[dpdk-dev] [PATCH 00/19] MLX5 FreeBSD support

[dpdk-dev] [PATCH 00/19] MLX5 FreeBSD support

[Srikanth Kaka]

This patch series adds support for MLX5 PMD on FreeBSD

Srikanth Kaka (19):
  common/mlx5: FreeBSD stub
  net/mlx5: FreeBSD stub
  common/mlx5: FreeBSD disabling auxiliary bus support
  net/mlx5: FreeBSD disabling auxiliary bus support
  net/mlx5: Modified PCI probe to work on FreeBSD
  common/mlx5: Define PF_INET socket
  net/mlx5: Use the newly defined INET socket
  common/mlx5: derive PCI addr in FreeBSD
  common/mlx5: get interface name
  net/mlx5: fix socket MAC request
  net/mlx5: removing port representator support
  net/mlx5: Added procedure to detect link state
  net/mlx5: Added placeholder for VLAN vmwa
  net/mlx5: Added stats support
  net/mlx5: making flow control DPDK callback invalid
  net/mlx5: making module DPDK callbacks invalid
  common/mlx5: fixed missing dependency in mlx5_glue.h
  net/mlx5: fixed compilation warnings
  mlx5: Added meson support for FreeBSD

 drivers/common/mlx5/freebsd/meson.build       |  189 ++
 drivers/common/mlx5/freebsd/mlx5_common_os.c  |  387 +++
 drivers/common/mlx5/freebsd/mlx5_common_os.h  |  304 ++
 .../common/mlx5/freebsd/mlx5_common_verbs.c   |   90 +
 drivers/common/mlx5/freebsd/mlx5_glue.c       | 1505 ++++++++++
 drivers/common/mlx5/freebsd/mlx5_glue.h       |  374 +++
 drivers/common/mlx5/freebsd/mlx5_inet.c       |  306 ++
 drivers/common/mlx5/freebsd/mlx5_inet.h       |   75 +
 drivers/common/mlx5/meson.build               |   12 +-
 drivers/net/mlx5/freebsd/meson.build          |   14 +
 drivers/net/mlx5/freebsd/mlx5_ethdev_os.c     | 1187 ++++++++
 drivers/net/mlx5/freebsd/mlx5_flow_os.c       |   38 +
 drivers/net/mlx5/freebsd/mlx5_flow_os.h       |  484 +++
 drivers/net/mlx5/freebsd/mlx5_mp_os.c         |  305 ++
 drivers/net/mlx5/freebsd/mlx5_os.c            | 2600 +++++++++++++++++
 drivers/net/mlx5/freebsd/mlx5_os.h            |   22 +
 drivers/net/mlx5/freebsd/mlx5_socket.c        |  249 ++
 drivers/net/mlx5/freebsd/mlx5_verbs.c         | 1208 ++++++++
 drivers/net/mlx5/freebsd/mlx5_verbs.h         |   18 +
 drivers/net/mlx5/freebsd/mlx5_vlan_os.c       |   84 +
 drivers/net/mlx5/meson.build                  |   14 +-
 21 files changed, 9458 insertions(+), 7 deletions(-)
 create mode 100644 drivers/common/mlx5/freebsd/meson.build
 create mode 100644 drivers/common/mlx5/freebsd/mlx5_common_os.c
 create mode 100644 drivers/common/mlx5/freebsd/mlx5_common_os.h
 create mode 100644 drivers/common/mlx5/freebsd/mlx5_common_verbs.c
 create mode 100644 drivers/common/mlx5/freebsd/mlx5_glue.c
 create mode 100644 drivers/common/mlx5/freebsd/mlx5_glue.h
 create mode 100644 drivers/common/mlx5/freebsd/mlx5_inet.c
 create mode 100644 drivers/common/mlx5/freebsd/mlx5_inet.h
 create mode 100644 drivers/net/mlx5/freebsd/meson.build
 create mode 100644 drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
 create mode 100644 drivers/net/mlx5/freebsd/mlx5_flow_os.c
 create mode 100644 drivers/net/mlx5/freebsd/mlx5_flow_os.h
 create mode 100644 drivers/net/mlx5/freebsd/mlx5_mp_os.c
 create mode 100644 drivers/net/mlx5/freebsd/mlx5_os.c
 create mode 100644 drivers/net/mlx5/freebsd/mlx5_os.h
 create mode 100644 drivers/net/mlx5/freebsd/mlx5_socket.c
 create mode 100644 drivers/net/mlx5/freebsd/mlx5_verbs.c
 create mode 100644 drivers/net/mlx5/freebsd/mlx5_verbs.h
 create mode 100644 drivers/net/mlx5/freebsd/mlx5_vlan_os.c

-- 
2.30.2

[dpdk-dev] [PATCH 01/19] common/mlx5: stub for FreeBSD

[Srikanth Kaka]

These files are a copy of their Linux equivalents.
They will be ported to FreeBSD.

Signed-off-by: Srikanth Kaka <srikanth.k@oneconvergence.com>
Signed-off-by: Vag Singh <vag.singh@oneconvergence.com>
Signed-off-by: Anand Thulasiram <avelu@juniper.net>
---
 drivers/common/mlx5/freebsd/mlx5_common_os.c  |  430 +++++
 drivers/common/mlx5/freebsd/mlx5_common_os.h  |  299 ++++
 .../common/mlx5/freebsd/mlx5_common_verbs.c   |   93 +
 drivers/common/mlx5/freebsd/mlx5_glue.c       | 1505 +++++++++++++++++
 drivers/common/mlx5/freebsd/mlx5_glue.h       |  373 ++++
 5 files changed, 2700 insertions(+)
 create mode 100644 drivers/common/mlx5/freebsd/mlx5_common_os.c
 create mode 100644 drivers/common/mlx5/freebsd/mlx5_common_os.h
 create mode 100644 drivers/common/mlx5/freebsd/mlx5_common_verbs.c
 create mode 100644 drivers/common/mlx5/freebsd/mlx5_glue.c
 create mode 100644 drivers/common/mlx5/freebsd/mlx5_glue.h

diff --git a/drivers/common/mlx5/freebsd/mlx5_common_os.c b/drivers/common/mlx5/freebsd/mlx5_common_os.c
new file mode 100644
index 0000000000..9e0c823c97
--- /dev/null
+++ b/drivers/common/mlx5/freebsd/mlx5_common_os.c
@@ -0,0 +1,430 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2020 Mellanox Technologies, Ltd
+ */
+
+#include <unistd.h>
+#include <string.h>
+#include <stdio.h>
+#ifdef RTE_IBVERBS_LINK_DLOPEN
+#include <dlfcn.h>
+#endif
+#include <dirent.h>
+#include <net/if.h>
+
+#include <rte_errno.h>
+#include <rte_string_fns.h>
+
+#include "mlx5_common.h"
+#include "mlx5_common_log.h"
+#include "mlx5_common_os.h"
+#include "mlx5_glue.h"
+
+#ifdef MLX5_GLUE
+const struct mlx5_glue *mlx5_glue;
+#endif
+
+int
+mlx5_get_pci_addr(const char *dev_path, struct rte_pci_addr *pci_addr)
+{
+	FILE *file;
+	char line[32];
+	int rc = -ENOENT;
+	MKSTR(path, "%s/device/uevent", dev_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);
+
+		/* Truncate long lines. */
+		if (len == (sizeof(line) - 1)) {
+			while (line[(len - 1)] != '\n') {
+				int ret = fgetc(file);
+
+				if (ret == EOF)
+					goto exit;
+				line[(len - 1)] = ret;
+			}
+			/* No match for long lines. */
+			continue;
+		}
+		/* 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) {
+			rc = 0;
+			break;
+		}
+	}
+exit:
+	fclose(file);
+	if (rc)
+		rte_errno = -rc;
+	return rc;
+}
+
+/**
+ * Extract port name, as a number, from sysfs or netlink information.
+ *
+ * @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
+ *
+ * @return
+ *   port_name field set according to recognized name format.
+ */
+void
+mlx5_translate_port_name(const char *port_name_in,
+			 struct mlx5_switch_info *port_info_out)
+{
+	char ctrl = 0, pf_c1, pf_c2, vf_c1, vf_c2, eol;
+	char *end;
+	int sc_items;
+
+	sc_items = sscanf(port_name_in, "%c%d",
+			  &ctrl, &port_info_out->ctrl_num);
+	if (sc_items == 2 && ctrl == 'c') {
+		port_name_in++; /* 'c' */
+		port_name_in += snprintf(NULL, 0, "%d",
+					  port_info_out->ctrl_num);
+	}
+	/* Check for port-name as a string of the form pf0vf0 or pf0sf0 */
+	sc_items = sscanf(port_name_in, "%c%c%d%c%c%d%c",
+			  &pf_c1, &pf_c2, &port_info_out->pf_num,
+			  &vf_c1, &vf_c2, &port_info_out->port_name, &eol);
+	if (sc_items == 6 && pf_c1 == 'p' && pf_c2 == 'f') {
+		if (vf_c1 == 'v' && vf_c2 == 'f') {
+			/* Kernel ver >= 5.0 or OFED ver >= 4.6 */
+			port_info_out->name_type =
+					MLX5_PHYS_PORT_NAME_TYPE_PFVF;
+			return;
+		}
+		if (vf_c1 == 's' && vf_c2 == 'f') {
+			/* Kernel ver >= 5.11 or OFED ver >= 5.1 */
+			port_info_out->name_type =
+					MLX5_PHYS_PORT_NAME_TYPE_PFSF;
+			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%c",
+			  &pf_c1, &port_info_out->port_name, &eol);
+	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 string of the form pf0
+	 * (support kernel ver >= 5.7 for HPF representor on BF).
+	 */
+	sc_items = sscanf(port_name_in, "%c%c%d%c",
+			  &pf_c1, &pf_c2, &port_info_out->pf_num, &eol);
+	if (sc_items == 3 && pf_c1 == 'p' && pf_c2 == 'f') {
+		port_info_out->port_name = -1;
+		port_info_out->name_type = MLX5_PHYS_PORT_NAME_TYPE_PFHPF;
+		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;
+	}
+	port_info_out->name_type = MLX5_PHYS_PORT_NAME_TYPE_UNKNOWN;
+}
+
+int
+mlx5_get_ifname_sysfs(const char *ibdev_path, char *ifname)
+{
+	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, IF_NAMESIZE);
+	}
+	closedir(dir);
+	if (match[0] == '\0') {
+		rte_errno = ENOENT;
+		return -rte_errno;
+	}
+	strncpy(ifname, match, IF_NAMESIZE);
+	return 0;
+}
+
+#ifdef MLX5_GLUE
+
+/**
+ * Suffix RTE_EAL_PMD_PATH with "-glue".
+ *
+ * This function performs a sanity check on RTE_EAL_PMD_PATH before
+ * suffixing its last component.
+ *
+ * @param buf[out]
+ *   Output buffer, should be large enough otherwise NULL is returned.
+ * @param size
+ *   Size of @p out.
+ *
+ * @return
+ *   Pointer to @p buf or @p NULL in case suffix cannot be appended.
+ */
+static char *
+mlx5_glue_path(char *buf, size_t size)
+{
+	static const char *const bad[] = { "/", ".", "..", NULL };
+	const char *path = RTE_EAL_PMD_PATH;
+	size_t len = strlen(path);
+	size_t off;
+	int i;
+
+	while (len && path[len - 1] == '/')
+		--len;
+	for (off = len; off && path[off - 1] != '/'; --off)
+		;
+	for (i = 0; bad[i]; ++i)
+		if (!strncmp(path + off, bad[i], (int)(len - off)))
+			goto error;
+	i = snprintf(buf, size, "%.*s-glue", (int)len, path);
+	if (i == -1 || (size_t)i >= size)
+		goto error;
+	return buf;
+error:
+	RTE_LOG(ERR, PMD, "unable to append \"-glue\" to last component of"
+		" RTE_EAL_PMD_PATH (\"" RTE_EAL_PMD_PATH "\"), please"
+		" re-configure DPDK");
+	return NULL;
+}
+
+static int
+mlx5_glue_dlopen(void)
+{
+	char glue_path[sizeof(RTE_EAL_PMD_PATH) - 1 + sizeof("-glue")];
+	void *handle = NULL;
+
+	char const *path[] = {
+		/*
+		 * A basic security check is necessary before trusting
+		 * MLX5_GLUE_PATH, which may override RTE_EAL_PMD_PATH.
+		 */
+		(geteuid() == getuid() && getegid() == getgid() ?
+		 getenv("MLX5_GLUE_PATH") : NULL),
+		/*
+		 * When RTE_EAL_PMD_PATH is set, use its glue-suffixed
+		 * variant, otherwise let dlopen() look up libraries on its
+		 * own.
+		 */
+		(*RTE_EAL_PMD_PATH ?
+		 mlx5_glue_path(glue_path, sizeof(glue_path)) : ""),
+	};
+	unsigned int i = 0;
+	void **sym;
+	const char *dlmsg;
+
+	while (!handle && i != RTE_DIM(path)) {
+		const char *end;
+		size_t len;
+		int ret;
+
+		if (!path[i]) {
+			++i;
+			continue;
+		}
+		end = strpbrk(path[i], ":;");
+		if (!end)
+			end = path[i] + strlen(path[i]);
+		len = end - path[i];
+		ret = 0;
+		do {
+			char name[ret + 1];
+
+			ret = snprintf(name, sizeof(name), "%.*s%s" MLX5_GLUE,
+				       (int)len, path[i],
+				       (!len || *(end - 1) == '/') ? "" : "/");
+			if (ret == -1)
+				break;
+			if (sizeof(name) != (size_t)ret + 1)
+				continue;
+			DRV_LOG(DEBUG, "Looking for rdma-core glue as "
+				"\"%s\"", name);
+			handle = dlopen(name, RTLD_LAZY);
+			break;
+		} while (1);
+		path[i] = end + 1;
+		if (!*end)
+			++i;
+	}
+	if (!handle) {
+		rte_errno = EINVAL;
+		dlmsg = dlerror();
+		if (dlmsg)
+			DRV_LOG(WARNING, "Cannot load glue library: %s", dlmsg);
+		goto glue_error;
+	}
+	sym = dlsym(handle, "mlx5_glue");
+	if (!sym || !*sym) {
+		rte_errno = EINVAL;
+		dlmsg = dlerror();
+		if (dlmsg)
+			DRV_LOG(ERR, "Cannot resolve glue symbol: %s", dlmsg);
+		goto glue_error;
+	}
+	mlx5_glue = *sym;
+	return 0;
+
+glue_error:
+	if (handle)
+		dlclose(handle);
+	return -1;
+}
+
+#endif
+
+/**
+ * Initialization routine for run-time dependency on rdma-core.
+ */
+void
+mlx5_glue_constructor(void)
+{
+	/*
+	 * RDMAV_HUGEPAGES_SAFE tells ibv_fork_init() we intend to use
+	 * huge pages. Calling ibv_fork_init() during init allows
+	 * applications to use fork() safely for purposes other than
+	 * using this PMD, which is not supported in forked processes.
+	 */
+	setenv("RDMAV_HUGEPAGES_SAFE", "1", 1);
+	/* Match the size of Rx completion entry to the size of a cacheline. */
+	if (RTE_CACHE_LINE_SIZE == 128)
+		setenv("MLX5_CQE_SIZE", "128", 0);
+	/*
+	 * MLX5_DEVICE_FATAL_CLEANUP tells ibv_destroy functions to
+	 * cleanup all the Verbs resources even when the device was removed.
+	 */
+	setenv("MLX5_DEVICE_FATAL_CLEANUP", "1", 1);
+
+#ifdef MLX5_GLUE
+	if (mlx5_glue_dlopen() != 0)
+		goto glue_error;
+#endif
+
+#ifdef RTE_LIBRTE_MLX5_DEBUG
+	/* Glue structure must not contain any NULL pointers. */
+	{
+		unsigned int i;
+
+		for (i = 0; i != sizeof(*mlx5_glue) / sizeof(void *); ++i)
+			MLX5_ASSERT(((const void *const *)mlx5_glue)[i]);
+	}
+#endif
+	if (strcmp(mlx5_glue->version, MLX5_GLUE_VERSION)) {
+		rte_errno = EINVAL;
+		DRV_LOG(ERR, "rdma-core glue \"%s\" mismatch: \"%s\" is "
+			"required", mlx5_glue->version, MLX5_GLUE_VERSION);
+		goto glue_error;
+	}
+	mlx5_glue->fork_init();
+	return;
+
+glue_error:
+	DRV_LOG(WARNING, "Cannot initialize MLX5 common due to missing"
+		" run-time dependency on rdma-core libraries (libibverbs,"
+		" libmlx5)");
+	mlx5_glue = NULL;
+}
+
+struct ibv_device *
+mlx5_os_get_ibv_device(const struct rte_pci_addr *addr)
+{
+	int n;
+	struct ibv_device **ibv_list = mlx5_glue->get_device_list(&n);
+	struct ibv_device *ibv_match = NULL;
+
+	if (ibv_list == NULL) {
+		rte_errno = ENOSYS;
+		return NULL;
+	}
+	while (n-- > 0) {
+		struct rte_pci_addr paddr;
+
+		DRV_LOG(DEBUG, "Checking device \"%s\"..", ibv_list[n]->name);
+		if (mlx5_get_pci_addr(ibv_list[n]->ibdev_path, &paddr) != 0)
+			continue;
+		if (rte_pci_addr_cmp(addr, &paddr) != 0)
+			continue;
+		ibv_match = ibv_list[n];
+		break;
+	}
+	if (ibv_match == NULL)
+		rte_errno = ENOENT;
+	mlx5_glue->free_device_list(ibv_list);
+	return ibv_match;
+}
diff --git a/drivers/common/mlx5/freebsd/mlx5_common_os.h b/drivers/common/mlx5/freebsd/mlx5_common_os.h
new file mode 100644
index 0000000000..c3202b6786
--- /dev/null
+++ b/drivers/common/mlx5/freebsd/mlx5_common_os.h
@@ -0,0 +1,299 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2020 Mellanox Technologies, Ltd
+ */
+
+#ifndef RTE_PMD_MLX5_COMMON_OS_H_
+#define RTE_PMD_MLX5_COMMON_OS_H_
+
+#include <stdio.h>
+#include <malloc.h>
+
+#include <rte_pci.h>
+#include <rte_debug.h>
+#include <rte_atomic.h>
+#include <rte_log.h>
+#include <rte_kvargs.h>
+#include <rte_devargs.h>
+
+#include "mlx5_autoconf.h"
+#include "mlx5_glue.h"
+#include "mlx5_malloc.h"
+
+/**
+ * Get device name. Given an ibv_device pointer - return a
+ * pointer to the corresponding device name.
+ *
+ * @param[in] dev
+ *   Pointer to ibv device.
+ *
+ * @return
+ *   Pointer to device name if dev is valid, NULL otherwise.
+ */
+static inline const char *
+mlx5_os_get_dev_device_name(void *dev)
+{
+	if (!dev)
+		return NULL;
+	return ((struct ibv_device *)dev)->name;
+}
+
+/**
+ * Get ibv device name. Given an ibv_context pointer - return a
+ * pointer to the corresponding device name.
+ *
+ * @param[in] ctx
+ *   Pointer to ibv context.
+ *
+ * @return
+ *   Pointer to device name if ctx is valid, NULL otherwise.
+ */
+static inline const char *
+mlx5_os_get_ctx_device_name(void *ctx)
+{
+	if (!ctx)
+		return NULL;
+	return ((struct ibv_context *)ctx)->device->name;
+}
+
+/**
+ * Get ibv device path name. Given an ibv_context pointer - return a
+ * pointer to the corresponding device path name.
+ *
+ * @param[in] ctx
+ *   Pointer to ibv context.
+ *
+ * @return
+ *   Pointer to device path name if ctx is valid, NULL otherwise.
+ */
+
+static inline const char *
+mlx5_os_get_ctx_device_path(void *ctx)
+{
+	if (!ctx)
+		return NULL;
+
+	return ((struct ibv_context *)ctx)->device->ibdev_path;
+}
+
+/**
+ * Get umem id. Given a pointer to umem object of type
+ * 'struct mlx5dv_devx_umem *' - return its id.
+ *
+ * @param[in] umem
+ *    Pointer to umem object.
+ *
+ * @return
+ *    The umem id if umem is valid, 0 otherwise.
+ */
+static inline uint32_t
+mlx5_os_get_umem_id(void *umem)
+{
+	if (!umem)
+		return 0;
+	return ((struct mlx5dv_devx_umem *)umem)->umem_id;
+}
+
+/**
+ * Get fd. Given a pointer to DevX channel object of type
+ * 'struct mlx5dv_devx_event_channel*' - return its fd.
+ *
+ * @param[in] channel
+ *    Pointer to channel object.
+ *
+ * @return
+ *    The fd if channel is valid, 0 otherwise.
+ */
+static inline int
+mlx5_os_get_devx_channel_fd(void *channel)
+{
+	if (!channel)
+		return 0;
+	return ((struct mlx5dv_devx_event_channel *)channel)->fd;
+}
+
+/**
+ * Get mmap offset. Given a pointer to an DevX UAR object of type
+ * 'struct mlx5dv_devx_uar *' - return its mmap offset.
+ *
+ * @param[in] uar
+ *    Pointer to UAR object.
+ *
+ * @return
+ *    The mmap offset if uar is valid, 0 otherwise.
+ */
+static inline off_t
+mlx5_os_get_devx_uar_mmap_offset(void *uar)
+{
+#ifdef HAVE_MLX5DV_DEVX_UAR_OFFSET
+	if (!uar)
+		return 0;
+	return ((struct mlx5dv_devx_uar *)uar)->mmap_off;
+#else
+	RTE_SET_USED(uar);
+	return 0;
+#endif
+}
+
+/**
+ * Get base addr pointer. Given a pointer to an UAR object of type
+ * 'struct mlx5dv_devx_uar *' - return its base address.
+ *
+ * @param[in] uar
+ *    Pointer to an UAR object.
+ *
+ * @return
+ *    The base address if UAR is valid, 0 otherwise.
+ */
+static inline void *
+mlx5_os_get_devx_uar_base_addr(void *uar)
+{
+#ifdef HAVE_MLX5DV_DEVX_UAR_OFFSET
+	if (!uar)
+		return NULL;
+	return ((struct mlx5dv_devx_uar *)uar)->base_addr;
+#else
+	RTE_SET_USED(uar);
+	return NULL;
+#endif
+}
+
+/**
+ * Get reg addr pointer. Given a pointer to an UAR object of type
+ * 'struct mlx5dv_devx_uar *' - return its reg address.
+ *
+ * @param[in] uar
+ *    Pointer to an UAR object.
+ *
+ * @return
+ *    The reg address if UAR is valid, 0 otherwise.
+ */
+static inline void *
+mlx5_os_get_devx_uar_reg_addr(void *uar)
+{
+#ifdef HAVE_MLX5DV_DEVX_UAR_OFFSET
+	if (!uar)
+		return NULL;
+	return ((struct mlx5dv_devx_uar *)uar)->reg_addr;
+#else
+	RTE_SET_USED(uar);
+	return NULL;
+#endif
+}
+
+/**
+ * Get page id. Given a pointer to an UAR object of type
+ * 'struct mlx5dv_devx_uar *' - return its page id.
+ *
+ * @param[in] uar
+ *    Pointer to an UAR object.
+ *
+ * @return
+ *    The page id if UAR is valid, 0 otherwise.
+ */
+static inline uint32_t
+mlx5_os_get_devx_uar_page_id(void *uar)
+{
+#ifdef HAVE_MLX5DV_DEVX_UAR_OFFSET
+	if (!uar)
+		return 0;
+	return ((struct mlx5dv_devx_uar *)uar)->page_id;
+#else
+	RTE_SET_USED(uar);
+	return 0;
+#endif
+}
+
+__rte_internal
+static inline void *
+mlx5_os_alloc_pd(void *ctx)
+{
+	return mlx5_glue->alloc_pd(ctx);
+}
+
+__rte_internal
+static inline int
+mlx5_os_dealloc_pd(void *pd)
+{
+	return mlx5_glue->dealloc_pd(pd);
+}
+
+__rte_internal
+static inline void *
+mlx5_os_umem_reg(void *ctx, void *addr, size_t size, uint32_t access)
+{
+	return mlx5_glue->devx_umem_reg(ctx, addr, size, access);
+}
+
+__rte_internal
+static inline int
+mlx5_os_umem_dereg(void *pumem)
+{
+	return mlx5_glue->devx_umem_dereg(pumem);
+}
+
+static inline void *
+mlx5_os_devx_create_event_channel(void *ctx, int flags)
+{
+	return mlx5_glue->devx_create_event_channel(ctx, flags);
+}
+
+static inline void
+mlx5_os_devx_destroy_event_channel(void *eventc)
+{
+	mlx5_glue->devx_destroy_event_channel(eventc);
+}
+
+static inline int
+mlx5_os_devx_subscribe_devx_event(void *eventc,
+				  void *obj,
+				  uint16_t events_sz, uint16_t events_num[],
+				  uint64_t cookie)
+{
+	return mlx5_glue->devx_subscribe_devx_event(eventc, obj, events_sz,
+						    events_num, cookie);
+}
+
+/**
+ * Memory allocation optionally with alignment.
+ *
+ * @param[in] align
+ *    Alignment size (may be zero)
+ * @param[in] size
+ *    Size in bytes to allocate
+ *
+ * @return
+ *    Valid pointer to allocated memory, NULL in case of failure
+ */
+static inline void *
+mlx5_os_malloc(size_t align, size_t size)
+{
+	void *buf;
+
+	if (posix_memalign(&buf, align, size))
+		return NULL;
+	return buf;
+}
+
+/**
+ * This API de-allocates a memory that originally could have been
+ * allocated aligned or non-aligned. In Linux it is a wrapper
+ * around free().
+ *
+ * @param[in] addr
+ *    Pointer to address to free
+ *
+ */
+static inline void
+mlx5_os_free(void *addr)
+{
+	free(addr);
+}
+
+struct ibv_device *
+mlx5_os_get_ibv_device(const struct rte_pci_addr *addr);
+
+__rte_internal
+struct ibv_device *
+mlx5_os_get_ibv_dev(const struct rte_device *dev);
+
+#endif /* RTE_PMD_MLX5_COMMON_OS_H_ */
diff --git a/drivers/common/mlx5/freebsd/mlx5_common_verbs.c b/drivers/common/mlx5/freebsd/mlx5_common_verbs.c
new file mode 100644
index 0000000000..9080bd3e87
--- /dev/null
+++ b/drivers/common/mlx5/freebsd/mlx5_common_verbs.c
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2020 Mellanox Technologies, Ltd
+ */
+
+#include <stddef.h>
+#include <errno.h>
+#include <string.h>
+#include <stdint.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <inttypes.h>
+
+#include <rte_errno.h>
+#include <rte_bus_pci.h>
+#include <rte_bus_auxiliary.h>
+
+#include "mlx5_common_utils.h"
+#include "mlx5_common_log.h"
+#include "mlx5_common_private.h"
+#include "mlx5_autoconf.h"
+#include <mlx5_glue.h>
+#include <mlx5_common.h>
+#include <mlx5_common_mr.h>
+
+struct ibv_device *
+mlx5_os_get_ibv_dev(const struct rte_device *dev)
+{
+	struct ibv_device *ibv;
+
+	if (mlx5_dev_is_pci(dev))
+		ibv = mlx5_os_get_ibv_device(&RTE_DEV_TO_PCI_CONST(dev)->addr);
+	else
+		ibv = mlx5_get_aux_ibv_device(RTE_DEV_TO_AUXILIARY_CONST(dev));
+	if (ibv == NULL) {
+		rte_errno = ENODEV;
+		DRV_LOG(ERR, "Verbs device not found: %s", dev->name);
+	}
+	return ibv;
+}
+
+/**
+ * Register mr. Given protection domain pointer, pointer to addr and length
+ * register the memory region.
+ *
+ * @param[in] pd
+ *   Pointer to protection domain context.
+ * @param[in] addr
+ *   Pointer to memory start address.
+ * @param[in] length
+ *   Length of the memory to register.
+ * @param[out] pmd_mr
+ *   pmd_mr struct set with lkey, address, length and pointer to mr object
+ *
+ * @return
+ *   0 on successful registration, -1 otherwise
+ */
+int
+mlx5_common_verbs_reg_mr(void *pd, void *addr, size_t length,
+			 struct mlx5_pmd_mr *pmd_mr)
+{
+	struct ibv_mr *ibv_mr;
+
+	ibv_mr = mlx5_glue->reg_mr(pd, addr, length,
+				   IBV_ACCESS_LOCAL_WRITE |
+				   (haswell_broadwell_cpu ? 0 :
+				   IBV_ACCESS_RELAXED_ORDERING));
+	if (!ibv_mr)
+		return -1;
+
+	*pmd_mr = (struct mlx5_pmd_mr){
+		.lkey = ibv_mr->lkey,
+		.addr = ibv_mr->addr,
+		.len = ibv_mr->length,
+		.obj = (void *)ibv_mr,
+	};
+	return 0;
+}
+
+/**
+ * Deregister mr. Given the mlx5 pmd MR - deregister the MR
+ *
+ * @param[in] pmd_mr
+ *   pmd_mr struct set with lkey, address, length and pointer to mr object
+ *
+ */
+void
+mlx5_common_verbs_dereg_mr(struct mlx5_pmd_mr *pmd_mr)
+{
+	if (pmd_mr && pmd_mr->obj != NULL) {
+		claim_zero(mlx5_glue->dereg_mr(pmd_mr->obj));
+		memset(pmd_mr, 0, sizeof(*pmd_mr));
+	}
+}
diff --git a/drivers/common/mlx5/freebsd/mlx5_glue.c b/drivers/common/mlx5/freebsd/mlx5_glue.c
new file mode 100644
index 0000000000..037ca961a0
--- /dev/null
+++ b/drivers/common/mlx5/freebsd/mlx5_glue.c
@@ -0,0 +1,1505 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2018 6WIND S.A.
+ * Copyright 2018 Mellanox Technologies, Ltd
+ */
+
+#include <errno.h>
+#include <stdalign.h>
+#include <stddef.h>
+#include <stdint.h>
+#include <stdlib.h>
+/*
+ * Not needed by this file; included to work around the lack of off_t
+ * definition for mlx5dv.h with unpatched rdma-core versions.
+ */
+#include <sys/types.h>
+
+#include "mlx5_glue.h"
+
+static int
+mlx5_glue_fork_init(void)
+{
+	return ibv_fork_init();
+}
+
+static struct ibv_pd *
+mlx5_glue_alloc_pd(struct ibv_context *context)
+{
+	return ibv_alloc_pd(context);
+}
+
+static int
+mlx5_glue_dealloc_pd(struct ibv_pd *pd)
+{
+	return ibv_dealloc_pd(pd);
+}
+
+static struct ibv_device **
+mlx5_glue_get_device_list(int *num_devices)
+{
+	return ibv_get_device_list(num_devices);
+}
+
+static void
+mlx5_glue_free_device_list(struct ibv_device **list)
+{
+	ibv_free_device_list(list);
+}
+
+static struct ibv_context *
+mlx5_glue_open_device(struct ibv_device *device)
+{
+	return ibv_open_device(device);
+}
+
+static int
+mlx5_glue_close_device(struct ibv_context *context)
+{
+	return ibv_close_device(context);
+}
+
+static int
+mlx5_glue_query_device(struct ibv_context *context,
+		       struct ibv_device_attr *device_attr)
+{
+	return ibv_query_device(context, device_attr);
+}
+
+static int
+mlx5_glue_query_device_ex(struct ibv_context *context,
+			  const struct ibv_query_device_ex_input *input,
+			  struct ibv_device_attr_ex *attr)
+{
+	return ibv_query_device_ex(context, input, attr);
+}
+
+static int
+mlx5_glue_query_rt_values_ex(struct ibv_context *context,
+			  struct ibv_values_ex *values)
+{
+	return ibv_query_rt_values_ex(context, values);
+}
+
+static int
+mlx5_glue_query_port(struct ibv_context *context, uint8_t port_num,
+		     struct ibv_port_attr *port_attr)
+{
+	return ibv_query_port(context, port_num, port_attr);
+}
+
+static struct ibv_comp_channel *
+mlx5_glue_create_comp_channel(struct ibv_context *context)
+{
+	return ibv_create_comp_channel(context);
+}
+
+static int
+mlx5_glue_destroy_comp_channel(struct ibv_comp_channel *channel)
+{
+	return ibv_destroy_comp_channel(channel);
+}
+
+static struct ibv_cq *
+mlx5_glue_create_cq(struct ibv_context *context, int cqe, void *cq_context,
+		    struct ibv_comp_channel *channel, int comp_vector)
+{
+	return ibv_create_cq(context, cqe, cq_context, channel, comp_vector);
+}
+
+static int
+mlx5_glue_destroy_cq(struct ibv_cq *cq)
+{
+	return ibv_destroy_cq(cq);
+}
+
+static int
+mlx5_glue_get_cq_event(struct ibv_comp_channel *channel, struct ibv_cq **cq,
+		       void **cq_context)
+{
+	return ibv_get_cq_event(channel, cq, cq_context);
+}
+
+static void
+mlx5_glue_ack_cq_events(struct ibv_cq *cq, unsigned int nevents)
+{
+	ibv_ack_cq_events(cq, nevents);
+}
+
+static struct ibv_rwq_ind_table *
+mlx5_glue_create_rwq_ind_table(struct ibv_context *context,
+			       struct ibv_rwq_ind_table_init_attr *init_attr)
+{
+	return ibv_create_rwq_ind_table(context, init_attr);
+}
+
+static int
+mlx5_glue_destroy_rwq_ind_table(struct ibv_rwq_ind_table *rwq_ind_table)
+{
+	return ibv_destroy_rwq_ind_table(rwq_ind_table);
+}
+
+static struct ibv_wq *
+mlx5_glue_create_wq(struct ibv_context *context,
+		    struct ibv_wq_init_attr *wq_init_attr)
+{
+	return ibv_create_wq(context, wq_init_attr);
+}
+
+static int
+mlx5_glue_destroy_wq(struct ibv_wq *wq)
+{
+	return ibv_destroy_wq(wq);
+}
+static int
+mlx5_glue_modify_wq(struct ibv_wq *wq, struct ibv_wq_attr *wq_attr)
+{
+	return ibv_modify_wq(wq, wq_attr);
+}
+
+static struct ibv_flow *
+mlx5_glue_create_flow(struct ibv_qp *qp, struct ibv_flow_attr *flow)
+{
+	return ibv_create_flow(qp, flow);
+}
+
+static int
+mlx5_glue_destroy_flow(struct ibv_flow *flow_id)
+{
+	return ibv_destroy_flow(flow_id);
+}
+
+static int
+mlx5_glue_destroy_flow_action(void *action)
+{
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+#ifdef HAVE_MLX5DV_DR
+	return mlx5dv_dr_action_destroy(action);
+#else
+	struct mlx5dv_flow_action_attr *attr = action;
+	int res = 0;
+	switch (attr->type) {
+	case MLX5DV_FLOW_ACTION_TAG:
+		break;
+	default:
+		res = ibv_destroy_flow_action(attr->action);
+		break;
+	}
+	free(action);
+	return res;
+#endif
+#else
+	(void)action;
+	return -ENOTSUP;
+#endif
+}
+
+static struct ibv_qp *
+mlx5_glue_create_qp(struct ibv_pd *pd, struct ibv_qp_init_attr *qp_init_attr)
+{
+	return ibv_create_qp(pd, qp_init_attr);
+}
+
+static struct ibv_qp *
+mlx5_glue_create_qp_ex(struct ibv_context *context,
+		       struct ibv_qp_init_attr_ex *qp_init_attr_ex)
+{
+	return ibv_create_qp_ex(context, qp_init_attr_ex);
+}
+
+static int
+mlx5_glue_destroy_qp(struct ibv_qp *qp)
+{
+	return ibv_destroy_qp(qp);
+}
+
+static int
+mlx5_glue_modify_qp(struct ibv_qp *qp, struct ibv_qp_attr *attr, int attr_mask)
+{
+	return ibv_modify_qp(qp, attr, attr_mask);
+}
+
+static struct ibv_mr *
+mlx5_glue_reg_mr(struct ibv_pd *pd, void *addr, size_t length, int access)
+{
+	return ibv_reg_mr(pd, addr, length, access);
+}
+
+static struct ibv_mr *
+mlx5_glue_alloc_null_mr(struct ibv_pd *pd)
+{
+#ifdef HAVE_IBV_DEVX_OBJ
+	return ibv_alloc_null_mr(pd);
+#else
+	(void)pd;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static int
+mlx5_glue_dereg_mr(struct ibv_mr *mr)
+{
+	return ibv_dereg_mr(mr);
+}
+
+static struct ibv_counter_set *
+mlx5_glue_create_counter_set(struct ibv_context *context,
+			     struct ibv_counter_set_init_attr *init_attr)
+{
+#ifndef HAVE_IBV_DEVICE_COUNTERS_SET_V42
+	(void)context;
+	(void)init_attr;
+	return NULL;
+#else
+	return ibv_create_counter_set(context, init_attr);
+#endif
+}
+
+static int
+mlx5_glue_destroy_counter_set(struct ibv_counter_set *cs)
+{
+#ifndef HAVE_IBV_DEVICE_COUNTERS_SET_V42
+	(void)cs;
+	return -ENOTSUP;
+#else
+	return ibv_destroy_counter_set(cs);
+#endif
+}
+
+static int
+mlx5_glue_describe_counter_set(struct ibv_context *context,
+			       uint16_t counter_set_id,
+			       struct ibv_counter_set_description *cs_desc)
+{
+#ifndef HAVE_IBV_DEVICE_COUNTERS_SET_V42
+	(void)context;
+	(void)counter_set_id;
+	(void)cs_desc;
+	return -ENOTSUP;
+#else
+	return ibv_describe_counter_set(context, counter_set_id, cs_desc);
+#endif
+}
+
+static int
+mlx5_glue_query_counter_set(struct ibv_query_counter_set_attr *query_attr,
+			    struct ibv_counter_set_data *cs_data)
+{
+#ifndef HAVE_IBV_DEVICE_COUNTERS_SET_V42
+	(void)query_attr;
+	(void)cs_data;
+	return -ENOTSUP;
+#else
+	return ibv_query_counter_set(query_attr, cs_data);
+#endif
+}
+
+static struct ibv_counters *
+mlx5_glue_create_counters(struct ibv_context *context,
+			  struct ibv_counters_init_attr *init_attr)
+{
+#ifndef HAVE_IBV_DEVICE_COUNTERS_SET_V45
+	(void)context;
+	(void)init_attr;
+	errno = ENOTSUP;
+	return NULL;
+#else
+	return ibv_create_counters(context, init_attr);
+#endif
+}
+
+static int
+mlx5_glue_destroy_counters(struct ibv_counters *counters)
+{
+#ifndef HAVE_IBV_DEVICE_COUNTERS_SET_V45
+	(void)counters;
+	return -ENOTSUP;
+#else
+	return ibv_destroy_counters(counters);
+#endif
+}
+
+static int
+mlx5_glue_attach_counters(struct ibv_counters *counters,
+			  struct ibv_counter_attach_attr *attr,
+			  struct ibv_flow *flow)
+{
+#ifndef HAVE_IBV_DEVICE_COUNTERS_SET_V45
+	(void)counters;
+	(void)attr;
+	(void)flow;
+	return -ENOTSUP;
+#else
+	return ibv_attach_counters_point_flow(counters, attr, flow);
+#endif
+}
+
+static int
+mlx5_glue_query_counters(struct ibv_counters *counters,
+			 uint64_t *counters_value,
+			 uint32_t ncounters,
+			 uint32_t flags)
+{
+#ifndef HAVE_IBV_DEVICE_COUNTERS_SET_V45
+	(void)counters;
+	(void)counters_value;
+	(void)ncounters;
+	(void)flags;
+	return -ENOTSUP;
+#else
+	return ibv_read_counters(counters, counters_value, ncounters, flags);
+#endif
+}
+
+static void
+mlx5_glue_ack_async_event(struct ibv_async_event *event)
+{
+	ibv_ack_async_event(event);
+}
+
+static int
+mlx5_glue_get_async_event(struct ibv_context *context,
+			  struct ibv_async_event *event)
+{
+	return ibv_get_async_event(context, event);
+}
+
+static const char *
+mlx5_glue_port_state_str(enum ibv_port_state port_state)
+{
+	return ibv_port_state_str(port_state);
+}
+
+static struct ibv_cq *
+mlx5_glue_cq_ex_to_cq(struct ibv_cq_ex *cq)
+{
+	return ibv_cq_ex_to_cq(cq);
+}
+
+static void *
+mlx5_glue_dr_create_flow_action_dest_flow_tbl(void *tbl)
+{
+#ifdef HAVE_MLX5DV_DR
+	return mlx5dv_dr_action_create_dest_table(tbl);
+#else
+	(void)tbl;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static void *
+mlx5_glue_dr_create_flow_action_dest_port(void *domain, uint32_t port)
+{
+#ifdef HAVE_MLX5DV_DR_CREATE_DEST_IB_PORT
+	return mlx5dv_dr_action_create_dest_ib_port(domain, port);
+#else
+#ifdef HAVE_MLX5DV_DR_ESWITCH
+	return mlx5dv_dr_action_create_dest_vport(domain, port);
+#else
+	(void)domain;
+	(void)port;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+#endif
+}
+
+static void *
+mlx5_glue_dr_create_flow_action_drop(void)
+{
+#ifdef HAVE_MLX5DV_DR_ESWITCH
+	return mlx5dv_dr_action_create_drop();
+#else
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static void *
+mlx5_glue_dr_create_flow_action_push_vlan(struct mlx5dv_dr_domain *domain,
+					  rte_be32_t vlan_tag)
+{
+#ifdef HAVE_MLX5DV_DR_VLAN
+	return mlx5dv_dr_action_create_push_vlan(domain, vlan_tag);
+#else
+	(void)domain;
+	(void)vlan_tag;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static void *
+mlx5_glue_dr_create_flow_action_pop_vlan(void)
+{
+#ifdef HAVE_MLX5DV_DR_VLAN
+	return mlx5dv_dr_action_create_pop_vlan();
+#else
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static void *
+mlx5_glue_dr_create_flow_tbl(void *domain, uint32_t level)
+{
+#ifdef HAVE_MLX5DV_DR
+	return mlx5dv_dr_table_create(domain, level);
+#else
+	(void)domain;
+	(void)level;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static int
+mlx5_glue_dr_destroy_flow_tbl(void *tbl)
+{
+#ifdef HAVE_MLX5DV_DR
+	return mlx5dv_dr_table_destroy(tbl);
+#else
+	(void)tbl;
+	errno = ENOTSUP;
+	return errno;
+#endif
+}
+
+static void *
+mlx5_glue_dr_create_domain(struct ibv_context *ctx,
+			   enum  mlx5dv_dr_domain_type domain)
+{
+#ifdef HAVE_MLX5DV_DR
+	return mlx5dv_dr_domain_create(ctx, domain);
+#else
+	(void)ctx;
+	(void)domain;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static int
+mlx5_glue_dr_destroy_domain(void *domain)
+{
+#ifdef HAVE_MLX5DV_DR
+	return mlx5dv_dr_domain_destroy(domain);
+#else
+	(void)domain;
+	errno = ENOTSUP;
+	return errno;
+#endif
+}
+
+static int
+mlx5_glue_dr_sync_domain(void *domain, uint32_t flags)
+{
+#ifdef HAVE_MLX5DV_DR
+	return mlx5dv_dr_domain_sync(domain, flags);
+#else
+	(void)domain;
+	(void)flags;
+	errno = ENOTSUP;
+	return errno;
+#endif
+}
+
+static struct ibv_cq_ex *
+mlx5_glue_dv_create_cq(struct ibv_context *context,
+		       struct ibv_cq_init_attr_ex *cq_attr,
+		       struct mlx5dv_cq_init_attr *mlx5_cq_attr)
+{
+	return mlx5dv_create_cq(context, cq_attr, mlx5_cq_attr);
+}
+
+static struct ibv_wq *
+mlx5_glue_dv_create_wq(struct ibv_context *context,
+		       struct ibv_wq_init_attr *wq_attr,
+		       struct mlx5dv_wq_init_attr *mlx5_wq_attr)
+{
+#ifndef HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT
+	(void)context;
+	(void)wq_attr;
+	(void)mlx5_wq_attr;
+	errno = ENOTSUP;
+	return NULL;
+#else
+	return mlx5dv_create_wq(context, wq_attr, mlx5_wq_attr);
+#endif
+}
+
+static int
+mlx5_glue_dv_query_device(struct ibv_context *ctx,
+			  struct mlx5dv_context *attrs_out)
+{
+	return mlx5dv_query_device(ctx, attrs_out);
+}
+
+static int
+mlx5_glue_dv_set_context_attr(struct ibv_context *ibv_ctx,
+			      enum mlx5dv_set_ctx_attr_type type, void *attr)
+{
+	return mlx5dv_set_context_attr(ibv_ctx, type, attr);
+}
+
+static int
+mlx5_glue_dv_init_obj(struct mlx5dv_obj *obj, uint64_t obj_type)
+{
+	return mlx5dv_init_obj(obj, obj_type);
+}
+
+static struct ibv_qp *
+mlx5_glue_dv_create_qp(struct ibv_context *context,
+		       struct ibv_qp_init_attr_ex *qp_init_attr_ex,
+		       struct mlx5dv_qp_init_attr *dv_qp_init_attr)
+{
+#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT
+	return mlx5dv_create_qp(context, qp_init_attr_ex, dv_qp_init_attr);
+#else
+	(void)context;
+	(void)qp_init_attr_ex;
+	(void)dv_qp_init_attr;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static void *
+mlx5_glue_dv_create_flow_matcher(struct ibv_context *context,
+				 struct mlx5dv_flow_matcher_attr *matcher_attr,
+				 void *tbl)
+{
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+#ifdef HAVE_MLX5DV_DR
+	(void)context;
+	return mlx5dv_dr_matcher_create(tbl, matcher_attr->priority,
+					matcher_attr->match_criteria_enable,
+					matcher_attr->match_mask);
+#else
+	(void)tbl;
+	return mlx5dv_create_flow_matcher(context, matcher_attr);
+#endif
+#else
+	(void)context;
+	(void)matcher_attr;
+	(void)tbl;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static void *
+mlx5_glue_dv_create_flow(void *matcher,
+			 void *match_value,
+			 size_t num_actions,
+			 void *actions[])
+{
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+#ifdef HAVE_MLX5DV_DR
+	return mlx5dv_dr_rule_create(matcher, match_value, num_actions,
+				     (struct mlx5dv_dr_action **)actions);
+#else
+	size_t i;
+	struct mlx5dv_flow_action_attr actions_attr[8];
+
+	if (num_actions > 8)
+		return NULL;
+	for (i = 0; i < num_actions; i++)
+		actions_attr[i] =
+			*((struct mlx5dv_flow_action_attr *)(actions[i]));
+	return mlx5dv_create_flow(matcher, match_value,
+				  num_actions, actions_attr);
+#endif
+#else
+	(void)matcher;
+	(void)match_value;
+	(void)num_actions;
+	(void)actions;
+	return NULL;
+#endif
+}
+
+static void *
+mlx5_glue_dv_create_flow_action_counter(void *counter_obj, uint32_t offset)
+{
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+#ifdef HAVE_MLX5DV_DR
+	return mlx5dv_dr_action_create_flow_counter(counter_obj, offset);
+#else
+	struct mlx5dv_flow_action_attr *action;
+
+	(void)offset;
+	action = malloc(sizeof(*action));
+	if (!action)
+		return NULL;
+	action->type = MLX5DV_FLOW_ACTION_COUNTERS_DEVX;
+	action->obj = counter_obj;
+	return action;
+#endif
+#else
+	(void)counter_obj;
+	(void)offset;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static void *
+mlx5_glue_dv_create_flow_action_dest_ibv_qp(void *qp)
+{
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+#ifdef HAVE_MLX5DV_DR
+	return mlx5dv_dr_action_create_dest_ibv_qp(qp);
+#else
+	struct mlx5dv_flow_action_attr *action;
+
+	action = malloc(sizeof(*action));
+	if (!action)
+		return NULL;
+	action->type = MLX5DV_FLOW_ACTION_DEST_IBV_QP;
+	action->obj = qp;
+	return action;
+#endif
+#else
+	(void)qp;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static void *
+mlx5_glue_dv_create_flow_action_dest_devx_tir(void *tir)
+{
+#ifdef HAVE_MLX5DV_DR_ACTION_DEST_DEVX_TIR
+	return mlx5dv_dr_action_create_dest_devx_tir(tir);
+#else
+	(void)tir;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static void *
+mlx5_glue_dv_create_flow_action_modify_header
+					(struct ibv_context *ctx,
+					 enum mlx5dv_flow_table_type ft_type,
+					 void *domain, uint64_t flags,
+					 size_t actions_sz,
+					 uint64_t actions[])
+{
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+#ifdef HAVE_MLX5DV_DR
+	(void)ctx;
+	(void)ft_type;
+	return mlx5dv_dr_action_create_modify_header(domain, flags, actions_sz,
+						     (__be64 *)actions);
+#else
+	struct mlx5dv_flow_action_attr *action;
+
+	(void)domain;
+	(void)flags;
+	action = malloc(sizeof(*action));
+	if (!action)
+		return NULL;
+	action->type = MLX5DV_FLOW_ACTION_IBV_FLOW_ACTION;
+	action->action = mlx5dv_create_flow_action_modify_header
+		(ctx, actions_sz, actions, ft_type);
+	return action;
+#endif
+#else
+	(void)ctx;
+	(void)ft_type;
+	(void)domain;
+	(void)flags;
+	(void)actions_sz;
+	(void)actions;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static void *
+mlx5_glue_dv_create_flow_action_packet_reformat
+		(struct ibv_context *ctx,
+		 enum mlx5dv_flow_action_packet_reformat_type reformat_type,
+		 enum mlx5dv_flow_table_type ft_type,
+		 struct mlx5dv_dr_domain *domain,
+		 uint32_t flags, size_t data_sz, void *data)
+{
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+#ifdef HAVE_MLX5DV_DR
+	(void)ctx;
+	(void)ft_type;
+	return mlx5dv_dr_action_create_packet_reformat(domain, flags,
+						       reformat_type, data_sz,
+						       data);
+#else
+	(void)domain;
+	(void)flags;
+	struct mlx5dv_flow_action_attr *action;
+
+	action = malloc(sizeof(*action));
+	if (!action)
+		return NULL;
+	action->type = MLX5DV_FLOW_ACTION_IBV_FLOW_ACTION;
+	action->action = mlx5dv_create_flow_action_packet_reformat
+		(ctx, data_sz, data, reformat_type, ft_type);
+	return action;
+#endif
+#else
+	(void)ctx;
+	(void)reformat_type;
+	(void)ft_type;
+	(void)domain;
+	(void)flags;
+	(void)data_sz;
+	(void)data;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static void *
+mlx5_glue_dv_create_flow_action_tag(uint32_t tag)
+{
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+#ifdef HAVE_MLX5DV_DR
+	return mlx5dv_dr_action_create_tag(tag);
+#else /* HAVE_MLX5DV_DR */
+	struct mlx5dv_flow_action_attr *action;
+
+	action = malloc(sizeof(*action));
+	if (!action)
+		return NULL;
+	action->type = MLX5DV_FLOW_ACTION_TAG;
+	action->tag_value = tag;
+	return action;
+#endif /* HAVE_MLX5DV_DR */
+#else /* HAVE_IBV_FLOW_DV_SUPPORT */
+	(void)tag;
+	errno = ENOTSUP;
+	return NULL;
+#endif /* HAVE_IBV_FLOW_DV_SUPPORT */
+}
+
+static void *
+mlx5_glue_dv_create_flow_action_meter(struct mlx5dv_dr_flow_meter_attr *attr)
+{
+#if defined(HAVE_MLX5DV_DR) && defined(HAVE_MLX5_DR_CREATE_ACTION_FLOW_METER)
+	return mlx5dv_dr_action_create_flow_meter(attr);
+#else
+	(void)attr;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static int
+mlx5_glue_dv_modify_flow_action_meter(void *action,
+				      struct mlx5dv_dr_flow_meter_attr *attr,
+				      uint64_t modify_bits)
+{
+#if defined(HAVE_MLX5DV_DR) && defined(HAVE_MLX5_DR_CREATE_ACTION_FLOW_METER)
+	return mlx5dv_dr_action_modify_flow_meter(action, attr, modify_bits);
+#else
+	(void)action;
+	(void)attr;
+	(void)modify_bits;
+	errno = ENOTSUP;
+	return errno;
+#endif
+}
+
+static void *
+mlx5_glue_dv_create_flow_action_aso(struct mlx5dv_dr_domain *domain,
+				    void *aso_obj,
+				    uint32_t offset,
+				    uint32_t flags,
+				    uint8_t return_reg_c)
+{
+#if defined(HAVE_MLX5DV_DR) && defined(HAVE_MLX5_DR_CREATE_ACTION_ASO)
+	return mlx5dv_dr_action_create_aso(domain, aso_obj, offset,
+					   flags, return_reg_c);
+#else
+	(void)domain;
+	(void)aso_obj;
+	(void)offset;
+	(void)flags;
+	(void)return_reg_c;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static void *
+mlx5_glue_dr_create_flow_action_default_miss(void)
+{
+#if defined(HAVE_MLX5DV_DR) && defined(HAVE_MLX5_DR_CREATE_ACTION_DEFAULT_MISS)
+	return mlx5dv_dr_action_create_default_miss();
+#else
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static int
+mlx5_glue_dv_destroy_flow(void *flow_id)
+{
+#ifdef HAVE_MLX5DV_DR
+	return mlx5dv_dr_rule_destroy(flow_id);
+#else
+	return ibv_destroy_flow(flow_id);
+#endif
+}
+
+static int
+mlx5_glue_dv_destroy_flow_matcher(void *matcher)
+{
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+#ifdef HAVE_MLX5DV_DR
+	return mlx5dv_dr_matcher_destroy(matcher);
+#else
+	return mlx5dv_destroy_flow_matcher(matcher);
+#endif
+#else
+	(void)matcher;
+	errno = ENOTSUP;
+	return errno;
+#endif
+}
+
+static struct ibv_context *
+mlx5_glue_dv_open_device(struct ibv_device *device)
+{
+#ifdef HAVE_IBV_DEVX_OBJ
+	return mlx5dv_open_device(device,
+				  &(struct mlx5dv_context_attr){
+					.flags = MLX5DV_CONTEXT_FLAGS_DEVX,
+				  });
+#else
+	(void)device;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static struct mlx5dv_devx_obj *
+mlx5_glue_devx_obj_create(struct ibv_context *ctx,
+			  const void *in, size_t inlen,
+			  void *out, size_t outlen)
+{
+#ifdef HAVE_IBV_DEVX_OBJ
+	return mlx5dv_devx_obj_create(ctx, in, inlen, out, outlen);
+#else
+	(void)ctx;
+	(void)in;
+	(void)inlen;
+	(void)out;
+	(void)outlen;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static int
+mlx5_glue_devx_obj_destroy(struct mlx5dv_devx_obj *obj)
+{
+#ifdef HAVE_IBV_DEVX_OBJ
+	return mlx5dv_devx_obj_destroy(obj);
+#else
+	(void)obj;
+	return -ENOTSUP;
+#endif
+}
+
+static int
+mlx5_glue_devx_obj_query(struct mlx5dv_devx_obj *obj,
+			 const void *in, size_t inlen,
+			 void *out, size_t outlen)
+{
+#ifdef HAVE_IBV_DEVX_OBJ
+	return mlx5dv_devx_obj_query(obj, in, inlen, out, outlen);
+#else
+	(void)obj;
+	(void)in;
+	(void)inlen;
+	(void)out;
+	(void)outlen;
+	return -ENOTSUP;
+#endif
+}
+
+static int
+mlx5_glue_devx_obj_modify(struct mlx5dv_devx_obj *obj,
+			  const void *in, size_t inlen,
+			  void *out, size_t outlen)
+{
+#ifdef HAVE_IBV_DEVX_OBJ
+	return mlx5dv_devx_obj_modify(obj, in, inlen, out, outlen);
+#else
+	(void)obj;
+	(void)in;
+	(void)inlen;
+	(void)out;
+	(void)outlen;
+	return -ENOTSUP;
+#endif
+}
+
+static int
+mlx5_glue_devx_general_cmd(struct ibv_context *ctx,
+			   const void *in, size_t inlen,
+			   void *out, size_t outlen)
+{
+#ifdef HAVE_IBV_DEVX_OBJ
+	return mlx5dv_devx_general_cmd(ctx, in, inlen, out, outlen);
+#else
+	(void)ctx;
+	(void)in;
+	(void)inlen;
+	(void)out;
+	(void)outlen;
+	return -ENOTSUP;
+#endif
+}
+
+static struct mlx5dv_devx_cmd_comp *
+mlx5_glue_devx_create_cmd_comp(struct ibv_context *ctx)
+{
+#ifdef HAVE_IBV_DEVX_ASYNC
+	return mlx5dv_devx_create_cmd_comp(ctx);
+#else
+	(void)ctx;
+	errno = -ENOTSUP;
+	return NULL;
+#endif
+}
+
+static void
+mlx5_glue_devx_destroy_cmd_comp(struct mlx5dv_devx_cmd_comp *cmd_comp)
+{
+#ifdef HAVE_IBV_DEVX_ASYNC
+	mlx5dv_devx_destroy_cmd_comp(cmd_comp);
+#else
+	(void)cmd_comp;
+	errno = -ENOTSUP;
+#endif
+}
+
+static int
+mlx5_glue_devx_obj_query_async(struct mlx5dv_devx_obj *obj, const void *in,
+			       size_t inlen, size_t outlen, uint64_t wr_id,
+			       struct mlx5dv_devx_cmd_comp *cmd_comp)
+{
+#ifdef HAVE_IBV_DEVX_ASYNC
+	return mlx5dv_devx_obj_query_async(obj, in, inlen, outlen, wr_id,
+					   cmd_comp);
+#else
+	(void)obj;
+	(void)in;
+	(void)inlen;
+	(void)outlen;
+	(void)wr_id;
+	(void)cmd_comp;
+	return -ENOTSUP;
+#endif
+}
+
+static int
+mlx5_glue_devx_get_async_cmd_comp(struct mlx5dv_devx_cmd_comp *cmd_comp,
+				  struct mlx5dv_devx_async_cmd_hdr *cmd_resp,
+				  size_t cmd_resp_len)
+{
+#ifdef HAVE_IBV_DEVX_ASYNC
+	return mlx5dv_devx_get_async_cmd_comp(cmd_comp, cmd_resp,
+					      cmd_resp_len);
+#else
+	(void)cmd_comp;
+	(void)cmd_resp;
+	(void)cmd_resp_len;
+	return -ENOTSUP;
+#endif
+}
+
+static struct mlx5dv_devx_umem *
+mlx5_glue_devx_umem_reg(struct ibv_context *context, void *addr, size_t size,
+			uint32_t access)
+{
+#ifdef HAVE_IBV_DEVX_OBJ
+	return mlx5dv_devx_umem_reg(context, addr, size, access);
+#else
+	(void)context;
+	(void)addr;
+	(void)size;
+	(void)access;
+	errno = -ENOTSUP;
+	return NULL;
+#endif
+}
+
+static int
+mlx5_glue_devx_umem_dereg(struct mlx5dv_devx_umem *dv_devx_umem)
+{
+#ifdef HAVE_IBV_DEVX_OBJ
+	return mlx5dv_devx_umem_dereg(dv_devx_umem);
+#else
+	(void)dv_devx_umem;
+	return -ENOTSUP;
+#endif
+}
+
+static int
+mlx5_glue_devx_qp_query(struct ibv_qp *qp,
+			const void *in, size_t inlen,
+			void *out, size_t outlen)
+{
+#ifdef HAVE_IBV_DEVX_QP
+	return mlx5dv_devx_qp_query(qp, in, inlen, out, outlen);
+#else
+	(void)qp;
+	(void)in;
+	(void)inlen;
+	(void)out;
+	(void)outlen;
+	errno = ENOTSUP;
+	return errno;
+#endif
+}
+
+static int
+mlx5_glue_devx_wq_query(struct ibv_wq *wq, const void *in, size_t inlen,
+			void *out, size_t outlen)
+{
+#ifdef HAVE_IBV_DEVX_QP
+	return mlx5dv_devx_wq_query(wq, in, inlen, out, outlen);
+#else
+	(void)wq;
+	(void)in;
+	(void)inlen;
+	(void)out;
+	(void)outlen;
+	errno = ENOTSUP;
+	return errno;
+#endif
+}
+
+static int
+mlx5_glue_devx_port_query(struct ibv_context *ctx,
+			  uint32_t port_num,
+			  struct mlx5_port_info *info)
+{
+	int err = 0;
+
+	info->query_flags = 0;
+#ifdef HAVE_MLX5DV_DR_DEVX_PORT_V35
+	/* The DevX port query API is implemented (rdma-core v35 and above). */
+	struct mlx5_ib_uapi_query_port devx_port;
+
+	memset(&devx_port, 0, sizeof(devx_port));
+	err = mlx5dv_query_port(ctx, port_num, &devx_port);
+	if (err)
+		return err;
+	if (devx_port.flags & MLX5DV_QUERY_PORT_VPORT_REG_C0) {
+		info->vport_meta_tag = devx_port.reg_c0.value;
+		info->vport_meta_mask = devx_port.reg_c0.mask;
+		info->query_flags |= MLX5_PORT_QUERY_REG_C0;
+	}
+	if (devx_port.flags & MLX5DV_QUERY_PORT_VPORT) {
+		info->vport_id = devx_port.vport;
+		info->query_flags |= MLX5_PORT_QUERY_VPORT;
+	}
+#else
+#ifdef HAVE_MLX5DV_DR_DEVX_PORT
+	/* The legacy DevX port query API is implemented (prior v35). */
+	struct mlx5dv_devx_port devx_port = {
+		.comp_mask = MLX5DV_DEVX_PORT_VPORT |
+			     MLX5DV_DEVX_PORT_MATCH_REG_C_0
+	};
+
+	err = mlx5dv_query_devx_port(ctx, port_num, &devx_port);
+	if (err)
+		return err;
+	if (devx_port.comp_mask & MLX5DV_DEVX_PORT_MATCH_REG_C_0) {
+		info->vport_meta_tag = devx_port.reg_c_0.value;
+		info->vport_meta_mask = devx_port.reg_c_0.mask;
+		info->query_flags |= MLX5_PORT_QUERY_REG_C0;
+	}
+	if (devx_port.comp_mask & MLX5DV_DEVX_PORT_VPORT) {
+		info->vport_id = devx_port.vport_num;
+		info->query_flags |= MLX5_PORT_QUERY_VPORT;
+	}
+#else
+	RTE_SET_USED(ctx);
+	RTE_SET_USED(port_num);
+#endif /* HAVE_MLX5DV_DR_DEVX_PORT */
+#endif /* HAVE_MLX5DV_DR_DEVX_PORT_V35 */
+	return err;
+}
+
+static int
+mlx5_glue_dr_dump_single_rule(FILE *file, void *rule)
+{
+#ifdef HAVE_MLX5_DR_FLOW_DUMP_RULE
+	return mlx5dv_dump_dr_rule(file, rule);
+#else
+	RTE_SET_USED(file);
+	RTE_SET_USED(rule);
+	return -ENOTSUP;
+#endif
+}
+
+static int
+mlx5_glue_dr_dump_domain(FILE *file, void *domain)
+{
+#ifdef HAVE_MLX5_DR_FLOW_DUMP
+	return mlx5dv_dump_dr_domain(file, domain);
+#else
+	RTE_SET_USED(file);
+	RTE_SET_USED(domain);
+	return -ENOTSUP;
+#endif
+}
+
+static void *
+mlx5_glue_dr_create_flow_action_sampler
+			(struct mlx5dv_dr_flow_sampler_attr *attr)
+{
+#ifdef HAVE_MLX5_DR_CREATE_ACTION_FLOW_SAMPLE
+	return mlx5dv_dr_action_create_flow_sampler(attr);
+#else
+	(void)attr;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static void *
+mlx5_glue_dr_action_create_dest_array
+			(void *domain,
+			 size_t num_dest,
+			 struct mlx5dv_dr_action_dest_attr *dests[])
+{
+#ifdef HAVE_MLX5_DR_CREATE_ACTION_DEST_ARRAY
+	return mlx5dv_dr_action_create_dest_array
+				(domain,
+				num_dest,
+				dests);
+#else
+	(void)domain;
+	(void)num_dest;
+	(void)dests;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static int
+mlx5_glue_devx_query_eqn(struct ibv_context *ctx, uint32_t cpus,
+			 uint32_t *eqn)
+{
+#ifdef HAVE_IBV_DEVX_OBJ
+	return mlx5dv_devx_query_eqn(ctx, cpus, eqn);
+#else
+	(void)ctx;
+	(void)cpus;
+	(void)eqn;
+	return -ENOTSUP;
+#endif
+}
+
+static struct mlx5dv_devx_event_channel *
+mlx5_glue_devx_create_event_channel(struct ibv_context *ctx, int flags)
+{
+#ifdef HAVE_IBV_DEVX_EVENT
+	return mlx5dv_devx_create_event_channel(ctx, flags);
+#else
+	(void)ctx;
+	(void)flags;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static void
+mlx5_glue_devx_destroy_event_channel(struct mlx5dv_devx_event_channel *eventc)
+{
+#ifdef HAVE_IBV_DEVX_EVENT
+	mlx5dv_devx_destroy_event_channel(eventc);
+#else
+	(void)eventc;
+#endif
+}
+
+static int
+mlx5_glue_devx_subscribe_devx_event(struct mlx5dv_devx_event_channel *eventc,
+				    struct mlx5dv_devx_obj *obj,
+				    uint16_t events_sz, uint16_t events_num[],
+				    uint64_t cookie)
+{
+#ifdef HAVE_IBV_DEVX_EVENT
+	return mlx5dv_devx_subscribe_devx_event(eventc, obj, events_sz,
+						events_num, cookie);
+#else
+	(void)eventc;
+	(void)obj;
+	(void)events_sz;
+	(void)events_num;
+	(void)cookie;
+	return -ENOTSUP;
+#endif
+}
+
+static int
+mlx5_glue_devx_subscribe_devx_event_fd(struct mlx5dv_devx_event_channel *eventc,
+				       int fd, struct mlx5dv_devx_obj *obj,
+				       uint16_t event_num)
+{
+#ifdef HAVE_IBV_DEVX_EVENT
+	return mlx5dv_devx_subscribe_devx_event_fd(eventc, fd, obj, event_num);
+#else
+	(void)eventc;
+	(void)fd;
+	(void)obj;
+	(void)event_num;
+	return -ENOTSUP;
+#endif
+}
+
+static ssize_t
+mlx5_glue_devx_get_event(struct mlx5dv_devx_event_channel *eventc,
+			 struct mlx5dv_devx_async_event_hdr *event_data,
+			 size_t event_resp_len)
+{
+#ifdef HAVE_IBV_DEVX_EVENT
+	return mlx5dv_devx_get_event(eventc, event_data, event_resp_len);
+#else
+	(void)eventc;
+	(void)event_data;
+	(void)event_resp_len;
+	errno = ENOTSUP;
+	return -1;
+#endif
+}
+
+static struct mlx5dv_devx_uar *
+mlx5_glue_devx_alloc_uar(struct ibv_context *context, uint32_t flags)
+{
+#ifdef HAVE_IBV_DEVX_OBJ
+	return mlx5dv_devx_alloc_uar(context, flags);
+#else
+	(void)context;
+	(void)flags;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static void
+mlx5_glue_devx_free_uar(struct mlx5dv_devx_uar *devx_uar)
+{
+#ifdef HAVE_IBV_DEVX_OBJ
+	mlx5dv_devx_free_uar(devx_uar);
+#else
+	(void)devx_uar;
+#endif
+}
+
+static struct mlx5dv_var *
+mlx5_glue_dv_alloc_var(struct ibv_context *context, uint32_t flags)
+{
+#ifdef HAVE_IBV_VAR
+	return mlx5dv_alloc_var(context, flags);
+#else
+	(void)context;
+	(void)flags;
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static void
+mlx5_glue_dv_free_var(struct mlx5dv_var *var)
+{
+#ifdef HAVE_IBV_VAR
+	mlx5dv_free_var(var);
+#else
+	(void)var;
+	errno = ENOTSUP;
+#endif
+}
+
+static void
+mlx5_glue_dr_reclaim_domain_memory(void *domain, uint32_t enable)
+{
+#ifdef HAVE_MLX5DV_DR_MEM_RECLAIM
+	mlx5dv_dr_domain_set_reclaim_device_memory(domain, enable);
+#else
+	(void)(enable);
+	(void)(domain);
+#endif
+}
+
+static struct mlx5dv_pp *
+mlx5_glue_dv_alloc_pp(struct ibv_context *context,
+		      size_t pp_context_sz,
+		      const void *pp_context,
+		      uint32_t flags)
+{
+#ifdef HAVE_MLX5DV_PP_ALLOC
+	return mlx5dv_pp_alloc(context, pp_context_sz, pp_context, flags);
+#else
+	RTE_SET_USED(context);
+	RTE_SET_USED(pp_context_sz);
+	RTE_SET_USED(pp_context);
+	RTE_SET_USED(flags);
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static void
+mlx5_glue_dr_allow_duplicate_rules(void *domain, uint32_t allow)
+{
+#ifdef HAVE_MLX5_DR_ALLOW_DUPLICATE
+	mlx5dv_dr_domain_allow_duplicate_rules(domain, allow);
+#else
+	(void)(allow);
+	(void)(domain);
+#endif
+}
+
+static void
+mlx5_glue_dv_free_pp(struct mlx5dv_pp *pp)
+{
+#ifdef HAVE_MLX5DV_PP_ALLOC
+	mlx5dv_pp_free(pp);
+#else
+	RTE_SET_USED(pp);
+#endif
+}
+
+__rte_cache_aligned
+const struct mlx5_glue *mlx5_glue = &(const struct mlx5_glue) {
+	.version = MLX5_GLUE_VERSION,
+	.fork_init = mlx5_glue_fork_init,
+	.alloc_pd = mlx5_glue_alloc_pd,
+	.dealloc_pd = mlx5_glue_dealloc_pd,
+	.get_device_list = mlx5_glue_get_device_list,
+	.free_device_list = mlx5_glue_free_device_list,
+	.open_device = mlx5_glue_open_device,
+	.close_device = mlx5_glue_close_device,
+	.query_device = mlx5_glue_query_device,
+	.query_device_ex = mlx5_glue_query_device_ex,
+	.query_rt_values_ex = mlx5_glue_query_rt_values_ex,
+	.query_port = mlx5_glue_query_port,
+	.create_comp_channel = mlx5_glue_create_comp_channel,
+	.destroy_comp_channel = mlx5_glue_destroy_comp_channel,
+	.create_cq = mlx5_glue_create_cq,
+	.destroy_cq = mlx5_glue_destroy_cq,
+	.get_cq_event = mlx5_glue_get_cq_event,
+	.ack_cq_events = mlx5_glue_ack_cq_events,
+	.create_rwq_ind_table = mlx5_glue_create_rwq_ind_table,
+	.destroy_rwq_ind_table = mlx5_glue_destroy_rwq_ind_table,
+	.create_wq = mlx5_glue_create_wq,
+	.destroy_wq = mlx5_glue_destroy_wq,
+	.modify_wq = mlx5_glue_modify_wq,
+	.create_flow = mlx5_glue_create_flow,
+	.destroy_flow = mlx5_glue_destroy_flow,
+	.destroy_flow_action = mlx5_glue_destroy_flow_action,
+	.create_qp = mlx5_glue_create_qp,
+	.create_qp_ex = mlx5_glue_create_qp_ex,
+	.destroy_qp = mlx5_glue_destroy_qp,
+	.modify_qp = mlx5_glue_modify_qp,
+	.reg_mr = mlx5_glue_reg_mr,
+	.alloc_null_mr = mlx5_glue_alloc_null_mr,
+	.dereg_mr = mlx5_glue_dereg_mr,
+	.create_counter_set = mlx5_glue_create_counter_set,
+	.destroy_counter_set = mlx5_glue_destroy_counter_set,
+	.describe_counter_set = mlx5_glue_describe_counter_set,
+	.query_counter_set = mlx5_glue_query_counter_set,
+	.create_counters = mlx5_glue_create_counters,
+	.destroy_counters = mlx5_glue_destroy_counters,
+	.attach_counters = mlx5_glue_attach_counters,
+	.query_counters = mlx5_glue_query_counters,
+	.ack_async_event = mlx5_glue_ack_async_event,
+	.get_async_event = mlx5_glue_get_async_event,
+	.port_state_str = mlx5_glue_port_state_str,
+	.cq_ex_to_cq = mlx5_glue_cq_ex_to_cq,
+	.dr_create_flow_action_dest_flow_tbl =
+		mlx5_glue_dr_create_flow_action_dest_flow_tbl,
+	.dr_create_flow_action_dest_port =
+		mlx5_glue_dr_create_flow_action_dest_port,
+	.dr_create_flow_action_drop =
+		mlx5_glue_dr_create_flow_action_drop,
+	.dr_create_flow_action_push_vlan =
+		mlx5_glue_dr_create_flow_action_push_vlan,
+	.dr_create_flow_action_pop_vlan =
+		mlx5_glue_dr_create_flow_action_pop_vlan,
+	.dr_create_flow_tbl = mlx5_glue_dr_create_flow_tbl,
+	.dr_destroy_flow_tbl = mlx5_glue_dr_destroy_flow_tbl,
+	.dr_create_domain = mlx5_glue_dr_create_domain,
+	.dr_destroy_domain = mlx5_glue_dr_destroy_domain,
+	.dr_sync_domain = mlx5_glue_dr_sync_domain,
+	.dv_create_cq = mlx5_glue_dv_create_cq,
+	.dv_create_wq = mlx5_glue_dv_create_wq,
+	.dv_query_device = mlx5_glue_dv_query_device,
+	.dv_set_context_attr = mlx5_glue_dv_set_context_attr,
+	.dv_init_obj = mlx5_glue_dv_init_obj,
+	.dv_create_qp = mlx5_glue_dv_create_qp,
+	.dv_create_flow_matcher = mlx5_glue_dv_create_flow_matcher,
+	.dv_create_flow = mlx5_glue_dv_create_flow,
+	.dv_create_flow_action_counter =
+		mlx5_glue_dv_create_flow_action_counter,
+	.dv_create_flow_action_dest_ibv_qp =
+		mlx5_glue_dv_create_flow_action_dest_ibv_qp,
+	.dv_create_flow_action_dest_devx_tir =
+		mlx5_glue_dv_create_flow_action_dest_devx_tir,
+	.dv_create_flow_action_modify_header =
+		mlx5_glue_dv_create_flow_action_modify_header,
+	.dv_create_flow_action_packet_reformat =
+		mlx5_glue_dv_create_flow_action_packet_reformat,
+	.dv_create_flow_action_tag =  mlx5_glue_dv_create_flow_action_tag,
+	.dv_create_flow_action_meter = mlx5_glue_dv_create_flow_action_meter,
+	.dv_modify_flow_action_meter = mlx5_glue_dv_modify_flow_action_meter,
+	.dv_create_flow_action_aso = mlx5_glue_dv_create_flow_action_aso,
+	.dr_create_flow_action_default_miss =
+		mlx5_glue_dr_create_flow_action_default_miss,
+	.dv_destroy_flow = mlx5_glue_dv_destroy_flow,
+	.dv_destroy_flow_matcher = mlx5_glue_dv_destroy_flow_matcher,
+	.dv_open_device = mlx5_glue_dv_open_device,
+	.devx_obj_create = mlx5_glue_devx_obj_create,
+	.devx_obj_destroy = mlx5_glue_devx_obj_destroy,
+	.devx_obj_query = mlx5_glue_devx_obj_query,
+	.devx_obj_modify = mlx5_glue_devx_obj_modify,
+	.devx_general_cmd = mlx5_glue_devx_general_cmd,
+	.devx_create_cmd_comp = mlx5_glue_devx_create_cmd_comp,
+	.devx_destroy_cmd_comp = mlx5_glue_devx_destroy_cmd_comp,
+	.devx_obj_query_async = mlx5_glue_devx_obj_query_async,
+	.devx_get_async_cmd_comp = mlx5_glue_devx_get_async_cmd_comp,
+	.devx_umem_reg = mlx5_glue_devx_umem_reg,
+	.devx_umem_dereg = mlx5_glue_devx_umem_dereg,
+	.devx_qp_query = mlx5_glue_devx_qp_query,
+	.devx_wq_query = mlx5_glue_devx_wq_query,
+	.devx_port_query = mlx5_glue_devx_port_query,
+	.dr_dump_domain = mlx5_glue_dr_dump_domain,
+	.dr_dump_rule = mlx5_glue_dr_dump_single_rule,
+	.dr_reclaim_domain_memory = mlx5_glue_dr_reclaim_domain_memory,
+	.dr_create_flow_action_sampler =
+		mlx5_glue_dr_create_flow_action_sampler,
+	.dr_create_flow_action_dest_array =
+		mlx5_glue_dr_action_create_dest_array,
+	.dr_allow_duplicate_rules = mlx5_glue_dr_allow_duplicate_rules,
+	.devx_query_eqn = mlx5_glue_devx_query_eqn,
+	.devx_create_event_channel = mlx5_glue_devx_create_event_channel,
+	.devx_destroy_event_channel = mlx5_glue_devx_destroy_event_channel,
+	.devx_subscribe_devx_event = mlx5_glue_devx_subscribe_devx_event,
+	.devx_subscribe_devx_event_fd = mlx5_glue_devx_subscribe_devx_event_fd,
+	.devx_get_event = mlx5_glue_devx_get_event,
+	.devx_alloc_uar = mlx5_glue_devx_alloc_uar,
+	.devx_free_uar = mlx5_glue_devx_free_uar,
+	.dv_alloc_var = mlx5_glue_dv_alloc_var,
+	.dv_free_var = mlx5_glue_dv_free_var,
+	.dv_alloc_pp = mlx5_glue_dv_alloc_pp,
+	.dv_free_pp = mlx5_glue_dv_free_pp,
+};
diff --git a/drivers/common/mlx5/freebsd/mlx5_glue.h b/drivers/common/mlx5/freebsd/mlx5_glue.h
new file mode 100644
index 0000000000..f39ef2dac7
--- /dev/null
+++ b/drivers/common/mlx5/freebsd/mlx5_glue.h
@@ -0,0 +1,373 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2018 6WIND S.A.
+ * Copyright 2018 Mellanox Technologies, Ltd
+ */
+
+#ifndef MLX5_GLUE_H_
+#define MLX5_GLUE_H_
+
+#include <stddef.h>
+#include <stdint.h>
+/* Verbs headers do not support -pedantic. */
+#ifdef PEDANTIC
+#pragma GCC diagnostic ignored "-Wpedantic"
+#endif
+#include <infiniband/mlx5dv.h>
+#include <infiniband/verbs.h>
+#ifdef PEDANTIC
+#pragma GCC diagnostic error "-Wpedantic"
+#endif
+
+#include <rte_byteorder.h>
+
+#include "mlx5_autoconf.h"
+
+#ifndef MLX5_GLUE_VERSION
+#define MLX5_GLUE_VERSION ""
+#endif
+
+#ifndef HAVE_IBV_DEVICE_COUNTERS_SET_V42
+struct ibv_counter_set;
+struct ibv_counter_set_data;
+struct ibv_counter_set_description;
+struct ibv_counter_set_init_attr;
+struct ibv_query_counter_set_attr;
+#endif
+
+#ifndef HAVE_IBV_DEVICE_COUNTERS_SET_V45
+struct ibv_counters;
+struct ibv_counters_init_attr;
+struct ibv_counter_attach_attr;
+#endif
+
+#ifndef HAVE_IBV_DEVICE_TUNNEL_SUPPORT
+struct mlx5dv_qp_init_attr;
+#endif
+
+#ifndef HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT
+struct mlx5dv_wq_init_attr;
+#endif
+
+#ifndef HAVE_IBV_FLOW_DV_SUPPORT
+struct mlx5dv_flow_matcher;
+struct mlx5dv_flow_matcher_attr;
+struct mlx5dv_flow_action_attr;
+struct mlx5dv_flow_match_parameters;
+struct mlx5dv_dr_flow_meter_attr;
+struct ibv_flow_action;
+enum mlx5dv_flow_action_packet_reformat_type { packet_reformat_type = 0, };
+enum mlx5dv_flow_table_type { flow_table_type = 0, };
+#endif
+
+#ifndef HAVE_IBV_FLOW_DEVX_COUNTERS
+#define MLX5DV_FLOW_ACTION_COUNTERS_DEVX 0
+#endif
+
+#ifndef HAVE_IBV_DEVX_OBJ
+struct mlx5dv_devx_obj;
+struct mlx5dv_devx_umem { uint32_t umem_id; };
+struct mlx5dv_devx_uar { void *reg_addr; void *base_addr; uint32_t page_id; };
+#endif
+
+#ifndef HAVE_IBV_DEVX_ASYNC
+struct mlx5dv_devx_cmd_comp;
+struct mlx5dv_devx_async_cmd_hdr;
+#endif
+
+#ifndef HAVE_MLX5DV_DR
+enum  mlx5dv_dr_domain_type { unused, };
+struct mlx5dv_dr_domain;
+struct mlx5dv_dr_action;
+#define MLX5DV_DR_ACTION_FLAGS_ROOT_LEVEL 1
+#endif
+
+#ifndef HAVE_MLX5DV_DR_DEVX_PORT
+struct mlx5dv_devx_port;
+#endif
+
+#ifndef HAVE_MLX5DV_DR_DEVX_PORT_V35
+struct mlx5dv_port;
+#endif
+
+#define MLX5_PORT_QUERY_VPORT (1u << 0)
+#define MLX5_PORT_QUERY_REG_C0 (1u << 1)
+
+struct mlx5_port_info {
+	uint16_t query_flags;
+	uint16_t vport_id; /* Associated VF vport index (if any). */
+	uint32_t vport_meta_tag; /* Used for vport index match ove VF LAG. */
+	uint32_t vport_meta_mask; /* Used for vport index field match mask. */
+};
+
+#ifndef HAVE_MLX5_DR_CREATE_ACTION_FLOW_METER
+struct mlx5dv_dr_flow_meter_attr;
+#endif
+
+#ifndef HAVE_MLX5_DR_CREATE_ACTION_FLOW_SAMPLE
+struct mlx5dv_dr_flow_sampler_attr {
+	uint32_t sample_ratio;
+	void *default_next_table;
+	size_t num_sample_actions;
+	struct mlx5dv_dr_action **sample_actions;
+	uint64_t action;
+};
+#endif
+
+#ifndef HAVE_MLX5_DR_CREATE_ACTION_DEST_ARRAY
+enum mlx5dv_dr_action_dest_type {
+	MLX5DV_DR_ACTION_DEST,
+	MLX5DV_DR_ACTION_DEST_REFORMAT,
+};
+struct mlx5dv_dr_action_dest_reformat {
+	struct mlx5dv_dr_action *reformat;
+	struct mlx5dv_dr_action *dest;
+};
+struct mlx5dv_dr_action_dest_attr {
+	enum mlx5dv_dr_action_dest_type type;
+	union {
+		struct mlx5dv_dr_action *dest;
+		struct mlx5dv_dr_action_dest_reformat *dest_reformat;
+	};
+};
+#endif
+
+#ifndef HAVE_IBV_DEVX_EVENT
+struct mlx5dv_devx_event_channel { int fd; };
+struct mlx5dv_devx_async_event_hdr;
+#define MLX5DV_DEVX_CREATE_EVENT_CHANNEL_FLAGS_OMIT_EV_DATA 1
+#endif
+
+#ifndef HAVE_IBV_VAR
+struct mlx5dv_var { uint32_t page_id; uint32_t length; off_t mmap_off;
+			uint64_t comp_mask; };
+#endif
+
+#ifndef HAVE_IBV_RELAXED_ORDERING
+#define IBV_ACCESS_RELAXED_ORDERING 0
+#endif
+
+struct mlx5_glue {
+	const char *version;
+	int (*fork_init)(void);
+	struct ibv_pd *(*alloc_pd)(struct ibv_context *context);
+	int (*dealloc_pd)(struct ibv_pd *pd);
+	struct ibv_device **(*get_device_list)(int *num_devices);
+	void (*free_device_list)(struct ibv_device **list);
+	struct ibv_context *(*open_device)(struct ibv_device *device);
+	int (*close_device)(struct ibv_context *context);
+	int (*query_device)(struct ibv_context *context,
+			    struct ibv_device_attr *device_attr);
+	int (*query_device_ex)(struct ibv_context *context,
+			       const struct ibv_query_device_ex_input *input,
+			       struct ibv_device_attr_ex *attr);
+	int (*query_rt_values_ex)(struct ibv_context *context,
+			       struct ibv_values_ex *values);
+	int (*query_port)(struct ibv_context *context, uint8_t port_num,
+			  struct ibv_port_attr *port_attr);
+	struct ibv_comp_channel *(*create_comp_channel)
+		(struct ibv_context *context);
+	int (*destroy_comp_channel)(struct ibv_comp_channel *channel);
+	struct ibv_cq *(*create_cq)(struct ibv_context *context, int cqe,
+				    void *cq_context,
+				    struct ibv_comp_channel *channel,
+				    int comp_vector);
+	int (*destroy_cq)(struct ibv_cq *cq);
+	int (*get_cq_event)(struct ibv_comp_channel *channel,
+			    struct ibv_cq **cq, void **cq_context);
+	void (*ack_cq_events)(struct ibv_cq *cq, unsigned int nevents);
+	struct ibv_rwq_ind_table *(*create_rwq_ind_table)
+		(struct ibv_context *context,
+		 struct ibv_rwq_ind_table_init_attr *init_attr);
+	int (*destroy_rwq_ind_table)(struct ibv_rwq_ind_table *rwq_ind_table);
+	struct ibv_wq *(*create_wq)(struct ibv_context *context,
+				    struct ibv_wq_init_attr *wq_init_attr);
+	int (*destroy_wq)(struct ibv_wq *wq);
+	int (*modify_wq)(struct ibv_wq *wq, struct ibv_wq_attr *wq_attr);
+	struct ibv_flow *(*create_flow)(struct ibv_qp *qp,
+					struct ibv_flow_attr *flow);
+	int (*destroy_flow)(struct ibv_flow *flow_id);
+	int (*destroy_flow_action)(void *action);
+	struct ibv_qp *(*create_qp)(struct ibv_pd *pd,
+				    struct ibv_qp_init_attr *qp_init_attr);
+	struct ibv_qp *(*create_qp_ex)
+		(struct ibv_context *context,
+		 struct ibv_qp_init_attr_ex *qp_init_attr_ex);
+	int (*destroy_qp)(struct ibv_qp *qp);
+	int (*modify_qp)(struct ibv_qp *qp, struct ibv_qp_attr *attr,
+			 int attr_mask);
+	struct ibv_mr *(*reg_mr)(struct ibv_pd *pd, void *addr,
+				 size_t length, int access);
+	struct ibv_mr *(*alloc_null_mr)(struct ibv_pd *pd);
+	int (*dereg_mr)(struct ibv_mr *mr);
+	struct ibv_counter_set *(*create_counter_set)
+		(struct ibv_context *context,
+		 struct ibv_counter_set_init_attr *init_attr);
+	int (*destroy_counter_set)(struct ibv_counter_set *cs);
+	int (*describe_counter_set)
+		(struct ibv_context *context,
+		 uint16_t counter_set_id,
+		 struct ibv_counter_set_description *cs_desc);
+	int (*query_counter_set)(struct ibv_query_counter_set_attr *query_attr,
+				 struct ibv_counter_set_data *cs_data);
+	struct ibv_counters *(*create_counters)
+		(struct ibv_context *context,
+		 struct ibv_counters_init_attr *init_attr);
+	int (*destroy_counters)(struct ibv_counters *counters);
+	int (*attach_counters)(struct ibv_counters *counters,
+			       struct ibv_counter_attach_attr *attr,
+			       struct ibv_flow *flow);
+	int (*query_counters)(struct ibv_counters *counters,
+			      uint64_t *counters_value,
+			      uint32_t ncounters,
+			      uint32_t flags);
+	void (*ack_async_event)(struct ibv_async_event *event);
+	int (*get_async_event)(struct ibv_context *context,
+			       struct ibv_async_event *event);
+	const char *(*port_state_str)(enum ibv_port_state port_state);
+	struct ibv_cq *(*cq_ex_to_cq)(struct ibv_cq_ex *cq);
+	void *(*dr_create_flow_action_dest_flow_tbl)(void *tbl);
+	void *(*dr_create_flow_action_dest_port)(void *domain,
+						 uint32_t port);
+	void *(*dr_create_flow_action_drop)(void);
+	void *(*dr_create_flow_action_push_vlan)
+					(struct mlx5dv_dr_domain *domain,
+					 rte_be32_t vlan_tag);
+	void *(*dr_create_flow_action_pop_vlan)(void);
+	void *(*dr_create_flow_tbl)(void *domain, uint32_t level);
+	int (*dr_destroy_flow_tbl)(void *tbl);
+	void *(*dr_create_domain)(struct ibv_context *ctx,
+				  enum mlx5dv_dr_domain_type domain);
+	int (*dr_destroy_domain)(void *domain);
+	int (*dr_sync_domain)(void *domain, uint32_t flags);
+	struct ibv_cq_ex *(*dv_create_cq)
+		(struct ibv_context *context,
+		 struct ibv_cq_init_attr_ex *cq_attr,
+		 struct mlx5dv_cq_init_attr *mlx5_cq_attr);
+	struct ibv_wq *(*dv_create_wq)
+		(struct ibv_context *context,
+		 struct ibv_wq_init_attr *wq_attr,
+		 struct mlx5dv_wq_init_attr *mlx5_wq_attr);
+	int (*dv_query_device)(struct ibv_context *ctx_in,
+			       struct mlx5dv_context *attrs_out);
+	int (*dv_set_context_attr)(struct ibv_context *ibv_ctx,
+				   enum mlx5dv_set_ctx_attr_type type,
+				   void *attr);
+	int (*dv_init_obj)(struct mlx5dv_obj *obj, uint64_t obj_type);
+	struct ibv_qp *(*dv_create_qp)
+		(struct ibv_context *context,
+		 struct ibv_qp_init_attr_ex *qp_init_attr_ex,
+		 struct mlx5dv_qp_init_attr *dv_qp_init_attr);
+	void *(*dv_create_flow_matcher)
+		(struct ibv_context *context,
+		 struct mlx5dv_flow_matcher_attr *matcher_attr,
+		 void *tbl);
+	void *(*dv_create_flow)(void *matcher, void *match_value,
+			  size_t num_actions, void *actions[]);
+	void *(*dv_create_flow_action_counter)(void *obj, uint32_t  offset);
+	void *(*dv_create_flow_action_dest_ibv_qp)(void *qp);
+	void *(*dv_create_flow_action_dest_devx_tir)(void *tir);
+	void *(*dv_create_flow_action_modify_header)
+		(struct ibv_context *ctx, enum mlx5dv_flow_table_type ft_type,
+		 void *domain, uint64_t flags, size_t actions_sz,
+		 uint64_t actions[]);
+	void *(*dv_create_flow_action_packet_reformat)
+		(struct ibv_context *ctx,
+		 enum mlx5dv_flow_action_packet_reformat_type reformat_type,
+		 enum mlx5dv_flow_table_type ft_type,
+		 struct mlx5dv_dr_domain *domain,
+		 uint32_t flags, size_t data_sz, void *data);
+	void *(*dv_create_flow_action_tag)(uint32_t tag);
+	void *(*dv_create_flow_action_meter)
+		(struct mlx5dv_dr_flow_meter_attr *attr);
+	int (*dv_modify_flow_action_meter)(void *action,
+		struct mlx5dv_dr_flow_meter_attr *attr, uint64_t modify_bits);
+	void *(*dr_create_flow_action_default_miss)(void);
+	int (*dv_destroy_flow)(void *flow);
+	int (*dv_destroy_flow_matcher)(void *matcher);
+	struct ibv_context *(*dv_open_device)(struct ibv_device *device);
+	struct mlx5dv_var *(*dv_alloc_var)(struct ibv_context *context,
+					   uint32_t flags);
+	void (*dv_free_var)(struct mlx5dv_var *var);
+	struct mlx5dv_devx_uar *(*devx_alloc_uar)(struct ibv_context *context,
+						  uint32_t flags);
+	void (*devx_free_uar)(struct mlx5dv_devx_uar *devx_uar);
+	struct mlx5dv_devx_obj *(*devx_obj_create)
+					(struct ibv_context *ctx,
+					 const void *in, size_t inlen,
+					 void *out, size_t outlen);
+	int (*devx_obj_destroy)(struct mlx5dv_devx_obj *obj);
+	int (*devx_obj_query)(struct mlx5dv_devx_obj *obj,
+			      const void *in, size_t inlen,
+			      void *out, size_t outlen);
+	int (*devx_obj_modify)(struct mlx5dv_devx_obj *obj,
+			       const void *in, size_t inlen,
+			       void *out, size_t outlen);
+	int (*devx_general_cmd)(struct ibv_context *context,
+				const void *in, size_t inlen,
+				void *out, size_t outlen);
+	struct mlx5dv_devx_cmd_comp *(*devx_create_cmd_comp)
+					(struct ibv_context *context);
+	void (*devx_destroy_cmd_comp)(struct mlx5dv_devx_cmd_comp *cmd_comp);
+	int (*devx_obj_query_async)(struct mlx5dv_devx_obj *obj,
+				    const void *in, size_t inlen,
+				    size_t outlen, uint64_t wr_id,
+				    struct mlx5dv_devx_cmd_comp *cmd_comp);
+	int (*devx_get_async_cmd_comp)(struct mlx5dv_devx_cmd_comp *cmd_comp,
+				       struct mlx5dv_devx_async_cmd_hdr *resp,
+				       size_t cmd_resp_len);
+	struct mlx5dv_devx_umem *(*devx_umem_reg)(struct ibv_context *context,
+						  void *addr, size_t size,
+						  uint32_t access);
+	int (*devx_umem_dereg)(struct mlx5dv_devx_umem *dv_devx_umem);
+	int (*devx_qp_query)(struct ibv_qp *qp,
+			     const void *in, size_t inlen,
+			     void *out, size_t outlen);
+	int (*devx_wq_query)(struct ibv_wq *wq, const void *in, size_t inlen,
+			     void *out, size_t outlen);
+	int (*devx_port_query)(struct ibv_context *ctx,
+			       uint32_t port_num,
+			       struct mlx5_port_info *info);
+	int (*dr_dump_domain)(FILE *file, void *domain);
+	int (*dr_dump_rule)(FILE *file, void *rule);
+	int (*devx_query_eqn)(struct ibv_context *context, uint32_t cpus,
+			      uint32_t *eqn);
+	struct mlx5dv_devx_event_channel *(*devx_create_event_channel)
+				(struct ibv_context *context, int flags);
+	void (*devx_destroy_event_channel)
+			(struct mlx5dv_devx_event_channel *event_channel);
+	int (*devx_subscribe_devx_event)
+			(struct mlx5dv_devx_event_channel *event_channel,
+			 struct mlx5dv_devx_obj *obj,
+			 uint16_t events_sz,
+			 uint16_t events_num[],
+			 uint64_t cookie);
+	int (*devx_subscribe_devx_event_fd)
+			(struct mlx5dv_devx_event_channel *event_channel,
+			 int fd,
+			 struct mlx5dv_devx_obj *obj,
+			 uint16_t event_num);
+	ssize_t (*devx_get_event)
+			(struct mlx5dv_devx_event_channel *event_channel,
+			 struct mlx5dv_devx_async_event_hdr *event_data,
+			 size_t event_resp_len);
+	void (*dr_reclaim_domain_memory)(void *domain, uint32_t enable);
+	void (*dr_allow_duplicate_rules)(void *domain, uint32_t allow);
+	struct mlx5dv_pp *(*dv_alloc_pp)(struct ibv_context *context,
+					 size_t pp_context_sz,
+					 const void *pp_context,
+					 uint32_t flags);
+	void (*dv_free_pp)(struct mlx5dv_pp *pp);
+	void *(*dr_create_flow_action_sampler)
+			(struct mlx5dv_dr_flow_sampler_attr *attr);
+	void *(*dr_create_flow_action_dest_array)
+			(void *domain,
+			 size_t num_dest,
+			 struct mlx5dv_dr_action_dest_attr *dests[]);
+	void *(*dv_create_flow_action_aso)
+			(struct mlx5dv_dr_domain *domain, void *aso_obj,
+			 uint32_t offset, uint32_t flags, uint8_t return_reg_c);
+};
+
+extern const struct mlx5_glue *mlx5_glue;
+
+#endif /* MLX5_GLUE_H_ */
-- 
2.30.2

