Merge tag 'mlx5-updates-2019-02-15' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
Support Mellanox BlueField SmartNIC (mlx5-updates-2019-02-15)

Bodong Wang says,

BlueField device is a multi-core ARM processor in a highly integrated
system on chip coupled with the ConnectX interconnect controller.
BlueField device can be presented in one out of two modes:

- SEPARATED_HOST: ARM processors as a separated and orthogonal host
  like any other external host in the multi-host virtualization model.
- EMBEDDED_CPU: ARM processors as Embedded CPU (EC) and part of the
  external hosts virtualization model.

While existing driver already supports the device on separated_host
mode, this patch series focus on the functionalities of embedded_cpu
mode.

On embedded_cpu mode, BlueField device exposes regular network
controller PCI function in the BlueField host(e.g, x86). However, a
separate PCI function called Embedded CPU Physical Function(ECPF) is
also added to the ARM host side, where standard Linux distributions is
able to run on the ARM cores. Depends on the NV configuration from
firmware, ECPF can be the e-switch manager and firmware pages supplier.
If ECPF is configured as e-switch manager and page supplier, it will
take over the responsibilities from the PF on BlueField host includes:
- Owns, controls and manages all e-switch parts, and takes e-switch
  traffic by default. It also should perform ENABLE_HCA for the host
  PF just like a PF does for its VFs.
- Provides and manages the ICM host memory required for the HCA to
  store various contexts for itself, the PF and VFs belong the
  e-switch it manages.

The PF on BlueField host side is still responsible for:
- Control its own permanent MAC.
- PCI and SRIOV configurations and perform ENABLE_HCA for its VFs.

The ECPF can also retrieve information about the external host it
controls, like host identifier, PCI BDF and number of virtual functions.
As these parameters may be changed dynamically, an event will be triggered
to the driver on ECPF side.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

24 files changed, 1110 insertions, 485 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 6bb2a860b15b..82d636baaa4e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -13,7 +13,7 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o
 #
 mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		health.o mcg.o cq.o alloc.o qp.o port.o mr.o pd.o \
-		mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
+		transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
 		fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \
 		lib/devcom.o diag/fs_tracepoint.o diag/fw_tracer.o
 
@@ -35,7 +35,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o en/tc_tun.o
 #
 # Core extra
 #
-mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o
+mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o ecpf.o
 mlx5_core-$(CONFIG_MLX5_MPFS)      += lib/mpfs.o
 mlx5_core-$(CONFIG_VXLAN)          += lib/vxlan.o
 mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index e267ff93e8a8..be48c6440251 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -316,6 +316,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_DESTROY_GENERAL_OBJECT:
 	case MLX5_CMD_OP_DEALLOC_MEMIC:
 	case MLX5_CMD_OP_PAGE_FAULT_RESUME:
+	case MLX5_CMD_OP_QUERY_HOST_PARAMS:
 		return MLX5_CMD_STAT_OK;
 
 	case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -627,6 +628,7 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(QUERY_MODIFY_HEADER_CONTEXT);
 	MLX5_COMMAND_STR_CASE(ALLOC_MEMIC);
 	MLX5_COMMAND_STR_CASE(DEALLOC_MEMIC);
+	MLX5_COMMAND_STR_CASE(QUERY_HOST_PARAMS);
 	default: return "unknown command opcode";
 	}
 }
@@ -1729,12 +1731,57 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 }
 EXPORT_SYMBOL(mlx5_cmd_exec);
 
-int mlx5_cmd_exec_cb(struct mlx5_core_dev *dev, void *in, int in_size,
-		     void *out, int out_size, mlx5_cmd_cbk_t callback,
-		     void *context)
+void mlx5_cmd_init_async_ctx(struct mlx5_core_dev *dev,
+			     struct mlx5_async_ctx *ctx)
 {
-	return cmd_exec(dev, in, in_size, out, out_size, callback, context,
-			false);
+	ctx->dev = dev;
+	/* Starts at 1 to avoid doing wake_up if we are not cleaning up */
+	atomic_set(&ctx->num_inflight, 1);
+	init_waitqueue_head(&ctx->wait);
+}
+EXPORT_SYMBOL(mlx5_cmd_init_async_ctx);
+
+/**
+ * mlx5_cmd_cleanup_async_ctx - Clean up an async_ctx
+ * @ctx: The ctx to clean
+ *
+ * Upon return all callbacks given to mlx5_cmd_exec_cb() have been called. The
+ * caller must ensure that mlx5_cmd_exec_cb() is not called during or after
+ * the call mlx5_cleanup_async_ctx().
+ */
+void mlx5_cmd_cleanup_async_ctx(struct mlx5_async_ctx *ctx)
+{
+	atomic_dec(&ctx->num_inflight);
+	wait_event(ctx->wait, atomic_read(&ctx->num_inflight) == 0);
+}
+EXPORT_SYMBOL(mlx5_cmd_cleanup_async_ctx);
+
+static void mlx5_cmd_exec_cb_handler(int status, void *_work)
+{
+	struct mlx5_async_work *work = _work;
+	struct mlx5_async_ctx *ctx = work->ctx;
+
+	work->user_callback(status, work);
+	if (atomic_dec_and_test(&ctx->num_inflight))
+		wake_up(&ctx->wait);
+}
+
+int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
+		     void *out, int out_size, mlx5_async_cbk_t callback,
+		     struct mlx5_async_work *work)
+{
+	int ret;
+
+	work->ctx = ctx;
+	work->user_callback = callback;
+	if (WARN_ON(!atomic_inc_not_zero(&ctx->num_inflight)))
+		return -EIO;
+	ret = cmd_exec(ctx->dev, in, in_size, out, out_size,
+		       mlx5_cmd_exec_cb_handler, work, false);
+	if (ret && atomic_dec_and_test(&ctx->num_inflight))
+		wake_up(&ctx->wait);
+
+	return ret;
 }
 EXPORT_SYMBOL(mlx5_cmd_exec_cb);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
new file mode 100644
index 000000000000..4746f2d28fb6
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
@@ -0,0 +1,112 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "ecpf.h"
+
+bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev)
+{
+	return (ioread32be(&dev->iseg->initializing) >> MLX5_ECPU_BIT_NUM) & 1;
+}
+
+static int mlx5_peer_pf_enable_hca(struct mlx5_core_dev *dev)
+{
+	u32 out[MLX5_ST_SZ_DW(enable_hca_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(enable_hca_in)]   = {};
+
+	MLX5_SET(enable_hca_in, in, opcode, MLX5_CMD_OP_ENABLE_HCA);
+	MLX5_SET(enable_hca_in, in, function_id, 0);
+	MLX5_SET(enable_hca_in, in, embedded_cpu_function, 0);
+	return mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
+}
+
+static int mlx5_peer_pf_disable_hca(struct mlx5_core_dev *dev)
+{
+	u32 out[MLX5_ST_SZ_DW(disable_hca_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(disable_hca_in)]   = {};
+
+	MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA);
+	MLX5_SET(disable_hca_in, in, function_id, 0);
+	MLX5_SET(enable_hca_in, in, embedded_cpu_function, 0);
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
+static int mlx5_peer_pf_init(struct mlx5_core_dev *dev)
+{
+	int err;
+
+	err = mlx5_peer_pf_enable_hca(dev);
+	if (err)
+		mlx5_core_err(dev, "Failed to enable peer PF HCA err(%d)\n",
+			      err);
+
+	return err;
+}
+
+static void mlx5_peer_pf_cleanup(struct mlx5_core_dev *dev)
+{
+	int err;
+
+	err = mlx5_peer_pf_disable_hca(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to disable peer PF HCA err(%d)\n",
+			      err);
+		return;
+	}
+
+	err = mlx5_wait_for_pages(dev, &dev->priv.peer_pf_pages);
+	if (err)
+		mlx5_core_warn(dev, "Timeout reclaiming peer PF pages err(%d)\n",
+			       err);
+}
+
+int mlx5_ec_init(struct mlx5_core_dev *dev)
+{
+	int err = 0;
+
+	if (!mlx5_core_is_ecpf(dev))
+		return 0;
+
+	/* ECPF shall enable HCA for peer PF in the same way a PF
+	 * does this for its VFs.
+	 */
+	err = mlx5_peer_pf_init(dev);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+void mlx5_ec_cleanup(struct mlx5_core_dev *dev)
+{
+	if (!mlx5_core_is_ecpf(dev))
+		return;
+
+	mlx5_peer_pf_cleanup(dev);
+}
+
+static int mlx5_query_host_params_context(struct mlx5_core_dev *dev,
+					  u32 *out, int outlen)
+{
+	u32 in[MLX5_ST_SZ_DW(query_host_params_in)] = {};
+
+	MLX5_SET(query_host_params_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_HOST_PARAMS);
+
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+}
+
+int mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf)
+{
+	u32 out[MLX5_ST_SZ_DW(query_host_params_out)] = {};
+	int err;
+
+	err = mlx5_query_host_params_context(dev, out, sizeof(out));
+	if (err)
+		return err;
+
+	*num_vf = MLX5_GET(query_host_params_out, out,
+			   host_params_context.host_num_of_vfs);
+	mlx5_core_dbg(dev, "host_num_of_vfs %d\n", *num_vf);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h
new file mode 100644
index 000000000000..346372df218f
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_ECPF_H__
+#define __MLX5_ECPF_H__
+
+#include <linux/mlx5/driver.h>
+#include "mlx5_core.h"
+
+#ifdef CONFIG_MLX5_ESWITCH
+
+enum {
+	MLX5_ECPU_BIT_NUM = 23,
+};
+
+bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev);
+int mlx5_ec_init(struct mlx5_core_dev *dev);
+void mlx5_ec_cleanup(struct mlx5_core_dev *dev);
+int mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf);
+
+#else  /* CONFIG_MLX5_ESWITCH */
+
+static inline bool
+mlx5_read_embedded_cpu(struct mlx5_core_dev *dev) { return false; }
+static inline int mlx5_ec_init(struct mlx5_core_dev *dev) { return 0; }
+static inline void mlx5_ec_cleanup(struct mlx5_core_dev *dev) {}
+static inline int
+mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf)
+{ return -EOPNOTSUPP; }
+
+#endif /* CONFIG_MLX5_ESWITCH */
+
+#endif /* __MLX5_ECPF_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index 4a37713023be..122927f3a600 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -63,66 +63,168 @@ static const u32 mlx5e_link_speed[MLX5E_LINK_MODES_NUMBER] = {
 	[MLX5E_50GBASE_KR2]       = 50000,
 };
 
-u32 mlx5e_port_ptys2speed(u32 eth_proto_oper)
+static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = {
+	[MLX5E_SGMII_100M]			= 100,
+	[MLX5E_1000BASE_X_SGMII]		= 1000,
+	[MLX5E_5GBASE_R]			= 5000,
+	[MLX5E_10GBASE_XFI_XAUI_1]		= 10000,
+	[MLX5E_40GBASE_XLAUI_4_XLPPI_4]		= 40000,
+	[MLX5E_25GAUI_1_25GBASE_CR_KR]		= 25000,
+	[MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2]	= 50000,
+	[MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR]	= 50000,
+	[MLX5E_CAUI_4_100GBASE_CR4_KR4]		= 100000,
+	[MLX5E_200GAUI_4_200GBASE_CR4_KR4]	= 200000,
+	[MLX5E_400GAUI_8]			= 400000,
+};
+
+static void mlx5e_port_get_speed_arr(struct mlx5_core_dev *mdev,
+				     const u32 **arr, u32 *size)
+{
+	bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+
+	*size = ext ? ARRAY_SIZE(mlx5e_ext_link_speed) :
+		      ARRAY_SIZE(mlx5e_link_speed);
+	*arr  = ext ? mlx5e_ext_link_speed : mlx5e_link_speed;
+}
+
+int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
+			      struct mlx5e_port_eth_proto *eproto)
+{
+	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
+	int err;
+
+	if (!eproto)
+		return -EINVAL;
+
+	if (ext !=  MLX5_CAP_PCAM_FEATURE(dev, ptys_extended_ethernet))
+		return -EOPNOTSUPP;
+
+	err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, port);
+	if (err)
+		return err;
+
+	eproto->cap   = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
+					   eth_proto_capability);
+	eproto->admin = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_admin);
+	eproto->oper  = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_oper);
+	return 0;
+}
+
+void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status,
+				 u8 *an_disable_cap, u8 *an_disable_admin)
+{
+	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
+
+	*an_status = 0;
+	*an_disable_cap = 0;
+	*an_disable_admin = 0;
+
+	if (mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, 1))
+		return;
+
+	*an_status = MLX5_GET(ptys_reg, out, an_status);
+	*an_disable_cap = MLX5_GET(ptys_reg, out, an_disable_cap);
+	*an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin);
+}
+
+int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable,
+			   u32 proto_admin, bool ext)
+{
+	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
+	u32 in[MLX5_ST_SZ_DW(ptys_reg)];
+	u8 an_disable_admin;
+	u8 an_disable_cap;
+	u8 an_status;
+
+	mlx5_port_query_eth_autoneg(dev, &an_status, &an_disable_cap,
+				    &an_disable_admin);
+	if (!an_disable_cap && an_disable)
+		return -EPERM;
+
+	memset(in, 0, sizeof(in));
+
+	MLX5_SET(ptys_reg, in, local_port, 1);
+	MLX5_SET(ptys_reg, in, an_disable_admin, an_disable);
+	MLX5_SET(ptys_reg, in, proto_mask, MLX5_PTYS_EN);
+	if (ext)
+		MLX5_SET(ptys_reg, in, ext_eth_proto_admin, proto_admin);
+	else
+		MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin);
+
+	return mlx5_core_access_reg(dev, in, sizeof(in), out,
+			    sizeof(out), MLX5_REG_PTYS, 0, 1);
+}
+
+u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper)
 {
 	unsigned long temp = eth_proto_oper;
+	const u32 *table;
 	u32 speed = 0;
+	u32 max_size;
 	int i;
 
-	i = find_first_bit(&temp, MLX5E_LINK_MODES_NUMBER);
-	if (i < MLX5E_LINK_MODES_NUMBER)
-		speed = mlx5e_link_speed[i];
-
+	mlx5e_port_get_speed_arr(mdev, &table, &max_size);
+	i = find_first_bit(&temp, max_size);
+	if (i < max_size)
+		speed = table[i];
 	return speed;
 }
 
 int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 {
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {};
-	u32 eth_proto_oper;
+	struct mlx5e_port_eth_proto eproto;
+	bool ext;
 	int err;
 
