@ -1500,26 +487,6 @@ mlx5_select_rx_function(struct rte_eth_dev *dev)
 }
 
 /**
- * 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 the E-Switch parameters by port id.
  *
  * @param[in] port
@@ -1588,219 +555,6 @@ mlx5_dev_to_eswitch_info(struct rte_eth_dev *dev)
 }
 
 /**
- * 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;
-	}
-	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;
-	MLX5_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;
-}
-
-/**
- * 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;
-	}
-}
-
-/**
- * DPDK callback to retrieve plug-in module EEPROM information (type and size).
- *
- * @param dev
- *   Pointer to Ethernet device structure.
- * @param[out] modinfo
- *   Storage for plug-in module EEPROM information.
- *
- * @return
- *   0 on success, a negative errno value otherwise and rte_errno is set.
- */
-int
-mlx5_get_module_info(struct rte_eth_dev *dev,
-		     struct rte_eth_dev_module_info *modinfo)
-{
-	struct ethtool_modinfo info = {
-		.cmd = ETHTOOL_GMODULEINFO,
-	};
-	struct ifreq ifr = (struct ifreq) {
-		.ifr_data = (void *)&info,
-	};
-	int ret = 0;
-
-	if (!dev || !modinfo) {
-		DRV_LOG(WARNING, "missing argument, cannot get module info");
-		rte_errno = EINVAL;
-		return -rte_errno;
-	}
-	ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
-	if (ret) {
-		DRV_LOG(WARNING, "port %u ioctl(SIOCETHTOOL) failed: %s",
-			dev->data->port_id, strerror(rte_errno));
-		return ret;
-	}
-	modinfo->type = info.type;
-	modinfo->eeprom_len = info.eeprom_len;
-	return ret;
-}
-
-/**
- * DPDK callback to retrieve plug-in module EEPROM data.
- *
- * @param dev
- *   Pointer to Ethernet device structure.
- * @param[out] info
- *   Storage for plug-in module EEPROM data.
- *
- * @return
- *   0 on success, a negative errno value otherwise and rte_errno is set.
- */
-int mlx5_get_module_eeprom(struct rte_eth_dev *dev,
-			   struct rte_dev_eeprom_info *info)
-{
-	struct ethtool_eeprom *eeprom;
-	struct ifreq ifr;
-	int ret = 0;
-
-	if (!dev || !info) {
-		DRV_LOG(WARNING, "missing argument, cannot get module eeprom");
-		rte_errno = EINVAL;
-		return -rte_errno;
-	}
-	eeprom = rte_calloc(__func__, 1,
-			    (sizeof(struct ethtool_eeprom) + info->length), 0);
-	if (!eeprom) {
-		DRV_LOG(WARNING, "port %u cannot allocate memory for "
-			"eeprom data", dev->data->port_id);
-		rte_errno = ENOMEM;
-		return -rte_errno;
-	}
-	eeprom->cmd = ETHTOOL_GMODULEEEPROM;
-	eeprom->offset = info->offset;
-	eeprom->len = info->length;
-	ifr = (struct ifreq) {
-		.ifr_data = (void *)eeprom,
-	};
-	ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
-	if (ret)
-		DRV_LOG(WARNING, "port %u ioctl(SIOCETHTOOL) failed: %s",
-			dev->data->port_id, strerror(rte_errno));
-	else
-		rte_memcpy(info->data, eeprom->data, info->length);
-	rte_free(eeprom);
-	return ret;
-}
-
-/**
  * DPDK callback to retrieve hairpin capabilities.
  *
  * @param dev
@@ -1811,7 +565,8 @@ int mlx5_get_module_eeprom(struct rte_eth_dev *dev,
  * @return
  *   0 on success, a negative errno value otherwise and rte_errno is set.
  */
-int mlx5_hairpin_cap_get(struct rte_eth_dev *dev,
+int
+mlx5_hairpin_cap_get(struct rte_eth_dev *dev,
 			 struct rte_eth_hairpin_cap *cap)
 {
 	struct mlx5_priv *priv = dev->data->dev_private;
-- 
2.8.4



More information about the dev mailing list