[dpdk-dev] [PATCH 02/19] net/mlx5: stub for FreeBSD

[Srikanth Kaka]

These files are a copy of their Linux equivalents.
They will be ported to FreeBSD.

Signed-off-by: Srikanth Kaka <srikanth.k@oneconvergence.com>
Signed-off-by: Vag Singh <vag.singh@oneconvergence.com>
Signed-off-by: Anand Thulasiram <avelu@juniper.net>
---
 drivers/net/mlx5/freebsd/mlx5_ethdev_os.c | 1632 +++++++++++
 drivers/net/mlx5/freebsd/mlx5_flow_os.c   |   38 +
 drivers/net/mlx5/freebsd/mlx5_flow_os.h   |  484 ++++
 drivers/net/mlx5/freebsd/mlx5_mp_os.c     |  305 ++
 drivers/net/mlx5/freebsd/mlx5_os.c        | 3208 +++++++++++++++++++++
 drivers/net/mlx5/freebsd/mlx5_os.h        |   24 +
 drivers/net/mlx5/freebsd/mlx5_socket.c    |  249 ++
 drivers/net/mlx5/freebsd/mlx5_verbs.c     | 1208 ++++++++
 drivers/net/mlx5/freebsd/mlx5_verbs.h     |   18 +
 9 files changed, 7166 insertions(+)
 create mode 100644 drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
 create mode 100644 drivers/net/mlx5/freebsd/mlx5_flow_os.c
 create mode 100644 drivers/net/mlx5/freebsd/mlx5_flow_os.h
 create mode 100644 drivers/net/mlx5/freebsd/mlx5_mp_os.c
 create mode 100644 drivers/net/mlx5/freebsd/mlx5_os.c
 create mode 100644 drivers/net/mlx5/freebsd/mlx5_os.h
 create mode 100644 drivers/net/mlx5/freebsd/mlx5_socket.c
 create mode 100644 drivers/net/mlx5/freebsd/mlx5_verbs.c
 create mode 100644 drivers/net/mlx5/freebsd/mlx5_verbs.h