-	err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN, 1);
+	ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
 	if (err)
-		return err;
+		goto out;
 
-	eth_proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper);
-	*speed = mlx5e_port_ptys2speed(eth_proto_oper);
+	*speed = mlx5e_port_ptys2speed(mdev, eproto.oper);
 	if (!(*speed))
 		err = -EINVAL;
 
+out:
 	return err;
 }
 
 int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 {
+	struct mlx5e_port_eth_proto eproto;
 	u32 max_speed = 0;
-	u32 proto_cap;
+	const u32 *table;
+	u32 max_size;
+	bool ext;
 	int err;
 	int i;
 
-	err = mlx5_query_port_proto_cap(mdev, &proto_cap, MLX5_PTYS_EN);
+	ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
 	if (err)
 		return err;
 
-	for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i)
-		if (proto_cap & MLX5E_PROT_MASK(i))
-			max_speed = max(max_speed, mlx5e_link_speed[i]);
+	mlx5e_port_get_speed_arr(mdev, &table, &max_size);
+	for (i = 0; i < max_size; ++i)
+		if (eproto.cap & MLX5E_PROT_MASK(i))
+			max_speed = max(max_speed, table[i]);
 
 	*speed = max_speed;
 	return 0;
 }
 
-u32 mlx5e_port_speed2linkmodes(u32 speed)
+u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed)
 {
 	u32 link_modes = 0;
+	const u32 *table;
+	u32 max_size;
 	int i;
 
-	for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) {
-		if (mlx5e_link_speed[i] == speed)
+	mlx5e_port_get_speed_arr(mdev, &table, &max_size);
+	for (i = 0; i < max_size; ++i) {
+		if (table[i] == speed)
 			link_modes |= MLX5E_PROT_MASK(i);
 	}
-
 	return link_modes;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
index cd2160b8c9bf..70f536ec51c4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
@@ -36,10 +36,22 @@
 #include <linux/mlx5/driver.h>
 #include "en.h"
 
-u32 mlx5e_port_ptys2speed(u32 eth_proto_oper);
+struct mlx5e_port_eth_proto {
+	u32 cap;
+	u32 admin;
+	u32 oper;
+};
+
+int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
+			      struct mlx5e_port_eth_proto *eproto);
+void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status,
+				 u8 *an_disable_cap, u8 *an_disable_admin);
+int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable,
+			   u32 proto_admin, bool ext);
+u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper);
 int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
 int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
-u32 mlx5e_port_speed2linkmodes(u32 speed);
+u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed);
 
 int mlx5e_port_query_pbmc(struct mlx5_core_dev *mdev, void *out);
 int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 47233b9a4f81..3cd73254d020 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -696,13 +696,14 @@ static void get_speed_duplex(struct net_device *netdev,
 			     u32 eth_proto_oper,
 			     struct ethtool_link_ksettings *link_ksettings)
 {
+	struct mlx5e_priv *priv = netdev_priv(netdev);
 	u32 speed = SPEED_UNKNOWN;
 	u8 duplex = DUPLEX_UNKNOWN;
 
 	if (!netif_carrier_ok(netdev))
 		goto out;
 
-	speed = mlx5e_port_ptys2speed(eth_proto_oper);
+	speed = mlx5e_port_ptys2speed(priv->mdev, eth_proto_oper);
 	if (!speed) {
 		speed = SPEED_UNKNOWN;
 		goto out;
@@ -886,7 +887,7 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 				     const struct ethtool_link_ksettings *link_ksettings)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
-	u32 eth_proto_cap, eth_proto_admin;
+	struct mlx5e_port_eth_proto eproto;
 	bool an_changes = false;
 	u8 an_disable_admin;
 	u8 an_disable_cap;
@@ -900,16 +901,16 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 
 	link_modes = link_ksettings->base.autoneg == AUTONEG_ENABLE ?
 		mlx5e_ethtool2ptys_adver_link(link_ksettings->link_modes.advertising) :
-		mlx5e_port_speed2linkmodes(speed);
+		mlx5e_port_speed2linkmodes(mdev, speed);
 
-	err = mlx5_query_port_proto_cap(mdev, &eth_proto_cap, MLX5_PTYS_EN);
+	err = mlx5_port_query_eth_proto(mdev, 1, false, &eproto);
 	if (err) {
-		netdev_err(priv->netdev, "%s: query port eth proto cap failed: %d\n",
+		netdev_err(priv->netdev, "%s: query port eth proto failed: %d\n",
 			   __func__, err);
 		goto out;
 	}
 
-	link_modes = link_modes & eth_proto_cap;
+	link_modes = link_modes & eproto.cap;
 	if (!link_modes) {
 		netdev_err(priv->netdev, "%s: Not supported link mode(s) requested",
 			   __func__);
@@ -917,24 +918,17 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 		goto out;
 	}
 
-	err = mlx5_query_port_proto_admin(mdev, &eth_proto_admin, MLX5_PTYS_EN);
-	if (err) {
-		netdev_err(priv->netdev, "%s: query port eth proto admin failed: %d\n",
-			   __func__, err);
-		goto out;
-	}
-
-	mlx5_query_port_autoneg(mdev, MLX5_PTYS_EN, &an_status,
-				&an_disable_cap, &an_disable_admin);
+	mlx5_port_query_eth_autoneg(mdev, &an_status, &an_disable_cap,
+				    &an_disable_admin);
 
 	an_disable = link_ksettings->base.autoneg == AUTONEG_DISABLE;
 	an_changes = ((!an_disable && an_disable_admin) ||
 		      (an_disable && !an_disable_admin));
 
-	if (!an_changes && link_modes == eth_proto_admin)
+	if (!an_changes && link_modes == eproto.admin)
 		goto out;
 
-	mlx5_set_port_ptys(mdev, an_disable, link_modes, MLX5_PTYS_EN);
+	mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, false);
 	mlx5_toggle_port_link(mdev);
 
 out:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 7b5829406d95..287d48e5b073 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -153,7 +153,7 @@ static void mlx5e_rep_update_hw_counters(struct mlx5e_priv *priv)
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
 
-	if (rep->vport == FDB_UPLINK_VPORT)
+	if (rep->vport == MLX5_VPORT_UPLINK)
 		mlx5e_uplink_rep_update_hw_counters(priv);
 	else
 		mlx5e_vf_rep_update_hw_counters(priv);
@@ -1083,7 +1083,8 @@ static int mlx5e_vf_rep_open(struct net_device *dev)
 
 	if (!mlx5_modify_vport_admin_state(priv->mdev,
 					   MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
-					   rep->vport, MLX5_VPORT_ADMIN_STATE_UP))
+					   rep->vport, 1,
+					   MLX5_VPORT_ADMIN_STATE_UP))
 		netif_carrier_on(dev);
 
 unlock:
@@ -1101,7 +1102,8 @@ static int mlx5e_vf_rep_close(struct net_device *dev)
 	mutex_lock(&priv->state_lock);
 	mlx5_modify_vport_admin_state(priv->mdev,
 				      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
-				      rep->vport, MLX5_VPORT_ADMIN_STATE_DOWN);
+				      rep->vport, 1,
+				      MLX5_VPORT_ADMIN_STATE_DOWN);
 	ret = mlx5e_close_locked(dev);
 	mutex_unlock(&priv->state_lock);
 	return ret;
@@ -1119,7 +1121,7 @@ static int mlx5e_rep_get_phys_port_name(struct net_device *dev,
 	if (ret)
 		return ret;
 
-	if (rep->vport == FDB_UPLINK_VPORT)
+	if (rep->vport == MLX5_VPORT_UPLINK)
 		ret = snprintf(buf, len, "p%d", pf_num);
 	else
 		ret = snprintf(buf, len, "pf%dvf%d", pf_num, rep->vport - 1);
@@ -1206,7 +1208,7 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv)
 		return false;
 
 	rep = rpriv->rep;
-	return (rep->vport == FDB_UPLINK_VPORT);
+	return (rep->vport == MLX5_VPORT_UPLINK);
 }
 
 static bool mlx5e_rep_has_offload_stats(const struct net_device *dev, int attr_id)
@@ -1344,7 +1346,7 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 	params->sw_mtu      = netdev->mtu;
 
 	/* SQ */
-	if (rep->vport == FDB_UPLINK_VPORT)
+	if (rep->vport == MLX5_VPORT_UPLINK)
 		params->log_sq_size = MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
 	else
 		params->log_sq_size = MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE;
@@ -1371,7 +1373,7 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev)
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct mlx5_core_dev *mdev = priv->mdev;
 
-	if (rep->vport == FDB_UPLINK_VPORT) {
+	if (rep->vport == MLX5_VPORT_UPLINK) {
 		SET_NETDEV_DEV(netdev, &priv->mdev->pdev->dev);
 		netdev->netdev_ops = &mlx5e_netdev_ops_uplink_rep;
 		/* we want a persistent mac for the uplink rep */
@@ -1401,7 +1403,7 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev)
 	netdev->hw_features    |= NETIF_F_TSO6;
 	netdev->hw_features    |= NETIF_F_RXCSUM;
 
-	if (rep->vport != FDB_UPLINK_VPORT)
+	if (rep->vport != MLX5_VPORT_UPLINK)
 		netdev->features |= NETIF_F_VLAN_CHALLENGED;
 
 	netdev->features |= netdev->hw_features;
@@ -1554,7 +1556,7 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv)
 		return err;
 	}
 
-	if (rpriv->rep->vport == FDB_UPLINK_VPORT) {
+	if (rpriv->rep->vport == MLX5_VPORT_UPLINK) {
 		uplink_priv = &rpriv->uplink_priv;
 
 		/* init shared tc flow table */
@@ -1590,7 +1592,7 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv)
 	for (tc = 0; tc < priv->profile->max_tc; tc++)
 		mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]);
 
-	if (rpriv->rep->vport == FDB_UPLINK_VPORT) {
+	if (rpriv->rep->vport == MLX5_VPORT_UPLINK) {
 		/* clean indirect TC block notifications */
 		unregister_netdevice_notifier(&rpriv->uplink_priv.netdevice_nb);
 		mlx5e_rep_indr_clean_block_privs(rpriv);
@@ -1709,7 +1711,7 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	rpriv->rep = rep;
 
 	nch = mlx5e_get_max_num_channels(dev);
-	profile = (rep->vport == FDB_UPLINK_VPORT) ? &mlx5e_uplink_rep_profile : &mlx5e_vf_rep_profile;
+	profile = (rep->vport == MLX5_VPORT_UPLINK) ? &mlx5e_uplink_rep_profile : &mlx5e_vf_rep_profile;
 	netdev = mlx5e_create_netdev(dev, profile, nch, rpriv);
 	if (!netdev) {
 		pr_warn("Failed to create representor netdev for vport %d\n",
@@ -1722,7 +1724,7 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	rep->rep_if[REP_ETH].priv = rpriv;
 	INIT_LIST_HEAD(&rpriv->vport_sqs_list);
 
-	if (rep->vport == FDB_UPLINK_VPORT) {
+	if (rep->vport == MLX5_VPORT_UPLINK) {
 		err = mlx5e_create_mdev_resources(dev);
 		if (err)
 			goto err_destroy_netdev;
@@ -1758,7 +1760,7 @@ err_detach_netdev:
 	mlx5e_detach_netdev(netdev_priv(netdev));
 
 err_destroy_mdev_resources:
-	if (rep->vport == FDB_UPLINK_VPORT)
+	if (rep->vport == MLX5_VPORT_UPLINK)
 		mlx5e_destroy_mdev_resources(dev);
 
 err_destroy_netdev:
@@ -1778,7 +1780,7 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep)
 	unregister_netdev(netdev);
 	mlx5e_rep_neigh_cleanup(rpriv);
 	mlx5e_detach_netdev(priv);
-	if (rep->vport == FDB_UPLINK_VPORT)
+	if (rep->vport == MLX5_VPORT_UPLINK)
 		mlx5e_destroy_mdev_resources(priv->mdev);
 	mlx5e_destroy_netdev(priv);
 	kfree(ppriv); /* mlx5e_rep_priv */
@@ -1796,25 +1798,18 @@ static void *mlx5e_vport_rep_get_proto_dev(struct mlx5_eswitch_rep *rep)
 void mlx5e_rep_register_vport_reps(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_eswitch *esw = mdev->priv.eswitch;
-	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
-	int vport;
+	struct mlx5_eswitch_rep_if rep_if = {};
 
-	for (vport = 0; vport < total_vfs; vport++) {
-		struct mlx5_eswitch_rep_if rep_if = {};
+	rep_if.load = mlx5e_vport_rep_load;
+	rep_if.unload = mlx5e_vport_rep_unload;
+	rep_if.get_proto_dev = mlx5e_vport_rep_get_proto_dev;
 
-		rep_if.load = mlx5e_vport_rep_load;
-		rep_if.unload = mlx5e_vport_rep_unload;
-		rep_if.get_proto_dev = mlx5e_vport_rep_get_proto_dev;
-		mlx5_eswitch_register_vport_rep(esw, vport, &rep_if, REP_ETH);
-	}
+	mlx5_eswitch_register_vport_reps(esw, &rep_if, REP_ETH);
 }
 
 void mlx5e_rep_unregister_vport_reps(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_eswitch *esw = mdev->priv.eswitch;
-	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
-	int vport;
 