diff --git a/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c b/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
new file mode 100644
index 0000000000..f34133e2c6
--- /dev/null
+++ b/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
@@ -0,0 +1,1632 @@
+/* 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 <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_malloc.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 interface index from SubFunction device name. */
+int
+mlx5_auxiliary_get_ifindex(const char *sf_name)
+{
+	char if_name[IF_NAMESIZE] = { 0 };
+
+	if (mlx5_auxiliary_get_child_name(sf_name, "/net",
+					  if_name, sizeof(if_name)) != 0)
+		return -rte_errno;
+	return if_nametoindex(if_name);
+}
+
+/**
+ * Get interface name from private structure.
+ *
+ * This is a port representor-aware version of mlx5_get_ifname_sysfs().
+ *
+ * @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)[MLX5_NAMESIZE])
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	unsigned int ifindex;
+
+	MLX5_ASSERT(priv);
+	MLX5_ASSERT(priv->sh);
+	if (priv->master && priv->sh->bond.ifindex > 0) {
+		memcpy(ifname, priv->sh->bond.ifname, MLX5_NAMESIZE);
+		return 0;
+	}
+	ifindex = mlx5_ifindex(dev);
+	if (!ifindex) {
+		if (!priv->representor)
+			return mlx5_get_ifname_sysfs(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 netdev ifname.
+ *
+ * @param[in] ifname
+ *   Pointer to netdev name.
+ * @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.
+ */
+static int
+mlx5_ifreq_by_ifname(const char *ifname, 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;
+	}
+	rte_strscpy(ifr->ifr_name, ifname, sizeof(ifr->ifr_name));
+	ret = ioctl(sock, req, ifr);
+	if (ret == -1) {
+		rte_errno = errno;
+		goto error;
+	}
+	close(sock);
+	return 0;
+error:
+	close(sock);
+	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.
+ */
+static int
+mlx5_ifreq(const struct rte_eth_dev *dev, int req, struct ifreq *ifr)
+{
+	char ifname[sizeof(ifr->ifr_name)];
+	int ret;
+
+	ret = mlx5_get_ifname(dev, &ifname);
+	if (ret)
+		return -rte_errno;
+	return mlx5_ifreq_by_ifname(ifname, req, ifr);
+}
+
+/**
+ * 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.
+ */
+static 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, dev->device) {
+		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_UNKNOWN;
+	else
+		dev_link.link_speed = link_speed;
+	priv->link_speed_capa = 0;
+	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);
+	*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_UNKNOWN : 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_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);
+	*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 *)&ethpause;
+	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 *)&ethpause;
+	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 device 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;
+}
+
+/**
+ * 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).
+ */
+static 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_PFHPF:
+		/* Fallthrough */
+	case MLX5_PHYS_PORT_NAME_TYPE_PFVF:
+		/* Fallthrough */
+	case MLX5_PHYS_PORT_NAME_TYPE_PFSF:
+		/* New representors naming schema. */
+		switch_info->representor = 1;
+		break;
+	default:
+		switch_info->master = device_dir;
+		break;
+	}
+}
+
+/**
+ * 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, "%" RTE_STR(IF_NAMESIZE) "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;
+}
+
+/**
+ * Get bond information associated with network interface.
+ *
+ * @param pf_ifindex
+ *   Network interface index of bond slave interface
+ * @param[out] ifindex
+ *   Pointer to bond ifindex.
+ * @param[out] ifname
+ *   Pointer to bond ifname.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_sysfs_bond_info(unsigned int pf_ifindex, unsigned int *ifindex,
+		     char *ifname)
+{
+	char name[IF_NAMESIZE];
+	FILE *file;
+	unsigned int index;
+	int ret;
+
+	if (!if_indextoname(pf_ifindex, name) || !strlen(name)) {
+		rte_errno = errno;
+		return -rte_errno;
+	}
+	MKSTR(bond_if, "/sys/class/net/%s/master/ifindex", name);
+	/* read bond ifindex */
+	file = fopen(bond_if, "rb");
+	if (file == NULL) {
+		rte_errno = errno;
+		return -rte_errno;
+	}
+	ret = fscanf(file, "%u", &index);
+	fclose(file);
+	if (ret <= 0) {
+		rte_errno = errno;
+		return -rte_errno;
+	}
+	if (ifindex)
+		*ifindex = index;
+
+	/* read bond device name from symbol link */
+	if (ifname) {
+		if (!if_indextoname(index, ifname)) {
+			rte_errno = errno;
+			return -rte_errno;
+		}
+	}
+	return 0;
+}
+
+/**
+ * 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) {
+		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) {
+		DRV_LOG(WARNING, "missing argument, cannot get module eeprom");
+		rte_errno = EINVAL;
+		return -rte_errno;
+	}
+	eeprom = mlx5_malloc(MLX5_MEM_ZERO,
+			     (sizeof(struct ethtool_eeprom) + info->length), 0,
+			     SOCKET_ID_ANY);
+	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);
+	mlx5_free(eeprom);
+	return ret;
+}
+
+/**
+ * Read device counters table.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ * @param[in] pf
+ *   PF index in case of bonding device, -1 otherwise
+ * @param[out] stats
+ *   Counters table output buffer.
+ *
+ * @return
+ *   0 on success and stats is filled, negative errno value otherwise and
+ *   rte_errno is set.
+ */
+static int
+_mlx5_os_read_dev_counters(struct rte_eth_dev *dev, int pf, uint64_t *stats)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_xstats_ctrl *xstats_ctrl = &priv->xstats_ctrl;
+	unsigned int i;
+	struct ifreq ifr;
+	unsigned int stats_sz = xstats_ctrl->stats_n * sizeof(uint64_t);
+	unsigned char et_stat_buf[sizeof(struct ethtool_stats) + stats_sz];
+	struct ethtool_stats *et_stats = (struct ethtool_stats *)et_stat_buf;
+	int ret;
+
+	et_stats->cmd = ETHTOOL_GSTATS;
+	et_stats->n_stats = xstats_ctrl->stats_n;
+	ifr.ifr_data = (caddr_t)et_stats;
+	if (pf >= 0)
+		ret = mlx5_ifreq_by_ifname(priv->sh->bond.ports[pf].ifname,
+					   SIOCETHTOOL, &ifr);
+	else
+		ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
+	if (ret) {
+		DRV_LOG(WARNING,
+			"port %u unable to read statistic values from device",
+			dev->data->port_id);
+		return ret;
+	}
+	for (i = 0; i != xstats_ctrl->mlx5_stats_n; ++i) {
+		if (xstats_ctrl->info[i].dev)
+			continue;
+		stats[i] += (uint64_t)
+			    et_stats->data[xstats_ctrl->dev_table_idx[i]];
+	}
+	return 0;
+}
+
+/**
+ * Read device counters.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ * @param[out] stats
+ *   Counters table output buffer.
+ *
+ * @return
+ *   0 on success and stats is filled, negative errno value otherwise and
+ *   rte_errno is set.
+ */
+int
+mlx5_os_read_dev_counters(struct rte_eth_dev *dev, uint64_t *stats)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_xstats_ctrl *xstats_ctrl = &priv->xstats_ctrl;
+	int ret = 0, i;
+
+	memset(stats, 0, sizeof(*stats) * xstats_ctrl->mlx5_stats_n);
+	/* Read ifreq counters. */
+	if (priv->master && priv->pf_bond >= 0) {
+		/* Sum xstats from bonding device member ports. */
+		for (i = 0; i < priv->sh->bond.n_port; i++) {
+			ret = _mlx5_os_read_dev_counters(dev, i, stats);
+			if (ret)
+				return ret;
+		}
+	} else {
+		ret = _mlx5_os_read_dev_counters(dev, -1, stats);
+	}
+	/* Read IB counters. */
+	for (i = 0; i != xstats_ctrl->mlx5_stats_n; ++i) {
+		if (!xstats_ctrl->info[i].dev)
+			continue;
+		ret = mlx5_os_read_dev_stat(priv, xstats_ctrl->info[i].ctr_name,
+					    &stats[i]);
+		/* return last xstats counter if fail to read. */
+		if (ret != 0)
+			xstats_ctrl->xstats[i] = stats[i];
+		else
+			stats[i] = xstats_ctrl->xstats[i];
+	}
+	return ret;
+}
+
+/**
+ * Query the number of statistics provided by ETHTOOL.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ *
+ * @return
+ *   Number of statistics on success, negative errno value otherwise and
+ *   rte_errno is set.
+ */
+int
+mlx5_os_get_stats_n(struct rte_eth_dev *dev)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct ethtool_drvinfo drvinfo;
+	struct ifreq ifr;
+	int ret;
+
+	drvinfo.cmd = ETHTOOL_GDRVINFO;
+	ifr.ifr_data = (caddr_t)&drvinfo;
+	if (priv->master && priv->pf_bond >= 0)
+		/* Bonding PF. */
+		ret = mlx5_ifreq_by_ifname(priv->sh->bond.ports[0].ifname,
+					   SIOCETHTOOL, &ifr);
+	else
+		ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
+	if (ret) {
+		DRV_LOG(WARNING, "port %u unable to query number of statistics",
+			dev->data->port_id);
+		return ret;
+	}
+	return drvinfo.n_stats;
+}
+
+static const struct mlx5_counter_ctrl mlx5_counters_init[] = {
+	{
+		.dpdk_name = "rx_unicast_bytes",
+		.ctr_name = "rx_vport_unicast_bytes",
+	},
+	{
+		.dpdk_name = "rx_multicast_bytes",
+		.ctr_name = "rx_vport_multicast_bytes",
+	},
+	{
+		.dpdk_name = "rx_broadcast_bytes",
+		.ctr_name = "rx_vport_broadcast_bytes",
+	},
+	{
+		.dpdk_name = "rx_unicast_packets",
+		.ctr_name = "rx_vport_unicast_packets",
+	},
+	{
+		.dpdk_name = "rx_multicast_packets",
+		.ctr_name = "rx_vport_multicast_packets",
+	},
+	{
+		.dpdk_name = "rx_broadcast_packets",
+		.ctr_name = "rx_vport_broadcast_packets",
+	},
+	{
+		.dpdk_name = "tx_unicast_bytes",
+		.ctr_name = "tx_vport_unicast_bytes",
+	},
+	{
+		.dpdk_name = "tx_multicast_bytes",
+		.ctr_name = "tx_vport_multicast_bytes",
+	},
+	{
+		.dpdk_name = "tx_broadcast_bytes",
+		.ctr_name = "tx_vport_broadcast_bytes",
+	},
+	{
+		.dpdk_name = "tx_unicast_packets",
+		.ctr_name = "tx_vport_unicast_packets",
+	},
+	{
+		.dpdk_name = "tx_multicast_packets",
+		.ctr_name = "tx_vport_multicast_packets",
+	},
+	{
+		.dpdk_name = "tx_broadcast_packets",
+		.ctr_name = "tx_vport_broadcast_packets",
+	},
+	{
+		.dpdk_name = "rx_wqe_errors",
+		.ctr_name = "rx_wqe_err",
+	},
+	{
+		.dpdk_name = "rx_phy_crc_errors",
+		.ctr_name = "rx_crc_errors_phy",
+	},
+	{
+		.dpdk_name = "rx_phy_in_range_len_errors",
+		.ctr_name = "rx_in_range_len_errors_phy",
+	},
+	{
+		.dpdk_name = "rx_phy_symbol_errors",
+		.ctr_name = "rx_symbol_err_phy",
+	},
+	{
+		.dpdk_name = "tx_phy_errors",
+		.ctr_name = "tx_errors_phy",
+	},
+	{
+		.dpdk_name = "rx_out_of_buffer",
+		.ctr_name = "out_of_buffer",
+		.dev = 1,
+	},
+	{
+		.dpdk_name = "tx_phy_packets",
+		.ctr_name = "tx_packets_phy",
+	},
+	{
+		.dpdk_name = "rx_phy_packets",
+		.ctr_name = "rx_packets_phy",
+	},
+	{
+		.dpdk_name = "tx_phy_discard_packets",
+		.ctr_name = "tx_discards_phy",
+	},
+	{
+		.dpdk_name = "rx_phy_discard_packets",
+		.ctr_name = "rx_discards_phy",
+	},
+	{
+		.dpdk_name = "tx_phy_bytes",
+		.ctr_name = "tx_bytes_phy",
+	},
+	{
+		.dpdk_name = "rx_phy_bytes",
+		.ctr_name = "rx_bytes_phy",
+	},
+	/* Representor only */
+	{
+		.dpdk_name = "rx_vport_packets",
+		.ctr_name = "vport_rx_packets",
+	},
+	{
+		.dpdk_name = "rx_vport_bytes",
+		.ctr_name = "vport_rx_bytes",
+	},
+	{
+		.dpdk_name = "tx_vport_packets",
+		.ctr_name = "vport_tx_packets",
+	},
+	{
+		.dpdk_name = "tx_vport_bytes",
+		.ctr_name = "vport_tx_bytes",
+	},
+};
+
+static const unsigned int xstats_n = RTE_DIM(mlx5_counters_init);
+
+/**
+ * Init the structures to read device counters.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ */
+void
+mlx5_os_stats_init(struct rte_eth_dev *dev)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_xstats_ctrl *xstats_ctrl = &priv->xstats_ctrl;
+	struct mlx5_stats_ctrl *stats_ctrl = &priv->stats_ctrl;
+	unsigned int i;
+	unsigned int j;
+	struct ifreq ifr;
+	struct ethtool_gstrings *strings = NULL;
+	unsigned int dev_stats_n;
+	unsigned int str_sz;
+	int ret;
+
+	/* So that it won't aggregate for each init. */
+	xstats_ctrl->mlx5_stats_n = 0;
+	ret = mlx5_os_get_stats_n(dev);
+	if (ret < 0) {
+		DRV_LOG(WARNING, "port %u no extended statistics available",
+			dev->data->port_id);
+		return;
+	}
+	dev_stats_n = ret;
+	/* Allocate memory to grab stat names and values. */
+	str_sz = dev_stats_n * ETH_GSTRING_LEN;
+	strings = (struct ethtool_gstrings *)
+		  mlx5_malloc(0, str_sz + sizeof(struct ethtool_gstrings), 0,
+			      SOCKET_ID_ANY);
+	if (!strings) {
+		DRV_LOG(WARNING, "port %u unable to allocate memory for xstats",
+		     dev->data->port_id);
+		return;
+	}
+	strings->cmd = ETHTOOL_GSTRINGS;
+	strings->string_set = ETH_SS_STATS;
+	strings->len = dev_stats_n;
+	ifr.ifr_data = (caddr_t)strings;
+	if (priv->master && priv->pf_bond >= 0)
+		/* Bonding master. */
+		ret = mlx5_ifreq_by_ifname(priv->sh->bond.ports[0].ifname,
+					   SIOCETHTOOL, &ifr);
+	else
+		ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
+	if (ret) {
+		DRV_LOG(WARNING, "port %u unable to get statistic names",
+			dev->data->port_id);
+		goto free;
+	}
+	for (i = 0; i != dev_stats_n; ++i) {
+		const char *curr_string = (const char *)
+			&strings->data[i * ETH_GSTRING_LEN];
+
+		for (j = 0; j != xstats_n; ++j) {
+			if (!strcmp(mlx5_counters_init[j].ctr_name,
+				    curr_string)) {
+				unsigned int idx = xstats_ctrl->mlx5_stats_n++;
+
+				xstats_ctrl->dev_table_idx[idx] = i;
+				xstats_ctrl->info[idx] = mlx5_counters_init[j];
+				break;
+			}
+		}
+	}
+	/* Add dev counters. */
+	for (i = 0; i != xstats_n; ++i) {
+		if (mlx5_counters_init[i].dev) {
+			unsigned int idx = xstats_ctrl->mlx5_stats_n++;
+
+			xstats_ctrl->info[idx] = mlx5_counters_init[i];
+			xstats_ctrl->hw_stats[idx] = 0;
+		}
+	}
+	MLX5_ASSERT(xstats_ctrl->mlx5_stats_n <= MLX5_MAX_XSTATS);
+	xstats_ctrl->stats_n = dev_stats_n;
+	/* Copy to base at first time. */
+	ret = mlx5_os_read_dev_counters(dev, xstats_ctrl->base);
+	if (ret)
+		DRV_LOG(ERR, "port %u cannot read device counters: %s",
+			dev->data->port_id, strerror(rte_errno));
+	mlx5_os_read_dev_stat(priv, "out_of_buffer", &stats_ctrl->imissed_base);
+	stats_ctrl->imissed = 0;
+free:
+	mlx5_free(strings);
+}
+
+/**
+ * Get MAC address by querying netdevice.
+ *
+ * @param[in] dev
+ *   Pointer to Ethernet device.
+ * @param[out] mac
+ *   MAC address output buffer.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_get_mac(struct rte_eth_dev *dev, uint8_t (*mac)[RTE_ETHER_ADDR_LEN])
+{
+	struct ifreq request;
+	int ret;
+
+	ret = mlx5_ifreq(dev, SIOCGIFHWADDR, &request);
+	if (ret)
+		return ret;
+	memcpy(mac, request.ifr_hwaddr.sa_data, RTE_ETHER_ADDR_LEN);
+	return 0;
+}
diff --git a/drivers/net/mlx5/freebsd/mlx5_flow_os.c b/drivers/net/mlx5/freebsd/mlx5_flow_os.c
new file mode 100644
index 0000000000..893f00b824
--- /dev/null
+++ b/drivers/net/mlx5/freebsd/mlx5_flow_os.c
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2020 Mellanox Technologies, Ltd
+ */
+
+#include "mlx5_flow_os.h"
+
+#include <rte_thread.h>
+
+/* Key of thread specific flow workspace data. */
+static rte_thread_key key_workspace;
+
+int
+mlx5_flow_os_init_workspace_once(void)
+{
+	if (rte_thread_key_create(&key_workspace, flow_release_workspace)) {
+		DRV_LOG(ERR, "Can't create flow workspace data thread key.");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void *
+mlx5_flow_os_get_specific_workspace(void)
+{
+	return rte_thread_value_get(key_workspace);
+}
+
+int
+mlx5_flow_os_set_specific_workspace(struct mlx5_flow_workspace *data)
+{
+	return rte_thread_value_set(key_workspace, data);
+}
+
+void
+mlx5_flow_os_release_workspace(void)
+{
+	rte_thread_key_delete(key_workspace);
+}
diff --git a/drivers/net/mlx5/freebsd/mlx5_flow_os.h b/drivers/net/mlx5/freebsd/mlx5_flow_os.h
new file mode 100644
index 0000000000..1926d26410
--- /dev/null
+++ b/drivers/net/mlx5/freebsd/mlx5_flow_os.h
@@ -0,0 +1,484 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2020 Mellanox Technologies, Ltd
+ */
+
+#ifndef RTE_PMD_MLX5_FLOW_OS_H_
+#define RTE_PMD_MLX5_FLOW_OS_H_
+
+#include "mlx5_flow.h"
+
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+extern const struct mlx5_flow_driver_ops mlx5_flow_dv_drv_ops;
+#endif
+
+/**
+ * Get OS enforced flow type. MLX5_FLOW_TYPE_MAX means "non enforced type".
+ *
+ * @return
+ *   Flow type (MLX5_FLOW_TYPE_MAX)
+ */
+static inline enum mlx5_flow_drv_type
+mlx5_flow_os_get_type(void)
+{
+	return MLX5_FLOW_TYPE_MAX;
+}
+
+/**
+ * Check if item type is supported.
+ *
+ * @param item
+ *   Item type to check.
+ *
+ * @return
+ *   True is this item type is supported, false if not supported.
+ */
+static inline bool
+mlx5_flow_os_item_supported(int item __rte_unused)
+{
+	return true;
+}
+
+/**
+ * Check if action type is supported.
+ *
+ * @param action
+ *   Action type to check.
+ *
+ * @return
+ *   True is this action type is supported, false if not supported.
+ */
+static inline bool
+mlx5_flow_os_action_supported(int action __rte_unused)
+{
+	return true;
+}
+
+/**
+ * Create flow rule.
+ *
+ * @param[in] matcher
+ *   Pointer to match mask structure.
+ * @param[in] match_value
+ *   Pointer to match value structure.
+ * @param[in] num_actions
+ *   Number of actions in flow rule.
+ * @param[in] actions
+ *   Pointer to array of flow rule actions.
+ * @param[out] flow
+ *   Pointer to a valid flow rule object on success, NULL otherwise.
+ *
+ * @return
+ *   0 on success, or -1 on failure and errno is set.
+ */
+static inline int
+mlx5_flow_os_create_flow(void *matcher, void *match_value,
+			 size_t num_actions, void *actions[], void **flow)
+{
+	*flow = mlx5_glue->dv_create_flow(matcher, match_value,
+					  num_actions, actions);
+	return (*flow) ? 0 : -1;
+}
+
+/**
+ * Destroy flow rule.
+ *
+ * @param[in] drv_flow_ptr
+ *   Pointer to flow rule object.
+ *
+ * @return
+ *   0 on success, or the value of errno on failure.
+ */
+static inline int
+mlx5_flow_os_destroy_flow(void *drv_flow_ptr)
+{
+	return mlx5_glue->dv_destroy_flow(drv_flow_ptr);
+}
+
+/**
+ * Create flow table.
+ *
+ * @param[in] domain
+ *   Pointer to relevant domain.
+ * @param[in] table_id
+ *   Table ID.
+ * @param[out] table
+ *   Pointer to a valid flow table object on success, NULL otherwise.
+ *
+ * @return
+ *   0 on success, or -1 on failure and errno is set.
+ */
+static inline int
+mlx5_flow_os_create_flow_tbl(void *domain, uint32_t table_id, void **table)
+{
+	*table = mlx5_glue->dr_create_flow_tbl(domain, table_id);
+	return (*table) ? 0 : -1;
+}
+
+/**
+ * Destroy flow table.
+ *
+ * @param[in] table
+ *   Pointer to table object to destroy.
+ *
+ * @return
+ *   0 on success, or the value of errno on failure.
+ */
+static inline int
+mlx5_flow_os_destroy_flow_tbl(void *table)
+{
+	return mlx5_glue->dr_destroy_flow_tbl(table);
+}
+
+/**
+ * Create flow matcher in a flow table.
+ *
+ * @param[in] ctx
+ *   Pointer to relevant device context.
+ * @param[in] attr
+ *   Pointer to relevant attributes.
+ * @param[in] table
+ *   Pointer to table object.
+ * @param[out] matcher
+ *   Pointer to a valid flow matcher object on success, NULL otherwise.
+ *
+ * @return
+ *   0 on success, or -1 on failure and errno is set.
+ */
+static inline int
+mlx5_flow_os_create_flow_matcher(void *ctx, void *attr, void *table,
+				 void **matcher)
+{
+	*matcher = mlx5_glue->dv_create_flow_matcher(ctx, attr, table);
+	return (*matcher) ? 0 : -1;
+}
+
+/**
+ * Destroy flow matcher.
+ *
+ * @param[in] matcher
+ *   Pointer to matcher object to destroy.
+ *
+ * @return
+ *   0 on success, or the value of errno on failure.
+ */
+static inline int
+mlx5_flow_os_destroy_flow_matcher(void *matcher)
+{
+	return mlx5_glue->dv_destroy_flow_matcher(matcher);
+}
+
+/**
+ * Create flow action: packet reformat.
+ *
+ * @param[in] ctx
+ *   Pointer to relevant device context.
+ * @param[in] domain
+ *   Pointer to domain handler.
+ * @param[in] resource
+ *   Pointer to action data resource.
+ * @param[out] action
+ *   Pointer to a valid action on success, NULL otherwise.
+ *
+ *
+ * @return
+ *   0 on success, or -1 on failure and errno is set.
+ */
+static inline int
+mlx5_flow_os_create_flow_action_packet_reformat(void *ctx, void *domain,
+						void *resource, void **action)
+{
+	struct mlx5_flow_dv_encap_decap_resource *res =
+			(struct mlx5_flow_dv_encap_decap_resource *)resource;
+
+	*action = mlx5_glue->dv_create_flow_action_packet_reformat
+					(ctx, res->reformat_type, res->ft_type,
+					 domain, res->flags, res->size,
+					 (res->size ? res->buf : NULL));
+	return (*action) ? 0 : -1;
+}
+
+/**
+ * Create flow action: modify header.
+ *
+ * @param[in] ctx
+ *   Pointer to relevant device context.
+ * @param[in] domain
+ *   Pointer to domain handler.
+ * @param[in] resource
+ *   Pointer to action data resource.
+ * @param[in] actions_len
+ *   Total length of actions data in resource.
+ * @param[out] action
+ *   Pointer to a valid action on success, NULL otherwise.
+ *
+ *
+ * @return
+ *   0 on success, or -1 on failure and errno is set.
+ */
+static inline int
+mlx5_flow_os_create_flow_action_modify_header(void *ctx, void *domain,
+					      void *resource,
+					      uint32_t actions_len,
+					      void **action)
+{
+	struct mlx5_flow_dv_modify_hdr_resource *res =
+			(struct mlx5_flow_dv_modify_hdr_resource *)resource;
+
+	*action = mlx5_glue->dv_create_flow_action_modify_header
+					(ctx, res->ft_type, domain, res->root ?
+					 MLX5DV_DR_ACTION_FLAGS_ROOT_LEVEL : 0,
+					 actions_len, (uint64_t *)res->actions);
+	return (*action) ? 0 : -1;
+}
+
+/**
+ * Create flow action: destination flow table.
+ *
+ * @param[in] tbl_obj
+ *   Pointer to destination table object.
+ * @param[out] action
+ *   Pointer to a valid action on success, NULL otherwise.
+ *
+ * @return
+ *   0 on success, or -1 on failure and errno is set.
+ */
+static inline int
+mlx5_flow_os_create_flow_action_dest_flow_tbl(void *tbl_obj, void **action)
+{
+	*action = mlx5_glue->dr_create_flow_action_dest_flow_tbl(tbl_obj);
+	return (*action) ? 0 : -1;
+}
+
+/**
+ * Create flow action: destination port.
+ *
+ * @param[in] domain
+ *   Pointer to domain handler.
+ * @param[in] port_id
+ *   Destination port ID.
+ * @param[out] action
+ *   Pointer to a valid action on success, NULL otherwise.
+ *
+ * @return
+ *   0 on success, or -1 on failure and errno is set.
+ */
+static inline int
+mlx5_flow_os_create_flow_action_dest_port(void *domain, uint32_t port_id,
+					  void **action)
+{
+	/*
+	 * Depending on rdma_core version the glue routine calls
+	 * either mlx5dv_dr_action_create_dest_ib_port(domain, dev_port)
+	 * or mlx5dv_dr_action_create_dest_vport(domain, vport_id).
+	 */
+	*action = mlx5_glue->dr_create_flow_action_dest_port(domain, port_id);
+	return (*action) ? 0 : -1;
+}
+
+/**
+ * Create flow action: push vlan.
+ *
+ * @param[in] domain
+ *   Pointer to domain handler.
+ * @param[in] vlan_tag
+ *   VLAN tag value.
+ * @param[out] action
+ *   Pointer to a valid action on success, NULL otherwise.
+ *
+ * @return
+ *   0 on success, or -1 on failure and errno is set.
+ */
+static inline int
+mlx5_flow_os_create_flow_action_push_vlan(void *domain, rte_be32_t vlan_tag,
+					  void **action)
+{
+	*action = mlx5_glue->dr_create_flow_action_push_vlan(domain, vlan_tag);
+	return (*action) ? 0 : -1;
+}
+
+/**
+ * Create flow action: count.
+ *
+ * @param[in] cnt_obj
+ *   Pointer to DevX counter object.
+ * @param[in] offset
+ *   Offset of counter in array.
+ * @param[out] action
+ *   Pointer to a valid action on success, NULL otherwise.
+ *
+ * @return
+ *   0 on success, or -1 on failure and errno is set.
+ */
+static inline int
+mlx5_flow_os_create_flow_action_count(void *cnt_obj, uint16_t offset,
+				      void **action)
+{
+	*action = mlx5_glue->dv_create_flow_action_counter(cnt_obj, offset);
+	return (*action) ? 0 : -1;
+}
+
+/**
+ * Create flow action: tag.
+ *
+ * @param[in] tag
+ *   Tag value.
+ * @param[out] action
+ *   Pointer to a valid action on success, NULL otherwise.
+ *
+ * @return
+ *   0 on success, or -1 on failure and errno is set.
+ */
+static inline int
+mlx5_flow_os_create_flow_action_tag(uint32_t tag, void **action)
+{
+	*action = mlx5_glue->dv_create_flow_action_tag(tag);
+	return (*action) ? 0 : -1;
+}
+
+/**
+ * Create flow action: drop.
+ *
+ * @param[out] action
+ *   Pointer to a valid action on success, NULL otherwise.
+ *
+ * @return
+ *   0 on success, or -1 on failure and errno is set.
+ */
+static inline int
+mlx5_flow_os_create_flow_action_drop(void **action)
+{
+	*action = mlx5_glue->dr_create_flow_action_drop();
+	return (*action) ? 0 : -1;
+}
+
+/**
+ * Create flow action: default miss.
+ *
+ * @param[out] action
+ *   Pointer to a valid action on success, NULL otherwise.
+ *
+ * @return
+ *   0 on success, or -1 on failure and errno is set.
+ */
+static inline int
+mlx5_flow_os_create_flow_action_default_miss(void **action)
+{
+	*action = mlx5_glue->dr_create_flow_action_default_miss();
+	return (*action) ? 0 : -1;
+}
+
+/**
+ * Create flow action: dest_devx_tir
+ *
+ * @param[in] tir
+ *   Pointer to DevX tir object
+ * @param[out] action
+ *   Pointer to a valid action on success, NULL otherwise.
+ *
+ * @return
+ *   0 on success, or -1 on failure and errno is set.
+ */
+static inline int
+mlx5_flow_os_create_flow_action_dest_devx_tir(struct mlx5_devx_obj *tir,
+					      void **action)
+{
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+	*action = mlx5_glue->dv_create_flow_action_dest_devx_tir(tir->obj);
+	return (*action) ? 0 : -1;
+#else
+	/* If no DV support - skip the operation and return success */
+	RTE_SET_USED(tir);
+	*action = 0;
+	return 0;
+#endif
+}
+
+/**
+ * Create flow action: sampler
+ *
+ * @param[in] attr
+ *   Pointer to sampler attribute
+ * @param[out] action
+ *   Pointer to a valid action on success, NULL otherwise.
+ *
+ * @return
+ *   0 on success, or -1 on failure and errno is set.
+ */
+static inline int
+mlx5_os_flow_dr_create_flow_action_sampler
+			(struct mlx5dv_dr_flow_sampler_attr *attr,
+			void **action)
+{
+	*action = mlx5_glue->dr_create_flow_action_sampler(attr);
+	return (*action) ? 0 : -1;
+}
+
+/**
+ * Create flow action: dest_array
+ *
+ * @param[in] domain
+ *   Pointer to relevant domain.
+ * @param[in] num_dest
+ *   Number of destinations array.
+ * @param[in] dests
+ *   Array of destination attributes.
+ * @param[out] action
+ *   Pointer to a valid action on success, NULL otherwise.
+ *
+ * @return
+ *   0 on success, or -1 on failure and errno is set.
+ */
+static inline int
+mlx5_os_flow_dr_create_flow_action_dest_array
+			(void *domain,
+			 size_t num_dest,
+			 struct mlx5dv_dr_action_dest_attr *dests[],
+			 void **action)
+{
+	*action = mlx5_glue->dr_create_flow_action_dest_array(
+						domain, num_dest, dests);
+	return (*action) ? 0 : -1;
+}
+
+/**
+ * Destroy flow action.
+ *
+ * @param[in] action
+ *   Pointer to action object to destroy.
+ *
+ * @return
+ *   0 on success, or the value of errno on failure.
+ */
+static inline int
+mlx5_flow_os_destroy_flow_action(void *action)
+{
+	return mlx5_glue->destroy_flow_action(action);
+}
+
+/**
+ * OS wrapper over Verbs API.
+ * Adjust flow priority based on the highest layer and the request priority.
+ *
+ * @param[in] dev
+ *    Pointer to the Ethernet device structure.
+ * @param[in] priority
+ *    The rule base priority.
+ * @param[in] subpriority
+ *    The priority based on the items.
+ *
+ * @return
+ *    The new priority.
+ */
+static inline uint32_t
+mlx5_os_flow_adjust_priority(struct rte_eth_dev *dev, int32_t priority,
+			  uint32_t subpriority)
+{
+	return mlx5_flow_adjust_priority(dev, priority, subpriority);
+}
+
+static inline int
+mlx5_os_flow_dr_sync_domain(void *domain, uint32_t flags)
+{
+	return mlx5_glue->dr_sync_domain(domain, flags);
+}
+#endif /* RTE_PMD_MLX5_FLOW_OS_H_ */
diff --git a/drivers/net/mlx5/freebsd/mlx5_mp_os.c b/drivers/net/mlx5/freebsd/mlx5_mp_os.c
new file mode 100644
index 0000000000..3a4aa766f8
--- /dev/null
+++ b/drivers/net/mlx5/freebsd/mlx5_mp_os.c
@@ -0,0 +1,305 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2019 6WIND S.A.
+ * Copyright 2019 Mellanox Technologies, Ltd
+ */
+
+#include <stdio.h>
+#include <time.h>
+
+#include <rte_eal.h>
+#include <ethdev_driver.h>
+#include <rte_string_fns.h>
+
+#include <mlx5_common_mp.h>
+#include <mlx5_common_mr.h>
+#include <mlx5_malloc.h>
+
+#include "mlx5.h"
+#include "mlx5_rxtx.h"
+#include "mlx5_rx.h"
+#include "mlx5_tx.h"
+#include "mlx5_utils.h"
+
+int
+mlx5_mp_os_primary_handle(const struct rte_mp_msg *mp_msg, const void *peer)
+{
+	struct rte_mp_msg mp_res;
+	struct mlx5_mp_param *res = (struct mlx5_mp_param *)mp_res.param;
+	const struct mlx5_mp_param *param =
+		(const struct mlx5_mp_param *)mp_msg->param;
+	struct rte_eth_dev *dev;
+	struct mlx5_priv *priv;
+	struct mr_cache_entry entry;
+	uint32_t lkey;
+	int ret;
+
+	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_PRIMARY);
+	if (!rte_eth_dev_is_valid_port(param->port_id)) {
+		rte_errno = ENODEV;
+		DRV_LOG(ERR, "port %u invalid port ID", param->port_id);
+		return -rte_errno;
+	}
+	dev = &rte_eth_devices[param->port_id];
+	priv = dev->data->dev_private;
+	switch (param->type) {
+	case MLX5_MP_REQ_CREATE_MR:
+		mp_init_msg(&priv->mp_id, &mp_res, param->type);
+		lkey = mlx5_mr_create_primary(priv->sh->pd,
+					      &priv->sh->share_cache,
+					      &entry, param->args.addr,
+					      priv->config.mr_ext_memseg_en);
+		if (lkey == UINT32_MAX)
+			res->result = -rte_errno;
+		ret = rte_mp_reply(&mp_res, peer);
+		break;
+	case MLX5_MP_REQ_VERBS_CMD_FD:
+		mp_init_msg(&priv->mp_id, &mp_res, param->type);
+		mp_res.num_fds = 1;
+		mp_res.fds[0] = ((struct ibv_context *)priv->sh->ctx)->cmd_fd;
+		res->result = 0;
+		ret = rte_mp_reply(&mp_res, peer);
+		break;
+	case MLX5_MP_REQ_QUEUE_STATE_MODIFY:
+		mp_init_msg(&priv->mp_id, &mp_res, param->type);
+		res->result = mlx5_queue_state_modify_primary
+					(dev, &param->args.state_modify);
+		ret = rte_mp_reply(&mp_res, peer);
+		break;
+	case MLX5_MP_REQ_QUEUE_RX_STOP:
+		mp_init_msg(&priv->mp_id, &mp_res, param->type);
+		res->result = mlx5_rx_queue_stop_primary
+					(dev, param->args.queue_id.queue_id);
+		ret = rte_mp_reply(&mp_res, peer);
+		break;
+	case MLX5_MP_REQ_QUEUE_RX_START:
+		mp_init_msg(&priv->mp_id, &mp_res, param->type);
+		res->result = mlx5_rx_queue_start_primary
+					(dev, param->args.queue_id.queue_id);
+		ret = rte_mp_reply(&mp_res, peer);
+		break;
+	case MLX5_MP_REQ_QUEUE_TX_STOP:
+		mp_init_msg(&priv->mp_id, &mp_res, param->type);
+		res->result = mlx5_tx_queue_stop_primary
+					(dev, param->args.queue_id.queue_id);
+		ret = rte_mp_reply(&mp_res, peer);
+		break;
+	case MLX5_MP_REQ_QUEUE_TX_START:
+		mp_init_msg(&priv->mp_id, &mp_res, param->type);
+		res->result = mlx5_tx_queue_start_primary
+					(dev, param->args.queue_id.queue_id);
+		ret = rte_mp_reply(&mp_res, peer);
+		break;
+	default:
+		rte_errno = EINVAL;
+		DRV_LOG(ERR, "port %u invalid mp request type",
+			dev->data->port_id);
+		return -rte_errno;
+	}
+	return ret;
+}
+
+/**
+ * IPC message handler of a secondary process.
+ *
+ * @param[in] dev
+ *   Pointer to Ethernet structure.
+ * @param[in] peer
+ *   Pointer to the peer socket path.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_mp_os_secondary_handle(const struct rte_mp_msg *mp_msg, const void *peer)
+{
+struct rte_mp_msg mp_res;
+	struct mlx5_mp_param *res = (struct mlx5_mp_param *)mp_res.param;
+	const struct mlx5_mp_param *param =
+		(const struct mlx5_mp_param *)mp_msg->param;
+	struct rte_eth_dev *dev;
+	struct mlx5_proc_priv *ppriv;
+	struct mlx5_priv *priv;
+	int ret;
+
+	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_SECONDARY);
+	if (!rte_eth_dev_is_valid_port(param->port_id)) {
+		rte_errno = ENODEV;
+		DRV_LOG(ERR, "port %u invalid port ID", param->port_id);
+		return -rte_errno;
+	}
+	dev = &rte_eth_devices[param->port_id];
+	priv = dev->data->dev_private;
+	switch (param->type) {
+	case MLX5_MP_REQ_START_RXTX:
+		DRV_LOG(INFO, "port %u starting datapath", dev->data->port_id);
+		dev->rx_pkt_burst = mlx5_select_rx_function(dev);
+		dev->tx_pkt_burst = mlx5_select_tx_function(dev);
+		ppriv = (struct mlx5_proc_priv *)dev->process_private;
+		/* If Tx queue number changes, re-initialize UAR. */
+		if (ppriv->uar_table_sz != priv->txqs_n) {
+			mlx5_tx_uar_uninit_secondary(dev);
+			mlx5_proc_priv_uninit(dev);
+			ret = mlx5_proc_priv_init(dev);
+			if (ret)
+				return -rte_errno;
+			ret = mlx5_tx_uar_init_secondary(dev, mp_msg->fds[0]);
+			if (ret) {
+				mlx5_proc_priv_uninit(dev);
+				return -rte_errno;
+			}
+		}
+		rte_mb();
+		mp_init_msg(&priv->mp_id, &mp_res, param->type);
+		res->result = 0;
+		ret = rte_mp_reply(&mp_res, peer);
+		break;
+	case MLX5_MP_REQ_STOP_RXTX:
+		DRV_LOG(INFO, "port %u stopping datapath", dev->data->port_id);
+		dev->rx_pkt_burst = removed_rx_burst;
+		dev->tx_pkt_burst = removed_tx_burst;
+		rte_mb();
+		mp_init_msg(&priv->mp_id, &mp_res, param->type);
+		res->result = 0;
+		ret = rte_mp_reply(&mp_res, peer);
+		break;
+	default:
+		rte_errno = EINVAL;
+		DRV_LOG(ERR, "port %u invalid mp request type",
+			dev->data->port_id);
+		return -rte_errno;
+	}
+	return ret;
+}
+
+/**
+ * Broadcast request of stopping/starting data-path to secondary processes.
+ *
+ * @param[in] dev
+ *   Pointer to Ethernet structure.
+ * @param[in] type
+ *   Request type.
+ */
+static void
+mp_req_on_rxtx(struct rte_eth_dev *dev, enum mlx5_mp_req_type type)
+{
+	struct rte_mp_msg mp_req;
+	struct rte_mp_msg *mp_res;
+	struct rte_mp_reply mp_rep;
+	struct mlx5_mp_param *res;
+	struct timespec ts = {.tv_sec = MLX5_MP_REQ_TIMEOUT_SEC, .tv_nsec = 0};
+	struct mlx5_priv *priv = dev->data->dev_private;
+	int ret;
+	int i;
+
+	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_PRIMARY);
+	if (!mlx5_shared_data->secondary_cnt)
+		return;
+	if (type != MLX5_MP_REQ_START_RXTX && type != MLX5_MP_REQ_STOP_RXTX) {
+		DRV_LOG(ERR, "port %u unknown request (req_type %d)",
+			dev->data->port_id, type);
+		return;
+	}
+	mp_init_msg(&priv->mp_id, &mp_req, type);
+	if (type == MLX5_MP_REQ_START_RXTX) {
+		mp_req.num_fds = 1;
+		mp_req.fds[0] = ((struct ibv_context *)priv->sh->ctx)->cmd_fd;
+	}
+	ret = rte_mp_request_sync(&mp_req, &mp_rep, &ts);
+	if (ret) {
+		if (rte_errno != ENOTSUP)
+			DRV_LOG(ERR, "port %u failed to request stop/start Rx/Tx (%d)",
+				dev->data->port_id, type);
+		goto exit;
+	}
+	if (mp_rep.nb_sent != mp_rep.nb_received) {
+		DRV_LOG(ERR,
+			"port %u not all secondaries responded (req_type %d)",
+			dev->data->port_id, type);
+		goto exit;
+	}
+	for (i = 0; i < mp_rep.nb_received; i++) {
+		mp_res = &mp_rep.msgs[i];
+		res = (struct mlx5_mp_param *)mp_res->param;
+		if (res->result) {
+			DRV_LOG(ERR, "port %u request failed on secondary #%d",
+				dev->data->port_id, i);
+			goto exit;
+		}
+	}
+exit:
+	mlx5_free(mp_rep.msgs);
+}
+
+/**
+ * Broadcast request of starting data-path to secondary processes. The request
+ * is synchronous.
+ *
+ * @param[in] dev
+ *   Pointer to Ethernet structure.
+ */
+void
+mlx5_mp_os_req_start_rxtx(struct rte_eth_dev *dev)
+{
+	mp_req_on_rxtx(dev, MLX5_MP_REQ_START_RXTX);
+}
+
+/**
+ * Broadcast request of stopping data-path to secondary processes. The request
+ * is synchronous.
+ *
+ * @param[in] dev
+ *   Pointer to Ethernet structure.
+ */
+void
+mlx5_mp_os_req_stop_rxtx(struct rte_eth_dev *dev)
+{
+	mp_req_on_rxtx(dev, MLX5_MP_REQ_STOP_RXTX);
+}
+
+/**
+ * Request Verbs Rx/Tx queue stop or start to the primary process.
+ *
+ * @param[in] dev
+ *   Pointer to Ethernet structure.
+ * @param queue_id
+ *   Queue ID to control.
+ * @param req_type
+ *   request type
+ *     MLX5_MP_REQ_QUEUE_RX_START - start Rx queue
+ *     MLX5_MP_REQ_QUEUE_TX_START - stop Tx queue
+ *     MLX5_MP_REQ_QUEUE_RX_STOP - stop Rx queue
+ *     MLX5_MP_REQ_QUEUE_TX_STOP - stop Tx queue
+ * @return
+ *   0 on success, a negative errno value otherwise and
+ *     rte_errno is set.
+ */
+int
+mlx5_mp_os_req_queue_control(struct rte_eth_dev *dev, uint16_t queue_id,
+			  enum mlx5_mp_req_type req_type)
+{
+	struct rte_mp_msg mp_req;
+	struct rte_mp_msg *mp_res;
+	struct rte_mp_reply mp_rep;
+	struct mlx5_mp_param *req = (struct mlx5_mp_param *)mp_req.param;
+	struct mlx5_mp_param *res;
+	struct timespec ts = {.tv_sec = MLX5_MP_REQ_TIMEOUT_SEC, .tv_nsec = 0};
+	struct mlx5_priv *priv;
+	int ret;
+
+	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_SECONDARY);
+	priv = dev->data->dev_private;
+	mp_init_msg(&priv->mp_id, &mp_req, req_type);
+	req->args.queue_id.queue_id = queue_id;
+	ret = rte_mp_request_sync(&mp_req, &mp_rep, &ts);
+	if (ret) {
+		DRV_LOG(ERR, "port %u request to primary process failed",
+			dev->data->port_id);
+		return -rte_errno;
+	}
+	MLX5_ASSERT(mp_rep.nb_received == 1);
+	mp_res = &mp_rep.msgs[0];
+	res = (struct mlx5_mp_param *)mp_res->param;
+	ret = res->result;
+	free(mp_rep.msgs);
+	return ret;
+}
diff --git a/drivers/net/mlx5/freebsd/mlx5_os.c b/drivers/net/mlx5/freebsd/mlx5_os.c
new file mode 100644
index 0000000000..3746057673
--- /dev/null
+++ b/drivers/net/mlx5/freebsd/mlx5_os.c
@@ -0,0 +1,3208 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2015 6WIND S.A.
+ * Copyright 2020 Mellanox Technologies, Ltd
+ */
+
+#include <stddef.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <net/if.h>
+#include <linux/rtnetlink.h>
+#include <linux/sockios.h>
+#include <linux/ethtool.h>
+#include <fcntl.h>
+
+#include <rte_malloc.h>
+#include <ethdev_driver.h>
+#include <ethdev_pci.h>
+#include <rte_pci.h>
+#include <rte_bus_pci.h>
+#include <rte_bus_auxiliary.h>
+#include <rte_common.h>
+#include <rte_kvargs.h>
+#include <rte_rwlock.h>
+#include <rte_spinlock.h>
+#include <rte_string_fns.h>
+#include <rte_alarm.h>
+#include <rte_eal_paging.h>
+
+#include <mlx5_glue.h>
+#include <mlx5_devx_cmds.h>
+#include <mlx5_common.h>
+#include <mlx5_common_mp.h>
+#include <mlx5_common_mr.h>
+#include <mlx5_malloc.h>
+
+#include "mlx5_defs.h"
+#include "mlx5.h"
+#include "mlx5_common_os.h"
+#include "mlx5_utils.h"
+#include "mlx5_rxtx.h"
+#include "mlx5_rx.h"
+#include "mlx5_tx.h"
+#include "mlx5_autoconf.h"
+#include "mlx5_mr.h"
+#include "mlx5_flow.h"
+#include "rte_pmd_mlx5.h"
+#include "mlx5_verbs.h"
+#include "mlx5_nl.h"
+#include "mlx5_devx.h"
+
+#ifndef HAVE_IBV_MLX5_MOD_MPW
+#define MLX5DV_CONTEXT_FLAGS_MPW_ALLOWED (1 << 2)
+#define MLX5DV_CONTEXT_FLAGS_ENHANCED_MPW (1 << 3)
+#endif
+
+#ifndef HAVE_IBV_MLX5_MOD_CQE_128B_COMP
+#define MLX5DV_CONTEXT_FLAGS_CQE_128B_COMP (1 << 4)
+#endif
+
+static const char *MZ_MLX5_PMD_SHARED_DATA = "mlx5_pmd_shared_data";
+
+/* Spinlock for mlx5_shared_data allocation. */
+static rte_spinlock_t mlx5_shared_data_lock = RTE_SPINLOCK_INITIALIZER;
+
+/* Process local data for secondary processes. */
+static struct mlx5_local_data mlx5_local_data;
+
+/* rte flow indexed pool configuration. */
+static struct mlx5_indexed_pool_config icfg[] = {
+	{
+		.size = sizeof(struct rte_flow),
+		.trunk_size = 64,
+		.need_lock = 1,
+		.release_mem_en = 0,
+		.malloc = mlx5_malloc,
+		.free = mlx5_free,
+		.per_core_cache = 0,
+		.type = "ctl_flow_ipool",
+	},
+	{
+		.size = sizeof(struct rte_flow),
+		.trunk_size = 64,
+		.grow_trunk = 3,
+		.grow_shift = 2,
+		.need_lock = 1,
+		.release_mem_en = 0,
+		.malloc = mlx5_malloc,
+		.free = mlx5_free,
+		.per_core_cache = 1 << 14,
+		.type = "rte_flow_ipool",
+	},
+	{
+		.size = sizeof(struct rte_flow),
+		.trunk_size = 64,
+		.grow_trunk = 3,
+		.grow_shift = 2,
+		.need_lock = 1,
+		.release_mem_en = 0,
+		.malloc = mlx5_malloc,
+		.free = mlx5_free,
+		.per_core_cache = 0,
+		.type = "mcp_flow_ipool",
+	},
+};
+
+/**
+ * Set the completion channel file descriptor interrupt as non-blocking.
+ *
+ * @param[in] rxq_obj
+ *   Pointer to RQ channel object, which includes the channel fd
+ *
+ * @param[out] fd
+ *   The file descriptor (representing the intetrrupt) used in this channel.
+ *
+ * @return
+ *   0 on successfully setting the fd to non-blocking, non-zero otherwise.
+ */
+int
+mlx5_os_set_nonblock_channel_fd(int fd)
+{
+	int flags;
+
+	flags = fcntl(fd, F_GETFL);
+	return fcntl(fd, F_SETFL, flags | O_NONBLOCK);
+}
+
+/**
+ * Get mlx5 device attributes. The glue function query_device_ex() is called
+ * with out parameter of type 'struct ibv_device_attr_ex *'. Then fill in mlx5
+ * device attributes from the glue out parameter.
+ *
+ * @param dev
+ *   Pointer to ibv context.
+ *
+ * @param device_attr
+ *   Pointer to mlx5 device attributes.
+ *
+ * @return
+ *   0 on success, non zero error number otherwise
+ */
+int
+mlx5_os_get_dev_attr(void *ctx, struct mlx5_dev_attr *device_attr)
+{
+	int err;
+	struct ibv_device_attr_ex attr_ex;
+	memset(device_attr, 0, sizeof(*device_attr));
+	err = mlx5_glue->query_device_ex(ctx, NULL, &attr_ex);
+	if (err)
+		return err;
+
+	device_attr->device_cap_flags_ex = attr_ex.device_cap_flags_ex;
+	device_attr->max_qp_wr = attr_ex.orig_attr.max_qp_wr;
+	device_attr->max_sge = attr_ex.orig_attr.max_sge;
+	device_attr->max_cq = attr_ex.orig_attr.max_cq;
+	device_attr->max_cqe = attr_ex.orig_attr.max_cqe;
+	device_attr->max_mr = attr_ex.orig_attr.max_mr;
+	device_attr->max_pd = attr_ex.orig_attr.max_pd;
+	device_attr->max_qp = attr_ex.orig_attr.max_qp;
+	device_attr->max_srq = attr_ex.orig_attr.max_srq;
+	device_attr->max_srq_wr = attr_ex.orig_attr.max_srq_wr;
+	device_attr->raw_packet_caps = attr_ex.raw_packet_caps;
+	device_attr->max_rwq_indirection_table_size =
+		attr_ex.rss_caps.max_rwq_indirection_table_size;
+	device_attr->max_tso = attr_ex.tso_caps.max_tso;
+	device_attr->tso_supported_qpts = attr_ex.tso_caps.supported_qpts;
+
+	struct mlx5dv_context dv_attr = { .comp_mask = 0 };
+	err = mlx5_glue->dv_query_device(ctx, &dv_attr);
+	if (err)
+		return err;
+
+	device_attr->flags = dv_attr.flags;
+	device_attr->comp_mask = dv_attr.comp_mask;
+#ifdef HAVE_IBV_MLX5_MOD_SWP
+	device_attr->sw_parsing_offloads =
+		dv_attr.sw_parsing_caps.sw_parsing_offloads;
+#endif
+	device_attr->min_single_stride_log_num_of_bytes =
+		dv_attr.striding_rq_caps.min_single_stride_log_num_of_bytes;
+	device_attr->max_single_stride_log_num_of_bytes =
+		dv_attr.striding_rq_caps.max_single_stride_log_num_of_bytes;
+	device_attr->min_single_wqe_log_num_of_strides =
+		dv_attr.striding_rq_caps.min_single_wqe_log_num_of_strides;
+	device_attr->max_single_wqe_log_num_of_strides =
+		dv_attr.striding_rq_caps.max_single_wqe_log_num_of_strides;
+	device_attr->stride_supported_qpts =
+		dv_attr.striding_rq_caps.supported_qpts;
+#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT
+	device_attr->tunnel_offloads_caps = dv_attr.tunnel_offloads_caps;
+#endif
+	strlcpy(device_attr->fw_ver, attr_ex.orig_attr.fw_ver,
+		sizeof(device_attr->fw_ver));
+
+	return err;
+}
+
+/**
+ * Verbs callback to allocate a memory. This function should allocate the space
+ * according to the size provided residing inside a huge page.
+ * Please note that all allocation must respect the alignment from libmlx5
+ * (i.e. currently rte_mem_page_size()).
+ *
+ * @param[in] size
+ *   The size in bytes of the memory to allocate.
+ * @param[in] data
+ *   A pointer to the callback data.
+ *
+ * @return
+ *   Allocated buffer, NULL otherwise and rte_errno is set.
+ */
+static void *
+mlx5_alloc_verbs_buf(size_t size, void *data)
+{
+	struct mlx5_dev_ctx_shared *sh = data;
+	void *ret;
+	size_t alignment = rte_mem_page_size();
+	if (alignment == (size_t)-1) {
+		DRV_LOG(ERR, "Failed to get mem page size");
+		rte_errno = ENOMEM;
+		return NULL;
+	}
+
+	MLX5_ASSERT(data != NULL);
+	ret = mlx5_malloc(0, size, alignment, sh->numa_node);
+	if (!ret && size)
+		rte_errno = ENOMEM;
+	return ret;
+}
+
+/**
+ * Detect misc5 support or not
+ *
+ * @param[in] priv
+ *   Device private data pointer
+ */
+#ifdef HAVE_MLX5DV_DR
+static void
+__mlx5_discovery_misc5_cap(struct mlx5_priv *priv)
+{
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+	/* Dummy VxLAN matcher to detect rdma-core misc5 cap
+	 * Case: IPv4--->UDP--->VxLAN--->vni
+	 */
+	void *tbl;
+	struct mlx5_flow_dv_match_params matcher_mask;
+	void *match_m;
+	void *matcher;
+	void *headers_m;
+	void *misc5_m;
+	uint32_t *tunnel_header_m;
+	struct mlx5dv_flow_matcher_attr dv_attr;
+
+	memset(&matcher_mask, 0, sizeof(matcher_mask));
+	matcher_mask.size = sizeof(matcher_mask.buf);
+	match_m = matcher_mask.buf;
+	headers_m = MLX5_ADDR_OF(fte_match_param, match_m, outer_headers);
+	misc5_m = MLX5_ADDR_OF(fte_match_param,
+			       match_m, misc_parameters_5);
+	tunnel_header_m = (uint32_t *)
+				MLX5_ADDR_OF(fte_match_set_misc5,
+				misc5_m, tunnel_header_1);
+	MLX5_SET(fte_match_set_lyr_2_4, headers_m, ip_protocol, 0xff);
+	MLX5_SET(fte_match_set_lyr_2_4, headers_m, ip_version, 4);
+	MLX5_SET(fte_match_set_lyr_2_4, headers_m, udp_dport, 0xffff);
+	*tunnel_header_m = 0xffffff;
+
+	tbl = mlx5_glue->dr_create_flow_tbl(priv->sh->rx_domain, 1);
+	if (!tbl) {
+		DRV_LOG(INFO, "No SW steering support");
+		return;
+	}
+	dv_attr.type = IBV_FLOW_ATTR_NORMAL,
+	dv_attr.match_mask = (void *)&matcher_mask,
+	dv_attr.match_criteria_enable =
+			(1 << MLX5_MATCH_CRITERIA_ENABLE_OUTER_BIT) |
+			(1 << MLX5_MATCH_CRITERIA_ENABLE_MISC5_BIT);
+	dv_attr.priority = 3;
+#ifdef HAVE_MLX5DV_DR_ESWITCH
+	void *misc2_m;
+	if (priv->config.dv_esw_en) {
+		/* FDB enabled reg_c_0 */
+		dv_attr.match_criteria_enable |=
+				(1 << MLX5_MATCH_CRITERIA_ENABLE_MISC2_BIT);
+		misc2_m = MLX5_ADDR_OF(fte_match_param,
+				       match_m, misc_parameters_2);
+		MLX5_SET(fte_match_set_misc2, misc2_m,
+			 metadata_reg_c_0, 0xffff);
+	}
+#endif
+	matcher = mlx5_glue->dv_create_flow_matcher(priv->sh->ctx,
+						    &dv_attr, tbl);
+	if (matcher) {
+		priv->sh->misc5_cap = 1;
+		mlx5_glue->dv_destroy_flow_matcher(matcher);
+	}
+	mlx5_glue->dr_destroy_flow_tbl(tbl);
+#else
+	RTE_SET_USED(priv);
+#endif
+}
+#endif
+
+/**
+ * Verbs callback to free a memory.
+ *
+ * @param[in] ptr
+ *   A pointer to the memory to free.
+ * @param[in] data
+ *   A pointer to the callback data.
+ */
+static void
+mlx5_free_verbs_buf(void *ptr, void *data __rte_unused)
+{
+	MLX5_ASSERT(data != NULL);
+	mlx5_free(ptr);
+}
+
+/**
+ * Initialize DR related data within private structure.
+ * Routine checks the reference counter and does actual
+ * resources creation/initialization only if counter is zero.
+ *
+ * @param[in] priv
+ *   Pointer to the private device data structure.
+ *
+ * @return
+ *   Zero on success, positive error code otherwise.
+ */
+static int
+mlx5_alloc_shared_dr(struct mlx5_priv *priv)
+{
+	struct mlx5_dev_ctx_shared *sh = priv->sh;
+	char s[MLX5_NAME_SIZE] __rte_unused;
+	int err;
+
+	MLX5_ASSERT(sh && sh->refcnt);
+	if (sh->refcnt > 1)
+		return 0;
+	err = mlx5_alloc_table_hash_list(priv);
+	if (err)
+		goto error;
+	/* The resources below are only valid with DV support. */
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+	/* Init port id action list. */
+	snprintf(s, sizeof(s), "%s_port_id_action_list", sh->ibdev_name);
+	sh->port_id_action_list = mlx5_list_create(s, sh, true,
+						   flow_dv_port_id_create_cb,
+						   flow_dv_port_id_match_cb,
+						   flow_dv_port_id_remove_cb,
+						   flow_dv_port_id_clone_cb,
+						 flow_dv_port_id_clone_free_cb);
+	if (!sh->port_id_action_list)
+		goto error;
+	/* Init push vlan action list. */
+	snprintf(s, sizeof(s), "%s_push_vlan_action_list", sh->ibdev_name);
+	sh->push_vlan_action_list = mlx5_list_create(s, sh, true,
+						    flow_dv_push_vlan_create_cb,
+						    flow_dv_push_vlan_match_cb,
+						    flow_dv_push_vlan_remove_cb,
+						    flow_dv_push_vlan_clone_cb,
+					       flow_dv_push_vlan_clone_free_cb);
+	if (!sh->push_vlan_action_list)
+		goto error;
+	/* Init sample action list. */
+	snprintf(s, sizeof(s), "%s_sample_action_list", sh->ibdev_name);
+	sh->sample_action_list = mlx5_list_create(s, sh, true,
+						  flow_dv_sample_create_cb,
+						  flow_dv_sample_match_cb,
+						  flow_dv_sample_remove_cb,
+						  flow_dv_sample_clone_cb,
+						  flow_dv_sample_clone_free_cb);
+	if (!sh->sample_action_list)
+		goto error;
+	/* Init dest array action list. */
+	snprintf(s, sizeof(s), "%s_dest_array_list", sh->ibdev_name);
+	sh->dest_array_list = mlx5_list_create(s, sh, true,
+					       flow_dv_dest_array_create_cb,
+					       flow_dv_dest_array_match_cb,
+					       flow_dv_dest_array_remove_cb,
+					       flow_dv_dest_array_clone_cb,
+					      flow_dv_dest_array_clone_free_cb);
+	if (!sh->dest_array_list)
+		goto error;
+#endif
+#ifdef HAVE_MLX5DV_DR
+	void *domain;
+
+	/* Reference counter is zero, we should initialize structures. */
+	domain = mlx5_glue->dr_create_domain(sh->ctx,
+					     MLX5DV_DR_DOMAIN_TYPE_NIC_RX);
+	if (!domain) {
+		DRV_LOG(ERR, "ingress mlx5dv_dr_create_domain failed");
+		err = errno;
+		goto error;
+	}
+	sh->rx_domain = domain;
+	domain = mlx5_glue->dr_create_domain(sh->ctx,
+					     MLX5DV_DR_DOMAIN_TYPE_NIC_TX);
+	if (!domain) {
+		DRV_LOG(ERR, "egress mlx5dv_dr_create_domain failed");
+		err = errno;
+		goto error;
+	}
+	sh->tx_domain = domain;
+#ifdef HAVE_MLX5DV_DR_ESWITCH
+	if (priv->config.dv_esw_en) {
+		domain  = mlx5_glue->dr_create_domain
+			(sh->ctx, MLX5DV_DR_DOMAIN_TYPE_FDB);
+		if (!domain) {
+			DRV_LOG(ERR, "FDB mlx5dv_dr_create_domain failed");
+			err = errno;
+			goto error;
+		}
+		sh->fdb_domain = domain;
+	}
+	/*
+	 * The drop action is just some dummy placeholder in rdma-core. It
+	 * does not belong to domains and has no any attributes, and, can be
+	 * shared by the entire device.
+	 */
+	sh->dr_drop_action = mlx5_glue->dr_create_flow_action_drop();
+	if (!sh->dr_drop_action) {
+		DRV_LOG(ERR, "FDB mlx5dv_dr_create_flow_action_drop");
+		err = errno;
+		goto error;
+	}
+#endif
+	if (!sh->tunnel_hub && priv->config.dv_miss_info)
+		err = mlx5_alloc_tunnel_hub(sh);
+	if (err) {
+		DRV_LOG(ERR, "mlx5_alloc_tunnel_hub failed err=%d", err);
+		goto error;
+	}
+	if (priv->config.reclaim_mode == MLX5_RCM_AGGR) {
+		mlx5_glue->dr_reclaim_domain_memory(sh->rx_domain, 1);
+		mlx5_glue->dr_reclaim_domain_memory(sh->tx_domain, 1);
+		if (sh->fdb_domain)
+			mlx5_glue->dr_reclaim_domain_memory(sh->fdb_domain, 1);
+	}
+	sh->pop_vlan_action = mlx5_glue->dr_create_flow_action_pop_vlan();
+	if (!priv->config.allow_duplicate_pattern) {
+#ifndef HAVE_MLX5_DR_ALLOW_DUPLICATE
+		DRV_LOG(WARNING, "Disallow duplicate pattern is not supported - maybe old rdma-core version?");
+#endif
+		mlx5_glue->dr_allow_duplicate_rules(sh->rx_domain, 0);
+		mlx5_glue->dr_allow_duplicate_rules(sh->tx_domain, 0);
+		if (sh->fdb_domain)
+			mlx5_glue->dr_allow_duplicate_rules(sh->fdb_domain, 0);
+	}
+
+	__mlx5_discovery_misc5_cap(priv);
+#endif /* HAVE_MLX5DV_DR */
+	sh->default_miss_action =
+			mlx5_glue->dr_create_flow_action_default_miss();
+	if (!sh->default_miss_action)
+		DRV_LOG(WARNING, "Default miss action is not supported.");
+	return 0;
+error:
+	/* Rollback the created objects. */
+	if (sh->rx_domain) {
+		mlx5_glue->dr_destroy_domain(sh->rx_domain);
+		sh->rx_domain = NULL;
+	}
+	if (sh->tx_domain) {
+		mlx5_glue->dr_destroy_domain(sh->tx_domain);
+		sh->tx_domain = NULL;
+	}
+	if (sh->fdb_domain) {
+		mlx5_glue->dr_destroy_domain(sh->fdb_domain);
+		sh->fdb_domain = NULL;
+	}
+	if (sh->dr_drop_action) {
+		mlx5_glue->destroy_flow_action(sh->dr_drop_action);
+		sh->dr_drop_action = NULL;
+	}
+	if (sh->pop_vlan_action) {
+		mlx5_glue->destroy_flow_action(sh->pop_vlan_action);
+		sh->pop_vlan_action = NULL;
+	}
+	if (sh->encaps_decaps) {
+		mlx5_hlist_destroy(sh->encaps_decaps);
+		sh->encaps_decaps = NULL;
+	}
+	if (sh->modify_cmds) {
+		mlx5_hlist_destroy(sh->modify_cmds);
+		sh->modify_cmds = NULL;
+	}
+	if (sh->tag_table) {
+		/* tags should be destroyed with flow before. */
+		mlx5_hlist_destroy(sh->tag_table);
+		sh->tag_table = NULL;
+	}
+	if (sh->tunnel_hub) {
+		mlx5_release_tunnel_hub(sh, priv->dev_port);
+		sh->tunnel_hub = NULL;
+	}
+	mlx5_free_table_hash_list(priv);
+	if (sh->port_id_action_list) {
+		mlx5_list_destroy(sh->port_id_action_list);
+		sh->port_id_action_list = NULL;
+	}
+	if (sh->push_vlan_action_list) {
+		mlx5_list_destroy(sh->push_vlan_action_list);
+		sh->push_vlan_action_list = NULL;
+	}
+	if (sh->sample_action_list) {
+		mlx5_list_destroy(sh->sample_action_list);
+		sh->sample_action_list = NULL;
+	}
+	if (sh->dest_array_list) {
+		mlx5_list_destroy(sh->dest_array_list);
+		sh->dest_array_list = NULL;
+	}
+	return err;
+}
+
+/**
+ * Destroy DR related data within private structure.
+ *
+ * @param[in] priv
+ *   Pointer to the private device data structure.
+ */
+void
+mlx5_os_free_shared_dr(struct mlx5_priv *priv)
+{
+	struct mlx5_dev_ctx_shared *sh = priv->sh;
+
+	MLX5_ASSERT(sh && sh->refcnt);
+	if (sh->refcnt > 1)
+		return;
+#ifdef HAVE_MLX5DV_DR
+	if (sh->rx_domain) {
+		mlx5_glue->dr_destroy_domain(sh->rx_domain);
+		sh->rx_domain = NULL;
+	}
+	if (sh->tx_domain) {
+		mlx5_glue->dr_destroy_domain(sh->tx_domain);
+		sh->tx_domain = NULL;
+	}
+#ifdef HAVE_MLX5DV_DR_ESWITCH
+	if (sh->fdb_domain) {
+		mlx5_glue->dr_destroy_domain(sh->fdb_domain);
+		sh->fdb_domain = NULL;
+	}
+	if (sh->dr_drop_action) {
+		mlx5_glue->destroy_flow_action(sh->dr_drop_action);
+		sh->dr_drop_action = NULL;
+	}
+#endif
+	if (sh->pop_vlan_action) {
+		mlx5_glue->destroy_flow_action(sh->pop_vlan_action);
+		sh->pop_vlan_action = NULL;
+	}
+#endif /* HAVE_MLX5DV_DR */
+	if (sh->default_miss_action)
+		mlx5_glue->destroy_flow_action
+				(sh->default_miss_action);
+	if (sh->encaps_decaps) {
+		mlx5_hlist_destroy(sh->encaps_decaps);
+		sh->encaps_decaps = NULL;
+	}
+	if (sh->modify_cmds) {
+		mlx5_hlist_destroy(sh->modify_cmds);
+		sh->modify_cmds = NULL;
+	}
+	if (sh->tag_table) {
+		/* tags should be destroyed with flow before. */
+		mlx5_hlist_destroy(sh->tag_table);
+		sh->tag_table = NULL;
+	}
+	if (sh->tunnel_hub) {
+		mlx5_release_tunnel_hub(sh, priv->dev_port);
+		sh->tunnel_hub = NULL;
+	}
+	mlx5_free_table_hash_list(priv);
+	if (sh->port_id_action_list) {
+		mlx5_list_destroy(sh->port_id_action_list);
+		sh->port_id_action_list = NULL;
+	}
+	if (sh->push_vlan_action_list) {
+		mlx5_list_destroy(sh->push_vlan_action_list);
+		sh->push_vlan_action_list = NULL;
+	}
+	if (sh->sample_action_list) {
+		mlx5_list_destroy(sh->sample_action_list);
+		sh->sample_action_list = NULL;
+	}
+	if (sh->dest_array_list) {
+		mlx5_list_destroy(sh->dest_array_list);
+		sh->dest_array_list = NULL;
+	}
+}
+
+/**
+ * Initialize shared data between primary and secondary process.
+ *
+ * A memzone is reserved by primary process and secondary processes attach to
+ * the memzone.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_init_shared_data(void)
+{
+	const struct rte_memzone *mz;
+	int ret = 0;
+
+	rte_spinlock_lock(&mlx5_shared_data_lock);
+	if (mlx5_shared_data == NULL) {
+		if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+			/* Allocate shared memory. */
+			mz = rte_memzone_reserve(MZ_MLX5_PMD_SHARED_DATA,
+						 sizeof(*mlx5_shared_data),
+						 SOCKET_ID_ANY, 0);
+			if (mz == NULL) {
+				DRV_LOG(ERR,
+					"Cannot allocate mlx5 shared data");
+				ret = -rte_errno;
+				goto error;
+			}
+			mlx5_shared_data = mz->addr;
+			memset(mlx5_shared_data, 0, sizeof(*mlx5_shared_data));
+			rte_spinlock_init(&mlx5_shared_data->lock);
+		} else {
+			/* Lookup allocated shared memory. */
+			mz = rte_memzone_lookup(MZ_MLX5_PMD_SHARED_DATA);
+			if (mz == NULL) {
+				DRV_LOG(ERR,
+					"Cannot attach mlx5 shared data");
+				ret = -rte_errno;
+				goto error;
+			}
+			mlx5_shared_data = mz->addr;
+			memset(&mlx5_local_data, 0, sizeof(mlx5_local_data));
+		}
+	}
+error:
+	rte_spinlock_unlock(&mlx5_shared_data_lock);
+	return ret;
+}
+
+/**
+ * PMD global initialization.
+ *
+ * Independent from individual device, this function initializes global
+ * per-PMD data structures distinguishing primary and secondary processes.
+ * Hence, each initialization is called once per a process.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_init_once(void)
+{
+	struct mlx5_shared_data *sd;
+	struct mlx5_local_data *ld = &mlx5_local_data;
+	int ret = 0;
+
+	if (mlx5_init_shared_data())
+		return -rte_errno;
+	sd = mlx5_shared_data;
+	MLX5_ASSERT(sd);
+	rte_spinlock_lock(&sd->lock);
+	switch (rte_eal_process_type()) {
+	case RTE_PROC_PRIMARY:
+		if (sd->init_done)
+			break;
+		LIST_INIT(&sd->mem_event_cb_list);
+		rte_rwlock_init(&sd->mem_event_rwlock);
+		rte_mem_event_callback_register("MLX5_MEM_EVENT_CB",
+						mlx5_mr_mem_event_cb, NULL);
+		ret = mlx5_mp_init_primary(MLX5_MP_NAME,
+					   mlx5_mp_os_primary_handle);
+		if (ret)
+			goto out;
+		sd->init_done = true;
+		break;
+	case RTE_PROC_SECONDARY:
+		if (ld->init_done)
+			break;
+		ret = mlx5_mp_init_secondary(MLX5_MP_NAME,
+					     mlx5_mp_os_secondary_handle);
+		if (ret)
+			goto out;
+		++sd->secondary_cnt;
+		ld->init_done = true;
+		break;
+	default:
+		break;
+	}
+out:
+	rte_spinlock_unlock(&sd->lock);
+	return ret;
+}
+
+/**
+ * Create the Tx queue DevX/Verbs object.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ * @param idx
+ *   Queue index in DPDK Tx queue array.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_os_txq_obj_new(struct rte_eth_dev *dev, uint16_t idx)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_txq_data *txq_data = (*priv->txqs)[idx];
+	struct mlx5_txq_ctrl *txq_ctrl =
+			container_of(txq_data, struct mlx5_txq_ctrl, txq);
+
+	if (txq_ctrl->type == MLX5_TXQ_TYPE_HAIRPIN)
+		return mlx5_txq_devx_obj_new(dev, idx);
+#ifdef HAVE_MLX5DV_DEVX_UAR_OFFSET
+	if (!priv->config.dv_esw_en)
+		return mlx5_txq_devx_obj_new(dev, idx);
+#endif
+	return mlx5_txq_ibv_obj_new(dev, idx);
+}
+
+/**
+ * Release an Tx DevX/verbs queue object.
+ *
+ * @param txq_obj
+ *   DevX/Verbs Tx queue object.
+ */
+static void
+mlx5_os_txq_obj_release(struct mlx5_txq_obj *txq_obj)
+{
+	if (txq_obj->txq_ctrl->type == MLX5_TXQ_TYPE_HAIRPIN) {
+		mlx5_txq_devx_obj_release(txq_obj);
+		return;
+	}
+#ifdef HAVE_MLX5DV_DEVX_UAR_OFFSET
+	if (!txq_obj->txq_ctrl->priv->config.dv_esw_en) {
+		mlx5_txq_devx_obj_release(txq_obj);
+		return;
+	}
+#endif
+	mlx5_txq_ibv_obj_release(txq_obj);
+}
+
+/**
+ * DV flow counter mode detect and config.
+ *
+ * @param dev
+ *   Pointer to rte_eth_dev structure.
+ *
+ */
+static void
+mlx5_flow_counter_mode_config(struct rte_eth_dev *dev __rte_unused)
+{
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_dev_ctx_shared *sh = priv->sh;
+	bool fallback;
+
+#ifndef HAVE_IBV_DEVX_ASYNC
+	fallback = true;
+#else
+	fallback = false;
+	if (!priv->config.devx || !priv->config.dv_flow_en ||