-	for (vport = total_vfs - 1; vport >= 0; vport--)
-		mlx5_eswitch_unregister_vport_rep(esw, vport, REP_ETH);
+	mlx5_eswitch_unregister_vport_reps(esw, REP_ETH);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index e9437757cad7..05892fc4e03f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1776,7 +1776,7 @@ static int parse_cls_flower(struct mlx5e_priv *priv,
 
 	if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH)) {
 		rep = rpriv->rep;
-		if (rep->vport != FDB_UPLINK_VPORT &&
+		if (rep->vport != MLX5_VPORT_UPLINK &&
 		    (esw->offloads.inline_mode != MLX5_INLINE_MODE_NONE &&
 		    esw->offloads.inline_mode < match_level)) {
 			NL_SET_ERR_MSG_MOD(extack,
@@ -2693,7 +2693,7 @@ static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv, int flags)
 static bool is_peer_flow_needed(struct mlx5e_tc_flow *flow)
 {
 	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
-	bool is_rep_ingress = attr->in_rep->vport != FDB_UPLINK_VPORT &&
+	bool is_rep_ingress = attr->in_rep->vport != MLX5_VPORT_UPLINK &&
 			      flow->flags & MLX5E_TC_FLOW_INGRESS;
 	bool act_is_encap = !!(attr->action &
 			       MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT);
@@ -2816,7 +2816,7 @@ static int mlx5e_tc_add_fdb_peer_flow(struct tc_cls_flower_offload *f,
 	 * original flow and packets redirected from uplink use the
 	 * peer mdev.
 	 */
-	if (flow->esw_attr->in_rep->vport == FDB_UPLINK_VPORT)
+	if (flow->esw_attr->in_rep->vport == MLX5_VPORT_UPLINK)
 		in_mdev = peer_priv->mdev;
 	else
 		in_mdev = priv->mdev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index ee04aab65a9f..bb6e5b5d9681 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -34,6 +34,7 @@
 #include <linux/notifier.h>
 #include <linux/module.h>
 #include <linux/mlx5/driver.h>
+#include <linux/mlx5/vport.h>
 #include <linux/mlx5/eq.h>
 #include <linux/mlx5/cmd.h>
 #ifdef CONFIG_RFS_ACCEL
@@ -114,11 +115,11 @@ static struct mlx5_core_cq *mlx5_eq_cq_get(struct mlx5_eq *eq, u32 cqn)
 	struct mlx5_cq_table *table = &eq->cq_table;
 	struct mlx5_core_cq *cq = NULL;
 
-	spin_lock(&table->lock);
+	rcu_read_lock();
 	cq = radix_tree_lookup(&table->tree, cqn);
 	if (likely(cq))
 		mlx5_cq_hold(cq);
-	spin_unlock(&table->lock);
+	rcu_read_unlock();
 
 	return cq;
 }
@@ -371,9 +372,9 @@ int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq)
 	struct mlx5_cq_table *table = &eq->cq_table;
 	int err;
 
-	spin_lock_irq(&table->lock);
+	spin_lock(&table->lock);
 	err = radix_tree_insert(&table->tree, cq->cqn, cq);
-	spin_unlock_irq(&table->lock);
+	spin_unlock(&table->lock);
 
 	return err;
 }
@@ -383,9 +384,9 @@ int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq)
 	struct mlx5_cq_table *table = &eq->cq_table;
 	struct mlx5_core_cq *tmp;
 
-	spin_lock_irq(&table->lock);
+	spin_lock(&table->lock);
 	tmp = radix_tree_delete(&table->tree, cq->cqn);
-	spin_unlock_irq(&table->lock);
+	spin_unlock(&table->lock);
 
 	if (!tmp) {
 		mlx5_core_warn(eq->dev, "cq 0x%x not found in eq 0x%x tree\n", eq->eqn, cq->cqn);
@@ -530,6 +531,9 @@ static u64 gather_async_events_mask(struct mlx5_core_dev *dev)
 	if (MLX5_CAP_GEN(dev, max_num_of_monitor_counters))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_MONITOR_COUNTER);
 
+	if (mlx5_core_is_ecpf_esw_manager(dev))
+		async_event_mask |= (1ull << MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE);
+
 	return async_event_mask;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 5b492b67f4e1..e18af31336e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -39,8 +39,7 @@
 #include "lib/eq.h"
 #include "eswitch.h"
 #include "fs_core.h"
-
-#define UPLINK_VPORT 0xFFFF
+#include "ecpf.h"
 
 enum {
 	MLX5_ACTION_NONE = 0,
@@ -52,7 +51,7 @@ enum {
 struct vport_addr {
 	struct l2addr_node     node;
 	u8                     action;
-	u32                    vport;
+	u16                    vport;
 	struct mlx5_flow_handle *flow_rule;
 	bool mpfs; /* UC MAC was added to MPFs */
 	/* A flag indicating that mac was added due to mc promiscuous vport */
@@ -70,6 +69,28 @@ enum {
 			    MC_ADDR_CHANGE | \
 			    PROMISC_CHANGE)
 
+/* The vport getter/iterator are only valid after esw->total_vports
+ * and vport->vport are initialized in mlx5_eswitch_init.
+ */
+#define mlx5_esw_for_all_vports(esw, i, vport)			\
+	for ((i) = MLX5_VPORT_PF;				\
+	     (vport) = &(esw)->vports[i],			\
+	     (i) < (esw)->total_vports; (i)++)
+
+#define mlx5_esw_for_each_vf_vport(esw, i, vport, nvfs)	\
+	for ((i) = MLX5_VPORT_FIRST_VF;				\
+	     (vport) = &(esw)->vports[i],			\
+	     (i) <= (nvfs); (i)++)
+
+static struct mlx5_vport *mlx5_eswitch_get_vport(struct mlx5_eswitch *esw,
+						 u16 vport_num)
+{
+	u16 idx = mlx5_eswitch_vport_num_to_index(esw, vport_num);
+
+	WARN_ON(vport_num > esw->total_vports - 1);
+	return &esw->vports[idx];
+}
+
 static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport,
 					u32 events_mask)
 {
@@ -115,7 +136,7 @@ static int modify_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport,
 	return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
 }
 
-static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u32 vport,
+static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u16 vport,
 				  u16 vlan, u8 qos, u8 set_flags)
 {
 	u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {0};
@@ -152,7 +173,7 @@ static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u32 vport,
 
 /* E-Switch FDB */
 static struct mlx5_flow_handle *
-__esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
+__esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u16 vport, bool rx_rule,
 			 u8 mac_c[ETH_ALEN], u8 mac_v[ETH_ALEN])
 {
 	int match_header = (is_zero_ether_addr(mac_c) ? 0 :
@@ -188,7 +209,7 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
 					misc_parameters);
 		mc_misc  = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
 					misc_parameters);
-		MLX5_SET(fte_match_set_misc, mv_misc, source_port, UPLINK_VPORT);
+		MLX5_SET(fte_match_set_misc, mv_misc, source_port, MLX5_VPORT_UPLINK);
 		MLX5_SET_TO_ONES(fte_match_set_misc, mc_misc, source_port);
 	}
 
@@ -215,7 +236,7 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
 }
 
 static struct mlx5_flow_handle *
-esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport)
+esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u16 vport)
 {
 	u8 mac_c[ETH_ALEN];
 
@@ -224,7 +245,7 @@ esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport)
 }
 
 static struct mlx5_flow_handle *
-esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport)
+esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u16 vport)
 {
 	u8 mac_c[ETH_ALEN];
 	u8 mac_v[ETH_ALEN];
@@ -237,7 +258,7 @@ esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport)
 }
 
 static struct mlx5_flow_handle *
-esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 vport)
+esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u16 vport)
 {
 	u8 mac_c[ETH_ALEN];
 	u8 mac_v[ETH_ALEN];
@@ -377,19 +398,19 @@ typedef int (*vport_addr_action)(struct mlx5_eswitch *esw,
 static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 {
 	u8 *mac = vaddr->node.addr;
-	u32 vport = vaddr->vport;
+	u16 vport = vaddr->vport;
 	int err;
 
-	/* Skip mlx5_mpfs_add_mac for PFs,
-	 * it is already done by the PF netdev in mlx5e_execute_l2_action
+	/* Skip mlx5_mpfs_add_mac for eswitch_managers,
+	 * it is already done by its netdev in mlx5e_execute_l2_action
 	 */
-	if (!vport)
+	if (esw->manager_vport == vport)
 		goto fdb_add;
 
 	err = mlx5_mpfs_add_mac(esw->dev, mac);
 	if (err) {
 		esw_warn(esw->dev,
-			 "Failed to add L2 table mac(%pM) for vport(%d), err(%d)\n",
+			 "Failed to add L2 table mac(%pM) for vport(0x%x), err(%d)\n",
 			 mac, vport, err);
 		return err;
 	}
@@ -409,13 +430,13 @@ fdb_add:
 static int esw_del_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 {
 	u8 *mac = vaddr->node.addr;
-	u32 vport = vaddr->vport;
+	u16 vport = vaddr->vport;
 	int err = 0;
 
-	/* Skip mlx5_mpfs_del_mac for PFs,
-	 * it is already done by the PF netdev in mlx5e_execute_l2_action
+	/* Skip mlx5_mpfs_del_mac for eswitch managerss,
+	 * it is already done by its netdev in mlx5e_execute_l2_action
 	 */
-	if (!vport || !vaddr->mpfs)
+	if (!vaddr->mpfs || esw->manager_vport == vport)
 		goto fdb_del;
 
 	err = mlx5_mpfs_del_mac(esw->dev, mac);
@@ -438,17 +459,18 @@ static void update_allmulti_vports(struct mlx5_eswitch *esw,
 				   struct esw_mc_addr *esw_mc)
 {
 	u8 *mac = vaddr->node.addr;
-	u32 vport_idx = 0;
+	struct mlx5_vport *vport;
+	u16 i, vport_num;
 
-	for (vport_idx = 0; vport_idx < esw->total_vports; vport_idx++) {
-		struct mlx5_vport *vport = &esw->vports[vport_idx];
+	mlx5_esw_for_all_vports(esw, i, vport) {
 		struct hlist_head *vport_hash = vport->mc_list;
 		struct vport_addr *iter_vaddr =
 					l2addr_hash_find(vport_hash,
 							 mac,
 							 struct vport_addr);
+		vport_num = vport->vport;
 		if (IS_ERR_OR_NULL(vport->allmulti_rule) ||
-		    vaddr->vport == vport_idx)
+		    vaddr->vport == vport_num)
 			continue;
 		switch (vaddr->action) {
 		case MLX5_ACTION_ADD:
@@ -460,14 +482,14 @@ static void update_allmulti_vports(struct mlx5_eswitch *esw,
 			if (!iter_vaddr) {
 				esw_warn(esw->dev,
 					 "ALL-MULTI: Failed to add MAC(%pM) to vport[%d] DB\n",
-					 mac, vport_idx);
+					 mac, vport_num);
 				continue;
 			}
-			iter_vaddr->vport = vport_idx;
+			iter_vaddr->vport = vport_num;
 			iter_vaddr->flow_rule =
 					esw_fdb_set_vport_rule(esw,
 							       mac,
-							       vport_idx);
+							       vport_num);
 			iter_vaddr->mc_promisc = true;
 			break;
 		case MLX5_ACTION_DEL:
@@ -485,7 +507,7 @@ static int esw_add_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 	struct hlist_head *hash = esw->mc_table;
 	struct esw_mc_addr *esw_mc;
 	u8 *mac = vaddr->node.addr;
-	u32 vport = vaddr->vport;
+	u16 vport = vaddr->vport;
 
 	if (!esw->fdb_table.legacy.fdb)
 		return 0;
@@ -499,7 +521,7 @@ static int esw_add_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 		return -ENOMEM;
 
 	esw_mc->uplink_rule = /* Forward MC MAC to Uplink */
-		esw_fdb_set_vport_rule(esw, mac, UPLINK_VPORT);
+		esw_fdb_set_vport_rule(esw, mac, MLX5_VPORT_UPLINK);
 
 	/* Add this multicast mac to all the mc promiscuous vports */
 	update_allmulti_vports(esw, vaddr, esw_mc);
@@ -525,7 +547,7 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 	struct hlist_head *hash = esw->mc_table;
 	struct esw_mc_addr *esw_mc;
 	u8 *mac = vaddr->node.addr;
-	u32 vport = vaddr->vport;
+	u16 vport = vaddr->vport;
 
 	if (!esw->fdb_table.legacy.fdb)
 		return 0;
@@ -564,9 +586,9 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 
 /* Apply vport UC/MC list to HW l2 table and FDB table */
 static void esw_apply_vport_addr_list(struct mlx5_eswitch *esw,
-				      u32 vport_num, int list_type)
+				      u16 vport_num, int list_type)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
+	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
 	bool is_uc = list_type == MLX5_NVPRT_LIST_TYPE_UC;
 	vport_addr_action vport_addr_add;
 	vport_addr_action vport_addr_del;
@@ -599,9 +621,9 @@ static void esw_apply_vport_addr_list(struct mlx5_eswitch *esw,
 
 /* Sync vport UC/MC list from vport context */
 static void esw_update_vport_addr_list(struct mlx5_eswitch *esw,
-				       u32 vport_num, int list_type)
+				       u16 vport_num, int list_type)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
+	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
 	bool is_uc = list_type == MLX5_NVPRT_LIST_TYPE_UC;
 	u8 (*mac_list)[ETH_ALEN];
 	struct l2addr_node *node;
@@ -686,9 +708,9 @@ out:
 /* Sync vport UC/MC list from vport context
  * Must be called after esw_update_vport_addr_list
  */
-static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u32 vport_num)
+static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u16 vport_num)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
+	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
 	struct l2addr_node *node;
 	struct vport_addr *addr;
 	struct hlist_head *hash;
@@ -721,11 +743,11 @@ static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u32 vport_num)
 }
 
 /* Apply vport rx mode to HW FDB table */
-static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num,
+static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u16 vport_num,
 				    bool promisc, bool mc_promisc)
 {
+	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
 	struct esw_mc_addr *allmulti_addr = &esw->mc_promisc;
-	struct mlx5_vport *vport = &esw->vports[vport_num];
 
 	if (IS_ERR_OR_NULL(vport->allmulti_rule) != mc_promisc)
 		goto promisc;
@@ -736,7 +758,7 @@ static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num,
 		if (!allmulti_addr->uplink_rule)
 			allmulti_addr->uplink_rule =
 				esw_fdb_set_vport_allmulti_rule(esw,
-								UPLINK_VPORT);
+								MLX5_VPORT_UPLINK);
 		allmulti_addr->refcnt++;
 	} else if (vport->allmulti_rule) {
 		mlx5_del_flow_rules(vport->allmulti_rule);
@@ -764,9 +786,9 @@ promisc:
 }
 
 /* Sync vport rx mode from vport context */
-static void esw_update_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num)
+static void esw_update_vport_rx_mode(struct mlx5_eswitch *esw, u16 vport_num)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
+	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
 	int promisc_all = 0;
 	int promisc_uc = 0;
 	int promisc_mc = 0;
@@ -1343,8 +1365,8 @@ static void esw_destroy_tsar(struct mlx5_eswitch *esw)
 static int esw_vport_enable_qos(struct mlx5_eswitch *esw, int vport_num,
 				u32 initial_max_rate, u32 initial_bw_share)
 {
+	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
 	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
-	struct mlx5_vport *vport = &esw->vports[vport_num];
 	struct mlx5_core_dev *dev = esw->dev;
 	void *vport_elem;
 	int err = 0;
@@ -1383,7 +1405,7 @@ static int esw_vport_enable_qos(struct mlx5_eswitch *esw, int vport_num,
 
 static void esw_vport_disable_qos(struct mlx5_eswitch *esw, int vport_num)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
+	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
 	int err = 0;
 
 	if (!vport->qos.enabled)
@@ -1402,8 +1424,8 @@ static void esw_vport_disable_qos(struct mlx5_eswitch *esw, int vport_num)
 static int esw_vport_qos_config(struct mlx5_eswitch *esw, int vport_num,
 				u32 max_rate, u32 bw_share)
 {
+	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
 	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
-	struct mlx5_vport *vport = &esw->vports[vport_num];
 	struct mlx5_core_dev *dev = esw->dev;
 	void *vport_elem;
 	u32 bitmask = 0;
@@ -1459,15 +1481,22 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw,
 {
 	int vport_num = vport->vport;
 
-	if (!vport_num)
+	if (esw->manager_vport == vport_num)
 		return;
 
 	mlx5_modify_vport_admin_state(esw->dev,
 				      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
-				      vport_num,
+				      vport_num, 1,
 				      vport->info.link_state);
-	mlx5_modify_nic_vport_mac_address(esw->dev, vport_num, vport->info.mac);
-	mlx5_modify_nic_vport_node_guid(esw->dev, vport_num, vport->info.node_guid);
+
+	/* Host PF has its own mac/guid. */
+	if (vport_num) {
+		mlx5_modify_nic_vport_mac_address(esw->dev, vport_num,
+						  vport->info.mac);
+		mlx5_modify_nic_vport_node_guid(esw->dev, vport_num,
+						vport->info.node_guid);
+	}
+
 	modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan, vport->info.qos,
 			       (vport->info.vlan || vport->info.qos));
 
@@ -1513,10 +1542,10 @@ static void esw_vport_destroy_drop_counters(struct mlx5_vport *vport)
 		mlx5_fc_destroy(dev, vport->egress.drop_counter);
 }
 
-static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
+static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 			     int enable_events)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
+	u16 vport_num = vport->vport;
 
 	mutex_lock(&esw->state_lock);
 	WARN_ON(vport->enabled);
@@ -1539,8 +1568,11 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
 	vport->enabled_events = enable_events;
 	vport->enabled = true;
 
-	/* only PF is trusted by default */
-	if (!vport_num)
+	/* Esw manager is trusted by default. Host PF (vport 0) is trusted as well
+	 * in smartNIC as it's a vport group manager.
+	 */
+	if (esw->manager_vport == vport_num ||
+	    (!vport_num && mlx5_core_is_ecpf(esw->dev)))
 		vport->info.trusted = true;
 
 	esw_vport_change_handle_locked(vport);
@@ -1550,9 +1582,10 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
 	mutex_unlock(&esw->state_lock);
 }
 
-static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
+static void esw_disable_vport(struct mlx5_eswitch *esw,
+			      struct mlx5_vport *vport)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
+	u16 vport_num = vport->vport;
 
 	if (!vport->enabled)
 		return;
@@ -1573,10 +1606,10 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 	esw_vport_change_handle_locked(vport);
 	vport->enabled_events = 0;
 	esw_vport_disable_qos(esw, vport_num);
-	if (vport_num && esw->mode == SRIOV_LEGACY) {
+	if (esw->mode == SRIOV_LEGACY) {
 		mlx5_modify_vport_admin_state(esw->dev,
 					      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
-					      vport_num,
+					      vport_num, 1,
 					      MLX5_VPORT_ADMIN_STATE_DOWN);
 		esw_vport_disable_egress_acl(esw, vport);
 		esw_vport_disable_ingress_acl(esw, vport);
@@ -1595,7 +1628,7 @@ static int eswitch_vport_event(struct notifier_block *nb,
 	u16 vport_num;
 
 	vport_num = be16_to_cpu(eqe->data.vport_change.vport_num);
-	vport = &esw->vports[vport_num];
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
 	if (vport->enabled)
 		queue_work(esw->work_queue, &vport->vport_change_handler);
 
@@ -1607,6 +1640,8 @@ static int eswitch_vport_event(struct notifier_block *nb,
 
 int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 {
+	int vf_nvports = 0, total_nvports = 0;
+	struct mlx5_vport *vport;
 	int err;
 	int i, enabled_events;
 
@@ -1624,6 +1659,18 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 
 	esw_info(esw->dev, "E-Switch enable SRIOV: nvfs(%d) mode (%d)\n", nvfs, mode);
 
+	if (mode == SRIOV_OFFLOADS) {
+		if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+			err = mlx5_query_host_params_num_vfs(esw->dev, &vf_nvports);
+			if (err)
+				return err;
+			total_nvports = esw->total_vports;
+		} else {
+			vf_nvports = nvfs;
+			total_nvports = nvfs + MLX5_SPECIAL_VPORTS(esw->dev);
+		}
+	}
+
 	esw->mode = mode;
 
 	mlx5_lag_update(esw->dev);
@@ -1633,7 +1680,7 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 	} else {
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
-		err = esw_offloads_init(esw, nvfs + 1);
+		err = esw_offloads_init(esw, vf_nvports, total_nvports);
 	}
 
 	if (err)
@@ -1648,8 +1695,20 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 	 * 2. FDB/Eswitch is programmed by user space tools
 	 */
 	enabled_events = (mode == SRIOV_LEGACY) ? SRIOV_VPORT_EVENTS : 0;
-	for (i = 0; i <= nvfs; i++)
-		esw_enable_vport(esw, i, enabled_events);
+
+	/* Enable PF vport */
+	vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF);
+	esw_enable_vport(esw, vport, enabled_events);
+
+	/* Enable ECPF vports */
+	if (mlx5_ecpf_vport_exists(esw->dev)) {
+		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF);
+		esw_enable_vport(esw, vport, enabled_events);
+	}
+
+	/* Enable VF vports */
+	mlx5_esw_for_each_vf_vport(esw, i, vport, nvfs)
+		esw_enable_vport(esw, vport, enabled_events);
 
 	if (mode == SRIOV_LEGACY) {
 		MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE);
@@ -1674,8 +1733,8 @@ abort:
 void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
 {
 	struct esw_mc_addr *mc_promisc;
+	struct mlx5_vport *vport;
 	int old_mode;
-	int nvports;
 	int i;
 
 	if (!ESW_ALLOWED(esw) || esw->mode == SRIOV_NONE)
@@ -1685,13 +1744,12 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
 		 esw->enabled_vports, esw->mode);
 
 	mc_promisc = &esw->mc_promisc;
-	nvports = esw->enabled_vports;
 
 	if (esw->mode == SRIOV_LEGACY)
 		mlx5_eq_notifier_unregister(esw->dev, &esw->nb);
 
-	for (i = 0; i < esw->total_vports; i++)
-		esw_disable_vport(esw, i);
+	mlx5_esw_for_all_vports(esw, i, vport)
+		esw_disable_vport(esw, vport);
 
 	if (mc_promisc && mc_promisc->uplink_rule)
 		mlx5_del_flow_rules(mc_promisc->uplink_rule);
@@ -1701,7 +1759,7 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
 	if (esw->mode == SRIOV_LEGACY)
 		esw_destroy_legacy_fdb_table(esw);
 	else if (esw->mode == SRIOV_OFFLOADS)
-		esw_offloads_cleanup(esw, nvports);
+		esw_offloads_cleanup(esw);
 
 	old_mode = esw->mode;
 	esw->mode = SRIOV_NONE;
@@ -1718,8 +1776,8 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 {
 	int total_vports = MLX5_TOTAL_VPORTS(dev);
 	struct mlx5_eswitch *esw;
-	int vport_num;
-	int err;
+	struct mlx5_vport *vport;
+	int err, i;
 
 	if (!MLX5_VPORT_MANAGER(dev))
 		return 0;
@@ -1735,6 +1793,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 		return -ENOMEM;
 
 	esw->dev = dev;
+	esw->manager_vport = mlx5_eswitch_manager_vport(dev);
 
 	esw->work_queue = create_singlethread_workqueue("mlx5_esw_wq");
 	if (!esw->work_queue) {
@@ -1749,6 +1808,8 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 		goto abort;
 	}
 
+	esw->total_vports = total_vports;
+
 	err = esw_offloads_init_reps(esw);
 	if (err)
 		goto abort;
@@ -1757,17 +1818,14 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	hash_init(esw->offloads.mod_hdr_tbl);
 	mutex_init(&esw->state_lock);
 
-	for (vport_num = 0; vport_num < total_vports; vport_num++) {
-		struct mlx5_vport *vport = &esw->vports[vport_num];
-
-		vport->vport = vport_num;
+	mlx5_esw_for_all_vports(esw, i, vport) {
+		vport->vport = mlx5_eswitch_index_to_vport_num(esw, i);
 		vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
 		vport->dev = dev;
 		INIT_WORK(&vport->vport_change_handler,
 			  esw_vport_change_handler);
 	}
 
-	esw->total_vports = total_vports;
 	esw->enabled_vports = 0;
 	esw->mode = SRIOV_NONE;
 	esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE;
@@ -1866,7 +1924,7 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
 
 	err = mlx5_modify_vport_admin_state(esw->dev,
 					    MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
-					    vport, link_state);
+					    vport, 1, link_state);
 	if (err) {
 		mlx5_core_warn(esw->dev,
 			       "Failed to set vport %d link state, err = %d",
@@ -2009,8 +2067,7 @@ static u32 calculate_vports_min_rate_divider(struct mlx5_eswitch *esw)
 	u32 max_guarantee = 0;
 	int i;
 
-	for (i = 0; i < esw->total_vports; i++) {
-		evport = &esw->vports[i];
+	mlx5_esw_for_all_vports(esw, i, evport) {
 		if (!evport->enabled || evport->info.min_rate < max_guarantee)
 			continue;
 		max_guarantee = evport->info.min_rate;
@@ -2029,8 +2086,7 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider)
 	int err;
 	int i;
 
-	for (i = 0; i < esw->total_vports; i++) {
-		evport = &esw->vports[i];
+	mlx5_esw_for_all_vports(esw, i, evport) {
 		if (!evport->enabled)
 			continue;
 		vport_min_rate = evport->info.min_rate;
@@ -2045,7 +2101,7 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider)
 		if (bw_share == evport->qos.bw_share)
 			continue;
 
-		err = esw_vport_qos_config(esw, i, vport_max_rate,
+		err = esw_vport_qos_config(esw, evport->vport, vport_max_rate,
 					   bw_share);
 		if (!err)
 			evport->qos.bw_share = bw_share;
@@ -2128,7 +2184,7 @@ static int mlx5_eswitch_query_vport_drop_stats(struct mlx5_core_dev *dev,
 	    !MLX5_CAP_GEN(dev, transmit_discard_vport_down))
 		return 0;
 
-	err = mlx5_query_vport_down_stats(dev, vport_idx,
+	err = mlx5_query_vport_down_stats(dev, vport_idx, 1,
 					  &rx_discard_vport_down,
 					  &tx_discard_vport_down);
 	if (err)
@@ -2165,8 +2221,7 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
 		 MLX5_CMD_OP_QUERY_VPORT_COUNTER);
 	MLX5_SET(query_vport_counter_in, in, op_mod, 0);
 	MLX5_SET(query_vport_counter_in, in, vport_number, vport);
-	if (vport)
-		MLX5_SET(query_vport_counter_in, in, other_vport, 1);
+	MLX5_SET(query_vport_counter_in, in, other_vport, 1);
 
 	memset(out, 0, outlen);
 	err = mlx5_cmd_exec(esw->dev, in, sizeof(in), out, outlen);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 748ff178a1d6..af5581a57e56 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -38,6 +38,7 @@
 #include <net/devlink.h>
 #include <linux/mlx5/device.h>
 #include <linux/mlx5/eswitch.h>
+#include <linux/mlx5/vport.h>
 #include <linux/mlx5/fs.h>
 #include "lib/mpfs.h"
 
@@ -49,8 +50,6 @@
 #define MLX5_MAX_MC_PER_VPORT(dev) \
 	(1 << MLX5_CAP_GEN(dev, log_max_current_mc_list))
 
-#define FDB_UPLINK_VPORT 0xffff
-
 #define MLX5_MIN_BW_SHARE 1
 
 #define MLX5_RATE_TO_BW_SHARE(rate, divider, limit) \
@@ -183,6 +182,16 @@ struct esw_mc_addr { /* SRIOV only */
 	u32                    refcnt;
 };
 
+struct mlx5_host_work {
+	struct work_struct	work;
+	struct mlx5_eswitch	*esw;
+};
+
+struct mlx5_host_info {
+	struct mlx5_nb		nb;
+	u16			num_vfs;
+};
+
 struct mlx5_eswitch {
 	struct mlx5_core_dev    *dev;
 	struct mlx5_nb          nb;
@@ -206,10 +215,13 @@ struct mlx5_eswitch {
 	struct mlx5_esw_offload offloads;
 	int                     mode;
 	int                     nvports;
+	u16                     manager_vport;
+	struct mlx5_host_info	host_info;
 };
 
-void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports);
-int esw_offloads_init(struct mlx5_eswitch *esw, int nvports);
+void esw_offloads_cleanup(struct mlx5_eswitch *esw);
+int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports,
+		      int total_nvports);
 void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw);
 int esw_offloads_init_reps(struct mlx5_eswitch *esw);
 