+	    !priv->config.hca_attr.flow_counters_dump ||
+	    !(priv->config.hca_attr.flow_counter_bulk_alloc_bitmap & 0x4) ||
+	    (mlx5_flow_dv_discover_counter_offset_support(dev) == -ENOTSUP))
+		fallback = true;
+#endif
+	if (fallback)
+		DRV_LOG(INFO, "Use fall-back DV counter management. Flow "
+			"counter dump:%d, bulk_alloc_bitmap:0x%hhx.",
+			priv->config.hca_attr.flow_counters_dump,
+			priv->config.hca_attr.flow_counter_bulk_alloc_bitmap);
+	/* Initialize fallback mode only on the port initializes sh. */
+	if (sh->refcnt == 1)
+		sh->cmng.counter_fallback = fallback;
+	else if (fallback != sh->cmng.counter_fallback)
+		DRV_LOG(WARNING, "Port %d in sh has different fallback mode "
+			"with others:%d.", PORT_ID(priv), fallback);
+#endif
+}
+
+/**
+ * DR flow drop action support detect.
+ *
+ * @param dev
+ *   Pointer to rte_eth_dev structure.
+ *
+ */
+static void
+mlx5_flow_drop_action_config(struct rte_eth_dev *dev __rte_unused)
+{
+#ifdef HAVE_MLX5DV_DR
+	struct mlx5_priv *priv = dev->data->dev_private;
+
+	if (!priv->config.dv_flow_en || !priv->sh->dr_drop_action)
+		return;
+	/**
+	 * DR supports drop action placeholder when it is supported;
+	 * otherwise, use the queue drop action.
+	 */
+	if (mlx5_flow_discover_dr_action_support(dev))
+		priv->root_drop_action = priv->drop_queue.hrxq->action;
+	else
+		priv->root_drop_action = priv->sh->dr_drop_action;
+#endif
+}
+
+static void
+mlx5_queue_counter_id_prepare(struct rte_eth_dev *dev)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	void *ctx = priv->sh->ctx;
+
+	priv->q_counters = mlx5_devx_cmd_queue_counter_alloc(ctx);
+	if (!priv->q_counters) {
+		struct ibv_cq *cq = mlx5_glue->create_cq(ctx, 1, NULL, NULL, 0);
+		struct ibv_wq *wq;
+
+		DRV_LOG(DEBUG, "Port %d queue counter object cannot be created "
+			"by DevX - fall-back to use the kernel driver global "
+			"queue counter.", dev->data->port_id);
+		/* Create WQ by kernel and query its queue counter ID. */
+		if (cq) {
+			wq = mlx5_glue->create_wq(ctx,
+						  &(struct ibv_wq_init_attr){
+						    .wq_type = IBV_WQT_RQ,
+						    .max_wr = 1,
+						    .max_sge = 1,
+						    .pd = priv->sh->pd,
+						    .cq = cq,
+						});
+			if (wq) {
+				/* Counter is assigned only on RDY state. */
+				int ret = mlx5_glue->modify_wq(wq,
+						 &(struct ibv_wq_attr){
+						 .attr_mask = IBV_WQ_ATTR_STATE,
+						 .wq_state = IBV_WQS_RDY,
+						});
+
+				if (ret == 0)
+					mlx5_devx_cmd_wq_query(wq,
+							 &priv->counter_set_id);
+				claim_zero(mlx5_glue->destroy_wq(wq));
+			}
+			claim_zero(mlx5_glue->destroy_cq(cq));
+		}
+	} else {
+		priv->counter_set_id = priv->q_counters->id;
+	}
+	if (priv->counter_set_id == 0)
+		DRV_LOG(INFO, "Part of the port %d statistics will not be "
+			"available.", dev->data->port_id);
+}
+
+/**
+ * Check if representor spawn info match devargs.
+ *
+ * @param spawn
+ *   Verbs device parameters (name, port, switch_info) to spawn.
+ * @param eth_da
+ *   Device devargs to probe.
+ *
+ * @return
+ *   Match result.
+ */
+static bool
+mlx5_representor_match(struct mlx5_dev_spawn_data *spawn,
+		       struct rte_eth_devargs *eth_da)
+{
+	struct mlx5_switch_info *switch_info = &spawn->info;
+	unsigned int p, f;
+	uint16_t id;
+	uint16_t repr_id = mlx5_representor_id_encode(switch_info,
+						      eth_da->type);
+
+	switch (eth_da->type) {
+	case RTE_ETH_REPRESENTOR_SF:
+		if (!(spawn->info.port_name == -1 &&
+		      switch_info->name_type ==
+				MLX5_PHYS_PORT_NAME_TYPE_PFHPF) &&
+		    switch_info->name_type != MLX5_PHYS_PORT_NAME_TYPE_PFSF) {
+			rte_errno = EBUSY;
+			return false;
+		}
+		break;
+	case RTE_ETH_REPRESENTOR_VF:
+		/* Allows HPF representor index -1 as exception. */
+		if (!(spawn->info.port_name == -1 &&
+		      switch_info->name_type ==
+				MLX5_PHYS_PORT_NAME_TYPE_PFHPF) &&
+		    switch_info->name_type != MLX5_PHYS_PORT_NAME_TYPE_PFVF) {
+			rte_errno = EBUSY;
+			return false;
+		}
+		break;
+	case RTE_ETH_REPRESENTOR_NONE:
+		rte_errno = EBUSY;
+		return false;
+	default:
+		rte_errno = ENOTSUP;
+		DRV_LOG(ERR, "unsupported representor type");
+		return false;
+	}
+	/* Check representor ID: */
+	for (p = 0; p < eth_da->nb_ports; ++p) {
+		if (spawn->pf_bond < 0) {
+			/* For non-LAG mode, allow and ignore pf. */
+			switch_info->pf_num = eth_da->ports[p];
+			repr_id = mlx5_representor_id_encode(switch_info,
+							     eth_da->type);
+		}
+		for (f = 0; f < eth_da->nb_representor_ports; ++f) {
+			id = MLX5_REPRESENTOR_ID
+				(eth_da->ports[p], eth_da->type,
+				 eth_da->representor_ports[f]);
+			if (repr_id == id)
+				return true;
+		}
+	}
+	rte_errno = EBUSY;
+	return false;
+}
+
+
+/**
+ * Spawn an Ethernet device from Verbs information.
+ *
+ * @param dpdk_dev
+ *   Backing DPDK device.
+ * @param spawn
+ *   Verbs device parameters (name, port, switch_info) to spawn.
+ * @param config
+ *   Device configuration parameters.
+ * @param config
+ *   Device arguments.
+ *
+ * @return
+ *   A valid Ethernet device object on success, NULL otherwise and rte_errno
+ *   is set. The following errors are defined:
+ *
+ *   EBUSY: device is not supposed to be spawned.
+ *   EEXIST: device is already spawned
+ */
+static struct rte_eth_dev *
+mlx5_dev_spawn(struct rte_device *dpdk_dev,
+	       struct mlx5_dev_spawn_data *spawn,
+	       struct mlx5_dev_config *config,
+	       struct rte_eth_devargs *eth_da)
+{
+	const struct mlx5_switch_info *switch_info = &spawn->info;
+	struct mlx5_dev_ctx_shared *sh = NULL;
+	struct ibv_port_attr port_attr;
+	struct mlx5dv_context dv_attr = { .comp_mask = 0 };
+	struct rte_eth_dev *eth_dev = NULL;
+	struct mlx5_priv *priv = NULL;
+	int err = 0;
+	unsigned int hw_padding = 0;
+	unsigned int mps;
+	unsigned int tunnel_en = 0;
+	unsigned int mpls_en = 0;
+	unsigned int swp = 0;
+	unsigned int mprq = 0;
+	unsigned int mprq_min_stride_size_n = 0;
+	unsigned int mprq_max_stride_size_n = 0;
+	unsigned int mprq_min_stride_num_n = 0;
+	unsigned int mprq_max_stride_num_n = 0;
+	struct rte_ether_addr mac;
+	char name[RTE_ETH_NAME_MAX_LEN];
+	int own_domain_id = 0;
+	uint16_t port_id;
+	struct mlx5_port_info vport_info = { .query_flags = 0 };
+	int i;
+
+	/* Determine if this port representor is supposed to be spawned. */
+	if (switch_info->representor && dpdk_dev->devargs &&
+	    !mlx5_representor_match(spawn, eth_da))
+		return NULL;
+	/* Build device name. */
+	if (spawn->pf_bond < 0) {
+		/* Single device. */
+		if (!switch_info->representor)
+			strlcpy(name, dpdk_dev->name, sizeof(name));
+		else
+			err = snprintf(name, sizeof(name), "%s_representor_%s%u",
+				 dpdk_dev->name,
+				 switch_info->name_type ==
+				 MLX5_PHYS_PORT_NAME_TYPE_PFSF ? "sf" : "vf",
+				 switch_info->port_name);
+	} else {
+		/* Bonding device. */
+		if (!switch_info->representor) {
+			err = snprintf(name, sizeof(name), "%s_%s",
+				 dpdk_dev->name,
+				 mlx5_os_get_dev_device_name(spawn->phys_dev));
+		} else {
+			err = snprintf(name, sizeof(name), "%s_%s_representor_c%dpf%d%s%u",
+				dpdk_dev->name,
+				mlx5_os_get_dev_device_name(spawn->phys_dev),
+				switch_info->ctrl_num,
+				switch_info->pf_num,
+				switch_info->name_type ==
+				MLX5_PHYS_PORT_NAME_TYPE_PFSF ? "sf" : "vf",
+				switch_info->port_name);
+		}
+	}
+	if (err >= (int)sizeof(name))
+		DRV_LOG(WARNING, "device name overflow %s", name);
+	/* check if the device is already spawned */
+	if (rte_eth_dev_get_port_by_name(name, &port_id) == 0) {
+		rte_errno = EEXIST;
+		return NULL;
+	}
+	DRV_LOG(DEBUG, "naming Ethernet device \"%s\"", name);
+	if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
+		struct mlx5_mp_id mp_id;
+
+		eth_dev = rte_eth_dev_attach_secondary(name);
+		if (eth_dev == NULL) {
+			DRV_LOG(ERR, "can not attach rte ethdev");
+			rte_errno = ENOMEM;
+			return NULL;
+		}
+		eth_dev->device = dpdk_dev;
+		eth_dev->dev_ops = &mlx5_dev_sec_ops;
+		eth_dev->rx_descriptor_status = mlx5_rx_descriptor_status;
+		eth_dev->tx_descriptor_status = mlx5_tx_descriptor_status;
+		err = mlx5_proc_priv_init(eth_dev);
+		if (err)
+			return NULL;
+		mp_id.port_id = eth_dev->data->port_id;
+		strlcpy(mp_id.name, MLX5_MP_NAME, RTE_MP_MAX_NAME_LEN);
+		/* Receive command fd from primary process */
+		err = mlx5_mp_req_verbs_cmd_fd(&mp_id);
+		if (err < 0)
+			goto err_secondary;
+		/* Remap UAR for Tx queues. */
+		err = mlx5_tx_uar_init_secondary(eth_dev, err);
+		if (err)
+			goto err_secondary;
+		/*
+		 * Ethdev pointer is still required as input since
+		 * the primary device is not accessible from the
+		 * secondary process.
+		 */
+		eth_dev->rx_pkt_burst = mlx5_select_rx_function(eth_dev);
+		eth_dev->tx_pkt_burst = mlx5_select_tx_function(eth_dev);
+		return eth_dev;
+err_secondary:
+		mlx5_dev_close(eth_dev);
+		return NULL;
+	}
+	/*
+	 * Some parameters ("tx_db_nc" in particularly) are needed in
+	 * advance to create dv/verbs device context. We proceed the
+	 * devargs here to get ones, and later proceed devargs again
+	 * to override some hardware settings.
+	 */
+	err = mlx5_args(config, dpdk_dev->devargs);
+	if (err) {
+		err = rte_errno;
+		DRV_LOG(ERR, "failed to process device arguments: %s",
+			strerror(rte_errno));
+		goto error;
+	}
+	if (config->dv_miss_info) {
+		if (switch_info->master || switch_info->representor)
+			config->dv_xmeta_en = MLX5_XMETA_MODE_META16;
+	}
+	mlx5_malloc_mem_select(config->sys_mem_en);
+	sh = mlx5_alloc_shared_dev_ctx(spawn, config);
+	if (!sh)
+		return NULL;
+	config->devx = sh->devx;
+#ifdef HAVE_MLX5DV_DR_ACTION_DEST_DEVX_TIR
+	config->dest_tir = 1;
+#endif
+#ifdef HAVE_IBV_MLX5_MOD_SWP
+	dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_SWP;
+#endif
+	/*
+	 * Multi-packet send is supported by ConnectX-4 Lx PF as well
+	 * as all ConnectX-5 devices.
+	 */
+#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT
+	dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_TUNNEL_OFFLOADS;
+#endif
+#ifdef HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT
+	dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_STRIDING_RQ;
+#endif
+	mlx5_glue->dv_query_device(sh->ctx, &dv_attr);
+	if (dv_attr.flags & MLX5DV_CONTEXT_FLAGS_MPW_ALLOWED) {
+		if (dv_attr.flags & MLX5DV_CONTEXT_FLAGS_ENHANCED_MPW) {
+			DRV_LOG(DEBUG, "enhanced MPW is supported");
+			mps = MLX5_MPW_ENHANCED;
+		} else {
+			DRV_LOG(DEBUG, "MPW is supported");
+			mps = MLX5_MPW;
+		}
+	} else {
+		DRV_LOG(DEBUG, "MPW isn't supported");
+		mps = MLX5_MPW_DISABLED;
+	}
+#ifdef HAVE_IBV_MLX5_MOD_SWP
+	if (dv_attr.comp_mask & MLX5DV_CONTEXT_MASK_SWP)
+		swp = dv_attr.sw_parsing_caps.sw_parsing_offloads;
+	DRV_LOG(DEBUG, "SWP support: %u", swp);
+#endif
+	config->swp = !!swp;
+#ifdef HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT
+	if (dv_attr.comp_mask & MLX5DV_CONTEXT_MASK_STRIDING_RQ) {
+		struct mlx5dv_striding_rq_caps mprq_caps =
+			dv_attr.striding_rq_caps;
+
+		DRV_LOG(DEBUG, "\tmin_single_stride_log_num_of_bytes: %d",
+			mprq_caps.min_single_stride_log_num_of_bytes);
+		DRV_LOG(DEBUG, "\tmax_single_stride_log_num_of_bytes: %d",
+			mprq_caps.max_single_stride_log_num_of_bytes);
+		DRV_LOG(DEBUG, "\tmin_single_wqe_log_num_of_strides: %d",
+			mprq_caps.min_single_wqe_log_num_of_strides);
+		DRV_LOG(DEBUG, "\tmax_single_wqe_log_num_of_strides: %d",
+			mprq_caps.max_single_wqe_log_num_of_strides);
+		DRV_LOG(DEBUG, "\tsupported_qpts: %d",
+			mprq_caps.supported_qpts);
+		DRV_LOG(DEBUG, "device supports Multi-Packet RQ");
+		mprq = 1;
+		mprq_min_stride_size_n =
+			mprq_caps.min_single_stride_log_num_of_bytes;
+		mprq_max_stride_size_n =
+			mprq_caps.max_single_stride_log_num_of_bytes;
+		mprq_min_stride_num_n =
+			mprq_caps.min_single_wqe_log_num_of_strides;
+		mprq_max_stride_num_n =
+			mprq_caps.max_single_wqe_log_num_of_strides;
+	}
+#endif
+	/* Rx CQE compression is enabled by default. */
+	config->cqe_comp = 1;
+#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT
+	if (dv_attr.comp_mask & MLX5DV_CONTEXT_MASK_TUNNEL_OFFLOADS) {
+		tunnel_en = ((dv_attr.tunnel_offloads_caps &
+			      MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_VXLAN) &&
+			     (dv_attr.tunnel_offloads_caps &
+			      MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_GRE) &&
+			     (dv_attr.tunnel_offloads_caps &
+			      MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_GENEVE));
+	}
+	DRV_LOG(DEBUG, "tunnel offloading is %ssupported",
+		tunnel_en ? "" : "not ");
+#else
+	DRV_LOG(WARNING,
+		"tunnel offloading disabled due to old OFED/rdma-core version");
+#endif
+	config->tunnel_en = tunnel_en;
+#ifdef HAVE_IBV_DEVICE_MPLS_SUPPORT
+	mpls_en = ((dv_attr.tunnel_offloads_caps &
+		    MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_CW_MPLS_OVER_GRE) &&
+		   (dv_attr.tunnel_offloads_caps &
+		    MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_CW_MPLS_OVER_UDP));
+	DRV_LOG(DEBUG, "MPLS over GRE/UDP tunnel offloading is %ssupported",
+		mpls_en ? "" : "not ");
+#else
+	DRV_LOG(WARNING, "MPLS over GRE/UDP tunnel offloading disabled due to"
+		" old OFED/rdma-core version or firmware configuration");
+#endif
+	config->mpls_en = mpls_en;
+	/* Check port status. */
+	err = mlx5_glue->query_port(sh->ctx, spawn->phys_port, &port_attr);
+	if (err) {
+		DRV_LOG(ERR, "port query failed: %s", strerror(err));
+		goto error;
+	}
+	if (port_attr.link_layer != IBV_LINK_LAYER_ETHERNET) {
+		DRV_LOG(ERR, "port is not configured in Ethernet mode");
+		err = EINVAL;
+		goto error;
+	}
+	if (port_attr.state != IBV_PORT_ACTIVE)
+		DRV_LOG(DEBUG, "port is not active: \"%s\" (%d)",
+			mlx5_glue->port_state_str(port_attr.state),
+			port_attr.state);
+	/* Allocate private eth device data. */
+	priv = mlx5_malloc(MLX5_MEM_ZERO | MLX5_MEM_RTE,
+			   sizeof(*priv),
+			   RTE_CACHE_LINE_SIZE, SOCKET_ID_ANY);
+	if (priv == NULL) {
+		DRV_LOG(ERR, "priv allocation failure");
+		err = ENOMEM;
+		goto error;
+	}
+	priv->sh = sh;
+	priv->dev_port = spawn->phys_port;
+	priv->pci_dev = spawn->pci_dev;
+	priv->mtu = RTE_ETHER_MTU;
+	/* Some internal functions rely on Netlink sockets, open them now. */
+	priv->nl_socket_rdma = mlx5_nl_init(NETLINK_RDMA);
+	priv->nl_socket_route =	mlx5_nl_init(NETLINK_ROUTE);
+	priv->representor = !!switch_info->representor;
+	priv->master = !!switch_info->master;
+	priv->domain_id = RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID;
+	priv->vport_meta_tag = 0;
+	priv->vport_meta_mask = 0;
+	priv->pf_bond = spawn->pf_bond;
+
+	DRV_LOG(DEBUG,
+		"dev_port=%u bus=%s pci=%s master=%d representor=%d pf_bond=%d\n",
+		priv->dev_port, dpdk_dev->bus->name,
+		priv->pci_dev ? priv->pci_dev->name : "NONE",
+		priv->master, priv->representor, priv->pf_bond);
+
+	/*
+	 * If we have E-Switch we should determine the vport attributes.
+	 * E-Switch may use either source vport field or reg_c[0] metadata
+	 * register to match on vport index. The engaged part of metadata
+	 * register is defined by mask.
+	 */
+	if (switch_info->representor || switch_info->master) {
+		err = mlx5_glue->devx_port_query(sh->ctx,
+						 spawn->phys_port,
+						 &vport_info);
+		if (err) {
+			DRV_LOG(WARNING,
+				"can't query devx port %d on device %s",
+				spawn->phys_port,
+				mlx5_os_get_dev_device_name(spawn->phys_dev));
+			vport_info.query_flags = 0;
+		}
+	}
+	if (vport_info.query_flags & MLX5_PORT_QUERY_REG_C0) {
+		priv->vport_meta_tag = vport_info.vport_meta_tag;
+		priv->vport_meta_mask = vport_info.vport_meta_mask;
+		if (!priv->vport_meta_mask) {
+			DRV_LOG(ERR, "vport zero mask for port %d"
+				     " on bonding device %s",
+				     spawn->phys_port,
+				     mlx5_os_get_dev_device_name
+							(spawn->phys_dev));
+			err = ENOTSUP;
+			goto error;
+		}
+		if (priv->vport_meta_tag & ~priv->vport_meta_mask) {
+			DRV_LOG(ERR, "invalid vport tag for port %d"
+				     " on bonding device %s",
+				     spawn->phys_port,
+				     mlx5_os_get_dev_device_name
+							(spawn->phys_dev));
+			err = ENOTSUP;
+			goto error;
+		}
+	}
+	if (vport_info.query_flags & MLX5_PORT_QUERY_VPORT) {
+		priv->vport_id = vport_info.vport_id;
+	} else if (spawn->pf_bond >= 0 &&
+		   (switch_info->representor || switch_info->master)) {
+		DRV_LOG(ERR, "can't deduce vport index for port %d"
+			     " on bonding device %s",
+			     spawn->phys_port,
+			     mlx5_os_get_dev_device_name(spawn->phys_dev));
+		err = ENOTSUP;
+		goto error;
+	} else {
+		/*
+		 * Suppose vport index in compatible way. Kernel/rdma_core
+		 * support single E-Switch per PF configurations only and
+		 * vport_id field contains the vport index for associated VF,
+		 * which is deduced from representor port name.
+		 * For example, let's have the IB device port 10, it has
+		 * attached network device eth0, which has port name attribute
+		 * pf0vf2, we can deduce the VF number as 2, and set vport index
+		 * as 3 (2+1). This assigning schema should be changed if the
+		 * multiple E-Switch instances per PF configurations or/and PCI
+		 * subfunctions are added.
+		 */
+		priv->vport_id = switch_info->representor ?
+				 switch_info->port_name + 1 : -1;
+	}
+	priv->representor_id = mlx5_representor_id_encode(switch_info,
+							  eth_da->type);
+	/*
+	 * Look for sibling devices in order to reuse their switch domain
+	 * if any, otherwise allocate one.
+	 */
+	MLX5_ETH_FOREACH_DEV(port_id, dpdk_dev) {
+		const struct mlx5_priv *opriv =
+			rte_eth_devices[port_id].data->dev_private;
+
+		if (!opriv ||
+		    opriv->sh != priv->sh ||
+			opriv->domain_id ==
+			RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID)
+			continue;
+		priv->domain_id = opriv->domain_id;
+		DRV_LOG(DEBUG, "dev_port-%u inherit domain_id=%u\n",
+			priv->dev_port, priv->domain_id);
+		break;
+	}
+	if (priv->domain_id == RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID) {
+		err = rte_eth_switch_domain_alloc(&priv->domain_id);
+		if (err) {
+			err = rte_errno;
+			DRV_LOG(ERR, "unable to allocate switch domain: %s",
+				strerror(rte_errno));
+			goto error;
+		}
+		own_domain_id = 1;
+		DRV_LOG(DEBUG, "dev_port-%u new domain_id=%u\n",
+			priv->dev_port, priv->domain_id);
+	}
+	/* Override some values set by hardware configuration. */
+	mlx5_args(config, dpdk_dev->devargs);
+	err = mlx5_dev_check_sibling_config(priv, config, dpdk_dev);
+	if (err)
+		goto error;
+	config->hw_csum = !!(sh->device_attr.device_cap_flags_ex &
+			    IBV_DEVICE_RAW_IP_CSUM);
+	DRV_LOG(DEBUG, "checksum offloading is %ssupported",
+		(config->hw_csum ? "" : "not "));
+#if !defined(HAVE_IBV_DEVICE_COUNTERS_SET_V42) && \
+	!defined(HAVE_IBV_DEVICE_COUNTERS_SET_V45)
+	DRV_LOG(DEBUG, "counters are not supported");
+#endif
+#if !defined(HAVE_IBV_FLOW_DV_SUPPORT) || !defined(HAVE_MLX5DV_DR)
+	if (config->dv_flow_en) {
+		DRV_LOG(WARNING, "DV flow is not supported");
+		config->dv_flow_en = 0;
+	}
+#endif
+	if (spawn->max_port > UINT8_MAX) {
+		/* Verbs can't support ports larger than 255 by design. */
+		DRV_LOG(ERR, "can't support IB ports > UINT8_MAX");
+		err = EINVAL;
+		goto error;
+	}
+	config->ind_table_max_size =
+		sh->device_attr.max_rwq_indirection_table_size;
+	/*
+	 * Remove this check once DPDK supports larger/variable
+	 * indirection tables.
+	 */
+	if (config->ind_table_max_size > (unsigned int)ETH_RSS_RETA_SIZE_512)
+		config->ind_table_max_size = ETH_RSS_RETA_SIZE_512;
+	DRV_LOG(DEBUG, "maximum Rx indirection table size is %u",
+		config->ind_table_max_size);
+	config->hw_vlan_strip = !!(sh->device_attr.raw_packet_caps &
+				  IBV_RAW_PACKET_CAP_CVLAN_STRIPPING);
+	DRV_LOG(DEBUG, "VLAN stripping is %ssupported",
+		(config->hw_vlan_strip ? "" : "not "));
+	config->hw_fcs_strip = !!(sh->device_attr.raw_packet_caps &
+				 IBV_RAW_PACKET_CAP_SCATTER_FCS);
+#if defined(HAVE_IBV_WQ_FLAG_RX_END_PADDING)
+	hw_padding = !!sh->device_attr.rx_pad_end_addr_align;
+#elif defined(HAVE_IBV_WQ_FLAGS_PCI_WRITE_END_PADDING)
+	hw_padding = !!(sh->device_attr.device_cap_flags_ex &
+			IBV_DEVICE_PCI_WRITE_END_PADDING);
+#endif
+	if (config->hw_padding && !hw_padding) {
+		DRV_LOG(DEBUG, "Rx end alignment padding isn't supported");
+		config->hw_padding = 0;
+	} else if (config->hw_padding) {
+		DRV_LOG(DEBUG, "Rx end alignment padding is enabled");
+	}
+	config->tso = (sh->device_attr.max_tso > 0 &&
+		      (sh->device_attr.tso_supported_qpts &
+		       (1 << IBV_QPT_RAW_PACKET)));
+	if (config->tso)
+		config->tso_max_payload_sz = sh->device_attr.max_tso;
+	/*
+	 * MPW is disabled by default, while the Enhanced MPW is enabled
+	 * by default.
+	 */
+	if (config->mps == MLX5_ARG_UNSET)
+		config->mps = (mps == MLX5_MPW_ENHANCED) ? MLX5_MPW_ENHANCED :
+							  MLX5_MPW_DISABLED;
+	else
+		config->mps = config->mps ? mps : MLX5_MPW_DISABLED;
+	DRV_LOG(INFO, "%sMPS is %s",
+		config->mps == MLX5_MPW_ENHANCED ? "enhanced " :
+		config->mps == MLX5_MPW ? "legacy " : "",
+		config->mps != MLX5_MPW_DISABLED ? "enabled" : "disabled");
+	if (config->devx) {
+		err = mlx5_devx_cmd_query_hca_attr(sh->ctx, &config->hca_attr);
+		if (err) {
+			err = -err;
+			goto error;
+		}
+		/* Check relax ordering support. */
+		if (!haswell_broadwell_cpu) {
+			sh->cmng.relaxed_ordering_write =
+				config->hca_attr.relaxed_ordering_write;
+			sh->cmng.relaxed_ordering_read =
+				config->hca_attr.relaxed_ordering_read;
+		} else {
+			sh->cmng.relaxed_ordering_read = 0;
+			sh->cmng.relaxed_ordering_write = 0;
+		}
+		sh->rq_ts_format = config->hca_attr.rq_ts_format;
+		sh->sq_ts_format = config->hca_attr.sq_ts_format;
+		sh->steering_format_version =
+			config->hca_attr.steering_format_version;
+		sh->qp_ts_format = config->hca_attr.qp_ts_format;
+		/* Check for LRO support. */
+		if (config->dest_tir && config->hca_attr.lro_cap &&
+		    config->dv_flow_en) {
+			/* TBD check tunnel lro caps. */
+			config->lro.supported = config->hca_attr.lro_cap;
+			DRV_LOG(DEBUG, "Device supports LRO");
+			/*
+			 * If LRO timeout is not configured by application,
+			 * use the minimal supported value.
+			 */
+			if (!config->lro.timeout)
+				config->lro.timeout =
+				config->hca_attr.lro_timer_supported_periods[0];
+			DRV_LOG(DEBUG, "LRO session timeout set to %d usec",
+				config->lro.timeout);
+			DRV_LOG(DEBUG, "LRO minimal size of TCP segment "
+				"required for coalescing is %d bytes",
+				config->hca_attr.lro_min_mss_size);
+		}
+#if defined(HAVE_MLX5DV_DR) && \
+	(defined(HAVE_MLX5_DR_CREATE_ACTION_FLOW_METER) || \
+	 defined(HAVE_MLX5_DR_CREATE_ACTION_ASO))
+		if (config->hca_attr.qos.sup &&
+		    config->hca_attr.qos.flow_meter_old &&
+		    config->dv_flow_en) {
+			uint8_t reg_c_mask =
+				config->hca_attr.qos.flow_meter_reg_c_ids;
+			/*
+			 * Meter needs two REG_C's for color match and pre-sfx
+			 * flow match. Here get the REG_C for color match.
+			 * REG_C_0 and REG_C_1 is reserved for metadata feature.
+			 */
+			reg_c_mask &= 0xfc;
+			if (__builtin_popcount(reg_c_mask) < 1) {
+				priv->mtr_en = 0;
+				DRV_LOG(WARNING, "No available register for"
+					" meter.");
+			} else {
+				/*
+				 * The meter color register is used by the
+				 * flow-hit feature as well.
+				 * The flow-hit feature must use REG_C_3
+				 * Prefer REG_C_3 if it is available.
+				 */
+				if (reg_c_mask & (1 << (REG_C_3 - REG_C_0)))
+					priv->mtr_color_reg = REG_C_3;
+				else
+					priv->mtr_color_reg = ffs(reg_c_mask)
+							      - 1 + REG_C_0;
+				priv->mtr_en = 1;
+				priv->mtr_reg_share =
+				      config->hca_attr.qos.flow_meter;
+				DRV_LOG(DEBUG, "The REG_C meter uses is %d",
+					priv->mtr_color_reg);
+			}
+		}
+		if (config->hca_attr.qos.sup &&
+			config->hca_attr.qos.flow_meter_aso_sup) {
+			uint32_t log_obj_size =
+				rte_log2_u32(MLX5_ASO_MTRS_PER_POOL >> 1);
+			if (log_obj_size >=
+			config->hca_attr.qos.log_meter_aso_granularity &&
+			log_obj_size <=
+			config->hca_attr.qos.log_meter_aso_max_alloc)
+				sh->meter_aso_en = 1;
+		}
+		if (priv->mtr_en) {
+			err = mlx5_aso_flow_mtrs_mng_init(priv->sh);
+			if (err) {
+				err = -err;
+				goto error;
+			}
+		}
+		if (config->hca_attr.flow.tunnel_header_0_1)
+			sh->tunnel_header_0_1 = 1;
+#endif
+#ifdef HAVE_MLX5_DR_CREATE_ACTION_ASO
+		if (config->hca_attr.flow_hit_aso &&
+		    priv->mtr_color_reg == REG_C_3) {
+			sh->flow_hit_aso_en = 1;
+			err = mlx5_flow_aso_age_mng_init(sh);
+			if (err) {
+				err = -err;
+				goto error;
+			}
+			DRV_LOG(DEBUG, "Flow Hit ASO is supported.");
+		}
+#endif /* HAVE_MLX5_DR_CREATE_ACTION_ASO */
+#if defined(HAVE_MLX5_DR_CREATE_ACTION_ASO) && \
+	defined(HAVE_MLX5_DR_ACTION_ASO_CT)
+		if (config->hca_attr.ct_offload &&
+		    priv->mtr_color_reg == REG_C_3) {
+			err = mlx5_flow_aso_ct_mng_init(sh);
+			if (err) {
+				err = -err;
+				goto error;
+			}
+			DRV_LOG(DEBUG, "CT ASO is supported.");
+			sh->ct_aso_en = 1;
+		}
+#endif /* HAVE_MLX5_DR_CREATE_ACTION_ASO && HAVE_MLX5_DR_ACTION_ASO_CT */
+#if defined(HAVE_MLX5DV_DR) && defined(HAVE_MLX5_DR_CREATE_ACTION_FLOW_SAMPLE)
+		if (config->hca_attr.log_max_ft_sampler_num > 0  &&
+		    config->dv_flow_en) {
+			priv->sampler_en = 1;
+			DRV_LOG(DEBUG, "Sampler enabled!");
+		} else {
+			priv->sampler_en = 0;
+			if (!config->hca_attr.log_max_ft_sampler_num)
+				DRV_LOG(WARNING,
+					"No available register for sampler.");
+			else
+				DRV_LOG(DEBUG, "DV flow is not supported!");
+		}
+#endif
+	}
+	if (config->cqe_comp && RTE_CACHE_LINE_SIZE == 128 &&
+	    !(dv_attr.flags & MLX5DV_CONTEXT_FLAGS_CQE_128B_COMP)) {
+		DRV_LOG(WARNING, "Rx CQE 128B compression is not supported");
+		config->cqe_comp = 0;
+	}
+	if (config->cqe_comp_fmt == MLX5_CQE_RESP_FORMAT_FTAG_STRIDX &&
+	    (!config->devx || !config->hca_attr.mini_cqe_resp_flow_tag)) {
+		DRV_LOG(WARNING, "Flow Tag CQE compression"
+				 " format isn't supported.");
+		config->cqe_comp = 0;
+	}
+	if (config->cqe_comp_fmt == MLX5_CQE_RESP_FORMAT_L34H_STRIDX &&
+	    (!config->devx || !config->hca_attr.mini_cqe_resp_l3_l4_tag)) {
+		DRV_LOG(WARNING, "L3/L4 Header CQE compression"
+				 " format isn't supported.");
+		config->cqe_comp = 0;
+	}
+	DRV_LOG(DEBUG, "Rx CQE compression is %ssupported",
+			config->cqe_comp ? "" : "not ");
+	if (config->tx_pp) {
+		DRV_LOG(DEBUG, "Timestamp counter frequency %u kHz",
+			config->hca_attr.dev_freq_khz);
+		DRV_LOG(DEBUG, "Packet pacing is %ssupported",
+			config->hca_attr.qos.packet_pacing ? "" : "not ");
+		DRV_LOG(DEBUG, "Cross channel ops are %ssupported",
+			config->hca_attr.cross_channel ? "" : "not ");
+		DRV_LOG(DEBUG, "WQE index ignore is %ssupported",
+			config->hca_attr.wqe_index_ignore ? "" : "not ");
+		DRV_LOG(DEBUG, "Non-wire SQ feature is %ssupported",
+			config->hca_attr.non_wire_sq ? "" : "not ");
+		DRV_LOG(DEBUG, "Static WQE SQ feature is %ssupported (%d)",
+			config->hca_attr.log_max_static_sq_wq ? "" : "not ",
+			config->hca_attr.log_max_static_sq_wq);
+		DRV_LOG(DEBUG, "WQE rate PP mode is %ssupported",
+			config->hca_attr.qos.wqe_rate_pp ? "" : "not ");
+		if (!config->devx) {
+			DRV_LOG(ERR, "DevX is required for packet pacing");
+			err = ENODEV;
+			goto error;
+		}
+		if (!config->hca_attr.qos.packet_pacing) {
+			DRV_LOG(ERR, "Packet pacing is not supported");
+			err = ENODEV;
+			goto error;
+		}
+		if (!config->hca_attr.cross_channel) {
+			DRV_LOG(ERR, "Cross channel operations are"
+				     " required for packet pacing");
+			err = ENODEV;
+			goto error;
+		}
+		if (!config->hca_attr.wqe_index_ignore) {
+			DRV_LOG(ERR, "WQE index ignore feature is"
+				     " required for packet pacing");
+			err = ENODEV;
+			goto error;
+		}
+		if (!config->hca_attr.non_wire_sq) {
+			DRV_LOG(ERR, "Non-wire SQ feature is"
+				     " required for packet pacing");
+			err = ENODEV;
+			goto error;
+		}
+		if (!config->hca_attr.log_max_static_sq_wq) {
+			DRV_LOG(ERR, "Static WQE SQ feature is"
+				     " required for packet pacing");
+			err = ENODEV;
+			goto error;
+		}
+		if (!config->hca_attr.qos.wqe_rate_pp) {
+			DRV_LOG(ERR, "WQE rate mode is required"
+				     " for packet pacing");
+			err = ENODEV;
+			goto error;
+		}
+#ifndef HAVE_MLX5DV_DEVX_UAR_OFFSET
+		DRV_LOG(ERR, "DevX does not provide UAR offset,"
+			     " can't create queues for packet pacing");
+		err = ENODEV;
+		goto error;
+#endif
+	}
+	if (config->devx) {
+		uint32_t reg[MLX5_ST_SZ_DW(register_mtutc)];
+
+		err = config->hca_attr.access_register_user ?
+			mlx5_devx_cmd_register_read
+				(sh->ctx, MLX5_REGISTER_ID_MTUTC, 0,
+				reg, MLX5_ST_SZ_DW(register_mtutc)) : ENOTSUP;
+		if (!err) {
+			uint32_t ts_mode;
+
+			/* MTUTC register is read successfully. */
+			ts_mode = MLX5_GET(register_mtutc, reg,
+					   time_stamp_mode);
+			if (ts_mode == MLX5_MTUTC_TIMESTAMP_MODE_REAL_TIME)
+				config->rt_timestamp = 1;
+		} else {
+			/* Kernel does not support register reading. */
+			if (config->hca_attr.dev_freq_khz ==
+						 (NS_PER_S / MS_PER_S))
+				config->rt_timestamp = 1;
+		}
+	}
+	/*
+	 * If HW has bug working with tunnel packet decapsulation and
+	 * scatter FCS, and decapsulation is needed, clear the hw_fcs_strip
+	 * bit. Then DEV_RX_OFFLOAD_KEEP_CRC bit will not be set anymore.
+	 */
+	if (config->hca_attr.scatter_fcs_w_decap_disable && config->decap_en)
+		config->hw_fcs_strip = 0;
+	DRV_LOG(DEBUG, "FCS stripping configuration is %ssupported",
+		(config->hw_fcs_strip ? "" : "not "));
+	if (config->mprq.enabled && mprq) {
+		if (config->mprq.stride_num_n &&
+		    (config->mprq.stride_num_n > mprq_max_stride_num_n ||
+		     config->mprq.stride_num_n < mprq_min_stride_num_n)) {
+			config->mprq.stride_num_n =
+				RTE_MIN(RTE_MAX(MLX5_MPRQ_STRIDE_NUM_N,
+						mprq_min_stride_num_n),
+					mprq_max_stride_num_n);
+			DRV_LOG(WARNING,
+				"the number of strides"
+				" for Multi-Packet RQ is out of range,"
+				" setting default value (%u)",
+				1 << config->mprq.stride_num_n);
+		}
+		if (config->mprq.stride_size_n &&
+		    (config->mprq.stride_size_n > mprq_max_stride_size_n ||
+		     config->mprq.stride_size_n < mprq_min_stride_size_n)) {
+			config->mprq.stride_size_n =
+				RTE_MIN(RTE_MAX(MLX5_MPRQ_STRIDE_SIZE_N,
+						mprq_min_stride_size_n),
+					mprq_max_stride_size_n);
+			DRV_LOG(WARNING,
+				"the size of a stride"
+				" for Multi-Packet RQ is out of range,"
+				" setting default value (%u)",
+				1 << config->mprq.stride_size_n);
+		}
+		config->mprq.min_stride_size_n = mprq_min_stride_size_n;
+		config->mprq.max_stride_size_n = mprq_max_stride_size_n;
+	} else if (config->mprq.enabled && !mprq) {
+		DRV_LOG(WARNING, "Multi-Packet RQ isn't supported");
+		config->mprq.enabled = 0;
+	}
+	if (config->max_dump_files_num == 0)
+		config->max_dump_files_num = 128;
+	eth_dev = rte_eth_dev_allocate(name);
+	if (eth_dev == NULL) {
+		DRV_LOG(ERR, "can not allocate rte ethdev");
+		err = ENOMEM;
+		goto error;
+	}
+	if (priv->representor) {
+		eth_dev->data->dev_flags |= RTE_ETH_DEV_REPRESENTOR;
+		eth_dev->data->representor_id = priv->representor_id;
+	}
+	priv->mp_id.port_id = eth_dev->data->port_id;
+	strlcpy(priv->mp_id.name, MLX5_MP_NAME, RTE_MP_MAX_NAME_LEN);
+	/*
+	 * Store associated network device interface index. This index
+	 * is permanent throughout the lifetime of device. So, we may store
+	 * the ifindex here and use the cached value further.
+	 */
+	MLX5_ASSERT(spawn->ifindex);
+	priv->if_index = spawn->ifindex;
+	eth_dev->data->dev_private = priv;
+	priv->dev_data = eth_dev->data;
+	eth_dev->data->mac_addrs = priv->mac;
+	eth_dev->device = dpdk_dev;
+	eth_dev->data->dev_flags |= RTE_ETH_DEV_AUTOFILL_QUEUE_XSTATS;
+	/* Configure the first MAC address by default. */
+	if (mlx5_get_mac(eth_dev, &mac.addr_bytes)) {
+		DRV_LOG(ERR,
+			"port %u cannot get MAC address, is mlx5_en"
+			" loaded? (errno: %s)",
+			eth_dev->data->port_id, strerror(rte_errno));
+		err = ENODEV;
+		goto error;
+	}
+	DRV_LOG(INFO,
+		"port %u MAC address is " RTE_ETHER_ADDR_PRT_FMT,
+		eth_dev->data->port_id, RTE_ETHER_ADDR_BYTES(&mac));
+#ifdef RTE_LIBRTE_MLX5_DEBUG
+	{
+		char ifname[MLX5_NAMESIZE];
+
+		if (mlx5_get_ifname(eth_dev, &ifname) == 0)
+			DRV_LOG(DEBUG, "port %u ifname is \"%s\"",
+				eth_dev->data->port_id, ifname);
+		else
+			DRV_LOG(DEBUG, "port %u ifname is unknown",
+				eth_dev->data->port_id);
+	}
+#endif
+	/* Get actual MTU if possible. */
+	err = mlx5_get_mtu(eth_dev, &priv->mtu);
+	if (err) {
+		err = rte_errno;
+		goto error;
+	}
+	DRV_LOG(DEBUG, "port %u MTU is %u", eth_dev->data->port_id,
+		priv->mtu);
+	/* Initialize burst functions to prevent crashes before link-up. */
+	eth_dev->rx_pkt_burst = removed_rx_burst;
+	eth_dev->tx_pkt_burst = removed_tx_burst;
+	eth_dev->dev_ops = &mlx5_dev_ops;
+	eth_dev->rx_descriptor_status = mlx5_rx_descriptor_status;
+	eth_dev->tx_descriptor_status = mlx5_tx_descriptor_status;
+	eth_dev->rx_queue_count = mlx5_rx_queue_count;
+	/* Register MAC address. */
+	claim_zero(mlx5_mac_addr_add(eth_dev, &mac, 0, 0));
+	if (config->vf && config->vf_nl_en)
+		mlx5_nl_mac_addr_sync(priv->nl_socket_route,
+				      mlx5_ifindex(eth_dev),
+				      eth_dev->data->mac_addrs,
+				      MLX5_MAX_MAC_ADDRESSES);
+	priv->ctrl_flows = 0;
+	rte_spinlock_init(&priv->flow_list_lock);
+	TAILQ_INIT(&priv->flow_meters);
+	priv->mtr_profile_tbl = mlx5_l3t_create(MLX5_L3T_TYPE_PTR);
+	if (!priv->mtr_profile_tbl)
+		goto error;
+	/* Hint libmlx5 to use PMD allocator for data plane resources */
+	mlx5_glue->dv_set_context_attr(sh->ctx,
+			MLX5DV_CTX_ATTR_BUF_ALLOCATORS,
+			(void *)((uintptr_t)&(struct mlx5dv_ctx_allocators){
+				.alloc = &mlx5_alloc_verbs_buf,
+				.free = &mlx5_free_verbs_buf,
+				.data = sh,
+			}));
+	/* Bring Ethernet device up. */
+	DRV_LOG(DEBUG, "port %u forcing Ethernet interface up",
+		eth_dev->data->port_id);
+	mlx5_set_link_up(eth_dev);
+	/*
+	 * Even though the interrupt handler is not installed yet,
+	 * interrupts will still trigger on the async_fd from
+	 * Verbs context returned by ibv_open_device().
+	 */
+	mlx5_link_update(eth_dev, 0);
+#ifdef HAVE_MLX5DV_DR_ESWITCH
+	if (!(config->hca_attr.eswitch_manager && config->dv_flow_en &&
+	      (switch_info->representor || switch_info->master)))
+		config->dv_esw_en = 0;
+#else
+	config->dv_esw_en = 0;
+#endif
+	/* Detect minimal data bytes to inline. */
+	mlx5_set_min_inline(spawn, config);
+	/* Store device configuration on private structure. */
+	priv->config = *config;
+	for (i = 0; i < MLX5_FLOW_TYPE_MAXI; i++) {
+		icfg[i].release_mem_en = !!config->reclaim_mode;
+		if (config->reclaim_mode)
+			icfg[i].per_core_cache = 0;
+		priv->flows[i] = mlx5_ipool_create(&icfg[i]);
+		if (!priv->flows[i])
+			goto error;
+	}
+	/* Create context for virtual machine VLAN workaround. */
+	priv->vmwa_context = mlx5_vlan_vmwa_init(eth_dev, spawn->ifindex);
+	if (config->dv_flow_en) {
+		err = mlx5_alloc_shared_dr(priv);
+		if (err)
+			goto error;
+	}
+	if (config->devx && config->dv_flow_en && config->dest_tir) {
+		priv->obj_ops = devx_obj_ops;
+		priv->obj_ops.drop_action_create =
+						ibv_obj_ops.drop_action_create;
+		priv->obj_ops.drop_action_destroy =
+						ibv_obj_ops.drop_action_destroy;
+#ifndef HAVE_MLX5DV_DEVX_UAR_OFFSET
+		priv->obj_ops.txq_obj_modify = ibv_obj_ops.txq_obj_modify;
+#else
+		if (config->dv_esw_en)
+			priv->obj_ops.txq_obj_modify =
+						ibv_obj_ops.txq_obj_modify;
+#endif
+		/* Use specific wrappers for Tx object. */
+		priv->obj_ops.txq_obj_new = mlx5_os_txq_obj_new;
+		priv->obj_ops.txq_obj_release = mlx5_os_txq_obj_release;
+		mlx5_queue_counter_id_prepare(eth_dev);
+		priv->obj_ops.lb_dummy_queue_create =
+					mlx5_rxq_ibv_obj_dummy_lb_create;
+		priv->obj_ops.lb_dummy_queue_release =
+					mlx5_rxq_ibv_obj_dummy_lb_release;
+	} else {
+		priv->obj_ops = ibv_obj_ops;
+	}
+	if (config->tx_pp &&
+	    (priv->config.dv_esw_en ||
+	     priv->obj_ops.txq_obj_new != mlx5_os_txq_obj_new)) {
+		/*
+		 * HAVE_MLX5DV_DEVX_UAR_OFFSET is required to support
+		 * packet pacing and already checked above.
+		 * Hence, we should only make sure the SQs will be created
+		 * with DevX, not with Verbs.
+		 * Verbs allocates the SQ UAR on its own and it can't be shared
+		 * with Clock Queue UAR as required for Tx scheduling.
+		 */
+		DRV_LOG(ERR, "Verbs SQs, UAR can't be shared as required for packet pacing");
+		err = ENODEV;
+		goto error;
+	}
+	priv->drop_queue.hrxq = mlx5_drop_action_create(eth_dev);
+	if (!priv->drop_queue.hrxq)
+		goto error;
+	/* Supported Verbs flow priority number detection. */
+	err = mlx5_flow_discover_priorities(eth_dev);
+	if (err < 0) {
+		err = -err;
+		goto error;
+	}
+	priv->config.flow_prio = err;
+	if (!priv->config.dv_esw_en &&
+	    priv->config.dv_xmeta_en != MLX5_XMETA_MODE_LEGACY) {
+		DRV_LOG(WARNING, "metadata mode %u is not supported "
+				 "(no E-Switch)", priv->config.dv_xmeta_en);
+		priv->config.dv_xmeta_en = MLX5_XMETA_MODE_LEGACY;
+	}
+	mlx5_set_metadata_mask(eth_dev);
+	if (priv->config.dv_xmeta_en != MLX5_XMETA_MODE_LEGACY &&
+	    !priv->sh->dv_regc0_mask) {
+		DRV_LOG(ERR, "metadata mode %u is not supported "
+			     "(no metadata reg_c[0] is available)",
+			     priv->config.dv_xmeta_en);
+			err = ENOTSUP;
+			goto error;
+	}
+	priv->hrxqs = mlx5_list_create("hrxq", eth_dev, true,
+				       mlx5_hrxq_create_cb,
+				       mlx5_hrxq_match_cb,
+				       mlx5_hrxq_remove_cb,
+				       mlx5_hrxq_clone_cb,
+				       mlx5_hrxq_clone_free_cb);
+	if (!priv->hrxqs)
+		goto error;
+	rte_rwlock_init(&priv->ind_tbls_lock);
+	/* Query availability of metadata reg_c's. */
+	err = mlx5_flow_discover_mreg_c(eth_dev);
+	if (err < 0) {
+		err = -err;
+		goto error;
+	}
+	if (!mlx5_flow_ext_mreg_supported(eth_dev)) {
+		DRV_LOG(DEBUG,
+			"port %u extensive metadata register is not supported",
+			eth_dev->data->port_id);
+		if (priv->config.dv_xmeta_en != MLX5_XMETA_MODE_LEGACY) {
+			DRV_LOG(ERR, "metadata mode %u is not supported "
+				     "(no metadata registers available)",
+				     priv->config.dv_xmeta_en);
+			err = ENOTSUP;
+			goto error;
+		}
+	}
+	if (priv->config.dv_flow_en &&
+	    priv->config.dv_xmeta_en != MLX5_XMETA_MODE_LEGACY &&
+	    mlx5_flow_ext_mreg_supported(eth_dev) &&
+	    priv->sh->dv_regc0_mask) {
+		priv->mreg_cp_tbl = mlx5_hlist_create(MLX5_FLOW_MREG_HNAME,
+						      MLX5_FLOW_MREG_HTABLE_SZ,
+						      false, true, eth_dev,
+						      flow_dv_mreg_create_cb,
+						      flow_dv_mreg_match_cb,
+						      flow_dv_mreg_remove_cb,
+						      flow_dv_mreg_clone_cb,
+						    flow_dv_mreg_clone_free_cb);
+		if (!priv->mreg_cp_tbl) {
+			err = ENOMEM;
+			goto error;
+		}
+	}
+	rte_spinlock_init(&priv->shared_act_sl);
+	mlx5_flow_counter_mode_config(eth_dev);
+	mlx5_flow_drop_action_config(eth_dev);
+	if (priv->config.dv_flow_en)
+		eth_dev->data->dev_flags |= RTE_ETH_DEV_FLOW_OPS_THREAD_SAFE;
+	return eth_dev;
+error:
+	if (priv) {
+		if (priv->mreg_cp_tbl)
+			mlx5_hlist_destroy(priv->mreg_cp_tbl);
+		if (priv->sh)
+			mlx5_os_free_shared_dr(priv);
+		if (priv->nl_socket_route >= 0)
+			close(priv->nl_socket_route);
+		if (priv->nl_socket_rdma >= 0)
+			close(priv->nl_socket_rdma);
+		if (priv->vmwa_context)
+			mlx5_vlan_vmwa_exit(priv->vmwa_context);
+		if (eth_dev && priv->drop_queue.hrxq)
+			mlx5_drop_action_destroy(eth_dev);
+		if (priv->mtr_profile_tbl)
+			mlx5_l3t_destroy(priv->mtr_profile_tbl);
+		if (own_domain_id)
+			claim_zero(rte_eth_switch_domain_free(priv->domain_id));
+		if (priv->hrxqs)
+			mlx5_list_destroy(priv->hrxqs);
+		mlx5_free(priv);
+		if (eth_dev != NULL)
+			eth_dev->data->dev_private = NULL;
+	}
+	if (eth_dev != NULL) {
+		/* mac_addrs must not be freed alone because part of
+		 * dev_private
+		 **/
+		eth_dev->data->mac_addrs = NULL;
+		rte_eth_dev_release_port(eth_dev);
+	}
+	if (sh)
+		mlx5_free_shared_dev_ctx(sh);
+	MLX5_ASSERT(err > 0);
+	rte_errno = err;
+	return NULL;
+}
+
+/**
+ * Comparison callback to sort device data.
+ *
+ * This is meant to be used with qsort().
+ *
+ * @param a[in]
+ *   Pointer to pointer to first data object.
+ * @param b[in]
+ *   Pointer to pointer to second data object.
+ *
+ * @return
+ *   0 if both objects are equal, less than 0 if the first argument is less
+ *   than the second, greater than 0 otherwise.
+ */
+static int
+mlx5_dev_spawn_data_cmp(const void *a, const void *b)
+{
+	const struct mlx5_switch_info *si_a =
+		&((const struct mlx5_dev_spawn_data *)a)->info;
+	const struct mlx5_switch_info *si_b =
+		&((const struct mlx5_dev_spawn_data *)b)->info;
+	int ret;
+
+	/* Master device first. */
+	ret = si_b->master - si_a->master;
+	if (ret)
+		return ret;
+	/* Then representor devices. */
+	ret = si_b->representor - si_a->representor;
+	if (ret)
+		return ret;
+	/* Unidentified devices come last in no specific order. */
+	if (!si_a->representor)
+		return 0;
+	/* Order representors by name. */
+	return si_a->port_name - si_b->port_name;
+}
+
+/**
+ * Match PCI information for possible slaves of bonding device.
+ *
+ * @param[in] ibv_dev
+ *   Pointer to Infiniband device structure.
+ * @param[in] pci_dev
+ *   Pointer to primary PCI address structure to match.
+ * @param[in] nl_rdma
+ *   Netlink RDMA group socket handle.
+ * @param[in] owner
+ *   Rerepsentor owner PF index.
+ * @param[out] bond_info
+ *   Pointer to bonding information.
+ *
+ * @return
+ *   negative value if no bonding device found, otherwise
+ *   positive index of slave PF in bonding.
+ */
+static int
+mlx5_device_bond_pci_match(const struct ibv_device *ibv_dev,
+			   const struct rte_pci_addr *pci_dev,
+			   int nl_rdma, uint16_t owner,
+			   struct mlx5_bond_info *bond_info)
+{
+	char ifname[IF_NAMESIZE + 1];
+	unsigned int ifindex;
+	unsigned int np, i;
+	FILE *bond_file = NULL, *file;
+	int pf = -1;
+	int ret;
+
+	/*
+	 * Try to get master device name. If something goes
+	 * wrong suppose the lack of kernel support and no
+	 * bonding devices.
+	 */
+	memset(bond_info, 0, sizeof(*bond_info));
+	if (nl_rdma < 0)
+		return -1;
+	if (!strstr(ibv_dev->name, "bond"))
+		return -1;
+	np = mlx5_nl_portnum(nl_rdma, ibv_dev->name);
+	if (!np)
+		return -1;
+	/*
+	 * The Master device might not be on the predefined
+	 * port (not on port index 1, it is not garanted),
+	 * we have to scan all Infiniband device port and
+	 * find master.
+	 */
+	for (i = 1; i <= np; ++i) {
+		/* Check whether Infiniband port is populated. */
+		ifindex = mlx5_nl_ifindex(nl_rdma, ibv_dev->name, i);
+		if (!ifindex)
+			continue;
+		if (!if_indextoname(ifindex, ifname))
+			continue;
+		/* Try to read bonding slave names from sysfs. */
+		MKSTR(slaves,
+		      "/sys/class/net/%s/master/bonding/slaves", ifname);
+		bond_file = fopen(slaves, "r");
+		if (bond_file)
+			break;
+	}
+	if (!bond_file)
+		return -1;
+	/* Use safe format to check maximal buffer length. */
+	MLX5_ASSERT(atol(RTE_STR(IF_NAMESIZE)) == IF_NAMESIZE);
+	while (fscanf(bond_file, "%" RTE_STR(IF_NAMESIZE) "s", ifname) == 1) {
+		char tmp_str[IF_NAMESIZE + 32];
+		struct rte_pci_addr pci_addr;
+		struct mlx5_switch_info	info;
+
+		/* Process slave interface names in the loop. */
+		snprintf(tmp_str, sizeof(tmp_str),
+			 "/sys/class/net/%s", ifname);
+		if (mlx5_get_pci_addr(tmp_str, &pci_addr)) {
+			DRV_LOG(WARNING, "can not get PCI address"
+					 " for netdev \"%s\"", ifname);
+			continue;
+		}
+		/* Slave interface PCI address match found. */
+		snprintf(tmp_str, sizeof(tmp_str),
+			 "/sys/class/net/%s/phys_port_name", ifname);
+		file = fopen(tmp_str, "rb");
+		if (!file)
+			break;
+		info.name_type = MLX5_PHYS_PORT_NAME_TYPE_NOTSET;
+		if (fscanf(file, "%32s", tmp_str) == 1)
+			mlx5_translate_port_name(tmp_str, &info);
+		fclose(file);
+		/* Only process PF ports. */
+		if (info.name_type != MLX5_PHYS_PORT_NAME_TYPE_LEGACY &&
+		    info.name_type != MLX5_PHYS_PORT_NAME_TYPE_UPLINK)
+			continue;
+		/* Check max bonding member. */
+		if (info.port_name >= MLX5_BOND_MAX_PORTS) {
+			DRV_LOG(WARNING, "bonding index out of range, "
+				"please increase MLX5_BOND_MAX_PORTS: %s",
+				tmp_str);
+			break;
+		}
+		/* Match PCI address, allows BDF0+pfx or BDFx+pfx. */
+		if (pci_dev->domain == pci_addr.domain &&
+		    pci_dev->bus == pci_addr.bus &&
+		    pci_dev->devid == pci_addr.devid &&
+		    ((pci_dev->function == 0 &&
+		      pci_dev->function + owner == pci_addr.function) ||
+		     (pci_dev->function == owner &&
+		      pci_addr.function == owner)))
+			pf = info.port_name;
+		/* Get ifindex. */
+		snprintf(tmp_str, sizeof(tmp_str),
+			 "/sys/class/net/%s/ifindex", ifname);
+		file = fopen(tmp_str, "rb");
+		if (!file)
+			break;
+		ret = fscanf(file, "%u", &ifindex);
+		fclose(file);
+		if (ret != 1)
+			break;
+		/* Save bonding info. */
+		strncpy(bond_info->ports[info.port_name].ifname, ifname,
+			sizeof(bond_info->ports[0].ifname));
+		bond_info->ports[info.port_name].pci_addr = pci_addr;
+		bond_info->ports[info.port_name].ifindex = ifindex;
+		bond_info->n_port++;
+	}
+	if (pf >= 0) {
+		/* Get bond interface info */
+		ret = mlx5_sysfs_bond_info(ifindex, &bond_info->ifindex,
+					   bond_info->ifname);
+		if (ret)
+			DRV_LOG(ERR, "unable to get bond info: %s",
+				strerror(rte_errno));
+		else
+			DRV_LOG(INFO, "PF device %u, bond device %u(%s)",
+				ifindex, bond_info->ifindex, bond_info->ifname);
+	}
+	return pf;
+}
+
+static void
+mlx5_os_config_default(struct mlx5_dev_config *config)
+{
+	memset(config, 0, sizeof(*config));
+	config->mps = MLX5_ARG_UNSET;
+	config->dbnc = MLX5_ARG_UNSET;
+	config->rx_vec_en = 1;
+	config->txq_inline_max = MLX5_ARG_UNSET;
+	config->txq_inline_min = MLX5_ARG_UNSET;
+	config->txq_inline_mpw = MLX5_ARG_UNSET;
+	config->txqs_inline = MLX5_ARG_UNSET;
+	config->vf_nl_en = 1;
+	config->mr_ext_memseg_en = 1;
+	config->mprq.max_memcpy_len = MLX5_MPRQ_MEMCPY_DEFAULT_LEN;
+	config->mprq.min_rxqs_num = MLX5_MPRQ_MIN_RXQS;
+	config->dv_esw_en = 1;
+	config->dv_flow_en = 1;
+	config->decap_en = 1;
+	config->log_hp_size = MLX5_ARG_UNSET;
+	config->allow_duplicate_pattern = 1;
+}
+
+/**
+ * Register a PCI device within bonding.
+ *
+ * This function spawns Ethernet devices out of a given PCI device and
+ * bonding owner PF index.
+ *
+ * @param[in] pci_dev
+ *   PCI device information.
+ * @param[in] req_eth_da
+ *   Requested ethdev device argument.
+ * @param[in] owner_id
+ *   Requested owner PF port ID within bonding device, default to 0.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev,
+		     struct rte_eth_devargs *req_eth_da,
+		     uint16_t owner_id)
+{
+	struct ibv_device **ibv_list;
+	/*
+	 * Number of found IB Devices matching with requested PCI BDF.
+	 * nd != 1 means there are multiple IB devices over the same
+	 * PCI device and we have representors and master.
+	 */
+	unsigned int nd = 0;
+	/*
+	 * Number of found IB device Ports. nd = 1 and np = 1..n means
+	 * we have the single multiport IB device, and there may be
+	 * representors attached to some of found ports.
+	 */
+	unsigned int np = 0;
+	/*
+	 * Number of DPDK ethernet devices to Spawn - either over
+	 * multiple IB devices or multiple ports of single IB device.
+	 * Actually this is the number of iterations to spawn.
+	 */
+	unsigned int ns = 0;
+	/*
+	 * Bonding device
+	 *   < 0 - no bonding device (single one)
+	 *  >= 0 - bonding device (value is slave PF index)
+	 */
+	int bd = -1;
+	struct mlx5_dev_spawn_data *list = NULL;
+	struct mlx5_dev_config dev_config;
+	unsigned int dev_config_vf;
+	struct rte_eth_devargs eth_da = *req_eth_da;
+	struct rte_pci_addr owner_pci = pci_dev->addr; /* Owner PF. */
+	struct mlx5_bond_info bond_info;
+	int ret = -1;
+
+	errno = 0;
+	ibv_list = mlx5_glue->get_device_list(&ret);
+	if (!ibv_list) {
+		rte_errno = errno ? errno : ENOSYS;
+		DRV_LOG(ERR, "cannot list devices, is ib_uverbs loaded?");
+		return -rte_errno;
+	}
+	/*
+	 * First scan the list of all Infiniband devices to find
+	 * matching ones, gathering into the list.
+	 */
+	struct ibv_device *ibv_match[ret + 1];
+	int nl_route = mlx5_nl_init(NETLINK_ROUTE);
+	int nl_rdma = mlx5_nl_init(NETLINK_RDMA);
+	unsigned int i;
+
+	while (ret-- > 0) {
+		struct rte_pci_addr pci_addr;
+
+		DRV_LOG(DEBUG, "checking device \"%s\"", ibv_list[ret]->name);
+		bd = mlx5_device_bond_pci_match
+				(ibv_list[ret], &owner_pci, nl_rdma, owner_id,
+				 &bond_info);
+		if (bd >= 0) {
+			/*
+			 * Bonding device detected. Only one match is allowed,
+			 * the bonding is supported over multi-port IB device,
+			 * there should be no matches on representor PCI
+			 * functions or non VF LAG bonding devices with
+			 * specified address.
+			 */
+			if (nd) {
+				DRV_LOG(ERR,
+					"multiple PCI match on bonding device"
+					"\"%s\" found", ibv_list[ret]->name);
+				rte_errno = ENOENT;
+				ret = -rte_errno;
+				goto exit;
+			}
+			/* Amend owner pci address if owner PF ID specified. */
+			if (eth_da.nb_representor_ports)
+				owner_pci.function += owner_id;
+			DRV_LOG(INFO, "PCI information matches for"
+				      " slave %d bonding device \"%s\"",
+				      bd, ibv_list[ret]->name);
+			ibv_match[nd++] = ibv_list[ret];
+			break;
+		} else {
+			/* Bonding device not found. */
+			if (mlx5_get_pci_addr(ibv_list[ret]->ibdev_path,
+					      &pci_addr))
+				continue;
+			if (owner_pci.domain != pci_addr.domain ||
+			    owner_pci.bus != pci_addr.bus ||
+			    owner_pci.devid != pci_addr.devid ||
+			    owner_pci.function != pci_addr.function)
+				continue;
+			DRV_LOG(INFO, "PCI information matches for device \"%s\"",
+				ibv_list[ret]->name);
+			ibv_match[nd++] = ibv_list[ret];
+		}
+	}
+	ibv_match[nd] = NULL;
+	if (!nd) {
+		/* No device matches, just complain and bail out. */
+		DRV_LOG(WARNING,
+			"no Verbs device matches PCI device " PCI_PRI_FMT ","
+			" are kernel drivers loaded?",
+			owner_pci.domain, owner_pci.bus,
+			owner_pci.devid, owner_pci.function);
+		rte_errno = ENOENT;
+		ret = -rte_errno;
+		goto exit;
+	}
+	if (nd == 1) {
+		/*
+		 * Found single matching device may have multiple ports.
+		 * Each port may be representor, we have to check the port
+		 * number and check the representors existence.
+		 */
+		if (nl_rdma >= 0)
+			np = mlx5_nl_portnum(nl_rdma, ibv_match[0]->name);
+		if (!np)
+			DRV_LOG(WARNING, "can not get IB device \"%s\""
+					 " ports number", ibv_match[0]->name);
+		if (bd >= 0 && !np) {
+			DRV_LOG(ERR, "can not get ports"
+				     " for bonding device");
+			rte_errno = ENOENT;
+			ret = -rte_errno;
+			goto exit;
+		}
+	}
+	/*
+	 * Now we can determine the maximal
+	 * amount of devices to be spawned.
+	 */
+	list = mlx5_malloc(MLX5_MEM_ZERO,
+			   sizeof(struct mlx5_dev_spawn_data) *
+			   (np ? np : nd),
+			   RTE_CACHE_LINE_SIZE, SOCKET_ID_ANY);
+	if (!list) {
+		DRV_LOG(ERR, "spawn data array allocation failure");
+		rte_errno = ENOMEM;
+		ret = -rte_errno;
+		goto exit;
+	}
+	if (bd >= 0 || np > 1) {
+		/*
+		 * Single IB device with multiple ports found,
+		 * it may be E-Switch master device and representors.
+		 * We have to perform identification through the ports.
+		 */
+		MLX5_ASSERT(nl_rdma >= 0);
+		MLX5_ASSERT(ns == 0);
+		MLX5_ASSERT(nd == 1);
+		MLX5_ASSERT(np);
+		for (i = 1; i <= np; ++i) {
+			list[ns].bond_info = &bond_info;
+			list[ns].max_port = np;
+			list[ns].phys_port = i;
+			list[ns].phys_dev = ibv_match[0];
+			list[ns].eth_dev = NULL;
+			list[ns].pci_dev = pci_dev;
+			list[ns].pf_bond = bd;
+			list[ns].ifindex = mlx5_nl_ifindex
+				(nl_rdma,
+				mlx5_os_get_dev_device_name
+						(list[ns].phys_dev), i);
+			if (!list[ns].ifindex) {
+				/*
+				 * No network interface index found for the
+				 * specified port, it means there is no
+				 * representor on this port. It's OK,
+				 * there can be disabled ports, for example
+				 * if sriov_numvfs < sriov_totalvfs.
+				 */
+				continue;
+			}
+			ret = -1;
+			if (nl_route >= 0)
+				ret = mlx5_nl_switch_info
+					       (nl_route,
+						list[ns].ifindex,
+						&list[ns].info);
+			if (ret || (!list[ns].info.representor &&
+				    !list[ns].info.master)) {
+				/*
+				 * We failed to recognize representors with
+				 * Netlink, let's try to perform the task
+				 * with sysfs.
+				 */
+				ret =  mlx5_sysfs_switch_info
+						(list[ns].ifindex,
+						 &list[ns].info);
+			}
+			if (!ret && bd >= 0) {
+				switch (list[ns].info.name_type) {
+				case MLX5_PHYS_PORT_NAME_TYPE_UPLINK:
+					if (np == 1) {
+						/*
+						 * Force standalone bonding
+						 * device for ROCE LAG
+						 * confgiurations.
+						 */
+						list[ns].info.master = 0;
+						list[ns].info.representor = 0;
+					}
+					if (list[ns].info.port_name == bd)
+						ns++;
+					break;
+				case MLX5_PHYS_PORT_NAME_TYPE_PFHPF:
+					/* Fallthrough */
+				case MLX5_PHYS_PORT_NAME_TYPE_PFVF:
+					/* Fallthrough */
+				case MLX5_PHYS_PORT_NAME_TYPE_PFSF:
+					if (list[ns].info.pf_num == bd)
+						ns++;
+					break;
+				default:
+					break;
+				}
+				continue;
+			}
+			if (!ret && (list[ns].info.representor ^
+				     list[ns].info.master))
+				ns++;
+		}
+		if (!ns) {
+			DRV_LOG(ERR,
+				"unable to recognize master/representors"
+				" on the IB device with multiple ports");
+			rte_errno = ENOENT;
+			ret = -rte_errno;
+			goto exit;
+		}
+	} else {
+		/*
+		 * The existence of several matching entries (nd > 1) means
+		 * port representors have been instantiated. No existing Verbs
+		 * call nor sysfs entries can tell them apart, this can only
+		 * be done through Netlink calls assuming kernel drivers are
+		 * recent enough to support them.
+		 *
+		 * In the event of identification failure through Netlink,
+		 * try again through sysfs, then:
+		 *
+		 * 1. A single IB device matches (nd == 1) with single
+		 *    port (np=0/1) and is not a representor, assume
+		 *    no switch support.
+		 *
+		 * 2. Otherwise no safe assumptions can be made;
+		 *    complain louder and bail out.
+		 */
+		for (i = 0; i != nd; ++i) {
+			memset(&list[ns].info, 0, sizeof(list[ns].info));
+			list[ns].bond_info = NULL;
+			list[ns].max_port = 1;
+			list[ns].phys_port = 1;
+			list[ns].phys_dev = ibv_match[i];
+			list[ns].eth_dev = NULL;
+			list[ns].pci_dev = pci_dev;
+			list[ns].pf_bond = -1;
+			list[ns].ifindex = 0;
+			if (nl_rdma >= 0)
+				list[ns].ifindex = mlx5_nl_ifindex
+				(nl_rdma,
+				mlx5_os_get_dev_device_name
+						(list[ns].phys_dev), 1);
+			if (!list[ns].ifindex) {
+				char ifname[IF_NAMESIZE];
+
+				/*
+				 * Netlink failed, it may happen with old
+				 * ib_core kernel driver (before 4.16).
+				 * We can assume there is old driver because
+				 * here we are processing single ports IB
+				 * devices. Let's try sysfs to retrieve
+				 * the ifindex. The method works for
+				 * master device only.
+				 */
+				if (nd > 1) {
+					/*
+					 * Multiple devices found, assume
+					 * representors, can not distinguish
+					 * master/representor and retrieve
+					 * ifindex via sysfs.
+					 */
+					continue;
+				}
+				ret = mlx5_get_ifname_sysfs
+					(ibv_match[i]->ibdev_path, ifname);
+				if (!ret)
+					list[ns].ifindex =
+						if_nametoindex(ifname);
+				if (!list[ns].ifindex) {
+					/*
+					 * No network interface index found
+					 * for the specified device, it means
+					 * there it is neither representor
+					 * nor master.
+					 */
+					continue;
+				}
+			}
+			ret = -1;
+			if (nl_route >= 0)
+				ret = mlx5_nl_switch_info
+					       (nl_route,
+						list[ns].ifindex,
+						&list[ns].info);
+			if (ret || (!list[ns].info.representor &&
+				    !list[ns].info.master)) {
+				/*
+				 * We failed to recognize representors with
+				 * Netlink, let's try to perform the task
+				 * with sysfs.
+				 */
+				ret =  mlx5_sysfs_switch_info
+						(list[ns].ifindex,
+						 &list[ns].info);
+			}
+			if (!ret && (list[ns].info.representor ^
+				     list[ns].info.master)) {
+				ns++;
+			} else if ((nd == 1) &&
+				   !list[ns].info.representor &&
+				   !list[ns].info.master) {
+				/*
+				 * Single IB device with
+				 * one physical port and
+				 * attached network device.
+				 * May be SRIOV is not enabled
+				 * or there is no representors.
+				 */
+				DRV_LOG(INFO, "no E-Switch support detected");
+				ns++;
+				break;
+			}
+		}
+		if (!ns) {
+			DRV_LOG(ERR,
+				"unable to recognize master/representors"
+				" on the multiple IB devices");
+			rte_errno = ENOENT;
+			ret = -rte_errno;
+			goto exit;
+		}
+		/*
+		 * New kernels may add the switch_id attribute for the case
+		 * there is no E-Switch and we wrongly recognized the
+		 * only device as master. Override this if there is the
+		 * single device with single port and new device name
+		 * format present.
+		 */
+		if (nd == 1 &&
+		    list[0].info.name_type == MLX5_PHYS_PORT_NAME_TYPE_UPLINK) {
+			list[0].info.master = 0;
+			list[0].info.representor = 0;
+		}
+	}
+	MLX5_ASSERT(ns);
+	/*
+	 * Sort list to probe devices in natural order for users convenience
+	 * (i.e. master first, then representors from lowest to highest ID).
+	 */
+	qsort(list, ns, sizeof(*list), mlx5_dev_spawn_data_cmp);
+	/* Device specific configuration. */
+	switch (pci_dev->id.device_id) {
+	case PCI_DEVICE_ID_MELLANOX_CONNECTX4VF:
+	case PCI_DEVICE_ID_MELLANOX_CONNECTX4LXVF:
+	case PCI_DEVICE_ID_MELLANOX_CONNECTX5VF:
+	case PCI_DEVICE_ID_MELLANOX_CONNECTX5EXVF:
+	case PCI_DEVICE_ID_MELLANOX_CONNECTX5BFVF:
+	case PCI_DEVICE_ID_MELLANOX_CONNECTX6VF:
+	case PCI_DEVICE_ID_MELLANOX_CONNECTXVF:
+		dev_config_vf = 1;
+		break;
+	default:
+		dev_config_vf = 0;
+		break;
+	}
+	if (eth_da.type != RTE_ETH_REPRESENTOR_NONE) {
+		/* Set devargs default values. */
+		if (eth_da.nb_mh_controllers == 0) {
+			eth_da.nb_mh_controllers = 1;
+			eth_da.mh_controllers[0] = 0;
+		}
+		if (eth_da.nb_ports == 0 && ns > 0) {
+			if (list[0].pf_bond >= 0 && list[0].info.representor)
+				DRV_LOG(WARNING, "Representor on Bonding device should use pf#vf# syntax: %s",
+					pci_dev->device.devargs->args);
+			eth_da.nb_ports = 1;
+			eth_da.ports[0] = list[0].info.pf_num;
+		}
+		if (eth_da.nb_representor_ports == 0) {
+			eth_da.nb_representor_ports = 1;
+			eth_da.representor_ports[0] = 0;
+		}
+	}
+	for (i = 0; i != ns; ++i) {
+		uint32_t restore;
+
+		/* Default configuration. */
+		mlx5_os_config_default(&dev_config);
+		dev_config.vf = dev_config_vf;
+		list[i].numa_node = pci_dev->device.numa_node;
+		list[i].eth_dev = mlx5_dev_spawn(&pci_dev->device,