@@ -365,6 +377,53 @@ bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0,
 
 #define esw_debug(dev, format, ...)				\
 	mlx5_core_dbg_mask(dev, MLX5_DEBUG_ESWITCH_MASK, format, ##__VA_ARGS__)
+
+/* The returned number is valid only when the dev is eswitch manager. */
+static inline u16 mlx5_eswitch_manager_vport(struct mlx5_core_dev *dev)
+{
+	return mlx5_core_is_ecpf_esw_manager(dev) ?
+		MLX5_VPORT_ECPF : MLX5_VPORT_PF;
+}
+
+static inline int mlx5_eswitch_uplink_idx(struct mlx5_eswitch *esw)
+{
+	/* Uplink always locate at the last element of the array.*/
+	return esw->total_vports - 1;
+}
+
+static inline int mlx5_eswitch_ecpf_idx(struct mlx5_eswitch *esw)
+{
+	return esw->total_vports - 2;
+}
+
+static inline int mlx5_eswitch_vport_num_to_index(struct mlx5_eswitch *esw,
+						  u16 vport_num)
+{
+	if (vport_num == MLX5_VPORT_ECPF) {
+		if (!mlx5_ecpf_vport_exists(esw->dev))
+			esw_warn(esw->dev, "ECPF vport doesn't exist!\n");
+		return mlx5_eswitch_ecpf_idx(esw);
+	}
+
+	if (vport_num == MLX5_VPORT_UPLINK)
+		return mlx5_eswitch_uplink_idx(esw);
+
+	return vport_num;
+}
+
+static inline int mlx5_eswitch_index_to_vport_num(struct mlx5_eswitch *esw,
+						  int index)
+{
+	if (index == mlx5_eswitch_ecpf_idx(esw) &&
+	    mlx5_ecpf_vport_exists(esw->dev))
+		return MLX5_VPORT_ECPF;
+
+	if (index == mlx5_eswitch_uplink_idx(esw))
+		return MLX5_VPORT_UPLINK;
+
+	return index;
+}
+
 #else  /* CONFIG_MLX5_ESWITCH */
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index d4e6fe5b9300..f2260391be5b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -40,15 +40,59 @@
 #include "en.h"
 #include "fs_core.h"
 #include "lib/devcom.h"
+#include "ecpf.h"
+#include "lib/eq.h"
 
 enum {
 	FDB_FAST_PATH = 0,
 	FDB_SLOW_PATH
 };
 
+/* There are two match-all miss flows, one for unicast dst mac and
+ * one for multicast.
+ */
+#define MLX5_ESW_MISS_FLOWS (2)
+
 #define fdb_prio_table(esw, chain, prio, level) \
 	(esw)->fdb_table.offloads.fdb_prio[(chain)][(prio)][(level)]
 
+#define UPLINK_REP_INDEX 0
+
+/* The rep getter/iterator are only valid after esw->total_vports
+ * and vport->vport are initialized in mlx5_eswitch_init.
+ */
+#define mlx5_esw_for_all_reps(esw, i, rep)			\
+	for ((i) = MLX5_VPORT_PF;				\
+	     (rep) = &(esw)->offloads.vport_reps[i],		\
+	     (i) < (esw)->total_vports; (i)++)
+
+#define mlx5_esw_for_each_vf_rep(esw, i, rep, nvfs)		\
+	for ((i) = MLX5_VPORT_FIRST_VF;				\
+	     (rep) = &(esw)->offloads.vport_reps[i],		\
+	     (i) <= (nvfs); (i)++)
+
+#define mlx5_esw_for_each_vf_rep_reverse(esw, i, rep, nvfs)	\
+	for ((i) = (nvfs);					\
+	     (rep) = &(esw)->offloads.vport_reps[i],		\
+	     (i) >= MLX5_VPORT_FIRST_VF; (i)--)
+
+#define mlx5_esw_for_each_vf_vport(esw, vport, nvfs)		\
+	for ((vport) = MLX5_VPORT_FIRST_VF;			\
+	     (vport) <= (nvfs); (vport)++)
+
+#define mlx5_esw_for_each_vf_vport_reverse(esw, vport, nvfs)	\
+	for ((vport) = (nvfs);					\
+	     (vport) >= MLX5_VPORT_FIRST_VF; (vport)--)
+
+static struct mlx5_eswitch_rep *mlx5_eswitch_get_rep(struct mlx5_eswitch *esw,
+						     u16 vport_num)
+{
+	u16 idx = mlx5_eswitch_vport_num_to_index(esw, vport_num);
+
+	WARN_ON(idx > esw->total_vports - 1);
+	return &esw->offloads.vport_reps[idx];
+}
+
 static struct mlx5_flow_table *
 esw_get_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level);
 static void
@@ -319,7 +363,7 @@ static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val)
 	esw_debug(esw->dev, "%s applying global %s policy\n", __func__, val ? "pop" : "none");
 	for (vf_vport = 1; vf_vport < esw->enabled_vports; vf_vport++) {
 		rep = &esw->offloads.vport_reps[vf_vport];
-		if (!rep->rep_if[REP_ETH].valid)
+		if (rep->rep_if[REP_ETH].state != REP_LOADED)
 			continue;
 
 		err = __mlx5_eswitch_set_vport_vlan(esw, rep->vport, 0, 0, val);
@@ -360,15 +404,15 @@ static int esw_add_vlan_action_check(struct mlx5_esw_flow_attr *attr,
 	in_rep  = attr->in_rep;
 	out_rep = attr->dests[0].rep;
 
-	if (push && in_rep->vport == FDB_UPLINK_VPORT)
+	if (push && in_rep->vport == MLX5_VPORT_UPLINK)
 		goto out_notsupp;
 
-	if (pop && out_rep->vport == FDB_UPLINK_VPORT)
+	if (pop && out_rep->vport == MLX5_VPORT_UPLINK)
 		goto out_notsupp;
 
 	/* vport has vlan push configured, can't offload VF --> wire rules w.o it */
 	if (!push && !pop && fwd)
-		if (in_rep->vlan && out_rep->vport == FDB_UPLINK_VPORT)
+		if (in_rep->vlan && out_rep->vport == MLX5_VPORT_UPLINK)
 			goto out_notsupp;
 
 	/* protects against (1) setting rules with different vlans to push and
@@ -410,7 +454,7 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
 
 	if (!push && !pop && fwd) {
 		/* tracks VF --> wire rules without vlan push action */
-		if (attr->dests[0].rep->vport == FDB_UPLINK_VPORT) {
+		if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) {
 			vport->vlan_refcount++;
 			attr->vlan_handled = true;
 		}
@@ -470,7 +514,7 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
 
 	if (!push && !pop && fwd) {
 		/* tracks VF --> wire rules without vlan push action */
-		if (attr->dests[0].rep->vport == FDB_UPLINK_VPORT)
+		if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK)
 			vport->vlan_refcount--;
 
 		return 0;
@@ -517,7 +561,8 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn
 
 	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
 	MLX5_SET(fte_match_set_misc, misc, source_sqn, sqn);
-	MLX5_SET(fte_match_set_misc, misc, source_port, 0x0); /* source vport is 0 */
+	/* source vport is the esw manager */
+	MLX5_SET(fte_match_set_misc, misc, source_port, esw->manager_vport);
 
 	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
 	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_sqn);
@@ -562,7 +607,7 @@ static void peer_miss_rules_setup(struct mlx5_core_dev *peer_dev,
 			 source_eswitch_owner_vhca_id);
 
 	dest->type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
-	dest->vport.num = 0;
+	dest->vport.num = peer_dev->priv.eswitch->manager_vport;
 	dest->vport.vhca_id = MLX5_CAP_GEN(peer_dev, vhca_id);
 	dest->vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
 }
@@ -596,14 +641,35 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
 			    misc_parameters);
 
-	for (i = 1; i < nvports; i++) {
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_PF);
+		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
+					   spec, &flow_act, &dest, 1);
+		if (IS_ERR(flow)) {
+			err = PTR_ERR(flow);
+			goto add_pf_flow_err;
+		}
+		flows[MLX5_VPORT_PF] = flow;
+	}
+
+	if (mlx5_ecpf_vport_exists(esw->dev)) {
+		MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_ECPF);
+		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
+					   spec, &flow_act, &dest, 1);
+		if (IS_ERR(flow)) {
+			err = PTR_ERR(flow);
+			goto add_ecpf_flow_err;
+		}
+		flows[mlx5_eswitch_ecpf_idx(esw)] = flow;
+	}
+
+	mlx5_esw_for_each_vf_vport(esw, i, mlx5_core_max_vfs(esw->dev)) {
 		MLX5_SET(fte_match_set_misc, misc, source_port, i);
 		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
 					   spec, &flow_act, &dest, 1);
 		if (IS_ERR(flow)) {
 			err = PTR_ERR(flow);
-			esw_warn(esw->dev, "FDB: Failed to add peer miss flow rule err %d\n", err);
-			goto add_flow_err;
+			goto add_vf_flow_err;
 		}
 		flows[i] = flow;
 	}
@@ -613,9 +679,18 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 	kvfree(spec);
 	return 0;
 
-add_flow_err:
-	for (i--; i > 0; i--)
+add_vf_flow_err:
+	nvports = --i;
+	mlx5_esw_for_each_vf_vport_reverse(esw, i, nvports)
 		mlx5_del_flow_rules(flows[i]);
+
+	if (mlx5_ecpf_vport_exists(esw->dev))
+		mlx5_del_flow_rules(flows[mlx5_eswitch_ecpf_idx(esw)]);
+add_ecpf_flow_err:
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev))
+		mlx5_del_flow_rules(flows[MLX5_VPORT_PF]);
+add_pf_flow_err:
+	esw_warn(esw->dev, "FDB: Failed to add peer miss flow rule err %d\n", err);
 	kvfree(flows);
 alloc_flows_err:
 	kvfree(spec);
@@ -629,9 +704,15 @@ static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw)
 
 	flows = esw->fdb_table.offloads.peer_miss_rules;
 
-	for (i = 1; i < esw->total_vports; i++)
+	mlx5_esw_for_each_vf_vport_reverse(esw, i, mlx5_core_max_vfs(esw->dev))
 		mlx5_del_flow_rules(flows[i]);
 
+	if (mlx5_ecpf_vport_exists(esw->dev))
+		mlx5_del_flow_rules(flows[mlx5_eswitch_ecpf_idx(esw)]);
+
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev))
+		mlx5_del_flow_rules(flows[MLX5_VPORT_PF]);
+
 	kvfree(flows);
 }
 
@@ -661,7 +742,7 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw)
 	dmac_c[0] = 0x01;
 
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
-	dest.vport.num = 0;
+	dest.vport.num = esw->manager_vport;
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 
 	flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec,
@@ -905,8 +986,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 		esw->fdb_table.offloads.fdb_left[i] =
 			ESW_POOLS[i] <= fdb_max ? ESW_SIZE / ESW_POOLS[i] : 0;
 
-	table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ + 2 +
-		esw->total_vports;
+	table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ +
+		MLX5_ESW_MISS_FLOWS + esw->total_vports;
 
 	/* create the slow path fdb with encap set, so further table instances
 	 * can be created at run time while VFs are probed if the FW allows that.
@@ -1000,7 +1081,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 	dmac[0] = 0x01;
 
 	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
-	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix + 2);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
+		 ix + MLX5_ESW_MISS_FLOWS);
 
 	g = mlx5_create_flow_group(fdb, flow_group_in);
 	if (IS_ERR(g)) {
@@ -1049,7 +1131,7 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
 	esw_destroy_offloads_fast_fdb_tables(esw);
 }
 
-static int esw_create_offloads_table(struct mlx5_eswitch *esw)
+static int esw_create_offloads_table(struct mlx5_eswitch *esw, int nvports)
 {
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_core_dev *dev = esw->dev;
@@ -1063,7 +1145,7 @@ static int esw_create_offloads_table(struct mlx5_eswitch *esw)
 		return -EOPNOTSUPP;
 	}
 
-	ft_attr.max_fte = dev->priv.sriov.num_vfs + 2;
+	ft_attr.max_fte = nvports + MLX5_ESW_MISS_FLOWS;
 
 	ft_offloads = mlx5_create_flow_table(ns, &ft_attr);
 	if (IS_ERR(ft_offloads)) {
@@ -1083,16 +1165,15 @@ static void esw_destroy_offloads_table(struct mlx5_eswitch *esw)
 	mlx5_destroy_flow_table(offloads->ft_offloads);
 }
 
-static int esw_create_vport_rx_group(struct mlx5_eswitch *esw)
+static int esw_create_vport_rx_group(struct mlx5_eswitch *esw, int nvports)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_flow_group *g;
-	struct mlx5_priv *priv = &esw->dev->priv;
 	u32 *flow_group_in;
 	void *match_criteria, *misc;
 	int err = 0;
-	int nvports = priv->sriov.num_vfs + 2;
 
+	nvports = nvports + MLX5_ESW_MISS_FLOWS;
 	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
 	if (!flow_group_in)
 		return -ENOMEM;
@@ -1169,7 +1250,8 @@ static int esw_offloads_start(struct mlx5_eswitch *esw,
 {
 	int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs;
 
-	if (esw->mode != SRIOV_LEGACY) {
+	if (esw->mode != SRIOV_LEGACY &&
+	    !mlx5_core_is_ecpf_esw_manager(esw->dev)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Can't set offloads mode, SRIOV legacy not enabled");
 		return -EINVAL;
@@ -1207,9 +1289,8 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw)
 {
 	int total_vfs = MLX5_TOTAL_VPORTS(esw->dev);
 	struct mlx5_core_dev *dev = esw->dev;
-	struct mlx5_esw_offload *offloads;
 	struct mlx5_eswitch_rep *rep;
-	u8 hw_id[ETH_ALEN];
+	u8 hw_id[ETH_ALEN], rep_type;
 	int vport;
 
 	esw->offloads.vport_reps = kcalloc(total_vfs,
@@ -1218,75 +1299,203 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw)
 	if (!esw->offloads.vport_reps)
 		return -ENOMEM;
 
-	offloads = &esw->offloads;
 	mlx5_query_nic_vport_mac_address(dev, 0, hw_id);
 
-	for (vport = 0; vport < total_vfs; vport++) {
-		rep = &offloads->vport_reps[vport];
-
-		rep->vport = vport;
+	mlx5_esw_for_all_reps(esw, vport, rep) {
+		rep->vport = mlx5_eswitch_index_to_vport_num(esw, vport);
 		ether_addr_copy(rep->hw_id, hw_id);
-	}
 
-	offloads->vport_reps[0].vport = FDB_UPLINK_VPORT;
+		for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++)
+			rep->rep_if[rep_type].state = REP_UNREGISTERED;
+	}
 
 	return 0;
 }
 
-static void esw_offloads_unload_reps_type(struct mlx5_eswitch *esw, int nvports,
-					  u8 rep_type)
+static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw,
+				      struct mlx5_eswitch_rep *rep, u8 rep_type)
+{
+	if (rep->rep_if[rep_type].state != REP_LOADED)
+		return;
+
+	rep->rep_if[rep_type].unload(rep);
+	rep->rep_if[rep_type].state = REP_REGISTERED;
+}
+
+static void __unload_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type)
 {
 	struct mlx5_eswitch_rep *rep;
-	int vport;
 
-	for (vport = nvports - 1; vport >= 0; vport--) {
-		rep = &esw->offloads.vport_reps[vport];
-		if (!rep->rep_if[rep_type].valid)
-			continue;
+	if (mlx5_ecpf_vport_exists(esw->dev)) {
+		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_ECPF);
+		__esw_offloads_unload_rep(esw, rep, rep_type);
+	}
 
-		rep->rep_if[rep_type].unload(rep);
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF);
+		__esw_offloads_unload_rep(esw, rep, rep_type);
 	}
+
+	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
+	__esw_offloads_unload_rep(esw, rep, rep_type);
+}
+
+static void __unload_reps_vf_vport(struct mlx5_eswitch *esw, int nvports,
+				   u8 rep_type)
+{
+	struct mlx5_eswitch_rep *rep;
+	int i;
+
+	mlx5_esw_for_each_vf_rep_reverse(esw, i, rep, nvports)
+		__esw_offloads_unload_rep(esw, rep, rep_type);
 }
 
-static void esw_offloads_unload_reps(struct mlx5_eswitch *esw, int nvports)
+static void esw_offloads_unload_vf_reps(struct mlx5_eswitch *esw, int nvports)
 {
 	u8 rep_type = NUM_REP_TYPES;
 
 	while (rep_type-- > 0)
-		esw_offloads_unload_reps_type(esw, nvports, rep_type);
+		__unload_reps_vf_vport(esw, nvports, rep_type);
 }
 
-static int esw_offloads_load_reps_type(struct mlx5_eswitch *esw, int nvports,
-				       u8 rep_type)
+static void __unload_reps_all_vport(struct mlx5_eswitch *esw, int nvports,
+				    u8 rep_type)
+{
+	__unload_reps_vf_vport(esw, nvports, rep_type);
+
+	/* Special vports must be the last to unload. */
+	__unload_reps_special_vport(esw, rep_type);
+}
+
+static void esw_offloads_unload_all_reps(struct mlx5_eswitch *esw, int nvports)
+{
+	u8 rep_type = NUM_REP_TYPES;
+
+	while (rep_type-- > 0)
+		__unload_reps_all_vport(esw, nvports, rep_type);
+}
+
+static int __esw_offloads_load_rep(struct mlx5_eswitch *esw,
+				   struct mlx5_eswitch_rep *rep, u8 rep_type)
+{
+	int err = 0;
+
+	if (rep->rep_if[rep_type].state != REP_REGISTERED)
+		return 0;
+
+	err = rep->rep_if[rep_type].load(esw->dev, rep);
+	if (err)
+		return err;
+
+	rep->rep_if[rep_type].state = REP_LOADED;
+
+	return 0;
+}
+
+static int __load_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type)
 {
 	struct mlx5_eswitch_rep *rep;
-	int vport;
 	int err;
 
-	for (vport = 0; vport < nvports; vport++) {
-		rep = &esw->offloads.vport_reps[vport];
-		if (!rep->rep_if[rep_type].valid)
-			continue;
+	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
+	err = __esw_offloads_load_rep(esw, rep, rep_type);
+	if (err)
+		return err;
 
-		err = rep->rep_if[rep_type].load(esw->dev, rep);
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF);
+		err = __esw_offloads_load_rep(esw, rep, rep_type);
 		if (err)
-			goto err_reps;
+			goto err_pf;
+	}
+
+	if (mlx5_ecpf_vport_exists(esw->dev)) {
+		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_ECPF);
+		err = __esw_offloads_load_rep(esw, rep, rep_type);
+		if (err)
+			goto err_ecpf;
 	}
 
 	return 0;
 
+err_ecpf:
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF);
+		__esw_offloads_unload_rep(esw, rep, rep_type);
+	}
+
+err_pf:
+	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
+	__esw_offloads_unload_rep(esw, rep, rep_type);
+	return err;
+}
+
+static int __load_reps_vf_vport(struct mlx5_eswitch *esw, int nvports,
+				u8 rep_type)
+{
+	struct mlx5_eswitch_rep *rep;
+	int err, i;
+
+	mlx5_esw_for_each_vf_rep(esw, i, rep, nvports) {
+		err = __esw_offloads_load_rep(esw, rep, rep_type);
+		if (err)
+			goto err_vf;
+	}
+
+	return 0;
+
+err_vf:
+	__unload_reps_vf_vport(esw, --i, rep_type);
+	return err;
+}
+
+static int esw_offloads_load_vf_reps(struct mlx5_eswitch *esw, int nvports)
+{
+	u8 rep_type = 0;
+	int err;
+
+	for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) {
+		err = __load_reps_vf_vport(esw, nvports, rep_type);
+		if (err)
+			goto err_reps;
+	}
+
+	return err;
+
 err_reps:
-	esw_offloads_unload_reps_type(esw, vport, rep_type);
+	while (rep_type-- > 0)
+		__unload_reps_vf_vport(esw, nvports, rep_type);
 	return err;
 }
 
-static int esw_offloads_load_reps(struct mlx5_eswitch *esw, int nvports)
+static int __load_reps_all_vport(struct mlx5_eswitch *esw, int nvports,
+				 u8 rep_type)
+{
+	int err;
+
+	/* Special vports must be loaded first. */
+	err = __load_reps_special_vport(esw, rep_type);
+	if (err)
+		return err;
+
+	err = __load_reps_vf_vport(esw, nvports, rep_type);
+	if (err)
+		goto err_vfs;
+
+	return 0;
+
+err_vfs:
+	__unload_reps_special_vport(esw, rep_type);
+	return err;
+}
+
+static int esw_offloads_load_all_reps(struct mlx5_eswitch *esw, int nvports)
 {
 	u8 rep_type = 0;
 	int err;
 
 	for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) {
-		err = esw_offloads_load_reps_type(esw, nvports, rep_type);
+		err = __load_reps_all_vport(esw, nvports, rep_type);
 		if (err)
 			goto err_reps;
 	}
@@ -1295,7 +1504,7 @@ static int esw_offloads_load_reps(struct mlx5_eswitch *esw, int nvports)
 
 err_reps:
 	while (rep_type-- > 0)
-		esw_offloads_unload_reps_type(esw, nvports, rep_type);
+		__unload_reps_all_vport(esw, nvports, rep_type);
 	return err;
 }
 
@@ -1398,7 +1607,7 @@ static void esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw)
 	mlx5_devcom_unregister_component(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
 }
 
-int esw_offloads_init(struct mlx5_eswitch *esw, int nvports)
+static int esw_offloads_steering_init(struct mlx5_eswitch *esw, int nvports)
 {
 	int err;
 
@@ -1408,24 +1617,16 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int nvports)
 	if (err)
 		return err;
 
-	err = esw_create_offloads_table(esw);
+	err = esw_create_offloads_table(esw, nvports);
 	if (err)
 		goto create_ft_err;
 
-	err = esw_create_vport_rx_group(esw);
+	err = esw_create_vport_rx_group(esw, nvports);
 	if (err)
 		goto create_fg_err;
 
-	err = esw_offloads_load_reps(esw, nvports);
-	if (err)
-		goto err_reps;
-
-	esw_offloads_devcom_init(esw);
 	return 0;
 
-err_reps:
-	esw_destroy_vport_rx_group(esw);
-
 create_fg_err:
 	esw_destroy_offloads_table(esw);
 
@@ -1435,6 +1636,95 @@ create_ft_err:
 	return err;
 }
 
+static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw)
+{
+	esw_destroy_vport_rx_group(esw);
+	esw_destroy_offloads_table(esw);
+	esw_destroy_offloads_fdb_tables(esw);
+}
+
+static void esw_host_params_event_handler(struct work_struct *work)
+{
+	struct mlx5_host_work *host_work;
+	struct mlx5_eswitch *esw;
+	int err, num_vf = 0;
+
+	host_work = container_of(work, struct mlx5_host_work, work);
+	esw = host_work->esw;
+
+	err = mlx5_query_host_params_num_vfs(esw->dev, &num_vf);
+	if (err || num_vf == esw->host_info.num_vfs)
+		goto out;
+
+	/* Number of VFs can only change from "0 to x" or "x to 0". */
+	if (esw->host_info.num_vfs > 0) {
+		esw_offloads_unload_vf_reps(esw, esw->host_info.num_vfs);
+	} else {
+		err = esw_offloads_load_vf_reps(esw, num_vf);
+
+		if (err)
+			goto out;
+	}
+
+	esw->host_info.num_vfs = num_vf;
+
+out:
+	kfree(host_work);
+}
+
+static int esw_host_params_event(struct notifier_block *nb,
+				 unsigned long type, void *data)
+{
+	struct mlx5_host_work *host_work;
+	struct mlx5_host_info *host_info;
+	struct mlx5_eswitch *esw;
+
+	host_work = kzalloc(sizeof(*host_work), GFP_ATOMIC);
+	if (!host_work)
+		return NOTIFY_DONE;
+
+	host_info = mlx5_nb_cof(nb, struct mlx5_host_info, nb);
+	esw = container_of(host_info, struct mlx5_eswitch, host_info);
+
+	host_work->esw = esw;
+
+	INIT_WORK(&host_work->work, esw_host_params_event_handler);
+	queue_work(esw->work_queue, &host_work->work);
+
+	return NOTIFY_OK;
+}
+
+int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports,
+		      int total_nvports)
+{
+	int err;
+
+	mutex_init(&esw->fdb_table.offloads.fdb_prio_lock);
+
+	err = esw_offloads_steering_init(esw, total_nvports);
+	if (err)
+		return err;
+
+	err = esw_offloads_load_all_reps(esw, vf_nvports);
+	if (err)
+		goto err_reps;
+
+	esw_offloads_devcom_init(esw);
+
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		MLX5_NB_INIT(&esw->host_info.nb, esw_host_params_event,
+			     HOST_PARAMS_CHANGE);
+		mlx5_eq_notifier_register(esw->dev, &esw->host_info.nb);
+		esw->host_info.num_vfs = vf_nvports;
+	}
+
+	return 0;
+
+err_reps:
+	esw_offloads_steering_cleanup(esw);
+	return err;
+}
+
 static int esw_offloads_stop(struct mlx5_eswitch *esw,
 			     struct netlink_ext_ack *extack)
 {
@@ -1454,13 +1744,21 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw,
 	return err;
 }
 
-void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports)
+void esw_offloads_cleanup(struct mlx5_eswitch *esw)
 {
+	u16 num_vfs;
+
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		mlx5_eq_notifier_unregister(esw->dev, &esw->host_info.nb);
+		flush_workqueue(esw->work_queue);
+		num_vfs = esw->host_info.num_vfs;
+	} else {
+		num_vfs = esw->dev->priv.sriov.num_vfs;
+	}
+
 	esw_offloads_devcom_cleanup(esw);
-	esw_offloads_unload_reps(esw, nvports);
-	esw_destroy_vport_rx_group(esw);
-	esw_destroy_offloads_table(esw);
-	esw_destroy_offloads_fdb_tables(esw);
+	esw_offloads_unload_all_reps(esw, num_vfs);
+	esw_offloads_steering_cleanup(esw);
 }
 
 static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
@@ -1549,7 +1847,8 @@ static int mlx5_devlink_eswitch_check(struct devlink *devlink)
 	if(!MLX5_ESWITCH_MANAGER(dev))
 		return -EPERM;
 
-	if (dev->priv.eswitch->mode == SRIOV_NONE)
+	if (dev->priv.eswitch->mode == SRIOV_NONE &&
+	    !mlx5_core_is_ecpf_esw_manager(dev))
 		return -EOPNOTSUPP;
 
 	return 0;
@@ -1761,47 +2060,45 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap)
 	return 0;
 }
 
-void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw,
-				     int vport_index,
-				     struct mlx5_eswitch_rep_if *__rep_if,
-				     u8 rep_type)
+void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw,
+				      struct mlx5_eswitch_rep_if *__rep_if,
+				      u8 rep_type)
 {
-	struct mlx5_esw_offload *offloads = &esw->offloads;
 	struct mlx5_eswitch_rep_if *rep_if;
+	struct mlx5_eswitch_rep *rep;
+	int i;
 
-	rep_if = &offloads->vport_reps[vport_index].rep_if[rep_type];
-
-	rep_if->load   = __rep_if->load;
-	rep_if->unload = __rep_if->unload;
-	rep_if->get_proto_dev = __rep_if->get_proto_dev;
-	rep_if->priv = __rep_if->priv;
+	mlx5_esw_for_all_reps(esw, i, rep) {
+		rep_if = &rep->rep_if[rep_type];
+		rep_if->load   = __rep_if->load;
+		rep_if->unload = __rep_if->unload;
+		rep_if->get_proto_dev = __rep_if->get_proto_dev;
+		rep_if->priv = __rep_if->priv;
 
-	rep_if->valid = true;
+		rep_if->state = REP_REGISTERED;
+	}
 }
-EXPORT_SYMBOL(mlx5_eswitch_register_vport_rep);
+EXPORT_SYMBOL(mlx5_eswitch_register_vport_reps);
 
-void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw,
-				       int vport_index, u8 rep_type)
+void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type)
 {
-	struct mlx5_esw_offload *offloads = &esw->offloads;
+	u16 max_vf = mlx5_core_max_vfs(esw->dev);
 	struct mlx5_eswitch_rep *rep;
+	int i;
 
-	rep = &offloads->vport_reps[vport_index];
-
-	if (esw->mode == SRIOV_OFFLOADS && esw->vports[vport_index].enabled)
-		rep->rep_if[rep_type].unload(rep);
+	if (esw->mode == SRIOV_OFFLOADS)
+		__unload_reps_all_vport(esw, max_vf, rep_type);
 
-	rep->rep_if[rep_type].valid = false;
+	mlx5_esw_for_all_reps(esw, i, rep)
+		rep->rep_if[rep_type].state = REP_UNREGISTERED;
 }
-EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_rep);
+EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_reps);
 
 void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type)
 {
-#define UPLINK_REP_INDEX 0
-	struct mlx5_esw_offload *offloads = &esw->offloads;
 	struct mlx5_eswitch_rep *rep;
 