+						 &list[i],
+						 &dev_config,
+						 &eth_da);
+		if (!list[i].eth_dev) {
+			if (rte_errno != EBUSY && rte_errno != EEXIST)
+				break;
+			/* Device is disabled or already spawned. Ignore it. */
+			continue;
+		}
+		restore = list[i].eth_dev->data->dev_flags;
+		rte_eth_copy_pci_info(list[i].eth_dev, pci_dev);
+		/**
+		 * Each representor has a dedicated interrupts vector.
+		 * rte_eth_copy_pci_info() assigns PF interrupts handle to
+		 * representor eth_dev object because representor and PF
+		 * share the same PCI address.
+		 * Override representor device with a dedicated
+		 * interrupts handle here.
+		 * Representor interrupts handle is released in mlx5_dev_stop().
+		 */
+		if (list[i].info.representor) {
+			struct rte_intr_handle *intr_handle;
+			intr_handle = mlx5_malloc(MLX5_MEM_SYS | MLX5_MEM_ZERO,
+						  sizeof(*intr_handle), 0,
+						  SOCKET_ID_ANY);
+			if (!intr_handle) {
+				DRV_LOG(ERR,
+					"port %u failed to allocate memory for interrupt handler "
+					"Rx interrupts will not be supported",
+					i);
+				rte_errno = ENOMEM;
+				ret = -rte_errno;
+				goto exit;
+			}
+			list[i].eth_dev->intr_handle = intr_handle;
+		}
+		/* Restore non-PCI flags cleared by the above call. */
+		list[i].eth_dev->data->dev_flags |= restore;
+		rte_eth_dev_probing_finish(list[i].eth_dev);
+	}
+	if (i != ns) {
+		DRV_LOG(ERR,
+			"probe of PCI device " PCI_PRI_FMT " aborted after"
+			" encountering an error: %s",
+			owner_pci.domain, owner_pci.bus,
+			owner_pci.devid, owner_pci.function,
+			strerror(rte_errno));
+		ret = -rte_errno;
+		/* Roll back. */
+		while (i--) {
+			if (!list[i].eth_dev)
+				continue;
+			mlx5_dev_close(list[i].eth_dev);
+			/* mac_addrs must not be freed because in dev_private */
+			list[i].eth_dev->data->mac_addrs = NULL;
+			claim_zero(rte_eth_dev_release_port(list[i].eth_dev));
+		}
+		/* Restore original error. */
+		rte_errno = -ret;
+	} else {
+		ret = 0;
+	}
+exit:
+	/*
+	 * Do the routine cleanup:
+	 * - close opened Netlink sockets
+	 * - free allocated spawn data array
+	 * - free the Infiniband device list
+	 */
+	if (nl_rdma >= 0)
+		close(nl_rdma);
+	if (nl_route >= 0)
+		close(nl_route);
+	if (list)
+		mlx5_free(list);
+	MLX5_ASSERT(ibv_list);
+	mlx5_glue->free_device_list(ibv_list);
+	return ret;
+}
+
+static int
+mlx5_os_parse_eth_devargs(struct rte_device *dev,
+			  struct rte_eth_devargs *eth_da)
+{
+	int ret = 0;
+
+	if (dev->devargs == NULL)
+		return 0;
+	memset(eth_da, 0, sizeof(*eth_da));
+	/* Parse representor information first from class argument. */
+	if (dev->devargs->cls_str)
+		ret = rte_eth_devargs_parse(dev->devargs->cls_str, eth_da);
+	if (ret != 0) {
+		DRV_LOG(ERR, "failed to parse device arguments: %s",
+			dev->devargs->cls_str);
+		return -rte_errno;
+	}
+	if (eth_da->type == RTE_ETH_REPRESENTOR_NONE) {
+		/* Parse legacy device argument */
+		ret = rte_eth_devargs_parse(dev->devargs->args, eth_da);
+		if (ret) {
+			DRV_LOG(ERR, "failed to parse device arguments: %s",
+				dev->devargs->args);
+			return -rte_errno;
+		}
+	}
+	return 0;
+}
+
+/**
+ * Callback to register a PCI device.
+ *
+ * This function spawns Ethernet devices out of a given PCI device.
+ *
+ * @param[in] pci_dev
+ *   PCI device information.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_os_pci_probe(struct rte_pci_device *pci_dev)
+{
+	struct rte_eth_devargs eth_da = { .nb_ports = 0 };
+	int ret = 0;
+	uint16_t p;
+
+	ret = mlx5_os_parse_eth_devargs(&pci_dev->device, &eth_da);
+	if (ret != 0)
+		return ret;
+
+	if (eth_da.nb_ports > 0) {
+		/* Iterate all port if devargs pf is range: "pf[0-1]vf[...]". */
+		for (p = 0; p < eth_da.nb_ports; p++) {
+			ret = mlx5_os_pci_probe_pf(pci_dev, &eth_da,
+						   eth_da.ports[p]);
+			if (ret)
+				break;
+		}
+		if (ret) {
+			DRV_LOG(ERR, "Probe of PCI device " PCI_PRI_FMT " "
+				"aborted due to proding failure of PF %u",
+				pci_dev->addr.domain, pci_dev->addr.bus,
+				pci_dev->addr.devid, pci_dev->addr.function,
+				eth_da.ports[p]);
+			mlx5_net_remove(&pci_dev->device);
+		}
+	} else {
+		ret = mlx5_os_pci_probe_pf(pci_dev, &eth_da, 0);
+	}
+	return ret;
+}
+
+/* Probe a single SF device on auxiliary bus, no representor support. */
+static int
+mlx5_os_auxiliary_probe(struct rte_device *dev)
+{
+	struct rte_eth_devargs eth_da = { .nb_ports = 0 };
+	struct mlx5_dev_config config;
+	struct mlx5_dev_spawn_data spawn = { .pf_bond = -1 };
+	struct rte_auxiliary_device *adev = RTE_DEV_TO_AUXILIARY(dev);
+	struct rte_eth_dev *eth_dev;
+	int ret = 0;
+
+	/* Parse ethdev devargs. */
+	ret = mlx5_os_parse_eth_devargs(dev, &eth_da);
+	if (ret != 0)
+		return ret;
+	/* Set default config data. */
+	mlx5_os_config_default(&config);
+	config.sf = 1;
+	/* Init spawn data. */
+	spawn.max_port = 1;
+	spawn.phys_port = 1;
+	spawn.phys_dev = mlx5_os_get_ibv_dev(dev);
+	if (spawn.phys_dev == NULL)
+		return -rte_errno;
+	ret = mlx5_auxiliary_get_ifindex(dev->name);
+	if (ret < 0) {
+		DRV_LOG(ERR, "failed to get ethdev ifindex: %s", dev->name);
+		return ret;
+	}
+	spawn.ifindex = ret;
+	spawn.numa_node = dev->numa_node;
+	/* Spawn device. */
+	eth_dev = mlx5_dev_spawn(dev, &spawn, &config, &eth_da);
+	if (eth_dev == NULL)
+		return -rte_errno;
+	/* Post create. */
+	eth_dev->intr_handle = &adev->intr_handle;
+	if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+		eth_dev->data->dev_flags |= RTE_ETH_DEV_INTR_LSC;
+		eth_dev->data->dev_flags |= RTE_ETH_DEV_INTR_RMV;
+		eth_dev->data->numa_node = dev->numa_node;
+	}
+	rte_eth_dev_probing_finish(eth_dev);
+	return 0;
+}
+
+/**
+ * Net class driver callback to probe a device.
+ *
+ * This function probe PCI bus device(s) or a single SF on auxiliary bus.
+ *
+ * @param[in] dev
+ *   Pointer to the generic device.
+ *
+ * @return
+ *   0 on success, the function cannot fail.
+ */
+int
+mlx5_os_net_probe(struct rte_device *dev)
+{
+	int ret;
+
+	if (rte_eal_process_type() == RTE_PROC_PRIMARY)
+		mlx5_pmd_socket_init();
+	ret = mlx5_init_once();
+	if (ret) {
+		DRV_LOG(ERR, "unable to init PMD global data: %s",
+			strerror(rte_errno));
+		return -rte_errno;
+	}
+	if (mlx5_dev_is_pci(dev))
+		return mlx5_os_pci_probe(RTE_DEV_TO_PCI(dev));
+	else
+		return mlx5_os_auxiliary_probe(dev);
+}
+
+static int
+mlx5_config_doorbell_mapping_env(const struct mlx5_dev_config *config)
+{
+	char *env;
+	int value;
+
+	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_PRIMARY);
+	/* Get environment variable to store. */
+	env = getenv(MLX5_SHUT_UP_BF);
+	value = env ? !!strcmp(env, "0") : MLX5_ARG_UNSET;
+	if (config->dbnc == MLX5_ARG_UNSET)
+		setenv(MLX5_SHUT_UP_BF, MLX5_SHUT_UP_BF_DEFAULT, 1);
+	else
+		setenv(MLX5_SHUT_UP_BF,
+		       config->dbnc == MLX5_TXDB_NCACHED ? "1" : "0", 1);
+	return value;
+}
+
+static void
+mlx5_restore_doorbell_mapping_env(int value)
+{
+	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_PRIMARY);
+	/* Restore the original environment variable state. */
+	if (value == MLX5_ARG_UNSET)
+		unsetenv(MLX5_SHUT_UP_BF);
+	else
+		setenv(MLX5_SHUT_UP_BF, value ? "1" : "0", 1);
+}
+
+/**
+ * Extract pdn of PD object using DV API.
+ *
+ * @param[in] pd
+ *   Pointer to the verbs PD object.
+ * @param[out] pdn
+ *   Pointer to the PD object number variable.
+ *
+ * @return
+ *   0 on success, error value otherwise.
+ */
+int
+mlx5_os_get_pdn(void *pd, uint32_t *pdn)
+{
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+	struct mlx5dv_obj obj;
+	struct mlx5dv_pd pd_info;
+	int ret = 0;
+
+	obj.pd.in = pd;
+	obj.pd.out = &pd_info;
+	ret = mlx5_glue->dv_init_obj(&obj, MLX5DV_OBJ_PD);
+	if (ret) {
+		DRV_LOG(DEBUG, "Fail to get PD object info");
+		return ret;
+	}
+	*pdn = pd_info.pdn;
+	return 0;
+#else
+	(void)pd;
+	(void)pdn;
+	return -ENOTSUP;
+#endif /* HAVE_IBV_FLOW_DV_SUPPORT */
+}
+
+/**
+ * Function API to open IB device.
+ *
+ * This function calls the Linux glue APIs to open a device.
+ *
+ * @param[in] spawn
+ *   Pointer to the IB device attributes (name, port, etc).
+ * @param[out] config
+ *   Pointer to device configuration structure.
+ * @param[out] sh
+ *   Pointer to shared context structure.
+ *
+ * @return
+ *   0 on success, a positive error value otherwise.
+ */
+int
+mlx5_os_open_device(const struct mlx5_dev_spawn_data *spawn,
+		     const struct mlx5_dev_config *config,
+		     struct mlx5_dev_ctx_shared *sh)
+{
+	int dbmap_env;
+	int err = 0;
+
+	pthread_mutex_init(&sh->txpp.mutex, NULL);
+	/*
+	 * Configure environment variable "MLX5_BF_SHUT_UP"
+	 * before the device creation. The rdma_core library
+	 * checks the variable at device creation and
+	 * stores the result internally.
+	 */
+	dbmap_env = mlx5_config_doorbell_mapping_env(config);
+	/* Try to open IB device with DV first, then usual Verbs. */
+	errno = 0;
+	sh->ctx = mlx5_glue->dv_open_device(spawn->phys_dev);
+	if (sh->ctx) {
+		sh->devx = 1;
+		DRV_LOG(DEBUG, "DevX is supported");
+		/* The device is created, no need for environment. */
+		mlx5_restore_doorbell_mapping_env(dbmap_env);
+	} else {
+		/* The environment variable is still configured. */
+		sh->ctx = mlx5_glue->open_device(spawn->phys_dev);
+		err = errno ? errno : ENODEV;
+		/*
+		 * The environment variable is not needed anymore,
+		 * all device creation attempts are completed.
+		 */
+		mlx5_restore_doorbell_mapping_env(dbmap_env);
+		if (!sh->ctx)
+			return err;
+		DRV_LOG(DEBUG, "DevX is NOT supported");
+		err = 0;
+	}
+	if (!err && sh->ctx) {
+		/* Hint libmlx5 to use PMD allocator for data plane resources */
+		mlx5_glue->dv_set_context_attr(sh->ctx,
+			MLX5DV_CTX_ATTR_BUF_ALLOCATORS,
+			(void *)((uintptr_t)&(struct mlx5dv_ctx_allocators){
+				.alloc = &mlx5_alloc_verbs_buf,
+				.free = &mlx5_free_verbs_buf,
+				.data = sh,
+			}));
+	}
+	return err;
+}
+
+/**
+ * Install shared asynchronous device events handler.
+ * This function is implemented to support event sharing
+ * between multiple ports of single IB device.
+ *
+ * @param sh
+ *   Pointer to mlx5_dev_ctx_shared object.
+ */
+void
+mlx5_os_dev_shared_handler_install(struct mlx5_dev_ctx_shared *sh)
+{
+	int ret;
+	int flags;
+
+	sh->intr_handle.fd = -1;
+	flags = fcntl(((struct ibv_context *)sh->ctx)->async_fd, F_GETFL);
+	ret = fcntl(((struct ibv_context *)sh->ctx)->async_fd,
+		    F_SETFL, flags | O_NONBLOCK);
+	if (ret) {
+		DRV_LOG(INFO, "failed to change file descriptor async event"
+			" queue");
+	} else {
+		sh->intr_handle.fd = ((struct ibv_context *)sh->ctx)->async_fd;
+		sh->intr_handle.type = RTE_INTR_HANDLE_EXT;
+		if (rte_intr_callback_register(&sh->intr_handle,
+					mlx5_dev_interrupt_handler, sh)) {
+			DRV_LOG(INFO, "Fail to install the shared interrupt.");
+			sh->intr_handle.fd = -1;
+		}
+	}
+	if (sh->devx) {
+#ifdef HAVE_IBV_DEVX_ASYNC
+		sh->intr_handle_devx.fd = -1;
+		sh->devx_comp =
+			(void *)mlx5_glue->devx_create_cmd_comp(sh->ctx);
+		struct mlx5dv_devx_cmd_comp *devx_comp = sh->devx_comp;
+		if (!devx_comp) {
+			DRV_LOG(INFO, "failed to allocate devx_comp.");
+			return;
+		}
+		flags = fcntl(devx_comp->fd, F_GETFL);
+		ret = fcntl(devx_comp->fd, F_SETFL, flags | O_NONBLOCK);
+		if (ret) {
+			DRV_LOG(INFO, "failed to change file descriptor"
+				" devx comp");
+			return;
+		}
+		sh->intr_handle_devx.fd = devx_comp->fd;
+		sh->intr_handle_devx.type = RTE_INTR_HANDLE_EXT;
+		if (rte_intr_callback_register(&sh->intr_handle_devx,
+					mlx5_dev_interrupt_handler_devx, sh)) {
+			DRV_LOG(INFO, "Fail to install the devx shared"
+				" interrupt.");
+			sh->intr_handle_devx.fd = -1;
+		}
+#endif /* HAVE_IBV_DEVX_ASYNC */
+	}
+}
+
+/**
+ * Uninstall shared asynchronous device events handler.
+ * This function is implemented to support event sharing
+ * between multiple ports of single IB device.
+ *
+ * @param dev
+ *   Pointer to mlx5_dev_ctx_shared object.
+ */
+void
+mlx5_os_dev_shared_handler_uninstall(struct mlx5_dev_ctx_shared *sh)
+{
+	if (sh->intr_handle.fd >= 0)
+		mlx5_intr_callback_unregister(&sh->intr_handle,
+					      mlx5_dev_interrupt_handler, sh);
+#ifdef HAVE_IBV_DEVX_ASYNC
+	if (sh->intr_handle_devx.fd >= 0)
+		rte_intr_callback_unregister(&sh->intr_handle_devx,
+				  mlx5_dev_interrupt_handler_devx, sh);
+	if (sh->devx_comp)
+		mlx5_glue->devx_destroy_cmd_comp(sh->devx_comp);
+#endif
+}
+
+/**
+ * Read statistics by a named counter.
+ *
+ * @param[in] priv
+ *   Pointer to the private device data structure.
+ * @param[in] ctr_name
+ *   Pointer to the name of the statistic counter to read
+ * @param[out] stat
+ *   Pointer to read statistic value.
+ * @return
+ *   0 on success and stat is valud, 1 if failed to read the value
+ *   rte_errno is set.
+ *
+ */
+int
+mlx5_os_read_dev_stat(struct mlx5_priv *priv, const char *ctr_name,
+		      uint64_t *stat)
+{
+	int fd;
+
+	if (priv->sh) {
+		if (priv->q_counters != NULL &&
+		    strcmp(ctr_name, "out_of_buffer") == 0)
+			return mlx5_devx_cmd_queue_counter_query
+					(priv->q_counters, 0, (uint32_t *)stat);
+		MKSTR(path, "%s/ports/%d/hw_counters/%s",
+		      priv->sh->ibdev_path,
+		      priv->dev_port,
+		      ctr_name);
+		fd = open(path, O_RDONLY);
+		/*
+		 * in switchdev the file location is not per port
+		 * but rather in <ibdev_path>/hw_counters/<file_name>.
+		 */
+		if (fd == -1) {
+			MKSTR(path1, "%s/hw_counters/%s",
+			      priv->sh->ibdev_path,
+			      ctr_name);
+			fd = open(path1, O_RDONLY);
+		}
+		if (fd != -1) {
+			char buf[21] = {'\0'};
+			ssize_t n = read(fd, buf, sizeof(buf));
+
+			close(fd);
+			if (n != -1) {
+				*stat = strtoull(buf, NULL, 10);
+				return 0;
+			}
+		}
+	}
+	*stat = 0;
+	return 1;
+}
+
+/**
+ * Set the reg_mr and dereg_mr call backs
+ *
+ * @param reg_mr_cb[out]
+ *   Pointer to reg_mr func
+ * @param dereg_mr_cb[out]
+ *   Pointer to dereg_mr func
+ *
+ */
+void
+mlx5_os_set_reg_mr_cb(mlx5_reg_mr_t *reg_mr_cb,
+		      mlx5_dereg_mr_t *dereg_mr_cb)
+{
+	*reg_mr_cb = mlx5_mr_verbs_ops.reg_mr;
+	*dereg_mr_cb = mlx5_mr_verbs_ops.dereg_mr;
+}
+
+/**
+ * Remove a MAC address from device
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param index
+ *   MAC address index.
+ */
+void
+mlx5_os_mac_addr_remove(struct rte_eth_dev *dev, uint32_t index)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	const int vf = priv->config.vf;
+
+	if (vf)
+		mlx5_nl_mac_addr_remove(priv->nl_socket_route,
+					mlx5_ifindex(dev), priv->mac_own,
+					&dev->data->mac_addrs[index], index);
+}
+
+/**
+ * Adds a MAC address to the device
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param mac_addr
+ *   MAC address to register.
+ * @param index
+ *   MAC address index.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise
+ */
+int
+mlx5_os_mac_addr_add(struct rte_eth_dev *dev, struct rte_ether_addr *mac,
+		     uint32_t index)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	const int vf = priv->config.vf;
+	int ret = 0;
+
+	if (vf)
+		ret = mlx5_nl_mac_addr_add(priv->nl_socket_route,
+					   mlx5_ifindex(dev), priv->mac_own,
+					   mac, index);
+	return ret;
+}
+
+/**
+ * Modify a VF MAC address
+ *
+ * @param priv
+ *   Pointer to device private data.
+ * @param mac_addr
+ *   MAC address to modify into.
+ * @param iface_idx
+ *   Net device interface index
+ * @param vf_index
+ *   VF index
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise
+ */
+int
+mlx5_os_vf_mac_addr_modify(struct mlx5_priv *priv,
+			   unsigned int iface_idx,
+			   struct rte_ether_addr *mac_addr,
+			   int vf_index)
+{
+	return mlx5_nl_vf_mac_addr_modify
+		(priv->nl_socket_route, iface_idx, mac_addr, vf_index);
+}
+
+/**
+ * Set device promiscuous mode
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param enable
+ *   0 - promiscuous is disabled, otherwise - enabled
+ *
+ * @return
+ *   0 on success, a negative error value otherwise
+ */
+int
+mlx5_os_set_promisc(struct rte_eth_dev *dev, int enable)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+
+	return mlx5_nl_promisc(priv->nl_socket_route,
+			       mlx5_ifindex(dev), !!enable);
+}
+
+/**
+ * Set device promiscuous mode
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param enable
+ *   0 - all multicase is disabled, otherwise - enabled
+ *
+ * @return
+ *   0 on success, a negative error value otherwise
+ */
+int
+mlx5_os_set_allmulti(struct rte_eth_dev *dev, int enable)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+
+	return mlx5_nl_allmulti(priv->nl_socket_route,
+				mlx5_ifindex(dev), !!enable);
+}
+
+/**
+ * Flush device MAC addresses
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ *
+ */
+void
+mlx5_os_mac_addr_flush(struct rte_eth_dev *dev)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+
+	mlx5_nl_mac_addr_flush(priv->nl_socket_route, mlx5_ifindex(dev),
+			       dev->data->mac_addrs,
+			       MLX5_MAX_MAC_ADDRESSES, priv->mac_own);
+}
diff --git a/drivers/net/mlx5/freebsd/mlx5_os.h b/drivers/net/mlx5/freebsd/mlx5_os.h
new file mode 100644
index 0000000000..2991d37df2
--- /dev/null
+++ b/drivers/net/mlx5/freebsd/mlx5_os.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2015 6WIND S.A.
+ * Copyright 2020 Mellanox Technologies, Ltd
+ */
+
+#ifndef RTE_PMD_MLX5_OS_H_
+#define RTE_PMD_MLX5_OS_H_
+
+#include <net/if.h>
+
+/* verb enumerations translations to local enums. */
+enum {
+	MLX5_FS_NAME_MAX = IBV_SYSFS_NAME_MAX + 1,
+	MLX5_FS_PATH_MAX = IBV_SYSFS_PATH_MAX + 1
+};
+
+/* Maximal data of sendmsg message(in bytes). */
+#define MLX5_SENDMSG_MAX 64
+
+#define MLX5_NAMESIZE IF_NAMESIZE
+
+int mlx5_auxiliary_get_ifindex(const char *sf_name);
+
+#endif /* RTE_PMD_MLX5_OS_H_ */
diff --git a/drivers/net/mlx5/freebsd/mlx5_socket.c b/drivers/net/mlx5/freebsd/mlx5_socket.c
new file mode 100644
index 0000000000..6356b66dc4
--- /dev/null
+++ b/drivers/net/mlx5/freebsd/mlx5_socket.c
@@ -0,0 +1,249 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2019 Mellanox Technologies, Ltd
+ */
+
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE
+#endif
+
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/stat.h>
+
+#include "rte_eal.h"
+#include "mlx5_utils.h"
+#include "mlx5.h"
+
+/* PMD socket service for tools. */
+
+#define MLX5_SOCKET_PATH "/var/tmp/dpdk_net_mlx5_%d"
+
+int server_socket; /* Unix socket for primary process. */
+struct rte_intr_handle server_intr_handle; /* Interrupt handler. */
+
+/**
+ * Handle server pmd socket interrupts.
+ */
+static void
+mlx5_pmd_socket_handle(void *cb __rte_unused)
+{
+	int conn_sock;
+	int ret;
+	struct cmsghdr *cmsg = NULL;
+	uint32_t data[MLX5_SENDMSG_MAX / sizeof(uint32_t)];
+	uint64_t flow_ptr = 0;
+	uint8_t  buf[CMSG_SPACE(sizeof(int))] = { 0 };
+	struct iovec io = {
+		.iov_base = data,
+		.iov_len = sizeof(data),
+	};
+	struct msghdr msg = {
+		.msg_iov = &io,
+		.msg_iovlen = 1,
+		.msg_control = buf,
+		.msg_controllen = sizeof(buf),
+	};
+
+	uint32_t port_id;
+	int fd;
+	FILE *file = NULL;
+	struct rte_eth_dev *dev;
+	struct rte_flow_error err;
+	struct mlx5_flow_dump_req  *dump_req;
+	struct mlx5_flow_dump_ack  *dump_ack;
+
+	memset(data, 0, sizeof(data));
+	/* Accept the connection from the client. */
+	conn_sock = accept(server_socket, NULL, NULL);
+	if (conn_sock < 0) {
+		DRV_LOG(WARNING, "connection failed: %s", strerror(errno));
+		return;
+	}
+	ret = recvmsg(conn_sock, &msg, MSG_WAITALL);
+	if (ret != sizeof(struct mlx5_flow_dump_req)) {
+		DRV_LOG(WARNING, "wrong message received: %s",
+			strerror(errno));
+		goto error;
+	}
+
+	/* Receive file descriptor. */
+	cmsg = CMSG_FIRSTHDR(&msg);
+	if (cmsg == NULL || cmsg->cmsg_type != SCM_RIGHTS ||
+	    cmsg->cmsg_len < sizeof(int)) {
+		DRV_LOG(WARNING, "invalid file descriptor message");
+		goto error;
+	}
+	memcpy(&fd, CMSG_DATA(cmsg), sizeof(fd));
+	file = fdopen(fd, "w");
+	if (!file) {
+		DRV_LOG(WARNING, "Failed to open file");
+		goto error;
+	}
+	/* Receive port number. */
+	if (msg.msg_iovlen != 1 || msg.msg_iov->iov_len < sizeof(uint16_t)) {
+		DRV_LOG(WARNING, "wrong port number message");
+		goto error;
+	}
+
+	dump_req = (struct mlx5_flow_dump_req *)msg.msg_iov->iov_base;
+	if (dump_req) {
+		port_id = dump_req->port_id;
+		flow_ptr = dump_req->flow_id;
+	} else {
+		DRV_LOG(WARNING, "Invalid message");
+		goto error;
+	}
+
+	if (!rte_eth_dev_is_valid_port(port_id)) {
+		DRV_LOG(WARNING, "Invalid port %u", port_id);
+		goto error;
+	}
+
+	/* Dump flow. */
+	dev = &rte_eth_devices[port_id];
+	if (flow_ptr == 0)
+		ret = mlx5_flow_dev_dump(dev, NULL, file, NULL);
+	else
+		ret = mlx5_flow_dev_dump(dev,
+			(struct rte_flow *)((uintptr_t)flow_ptr), file, &err);
+
+	/* Set-up the ancillary data and reply. */
+	msg.msg_controllen = 0;
+	msg.msg_control = NULL;
+	msg.msg_iovlen = 1;
+	msg.msg_iov = &io;
+	dump_ack = (struct mlx5_flow_dump_ack *)data;
+	dump_ack->rc = -ret;
+	io.iov_len = sizeof(struct mlx5_flow_dump_ack);
+	io.iov_base = dump_ack;
+	do {
+		ret = sendmsg(conn_sock, &msg, 0);
+	} while (ret < 0 && errno == EINTR);
+	if (ret < 0)
+		DRV_LOG(WARNING, "failed to send response %s",
+			strerror(errno));
+error:
+	if (conn_sock >= 0)
+		close(conn_sock);
+	if (file)
+		fclose(file);
+}
+
+/**
+ * Install interrupt handler.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ * @return
+ *   0 on success, a negative errno value otherwise.
+ */
+static int
+mlx5_pmd_interrupt_handler_install(void)
+{
+	MLX5_ASSERT(server_socket);
+	server_intr_handle.fd = server_socket;
+	server_intr_handle.type = RTE_INTR_HANDLE_EXT;
+	return rte_intr_callback_register(&server_intr_handle,
+					  mlx5_pmd_socket_handle, NULL);
+}
+
+/**
+ * Uninstall interrupt handler.
+ */
+static void
+mlx5_pmd_interrupt_handler_uninstall(void)
+{
+	if (server_socket) {
+		mlx5_intr_callback_unregister(&server_intr_handle,
+					      mlx5_pmd_socket_handle,
+					      NULL);
+	}
+	server_intr_handle.fd = 0;
+	server_intr_handle.type = RTE_INTR_HANDLE_UNKNOWN;
+}
+
+/**
+ * Initialise the socket to communicate with the secondary process
+ *
+ * @param[in] dev
+ *   Pointer to Ethernet device.
+ *
+ * @return
+ *   0 on success, a negative value otherwise.
+ */
+int
+mlx5_pmd_socket_init(void)
+{
+	struct sockaddr_un sun = {
+		.sun_family = AF_UNIX,
+	};
+	int ret;
+	int flags;
+
+	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_PRIMARY);
+	if (server_socket)
+		return 0;
+	/*
+	 * Initialize the socket to communicate with the secondary
+	 * process.
+	 */
+	ret = socket(AF_UNIX, SOCK_STREAM, 0);
+	if (ret < 0) {
+		DRV_LOG(WARNING, "Failed to open mlx5 socket: %s",
+			strerror(errno));
+		goto error;
+	}
+	server_socket = ret;
+	flags = fcntl(server_socket, F_GETFL, 0);
+	if (flags == -1)
+		goto error;
+	ret = fcntl(server_socket, F_SETFL, flags | O_NONBLOCK);
+	if (ret < 0)
+		goto error;
+	snprintf(sun.sun_path, sizeof(sun.sun_path), MLX5_SOCKET_PATH,
+		 getpid());
+	remove(sun.sun_path);
+	ret = bind(server_socket, (const struct sockaddr *)&sun, sizeof(sun));
+	if (ret < 0) {
+		DRV_LOG(WARNING,
+			"cannot bind mlx5 socket: %s", strerror(errno));
+		goto close;
+	}
+	ret = listen(server_socket, 0);
+	if (ret < 0) {
+		DRV_LOG(WARNING, "cannot listen on mlx5 socket: %s",
+			strerror(errno));
+		goto close;
+	}
+	if (mlx5_pmd_interrupt_handler_install()) {
+		DRV_LOG(WARNING, "cannot register interrupt handler for mlx5 socket: %s",
+			strerror(errno));
+		goto close;
+	}
+	return 0;
+close:
+	remove(sun.sun_path);
+error:
+	claim_zero(close(server_socket));
+	server_socket = 0;
+	DRV_LOG(ERR, "Cannot initialize socket: %s", strerror(errno));
+	return -errno;
+}
+
+/**
+ * Un-Initialize the pmd socket
+ */
+RTE_FINI(mlx5_pmd_socket_uninit)
+{
+	if (!server_socket)
+		return;
+	mlx5_pmd_interrupt_handler_uninstall();
+	claim_zero(close(server_socket));
+	server_socket = 0;
+	MKSTR(path, MLX5_SOCKET_PATH, getpid());
+	claim_zero(remove(path));
+}
diff --git a/drivers/net/mlx5/freebsd/mlx5_verbs.c b/drivers/net/mlx5/freebsd/mlx5_verbs.c
new file mode 100644
index 0000000000..d4fa202ac4
--- /dev/null
+++ b/drivers/net/mlx5/freebsd/mlx5_verbs.c
@@ -0,0 +1,1208 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2020 Mellanox Technologies, Ltd
+ */
+
+#include <stddef.h>
+#include <errno.h>
+#include <string.h>
+#include <stdint.h>
+#include <unistd.h>
+#include <inttypes.h>
+#include <sys/queue.h>
+
+#include "mlx5_autoconf.h"
+
+#include <rte_mbuf.h>
+#include <rte_malloc.h>
+#include <ethdev_driver.h>
+#include <rte_common.h>
+
+#include <mlx5_glue.h>
+#include <mlx5_common.h>
+#include <mlx5_common_mr.h>
+#include <mlx5_verbs.h>
+#include <mlx5_rx.h>
+#include <mlx5_tx.h>
+#include <mlx5_utils.h>
+#include <mlx5_malloc.h>
+
+/**
+ * Register mr. Given protection domain pointer, pointer to addr and length
+ * register the memory region.
+ *
+ * @param[in] pd
+ *   Pointer to protection domain context.
+ * @param[in] addr
+ *   Pointer to memory start address.
+ * @param[in] length
+ *   Length of the memory to register.
+ * @param[out] pmd_mr
+ *   pmd_mr struct set with lkey, address, length and pointer to mr object
+ *
+ * @return
+ *   0 on successful registration, -1 otherwise
+ */
+static int
+mlx5_reg_mr(void *pd, void *addr, size_t length,
+		 struct mlx5_pmd_mr *pmd_mr)
+{
+	return mlx5_common_verbs_reg_mr(pd, addr, length, pmd_mr);
+}
+
+/**
+ * Deregister mr. Given the mlx5 pmd MR - deregister the MR
+ *
+ * @param[in] pmd_mr
+ *   pmd_mr struct set with lkey, address, length and pointer to mr object
+ *
+ */
+static void
+mlx5_dereg_mr(struct mlx5_pmd_mr *pmd_mr)
+{
+	mlx5_common_verbs_dereg_mr(pmd_mr);
+}
+
+/* verbs operations. */
+const struct mlx5_mr_ops mlx5_mr_verbs_ops = {
+	.reg_mr = mlx5_reg_mr,
+	.dereg_mr = mlx5_dereg_mr,
+};
+
+/**
+ * Modify Rx WQ vlan stripping offload
+ *
+ * @param rxq_obj
+ *   Rx queue object.
+ *
+ * @return 0 on success, non-0 otherwise
+ */
+static int
+mlx5_rxq_obj_modify_wq_vlan_strip(struct mlx5_rxq_obj *rxq_obj, int on)
+{
+	uint16_t vlan_offloads =
+		(on ? IBV_WQ_FLAGS_CVLAN_STRIPPING : 0) |
+		0;
+	struct ibv_wq_attr mod;
+	mod = (struct ibv_wq_attr){
+		.attr_mask = IBV_WQ_ATTR_FLAGS,
+		.flags_mask = IBV_WQ_FLAGS_CVLAN_STRIPPING,
+		.flags = vlan_offloads,
+	};
+
+	return mlx5_glue->modify_wq(rxq_obj->wq, &mod);
+}
+
+/**
+ * Modifies the attributes for the specified WQ.
+ *
+ * @param rxq_obj
+ *   Verbs Rx queue object.
+ * @param type
+ *   Type of change queue state.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_ibv_modify_wq(struct mlx5_rxq_obj *rxq_obj, uint8_t type)
+{
+	struct ibv_wq_attr mod = {
+		.attr_mask = IBV_WQ_ATTR_STATE,
+		.wq_state = (enum ibv_wq_state)type,
+	};
+
+	return mlx5_glue->modify_wq(rxq_obj->wq, &mod);
+}
+
+/**
+ * Modify QP using Verbs API.
+ *
+ * @param txq_obj
+ *   Verbs Tx queue object.
+ * @param type
+ *   Type of change queue state.
+ * @param dev_port
+ *   IB device port number.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_ibv_modify_qp(struct mlx5_txq_obj *obj, enum mlx5_txq_modify_type type,
+		   uint8_t dev_port)
+{
+	struct ibv_qp_attr mod = {
+		.qp_state = IBV_QPS_RESET,
+		.port_num = dev_port,
+	};
+	int attr_mask = (IBV_QP_STATE | IBV_QP_PORT);
+	int ret;
+
+	if (type != MLX5_TXQ_MOD_RST2RDY) {
+		ret = mlx5_glue->modify_qp(obj->qp, &mod, IBV_QP_STATE);
+		if (ret) {
+			DRV_LOG(ERR, "Cannot change Tx QP state to RESET %s",
+				strerror(errno));
+			rte_errno = errno;
+			return ret;
+		}
+		if (type == MLX5_TXQ_MOD_RDY2RST)
+			return 0;
+	}
+	if (type == MLX5_TXQ_MOD_ERR2RDY)
+		attr_mask = IBV_QP_STATE;
+	mod.qp_state = IBV_QPS_INIT;
+	ret = mlx5_glue->modify_qp(obj->qp, &mod, attr_mask);
+	if (ret) {
+		DRV_LOG(ERR, "Cannot change Tx QP state to INIT %s",
+			strerror(errno));
+		rte_errno = errno;
+		return ret;
+	}
+	mod.qp_state = IBV_QPS_RTR;
+	ret = mlx5_glue->modify_qp(obj->qp, &mod, IBV_QP_STATE);
+	if (ret) {
+		DRV_LOG(ERR, "Cannot change Tx QP state to RTR %s",
+			strerror(errno));
+		rte_errno = errno;
+		return ret;
+	}
+	mod.qp_state = IBV_QPS_RTS;
+	ret = mlx5_glue->modify_qp(obj->qp, &mod, IBV_QP_STATE);
+	if (ret) {
+		DRV_LOG(ERR, "Cannot change Tx QP state to RTS %s",
+			strerror(errno));
+		rte_errno = errno;
+		return ret;
+	}
+	return 0;
+}
+
+/**
+ * Create a CQ Verbs object.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ * @param idx
+ *   Queue index in DPDK Rx queue array.
+ *
+ * @return
+ *   The Verbs CQ object initialized, NULL otherwise and rte_errno is set.
+ */
+static struct ibv_cq *
+mlx5_rxq_ibv_cq_create(struct rte_eth_dev *dev, uint16_t idx)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_rxq_data *rxq_data = (*priv->rxqs)[idx];
+	struct mlx5_rxq_ctrl *rxq_ctrl =
+		container_of(rxq_data, struct mlx5_rxq_ctrl, rxq);
+	struct mlx5_rxq_obj *rxq_obj = rxq_ctrl->obj;
+	unsigned int cqe_n = mlx5_rxq_cqe_num(rxq_data);
+	struct {
+		struct ibv_cq_init_attr_ex ibv;
+		struct mlx5dv_cq_init_attr mlx5;
+	} cq_attr;
+
+	cq_attr.ibv = (struct ibv_cq_init_attr_ex){
+		.cqe = cqe_n,
+		.channel = rxq_obj->ibv_channel,
+		.comp_mask = 0,
+	};
+	cq_attr.mlx5 = (struct mlx5dv_cq_init_attr){
+		.comp_mask = 0,
+	};
+	if (priv->config.cqe_comp && !rxq_data->hw_timestamp) {
+		cq_attr.mlx5.comp_mask |=
+				MLX5DV_CQ_INIT_ATTR_MASK_COMPRESSED_CQE;
+		rxq_data->byte_mask = UINT32_MAX;
+#ifdef HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT
+		if (mlx5_rxq_mprq_enabled(rxq_data)) {
+			cq_attr.mlx5.cqe_comp_res_format =
+					MLX5DV_CQE_RES_FORMAT_CSUM_STRIDX;
+			rxq_data->mcqe_format =
+					MLX5_CQE_RESP_FORMAT_CSUM_STRIDX;
+		} else {
+			cq_attr.mlx5.cqe_comp_res_format =
+					MLX5DV_CQE_RES_FORMAT_HASH;
+			rxq_data->mcqe_format =
+					MLX5_CQE_RESP_FORMAT_HASH;
+		}
+#else
+		cq_attr.mlx5.cqe_comp_res_format = MLX5DV_CQE_RES_FORMAT_HASH;
+		rxq_data->mcqe_format = MLX5_CQE_RESP_FORMAT_HASH;
+#endif
+		/*
+		 * For vectorized Rx, it must not be doubled in order to
+		 * make cq_ci and rq_ci aligned.
+		 */
+		if (mlx5_rxq_check_vec_support(rxq_data) < 0)
+			cq_attr.ibv.cqe *= 2;
+	} else if (priv->config.cqe_comp && rxq_data->hw_timestamp) {
+		DRV_LOG(DEBUG,
+			"Port %u Rx CQE compression is disabled for HW"
+			" timestamp.",
+			dev->data->port_id);
+	}
+#ifdef HAVE_IBV_MLX5_MOD_CQE_128B_PAD
+	if (RTE_CACHE_LINE_SIZE == 128) {
+		cq_attr.mlx5.comp_mask |= MLX5DV_CQ_INIT_ATTR_MASK_FLAGS;
+		cq_attr.mlx5.flags |= MLX5DV_CQ_INIT_ATTR_FLAGS_CQE_PAD;
+	}
+#endif
+	return mlx5_glue->cq_ex_to_cq(mlx5_glue->dv_create_cq(priv->sh->ctx,
+							      &cq_attr.ibv,
+							      &cq_attr.mlx5));
+}
+
+/**
+ * Create a WQ Verbs object.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ * @param idx
+ *   Queue index in DPDK Rx queue array.
+ *
+ * @return
+ *   The Verbs WQ object initialized, NULL otherwise and rte_errno is set.
+ */
+static struct ibv_wq *
+mlx5_rxq_ibv_wq_create(struct rte_eth_dev *dev, uint16_t idx)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_rxq_data *rxq_data = (*priv->rxqs)[idx];
+	struct mlx5_rxq_ctrl *rxq_ctrl =
+		container_of(rxq_data, struct mlx5_rxq_ctrl, rxq);
+	struct mlx5_rxq_obj *rxq_obj = rxq_ctrl->obj;
+	unsigned int wqe_n = 1 << rxq_data->elts_n;
+	struct {
+		struct ibv_wq_init_attr ibv;
+#ifdef HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT
+		struct mlx5dv_wq_init_attr mlx5;
+#endif
+	} wq_attr;
+
+	wq_attr.ibv = (struct ibv_wq_init_attr){
+		.wq_context = NULL, /* Could be useful in the future. */
+		.wq_type = IBV_WQT_RQ,
+		/* Max number of outstanding WRs. */
+		.max_wr = wqe_n >> rxq_data->sges_n,
+		/* Max number of scatter/gather elements in a WR. */
+		.max_sge = 1 << rxq_data->sges_n,
+		.pd = priv->sh->pd,
+		.cq = rxq_obj->ibv_cq,
+		.comp_mask = IBV_WQ_FLAGS_CVLAN_STRIPPING | 0,
+		.create_flags = (rxq_data->vlan_strip ?
+				 IBV_WQ_FLAGS_CVLAN_STRIPPING : 0),
+	};
+	/* By default, FCS (CRC) is stripped by hardware. */
+	if (rxq_data->crc_present) {
+		wq_attr.ibv.create_flags |= IBV_WQ_FLAGS_SCATTER_FCS;
+		wq_attr.ibv.comp_mask |= IBV_WQ_INIT_ATTR_FLAGS;
+	}
+	if (priv->config.hw_padding) {
+#if defined(HAVE_IBV_WQ_FLAG_RX_END_PADDING)
+		wq_attr.ibv.create_flags |= IBV_WQ_FLAG_RX_END_PADDING;
+		wq_attr.ibv.comp_mask |= IBV_WQ_INIT_ATTR_FLAGS;
+#elif defined(HAVE_IBV_WQ_FLAGS_PCI_WRITE_END_PADDING)
+		wq_attr.ibv.create_flags |= IBV_WQ_FLAGS_PCI_WRITE_END_PADDING;
+		wq_attr.ibv.comp_mask |= IBV_WQ_INIT_ATTR_FLAGS;
+#endif
+	}
+#ifdef HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT
+	wq_attr.mlx5 = (struct mlx5dv_wq_init_attr){
+		.comp_mask = 0,
+	};
+	if (mlx5_rxq_mprq_enabled(rxq_data)) {
+		struct mlx5dv_striding_rq_init_attr *mprq_attr =
+						&wq_attr.mlx5.striding_rq_attrs;
+
+		wq_attr.mlx5.comp_mask |= MLX5DV_WQ_INIT_ATTR_MASK_STRIDING_RQ;
+		*mprq_attr = (struct mlx5dv_striding_rq_init_attr){
+			.single_stride_log_num_of_bytes = rxq_data->strd_sz_n,
+			.single_wqe_log_num_of_strides = rxq_data->strd_num_n,
+			.two_byte_shift_en = MLX5_MPRQ_TWO_BYTE_SHIFT,
+		};
+	}
+	rxq_obj->wq = mlx5_glue->dv_create_wq(priv->sh->ctx, &wq_attr.ibv,
+					      &wq_attr.mlx5);
+#else
+	rxq_obj->wq = mlx5_glue->create_wq(priv->sh->ctx, &wq_attr.ibv);
+#endif
+	if (rxq_obj->wq) {
+		/*
+		 * Make sure number of WRs*SGEs match expectations since a queue
+		 * cannot allocate more than "desc" buffers.
+		 */
+		if (wq_attr.ibv.max_wr != (wqe_n >> rxq_data->sges_n) ||
+		    wq_attr.ibv.max_sge != (1u << rxq_data->sges_n)) {
+			DRV_LOG(ERR,
+				"Port %u Rx queue %u requested %u*%u but got"
+				" %u*%u WRs*SGEs.",
+				dev->data->port_id, idx,
+				wqe_n >> rxq_data->sges_n,
+				(1 << rxq_data->sges_n),
+				wq_attr.ibv.max_wr, wq_attr.ibv.max_sge);
+			claim_zero(mlx5_glue->destroy_wq(rxq_obj->wq));
+			rxq_obj->wq = NULL;
+			rte_errno = EINVAL;
+		}
+	}
+	return rxq_obj->wq;
+}
+
+/**
+ * Create the Rx queue Verbs object.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ * @param idx
+ *   Queue index in DPDK Rx queue array.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_rxq_ibv_obj_new(struct rte_eth_dev *dev, uint16_t idx)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_rxq_data *rxq_data = (*priv->rxqs)[idx];
+	struct mlx5_rxq_ctrl *rxq_ctrl =
+		container_of(rxq_data, struct mlx5_rxq_ctrl, rxq);
+	struct mlx5_rxq_obj *tmpl = rxq_ctrl->obj;
+	struct mlx5dv_cq cq_info;
+	struct mlx5dv_rwq rwq;
+	int ret = 0;
+	struct mlx5dv_obj obj;
+
+	MLX5_ASSERT(rxq_data);
+	MLX5_ASSERT(tmpl);
+	tmpl->rxq_ctrl = rxq_ctrl;
+	if (rxq_ctrl->irq) {
+		tmpl->ibv_channel =
+				mlx5_glue->create_comp_channel(priv->sh->ctx);
+		if (!tmpl->ibv_channel) {
+			DRV_LOG(ERR, "Port %u: comp channel creation failure.",
+				dev->data->port_id);
+			rte_errno = ENOMEM;
+			goto error;
+		}
+		tmpl->fd = ((struct ibv_comp_channel *)(tmpl->ibv_channel))->fd;
+	}
+	/* Create CQ using Verbs API. */
+	tmpl->ibv_cq = mlx5_rxq_ibv_cq_create(dev, idx);
+	if (!tmpl->ibv_cq) {
+		DRV_LOG(ERR, "Port %u Rx queue %u CQ creation failure.",
+			dev->data->port_id, idx);
+		rte_errno = ENOMEM;
+		goto error;
+	}
+	obj.cq.in = tmpl->ibv_cq;
+	obj.cq.out = &cq_info;
+	ret = mlx5_glue->dv_init_obj(&obj, MLX5DV_OBJ_CQ);
+	if (ret) {
+		rte_errno = ret;
+		goto error;
+	}
+	if (cq_info.cqe_size != RTE_CACHE_LINE_SIZE) {
+		DRV_LOG(ERR,
+			"Port %u wrong MLX5_CQE_SIZE environment "
+			"variable value: it should be set to %u.",
+			dev->data->port_id, RTE_CACHE_LINE_SIZE);
+		rte_errno = EINVAL;
+		goto error;
+	}
+	/* Fill the rings. */
+	rxq_data->cqe_n = log2above(cq_info.cqe_cnt);
+	rxq_data->cq_db = cq_info.dbrec;
+	rxq_data->cqes = (volatile struct mlx5_cqe (*)[])(uintptr_t)cq_info.buf;
+	rxq_data->cq_uar = cq_info.cq_uar;
+	rxq_data->cqn = cq_info.cqn;
+	/* Create WQ (RQ) using Verbs API. */
+	tmpl->wq = mlx5_rxq_ibv_wq_create(dev, idx);
+	if (!tmpl->wq) {
+		DRV_LOG(ERR, "Port %u Rx queue %u WQ creation failure.",
+			dev->data->port_id, idx);
+		rte_errno = ENOMEM;
+		goto error;
+	}
+	/* Change queue state to ready. */
+	ret = mlx5_ibv_modify_wq(tmpl, IBV_WQS_RDY);
+	if (ret) {
+		DRV_LOG(ERR,
+			"Port %u Rx queue %u WQ state to IBV_WQS_RDY failed.",
+			dev->data->port_id, idx);
+		rte_errno = ret;
+		goto error;
+	}
+	obj.rwq.in = tmpl->wq;
+	obj.rwq.out = &rwq;
+	ret = mlx5_glue->dv_init_obj(&obj, MLX5DV_OBJ_RWQ);
+	if (ret) {
+		rte_errno = ret;
+		goto error;
+	}
+	rxq_data->wqes = rwq.buf;
+	rxq_data->rq_db = rwq.dbrec;
+	rxq_data->cq_arm_sn = 0;
+	mlx5_rxq_initialize(rxq_data);
+	rxq_data->cq_ci = 0;
+	dev->data->rx_queue_state[idx] = RTE_ETH_QUEUE_STATE_STARTED;
+	rxq_ctrl->wqn = ((struct ibv_wq *)(tmpl->wq))->wq_num;
+	return 0;
+error:
+	ret = rte_errno; /* Save rte_errno before cleanup. */
+	if (tmpl->wq)
+		claim_zero(mlx5_glue->destroy_wq(tmpl->wq));
+	if (tmpl->ibv_cq)
+		claim_zero(mlx5_glue->destroy_cq(tmpl->ibv_cq));
+	if (tmpl->ibv_channel)
+		claim_zero(mlx5_glue->destroy_comp_channel(tmpl->ibv_channel));
+	rte_errno = ret; /* Restore rte_errno. */
+	return -rte_errno;
+}
+
+/**
+ * Release an Rx verbs queue object.
+ *
+ * @param rxq_obj
+ *   Verbs Rx queue object.
+ */
+static void
+mlx5_rxq_ibv_obj_release(struct mlx5_rxq_obj *rxq_obj)
+{
+	MLX5_ASSERT(rxq_obj);
+	MLX5_ASSERT(rxq_obj->wq);
+	MLX5_ASSERT(rxq_obj->ibv_cq);
+	claim_zero(mlx5_glue->destroy_wq(rxq_obj->wq));
+	claim_zero(mlx5_glue->destroy_cq(rxq_obj->ibv_cq));
+	if (rxq_obj->ibv_channel)
+		claim_zero(mlx5_glue->destroy_comp_channel
+							(rxq_obj->ibv_channel));
+}
+
+/**
+ * Get event for an Rx verbs queue object.
+ *
+ * @param rxq_obj
+ *   Verbs Rx queue object.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_rx_ibv_get_event(struct mlx5_rxq_obj *rxq_obj)
+{
+	struct ibv_cq *ev_cq;
+	void *ev_ctx;
+	int ret = mlx5_glue->get_cq_event(rxq_obj->ibv_channel,
+					  &ev_cq, &ev_ctx);
+
+	if (ret < 0 || ev_cq != rxq_obj->ibv_cq)
+		goto exit;
+	mlx5_glue->ack_cq_events(rxq_obj->ibv_cq, 1);
+	return 0;
+exit:
+	if (ret < 0)
+		rte_errno = errno;
+	else
+		rte_errno = EINVAL;
+	return -rte_errno;
+}
+
+/**
+ * Creates a receive work queue as a filed of indirection table.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ * @param log_n
+ *   Log of number of queues in the array.
+ * @param ind_tbl
+ *   Verbs indirection table object.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_ibv_ind_table_new(struct rte_eth_dev *dev, const unsigned int log_n,
+		       struct mlx5_ind_table_obj *ind_tbl)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct ibv_wq *wq[1 << log_n];
+	unsigned int i, j;
+
+	MLX5_ASSERT(ind_tbl);
+	for (i = 0; i != ind_tbl->queues_n; ++i) {
+		struct mlx5_rxq_data *rxq = (*priv->rxqs)[ind_tbl->queues[i]];
+		struct mlx5_rxq_ctrl *rxq_ctrl =
+				container_of(rxq, struct mlx5_rxq_ctrl, rxq);
+
+		wq[i] = rxq_ctrl->obj->wq;
+	}
+	MLX5_ASSERT(i > 0);
+	/* Finalise indirection table. */
+	for (j = 0; i != (unsigned int)(1 << log_n); ++j, ++i)
+		wq[i] = wq[j];
+	ind_tbl->ind_table = mlx5_glue->create_rwq_ind_table(priv->sh->ctx,
+					&(struct ibv_rwq_ind_table_init_attr){
+						.log_ind_tbl_size = log_n,
+						.ind_tbl = wq,
+						.comp_mask = 0,
+					});
+	if (!ind_tbl->ind_table) {
+		rte_errno = errno;
+		return -rte_errno;
+	}
+	return 0;
+}
+
+/**
+ * Destroys the specified Indirection Table.
+ *
+ * @param ind_table
+ *   Indirection table to release.
+ */
+static void
+mlx5_ibv_ind_table_destroy(struct mlx5_ind_table_obj *ind_tbl)
+{
+	claim_zero(mlx5_glue->destroy_rwq_ind_table(ind_tbl->ind_table));
+}
+
+/**
+ * Create an Rx Hash queue.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ * @param hrxq
+ *   Pointer to Rx Hash queue.
+ * @param tunnel
+ *   Tunnel type.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_ibv_hrxq_new(struct rte_eth_dev *dev, struct mlx5_hrxq *hrxq,
+		  int tunnel __rte_unused)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct ibv_qp *qp = NULL;
+	struct mlx5_ind_table_obj *ind_tbl = hrxq->ind_table;
+	const uint8_t *rss_key = hrxq->rss_key;
+	uint64_t hash_fields = hrxq->hash_fields;
+	int err;
+#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT
+	struct mlx5dv_qp_init_attr qp_init_attr;
+
+	memset(&qp_init_attr, 0, sizeof(qp_init_attr));
+	if (tunnel) {
+		qp_init_attr.comp_mask =
+				       MLX5DV_QP_INIT_ATTR_MASK_QP_CREATE_FLAGS;
+		qp_init_attr.create_flags = MLX5DV_QP_CREATE_TUNNEL_OFFLOADS;
+	}
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+	if (dev->data->dev_conf.lpbk_mode) {
+		/* Allow packet sent from NIC loop back w/o source MAC check. */
+		qp_init_attr.comp_mask |=
+				MLX5DV_QP_INIT_ATTR_MASK_QP_CREATE_FLAGS;
+		qp_init_attr.create_flags |=
+				MLX5DV_QP_CREATE_TIR_ALLOW_SELF_LOOPBACK_UC;
+	}
+#endif
+	qp = mlx5_glue->dv_create_qp
+			(priv->sh->ctx,
+			 &(struct ibv_qp_init_attr_ex){
+				.qp_type = IBV_QPT_RAW_PACKET,
+				.comp_mask =
+					IBV_QP_INIT_ATTR_PD |
+					IBV_QP_INIT_ATTR_IND_TABLE |
+					IBV_QP_INIT_ATTR_RX_HASH,
+				.rx_hash_conf = (struct ibv_rx_hash_conf){
+					.rx_hash_function =
+						IBV_RX_HASH_FUNC_TOEPLITZ,
+					.rx_hash_key_len = hrxq->rss_key_len,
+					.rx_hash_key =
+						(void *)(uintptr_t)rss_key,
+					.rx_hash_fields_mask = hash_fields,
+				},
+				.rwq_ind_tbl = ind_tbl->ind_table,
+				.pd = priv->sh->pd,
+			  },
+			  &qp_init_attr);
+#else
+	qp = mlx5_glue->create_qp_ex
+			(priv->sh->ctx,
+			 &(struct ibv_qp_init_attr_ex){
+				.qp_type = IBV_QPT_RAW_PACKET,
+				.comp_mask =
+					IBV_QP_INIT_ATTR_PD |
+					IBV_QP_INIT_ATTR_IND_TABLE |
+					IBV_QP_INIT_ATTR_RX_HASH,
+				.rx_hash_conf = (struct ibv_rx_hash_conf){
+					.rx_hash_function =
+						IBV_RX_HASH_FUNC_TOEPLITZ,
+					.rx_hash_key_len = hrxq->rss_key_len,
+					.rx_hash_key =
+						(void *)(uintptr_t)rss_key,
+					.rx_hash_fields_mask = hash_fields,
+				},
+				.rwq_ind_tbl = ind_tbl->ind_table,
+				.pd = priv->sh->pd,
+			 });
+#endif
+	if (!qp) {
+		rte_errno = errno;
+		goto error;
+	}
+	hrxq->qp = qp;
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+	hrxq->action = mlx5_glue->dv_create_flow_action_dest_ibv_qp(hrxq->qp);
+	if (!hrxq->action) {
+		rte_errno = errno;
+		goto error;
+	}
+#endif
+	return 0;
+error:
+	err = rte_errno; /* Save rte_errno before cleanup. */
+	if (qp)
+		claim_zero(mlx5_glue->destroy_qp(qp));
+	rte_errno = err; /* Restore rte_errno. */
+	return -rte_errno;
+}
+
+/**
+ * Destroy a Verbs queue pair.
+ *
+ * @param hrxq
+ *   Hash Rx queue to release its qp.
+ */
+static void
+mlx5_ibv_qp_destroy(struct mlx5_hrxq *hrxq)
+{
+	claim_zero(mlx5_glue->destroy_qp(hrxq->qp));
+}
+
+/**
+ * Release a drop Rx queue Verbs object.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ */
+static void
+mlx5_rxq_ibv_obj_drop_release(struct rte_eth_dev *dev)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_rxq_obj *rxq = priv->drop_queue.rxq;
+
+	if (rxq->wq)
+		claim_zero(mlx5_glue->destroy_wq(rxq->wq));
+	if (rxq->ibv_cq)
+		claim_zero(mlx5_glue->destroy_cq(rxq->ibv_cq));
+	mlx5_free(rxq);
+	priv->drop_queue.rxq = NULL;
+}
+
+/**
+ * Create a drop Rx queue Verbs object.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_rxq_ibv_obj_drop_create(struct rte_eth_dev *dev)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct ibv_context *ctx = priv->sh->ctx;
+	struct mlx5_rxq_obj *rxq = priv->drop_queue.rxq;
+
+	if (rxq)
+		return 0;
+	rxq = mlx5_malloc(MLX5_MEM_ZERO, sizeof(*rxq), 0, SOCKET_ID_ANY);
+	if (!rxq) {
+		DRV_LOG(DEBUG, "Port %u cannot allocate drop Rx queue memory.",
+		      dev->data->port_id);
+		rte_errno = ENOMEM;
+		return -rte_errno;
+	}
+	priv->drop_queue.rxq = rxq;
+	rxq->ibv_cq = mlx5_glue->create_cq(ctx, 1, NULL, NULL, 0);
+	if (!rxq->ibv_cq) {
+		DRV_LOG(DEBUG, "Port %u cannot allocate CQ for drop queue.",
+		      dev->data->port_id);
+		rte_errno = errno;
+		goto error;
+	}
+	rxq->wq = mlx5_glue->create_wq(ctx, &(struct ibv_wq_init_attr){
+						    .wq_type = IBV_WQT_RQ,
+						    .max_wr = 1,
+						    .max_sge = 1,
+						    .pd = priv->sh->pd,
+						    .cq = rxq->ibv_cq,
+					      });
+	if (!rxq->wq) {
+		DRV_LOG(DEBUG, "Port %u cannot allocate WQ for drop queue.",
+		      dev->data->port_id);
+		rte_errno = errno;
+		goto error;
+	}
+	priv->drop_queue.rxq = rxq;
+	return 0;
+error:
+	mlx5_rxq_ibv_obj_drop_release(dev);
+	return -rte_errno;
+}
+
+/**
+ * Create a Verbs drop action for Rx Hash queue.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_ibv_drop_action_create(struct rte_eth_dev *dev)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_hrxq *hrxq = priv->drop_queue.hrxq;
+	struct ibv_rwq_ind_table *ind_tbl = NULL;
+	struct mlx5_rxq_obj *rxq;
+	int ret;
+
+	MLX5_ASSERT(hrxq && hrxq->ind_table);
+	ret = mlx5_rxq_ibv_obj_drop_create(dev);
+	if (ret < 0)
+		goto error;
+	rxq = priv->drop_queue.rxq;
+	ind_tbl = mlx5_glue->create_rwq_ind_table
+				(priv->sh->ctx,
+				 &(struct ibv_rwq_ind_table_init_attr){
+					.log_ind_tbl_size = 0,
+					.ind_tbl = (struct ibv_wq **)&rxq->wq,
+					.comp_mask = 0,
+				 });
+	if (!ind_tbl) {
+		DRV_LOG(DEBUG, "Port %u"
+			" cannot allocate indirection table for drop queue.",
+			dev->data->port_id);
+		rte_errno = errno;
+		goto error;
+	}
+	hrxq->qp = mlx5_glue->create_qp_ex(priv->sh->ctx,
+		 &(struct ibv_qp_init_attr_ex){
+			.qp_type = IBV_QPT_RAW_PACKET,
+			.comp_mask = IBV_QP_INIT_ATTR_PD |
+				     IBV_QP_INIT_ATTR_IND_TABLE |
+				     IBV_QP_INIT_ATTR_RX_HASH,
+			.rx_hash_conf = (struct ibv_rx_hash_conf){
+				.rx_hash_function = IBV_RX_HASH_FUNC_TOEPLITZ,
+				.rx_hash_key_len = MLX5_RSS_HASH_KEY_LEN,
+				.rx_hash_key = rss_hash_default_key,
+				.rx_hash_fields_mask = 0,
+				},
+			.rwq_ind_tbl = ind_tbl,
+			.pd = priv->sh->pd
+		 });
+	if (!hrxq->qp) {
+		DRV_LOG(DEBUG, "Port %u cannot allocate QP for drop queue.",
+		      dev->data->port_id);
+		rte_errno = errno;
+		goto error;
+	}
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+	hrxq->action = mlx5_glue->dv_create_flow_action_dest_ibv_qp(hrxq->qp);
+	if (!hrxq->action) {
+		rte_errno = errno;
+		goto error;
+	}
+#endif
+	hrxq->ind_table->ind_table = ind_tbl;
+	return 0;
+error:
+	if (hrxq->qp)
+		claim_zero(mlx5_glue->destroy_qp(hrxq->qp));
+	if (ind_tbl)
+		claim_zero(mlx5_glue->destroy_rwq_ind_table(ind_tbl));
+	if (priv->drop_queue.rxq)
+		mlx5_rxq_ibv_obj_drop_release(dev);
+	return -rte_errno;
+}
+
+/**
+ * Release a drop hash Rx queue.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ */
+static void
+mlx5_ibv_drop_action_destroy(struct rte_eth_dev *dev)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_hrxq *hrxq = priv->drop_queue.hrxq;
+	struct ibv_rwq_ind_table *ind_tbl = hrxq->ind_table->ind_table;
+
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+	claim_zero(mlx5_glue->destroy_flow_action(hrxq->action));
+#endif
+	claim_zero(mlx5_glue->destroy_qp(hrxq->qp));
+	claim_zero(mlx5_glue->destroy_rwq_ind_table(ind_tbl));
+	mlx5_rxq_ibv_obj_drop_release(dev);
+}
+
+/**
+ * Create a QP Verbs object.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ * @param idx
+ *   Queue index in DPDK Tx queue array.
+ *
+ * @return
+ *   The QP Verbs object, NULL otherwise and rte_errno is set.
+ */
+static struct ibv_qp *
+mlx5_txq_ibv_qp_create(struct rte_eth_dev *dev, uint16_t idx)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_txq_data *txq_data = (*priv->txqs)[idx];
+	struct mlx5_txq_ctrl *txq_ctrl =
+			container_of(txq_data, struct mlx5_txq_ctrl, txq);
+	struct ibv_qp *qp_obj = NULL;
+	struct ibv_qp_init_attr_ex qp_attr = { 0 };
+	const int desc = 1 << txq_data->elts_n;
+
+	MLX5_ASSERT(txq_ctrl->obj->cq);
+	/* CQ to be associated with the send queue. */
+	qp_attr.send_cq = txq_ctrl->obj->cq;
+	/* CQ to be associated with the receive queue. */
+	qp_attr.recv_cq = txq_ctrl->obj->cq;
+	/* Max number of outstanding WRs. */
+	qp_attr.cap.max_send_wr = ((priv->sh->device_attr.max_qp_wr < desc) ?
+				   priv->sh->device_attr.max_qp_wr : desc);
+	/*
+	 * Max number of scatter/gather elements in a WR, must be 1 to prevent
+	 * libmlx5 from trying to affect must be 1 to prevent libmlx5 from
+	 * trying to affect too much memory. TX gather is not impacted by the
+	 * device_attr.max_sge limit and will still work properly.
+	 */
+	qp_attr.cap.max_send_sge = 1;
+	qp_attr.qp_type = IBV_QPT_RAW_PACKET,
+	/* Do *NOT* enable this, completions events are managed per Tx burst. */
+	qp_attr.sq_sig_all = 0;
+	qp_attr.pd = priv->sh->pd;
+	qp_attr.comp_mask = IBV_QP_INIT_ATTR_PD;
+	if (txq_data->inlen_send)
+		qp_attr.cap.max_inline_data = txq_ctrl->max_inline_data;
+	if (txq_data->tso_en) {
+		qp_attr.max_tso_header = txq_ctrl->max_tso_header;
+		qp_attr.comp_mask |= IBV_QP_INIT_ATTR_MAX_TSO_HEADER;
+	}
+	qp_obj = mlx5_glue->create_qp_ex(priv->sh->ctx, &qp_attr);
+	if (qp_obj == NULL) {
+		DRV_LOG(ERR, "Port %u Tx queue %u QP creation failure.",
+			dev->data->port_id, idx);
+		rte_errno = errno;
+	}
+	return qp_obj;
+}
+
+/**
+ * Create the Tx queue Verbs object.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ * @param idx
+ *   Queue index in DPDK Tx queue array.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_txq_ibv_obj_new(struct rte_eth_dev *dev, uint16_t idx)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_txq_data *txq_data = (*priv->txqs)[idx];
+	struct mlx5_txq_ctrl *txq_ctrl =
+		container_of(txq_data, struct mlx5_txq_ctrl, txq);
+	struct mlx5_txq_obj *txq_obj = txq_ctrl->obj;
+	unsigned int cqe_n;
+	struct mlx5dv_qp qp;
+	struct mlx5dv_cq cq_info;
+	struct mlx5dv_obj obj;
+	const int desc = 1 << txq_data->elts_n;
+	int ret = 0;
+
+	MLX5_ASSERT(txq_data);
+	MLX5_ASSERT(txq_obj);
+	txq_obj->txq_ctrl = txq_ctrl;
+	if (mlx5_getenv_int("MLX5_ENABLE_CQE_COMPRESSION")) {
+		DRV_LOG(ERR, "Port %u MLX5_ENABLE_CQE_COMPRESSION "
+			"must never be set.", dev->data->port_id);
+		rte_errno = EINVAL;
+		return -rte_errno;
+	}
+	cqe_n = desc / MLX5_TX_COMP_THRESH +
+		1 + MLX5_TX_COMP_THRESH_INLINE_DIV;
+	txq_obj->cq = mlx5_glue->create_cq(priv->sh->ctx, cqe_n, NULL, NULL, 0);
+	if (txq_obj->cq == NULL) {
+		DRV_LOG(ERR, "Port %u Tx queue %u CQ creation failure.",
+			dev->data->port_id, idx);
+		rte_errno = errno;
+		goto error;
+	}
+	txq_obj->qp = mlx5_txq_ibv_qp_create(dev, idx);
+	if (txq_obj->qp == NULL) {
+		rte_errno = errno;
+		goto error;
+	}
+	ret = mlx5_ibv_modify_qp(txq_obj, MLX5_TXQ_MOD_RST2RDY,
+				 (uint8_t)priv->dev_port);
+	if (ret) {
+		DRV_LOG(ERR, "Port %u Tx queue %u QP state modifying failed.",
+			dev->data->port_id, idx);
+		rte_errno = errno;
+		goto error;
+	}
+	qp.comp_mask = MLX5DV_QP_MASK_UAR_MMAP_OFFSET;
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+	/* If using DevX, need additional mask to read tisn value. */
+	if (priv->sh->devx && !priv->sh->tdn)
+		qp.comp_mask |= MLX5DV_QP_MASK_RAW_QP_HANDLES;
+#endif
+	obj.cq.in = txq_obj->cq;
+	obj.cq.out = &cq_info;
+	obj.qp.in = txq_obj->qp;
+	obj.qp.out = &qp;
+	ret = mlx5_glue->dv_init_obj(&obj, MLX5DV_OBJ_CQ | MLX5DV_OBJ_QP);
+	if (ret != 0) {
+		rte_errno = errno;
+		goto error;
+	}
+	if (cq_info.cqe_size != RTE_CACHE_LINE_SIZE) {
+		DRV_LOG(ERR,
+			"Port %u wrong MLX5_CQE_SIZE environment variable"
+			" value: it should be set to %u.",
+			dev->data->port_id, RTE_CACHE_LINE_SIZE);
+		rte_errno = EINVAL;
+		goto error;
+	}
+	txq_data->cqe_n = log2above(cq_info.cqe_cnt);
+	txq_data->cqe_s = 1 << txq_data->cqe_n;
+	txq_data->cqe_m = txq_data->cqe_s - 1;
+	txq_data->qp_num_8s = ((struct ibv_qp *)txq_obj->qp)->qp_num << 8;
+	txq_data->wqes = qp.sq.buf;
+	txq_data->wqe_n = log2above(qp.sq.wqe_cnt);
+	txq_data->wqe_s = 1 << txq_data->wqe_n;
+	txq_data->wqe_m = txq_data->wqe_s - 1;
+	txq_data->wqes_end = txq_data->wqes + txq_data->wqe_s;
+	txq_data->qp_db = &qp.dbrec[MLX5_SND_DBR];
+	txq_data->cq_db = cq_info.dbrec;
+	txq_data->cqes = (volatile struct mlx5_cqe *)cq_info.buf;
+	txq_data->cq_ci = 0;
+	txq_data->cq_pi = 0;
+	txq_data->wqe_ci = 0;
+	txq_data->wqe_pi = 0;
+	txq_data->wqe_comp = 0;
+	txq_data->wqe_thres = txq_data->wqe_s / MLX5_TX_COMP_THRESH_INLINE_DIV;
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+	/*
+	 * If using DevX need to query and store TIS transport domain value.
+	 * This is done once per port.
+	 * Will use this value on Rx, when creating matching TIR.
+	 */
+	if (priv->sh->devx && !priv->sh->tdn) {
+		ret = mlx5_devx_cmd_qp_query_tis_td(txq_obj->qp, qp.tisn,
+						    &priv->sh->tdn);
+		if (ret) {
+			DRV_LOG(ERR, "Fail to query port %u Tx queue %u QP TIS "
+				"transport domain.", dev->data->port_id, idx);
+			rte_errno = EINVAL;
+			goto error;
+		} else {
+			DRV_LOG(DEBUG, "Port %u Tx queue %u TIS number %d "
+				"transport domain %d.", dev->data->port_id,
+				idx, qp.tisn, priv->sh->tdn);
+		}
+	}
+#endif
+	txq_ctrl->bf_reg = qp.bf.reg;
+	if (qp.comp_mask & MLX5DV_QP_MASK_UAR_MMAP_OFFSET) {
+		txq_ctrl->uar_mmap_offset = qp.uar_mmap_offset;
+		DRV_LOG(DEBUG, "Port %u: uar_mmap_offset 0x%" PRIx64 ".",
+			dev->data->port_id, txq_ctrl->uar_mmap_offset);
+	} else {
+		DRV_LOG(ERR,
+			"Port %u failed to retrieve UAR info, invalid"
+			" libmlx5.so",
+			dev->data->port_id);
+		rte_errno = EINVAL;
+		goto error;
+	}
+	txq_uar_init(txq_ctrl);
+	dev->data->tx_queue_state[idx] = RTE_ETH_QUEUE_STATE_STARTED;
+	return 0;
+error:
+	ret = rte_errno; /* Save rte_errno before cleanup. */
+	if (txq_obj->cq)
+		claim_zero(mlx5_glue->destroy_cq(txq_obj->cq));
+	if (txq_obj->qp)
+		claim_zero(mlx5_glue->destroy_qp(txq_obj->qp));
+	rte_errno = ret; /* Restore rte_errno. */
+	return -rte_errno;
+}
+
+/*
+ * Create the dummy QP with minimal resources for loopback.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_rxq_ibv_obj_dummy_lb_create(struct rte_eth_dev *dev)
+{
+#if defined(HAVE_IBV_DEVICE_TUNNEL_SUPPORT) && defined(HAVE_IBV_FLOW_DV_SUPPORT)
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_dev_ctx_shared *sh = priv->sh;
+	struct ibv_context *ctx = sh->ctx;
+	struct mlx5dv_qp_init_attr qp_init_attr = {0};
+	struct {
+		struct ibv_cq_init_attr_ex ibv;
+		struct mlx5dv_cq_init_attr mlx5;
+	} cq_attr = {{0}};
+
+	if (dev->data->dev_conf.lpbk_mode) {
+		/* Allow packet sent from NIC loop back w/o source MAC check. */
+		qp_init_attr.comp_mask |=
+				MLX5DV_QP_INIT_ATTR_MASK_QP_CREATE_FLAGS;
+		qp_init_attr.create_flags |=
+				MLX5DV_QP_CREATE_TIR_ALLOW_SELF_LOOPBACK_UC;
+	} else {
+		return 0;
+	}
+	/* Only need to check refcnt, 0 after "sh" is allocated. */
+	if (!!(__atomic_fetch_add(&sh->self_lb.refcnt, 1, __ATOMIC_RELAXED))) {
+		MLX5_ASSERT(sh->self_lb.ibv_cq && sh->self_lb.qp);
+		priv->lb_used = 1;
+		return 0;
+	}
+	cq_attr.ibv = (struct ibv_cq_init_attr_ex){
+		.cqe = 1,
+		.channel = NULL,
+		.comp_mask = 0,
+	};
+	cq_attr.mlx5 = (struct mlx5dv_cq_init_attr){
+		.comp_mask = 0,
+	};
+	/* Only CQ is needed, no WQ(RQ) is required in this case. */
+	sh->self_lb.ibv_cq = mlx5_glue->cq_ex_to_cq(mlx5_glue->dv_create_cq(ctx,
+							&cq_attr.ibv,
+							&cq_attr.mlx5));
+	if (!sh->self_lb.ibv_cq) {
+		DRV_LOG(ERR, "Port %u cannot allocate CQ for loopback.",
+			dev->data->port_id);
+		rte_errno = errno;
+		goto error;
+	}
+	sh->self_lb.qp = mlx5_glue->dv_create_qp(ctx,
+				&(struct ibv_qp_init_attr_ex){
+					.qp_type = IBV_QPT_RAW_PACKET,
+					.comp_mask = IBV_QP_INIT_ATTR_PD,
+					.pd = sh->pd,
+					.send_cq = sh->self_lb.ibv_cq,
+					.recv_cq = sh->self_lb.ibv_cq,
+					.cap.max_recv_wr = 1,
+				},
+				&qp_init_attr);
+	if (!sh->self_lb.qp) {
+		DRV_LOG(DEBUG, "Port %u cannot allocate QP for loopback.",
+			dev->data->port_id);
+		rte_errno = errno;
+		goto error;
+	}
+	priv->lb_used = 1;
+	return 0;
+error:
+	if (sh->self_lb.ibv_cq) {
+		claim_zero(mlx5_glue->destroy_cq(sh->self_lb.ibv_cq));
+		sh->self_lb.ibv_cq = NULL;
+	}
+	(void)__atomic_sub_fetch(&sh->self_lb.refcnt, 1, __ATOMIC_RELAXED);
+	return -rte_errno;
+#else
+	RTE_SET_USED(dev);
+	return 0;
+#endif
+}
+
+/*
+ * Release the dummy queue resources for loopback.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ */
+void
+mlx5_rxq_ibv_obj_dummy_lb_release(struct rte_eth_dev *dev)
+{
+#if defined(HAVE_IBV_DEVICE_TUNNEL_SUPPORT) && defined(HAVE_IBV_FLOW_DV_SUPPORT)
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_dev_ctx_shared *sh = priv->sh;
+
+	if (!priv->lb_used)
+		return;
+	MLX5_ASSERT(__atomic_load_n(&sh->self_lb.refcnt, __ATOMIC_RELAXED));
+	if (!(__atomic_sub_fetch(&sh->self_lb.refcnt, 1, __ATOMIC_RELAXED))) {
+		if (sh->self_lb.qp) {
+			claim_zero(mlx5_glue->destroy_qp(sh->self_lb.qp));
+			sh->self_lb.qp = NULL;
+		}
+		if (sh->self_lb.ibv_cq) {
+			claim_zero(mlx5_glue->destroy_cq(sh->self_lb.ibv_cq));
+			sh->self_lb.ibv_cq = NULL;
+		}
+	}
+	priv->lb_used = 0;
+#else
+	RTE_SET_USED(dev);
+	return;
+#endif
+}
+
+/**
+ * Release an Tx verbs queue object.
+ *
+ * @param txq_obj
+ *   Verbs Tx queue object..
+ */
+void
+mlx5_txq_ibv_obj_release(struct mlx5_txq_obj *txq_obj)
+{
+	MLX5_ASSERT(txq_obj);
+	claim_zero(mlx5_glue->destroy_qp(txq_obj->qp));
+	claim_zero(mlx5_glue->destroy_cq(txq_obj->cq));
+}
+
+struct mlx5_obj_ops ibv_obj_ops = {
+	.rxq_obj_modify_vlan_strip = mlx5_rxq_obj_modify_wq_vlan_strip,
+	.rxq_obj_new = mlx5_rxq_ibv_obj_new,
+	.rxq_event_get = mlx5_rx_ibv_get_event,
+	.rxq_obj_modify = mlx5_ibv_modify_wq,
+	.rxq_obj_release = mlx5_rxq_ibv_obj_release,
+	.ind_table_new = mlx5_ibv_ind_table_new,
+	.ind_table_destroy = mlx5_ibv_ind_table_destroy,
+	.hrxq_new = mlx5_ibv_hrxq_new,
+	.hrxq_destroy = mlx5_ibv_qp_destroy,
+	.drop_action_create = mlx5_ibv_drop_action_create,
+	.drop_action_destroy = mlx5_ibv_drop_action_destroy,
+	.txq_obj_new = mlx5_txq_ibv_obj_new,
+	.txq_obj_modify = mlx5_ibv_modify_qp,
+	.txq_obj_release = mlx5_txq_ibv_obj_release,
+	.lb_dummy_queue_create = NULL,
+	.lb_dummy_queue_release = NULL,
+};
diff --git a/drivers/net/mlx5/freebsd/mlx5_verbs.h b/drivers/net/mlx5/freebsd/mlx5_verbs.h
new file mode 100644
index 0000000000..f7e8e2fe98
--- /dev/null
+++ b/drivers/net/mlx5/freebsd/mlx5_verbs.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2020 Mellanox Technologies, Ltd
+ */
+
+#ifndef RTE_PMD_MLX5_VERBS_H_
+#define RTE_PMD_MLX5_VERBS_H_
+
+#include "mlx5.h"
+
+int mlx5_txq_ibv_obj_new(struct rte_eth_dev *dev, uint16_t idx);
+void mlx5_txq_ibv_obj_release(struct mlx5_txq_obj *txq_obj);
+int mlx5_rxq_ibv_obj_dummy_lb_create(struct rte_eth_dev *dev);
+void mlx5_rxq_ibv_obj_dummy_lb_release(struct rte_eth_dev *dev);
+
+/* Verbs ops struct */
+extern const struct mlx5_mr_ops mlx5_mr_verbs_ops;
+extern struct mlx5_obj_ops ibv_obj_ops;
+#endif /* RTE_PMD_MLX5_VERBS_H_ */
-- 
2.30.2

[dpdk-dev] [PATCH 03/19] common/mlx5: disabling auxiliary bus support

[Srikanth Kaka]

Disabling auxiliary bus support in FreeBSD at this moment

Signed-off-by: Srikanth Kaka <srikanth.k@oneconvergence.com>
Signed-off-by: Vag Singh <vag.singh@oneconvergence.com>
Signed-off-by: Anand Thulasiram <avelu@juniper.net>
---
 drivers/common/mlx5/freebsd/mlx5_common_verbs.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/common/mlx5/freebsd/mlx5_common_verbs.c b/drivers/common/mlx5/freebsd/mlx5_common_verbs.c
index 9080bd3e87..6a6ab7a7a2 100644
--- a/drivers/common/mlx5/freebsd/mlx5_common_verbs.c
+++ b/drivers/common/mlx5/freebsd/mlx5_common_verbs.c
@@ -12,7 +12,6 @@
 
 #include <rte_errno.h>
 #include <rte_bus_pci.h>
-#include <rte_bus_auxiliary.h>
 
 #include "mlx5_common_utils.h"
 #include "mlx5_common_log.h"
@@ -25,12 +24,10 @@
 struct ibv_device *
 mlx5_os_get_ibv_dev(const struct rte_device *dev)
 {
-	struct ibv_device *ibv;
+	struct ibv_device *ibv = NULL;
 
 	if (mlx5_dev_is_pci(dev))
 		ibv = mlx5_os_get_ibv_device(&RTE_DEV_TO_PCI_CONST(dev)->addr);
-	else
-		ibv = mlx5_get_aux_ibv_device(RTE_DEV_TO_AUXILIARY_CONST(dev));
 	if (ibv == NULL) {
 		rte_errno = ENODEV;
 		DRV_LOG(ERR, "Verbs device not found: %s", dev->name);
-- 
2.30.2

[dpdk-dev] [PATCH 04/19] net/mlx5: disabling auxiliary bus support

[Srikanth Kaka]

Disabling auxiliary bus support in FreeBSD at this moment

Signed-off-by: Srikanth Kaka <srikanth.k@oneconvergence.com>
Signed-off-by: Vag Singh <vag.singh@oneconvergence.com>
Signed-off-by: Anand Thulasiram <avelu@juniper.net>
---
 drivers/net/mlx5/freebsd/mlx5_ethdev_os.c | 12 ------
 drivers/net/mlx5/freebsd/mlx5_os.c        | 52 +----------------------
 drivers/net/mlx5/freebsd/mlx5_os.h        |  2 -
 3 files changed, 2 insertions(+), 64 deletions(-)

diff --git a/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c b/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
index f34133e2c6..5cf3eab65a 100644
--- a/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
+++ b/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
@@ -128,18 +128,6 @@ struct ethtool_link_settings {
 #define ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT 2 /* 66 - 64 */
 #endif
 
-/* Get interface index from SubFunction device name. */
-int
-mlx5_auxiliary_get_ifindex(const char *sf_name)
-{
-	char if_name[IF_NAMESIZE] = { 0 };
-
-	if (mlx5_auxiliary_get_child_name(sf_name, "/net",
-					  if_name, sizeof(if_name)) != 0)
-		return -rte_errno;
-	return if_nametoindex(if_name);
-}
-
 /**
  * Get interface name from private structure.
  *
diff --git a/drivers/net/mlx5/freebsd/mlx5_os.c b/drivers/net/mlx5/freebsd/mlx5_os.c
index 3746057673..616bb73744 100644
--- a/drivers/net/mlx5/freebsd/mlx5_os.c
+++ b/drivers/net/mlx5/freebsd/mlx5_os.c
@@ -20,7 +20,6 @@
 #include <ethdev_pci.h>
 #include <rte_pci.h>
 #include <rte_bus_pci.h>
-#include <rte_bus_auxiliary.h>
 #include <rte_common.h>
 #include <rte_kvargs.h>
 #include <rte_rwlock.h>
@@ -2716,57 +2715,10 @@ mlx5_os_pci_probe(struct rte_pci_device *pci_dev)
 	}
 	return ret;
 }
-
-/* Probe a single SF device on auxiliary bus, no representor support. */
-static int
-mlx5_os_auxiliary_probe(struct rte_device *dev)
-{
-	struct rte_eth_devargs eth_da = { .nb_ports = 0 };
-	struct mlx5_dev_config config;
-	struct mlx5_dev_spawn_data spawn = { .pf_bond = -1 };
-	struct rte_auxiliary_device *adev = RTE_DEV_TO_AUXILIARY(dev);
-	struct rte_eth_dev *eth_dev;
-	int ret = 0;
-
-	/* Parse ethdev devargs. */
-	ret = mlx5_os_parse_eth_devargs(dev, &eth_da);
-	if (ret != 0)
-		return ret;
-	/* Set default config data. */
-	mlx5_os_config_default(&config);
-	config.sf = 1;
-	/* Init spawn data. */
-	spawn.max_port = 1;
-	spawn.phys_port = 1;
-	spawn.phys_dev = mlx5_os_get_ibv_dev(dev);
-	if (spawn.phys_dev == NULL)
-		return -rte_errno;
-	ret = mlx5_auxiliary_get_ifindex(dev->name);
-	if (ret < 0) {
-		DRV_LOG(ERR, "failed to get ethdev ifindex: %s", dev->name);
-		return ret;
-	}
-	spawn.ifindex = ret;
-	spawn.numa_node = dev->numa_node;
-	/* Spawn device. */
-	eth_dev = mlx5_dev_spawn(dev, &spawn, &config, &eth_da);
-	if (eth_dev == NULL)
-		return -rte_errno;
-	/* Post create. */
-	eth_dev->intr_handle = &adev->intr_handle;
-	if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
-		eth_dev->data->dev_flags |= RTE_ETH_DEV_INTR_LSC;
-		eth_dev->data->dev_flags |= RTE_ETH_DEV_INTR_RMV;
-		eth_dev->data->numa_node = dev->numa_node;
-	}
-	rte_eth_dev_probing_finish(eth_dev);
-	return 0;
-}
-
 /**
  * Net class driver callback to probe a device.
  *
- * This function probe PCI bus device(s) or a single SF on auxiliary bus.
+ * This function probe PCI bus device(s)
  *
  * @param[in] dev
  *   Pointer to the generic device.
@@ -2790,7 +2742,7 @@ mlx5_os_net_probe(struct rte_device *dev)
 	if (mlx5_dev_is_pci(dev))
 		return mlx5_os_pci_probe(RTE_DEV_TO_PCI(dev));
 	else
-		return mlx5_os_auxiliary_probe(dev);
+		return -ENOTSUP;
 }
 
 static int
diff --git a/drivers/net/mlx5/freebsd/mlx5_os.h b/drivers/net/mlx5/freebsd/mlx5_os.h
index 2991d37df2..af7cbeb418 100644
--- a/drivers/net/mlx5/freebsd/mlx5_os.h
+++ b/drivers/net/mlx5/freebsd/mlx5_os.h
@@ -19,6 +19,4 @@ enum {
 
 #define MLX5_NAMESIZE IF_NAMESIZE
 
-int mlx5_auxiliary_get_ifindex(const char *sf_name);
-
 #endif /* RTE_PMD_MLX5_OS_H_ */
-- 
2.30.2

[dpdk-dev] [PATCH 05/19] net/mlx5: modified PCI probe to work on FreeBSD

[Srikanth Kaka]

- Representor ports are not yet supported
- Disabling NETLINK_RDMA & NETLINK_ROUTE sockets as netlink sockets are not present
  on FreeBSD

Signed-off-by: Srikanth Kaka <srikanth.k@oneconvergence.com>
Signed-off-by: Vag Singh <vag.singh@oneconvergence.com>
Signed-off-by: Anand Thulasiram <avelu@juniper.net>
---
 drivers/net/mlx5/freebsd/mlx5_os.c | 828 ++++-------------------------
 1 file changed, 116 insertions(+), 712 deletions(-)

diff --git a/drivers/net/mlx5/freebsd/mlx5_os.c b/drivers/net/mlx5/freebsd/mlx5_os.c
index 616bb73744..5420a08cf9 100644
--- a/drivers/net/mlx5/freebsd/mlx5_os.c
+++ b/drivers/net/mlx5/freebsd/mlx5_os.c
@@ -10,9 +10,6 @@
 #include <stdlib.h>
 #include <errno.h>
 #include <net/if.h>
-#include <linux/rtnetlink.h>
-#include <linux/sockios.h>
-#include <linux/ethtool.h>
 #include <fcntl.h>
 
 #include <rte_malloc.h>
@@ -47,7 +44,6 @@
 #include "mlx5_flow.h"
 #include "rte_pmd_mlx5.h"
 #include "mlx5_verbs.h"
-#include "mlx5_nl.h"
 #include "mlx5_devx.h"
 
 #ifndef HAVE_IBV_MLX5_MOD_MPW
@@ -858,76 +854,6 @@ mlx5_queue_counter_id_prepare(struct rte_eth_dev *dev)
 			"available.", dev->data->port_id);
 }
 
-/**
- * Check if representor spawn info match devargs.
- *
- * @param spawn
- *   Verbs device parameters (name, port, switch_info) to spawn.
- * @param eth_da
- *   Device devargs to probe.
- *
- * @return
- *   Match result.
- */
-static bool
-mlx5_representor_match(struct mlx5_dev_spawn_data *spawn,
-		       struct rte_eth_devargs *eth_da)
-{
-	struct mlx5_switch_info *switch_info = &spawn->info;
-	unsigned int p, f;
-	uint16_t id;
-	uint16_t repr_id = mlx5_representor_id_encode(switch_info,
-						      eth_da->type);
-
-	switch (eth_da->type) {
-	case RTE_ETH_REPRESENTOR_SF:
-		if (!(spawn->info.port_name == -1 &&
-		      switch_info->name_type ==
-				MLX5_PHYS_PORT_NAME_TYPE_PFHPF) &&
-		    switch_info->name_type != MLX5_PHYS_PORT_NAME_TYPE_PFSF) {
-			rte_errno = EBUSY;
-			return false;
-		}
-		break;
-	case RTE_ETH_REPRESENTOR_VF:
-		/* Allows HPF representor index -1 as exception. */
-		if (!(spawn->info.port_name == -1 &&
-		      switch_info->name_type ==
-				MLX5_PHYS_PORT_NAME_TYPE_PFHPF) &&
-		    switch_info->name_type != MLX5_PHYS_PORT_NAME_TYPE_PFVF) {
-			rte_errno = EBUSY;
-			return false;
-		}
-		break;
-	case RTE_ETH_REPRESENTOR_NONE:
-		rte_errno = EBUSY;
-		return false;
-	default:
-		rte_errno = ENOTSUP;
-		DRV_LOG(ERR, "unsupported representor type");
-		return false;
-	}
-	/* Check representor ID: */
-	for (p = 0; p < eth_da->nb_ports; ++p) {
-		if (spawn->pf_bond < 0) {
-			/* For non-LAG mode, allow and ignore pf. */
-			switch_info->pf_num = eth_da->ports[p];
-			repr_id = mlx5_representor_id_encode(switch_info,
-							     eth_da->type);
-		}
-		for (f = 0; f < eth_da->nb_representor_ports; ++f) {
-			id = MLX5_REPRESENTOR_ID
-				(eth_da->ports[p], eth_da->type,
-				 eth_da->representor_ports[f]);
-			if (repr_id == id)
-				return true;
-		}
-	}
-	rte_errno = EBUSY;
-	return false;
-}
-
-
 /**
  * Spawn an Ethernet device from Verbs information.
  *
@@ -950,8 +876,7 @@ mlx5_representor_match(struct mlx5_dev_spawn_data *spawn,
 static struct rte_eth_dev *
 mlx5_dev_spawn(struct rte_device *dpdk_dev,
 	       struct mlx5_dev_spawn_data *spawn,
-	       struct mlx5_dev_config *config,
-	       struct rte_eth_devargs *eth_da)
+	       struct mlx5_dev_config *config)
 {
 	const struct mlx5_switch_info *switch_info = &spawn->info;
 	struct mlx5_dev_ctx_shared *sh = NULL;
@@ -977,40 +902,11 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 	struct mlx5_port_info vport_info = { .query_flags = 0 };
 	int i;
 
-	/* Determine if this port representor is supposed to be spawned. */
-	if (switch_info->representor && dpdk_dev->devargs &&
-	    !mlx5_representor_match(spawn, eth_da))
-		return NULL;
+	MLX5_ASSERT(spawn->pf_bond < 0);
+	MLX5_ASSERT(switch_info->representor == 0);
 	/* Build device name. */
-	if (spawn->pf_bond < 0) {
-		/* Single device. */
-		if (!switch_info->representor)
-			strlcpy(name, dpdk_dev->name, sizeof(name));
-		else
-			err = snprintf(name, sizeof(name), "%s_representor_%s%u",
-				 dpdk_dev->name,
-				 switch_info->name_type ==
-				 MLX5_PHYS_PORT_NAME_TYPE_PFSF ? "sf" : "vf",
-				 switch_info->port_name);
-	} else {
-		/* Bonding device. */
-		if (!switch_info->representor) {
-			err = snprintf(name, sizeof(name), "%s_%s",
-				 dpdk_dev->name,
-				 mlx5_os_get_dev_device_name(spawn->phys_dev));
-		} else {
-			err = snprintf(name, sizeof(name), "%s_%s_representor_c%dpf%d%s%u",
-				dpdk_dev->name,
-				mlx5_os_get_dev_device_name(spawn->phys_dev),
-				switch_info->ctrl_num,
-				switch_info->pf_num,
-				switch_info->name_type ==
-				MLX5_PHYS_PORT_NAME_TYPE_PFSF ? "sf" : "vf",
-				switch_info->port_name);
-		}
-	}
-	if (err >= (int)sizeof(name))
-		DRV_LOG(WARNING, "device name overflow %s", name);
+	strlcpy(name, dpdk_dev->name, sizeof(name));
+
 	/* check if the device is already spawned */
 	if (rte_eth_dev_get_port_by_name(name, &port_id) == 0) {
 		rte_errno = EEXIST;
@@ -1197,9 +1093,9 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 	priv->dev_port = spawn->phys_port;
 	priv->pci_dev = spawn->pci_dev;
 	priv->mtu = RTE_ETHER_MTU;
-	/* Some internal functions rely on Netlink sockets, open them now. */
-	priv->nl_socket_rdma = mlx5_nl_init(NETLINK_RDMA);
-	priv->nl_socket_route =	mlx5_nl_init(NETLINK_ROUTE);
+	/* RDMA core has no listener */
+	priv->nl_socket_rdma = -1;
+	priv->nl_socket_route =	-1;
 	priv->representor = !!switch_info->representor;
 	priv->master = !!switch_info->master;
 	priv->domain_id = RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID;
@@ -1280,7 +1176,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 				 switch_info->port_name + 1 : -1;
 	}
 	priv->representor_id = mlx5_representor_id_encode(switch_info,
-							  eth_da->type);
+							  RTE_ETH_REPRESENTOR_NONE);
 	/*
 	 * Look for sibling devices in order to reuse their switch domain
 	 * if any, otherwise allocate one.
@@ -1732,11 +1628,6 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 	eth_dev->rx_queue_count = mlx5_rx_queue_count;
 	/* Register MAC address. */
 	claim_zero(mlx5_mac_addr_add(eth_dev, &mac, 0, 0));
-	if (config->vf && config->vf_nl_en)
-		mlx5_nl_mac_addr_sync(priv->nl_socket_route,
-				      mlx5_ifindex(eth_dev),
-				      eth_dev->data->mac_addrs,
-				      MLX5_MAX_MAC_ADDRESSES);
 	priv->ctrl_flows = 0;
 	rte_spinlock_init(&priv->flow_list_lock);
 	TAILQ_INIT(&priv->flow_meters);
@@ -1977,148 +1868,6 @@ mlx5_dev_spawn_data_cmp(const void *a, const void *b)
 	return si_a->port_name - si_b->port_name;
 }
 
-/**
- * Match PCI information for possible slaves of bonding device.
- *
- * @param[in] ibv_dev
- *   Pointer to Infiniband device structure.
- * @param[in] pci_dev
- *   Pointer to primary PCI address structure to match.
- * @param[in] nl_rdma
- *   Netlink RDMA group socket handle.
- * @param[in] owner
- *   Rerepsentor owner PF index.
- * @param[out] bond_info
- *   Pointer to bonding information.
- *
- * @return
- *   negative value if no bonding device found, otherwise
- *   positive index of slave PF in bonding.
- */
-static int
-mlx5_device_bond_pci_match(const struct ibv_device *ibv_dev,
-			   const struct rte_pci_addr *pci_dev,
-			   int nl_rdma, uint16_t owner,
-			   struct mlx5_bond_info *bond_info)
-{
-	char ifname[IF_NAMESIZE + 1];
-	unsigned int ifindex;
-	unsigned int np, i;
-	FILE *bond_file = NULL, *file;
-	int pf = -1;
-	int ret;
-
-	/*
-	 * Try to get master device name. If something goes
-	 * wrong suppose the lack of kernel support and no
-	 * bonding devices.
-	 */
-	memset(bond_info, 0, sizeof(*bond_info));
-	if (nl_rdma < 0)
-		return -1;
-	if (!strstr(ibv_dev->name, "bond"))
-		return -1;
-	np = mlx5_nl_portnum(nl_rdma, ibv_dev->name);
-	if (!np)
-		return -1;
-	/*
-	 * The Master device might not be on the predefined
-	 * port (not on port index 1, it is not garanted),
-	 * we have to scan all Infiniband device port and
-	 * find master.
-	 */
-	for (i = 1; i <= np; ++i) {
-		/* Check whether Infiniband port is populated. */
-		ifindex = mlx5_nl_ifindex(nl_rdma, ibv_dev->name, i);
-		if (!ifindex)
-			continue;
-		if (!if_indextoname(ifindex, ifname))
-			continue;
-		/* Try to read bonding slave names from sysfs. */
-		MKSTR(slaves,
-		      "/sys/class/net/%s/master/bonding/slaves", ifname);
-		bond_file = fopen(slaves, "r");
-		if (bond_file)
-			break;
-	}
-	if (!bond_file)
-		return -1;
-	/* Use safe format to check maximal buffer length. */
-	MLX5_ASSERT(atol(RTE_STR(IF_NAMESIZE)) == IF_NAMESIZE);
-	while (fscanf(bond_file, "%" RTE_STR(IF_NAMESIZE) "s", ifname) == 1) {
-		char tmp_str[IF_NAMESIZE + 32];
-		struct rte_pci_addr pci_addr;
-		struct mlx5_switch_info	info;
-
-		/* Process slave interface names in the loop. */
-		snprintf(tmp_str, sizeof(tmp_str),
-			 "/sys/class/net/%s", ifname);
-		if (mlx5_get_pci_addr(tmp_str, &pci_addr)) {
-			DRV_LOG(WARNING, "can not get PCI address"
-					 " for netdev \"%s\"", ifname);
-			continue;
-		}
-		/* Slave interface PCI address match found. */
-		snprintf(tmp_str, sizeof(tmp_str),
-			 "/sys/class/net/%s/phys_port_name", ifname);
-		file = fopen(tmp_str, "rb");
-		if (!file)
-			break;
-		info.name_type = MLX5_PHYS_PORT_NAME_TYPE_NOTSET;
-		if (fscanf(file, "%32s", tmp_str) == 1)
-			mlx5_translate_port_name(tmp_str, &info);
-		fclose(file);
-		/* Only process PF ports. */
-		if (info.name_type != MLX5_PHYS_PORT_NAME_TYPE_LEGACY &&
-		    info.name_type != MLX5_PHYS_PORT_NAME_TYPE_UPLINK)
-			continue;
-		/* Check max bonding member. */
-		if (info.port_name >= MLX5_BOND_MAX_PORTS) {
-			DRV_LOG(WARNING, "bonding index out of range, "
-				"please increase MLX5_BOND_MAX_PORTS: %s",
-				tmp_str);
-			break;
-		}
-		/* Match PCI address, allows BDF0+pfx or BDFx+pfx. */
-		if (pci_dev->domain == pci_addr.domain &&
-		    pci_dev->bus == pci_addr.bus &&
-		    pci_dev->devid == pci_addr.devid &&
-		    ((pci_dev->function == 0 &&
-		      pci_dev->function + owner == pci_addr.function) ||
-		     (pci_dev->function == owner &&
-		      pci_addr.function == owner)))
-			pf = info.port_name;
-		/* Get ifindex. */
-		snprintf(tmp_str, sizeof(tmp_str),
-			 "/sys/class/net/%s/ifindex", ifname);
-		file = fopen(tmp_str, "rb");
-		if (!file)
-			break;
-		ret = fscanf(file, "%u", &ifindex);
-		fclose(file);
-		if (ret != 1)
-			break;
-		/* Save bonding info. */
-		strncpy(bond_info->ports[info.port_name].ifname, ifname,
-			sizeof(bond_info->ports[0].ifname));
-		bond_info->ports[info.port_name].pci_addr = pci_addr;
-		bond_info->ports[info.port_name].ifindex = ifindex;
-		bond_info->n_port++;
-	}
-	if (pf >= 0) {
-		/* Get bond interface info */
-		ret = mlx5_sysfs_bond_info(ifindex, &bond_info->ifindex,
-					   bond_info->ifname);
-		if (ret)
-			DRV_LOG(ERR, "unable to get bond info: %s",
-				strerror(rte_errno));
-		else
-			DRV_LOG(INFO, "PF device %u, bond device %u(%s)",
-				ifindex, bond_info->ifindex, bond_info->ifname);
-	}
-	return pf;
-}
-
 static void
 mlx5_os_config_default(struct mlx5_dev_config *config)
 {
@@ -2130,7 +1879,7 @@ mlx5_os_config_default(struct mlx5_dev_config *config)
 	config->txq_inline_min = MLX5_ARG_UNSET;
 	config->txq_inline_mpw = MLX5_ARG_UNSET;
 	config->txqs_inline = MLX5_ARG_UNSET;
-	config->vf_nl_en = 1;
+	config->vf_nl_en = 0;
 	config->mr_ext_memseg_en = 1;
 	config->mprq.max_memcpy_len = MLX5_MPRQ_MEMCPY_DEFAULT_LEN;
 	config->mprq.min_rxqs_num = MLX5_MPRQ_MIN_RXQS;
@@ -2142,25 +1891,18 @@ mlx5_os_config_default(struct mlx5_dev_config *config)
 }
 
 /**
- * Register a PCI device within bonding.
+ * Callback to register a PCI device.
  *
- * This function spawns Ethernet devices out of a given PCI device and
- * bonding owner PF index.
+ * This function spawns Ethernet devices out of a given PCI device.
  *
  * @param[in] pci_dev
  *   PCI device information.
- * @param[in] req_eth_da
- *   Requested ethdev device argument.
- * @param[in] owner_id
- *   Requested owner PF port ID within bonding device, default to 0.
  *
  * @return
  *   0 on success, a negative errno value otherwise and rte_errno is set.
  */
 static int
-mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev,
-		     struct rte_eth_devargs *req_eth_da,
-		     uint16_t owner_id)
+mlx5_os_pci_probe(struct rte_pci_device *pci_dev)
 {
 	struct ibv_device **ibv_list;
 	/*
@@ -2169,32 +1911,25 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev,
 	 * PCI device and we have representors and master.
 	 */
 	unsigned int nd = 0;
-	/*
-	 * Number of found IB device Ports. nd = 1 and np = 1..n means
-	 * we have the single multiport IB device, and there may be
-	 * representors attached to some of found ports.
-	 */
-	unsigned int np = 0;
 	/*
 	 * Number of DPDK ethernet devices to Spawn - either over
 	 * multiple IB devices or multiple ports of single IB device.
 	 * Actually this is the number of iterations to spawn.
 	 */
 	unsigned int ns = 0;
-	/*
-	 * Bonding device
-	 *   < 0 - no bonding device (single one)
-	 *  >= 0 - bonding device (value is slave PF index)
-	 */
-	int bd = -1;
 	struct mlx5_dev_spawn_data *list = NULL;
 	struct mlx5_dev_config dev_config;
 	unsigned int dev_config_vf;
-	struct rte_eth_devargs eth_da = *req_eth_da;
-	struct rte_pci_addr owner_pci = pci_dev->addr; /* Owner PF. */
-	struct mlx5_bond_info bond_info;
-	int ret = -1;
+	int ret;
 
+	if (rte_eal_process_type() == RTE_PROC_PRIMARY)
+		mlx5_pmd_socket_init();
+	ret = mlx5_init_once();
+	if (ret) {
+		DRV_LOG(ERR, "unable to init PMD global data: %s",
+			strerror(rte_errno));
+		return -rte_errno;
+	}
 	errno = 0;
 	ibv_list = mlx5_glue->get_device_list(&ret);
 	if (!ibv_list) {
@@ -2207,55 +1942,23 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev,
 	 * matching ones, gathering into the list.
 	 */
 	struct ibv_device *ibv_match[ret + 1];
-	int nl_route = mlx5_nl_init(NETLINK_ROUTE);
-	int nl_rdma = mlx5_nl_init(NETLINK_RDMA);
 	unsigned int i;
 
 	while (ret-- > 0) {
 		struct rte_pci_addr pci_addr;
 