-	rep = &offloads->vport_reps[UPLINK_REP_INDEX];
+	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
 	return rep->rep_if[rep_type].priv;
 }
 
@@ -1809,15 +2106,11 @@ void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw,
 				 int vport,
 				 u8 rep_type)
 {
-	struct mlx5_esw_offload *offloads = &esw->offloads;
 	struct mlx5_eswitch_rep *rep;
 
-	if (vport == FDB_UPLINK_VPORT)
-		vport = UPLINK_REP_INDEX;
-
-	rep = &offloads->vport_reps[vport];
+	rep = mlx5_eswitch_get_rep(esw, vport);
 
-	if (rep->rep_if[rep_type].valid &&
+	if (rep->rep_if[rep_type].state == REP_LOADED &&
 	    rep->rep_if[rep_type].get_proto_dev)
 		return rep->rep_if[rep_type].get_proto_dev(rep);
 	return NULL;
@@ -1826,13 +2119,13 @@ EXPORT_SYMBOL(mlx5_eswitch_get_proto_dev);
 
 void *mlx5_eswitch_uplink_get_proto_dev(struct mlx5_eswitch *esw, u8 rep_type)
 {
-	return mlx5_eswitch_get_proto_dev(esw, UPLINK_REP_INDEX, rep_type);
+	return mlx5_eswitch_get_proto_dev(esw, MLX5_VPORT_UPLINK, rep_type);
 }
 EXPORT_SYMBOL(mlx5_eswitch_uplink_get_proto_dev);
 
 struct mlx5_eswitch_rep *mlx5_eswitch_vport_rep(struct mlx5_eswitch *esw,
 						int vport)
 {
-	return &esw->offloads.vport_reps[vport];
+	return mlx5_eswitch_get_rep(esw, vport);
 }
 EXPORT_SYMBOL(mlx5_eswitch_vport_rep);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index 503035469d2d..5d5864e8df3c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -103,6 +103,8 @@ static const char *eqe_type_str(u8 type)
 		return "MLX5_EVENT_TYPE_STALL_EVENT";
 	case MLX5_EVENT_TYPE_CMD:
 		return "MLX5_EVENT_TYPE_CMD";
+	case MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE:
+		return "MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE";
 	case MLX5_EVENT_TYPE_PAGE_REQUEST:
 		return "MLX5_EVENT_TYPE_PAGE_REQUEST";
 	case MLX5_EVENT_TYPE_PAGE_FAULT:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index b354f3ee94c5..f2cfa012315e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -32,6 +32,7 @@
 
 #include <linux/mutex.h>
 #include <linux/mlx5/driver.h>
+#include <linux/mlx5/vport.h>
 #include <linux/mlx5/eswitch.h>
 
 #include "mlx5_core.h"
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index 2d223385dc81..04c5aca7f8c5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -343,6 +343,11 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 		roce_lag = !mlx5_sriov_is_enabled(dev0) &&
 			   !mlx5_sriov_is_enabled(dev1);
 
+#ifdef CONFIG_MLX5_ESWITCH
+		roce_lag &= dev0->priv.eswitch->mode == SRIOV_NONE &&
+			    dev1->priv.eswitch->mode == SRIOV_NONE;
+#endif
+
 		if (roce_lag)
 			mlx5_lag_remove_ib_devices(ldev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mad.c b/drivers/net/ethernet/mellanox/mlx5/core/mad.c
deleted file mode 100644
index 3a3b0005fd2b..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/mad.c
+++ /dev/null
@@ -1,75 +0,0 @@
-/*
- * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mlx5/driver.h>
-#include <linux/mlx5/cmd.h>
-#include "mlx5_core.h"
-
-int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb,
-		      u16 opmod, u8 port)
-{
-	int outlen = MLX5_ST_SZ_BYTES(mad_ifc_out);
-	int inlen = MLX5_ST_SZ_BYTES(mad_ifc_in);
-	int err = -ENOMEM;
-	void *data;
-	void *resp;
-	u32 *out;
-	u32 *in;
-
-	in = kzalloc(inlen, GFP_KERNEL);
-	out = kzalloc(outlen, GFP_KERNEL);
-	if (!in || !out)
-		goto out;
-
-	MLX5_SET(mad_ifc_in, in, opcode, MLX5_CMD_OP_MAD_IFC);
-	MLX5_SET(mad_ifc_in, in, op_mod, opmod);
-	MLX5_SET(mad_ifc_in, in, port, port);
-
-	data = MLX5_ADDR_OF(mad_ifc_in, in, mad);
-	memcpy(data, inb, MLX5_FLD_SZ_BYTES(mad_ifc_in, mad));
-
-	err = mlx5_cmd_exec(dev, in, inlen, out, outlen);
-	if (err)
-		goto out;
-
-	resp = MLX5_ADDR_OF(mad_ifc_out, out, response_mad_packet);
-	memcpy(outb, resp,
-	       MLX5_FLD_SZ_BYTES(mad_ifc_out, response_mad_packet));
-
-out:
-	kfree(out);
-	kfree(in);
-	return err;
-}
-EXPORT_SYMBOL_GPL(mlx5_core_mad_ifc);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index be81b319b0dc..40d591c8e76c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -65,6 +65,7 @@
 #include "lib/vxlan.h"
 #include "lib/devcom.h"
 #include "diag/fw_tracer.h"
+#include "ecpf.h"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver");
@@ -459,6 +460,50 @@ static int handle_hca_cap_atomic(struct mlx5_core_dev *dev)
 	return err;
 }
 
+static int handle_hca_cap_odp(struct mlx5_core_dev *dev)
+{
+	void *set_hca_cap;
+	void *set_ctx;
+	int set_sz;
+	int err;
+
+	if (!MLX5_CAP_GEN(dev, pg))
+		return 0;
+
+	err = mlx5_core_get_caps(dev, MLX5_CAP_ODP);
+	if (err)
+		return err;
+
+	if (!(MLX5_CAP_ODP_MAX(dev, ud_odp_caps.srq_receive) ||
+	      MLX5_CAP_ODP_MAX(dev, rc_odp_caps.srq_receive) ||
+	      MLX5_CAP_ODP_MAX(dev, xrc_odp_caps.srq_receive)))
+		return 0;
+
+	set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in);
+	set_ctx = kzalloc(set_sz, GFP_KERNEL);
+	if (!set_ctx)
+		return -ENOMEM;
+
+	set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability);
+	memcpy(set_hca_cap, dev->caps.hca_cur[MLX5_CAP_ODP],
+	       MLX5_ST_SZ_BYTES(odp_cap));
+
+	/* set ODP SRQ support for RC/UD and XRC transports */
+	MLX5_SET(odp_cap, set_hca_cap, ud_odp_caps.srq_receive,
+		 MLX5_CAP_ODP_MAX(dev, ud_odp_caps.srq_receive));
+
+	MLX5_SET(odp_cap, set_hca_cap, rc_odp_caps.srq_receive,
+		 MLX5_CAP_ODP_MAX(dev, rc_odp_caps.srq_receive));
+
+	MLX5_SET(odp_cap, set_hca_cap, xrc_odp_caps.srq_receive,
+		 MLX5_CAP_ODP_MAX(dev, xrc_odp_caps.srq_receive));
+
+	err = set_caps(dev, set_ctx, set_sz, MLX5_SET_HCA_CAP_OP_MOD_ODP);
+
+	kfree(set_ctx);
+	return err;
+}
+
 static int handle_hca_cap(struct mlx5_core_dev *dev)
 {
 	void *set_ctx = NULL;
@@ -567,6 +612,8 @@ int mlx5_core_enable_hca(struct mlx5_core_dev *dev, u16 func_id)
 
 	MLX5_SET(enable_hca_in, in, opcode, MLX5_CMD_OP_ENABLE_HCA);
 	MLX5_SET(enable_hca_in, in, function_id, func_id);
+	MLX5_SET(enable_hca_in, in, embedded_cpu_function,
+		 dev->caps.embedded_cpu);
 	return mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
 }
 
@@ -577,6 +624,8 @@ int mlx5_core_disable_hca(struct mlx5_core_dev *dev, u16 func_id)
 
 	MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA);
 	MLX5_SET(disable_hca_in, in, function_id, func_id);
+	MLX5_SET(enable_hca_in, in, embedded_cpu_function,
+		 dev->caps.embedded_cpu);
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
@@ -693,6 +742,11 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 		goto err_clr_master;
 	}
 
+	if (pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP32) &&
+	    pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP64) &&
+	    pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP128))
+		mlx5_core_dbg(dev, "Enabling pci atomics failed\n");
+
 	dev->iseg_base = pci_resource_start(dev->pdev, 0);
 	dev->iseg = ioremap(dev->iseg_base, sizeof(*dev->iseg));
 	if (!dev->iseg) {
@@ -849,6 +903,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	struct pci_dev *pdev = dev->pdev;
 	int err;
 
+	dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev);
 	mutex_lock(&dev->intf_state_mutex);
 	if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
 		dev_warn(&dev->pdev->dev, "%s: interface is up, NOP\n",
@@ -926,6 +981,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto reclaim_boot_pages;
 	}
 
+	err = handle_hca_cap_odp(dev);
+	if (err) {
+		dev_err(&pdev->dev, "handle_hca_cap_odp failed\n");
+		goto reclaim_boot_pages;
+	}
+
 	err = mlx5_satisfy_startup_pages(dev, 0);
 	if (err) {
 		dev_err(&pdev->dev, "failed to allocate init pages\n");
@@ -1014,6 +1075,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto err_sriov;
 	}
 
+	err = mlx5_ec_init(dev);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to init embedded CPU\n");
+		goto err_ec;
+	}
+
 	if (mlx5_device_registered(dev)) {
 		mlx5_attach_device(dev);
 	} else {
@@ -1031,6 +1098,9 @@ out:
 	return 0;
 
 err_reg_dev:
+	mlx5_ec_cleanup(dev);
+
+err_ec:
 	mlx5_sriov_detach(dev);
 
 err_sriov:
@@ -1105,6 +1175,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	if (mlx5_device_registered(dev))
 		mlx5_detach_device(dev);
 
+	mlx5_ec_cleanup(dev);
 	mlx5_sriov_detach(dev);
 	mlx5_cleanup_fs(dev);
 	mlx5_accel_ipsec_cleanup(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 4fdac020b795..9529cf9623e3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -121,7 +121,7 @@ int mlx5_modify_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 				       u32 modify_bitmask);
 int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 					u32 element_id);
-int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev);
+int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages);
 u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev,
 			     struct ptp_system_timestamp *sts);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index 0670165afd5f..ea744d8466ea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -51,9 +51,10 @@ void mlx5_cleanup_mkey_table(struct mlx5_core_dev *dev)
 
 int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev,
 			     struct mlx5_core_mkey *mkey,
-			     u32 *in, int inlen,
-			     u32 *out, int outlen,
-			     mlx5_cmd_cbk_t callback, void *context)
+			     struct mlx5_async_ctx *async_ctx, u32 *in,
+			     int inlen, u32 *out, int outlen,
+			     mlx5_async_cbk_t callback,
+			     struct mlx5_async_work *context)
 {
 	struct mlx5_mkey_table *table = &dev->priv.mkey_table;
 	u32 lout[MLX5_ST_SZ_DW(create_mkey_out)] = {0};
@@ -71,7 +72,7 @@ int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev,
 	MLX5_SET(mkc, mkc, mkey_7_0, key);
 
 	if (callback)
-		return mlx5_cmd_exec_cb(dev, in, inlen, out, outlen,
+		return mlx5_cmd_exec_cb(async_ctx, in, inlen, out, outlen,
 					callback, context);
 
 	err = mlx5_cmd_exec(dev, in, inlen, lout, sizeof(lout));
@@ -105,7 +106,7 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev,
 			  struct mlx5_core_mkey *mkey,
 			  u32 *in, int inlen)
 {
-	return mlx5_core_create_mkey_cb(dev, mkey, in, inlen,
+	return mlx5_core_create_mkey_cb(dev, mkey, NULL, in, inlen,
 					NULL, 0, NULL, NULL);
 }
 EXPORT_SYMBOL(mlx5_core_create_mkey);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index a83b517b0714..41025387ff2c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -48,6 +48,7 @@ enum {
 struct mlx5_pages_req {
 	struct mlx5_core_dev *dev;
 	u16	func_id;
+	u8	ec_function;
 	s32	npages;
 	struct work_struct work;
 };
@@ -143,6 +144,7 @@ static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id,
 	MLX5_SET(query_pages_in, in, op_mod, boot ?
 		 MLX5_QUERY_PAGES_IN_OP_MOD_BOOT_PAGES :
 		 MLX5_QUERY_PAGES_IN_OP_MOD_INIT_PAGES);
+	MLX5_SET(query_pages_in, in, embedded_cpu_function, mlx5_core_is_ecpf(dev));
 
 	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 	if (err)
@@ -253,7 +255,8 @@ err_mapping:
 	return err;
 }
 
-static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id)
+static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id,
+			     bool ec_function)
 {
 	u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0};
 	u32 in[MLX5_ST_SZ_DW(manage_pages_in)]   = {0};
@@ -262,6 +265,7 @@ static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id)
 	MLX5_SET(manage_pages_in, in, opcode, MLX5_CMD_OP_MANAGE_PAGES);
 	MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_CANT_GIVE);
 	MLX5_SET(manage_pages_in, in, function_id, func_id);
+	MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function);
 
 	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 	if (err)
@@ -270,7 +274,7 @@ static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id)
 }
 
 static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
-		      int notify_fail)
+		      int notify_fail, bool ec_function)
 {
 	u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0};
 	int inlen = MLX5_ST_SZ_BYTES(manage_pages_in);
@@ -305,6 +309,7 @@ retry:
 	MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_GIVE);
 	MLX5_SET(manage_pages_in, in, function_id, func_id);
 	MLX5_SET(manage_pages_in, in, input_num_entries, npages);
+	MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function);
 
 	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
 	if (err) {
@@ -316,8 +321,11 @@ retry:
 	dev->priv.fw_pages += npages;
 	if (func_id)
 		dev->priv.vfs_pages += npages;
+	else if (mlx5_core_is_ecpf(dev) && !ec_function)
+		dev->priv.peer_pf_pages += npages;
 