 		DRV_LOG(DEBUG, "checking device \"%s\"", ibv_list[ret]->name);
-		bd = mlx5_device_bond_pci_match
-				(ibv_list[ret], &owner_pci, nl_rdma, owner_id,
-				 &bond_info);
-		if (bd >= 0) {
-			/*
-			 * Bonding device detected. Only one match is allowed,
-			 * the bonding is supported over multi-port IB device,
-			 * there should be no matches on representor PCI
-			 * functions or non VF LAG bonding devices with
-			 * specified address.
-			 */
-			if (nd) {
-				DRV_LOG(ERR,
-					"multiple PCI match on bonding device"
-					"\"%s\" found", ibv_list[ret]->name);
-				rte_errno = ENOENT;
-				ret = -rte_errno;
-				goto exit;
-			}
-			/* Amend owner pci address if owner PF ID specified. */
-			if (eth_da.nb_representor_ports)
-				owner_pci.function += owner_id;
-			DRV_LOG(INFO, "PCI information matches for"
-				      " slave %d bonding device \"%s\"",
-				      bd, ibv_list[ret]->name);
-			ibv_match[nd++] = ibv_list[ret];
-			break;
-		} else {
-			/* Bonding device not found. */
-			if (mlx5_get_pci_addr(ibv_list[ret]->ibdev_path,
-					      &pci_addr))
-				continue;
-			if (owner_pci.domain != pci_addr.domain ||
-			    owner_pci.bus != pci_addr.bus ||
-			    owner_pci.devid != pci_addr.devid ||
-			    owner_pci.function != pci_addr.function)
-				continue;
-			DRV_LOG(INFO, "PCI information matches for device \"%s\"",
-				ibv_list[ret]->name);
-			ibv_match[nd++] = ibv_list[ret];
-		}
+		if (mlx5_get_pci_addr
+			(ibv_list[ret]->ibdev_path, &pci_addr))
+			continue;
+		if (pci_dev->addr.domain != pci_addr.domain ||
+		    pci_dev->addr.bus != pci_addr.bus ||
+		    pci_dev->addr.devid != pci_addr.devid ||
+		    pci_dev->addr.function != pci_addr.function)
+			continue;
+		DRV_LOG(INFO, "PCI information matches for device \"%s\"",
+			ibv_list[ret]->name);
+		ibv_match[nd++] = ibv_list[ret];
 	}
 	ibv_match[nd] = NULL;
 	if (!nd) {
@@ -2263,38 +1966,18 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev,
 		DRV_LOG(WARNING,
 			"no Verbs device matches PCI device " PCI_PRI_FMT ","
 			" are kernel drivers loaded?",
-			owner_pci.domain, owner_pci.bus,
-			owner_pci.devid, owner_pci.function);
+			pci_dev->addr.domain, pci_dev->addr.bus,
+			pci_dev->addr.devid, pci_dev->addr.function);
 		rte_errno = ENOENT;
 		ret = -rte_errno;
 		goto exit;
 	}
-	if (nd == 1) {
-		/*
-		 * Found single matching device may have multiple ports.
-		 * Each port may be representor, we have to check the port
-		 * number and check the representors existence.
-		 */
-		if (nl_rdma >= 0)
-			np = mlx5_nl_portnum(nl_rdma, ibv_match[0]->name);
-		if (!np)
-			DRV_LOG(WARNING, "can not get IB device \"%s\""
-					 " ports number", ibv_match[0]->name);
-		if (bd >= 0 && !np) {
-			DRV_LOG(ERR, "can not get ports"
-				     " for bonding device");
-			rte_errno = ENOENT;
-			ret = -rte_errno;
-			goto exit;
-		}
-	}
 	/*
 	 * Now we can determine the maximal
 	 * amount of devices to be spawned.
 	 */
 	list = mlx5_malloc(MLX5_MEM_ZERO,
-			   sizeof(struct mlx5_dev_spawn_data) *
-			   (np ? np : nd),
+			   sizeof(struct mlx5_dev_spawn_data) * nd,
 			   RTE_CACHE_LINE_SIZE, SOCKET_ID_ANY);
 	if (!list) {
 		DRV_LOG(ERR, "spawn data array allocation failure");
@@ -2302,220 +1985,70 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev,
 		ret = -rte_errno;
 		goto exit;
 	}
-	if (bd >= 0 || np > 1) {
-		/*
-		 * Single IB device with multiple ports found,
-		 * it may be E-Switch master device and representors.
-		 * We have to perform identification through the ports.
-		 */
-		MLX5_ASSERT(nl_rdma >= 0);
-		MLX5_ASSERT(ns == 0);
-		MLX5_ASSERT(nd == 1);
-		MLX5_ASSERT(np);
-		for (i = 1; i <= np; ++i) {
-			list[ns].bond_info = &bond_info;
-			list[ns].max_port = np;
-			list[ns].phys_port = i;
-			list[ns].phys_dev = ibv_match[0];
-			list[ns].eth_dev = NULL;
-			list[ns].pci_dev = pci_dev;
-			list[ns].pf_bond = bd;
-			list[ns].ifindex = mlx5_nl_ifindex
-				(nl_rdma,
-				mlx5_os_get_dev_device_name
-						(list[ns].phys_dev), i);
+	/*
+	 * 1. A single IB device matches (nd == 1) and
+	 *    is not a representor, assume no switch
+	 *    support.
+	 *
+	 * 2. Otherwise no safe assumptions can be made;
+	 *    complain louder and bail out.
+	 */
+	MLX5_ASSERT(nd);
+	for (i = 0; i != nd; ++i) {
+		memset(&list[ns].info, 0, sizeof(list[ns].info));
+		list[ns].max_port = 1;
+		list[ns].phys_port = 1;
+		list[ns].phys_dev = ibv_match[i];
+		list[ns].eth_dev = NULL;
+		list[ns].pci_dev = pci_dev;
+		list[ns].pf_bond = -1;
+		list[ns].ifindex = 0;
+		if (!list[ns].ifindex) {
+			char ifname[IF_NAMESIZE];
+
+			ret = mlx5_get_ifname_sysfs(ibv_match[i]->ibdev_path,
+					      ifname);
+			if (!ret)
+				list[ns].ifindex =
+					if_nametoindex(ifname);
 			if (!list[ns].ifindex) {
 				/*
-				 * No network interface index found for the
-				 * specified port, it means there is no
-				 * representor on this port. It's OK,
-				 * there can be disabled ports, for example
-				 * if sriov_numvfs < sriov_totalvfs.
-				 */
-				continue;
-			}
-			ret = -1;
-			if (nl_route >= 0)
-				ret = mlx5_nl_switch_info
-					       (nl_route,
-						list[ns].ifindex,
-						&list[ns].info);
-			if (ret || (!list[ns].info.representor &&
-				    !list[ns].info.master)) {
-				/*
-				 * We failed to recognize representors with
-				 * Netlink, let's try to perform the task
-				 * with sysfs.
+				 * No network interface index found
+				 * for the specified device, it means
+				 * there it is neither representor
+				 * nor master.
 				 */
-				ret =  mlx5_sysfs_switch_info
-						(list[ns].ifindex,
-						 &list[ns].info);
-			}
-			if (!ret && bd >= 0) {
-				switch (list[ns].info.name_type) {
-				case MLX5_PHYS_PORT_NAME_TYPE_UPLINK:
-					if (np == 1) {
-						/*
-						 * Force standalone bonding
-						 * device for ROCE LAG
-						 * confgiurations.
-						 */
-						list[ns].info.master = 0;
-						list[ns].info.representor = 0;
-					}
-					if (list[ns].info.port_name == bd)
-						ns++;
-					break;
-				case MLX5_PHYS_PORT_NAME_TYPE_PFHPF:
-					/* Fallthrough */
-				case MLX5_PHYS_PORT_NAME_TYPE_PFVF:
-					/* Fallthrough */
-				case MLX5_PHYS_PORT_NAME_TYPE_PFSF:
-					if (list[ns].info.pf_num == bd)
-						ns++;
-					break;
-				default:
-					break;
-				}
 				continue;
 			}
-			if (!ret && (list[ns].info.representor ^
-				     list[ns].info.master))
-				ns++;
-		}
-		if (!ns) {
-			DRV_LOG(ERR,
-				"unable to recognize master/representors"
-				" on the IB device with multiple ports");
-			rte_errno = ENOENT;
-			ret = -rte_errno;
-			goto exit;
-		}
-	} else {
-		/*
-		 * The existence of several matching entries (nd > 1) means
-		 * port representors have been instantiated. No existing Verbs
-		 * call nor sysfs entries can tell them apart, this can only
-		 * be done through Netlink calls assuming kernel drivers are
-		 * recent enough to support them.
-		 *
-		 * In the event of identification failure through Netlink,
-		 * try again through sysfs, then:
-		 *
-		 * 1. A single IB device matches (nd == 1) with single
-		 *    port (np=0/1) and is not a representor, assume
-		 *    no switch support.
-		 *
-		 * 2. Otherwise no safe assumptions can be made;
-		 *    complain louder and bail out.
-		 */
-		for (i = 0; i != nd; ++i) {
-			memset(&list[ns].info, 0, sizeof(list[ns].info));
-			list[ns].bond_info = NULL;
-			list[ns].max_port = 1;
-			list[ns].phys_port = 1;
-			list[ns].phys_dev = ibv_match[i];
-			list[ns].eth_dev = NULL;
-			list[ns].pci_dev = pci_dev;
-			list[ns].pf_bond = -1;
-			list[ns].ifindex = 0;
-			if (nl_rdma >= 0)
-				list[ns].ifindex = mlx5_nl_ifindex
-				(nl_rdma,
-				mlx5_os_get_dev_device_name
-						(list[ns].phys_dev), 1);
-			if (!list[ns].ifindex) {
-				char ifname[IF_NAMESIZE];
-
-				/*
-				 * Netlink failed, it may happen with old
-				 * ib_core kernel driver (before 4.16).
-				 * We can assume there is old driver because
-				 * here we are processing single ports IB
-				 * devices. Let's try sysfs to retrieve
-				 * the ifindex. The method works for
-				 * master device only.
-				 */
-				if (nd > 1) {
-					/*
-					 * Multiple devices found, assume
-					 * representors, can not distinguish
-					 * master/representor and retrieve
-					 * ifindex via sysfs.
-					 */
-					continue;
-				}
-				ret = mlx5_get_ifname_sysfs
-					(ibv_match[i]->ibdev_path, ifname);
-				if (!ret)
-					list[ns].ifindex =
-						if_nametoindex(ifname);
-				if (!list[ns].ifindex) {
-					/*
-					 * No network interface index found
-					 * for the specified device, it means
-					 * there it is neither representor
-					 * nor master.
-					 */
-					continue;
-				}
-			}
-			ret = -1;
-			if (nl_route >= 0)
-				ret = mlx5_nl_switch_info
-					       (nl_route,
-						list[ns].ifindex,
-						&list[ns].info);
-			if (ret || (!list[ns].info.representor &&
-				    !list[ns].info.master)) {
-				/*
-				 * We failed to recognize representors with
-				 * Netlink, let's try to perform the task
-				 * with sysfs.
-				 */
-				ret =  mlx5_sysfs_switch_info
-						(list[ns].ifindex,
-						 &list[ns].info);
-			}
-			if (!ret && (list[ns].info.representor ^
-				     list[ns].info.master)) {
-				ns++;
-			} else if ((nd == 1) &&
-				   !list[ns].info.representor &&
-				   !list[ns].info.master) {
-				/*
-				 * Single IB device with
-				 * one physical port and
-				 * attached network device.
-				 * May be SRIOV is not enabled
-				 * or there is no representors.
-				 */
-				DRV_LOG(INFO, "no E-Switch support detected");
-				ns++;
-				break;
-			}
 		}
-		if (!ns) {
-			DRV_LOG(ERR,
-				"unable to recognize master/representors"
-				" on the multiple IB devices");
-			rte_errno = ENOENT;
-			ret = -rte_errno;
-			goto exit;
-		}
-		/*
-		 * New kernels may add the switch_id attribute for the case
-		 * there is no E-Switch and we wrongly recognized the
-		 * only device as master. Override this if there is the
-		 * single device with single port and new device name
-		 * format present.
-		 */
-		if (nd == 1 &&
-		    list[0].info.name_type == MLX5_PHYS_PORT_NAME_TYPE_UPLINK) {
-			list[0].info.master = 0;
-			list[0].info.representor = 0;
+		ret = -1;
+		if (!ret && (list[ns].info.representor ^
+			     list[ns].info.master)) {
+			ns++;
+		} else if ((nd == 1) &&
+			   !list[ns].info.representor &&
+			   !list[ns].info.master) {
+			/*
+			 * Single IB device with
+			 * one physical port and
+			 * attached network device.
+			 * May be SRIOV is not enabled
+			 * or there is no representors.
+			 */
+			DRV_LOG(INFO, "no E-Switch support detected");
+			ns++;
+			break;
 		}
 	}
+	if (!ns) {
+		DRV_LOG(ERR,
+			"unable to recognize master/representors"
+			" on the multiple IB devices");
+		rte_errno = ENOENT;
+		ret = -rte_errno;
+		goto exit;
+	}
+
 	MLX5_ASSERT(ns);
 	/*
 	 * Sort list to probe devices in natural order for users convenience
@@ -2537,35 +2070,17 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev,
 		dev_config_vf = 0;
 		break;
 	}
-	if (eth_da.type != RTE_ETH_REPRESENTOR_NONE) {
-		/* Set devargs default values. */
-		if (eth_da.nb_mh_controllers == 0) {
-			eth_da.nb_mh_controllers = 1;
-			eth_da.mh_controllers[0] = 0;
-		}
-		if (eth_da.nb_ports == 0 && ns > 0) {
-			if (list[0].pf_bond >= 0 && list[0].info.representor)
-				DRV_LOG(WARNING, "Representor on Bonding device should use pf#vf# syntax: %s",
-					pci_dev->device.devargs->args);
-			eth_da.nb_ports = 1;
-			eth_da.ports[0] = list[0].info.pf_num;
-		}
-		if (eth_da.nb_representor_ports == 0) {
-			eth_da.nb_representor_ports = 1;
-			eth_da.representor_ports[0] = 0;
-		}
-	}
 	for (i = 0; i != ns; ++i) {
 		uint32_t restore;
 
 		/* Default configuration. */
 		mlx5_os_config_default(&dev_config);
 		dev_config.vf = dev_config_vf;
+		dev_config.allow_duplicate_pattern = 1;
 		list[i].numa_node = pci_dev->device.numa_node;
 		list[i].eth_dev = mlx5_dev_spawn(&pci_dev->device,
 						 &list[i],
-						 &dev_config,
-						 &eth_da);
+						 &dev_config);
 		if (!list[i].eth_dev) {
 			if (rte_errno != EBUSY && rte_errno != EEXIST)
 				break;
@@ -2574,31 +2089,6 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev,
 		}
 		restore = list[i].eth_dev->data->dev_flags;
 		rte_eth_copy_pci_info(list[i].eth_dev, pci_dev);
-		/**
-		 * Each representor has a dedicated interrupts vector.
-		 * rte_eth_copy_pci_info() assigns PF interrupts handle to
-		 * representor eth_dev object because representor and PF
-		 * share the same PCI address.
-		 * Override representor device with a dedicated
-		 * interrupts handle here.
-		 * Representor interrupts handle is released in mlx5_dev_stop().
-		 */
-		if (list[i].info.representor) {
-			struct rte_intr_handle *intr_handle;
-			intr_handle = mlx5_malloc(MLX5_MEM_SYS | MLX5_MEM_ZERO,
-						  sizeof(*intr_handle), 0,
-						  SOCKET_ID_ANY);
-			if (!intr_handle) {
-				DRV_LOG(ERR,
-					"port %u failed to allocate memory for interrupt handler "
-					"Rx interrupts will not be supported",
-					i);
-				rte_errno = ENOMEM;
-				ret = -rte_errno;
-				goto exit;
-			}
-			list[i].eth_dev->intr_handle = intr_handle;
-		}
 		/* Restore non-PCI flags cleared by the above call. */
 		list[i].eth_dev->data->dev_flags |= restore;
 		rte_eth_dev_probing_finish(list[i].eth_dev);
@@ -2607,8 +2097,8 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev,
 		DRV_LOG(ERR,
 			"probe of PCI device " PCI_PRI_FMT " aborted after"
 			" encountering an error: %s",
-			owner_pci.domain, owner_pci.bus,
-			owner_pci.devid, owner_pci.function,
+			pci_dev->addr.domain, pci_dev->addr.bus,
+			pci_dev->addr.devid, pci_dev->addr.function,
 			strerror(rte_errno));
 		ret = -rte_errno;
 		/* Roll back. */
@@ -2628,14 +2118,9 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev,
 exit:
 	/*
 	 * Do the routine cleanup:
-	 * - close opened Netlink sockets
 	 * - free allocated spawn data array
 	 * - free the Infiniband device list
 	 */
-	if (nl_rdma >= 0)
-		close(nl_rdma);
-	if (nl_route >= 0)
-		close(nl_route);
 	if (list)
 		mlx5_free(list);
 	MLX5_ASSERT(ibv_list);
@@ -2643,78 +2128,6 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev,
 	return ret;
 }
 
-static int
-mlx5_os_parse_eth_devargs(struct rte_device *dev,
-			  struct rte_eth_devargs *eth_da)
-{
-	int ret = 0;
-
-	if (dev->devargs == NULL)
-		return 0;
-	memset(eth_da, 0, sizeof(*eth_da));
-	/* Parse representor information first from class argument. */
-	if (dev->devargs->cls_str)
-		ret = rte_eth_devargs_parse(dev->devargs->cls_str, eth_da);
-	if (ret != 0) {
-		DRV_LOG(ERR, "failed to parse device arguments: %s",
-			dev->devargs->cls_str);
-		return -rte_errno;
-	}
-	if (eth_da->type == RTE_ETH_REPRESENTOR_NONE) {
-		/* Parse legacy device argument */
-		ret = rte_eth_devargs_parse(dev->devargs->args, eth_da);
-		if (ret) {
-			DRV_LOG(ERR, "failed to parse device arguments: %s",
-				dev->devargs->args);
-			return -rte_errno;
-		}
-	}
-	return 0;
-}
-
-/**
- * Callback to register a PCI device.
- *
- * This function spawns Ethernet devices out of a given PCI device.
- *
- * @param[in] pci_dev
- *   PCI device information.
- *
- * @return
- *   0 on success, a negative errno value otherwise and rte_errno is set.
- */
-static int
-mlx5_os_pci_probe(struct rte_pci_device *pci_dev)
-{
-	struct rte_eth_devargs eth_da = { .nb_ports = 0 };
-	int ret = 0;
-	uint16_t p;
-
-	ret = mlx5_os_parse_eth_devargs(&pci_dev->device, &eth_da);
-	if (ret != 0)
-		return ret;
-
-	if (eth_da.nb_ports > 0) {
-		/* Iterate all port if devargs pf is range: "pf[0-1]vf[...]". */
-		for (p = 0; p < eth_da.nb_ports; p++) {
-			ret = mlx5_os_pci_probe_pf(pci_dev, &eth_da,
-						   eth_da.ports[p]);
-			if (ret)
-				break;
-		}
-		if (ret) {
-			DRV_LOG(ERR, "Probe of PCI device " PCI_PRI_FMT " "
-				"aborted due to proding failure of PF %u",
-				pci_dev->addr.domain, pci_dev->addr.bus,
-				pci_dev->addr.devid, pci_dev->addr.function,
-				eth_da.ports[p]);
-			mlx5_net_remove(&pci_dev->device);
-		}
-	} else {
-		ret = mlx5_os_pci_probe_pf(pci_dev, &eth_da, 0);
-	}
-	return ret;
-}
 /**
  * Net class driver callback to probe a device.
  *
@@ -3040,13 +2453,8 @@ mlx5_os_set_reg_mr_cb(mlx5_reg_mr_t *reg_mr_cb,
 void
 mlx5_os_mac_addr_remove(struct rte_eth_dev *dev, uint32_t index)
 {
-	struct mlx5_priv *priv = dev->data->dev_private;
-	const int vf = priv->config.vf;
-
-	if (vf)
-		mlx5_nl_mac_addr_remove(priv->nl_socket_route,
-					mlx5_ifindex(dev), priv->mac_own,
-					&dev->data->mac_addrs[index], index);
+	RTE_SET_USED(dev);
+	RTE_SET_USED(index);
 }
 
 /**
@@ -3066,15 +2474,11 @@ int
 mlx5_os_mac_addr_add(struct rte_eth_dev *dev, struct rte_ether_addr *mac,
 		     uint32_t index)
 {
-	struct mlx5_priv *priv = dev->data->dev_private;
-	const int vf = priv->config.vf;
-	int ret = 0;
-
-	if (vf)
-		ret = mlx5_nl_mac_addr_add(priv->nl_socket_route,
-					   mlx5_ifindex(dev), priv->mac_own,
-					   mac, index);
-	return ret;
+	RTE_SET_USED(dev);
+	RTE_SET_USED(mac);
+	RTE_SET_USED(index);
+
+	return -ENOTSUP;
 }
 
 /**
@@ -3098,8 +2502,12 @@ mlx5_os_vf_mac_addr_modify(struct mlx5_priv *priv,
 			   struct rte_ether_addr *mac_addr,
 			   int vf_index)
 {
-	return mlx5_nl_vf_mac_addr_modify
-		(priv->nl_socket_route, iface_idx, mac_addr, vf_index);
+	RTE_SET_USED(priv);
+	RTE_SET_USED(idx);
+	RTE_SET_USED(mac_addr);
+	RTE_SET_USED(vf_index);
+
+	return -ENOTSUP;
 }
 
 /**
@@ -3116,10 +2524,10 @@ mlx5_os_vf_mac_addr_modify(struct mlx5_priv *priv,
 int
 mlx5_os_set_promisc(struct rte_eth_dev *dev, int enable)
 {
-	struct mlx5_priv *priv = dev->data->dev_private;
+	RTE_SET_USED(dev);
+	RTE_SET_USED(enable);
 
-	return mlx5_nl_promisc(priv->nl_socket_route,
-			       mlx5_ifindex(dev), !!enable);
+	return -ENOTSUP;
 }
 
 /**
@@ -3136,10 +2544,10 @@ mlx5_os_set_promisc(struct rte_eth_dev *dev, int enable)
 int
 mlx5_os_set_allmulti(struct rte_eth_dev *dev, int enable)
 {
-	struct mlx5_priv *priv = dev->data->dev_private;
+	RTE_SET_USED(dev);
+	RTE_SET_USED(enable);
 
-	return mlx5_nl_allmulti(priv->nl_socket_route,
-				mlx5_ifindex(dev), !!enable);
+	return -ENOTSUP;
 }
 
 /**
@@ -3152,9 +2560,5 @@ mlx5_os_set_allmulti(struct rte_eth_dev *dev, int enable)
 void
 mlx5_os_mac_addr_flush(struct rte_eth_dev *dev)
 {
-	struct mlx5_priv *priv = dev->data->dev_private;
-
-	mlx5_nl_mac_addr_flush(priv->nl_socket_route, mlx5_ifindex(dev),
-			       dev->data->mac_addrs,
-			       MLX5_MAX_MAC_ADDRESSES, priv->mac_own);
+	RTE_SET_USED(dev);
 }
-- 
2.30.2

[dpdk-dev] [PATCH 06/19] common/mlx5: define PF_INET socket

[Srikanth Kaka]

Similar to NETLINK ROUTE socket in Linux implementation, PF_INET sockets
are used to communicate with FreeBSD network stack

Signed-off-by: Srikanth Kaka <srikanth.k@oneconvergence.com>
Signed-off-by: Vag Singh <vag.singh@oneconvergence.com>
Signed-off-by: Anand Thulasiram <avelu@juniper.net>
---
 drivers/common/mlx5/freebsd/mlx5_inet.c | 306 ++++++++++++++++++++++++
 drivers/common/mlx5/freebsd/mlx5_inet.h |  75 ++++++
 2 files changed, 381 insertions(+)
 create mode 100644 drivers/common/mlx5/freebsd/mlx5_inet.c
 create mode 100644 drivers/common/mlx5/freebsd/mlx5_inet.h

diff --git a/drivers/common/mlx5/freebsd/mlx5_inet.c b/drivers/common/mlx5/freebsd/mlx5_inet.c
new file mode 100644
index 0000000000..5b21e7414e
--- /dev/null
+++ b/drivers/common/mlx5/freebsd/mlx5_inet.c
@@ -0,0 +1,306 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2018 Mellanox Technologies, Ltd
+ */
+
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <net/if.h>
+#include <net/if_types.h>
+#include <err.h>
+#include <errno.h>
+
+#include <rte_errno.h>
+
+#include "mlx5_inet.h"
+#include "mlx5_common_log.h"
+#include "mlx5_common_utils.h"
+#include "mlx5_malloc.h"
+
+/**
+ * Check all multicast mode is enabled in driver through Socket.
+ *
+ * @param inetsk_fd
+ *   Inet socket file descriptor.
+ * @param ifname
+ *   ifname buffer of mlx5_get_ifname(dev, ifname) function.
+ * @param port_id
+ *  port_id of the port .
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_inet_check_allmulti_flag(int inetsk_fd, char *ifname, uint16_t port_id)
+{
+	struct ifreq ifr;
+	int value;
+
+	if (inetsk_fd < 0)
+		return 0;
+
+	memset(&ifr, 0, sizeof(ifr));
+	(void)strlcpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name));
+
+	if (ioctl(inetsk_fd, SIOCGIFFLAGS, (caddr_t)&ifr) < 0)
+		return -errno;
+
+	value = (ifr.ifr_flags & 0xffff) | (ifr.ifr_flagshigh << 16);
+	if (!(value & IFF_ALLMULTI)) {
+		DRV_LOG(WARNING,
+			"port %u allmulti mode not enabled from kernel, "
+			"please disable it from DPDK", port_id);
+		return -1;
+	}
+	return 0;
+}
+
+/**
+ * Enable promiscuous / all multicast mode through Socket.
+ * We make a copy of ifreq to avoid SIOCIGIFFLAGS overwriting on the union
+ * portion of the ifreq structure.
+ *
+ * @param inetsk_fd
+ *   Inet socket file descriptor.
+ * @param ifname_output
+ *   ifname buffer of mlx5_get_ifname(dev, ifname) function.
+ * @param flags
+ *   IFF_PPROMISC for promiscuous, IFF_ALLMULTI for allmulti.
+ * @param enable
+ *   Nonzero to enable, disable otherwise.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_inet_device_flags(int inetsk_fd, char *ifname, int flags, int enable)
+{
+	struct ifreq ifr;
+	int value;
+
+	assert(!(flags & ~(IFF_PPROMISC)));
+	if (inetsk_fd < 0)
+		return 0;
+
+	memset(&ifr, 0, sizeof(ifr));
+	(void)strlcpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name));
+
+	if (ioctl(inetsk_fd, SIOCGIFFLAGS, (caddr_t)&ifr) < 0)
+		return -errno;
+
+	value = (ifr.ifr_flags & 0xffff) | (ifr.ifr_flagshigh << 16);
+	if (enable)
+		value |= flags;
+	else
+		value &= ~flags;
+
+	ifr.ifr_flags = value & 0xffff;
+	ifr.ifr_flagshigh = value >> 16;
+
+	if (ioctl(inetsk_fd, SIOCSIFFLAGS, (caddr_t)&ifr) < 0)
+		return -errno;
+
+	return 0;
+}
+
+/**
+ * Enable promiscuous mode through INET Socket.
+ *
+ * @param inetsk_fd
+ *   Inet socket file descriptor.
+ * @param ifname_output
+ *   ifname buffer of mlx5_get_ifname(dev, ifname) function.
+ * @param enable
+ *   Nonzero to enable, disable otherwise.
+ * @param port_id
+ *   port_id of the interface
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_inet_promisc(int inetsk_fd, char *ifname, int enable, uint16_t port_id)
+{
+	int ret = mlx5_inet_device_flags(inetsk_fd, ifname, IFF_PPROMISC, enable);
+
+	if (ret)
+		DRV_LOG(DEBUG,
+			"port %u cannot %s promisc mode: Socket error %s",
+			port_id, enable ? "enable" : "disable",
+			strerror(rte_errno));
+	return ret;
+}
+
+/**
+ * Modify the MAC address neighbour table with INET Socket.
+ *
+ * @param inetsk_fd
+ *   Inet socket file descriptor.
+ * @param ifname_output
+ *   ifname buffer of mlx5_get_ifname(dev, ifname) function.
+ * @param mac
+ *   MAC address to consider.
+ * @param port_id
+ *   port_id of the interface
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_inet_mac_addr_modify(int inetsk_fd, char *ifname, struct rte_ether_addr *mac, uint16_t port_id)
+{
+	struct ifreq ifr;
+
+	if (inetsk_fd < 0)
+		return 0;
+
+	memset(&ifr, 0, sizeof(ifr));
+	(void)strlcpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name));
+	ifr.ifr_addr.sa_family = AF_LINK;
+	memcpy(ifr.ifr_addr.sa_data, mac, RTE_ETHER_ADDR_LEN);
+	ifr.ifr_addr.sa_len = RTE_ETHER_ADDR_LEN;
+
+	if (ioctl(inetsk_fd, SIOCSIFLLADDR, &ifr) < 0) {
+		rte_errno = errno;
+		goto error;
+	}
+
+	return 0;
+error:
+	DRV_LOG(DEBUG,
+		"port %u cannot add MAC address %02X:%02X:%02X:%02X:%02X:%02X %s",
+		port_id,
+		mac->addr_bytes[0], mac->addr_bytes[1],
+		mac->addr_bytes[2], mac->addr_bytes[3],
+		mac->addr_bytes[4], mac->addr_bytes[5],
+		strerror(rte_errno));
+	return -rte_errno;
+}
+
+/**
+ * Set a MAC address.
+ *
+ * @param inetsk_fd
+ *   Inet socket file descriptor.
+ * @param ifname_output
+ *   ifname buffer of mlx5_get_ifname(dev, ifname) function.
+ * @param mac
+ *   MAC address to register.
+ * @param index
+ *   MAC address index.
+ * @param port_id
+ *   port_id of the interface
+ * @param mac_own
+ *   Current MAC address.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_inet_mac_addr_set(int inetsk_fd, char *ifname,
+		struct rte_ether_addr *mac, uint32_t index,
+		uint16_t port_id, uint64_t *mac_own)
+{
+	int ret;
+
+	ret = mlx5_inet_mac_addr_modify(inetsk_fd, ifname, mac, port_id);
+	if (!ret)
+		BITFIELD_SET(mac_own, index);
+	if (ret == -EEXIST)
+		return 0;
+	return ret;
+}
+
+/**
+ * DPDK callback to add a MAC address.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param mac_addr
+ *   MAC address to register.
+ * @param index
+ *   MAC address index.
+ * @param vmdq
+ *   VMDq pool index to associate address with (ignored).
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_inet_mac_addr_add(struct rte_ether_addr *mac __rte_unused,
+			uint32_t index __rte_unused,
+			uint32_t vmdq __rte_unused,
+			uint16_t port_id)
+{
+	DRV_LOG(INFO, "port %u add MAC not supported in FreeBSD",
+		port_id);
+	return -EOPNOTSUPP;
+}
+
+/**
+ * Before exiting, make interface LLADDR same as HWADDR
+ *
+ * @param inetsk_fd
+ *   Inet socket file descriptor.
+ * @param ifname_output
+ *   ifname buffer of mlx5_get_ifname(dev, ifname) function.
+ * @param lladdr
+ * @param port_id
+ *   port_id of the interface
+ */
+void
+mlx5_inet_mac_addr_flush(int inetsk_fd, char *ifname,
+			struct rte_ether_addr *lladdr,
+			uint16_t port_id)
+{
+	struct ifreq ifr;
+
+	if (inetsk_fd < 0)
+		return;
+
+	memset(&ifr, 0, sizeof(ifr));
+	(void)strlcpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name));
+	ifr.ifr_addr.sa_family = AF_LINK;
+
+	if (ioctl(inetsk_fd, SIOCGHWADDR, &ifr) < 0)
+		return;
+
+	if (memcmp(ifr.ifr_addr.sa_data, lladdr, RTE_ETHER_ADDR_LEN) == 0)
+		return;
+
+	mlx5_inet_mac_addr_modify(inetsk_fd, ifname,
+				  (struct rte_ether_addr *)&ifr.ifr_addr.sa_data,
+				  port_id);
+}
+
+/**
+ * Remove a MAC address.
+ *
+ * @param mac
+ *   MAC address to remove.
+ * @param index
+ *   MAC address index.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+void
+mlx5_inet_mac_addr_remove(uint16_t port_id, uint32_t index __rte_unused)
+{
+	DRV_LOG(INFO,
+		"port %u cannot remove MAC. Operation not supported in FreeBSD",
+		port_id);
+}
+
+/* No bind required on this socket as there are no incoming messages */
+int
+mlx5_inet_init(void)
+{
+	int s;
+
+	s = socket(PF_INET, SOCK_DGRAM, 0);
+	if (s < 0) {
+		rte_errno = errno;
+		return -rte_errno;
+	}
+
+	return s;
+}
diff --git a/drivers/common/mlx5/freebsd/mlx5_inet.h b/drivers/common/mlx5/freebsd/mlx5_inet.h
new file mode 100644
index 0000000000..1bbf4ffb47
--- /dev/null
+++ b/drivers/common/mlx5/freebsd/mlx5_inet.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2019 Mellanox Technologies, Ltd
+ */
+
+#ifndef RTE_PMD_MLX5_INET_H_
+#define RTE_PMD_MLX5_INET_H_
+
+#include <net/if.h>
+#include <netinet/in.h>
+
+#include <rte_ether.h>
+
+#include "mlx5_common.h"
+
+
+/* VLAN netdev for VLAN workaround. */
+struct mlx5_nl_vlan_dev {
+	uint32_t refcnt;
+	uint32_t ifindex; /**< Own interface index. */
+};
+
+/*
+ * Array of VLAN devices created on the base of VF
+ * used for workaround in virtual environments.
+ */
+
+struct mlx5_nl_vlan_vmwa_context {
+	int nl_socket;
+	uint32_t vf_ifindex;
+	rte_spinlock_t sl;
+	struct mlx5_nl_vlan_dev vlan_dev[4096];
+};
+
+__rte_internal
+void mlx5_nl_vlan_vmwa_delete(struct mlx5_nl_vlan_vmwa_context *vmwa,
+			      uint32_t ifindex);
+
+__rte_internal
+uint32_t mlx5_nl_vlan_vmwa_create(struct mlx5_nl_vlan_vmwa_context *vmwa,
+				  uint32_t ifindex, uint16_t tag);
+int
+mlx5_inet_check_allmulti_flag(int inetsk_fd, char *ifname, uint16_t port_id);
+
+int
+mlx5_inet_device_flags(int inetsk_fd, char *ifname, int flags, int enable);
+
+int
+mlx5_inet_promisc(int inetsk_fd, char *ifname, int enable, uint16_t port_id);
+
+int
+mlx5_inet_mac_addr_modify(int inetsk_fd, char *ifname,
+			struct rte_ether_addr *mac, uint16_t port_id);
+
+int
+mlx5_inet_mac_addr_set(int inetsk_fd, char *ifname,
+			struct rte_ether_addr *mac, uint32_t index,
+			uint16_t port_id, uint64_t *mac_own);
+
+int
+mlx5_inet_mac_addr_add(struct rte_ether_addr *mac __rte_unused,
+			uint32_t index __rte_unused,
+			uint32_t vmdq __rte_unused,
+			uint16_t port_id);
+
+void
+mlx5_inet_mac_addr_flush(int inetsk_fd, char *ifname,
+			struct rte_ether_addr *lladdr,
+			uint16_t port_id);
+
+void
+mlx5_inet_mac_addr_remove(uint16_t port_id, uint32_t index __rte_unused);
+
+int
+mlx5_inet_init(void);
+#endif /* RTE_PMD_MLX5_INET_H_ */
-- 
2.30.2

[dpdk-dev] [PATCH 07/19] net/mlx5: use the newly defined INET socket

[Srikanth Kaka]

All the FreeBSD network stack operation can use the INET socket for
set/unset MAC, enable/disable allmulti & promisc mode

Signed-off-by: Srikanth Kaka <srikanth.k@oneconvergence.com>
Signed-off-by: Vag Singh <vag.singh@oneconvergence.com>
Signed-off-by: Anand Thulasiram <avelu@juniper.net>
---
 drivers/net/mlx5/freebsd/mlx5_os.c | 74 ++++++++++++++++++++++--------
 1 file changed, 54 insertions(+), 20 deletions(-)

diff --git a/drivers/net/mlx5/freebsd/mlx5_os.c b/drivers/net/mlx5/freebsd/mlx5_os.c
index 5420a08cf9..cf394763fa 100644
--- a/drivers/net/mlx5/freebsd/mlx5_os.c
+++ b/drivers/net/mlx5/freebsd/mlx5_os.c
@@ -44,6 +44,7 @@
 #include "mlx5_flow.h"
 #include "rte_pmd_mlx5.h"
 #include "mlx5_verbs.h"
+#include "mlx5_inet.h"
 #include "mlx5_devx.h"
 
 #ifndef HAVE_IBV_MLX5_MOD_MPW
@@ -1095,7 +1096,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 	priv->mtu = RTE_ETHER_MTU;
 	/* RDMA core has no listener */
 	priv->nl_socket_rdma = -1;
-	priv->nl_socket_route =	-1;
+	priv->nl_socket_route =	mlx5_inet_init();
 	priv->representor = !!switch_info->representor;
 	priv->master = !!switch_info->master;
 	priv->domain_id = RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID;
@@ -2453,8 +2454,11 @@ mlx5_os_set_reg_mr_cb(mlx5_reg_mr_t *reg_mr_cb,
 void
 mlx5_os_mac_addr_remove(struct rte_eth_dev *dev, uint32_t index)
 {
-	RTE_SET_USED(dev);
-	RTE_SET_USED(index);
+	struct mlx5_priv *priv = dev->data->dev_private;
+	const int vf = priv->config.vf;
+
+	if (vf)
+		mlx5_inet_mac_addr_remove(dev->data->port_id, index);
 }
 
 /**
@@ -2474,11 +2478,18 @@ int
 mlx5_os_mac_addr_add(struct rte_eth_dev *dev, struct rte_ether_addr *mac,
 		     uint32_t index)
 {
-	RTE_SET_USED(dev);
-	RTE_SET_USED(mac);
-	RTE_SET_USED(index);
-
-	return -ENOTSUP;
+	struct mlx5_priv *priv = dev->data->dev_private;
+	const int vf = priv->config.vf;
+	int ret = 0;
+	char ifname[IF_NAMESIZE];
+
+	mlx5_get_ifname_sysfs(priv->sh->ibdev_path, ifname);
+	if (vf)
+		ret = mlx5_inet_mac_addr_set(priv->nl_socket_route,
+					     ifname, mac, index,
+					     dev->data->port_id,
+					     priv->mac_own);
+	return ret;
 }
 
 /**
@@ -2502,12 +2513,16 @@ mlx5_os_vf_mac_addr_modify(struct mlx5_priv *priv,
 			   struct rte_ether_addr *mac_addr,
 			   int vf_index)
 {
-	RTE_SET_USED(priv);
-	RTE_SET_USED(idx);
-	RTE_SET_USED(mac_addr);
-	RTE_SET_USED(vf_index);
+	char ifname[IF_NAMESIZE];
+	int ret;
 
-	return -ENOTSUP;
+	ret = mlx5_get_ifname_sysfs(priv->sh->ibdev_path, ifname);
+	if (!ret)
+		ret = mlx5_inet_mac_addr_set(priv->nl_socket_route, ifname,
+				mac_addr, vf_index,
+				priv->dev_data->port_id,
+				priv->mac_own);
+	return ret;
 }
 
 /**
@@ -2524,10 +2539,16 @@ mlx5_os_vf_mac_addr_modify(struct mlx5_priv *priv,
 int
 mlx5_os_set_promisc(struct rte_eth_dev *dev, int enable)
 {
-	RTE_SET_USED(dev);
-	RTE_SET_USED(enable);
+	struct mlx5_priv *priv = dev->data->dev_private;
+	char ifname[IF_NAMESIZE];
+	int ret;
 
-	return -ENOTSUP;
+	ret = mlx5_get_ifname_sysfs(priv->sh->ibdev_path, ifname);
+	if (!ret)
+		ret = mlx5_inet_promisc(priv->nl_socket_route,
+				 ifname, enable,
+				 dev->data->port_id);
+	return ret;
 }
 
 /**
@@ -2544,10 +2565,15 @@ mlx5_os_set_promisc(struct rte_eth_dev *dev, int enable)
 int
 mlx5_os_set_allmulti(struct rte_eth_dev *dev, int enable)
 {
-	RTE_SET_USED(dev);
-	RTE_SET_USED(enable);
+	struct mlx5_priv *priv = dev->data->dev_private;
+	char ifname[IF_NAMESIZE];
+	int ret;
 
-	return -ENOTSUP;
+	ret = mlx5_get_ifname_sysfs(priv->sh->ibdev_path, ifname);
+	if (!ret)
+		ret = mlx5_inet_check_allmulti_flag(priv->nl_socket_route,
+					     ifname, dev->data->port_id);
+	return ret;
 }
 
 /**
@@ -2560,5 +2586,13 @@ mlx5_os_set_allmulti(struct rte_eth_dev *dev, int enable)
 void
 mlx5_os_mac_addr_flush(struct rte_eth_dev *dev)
 {
-	RTE_SET_USED(dev);
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct rte_ether_addr *lladdr = &dev->data->mac_addrs[0];
+	char ifname[IF_NAMESIZE];
+
+	if (mlx5_get_ifname_sysfs(priv->sh->ibdev_path, ifname))
+		return;
+
+	mlx5_inet_mac_addr_flush(priv->nl_socket_route, ifname,
+				 lladdr, dev->data->port_id);
 }
-- 
2.30.2

[dpdk-dev] [PATCH 08/19] common/mlx5: derive PCI addr in FreeBSD

[Srikanth Kaka]

The FreeBSD OFED gives the Linux path as the IBV device path.
The PCI addr is derived by getting the IBV dev interface index and
finding the corresponding sysctl variable pertaining to it.

Signed-off-by: Srikanth Kaka <srikanth.k@oneconvergence.com>
Signed-off-by: Vag Singh <vag.singh@oneconvergence.com>
Signed-off-by: Anand Thulasiram <avelu@juniper.net>
---
 drivers/common/mlx5/freebsd/mlx5_common_os.c | 79 ++++++++++----------
 drivers/common/mlx5/freebsd/mlx5_common_os.h |  2 +
 2 files changed, 41 insertions(+), 40 deletions(-)

diff --git a/drivers/common/mlx5/freebsd/mlx5_common_os.c b/drivers/common/mlx5/freebsd/mlx5_common_os.c
index 9e0c823c97..af28ff756d 100644
--- a/drivers/common/mlx5/freebsd/mlx5_common_os.c
+++ b/drivers/common/mlx5/freebsd/mlx5_common_os.c
@@ -10,6 +10,7 @@
 #endif
 #include <dirent.h>
 #include <net/if.h>
+#include <sys/sysctl.h>
 
 #include <rte_errno.h>
 #include <rte_string_fns.h>
@@ -26,48 +27,46 @@ const struct mlx5_glue *mlx5_glue;
 int
 mlx5_get_pci_addr(const char *dev_path, struct rte_pci_addr *pci_addr)
 {
-	FILE *file;
-	char line[32];
-	int rc = -ENOENT;
-	MKSTR(path, "%s/device/uevent", dev_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);
-
-		/* Truncate long lines. */
-		if (len == (sizeof(line) - 1)) {
-			while (line[(len - 1)] != '\n') {
-				int ret = fgetc(file);
-
-				if (ret == EOF)
-					goto exit;
-				line[(len - 1)] = ret;
-			}
-			/* No match for long lines. */
-			continue;
-		}
-		/* 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) {
-			rc = 0;
+	char id[10];
+	char searchstr[MLX5_SYSCTL_BY_NAME_SIZE];
+	size_t length = MLX5_SYSCTL_BY_NAME_SIZE;
+	char name[MLX5_SYSCTL_BY_NAME_SIZE];
+	int traverse = 0;
+
+	strncpy(id, &dev_path[strlen("/sys/class/infiniband/mlx5_")],
+			strlen(dev_path) - strlen("/sys/class/infiniband/mlx5_"));
+	sprintf(searchstr, "dev.mlx5_core.%s.%slocation", id, "%");
+	sysctlbyname(searchstr, &name, &length, NULL, 0);
+
+	while (name[traverse]) {
+		if (name[traverse] == 'p' && name[traverse + 1] == 'c' &&
+				name[traverse + 2] == 'i')
 			break;
-		}
+		++traverse;
 	}
-exit:
-	fclose(file);
-	if (rc)
-		rte_errno = -rc;
-	return rc;
+	traverse += 3;
+
+	int end = traverse;
+
+	while (name[end] != ' ')
+		++end;
+
+	char address[end - traverse + 1];
+
+	memcpy(address, &name[traverse], end - traverse);
+	address[end - traverse] = '\0';
+
+	char *ptr = strtok(address, " :");
+
+	pci_addr->domain = (uint32_t)atoi(ptr);
+	ptr = strtok(NULL, " :");
+	pci_addr->bus = (uint8_t)atoi(ptr);
+	ptr =   strtok(NULL, " :");
+	pci_addr->devid = (uint8_t)atoi(ptr);
+	ptr =   strtok(NULL, " :");
+	pci_addr->function = (uint8_t)atoi(ptr);
+
+	return 0;
 }
 
 /**
diff --git a/drivers/common/mlx5/freebsd/mlx5_common_os.h b/drivers/common/mlx5/freebsd/mlx5_common_os.h
index c3202b6786..8fb681444f 100644
--- a/drivers/common/mlx5/freebsd/mlx5_common_os.h
+++ b/drivers/common/mlx5/freebsd/mlx5_common_os.h
@@ -19,6 +19,8 @@
 #include "mlx5_glue.h"
 #include "mlx5_malloc.h"
 
+#define MLX5_SYSCTL_BY_NAME_SIZE 100
+
 /**
  * Get device name. Given an ibv_device pointer - return a
  * pointer to the corresponding device name.
-- 
2.30.2

[dpdk-dev] [PATCH 09/19] common/mlx5: get interface name

[Srikanth Kaka]

All network stack operations use interface name. Get it using
IBV dev index and sysctl.

Signed-off-by: Srikanth Kaka <srikanth.k@oneconvergence.com>
Signed-off-by: Vag Singh <vag.singh@oneconvergence.com>
Signed-off-by: Anand Thulasiram <avelu@juniper.net>
---
 drivers/common/mlx5/freebsd/mlx5_common_os.c | 86 +++++---------------
 drivers/common/mlx5/freebsd/mlx5_common_os.h |  3 +
 2 files changed, 25 insertions(+), 64 deletions(-)

diff --git a/drivers/common/mlx5/freebsd/mlx5_common_os.c b/drivers/common/mlx5/freebsd/mlx5_common_os.c
index af28ff756d..303df16c9f 100644
--- a/drivers/common/mlx5/freebsd/mlx5_common_os.c
+++ b/drivers/common/mlx5/freebsd/mlx5_common_os.c
@@ -147,77 +147,35 @@ mlx5_translate_port_name(const char *port_name_in,
 }
 
 int
-mlx5_get_ifname_sysfs(const char *ibdev_path, char *ifname)
+mlx5_get_ibvindex(const char *ibdev_path)
 {
-	DIR *dir;
-	struct dirent *dent;
-	unsigned int dev_type = 0;
-	unsigned int dev_port_prev = ~0u;
-	char match[IF_NAMESIZE] = "";
+	unsigned int ibv_idx;
 
 	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;
+	sscanf(ibdev_path, "/sys/class/infiniband/mlx5_%u", &ibv_idx);
 
-		MKSTR(path, "%s/device/net/%s/%s",
-		      ibdev_path, name,
-		      (dev_type ? "dev_id" : "dev_port"));
+	return ibv_idx;
+}
 
-		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, IF_NAMESIZE);
-	}
-	closedir(dir);
-	if (match[0] == '\0') {
-		rte_errno = ENOENT;
+int
+mlx5_get_ifname_sysfs(const char *ibdev_path, char *ifname)
+{
+	char buffer[MLX5_SYSCTL_BY_NAME_SIZE];
+	char name[IF_NAMESIZE];
+	size_t len = IF_NAMESIZE;
+	unsigned int idx;
+
+	idx = mlx5_get_ibvindex(ibdev_path);
+
+	snprintf(buffer, sizeof(buffer), "dev.mlx5_core.%u.ifname", idx);
+	if (sysctlbyname(buffer, &name, &len, NULL, 0)) {
+		DRV_LOG(ERR, "port %u failed to get interface name: %s",
+			idx, strerror(errno));
+		rte_errno = errno;
 		return -rte_errno;
 	}
-	strncpy(ifname, match, IF_NAMESIZE);
+	strncpy(ifname, name, IF_NAMESIZE);
+
 	return 0;
 }
 
diff --git a/drivers/common/mlx5/freebsd/mlx5_common_os.h b/drivers/common/mlx5/freebsd/mlx5_common_os.h
index 8fb681444f..bb5f74c599 100644
--- a/drivers/common/mlx5/freebsd/mlx5_common_os.h
+++ b/drivers/common/mlx5/freebsd/mlx5_common_os.h
@@ -298,4 +298,7 @@ __rte_internal
 struct ibv_device *
 mlx5_os_get_ibv_dev(const struct rte_device *dev);
 
+int
+mlx5_get_ibvindex(const char *ibdev_path);
+
 #endif /* RTE_PMD_MLX5_COMMON_OS_H_ */
-- 
2.30.2

[dpdk-dev] [PATCH 10/19] net/mlx5: fix socket MAC request

[Srikanth Kaka]

Use correct socket request type and ifreq for FreeBSD

Signed-off-by: Srikanth Kaka <srikanth.k@oneconvergence.com>
Signed-off-by: Vag Singh <vag.singh@oneconvergence.com>
Signed-off-by: Anand Thulasiram <avelu@juniper.net>
---
 drivers/net/mlx5/freebsd/mlx5_ethdev_os.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c b/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
index 5cf3eab65a..03ae2e4aa9 100644
--- a/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
+++ b/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
@@ -14,11 +14,11 @@
 #include <errno.h>
 #include <dirent.h>
 #include <net/if.h>
+#include <sys/sockio.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>
@@ -1612,9 +1612,9 @@ mlx5_get_mac(struct rte_eth_dev *dev, uint8_t (*mac)[RTE_ETHER_ADDR_LEN])
 	struct ifreq request;
 	int ret;
 
-	ret = mlx5_ifreq(dev, SIOCGIFHWADDR, &request);
+	ret = mlx5_ifreq(dev, SIOCGHWADDR, &request);
 	if (ret)
 		return ret;
-	memcpy(mac, request.ifr_hwaddr.sa_data, RTE_ETHER_ADDR_LEN);
+	memcpy(mac, request.ifr_addr.sa_data, RTE_ETHER_ADDR_LEN);
 	return 0;
 }
-- 
2.30.2

[dpdk-dev] [PATCH 11/19] net/mlx5: removing port representator support

[Srikanth Kaka]

Removing port representator support from mlx5_get_ifname

Signed-off-by: Srikanth Kaka <srikanth.k@oneconvergence.com>
Signed-off-by: Vag Singh <vag.singh@oneconvergence.com>
Signed-off-by: Anand Thulasiram <avelu@juniper.net>
---
 drivers/net/mlx5/freebsd/mlx5_ethdev_os.c | 20 +-------------------
 1 file changed, 1 insertion(+), 19 deletions(-)

diff --git a/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c b/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
index 03ae2e4aa9..268649d16c 100644
--- a/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
+++ b/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
@@ -131,8 +131,6 @@ struct ethtool_link_settings {
 /**
  * Get interface name from private structure.
  *
- * This is a port representor-aware version of mlx5_get_ifname_sysfs().
- *
  * @param[in] dev
  *   Pointer to Ethernet device.
  * @param[out] ifname
@@ -145,26 +143,10 @@ int
 mlx5_get_ifname(const struct rte_eth_dev *dev, char (*ifname)[MLX5_NAMESIZE])
 {
 	struct mlx5_priv *priv = dev->data->dev_private;
-	unsigned int ifindex;
 
 	MLX5_ASSERT(priv);
 	MLX5_ASSERT(priv->sh);
-	if (priv->master && priv->sh->bond.ifindex > 0) {
-		memcpy(ifname, priv->sh->bond.ifname, MLX5_NAMESIZE);
-		return 0;
-	}
-	ifindex = mlx5_ifindex(dev);
-	if (!ifindex) {
-		if (!priv->representor)
-			return mlx5_get_ifname_sysfs(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;
+	return mlx5_get_ifname_sysfs(priv->sh->ibdev_path, *ifname);
 }
 
 /**
-- 
2.30.2

[dpdk-dev] [PATCH 12/19] net/mlx5: Added procedure to detect link state

[Srikanth Kaka]

Defined callback to retrieve physical link information - status,
speed and capability using ioctl

Signed-off-by: Srikanth Kaka <srikanth.k@oneconvergence.com>
Signed-off-by: Vag Singh <vag.singh@oneconvergence.com>
Signed-off-by: Anand Thulasiram <avelu@juniper.net>
---
 drivers/net/mlx5/freebsd/mlx5_ethdev_os.c | 349 +++++++---------------
 1 file changed, 108 insertions(+), 241 deletions(-)

diff --git a/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c b/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
index 268649d16c..b046b6e347 100644
--- a/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
+++ b/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
@@ -14,6 +14,7 @@
 #include <errno.h>
 #include <dirent.h>
 #include <net/if.h>
+#include <net/if_media.h>
 #include <sys/sockio.h>
 #include <sys/ioctl.h>
 #include <sys/socket.h>
@@ -308,265 +309,133 @@ mlx5_read_clock(struct rte_eth_dev *dev, uint64_t *clock)
 	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, dev->device) {
-		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;
-}
+static const struct ifmedia_baudrate ifmedia_baudrate_desc[] =
+	IFM_BAUDRATE_DESCRIPTIONS;
 
-/**
- * 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)
+static uint64_t
+mlx5_ifmedia_baudrate(int mword)
 {
-	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;
+	int i;
 
-	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;
+	for (i = 0; ifmedia_baudrate_desc[i].ifmb_word != 0; i++) {
+		if (IFM_TYPE_MATCH(mword, ifmedia_baudrate_desc[i].ifmb_word))
+			return (ifmedia_baudrate_desc[i].ifmb_baudrate);
 	}
-	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_UNKNOWN;
-	else
-		dev_link.link_speed = link_speed;
-	priv->link_speed_capa = 0;
-	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);
-	*link = dev_link;
-	return 0;
+	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)
-
+mlx5_link_update_bsd(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;
+	int link_speed = 0, sock;
+	struct ifmediareq ifmr;
+	char ifname[IF_NAMESIZE];
+	int *media_list;
 
-	ret = mlx5_ifreq(dev, SIOCGIFFLAGS, &ifr);
-	if (ret) {
-		DRV_LOG(WARNING, "port %u ioctl(SIOCGIFFLAGS) failed: %s",
+	sock = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP);
+	if (sock == -1) {
+		DRV_LOG(ERR,
+			"port %u CANT OPEN SOCKET FOR MEDIA REQUEST on FREEBSD: %s",
 			dev->data->port_id, strerror(rte_errno));
-		return ret;
+		return sock;
 	}
-	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;
-		}
+
+	mlx5_get_ifname(dev, &ifname);
+	memset(&ifmr, 0, sizeof(struct ifmediareq));
+	strlcpy(ifmr.ifm_name, ifname, sizeof(ifmr.ifm_name));
+
+	if (ioctl(sock, SIOCGIFXMEDIA, (caddr_t)&ifmr) < 0) {
+		DRV_LOG(ERR,
+			"ioctl(SIOCGIFMEDIA) on %s: %s",
+			ifname, strerror(errno));
+		close(sock);
+		return errno;
 	}
-	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;
+	media_list = (int *)malloc(ifmr.ifm_count * sizeof(int));
+	ifmr.ifm_ulist = media_list;
 
-	*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;
+	if (ioctl(sock, SIOCGIFXMEDIA, (caddr_t)&ifmr) < 0) {
+		DRV_LOG(ERR,
+			"ioctl(SIOCGIFMEDIA) on %s: %s",
+			ifname, strerror(errno));
+		close(sock);
+		return errno;
 	}
-	dev_link.link_speed = (ecmd->speed == UINT32_MAX) ?
-				ETH_SPEED_NUM_UNKNOWN : ecmd->speed;
-	sc = ecmd->link_mode_masks[0] |
-		((uint64_t)ecmd->link_mode_masks[1] << 32);
+
+	if (ifmr.ifm_status == (IFM_AVALID | IFM_ACTIVE))
+		dev_link.link_status = ETH_LINK_UP;
+	else
+		dev_link.link_status = ETH_LINK_DOWN;
+
+	link_speed = ifmr.ifm_status & IFM_AVALID ?
+			mlx5_ifmedia_baudrate(ifmr.ifm_active) / (1000 * 1000) : 0;
+
+	if (link_speed == 0)
+		dev_link.link_speed = ETH_SPEED_NUM_NONE;
+	else
+		dev_link.link_speed = link_speed;
+
 	priv->link_speed_capa = 0;
-	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);
+	/* Add support for duplex types */
+	dev_link.link_duplex = ETH_LINK_FULL_DUPLEX;
+	/* FreeBSD automatically negotiates speed,
+	 * so it is displayed in its capabilities.
+	 */
+	priv->link_speed_capa |= ETH_LINK_SPEED_AUTONEG;
+
+	for (int i = 1; i < ifmr.ifm_count; i += 2) {
+		switch (mlx5_ifmedia_baudrate(media_list[i]) / (1000 * 1000)) {
+		case 100000:
+			priv->link_speed_capa |= ETH_LINK_SPEED_100G;
+			break;
+		case 56000:
+			priv->link_speed_capa |= ETH_LINK_SPEED_56G;
+			break;
+		case 50000:
+			priv->link_speed_capa |= ETH_LINK_SPEED_50G;
+			break;
+		case 40000:
+			priv->link_speed_capa |= ETH_LINK_SPEED_40G;
+			break;
+		case 25000:
+			priv->link_speed_capa |= ETH_LINK_SPEED_25G;
+			break;
+		case 10000:
+			priv->link_speed_capa |= ETH_LINK_SPEED_10G;
+			break;
+		case 2500:
+			priv->link_speed_capa |= ETH_LINK_SPEED_2_5G;
+			break;
+		case 1000:
+			priv->link_speed_capa |= ETH_LINK_SPEED_1G;
+			break;
+		case 100:
+			priv->link_speed_capa |= (dev_link.link_duplex ==
+						ETH_LINK_FULL_DUPLEX) ?
+						ETH_LINK_SPEED_100M :
+						ETH_LINK_SPEED_100M_HD;
+			break;
+		case 10:
+			priv->link_speed_capa |= (dev_link.link_duplex ==
+						ETH_LINK_FULL_DUPLEX) ?
+						ETH_LINK_SPEED_10M :
+						ETH_LINK_SPEED_10M_HD;
+			break;
+		case 0:
+		default:
+			break;
+		}
+	}
 	dev_link.link_autoneg = !(dev->data->dev_conf.link_speeds &
-				  ETH_LINK_SPEED_FIXED);
+				ETH_LINK_SPEED_FIXED);
+	free(media_list);
 	*link = dev_link;
+	close(sock);
 	return 0;
 }
 