-	mlx5_core_dbg(dev, "err %d\n", err);
+	mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x, err %d\n",
+		      npages, ec_function, func_id, err);
 
 	kvfree(in);
 	return 0;
@@ -328,7 +336,7 @@ out_4k:
 out_free:
 	kvfree(in);
 	if (notify_fail)
-		page_notify_fail(dev, func_id);
+		page_notify_fail(dev, func_id, ec_function);
 	return err;
 }
 
@@ -364,7 +372,7 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev,
 }
 
 static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
-			 int *nclaimed)
+			 int *nclaimed, bool ec_function)
 {
 	int outlen = MLX5_ST_SZ_BYTES(manage_pages_out);
 	u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {0};
@@ -385,6 +393,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 	MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_TAKE);
 	MLX5_SET(manage_pages_in, in, function_id, func_id);
 	MLX5_SET(manage_pages_in, in, input_num_entries, npages);
+	MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function);
 
 	mlx5_core_dbg(dev, "npages %d, outlen %d\n", npages, outlen);
 	err = reclaim_pages_cmd(dev, in, sizeof(in), out, outlen);
@@ -410,6 +419,8 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 	dev->priv.fw_pages -= num_claimed;
 	if (func_id)
 		dev->priv.vfs_pages -= num_claimed;
+	else if (mlx5_core_is_ecpf(dev) && !ec_function)
+		dev->priv.peer_pf_pages -= num_claimed;
 
 out_free:
 	kvfree(out);
@@ -423,9 +434,10 @@ static void pages_work_handler(struct work_struct *work)
 	int err = 0;
 
 	if (req->npages < 0)
-		err = reclaim_pages(dev, req->func_id, -1 * req->npages, NULL);
+		err = reclaim_pages(dev, req->func_id, -1 * req->npages, NULL,
+				    req->ec_function);
 	else if (req->npages > 0)
-		err = give_pages(dev, req->func_id, req->npages, 1);
+		err = give_pages(dev, req->func_id, req->npages, 1, req->ec_function);
 
 	if (err)
 		mlx5_core_warn(dev, "%s fail %d\n",
@@ -434,6 +446,10 @@ static void pages_work_handler(struct work_struct *work)
 	kfree(req);
 }
 
+enum {
+	EC_FUNCTION_MASK = 0x8000,
+};
+
 static int req_pages_handler(struct notifier_block *nb,
 			     unsigned long type, void *data)
 {
@@ -441,6 +457,7 @@ static int req_pages_handler(struct notifier_block *nb,
 	struct mlx5_core_dev *dev;
 	struct mlx5_priv *priv;
 	struct mlx5_eqe *eqe;
+	bool ec_function;
 	u16 func_id;
 	s32 npages;
 
@@ -450,6 +467,7 @@ static int req_pages_handler(struct notifier_block *nb,
 
 	func_id = be16_to_cpu(eqe->data.req_pages.func_id);
 	npages  = be32_to_cpu(eqe->data.req_pages.num_pages);
+	ec_function = be16_to_cpu(eqe->data.req_pages.ec_function) & EC_FUNCTION_MASK;
 	mlx5_core_dbg(dev, "page request for func 0x%x, npages %d\n",
 		      func_id, npages);
 	req = kzalloc(sizeof(*req), GFP_ATOMIC);
@@ -461,6 +479,7 @@ static int req_pages_handler(struct notifier_block *nb,
 	req->dev = dev;
 	req->func_id = func_id;
 	req->npages = npages;
+	req->ec_function = ec_function;
 	INIT_WORK(&req->work, pages_work_handler);
 	queue_work(dev->priv.pg_wq, &req->work);
 	return NOTIFY_OK;
@@ -479,7 +498,7 @@ int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot)
 	mlx5_core_dbg(dev, "requested %d %s pages for func_id 0x%x\n",
 		      npages, boot ? "boot" : "init", func_id);
 
-	return give_pages(dev, func_id, npages, 0);
+	return give_pages(dev, func_id, npages, 0, mlx5_core_is_ecpf(dev));
 }
 
 enum {
@@ -513,7 +532,7 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
 			fwp = rb_entry(p, struct fw_page, rb_node);
 			err = reclaim_pages(dev, fwp->func_id,
 					    optimal_reclaimed_pages(),
-					    &nclaimed);
+					    &nclaimed, mlx5_core_is_ecpf(dev));
 
 			if (err) {
 				mlx5_core_warn(dev, "failed reclaiming pages (%d)\n",
@@ -535,6 +554,9 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
 	WARN(dev->priv.vfs_pages,
 	     "VFs FW pages counter is %d after reclaiming all pages\n",
 	     dev->priv.vfs_pages);
+	WARN(dev->priv.peer_pf_pages,
+	     "Peer PF FW pages counter is %d after reclaiming all pages\n",
+	     dev->priv.peer_pf_pages);
 
 	return 0;
 }
@@ -567,10 +589,10 @@ void mlx5_pagealloc_stop(struct mlx5_core_dev *dev)
 	flush_workqueue(dev->priv.pg_wq);
 }
 
-int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev)
+int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages)
 {
 	unsigned long end = jiffies + msecs_to_jiffies(MAX_RECLAIM_VFS_PAGES_TIME_MSECS);
-	int prev_vfs_pages = dev->priv.vfs_pages;
+	int prev_pages = *pages;
 
 	/* In case of internal error we will free the pages manually later */
 	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
@@ -578,16 +600,16 @@ int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev)
 		return 0;
 	}
 
-	mlx5_core_dbg(dev, "Waiting for %d pages from %s\n", prev_vfs_pages,
+	mlx5_core_dbg(dev, "Waiting for %d pages from %s\n", prev_pages,
 		      dev->priv.name);
-	while (dev->priv.vfs_pages) {
+	while (*pages) {
 		if (time_after(jiffies, end)) {
-			mlx5_core_warn(dev, "aborting while there are %d pending pages\n", dev->priv.vfs_pages);
+			mlx5_core_warn(dev, "aborting while there are %d pending pages\n", *pages);
 			return -ETIMEDOUT;
 		}
-		if (dev->priv.vfs_pages < prev_vfs_pages) {
+		if (*pages < prev_pages) {
 			end = jiffies + msecs_to_jiffies(MAX_RECLAIM_VFS_PAGES_TIME_MSECS);
-			prev_vfs_pages = dev->priv.vfs_pages;
+			prev_pages = *pages;
 		}
 		msleep(50);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 2b82f35f4c35..b81542820528 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -30,10 +30,7 @@
  * SOFTWARE.
  */
 
-#include <linux/module.h>
-#include <linux/mlx5/driver.h>
 #include <linux/mlx5/port.h>
-#include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
 
 int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in,
@@ -157,44 +154,6 @@ int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration)
 				    sizeof(out), MLX5_REG_MLCR, 0, 1);
 }
 
-int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev,
-			      u32 *proto_cap, int proto_mask)
-{
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
-	int err;
-
-	err = mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1);
-	if (err)
-		return err;
-
-	if (proto_mask == MLX5_PTYS_EN)
-		*proto_cap = MLX5_GET(ptys_reg, out, eth_proto_capability);
-	else
-		*proto_cap = MLX5_GET(ptys_reg, out, ib_proto_capability);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mlx5_query_port_proto_cap);
-
-int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev,
-				u32 *proto_admin, int proto_mask)
-{
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
-	int err;
-
-	err = mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1);
-	if (err)
-		return err;
-
-	if (proto_mask == MLX5_PTYS_EN)
-		*proto_admin = MLX5_GET(ptys_reg, out, eth_proto_admin);
-	else
-		*proto_admin = MLX5_GET(ptys_reg, out, ib_proto_admin);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mlx5_query_port_proto_admin);
-
 int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev,
 				    u8 *link_width_oper, u8 local_port)
 {
@@ -211,23 +170,6 @@ int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev,
 }
 EXPORT_SYMBOL_GPL(mlx5_query_port_link_width_oper);
 
-int mlx5_query_port_eth_proto_oper(struct mlx5_core_dev *dev,
-				   u32 *proto_oper, u8 local_port)
-{
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
-	int err;
-
-	err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN,
-				   local_port);
-	if (err)
-		return err;
-
-	*proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper);
-
-	return 0;
-}
-EXPORT_SYMBOL(mlx5_query_port_eth_proto_oper);
-
 int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev,
 				  u8 *proto_oper, u8 local_port)
 {
@@ -245,35 +187,6 @@ int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev,
 }
 EXPORT_SYMBOL(mlx5_query_port_ib_proto_oper);
 
-int mlx5_set_port_ptys(struct mlx5_core_dev *dev, bool an_disable,
-		       u32 proto_admin, int proto_mask)
-{
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
-	u32 in[MLX5_ST_SZ_DW(ptys_reg)];
-	u8 an_disable_admin;
-	u8 an_disable_cap;
-	u8 an_status;
-
-	mlx5_query_port_autoneg(dev, proto_mask, &an_status,
-				&an_disable_cap, &an_disable_admin);
-	if (!an_disable_cap && an_disable)
-		return -EPERM;
-
-	memset(in, 0, sizeof(in));
-
-	MLX5_SET(ptys_reg, in, local_port, 1);
-	MLX5_SET(ptys_reg, in, an_disable_admin, an_disable);
-	MLX5_SET(ptys_reg, in, proto_mask, proto_mask);
-	if (proto_mask == MLX5_PTYS_EN)
-		MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin);
-	else
-		MLX5_SET(ptys_reg, in, ib_proto_admin, proto_admin);
-
-	return mlx5_core_access_reg(dev, in, sizeof(in), out,
-				    sizeof(out), MLX5_REG_PTYS, 0, 1);
-}
-EXPORT_SYMBOL_GPL(mlx5_set_port_ptys);
-
 /* This function should be used after setting a port register only */
 void mlx5_toggle_port_link(struct mlx5_core_dev *dev)
 {
@@ -606,25 +519,6 @@ int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx)
 }
 EXPORT_SYMBOL_GPL(mlx5_query_port_pfc);
 
-void mlx5_query_port_autoneg(struct mlx5_core_dev *dev, int proto_mask,
-			     u8 *an_status,
-			     u8 *an_disable_cap, u8 *an_disable_admin)
-{
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
-
-	*an_status = 0;
-	*an_disable_cap = 0;
-	*an_disable_admin = 0;
-
-	if (mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1))
-		return;
-
-	*an_status = MLX5_GET(ptys_reg, out, an_status);
-	*an_disable_cap = MLX5_GET(ptys_reg, out, an_disable_cap);
-	*an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin);
-}
-EXPORT_SYMBOL_GPL(mlx5_query_port_autoneg);
-
 int mlx5_max_tc(struct mlx5_core_dev *mdev)
 {
 	u8 num_tc = MLX5_CAP_GEN(mdev, max_tc) ? : 8;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index 6e178030d8fb..7b23fa8d2d60 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -147,7 +147,7 @@ out:
 	if (MLX5_ESWITCH_MANAGER(dev))
 		mlx5_eswitch_disable_sriov(dev->priv.eswitch);
 
-	if (mlx5_wait_for_vf_pages(dev))
+	if (mlx5_wait_for_pages(dev, &dev->priv.vfs_pages))
 		mlx5_core_warn(dev, "timeout reclaiming VFs pages\n");
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 9b150ce9d315..ef95feca9961 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -64,7 +64,7 @@ u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport)
 }
 
 int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
-				  u16 vport, u8 state)
+				  u16 vport, u8 other_vport, u8 state)
 {
 	u32 in[MLX5_ST_SZ_DW(modify_vport_state_in)]   = {0};
 	u32 out[MLX5_ST_SZ_DW(modify_vport_state_out)] = {0};
@@ -73,8 +73,7 @@ int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
 		 MLX5_CMD_OP_MODIFY_VPORT_STATE);
 	MLX5_SET(modify_vport_state_in, in, op_mod, opmod);
 	MLX5_SET(modify_vport_state_in, in, vport_number, vport);
-	if (vport)
-		MLX5_SET(modify_vport_state_in, in, other_vport, 1);
+	MLX5_SET(modify_vport_state_in, in, other_vport, other_vport);
 	MLX5_SET(modify_vport_state_in, in, admin_state, state);
 
 	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
@@ -255,7 +254,7 @@ int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu)
 EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mtu);
 
 int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev,
-				  u32 vport,
+				  u16 vport,
 				  enum mlx5_list_type list_type,
 				  u8 addr_list[][ETH_ALEN],
 				  int *list_size)
@@ -373,7 +372,7 @@ int mlx5_modify_nic_vport_mac_list(struct mlx5_core_dev *dev,
 EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mac_list);
 
 int mlx5_query_nic_vport_vlans(struct mlx5_core_dev *dev,
-			       u32 vport,
+			       u16 vport,
 			       u16 vlans[],
 			       int *size)
 {
@@ -526,7 +525,7 @@ int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid)
 EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_node_guid);
 
 int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
-				    u32 vport, u64 node_guid)
+				    u16 vport, u64 node_guid)
 {
 	int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in);
 	void *nic_vport_context;
@@ -827,7 +826,7 @@ int mlx5_query_hca_vport_node_guid(struct mlx5_core_dev *dev,
 EXPORT_SYMBOL_GPL(mlx5_query_hca_vport_node_guid);
 
 int mlx5_query_nic_vport_promisc(struct mlx5_core_dev *mdev,
-				 u32 vport,
+				 u16 vport,
 				 int *promisc_uc,
 				 int *promisc_mc,
 				 int *promisc_all)
@@ -1057,7 +1056,7 @@ free:
 EXPORT_SYMBOL_GPL(mlx5_core_query_vport_counter);
 
 int mlx5_query_vport_down_stats(struct mlx5_core_dev *mdev, u16 vport,
-				u64 *rx_discard_vport_down,
+				u8 other_vport, u64 *rx_discard_vport_down,
 				u64 *tx_discard_vport_down)
 {
 	u32 out[MLX5_ST_SZ_DW(query_vnic_env_out)] = {0};
@@ -1068,8 +1067,7 @@ int mlx5_query_vport_down_stats(struct mlx5_core_dev *mdev, u16 vport,
 		 MLX5_CMD_OP_QUERY_VNIC_ENV);
 	MLX5_SET(query_vnic_env_in, in, op_mod, 0);
 	MLX5_SET(query_vnic_env_in, in, vport_number, vport);
-	if (vport)
-		MLX5_SET(query_vnic_env_in, in, other_vport, 1);
+	MLX5_SET(query_vnic_env_in, in, other_vport, other_vport);
 
 	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
 	if (err)