@@ -591,9 +460,7 @@ mlx5_link_update(struct rte_eth_dev *dev, int wait_to_complete)
 	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);
+		ret = mlx5_link_update_bsd(dev, &dev_link);
 		if (ret == 0)
 			break;
 		/* Handle wait to complete situation. */
-- 
2.30.2

[dpdk-dev] [PATCH 13/19] net/mlx5: added placeholder for VLAN vmwa

[Srikanth Kaka]

VLAN workaround for ESXi is not yet supported in FreeBSD,
adding placeholders

Signed-off-by: Srikanth Kaka <srikanth.k@oneconvergence.com>
Signed-off-by: Vag Singh <vag.singh@oneconvergence.com>
Signed-off-by: Anand Thulasiram <avelu@juniper.net>
---
 drivers/net/mlx5/freebsd/mlx5_vlan_os.c | 84 +++++++++++++++++++++++++
 1 file changed, 84 insertions(+)
 create mode 100644 drivers/net/mlx5/freebsd/mlx5_vlan_os.c

diff --git a/drivers/net/mlx5/freebsd/mlx5_vlan_os.c b/drivers/net/mlx5/freebsd/mlx5_vlan_os.c
new file mode 100644
index 0000000000..e2e17d0406
--- /dev/null
+++ b/drivers/net/mlx5/freebsd/mlx5_vlan_os.c
@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2015 6WIND S.A.
+ * Copyright 2015 Mellanox Technologies, Ltd
+ */
+
+#include <stddef.h>
+#include <errno.h>
+#include <stdint.h>
+#include <unistd.h>
+
+/*
+ * Not needed by this file; included to work around the lack of off_t
+ * definition for mlx5dv.h with unpatched rdma-core versions.
+ */
+#include <sys/types.h>
+
+#include <ethdev_driver.h>
+#include <rte_common.h>
+
+#include <mlx5.h>
+#include <mlx5_malloc.h>
+
+/*
+ * Release VLAN network device, created for VM workaround.
+ *
+ * @param[in] dev
+ *   Ethernet device object, Netlink context provider.
+ * @param[in] vlan
+ *   Object representing the network device to release.
+ */
+void
+mlx5_vlan_vmwa_release(struct rte_eth_dev *dev,
+			    struct mlx5_vf_vlan *vlan)
+{
+	RTE_SET_USED(dev);
+	RTE_SET_USED(vlan);
+}
+
+/**
+ * Acquire VLAN interface with specified tag for VM workaround.
+ *
+ * @param[in] dev
+ *   Ethernet device object, Netlink context provider.
+ * @param[in] vlan
+ *   Object representing the network device to acquire.
+ */
+void
+mlx5_vlan_vmwa_acquire(struct rte_eth_dev *dev,
+			    struct mlx5_vf_vlan *vlan)
+{
+	RTE_SET_USED(dev);
+	RTE_SET_USED(vlan);
+}
+
+/*
+ * Create per ethernet device VLAN VM workaround context
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param ifindex
+ *   Interface index.
+ *
+ * @Return
+ *   Pointer to mlx5_nl_vlan_vmwa_context
+ */
+void *
+mlx5_vlan_vmwa_init(struct rte_eth_dev *dev, uint32_t ifindex)
+{
+	RTE_SET_USED(dev);
+	RTE_SET_USED(ifindex);
+	return NULL;
+}
+
+/*
+ * Destroy per ethernet device VLAN VM workaround context
+ *
+ * @param dev
+ *   Pointer to VM context
+ */
+void
+mlx5_vlan_vmwa_exit(void *vmctx)
+{
+	RTE_SET_USED(vmctx);
+}
-- 
2.30.2

[dpdk-dev] [PATCH 14/19] net/mlx5: added stats support

[Srikanth Kaka]

Initialize device stats and fetch them using sysctl.
Removed ethtool traces

Signed-off-by: Srikanth Kaka <srikanth.k@oneconvergence.com>
Signed-off-by: Vag Singh <vag.singh@oneconvergence.com>
Signed-off-by: Anand Thulasiram <avelu@juniper.net>
---
 drivers/net/mlx5/freebsd/mlx5_ethdev_os.c | 361 +++++-----------------
 1 file changed, 84 insertions(+), 277 deletions(-)

diff --git a/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c b/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
index b046b6e347..f1946fa9f6 100644
--- a/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
+++ b/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
@@ -15,11 +15,11 @@
 #include <dirent.h>
 #include <net/if.h>
 #include <net/if_media.h>
+#include <sys/sysctl.h>
 #include <sys/sockio.h>
 #include <sys/ioctl.h>
 #include <sys/socket.h>
 #include <netinet/in.h>
-#include <linux/ethtool.h>
 #include <fcntl.h>
 #include <stdalign.h>
 #include <sys/un.h>
@@ -44,90 +44,7 @@
 #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
+static unsigned int xstats_n;
 
 /**
  * Get interface name from private structure.
@@ -1114,44 +1031,31 @@ int mlx5_get_module_eeprom(struct rte_eth_dev *dev,
  *   PF index in case of bonding device, -1 otherwise
  * @param[out] stats
  *   Counters table output buffer.
- *
- * @return
- *   0 on success and stats is filled, negative errno value otherwise and
- *   rte_errno is set.
  */
-static int
-_mlx5_os_read_dev_counters(struct rte_eth_dev *dev, int pf, uint64_t *stats)
+static void
+_mlx5_os_read_dev_counters(struct rte_eth_dev *dev, uint64_t *stats)
 {
 	struct mlx5_priv *priv = dev->data->dev_private;
 	struct mlx5_xstats_ctrl *xstats_ctrl = &priv->xstats_ctrl;
+	char stat_key[RTE_ETH_XSTATS_NAME_SIZE + 16];
 	unsigned int i;
-	struct ifreq ifr;
-	unsigned int stats_sz = xstats_ctrl->stats_n * sizeof(uint64_t);
-	unsigned char et_stat_buf[sizeof(struct ethtool_stats) + stats_sz];
-	struct ethtool_stats *et_stats = (struct ethtool_stats *)et_stat_buf;
-	int ret;
+	size_t len = sizeof(uint64_t);
+	uint64_t val;
+	int ibvindex, ret;
+
+	ibvindex = mlx5_get_ibvindex(priv->sh->ibdev_path);
 
-	et_stats->cmd = ETHTOOL_GSTATS;
-	et_stats->n_stats = xstats_ctrl->stats_n;
-	ifr.ifr_data = (caddr_t)et_stats;
-	if (pf >= 0)
-		ret = mlx5_ifreq_by_ifname(priv->sh->bond.ports[pf].ifname,
-					   SIOCETHTOOL, &ifr);
-	else
-		ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
-	if (ret) {
-		DRV_LOG(WARNING,
-			"port %u unable to read statistic values from device",
-			dev->data->port_id);
-		return ret;
-	}
 	for (i = 0; i != xstats_ctrl->mlx5_stats_n; ++i) {
-		if (xstats_ctrl->info[i].dev)
+		snprintf(stat_key, sizeof(stat_key), "dev.mce.%d.%s",
+			 ibvindex, xstats_ctrl->info[i].ctr_name);
+		ret = sysctlbyname(stat_key, &val, &len, NULL, 0);
+		if (ret == -1) {
+			DRV_LOG(WARNING, "port %u failed to get statistics: %s",
+				dev->data->port_id, strerror(errno));
 			continue;
-		stats[i] += (uint64_t)
-			    et_stats->data[xstats_ctrl->dev_table_idx[i]];
+		}
+		stats[i] += val;
 	}
-	return 0;
 }
 
 /**
@@ -1174,17 +1078,8 @@ mlx5_os_read_dev_counters(struct rte_eth_dev *dev, uint64_t *stats)
 	int ret = 0, i;
 
 	memset(stats, 0, sizeof(*stats) * xstats_ctrl->mlx5_stats_n);
-	/* Read ifreq counters. */
-	if (priv->master && priv->pf_bond >= 0) {
-		/* Sum xstats from bonding device member ports. */
-		for (i = 0; i < priv->sh->bond.n_port; i++) {
-			ret = _mlx5_os_read_dev_counters(dev, i, stats);
-			if (ret)
-				return ret;
-		}
-	} else {
-		ret = _mlx5_os_read_dev_counters(dev, -1, stats);
-	}
+	_mlx5_os_read_dev_counters(dev, stats);
+
 	/* Read IB counters. */
 	for (i = 0; i != xstats_ctrl->mlx5_stats_n; ++i) {
 		if (!xstats_ctrl->info[i].dev)
@@ -1201,158 +1096,129 @@ mlx5_os_read_dev_counters(struct rte_eth_dev *dev, uint64_t *stats)
 }
 
 /**
- * Query the number of statistics provided by ETHTOOL.
+ * Query the number of statistics.
  *
  * @param dev
  *   Pointer to Ethernet device.
  *
  * @return
- *   Number of statistics on success, negative errno value otherwise and
- *   rte_errno is set.
+ *   Number of statistics on success.
  */
 int
 mlx5_os_get_stats_n(struct rte_eth_dev *dev)
 {
-	struct mlx5_priv *priv = dev->data->dev_private;
-	struct ethtool_drvinfo drvinfo;
-	struct ifreq ifr;
-	int ret;
-
-	drvinfo.cmd = ETHTOOL_GDRVINFO;
-	ifr.ifr_data = (caddr_t)&drvinfo;
-	if (priv->master && priv->pf_bond >= 0)
-		/* Bonding PF. */
-		ret = mlx5_ifreq_by_ifname(priv->sh->bond.ports[0].ifname,
-					   SIOCETHTOOL, &ifr);
-	else
-		ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
-	if (ret) {
-		DRV_LOG(WARNING, "port %u unable to query number of statistics",
-			dev->data->port_id);
-		return ret;
-	}
-	return drvinfo.n_stats;
+	RTE_SET_USED(dev);
+	return xstats_n;
 }
 
 static const struct mlx5_counter_ctrl mlx5_counters_init[] = {
 	{
-		.dpdk_name = "rx_unicast_bytes",
-		.ctr_name = "rx_vport_unicast_bytes",
+		.dpdk_name = "rx_port_unicast_bytes",
+		.ctr_name = "vstats.rx_unicast_bytes",
 	},
 	{
-		.dpdk_name = "rx_multicast_bytes",
-		.ctr_name = "rx_vport_multicast_bytes",
+		.dpdk_name = "rx_port_multicast_bytes",
+		.ctr_name = "vstats.rx_multicast_bytes",
 	},
 	{
-		.dpdk_name = "rx_broadcast_bytes",
-		.ctr_name = "rx_vport_broadcast_bytes",
+		.dpdk_name = "rx_port_broadcast_bytes",
+		.ctr_name = "vstats.rx_broadcast_bytes",
 	},
 	{
-		.dpdk_name = "rx_unicast_packets",
-		.ctr_name = "rx_vport_unicast_packets",
+		.dpdk_name = "rx_port_unicast_packets",
+		.ctr_name = "vstats.rx_unicast_packets",
 	},
 	{
-		.dpdk_name = "rx_multicast_packets",
-		.ctr_name = "rx_vport_multicast_packets",
+		.dpdk_name = "rx_port_multicast_packets",
+		.ctr_name = "vstats.rx_multicast_packets",
 	},
 	{
-		.dpdk_name = "rx_broadcast_packets",
-		.ctr_name = "rx_vport_broadcast_packets",
+		.dpdk_name = "rx_port_broadcast_packets",
+		.ctr_name = "vstats.rx_broadcast_packets",
 	},
 	{
-		.dpdk_name = "tx_unicast_bytes",
-		.ctr_name = "tx_vport_unicast_bytes",
+		.dpdk_name = "tx_port_unicast_bytes",
+		.ctr_name = "vstats.tx_unicast_bytes",
 	},
 	{
-		.dpdk_name = "tx_multicast_bytes",
-		.ctr_name = "tx_vport_multicast_bytes",
+		.dpdk_name = "tx_port_multicast_bytes",
+		.ctr_name = "vstats.tx_multicast_bytes",
 	},
 	{
-		.dpdk_name = "tx_broadcast_bytes",
-		.ctr_name = "tx_vport_broadcast_bytes",
+		.dpdk_name = "tx_port_broadcast_bytes",
+		.ctr_name = "vstats.tx_broadcast_bytes",
 	},
 	{
-		.dpdk_name = "tx_unicast_packets",
-		.ctr_name = "tx_vport_unicast_packets",
+		.dpdk_name = "tx_port_unicast_packets",
+		.ctr_name = "vstats.tx_unicast_packets",
 	},
 	{
-		.dpdk_name = "tx_multicast_packets",
-		.ctr_name = "tx_vport_multicast_packets",
+		.dpdk_name = "tx_port_multicast_packets",
+		.ctr_name = "vstats.tx_multicast_packets",
 	},
 	{
-		.dpdk_name = "tx_broadcast_packets",
-		.ctr_name = "tx_vport_broadcast_packets",
+		.dpdk_name = "tx_port_broadcast_packets",
+		.ctr_name = "vstats.tx_broadcast_packets",
 	},
 	{
-		.dpdk_name = "rx_wqe_errors",
-		.ctr_name = "rx_wqe_err",
+		.dpdk_name = "rx_wqe_err",
+		.ctr_name = "vstats.rx_wqe_err",
 	},
 	{
-		.dpdk_name = "rx_phy_crc_errors",
-		.ctr_name = "rx_crc_errors_phy",
+		.dpdk_name = "rx_crc_align_errors",
+		.ctr_name = "pstats.crc_align_errors",
 	},
 	{
-		.dpdk_name = "rx_phy_in_range_len_errors",
-		.ctr_name = "rx_in_range_len_errors_phy",
+		.dpdk_name = "rx_in_range_len_errors",
+		.ctr_name = "pstats.in_range_len_errors",
 	},
 	{
-		.dpdk_name = "rx_phy_symbol_errors",
-		.ctr_name = "rx_symbol_err_phy",
+		.dpdk_name = "rx_symbol_err",
+		.ctr_name = "pstats.symbol_err",
 	},
 	{
-		.dpdk_name = "tx_phy_errors",
-		.ctr_name = "tx_errors_phy",
+		.dpdk_name = "tx_errors_packets",
+		.ctr_name = "vstats.tx_error_packets",
 	},
 	{
 		.dpdk_name = "rx_out_of_buffer",
-		.ctr_name = "out_of_buffer",
-		.dev = 1,
-	},
-	{
-		.dpdk_name = "tx_phy_packets",
-		.ctr_name = "tx_packets_phy",
-	},
-	{
-		.dpdk_name = "rx_phy_packets",
-		.ctr_name = "rx_packets_phy",
+		.ctr_name = "vstats.rx_out_of_buffer",
 	},
 	{
-		.dpdk_name = "tx_phy_discard_packets",
-		.ctr_name = "tx_discards_phy",
+		.dpdk_name = "lro_bytes",
+		.ctr_name = "vstats.lro_bytes",
 	},
 	{
-		.dpdk_name = "rx_phy_discard_packets",
-		.ctr_name = "rx_discards_phy",
+		.dpdk_name = "lro_packets",
+		.ctr_name = "vstats.lro_packets",
 	},
 	{
-		.dpdk_name = "tx_phy_bytes",
-		.ctr_name = "tx_bytes_phy",
+		.dpdk_name = "tso_bytes",
+		.ctr_name = "vstats.tso_bytes",
 	},
 	{
-		.dpdk_name = "rx_phy_bytes",
-		.ctr_name = "rx_bytes_phy",
+		.dpdk_name = "tso_packets",
+		.ctr_name = "vstats.tso_packets",
 	},
 	/* Representor only */
 	{
-		.dpdk_name = "rx_vport_packets",
-		.ctr_name = "vport_rx_packets",
+		.dpdk_name = "rx_packets",
+		.ctr_name = "vstats.rx_packets",
 	},
 	{
-		.dpdk_name = "rx_vport_bytes",
-		.ctr_name = "vport_rx_bytes",
+		.dpdk_name = "rx_bytes",
+		.ctr_name = "vstats.rx_bytes",
 	},
 	{
-		.dpdk_name = "tx_vport_packets",
-		.ctr_name = "vport_tx_packets",
+		.dpdk_name = "tx_packets",
+		.ctr_name = "vstats.tx_packets",
 	},
 	{
-		.dpdk_name = "tx_vport_bytes",
-		.ctr_name = "vport_tx_bytes",
+		.dpdk_name = "tx_bytes",
+		.ctr_name = "vstats.tx_bytes",
 	},
 };
 
-static const unsigned int xstats_n = RTE_DIM(mlx5_counters_init);
-
 /**
  * Init the structures to read device counters.
  *
@@ -1365,83 +1231,24 @@ mlx5_os_stats_init(struct rte_eth_dev *dev)
 	struct mlx5_priv *priv = dev->data->dev_private;
 	struct mlx5_xstats_ctrl *xstats_ctrl = &priv->xstats_ctrl;
 	struct mlx5_stats_ctrl *stats_ctrl = &priv->stats_ctrl;
-	unsigned int i;
-	unsigned int j;
-	struct ifreq ifr;
-	struct ethtool_gstrings *strings = NULL;
-	unsigned int dev_stats_n;
-	unsigned int str_sz;
-	int ret;
 
-	/* So that it won't aggregate for each init. */
+	xstats_n = RTE_DIM(mlx5_counters_init);
 	xstats_ctrl->mlx5_stats_n = 0;
-	ret = mlx5_os_get_stats_n(dev);
-	if (ret < 0) {
-		DRV_LOG(WARNING, "port %u no extended statistics available",
-			dev->data->port_id);
-		return;
-	}
-	dev_stats_n = ret;
-	/* Allocate memory to grab stat names and values. */
-	str_sz = dev_stats_n * ETH_GSTRING_LEN;
-	strings = (struct ethtool_gstrings *)
-		  mlx5_malloc(0, str_sz + sizeof(struct ethtool_gstrings), 0,
-			      SOCKET_ID_ANY);
-	if (!strings) {
-		DRV_LOG(WARNING, "port %u unable to allocate memory for xstats",
-		     dev->data->port_id);
-		return;
-	}
-	strings->cmd = ETHTOOL_GSTRINGS;
-	strings->string_set = ETH_SS_STATS;
-	strings->len = dev_stats_n;
-	ifr.ifr_data = (caddr_t)strings;
-	if (priv->master && priv->pf_bond >= 0)
-		/* Bonding master. */
-		ret = mlx5_ifreq_by_ifname(priv->sh->bond.ports[0].ifname,
-					   SIOCETHTOOL, &ifr);
-	else
-		ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr);
-	if (ret) {
-		DRV_LOG(WARNING, "port %u unable to get statistic names",
-			dev->data->port_id);
-		goto free;
-	}
-	for (i = 0; i != dev_stats_n; ++i) {
-		const char *curr_string = (const char *)
-			&strings->data[i * ETH_GSTRING_LEN];
-
-		for (j = 0; j != xstats_n; ++j) {
-			if (!strcmp(mlx5_counters_init[j].ctr_name,
-				    curr_string)) {
-				unsigned int idx = xstats_ctrl->mlx5_stats_n++;
-
-				xstats_ctrl->dev_table_idx[idx] = i;
-				xstats_ctrl->info[idx] = mlx5_counters_init[j];
-				break;
-			}
-		}
-	}
-	/* Add dev counters. */
-	for (i = 0; i != xstats_n; ++i) {
-		if (mlx5_counters_init[i].dev) {
-			unsigned int idx = xstats_ctrl->mlx5_stats_n++;
 
-			xstats_ctrl->info[idx] = mlx5_counters_init[i];
-			xstats_ctrl->hw_stats[idx] = 0;
-		}
+	for (unsigned int i = 0; i != xstats_n; ++i) {
+		unsigned int idx = xstats_ctrl->mlx5_stats_n++;
+
+		xstats_ctrl->dev_table_idx[idx] = i;
+		xstats_ctrl->info[idx] = mlx5_counters_init[i];
 	}
-	MLX5_ASSERT(xstats_ctrl->mlx5_stats_n <= MLX5_MAX_XSTATS);
-	xstats_ctrl->stats_n = dev_stats_n;
-	/* Copy to base at first time. */
-	ret = mlx5_os_read_dev_counters(dev, xstats_ctrl->base);
+	xstats_ctrl->stats_n = xstats_n;
+	int ret = mlx5_os_read_dev_counters(dev, xstats_ctrl->base);
+
 	if (ret)
 		DRV_LOG(ERR, "port %u cannot read device counters: %s",
 			dev->data->port_id, strerror(rte_errno));
 	mlx5_os_read_dev_stat(priv, "out_of_buffer", &stats_ctrl->imissed_base);
 	stats_ctrl->imissed = 0;
-free:
-	mlx5_free(strings);
 }
 
 /**
-- 
2.30.2

[dpdk-dev] [PATCH 15/19] net/mlx5: making flow control DPDK callback invalid

[Srikanth Kaka]

At present, flow control CBs are not being supported on FreeBSD

Signed-off-by: Srikanth Kaka <srikanth.k@oneconvergence.com>
Signed-off-by: Vag Singh <vag.singh@oneconvergence.com>
Signed-off-by: Anand Thulasiram <avelu@juniper.net>
---
 drivers/net/mlx5/freebsd/mlx5_ethdev_os.c | 61 ++++-------------------
 1 file changed, 10 insertions(+), 51 deletions(-)

diff --git a/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c b/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
index f1946fa9f6..a04bac8ed9 100644
--- a/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
+++ b/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
@@ -414,31 +414,12 @@ mlx5_link_update(struct rte_eth_dev *dev, int wait_to_complete)
 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;
+	RTE_SET_USED(fc_conf);
+	DRV_LOG(WARNING,
+		"port %u can not get flow control status. Operation not supported in FreeBSD",
+		dev->data->port_id);
 
-	ifr.ifr_data = (void *)&ethpause;
-	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;
+	return -EOPNOTSUPP;
 }
 
 /**
@@ -455,34 +436,12 @@ 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, struct rte_eth_fc_conf *fc_conf)
 {
-	struct ifreq ifr;
-	struct ethtool_pauseparam ethpause = {
-		.cmd = ETHTOOL_SPAUSEPARAM
-	};
-	int ret;
-
-	ifr.ifr_data = (void *)&ethpause;
-	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;
+	RTE_SET_USED(fc_conf);
+	DRV_LOG(WARNING,
+		"port %u can not modify flow control. Operation not supported in FreeBSD",
+		dev->data->port_id);
 
-	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;
+	return -EOPNOTSUPP;
 }
 
 /**
-- 
2.30.2

[dpdk-dev] [PATCH 16/19] net/mlx5: making module DPDK callbacks invalid

[Srikanth Kaka]

At present, DPDK module callbacks are not supported

Signed-off-by: Srikanth Kaka <srikanth.k@oneconvergence.com>
Signed-off-by: Vag Singh <vag.singh@oneconvergence.com>
Signed-off-by: Anand Thulasiram <avelu@juniper.net>
---
 drivers/net/mlx5/freebsd/mlx5_ethdev_os.c | 60 +++--------------------
 1 file changed, 6 insertions(+), 54 deletions(-)

diff --git a/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c b/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
index a04bac8ed9..5940803cfc 100644
--- a/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
+++ b/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
@@ -909,28 +909,9 @@ 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) {
-		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;
+	RTE_SET_USED(dev);
+	RTE_SET_USED(modinfo);
+	return -ENOTSUP;
 }
 
 /**
@@ -947,38 +928,9 @@ mlx5_get_module_info(struct rte_eth_dev *dev,
 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) {
-		DRV_LOG(WARNING, "missing argument, cannot get module eeprom");
-		rte_errno = EINVAL;
-		return -rte_errno;
-	}
-	eeprom = mlx5_malloc(MLX5_MEM_ZERO,
-			     (sizeof(struct ethtool_eeprom) + info->length), 0,
-			     SOCKET_ID_ANY);
-	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);
-	mlx5_free(eeprom);
-	return ret;
+	RTE_SET_USED(dev);
+	RTE_SET_USED(info);
+	return -ENOTSUP;
 }
 
 /**
-- 
2.30.2

[dpdk-dev] [PATCH 17/19] common/mlx5: fixed missing dependency in mlx5_glue.h

[Srikanth Kaka]

In FreeBSD, "FILE" needs stdio.h to be included

Signed-off-by: Srikanth Kaka <srikanth.k@oneconvergence.com>
Signed-off-by: Vag Singh <vag.singh@oneconvergence.com>
Signed-off-by: Anand Thulasiram <avelu@juniper.net>
---
 drivers/common/mlx5/freebsd/mlx5_glue.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/common/mlx5/freebsd/mlx5_glue.h b/drivers/common/mlx5/freebsd/mlx5_glue.h
index f39ef2dac7..9f12a5d71e 100644
--- a/drivers/common/mlx5/freebsd/mlx5_glue.h
+++ b/drivers/common/mlx5/freebsd/mlx5_glue.h
@@ -6,6 +6,7 @@
 #ifndef MLX5_GLUE_H_
 #define MLX5_GLUE_H_
 
+#include <stdio.h>
 #include <stddef.h>
 #include <stdint.h>
 /* Verbs headers do not support -pedantic. */
-- 
2.30.2

[dpdk-dev] [PATCH 18/19] net/mlx5: fixed compilation warnings

[Srikanth Kaka]

In FreeBSD, interface name instead of index is for network stack operations
The ALLMULTI is always enabled by kernel driver, we only check if the kernel
has enabled it or not and then accordingly enable/disable in PMD

Signed-off-by: Srikanth Kaka <srikanth.k@oneconvergence.com>
Signed-off-by: Vag Singh <vag.singh@oneconvergence.com>
Signed-off-by: Anand Thulasiram <avelu@juniper.net>
---
 drivers/net/mlx5/freebsd/mlx5_os.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/mlx5/freebsd/mlx5_os.c b/drivers/net/mlx5/freebsd/mlx5_os.c
index cf394763fa..376cceadb0 100644
--- a/drivers/net/mlx5/freebsd/mlx5_os.c
+++ b/drivers/net/mlx5/freebsd/mlx5_os.c
@@ -2516,6 +2516,7 @@ mlx5_os_vf_mac_addr_modify(struct mlx5_priv *priv,
 	char ifname[IF_NAMESIZE];
 	int ret;
 
+	RTE_SET_USED(iface_idx);
 	ret = mlx5_get_ifname_sysfs(priv->sh->ibdev_path, ifname);
 	if (!ret)
 		ret = mlx5_inet_mac_addr_set(priv->nl_socket_route, ifname,
@@ -2569,6 +2570,7 @@ mlx5_os_set_allmulti(struct rte_eth_dev *dev, int enable)
 	char ifname[IF_NAMESIZE];
 	int ret;
 
+	RTE_SET_USED(enable);
 	ret = mlx5_get_ifname_sysfs(priv->sh->ibdev_path, ifname);
 	if (!ret)
 		ret = mlx5_inet_check_allmulti_flag(priv->nl_socket_route,
-- 
2.30.2

[dpdk-dev] [PATCH 19/19] mlx5: Added meson support for FreeBSD

[Srikanth Kaka]

The freebsd/meson.build files are derived from their Linux counterparts
This commit includes meson files for both common/mlx5 and net/mlx5 as missing
either one of them will break compilation between the commits

Signed-off-by: Srikanth Kaka <srikanth.k@oneconvergence.com>
Signed-off-by: Vag Singh <vag.singh@oneconvergence.com>
Signed-off-by: Anand Thulasiram <avelu@juniper.net>
---
 drivers/common/mlx5/freebsd/meson.build | 189 ++++++++++++++++++++++++
 drivers/common/mlx5/meson.build         |  12 +-
 drivers/net/mlx5/freebsd/meson.build    |  14 ++
 drivers/net/mlx5/meson.build            |  14 +-
 4 files changed, 222 insertions(+), 7 deletions(-)
 create mode 100644 drivers/common/mlx5/freebsd/meson.build
 create mode 100644 drivers/net/mlx5/freebsd/meson.build

diff --git a/drivers/common/mlx5/freebsd/meson.build b/drivers/common/mlx5/freebsd/meson.build
new file mode 100644
index 0000000000..1385ffc0f7
--- /dev/null
+++ b/drivers/common/mlx5/freebsd/meson.build
@@ -0,0 +1,189 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright 2020 Mellanox Technologies, Ltd
+
+includes += include_directories('.')
+
+static_ibverbs = (get_option('ibverbs_link') == 'static')
+dlopen_ibverbs = (get_option('ibverbs_link') == 'dlopen')
+LIB_GLUE_BASE = 'librte_common_mlx5_glue.so'
+LIB_GLUE_VERSION = abi_version
+LIB_GLUE = LIB_GLUE_BASE + '.' + LIB_GLUE_VERSION
+if dlopen_ibverbs
+    dpdk_conf.set('RTE_IBVERBS_LINK_DLOPEN', 1)
+    cflags += [
+	    '-DMLX5_GLUE="@0@"'.format(LIB_GLUE),
+	    '-DMLX5_GLUE_VERSION="@0@"'.format(LIB_GLUE_VERSION),
+    ]
+endif
+
+libnames = [ 'mlx5', 'ibverbs' ]
+libs = []
+foreach libname:libnames
+    lib = dependency('lib' + libname, static:static_ibverbs, required:false, method: 'pkg-config')
+    if not lib.found() and not static_ibverbs
+	lib = cc.find_library(libname, required:false)
+    endif
+    if lib.found()
+	libs += lib
+	if not static_ibverbs and not dlopen_ibverbs
+	    ext_deps += lib
+	endif
+    else
+	build = false
+	reason = 'missing dependency, "' + libname + '"'
+	subdir_done()
+    endif
+endforeach
+if static_ibverbs or dlopen_ibverbs
+    # Build without adding shared libs to Requires.private
+    ibv_cflags = run_command(pkgconf, '--cflags', 'libibverbs').stdout()
+    ext_deps += declare_dependency(compile_args: ibv_cflags.split())
+endif
+if static_ibverbs
+    # Add static deps ldflags to internal apps and Libs.private
+    ibv_ldflags = run_command(ldflags_ibverbs_static, check:true).stdout()
+    ext_deps += declare_dependency(link_args:ibv_ldflags.split())
+endif
+
+sources += files('mlx5_inet.c')
+sources += files('mlx5_common_os.c')
+sources += files('mlx5_common_verbs.c')
+if not dlopen_ibverbs
+    sources += files('mlx5_glue.c')
+endif
+
+# To maintain the compatibility with the make build system
+# mlx5_autoconf.h file is still generated.
+# input array for meson member search:
+# [ "MACRO to define if found", "header for the search",
+#   "symbol to search", "struct member to search" ]
+has_member_args = [
+	[ 'HAVE_IBV_MLX5_MOD_SWP', 'infiniband/mlx5dv.h',
+	    'struct mlx5dv_sw_parsing_caps', 'sw_parsing_offloads' ],
+	[ 'HAVE_IBV_DEVICE_COUNTERS_SET_V42', 'infiniband/verbs.h',
+	    'struct ibv_counter_set_init_attr', 'counter_set_id' ],
+	[ 'HAVE_IBV_DEVICE_COUNTERS_SET_V45', 'infiniband/verbs.h',
+	    'struct ibv_counters_init_attr', 'comp_mask' ],
+	[ 'HAVE_MLX5DV_DEVX_UAR_OFFSET', 'infiniband/mlx5dv.h',
+	    'struct mlx5dv_devx_uar', 'mmap_off' ],
+]
+# input array for meson symbol search:
+# [ "MACRO to define if found", "header for the search",
+#   "symbol to search" ]
+has_sym_args = [
+	[ 'HAVE_IBV_RELAXED_ORDERING', 'infiniband/verbs.h',
+	    'IBV_ACCESS_RELAXED_ORDERING ' ],
+	[ 'HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT', 'infiniband/mlx5dv.h',
+	    'MLX5DV_CQE_RES_FORMAT_CSUM_STRIDX' ],
+	[ 'HAVE_IBV_DEVICE_TUNNEL_SUPPORT', 'infiniband/mlx5dv.h',
+	    'MLX5DV_CONTEXT_MASK_TUNNEL_OFFLOADS' ],
+	[ 'HAVE_IBV_MLX5_MOD_MPW', 'infiniband/mlx5dv.h',
+	    'MLX5DV_CONTEXT_FLAGS_MPW_ALLOWED' ],
+	[ 'HAVE_IBV_MLX5_MOD_CQE_128B_COMP', 'infiniband/mlx5dv.h',
+	    'MLX5DV_CONTEXT_FLAGS_CQE_128B_COMP' ],
+	[ 'HAVE_IBV_MLX5_MOD_CQE_128B_PAD', 'infiniband/mlx5dv.h',
+	    'MLX5DV_CQ_INIT_ATTR_FLAGS_CQE_PAD' ],
+	[ 'HAVE_IBV_FLOW_DV_SUPPORT', 'infiniband/mlx5dv.h',
+	    'mlx5dv_create_flow_action_packet_reformat' ],
+	[ 'HAVE_IBV_DEVICE_MPLS_SUPPORT', 'infiniband/verbs.h',
+	    'IBV_FLOW_SPEC_MPLS' ],
+	[ 'HAVE_IBV_WQ_FLAGS_PCI_WRITE_END_PADDING', 'infiniband/verbs.h',
+	    'IBV_WQ_FLAGS_PCI_WRITE_END_PADDING' ],
+	[ 'HAVE_IBV_WQ_FLAG_RX_END_PADDING', 'infiniband/verbs.h',
+	    'IBV_WQ_FLAG_RX_END_PADDING' ],
+	[ 'HAVE_MLX5DV_DR_DEVX_PORT', 'infiniband/mlx5dv.h',
+	    'mlx5dv_query_devx_port' ],
+	[ 'HAVE_MLX5DV_DR_DEVX_PORT_V35', 'infiniband/mlx5dv.h',
+	    'mlx5dv_query_port' ],
+	[ 'HAVE_MLX5DV_DR_CREATE_DEST_IB_PORT', 'infiniband/mlx5dv.h',
+	    'mlx5dv_dr_action_create_dest_ib_port' ],
+	[ 'HAVE_IBV_DEVX_OBJ', 'infiniband/mlx5dv.h',
+	    'mlx5dv_devx_obj_create' ],
+	[ 'HAVE_IBV_FLOW_DEVX_COUNTERS', 'infiniband/mlx5dv.h',
+	    'MLX5DV_FLOW_ACTION_COUNTERS_DEVX' ],
+	[ 'HAVE_MLX5_DR_CREATE_ACTION_DEFAULT_MISS', 'infiniband/mlx5dv.h',
+	    'MLX5DV_FLOW_ACTION_DEFAULT_MISS' ],
+	[ 'HAVE_IBV_DEVX_ASYNC', 'infiniband/mlx5dv.h',
+	    'mlx5dv_devx_obj_query_async' ],
+	[ 'HAVE_IBV_DEVX_QP', 'infiniband/mlx5dv.h',
+	    'mlx5dv_devx_qp_query' ],
+	[ 'HAVE_MLX5DV_PP_ALLOC', 'infiniband/mlx5dv.h',
+	    'mlx5dv_pp_alloc' ],
+	[ 'HAVE_MLX5DV_DR_ACTION_DEST_DEVX_TIR', 'infiniband/mlx5dv.h',
+	    'mlx5dv_dr_action_create_dest_devx_tir' ],
+	[ 'HAVE_IBV_DEVX_EVENT', 'infiniband/mlx5dv.h',
+	    'mlx5dv_devx_get_event' ],
+	[ 'HAVE_MLX5_DR_CREATE_ACTION_FLOW_METER', 'infiniband/mlx5dv.h',
+	    'mlx5dv_dr_action_create_flow_meter' ],
+	[ 'HAVE_MLX5DV_MMAP_GET_NC_PAGES_CMD', 'infiniband/mlx5dv.h',
+	    'MLX5_MMAP_GET_NC_PAGES_CMD' ],
+	[ 'HAVE_MLX5DV_DR', 'infiniband/mlx5dv.h',
+	    'MLX5DV_DR_DOMAIN_TYPE_NIC_RX' ],
+	[ 'HAVE_MLX5DV_DR_ESWITCH', 'infiniband/mlx5dv.h',
+	    'MLX5DV_DR_DOMAIN_TYPE_FDB' ],
+	[ 'HAVE_MLX5DV_DR_VLAN', 'infiniband/mlx5dv.h',
+	    'mlx5dv_dr_action_create_push_vlan' ],
+	[ 'HAVE_IBV_VAR', 'infiniband/mlx5dv.h', 'mlx5dv_alloc_var' ],
+	[ 'HAVE_MLX5_OPCODE_ENHANCED_MPSW', 'infiniband/mlx5dv.h',
+	    'MLX5_OPCODE_ENHANCED_MPSW' ],
+	[ 'HAVE_MLX5_OPCODE_SEND_EN', 'infiniband/mlx5dv.h',
+	    'MLX5_OPCODE_SEND_EN' ],
+	[ 'HAVE_MLX5_OPCODE_WAIT', 'infiniband/mlx5dv.h',
+	    'MLX5_OPCODE_WAIT' ],
+	[ 'HAVE_MLX5_OPCODE_ACCESS_ASO', 'infiniband/mlx5dv.h',
+	    'MLX5_OPCODE_ACCESS_ASO' ],
+	[ 'HAVE_MLX5_DR_FLOW_DUMP', 'infiniband/mlx5dv.h',
+	    'mlx5dv_dump_dr_domain'],
+	[ 'HAVE_MLX5_DR_CREATE_ACTION_FLOW_SAMPLE', 'infiniband/mlx5dv.h',
+	    'mlx5dv_dr_action_create_flow_sampler'],
+	[ 'HAVE_MLX5DV_DR_MEM_RECLAIM', 'infiniband/mlx5dv.h',
+	    'mlx5dv_dr_domain_set_reclaim_device_memory'],
+	[ 'HAVE_MLX5_DR_CREATE_ACTION_DEST_ARRAY', 'infiniband/mlx5dv.h',
+	    'mlx5dv_dr_action_create_dest_array'],
+	[ 'HAVE_MLX5_DR_CREATE_ACTION_ASO', 'infiniband/mlx5dv.h',
+	    'mlx5dv_dr_action_create_aso' ],
+	[ 'HAVE_INFINIBAND_VERBS_H', 'infiniband/verbs.h',
+	    'INFINIBAND_VERBS_H' ],
+	[ 'HAVE_MLX5_UMR_IMKEY', 'infiniband/mlx5dv.h',
+	    'MLX5_WQE_UMR_CTRL_FLAG_INLINE' ],
+	[ 'HAVE_MLX5_DR_FLOW_DUMP_RULE', 'infiniband/mlx5dv.h',
+	    'mlx5dv_dump_dr_rule' ],
+	[ 'HAVE_MLX5_DR_ACTION_ASO_CT', 'infiniband/mlx5dv.h',
+	    'MLX5DV_DR_ACTION_FLAGS_ASO_CT_DIRECTION_INITIATOR' ],
+	[ 'HAVE_MLX5_DR_ALLOW_DUPLICATE', 'infiniband/mlx5dv.h',
+	    'mlx5dv_dr_domain_allow_duplicate_rules' ],
+]
+config = configuration_data()
+foreach arg:has_sym_args
+    config.set(arg[0], cc.has_header_symbol(arg[1], arg[2], dependencies: libs))
+endforeach
+foreach arg:has_member_args
+    file_prefix = '#include <' + arg[1] + '>'
+    config.set(arg[0], cc.has_member(arg[2], arg[3], prefix : file_prefix, dependencies: libs))
+endforeach
+configure_file(output : 'mlx5_autoconf.h', configuration : config)
+
+# Build Glue Library
+if dlopen_ibverbs
+    dlopen_name = 'mlx5_glue'
+    dlopen_lib_name = 'rte_common_' + dlopen_name
+    dlopen_so_version = LIB_GLUE_VERSION
+    dlopen_sources = files('mlx5_glue.c')
+    dlopen_install_dir = [ eal_pmd_path + '-glue' ]
+    dlopen_includes = [global_inc]
+    dlopen_includes += include_directories('../../../../lib/eal/include/generic')
+    shared_lib = shared_library(
+	    dlopen_lib_name,
+	    dlopen_sources,
+	    include_directories: dlopen_includes,
+	    c_args: cflags,
+	    dependencies: libs,
+	    link_args: [
+		'-Wl,-export-dynamic',
+		'-Wl,-h,@0@'.format(LIB_GLUE),
+	    ],
+	    soversion: dlopen_so_version,
+	    install: true,
+	    install_dir: dlopen_install_dir,
+    )
+endif
diff --git a/drivers/common/mlx5/meson.build b/drivers/common/mlx5/meson.build
index 6ddbde7e8f..8037d57d81 100644
--- a/drivers/common/mlx5/meson.build
+++ b/drivers/common/mlx5/meson.build
@@ -1,9 +1,9 @@
 # SPDX-License-Identifier: BSD-3-Clause
 # Copyright 2019 Mellanox Technologies, Ltd
 
-if not (is_linux or (is_windows and is_ms_linker))
+if not (is_linux or (is_windows and is_ms_linker) or is_freebsd)
     build = false
-    reason = 'only supported on Linux and Windows build with clang'
+    reason = 'only supported on Linux, Windows and FreeBSD build with clang'
     subdir_done()
 endif
 
@@ -24,8 +24,14 @@ cflags_options = [
         '-Wno-strict-prototypes',
         '-D_BSD_SOURCE',
         '-D_DEFAULT_SOURCE',
-        '-D_XOPEN_SOURCE=600',
 ]
+
+if not is_freebsd
+    cflags_options += [
+	'-D_XOPEN_SOURCE=600',
+    ]
+endif
+
 foreach option:cflags_options
     if cc.has_argument(option)
         cflags += option
diff --git a/drivers/net/mlx5/freebsd/meson.build b/drivers/net/mlx5/freebsd/meson.build
new file mode 100644
index 0000000000..8412edce78
--- /dev/null
+++ b/drivers/net/mlx5/freebsd/meson.build
@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright 2020 Mellanox Technologies, Ltd
+
+includes += include_directories('.')
+sources += files(
+	'mlx5_socket.c',
+	'mlx5_os.c',
+	'mlx5_ethdev_os.c',
+	'mlx5_verbs.c',
+	'mlx5_mp_os.c',
+	'mlx5_vlan_os.c',
+	'mlx5_flow_os.c',
+)
+
diff --git a/drivers/net/mlx5/meson.build b/drivers/net/mlx5/meson.build
index dac7f1fabf..51172adf90 100644
--- a/drivers/net/mlx5/meson.build
+++ b/drivers/net/mlx5/meson.build
@@ -2,9 +2,9 @@
 # Copyright 2018 6WIND S.A.
 # Copyright 2018 Mellanox Technologies, Ltd
 
-if not (is_linux or is_windows)
+if not (is_linux or is_windows or is_freebsd)
     build = false
-    reason = 'only supported on Linux and Windows'
+    reason = 'only supported on Linux, Windows and FreeBSD'
     subdir_done()
 endif
 
@@ -38,7 +38,7 @@ sources = files(
         'mlx5_devx.c',
 )
 
-if is_linux
+if is_linux or is_freebsd
     sources += files(
             'mlx5_flow_verbs.c',
     )
@@ -54,8 +54,14 @@ cflags_options = [
         '-Wno-strict-prototypes',
         '-D_BSD_SOURCE',
         '-D_DEFAULT_SOURCE',
-        '-D_XOPEN_SOURCE=600',
 ]
+
+if not is_freebsd
+    cflags_options += [
+	    '-D_XOPEN_SOURCE=600',
+    ]
+endif
+
 foreach option:cflags_options
     if cc.has_argument(option)
         cflags += option
-- 
2.30.2

Re: [dpdk-dev] [PATCH 00/19] MLX5 FreeBSD support

[Thomas Monjalon]

27/09/2021 15:34, Srikanth Kaka:
> This patch series adds support for MLX5 PMD on FreeBSD
> 
>  drivers/common/mlx5/freebsd/meson.build       |  189 ++
>  drivers/common/mlx5/freebsd/mlx5_common_os.c  |  387 +++
>  drivers/common/mlx5/freebsd/mlx5_common_os.h  |  304 ++
>  .../common/mlx5/freebsd/mlx5_common_verbs.c   |   90 +
>  drivers/common/mlx5/freebsd/mlx5_glue.c       | 1505 ++++++++++
>  drivers/common/mlx5/freebsd/mlx5_glue.h       |  374 +++
>  drivers/common/mlx5/freebsd/mlx5_inet.c       |  306 ++
>  drivers/common/mlx5/freebsd/mlx5_inet.h       |   75 +
>  drivers/common/mlx5/meson.build               |   12 +-
>  drivers/net/mlx5/freebsd/meson.build          |   14 +
>  drivers/net/mlx5/freebsd/mlx5_ethdev_os.c     | 1187 ++++++++
>  drivers/net/mlx5/freebsd/mlx5_flow_os.c       |   38 +
>  drivers/net/mlx5/freebsd/mlx5_flow_os.h       |  484 +++
>  drivers/net/mlx5/freebsd/mlx5_mp_os.c         |  305 ++
>  drivers/net/mlx5/freebsd/mlx5_os.c            | 2600 +++++++++++++++++
>  drivers/net/mlx5/freebsd/mlx5_os.h            |   22 +
>  drivers/net/mlx5/freebsd/mlx5_socket.c        |  249 ++
>  drivers/net/mlx5/freebsd/mlx5_verbs.c         | 1208 ++++++++
>  drivers/net/mlx5/freebsd/mlx5_verbs.h         |   18 +
>  drivers/net/mlx5/freebsd/mlx5_vlan_os.c       |   84 +
>  drivers/net/mlx5/meson.build                  |   14 +-
>  21 files changed, 9458 insertions(+), 7 deletions(-)
>  create mode 100644 drivers/common/mlx5/freebsd/meson.build
>  create mode 100644 drivers/common/mlx5/freebsd/mlx5_common_os.c
>  create mode 100644 drivers/common/mlx5/freebsd/mlx5_common_os.h
>  create mode 100644 drivers/common/mlx5/freebsd/mlx5_common_verbs.c
>  create mode 100644 drivers/common/mlx5/freebsd/mlx5_glue.c
>  create mode 100644 drivers/common/mlx5/freebsd/mlx5_glue.h
>  create mode 100644 drivers/common/mlx5/freebsd/mlx5_inet.c
>  create mode 100644 drivers/common/mlx5/freebsd/mlx5_inet.h
>  create mode 100644 drivers/net/mlx5/freebsd/meson.build
>  create mode 100644 drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
>  create mode 100644 drivers/net/mlx5/freebsd/mlx5_flow_os.c
>  create mode 100644 drivers/net/mlx5/freebsd/mlx5_flow_os.h
>  create mode 100644 drivers/net/mlx5/freebsd/mlx5_mp_os.c
>  create mode 100644 drivers/net/mlx5/freebsd/mlx5_os.c
>  create mode 100644 drivers/net/mlx5/freebsd/mlx5_os.h
>  create mode 100644 drivers/net/mlx5/freebsd/mlx5_socket.c
>  create mode 100644 drivers/net/mlx5/freebsd/mlx5_verbs.c
>  create mode 100644 drivers/net/mlx5/freebsd/mlx5_verbs.h
>  create mode 100644 drivers/net/mlx5/freebsd/mlx5_vlan_os.c

That's a lot of new code, thanks for the effort.
Please could you summarize which features are supported,
what are the dependencies, and how is it tested?

Re: [dpdk-dev] [PATCH 00/19] MLX5 FreeBSD support

[Srikanth K]

Hi Thomas,

PFA the test report. It covers all the features that were tested across
various platforms.

The features mentioned in the test report depend on a modified FreeBSD
OFED. There is an ongoing review of these changes by the FreeBSD community.
https://reviews.freebsd.org/p/vag.singh_oneconvergence.com/

Regards,
Srikanth


On Wed, Sep 29, 2021 at 5:50 PM Thomas Monjalon <thomas@monjalon.net> wrote:

> 27/09/2021 15:34, Srikanth Kaka:
> > This patch series adds support for MLX5 PMD on FreeBSD
> >
> >  drivers/common/mlx5/freebsd/meson.build       |  189 ++
> >  drivers/common/mlx5/freebsd/mlx5_common_os.c  |  387 +++
> >  drivers/common/mlx5/freebsd/mlx5_common_os.h  |  304 ++
> >  .../common/mlx5/freebsd/mlx5_common_verbs.c   |   90 +
> >  drivers/common/mlx5/freebsd/mlx5_glue.c       | 1505 ++++++++++
> >  drivers/common/mlx5/freebsd/mlx5_glue.h       |  374 +++
> >  drivers/common/mlx5/freebsd/mlx5_inet.c       |  306 ++
> >  drivers/common/mlx5/freebsd/mlx5_inet.h       |   75 +
> >  drivers/common/mlx5/meson.build               |   12 +-
> >  drivers/net/mlx5/freebsd/meson.build          |   14 +
> >  drivers/net/mlx5/freebsd/mlx5_ethdev_os.c     | 1187 ++++++++
> >  drivers/net/mlx5/freebsd/mlx5_flow_os.c       |   38 +
> >  drivers/net/mlx5/freebsd/mlx5_flow_os.h       |  484 +++
> >  drivers/net/mlx5/freebsd/mlx5_mp_os.c         |  305 ++
> >  drivers/net/mlx5/freebsd/mlx5_os.c            | 2600 +++++++++++++++++
> >  drivers/net/mlx5/freebsd/mlx5_os.h            |   22 +
> >  drivers/net/mlx5/freebsd/mlx5_socket.c        |  249 ++
> >  drivers/net/mlx5/freebsd/mlx5_verbs.c         | 1208 ++++++++
> >  drivers/net/mlx5/freebsd/mlx5_verbs.h         |   18 +
> >  drivers/net/mlx5/freebsd/mlx5_vlan_os.c       |   84 +
> >  drivers/net/mlx5/meson.build                  |   14 +-
> >  21 files changed, 9458 insertions(+), 7 deletions(-)
> >  create mode 100644 drivers/common/mlx5/freebsd/meson.build
> >  create mode 100644 drivers/common/mlx5/freebsd/mlx5_common_os.c
> >  create mode 100644 drivers/common/mlx5/freebsd/mlx5_common_os.h
> >  create mode 100644 drivers/common/mlx5/freebsd/mlx5_common_verbs.c
> >  create mode 100644 drivers/common/mlx5/freebsd/mlx5_glue.c
> >  create mode 100644 drivers/common/mlx5/freebsd/mlx5_glue.h
> >  create mode 100644 drivers/common/mlx5/freebsd/mlx5_inet.c
> >  create mode 100644 drivers/common/mlx5/freebsd/mlx5_inet.h
> >  create mode 100644 drivers/net/mlx5/freebsd/meson.build
> >  create mode 100644 drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
> >  create mode 100644 drivers/net/mlx5/freebsd/mlx5_flow_os.c
> >  create mode 100644 drivers/net/mlx5/freebsd/mlx5_flow_os.h
> >  create mode 100644 drivers/net/mlx5/freebsd/mlx5_mp_os.c
> >  create mode 100644 drivers/net/mlx5/freebsd/mlx5_os.c
> >  create mode 100644 drivers/net/mlx5/freebsd/mlx5_os.h
> >  create mode 100644 drivers/net/mlx5/freebsd/mlx5_socket.c
> >  create mode 100644 drivers/net/mlx5/freebsd/mlx5_verbs.c
> >  create mode 100644 drivers/net/mlx5/freebsd/mlx5_verbs.h
> >  create mode 100644 drivers/net/mlx5/freebsd/mlx5_vlan_os.c
>
> That's a lot of new code, thanks for the effort.
> Please could you summarize which features are supported,
> what are the dependencies, and how is it tested?
>
>
>

Re: [dpdk-dev] [PATCH 00/19] MLX5 FreeBSD support

[Thomas Monjalon]

29/09/2021 17:56, Srikanth K:
> Hi Thomas,
> 
> PFA the test report. It covers all the features that were tested across
> various platforms.
> 
> The features mentioned in the test report depend on a modified FreeBSD
> OFED. There is an ongoing review of these changes by the FreeBSD community.
> https://reviews.freebsd.org/p/vag.singh_oneconvergence.com/

OK, this dependency is very important to notify in this patchset.
For next version, please add it in the cover letter.

The supported features (MTU, MAC, VLAN, RSS, fragments, jumbo, stats
and trust mode) should be listed in the cover letter as well as
in the mlx5 documentation. Please follow what was done for Windows.

About the patches organization, please do not fix or remove something
which was added in a previous patch. You need to have logical steps
done in each patch without going backward.
Please start with enabling compilation in first patch,
so each step can be tested.

Thanks

Re: [dpdk-dev] [PATCH 00/19] MLX5 FreeBSD support

[Srikanth K]

Sure, I will follow the Windows support approach.

Regarding the patches organization, they were arranged logically to the
best of my knowledge.
The approach followed is to take Linux PMD code and replace the Linux
dependent part with the
FreeBSD compatible code. All the removals are of this Linux dependent code.
For the same reason,
FreeBSD meson support is added in the last patch or otherwise Linux code
would break compilation
in FreeBSD.

The patches status is still "New" on the DPDK site, please let me know when
I can submit the next version.

Regards,
Srikanth


On Wed, Sep 29, 2021 at 9:50 PM Thomas Monjalon <thomas@monjalon.net> wrote:

> 29/09/2021 17:56, Srikanth K:
> > Hi Thomas,
> >
> > PFA the test report. It covers all the features that were tested across
> > various platforms.
> >
> > The features mentioned in the test report depend on a modified FreeBSD
> > OFED. There is an ongoing review of these changes by the FreeBSD
> community.
> > https://reviews.freebsd.org/p/vag.singh_oneconvergence.com/
>
> OK, this dependency is very important to notify in this patchset.
> For next version, please add it in the cover letter.
>
> The supported features (MTU, MAC, VLAN, RSS, fragments, jumbo, stats
> and trust mode) should be listed in the cover letter as well as
> in the mlx5 documentation. Please follow what was done for Windows.
>
> About the patches organization, please do not fix or remove something
> which was added in a previous patch. You need to have logical steps
> done in each patch without going backward.
> Please start with enabling compilation in first patch,
> so each step can be tested.
>
> Thanks
>
>
>

Re: [dpdk-dev] [PATCH 00/19] MLX5 FreeBSD support

[Thomas Monjalon]

30/09/2021 18:27, Srikanth K:
> Sure, I will follow the Windows support approach.
> 
> Regarding the patches organization, they were arranged logically to the
> best of my knowledge.

It is not.

> The approach followed is to take Linux PMD code and replace the Linux
> dependent part with the
> FreeBSD compatible code. All the removals are of this Linux dependent code.

The removals are in the directory drivers/net/mlx5/freebsd/
That's simple: don't add code that you remove later.

> For the same reason,
> FreeBSD meson support is added in the last patch or otherwise Linux code
> would break compilation
> in FreeBSD.

Simple: add only code which compiles.

> The patches status is still "New" on the DPDK site, please let me know when
> I can submit the next version.

You can submit new versions and mark old ones as superseded.
The full process is described in the contributing guide,
please read it carefully.


> On Wed, Sep 29, 2021 at 9:50 PM Thomas Monjalon <thomas@monjalon.net> wrote:
> 
> > 29/09/2021 17:56, Srikanth K:
> > > Hi Thomas,
> > >
> > > PFA the test report. It covers all the features that were tested across
> > > various platforms.
> > >
> > > The features mentioned in the test report depend on a modified FreeBSD
> > > OFED. There is an ongoing review of these changes by the FreeBSD
> > community.
> > > https://reviews.freebsd.org/p/vag.singh_oneconvergence.com/
> >
> > OK, this dependency is very important to notify in this patchset.
> > For next version, please add it in the cover letter.
> >
> > The supported features (MTU, MAC, VLAN, RSS, fragments, jumbo, stats
> > and trust mode) should be listed in the cover letter as well as
> > in the mlx5 documentation. Please follow what was done for Windows.
> >
> > About the patches organization, please do not fix or remove something
> > which was added in a previous patch. You need to have logical steps
> > done in each patch without going backward.
> > Please start with enabling compilation in first patch,
> > so each step can be tested.
> >
> > Thanks
> >
> >
> >
> 

Re: [dpdk-dev] [PATCH 00/19] MLX5 FreeBSD support

[Srikanth K]

Got it, thanks for the clarification.

Regards,
Srikanth


On Thu, Sep 30, 2021 at 10:25 PM Thomas Monjalon <thomas@monjalon.net>
wrote:

> 30/09/2021 18:27, Srikanth K:
> > Sure, I will follow the Windows support approach.
> >
> > Regarding the patches organization, they were arranged logically to the
> > best of my knowledge.
>
> It is not.
>
> > The approach followed is to take Linux PMD code and replace the Linux
> > dependent part with the
> > FreeBSD compatible code. All the removals are of this Linux dependent
> code.
>
> The removals are in the directory drivers/net/mlx5/freebsd/
> That's simple: don't add code that you remove later.
>
> > For the same reason,
> > FreeBSD meson support is added in the last patch or otherwise Linux code
> > would break compilation
> > in FreeBSD.
>
> Simple: add only code which compiles.
>
> > The patches status is still "New" on the DPDK site, please let me know
> when
> > I can submit the next version.
>
> You can submit new versions and mark old ones as superseded.
> The full process is described in the contributing guide,
> please read it carefully.
>
>
> > On Wed, Sep 29, 2021 at 9:50 PM Thomas Monjalon <thomas@monjalon.net>
> wrote:
> >
> > > 29/09/2021 17:56, Srikanth K:
> > > > Hi Thomas,
> > > >
> > > > PFA the test report. It covers all the features that were tested
> across
> > > > various platforms.
> > > >
> > > > The features mentioned in the test report depend on a modified
> FreeBSD
> > > > OFED. There is an ongoing review of these changes by the FreeBSD
> > > community.
> > > > https://reviews.freebsd.org/p/vag.singh_oneconvergence.com/
> > >
> > > OK, this dependency is very important to notify in this patchset.
> > > For next version, please add it in the cover letter.
> > >
> > > The supported features (MTU, MAC, VLAN, RSS, fragments, jumbo, stats
> > > and trust mode) should be listed in the cover letter as well as
> > > in the mlx5 documentation. Please follow what was done for Windows.
> > >
> > > About the patches organization, please do not fix or remove something
> > > which was added in a previous patch. You need to have logical steps
> > > done in each patch without going backward.
> > > Please start with enabling compilation in first patch,
> > > so each step can be tested.
> > >
> > > Thanks
> > >
> > >
> > >
> >
>
>
>
>
>
>