Merge branch 'mlx5-next' into rdma.git for-next

From
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux

To resolve conflicts with net-next and pick up the first patch.

* branch 'mlx5-next':
  net/mlx5: Factor out HCA capabilities functions
  IB/mlx5: Add support for 50Gbps per lane link modes
  net/mlx5: Add support to ext_* fields introduced in Port Type and Speed register
  net/mlx5: Add new fields to Port Type and Speed register
  net/mlx5: Refactor queries to speed fields in Port Type and Speed register
  net/mlx5: E-Switch, Avoid magic numbers when initializing offloads mode
  net/mlx5: Relocate vport macros to the vport header file
  net/mlx5: E-Switch, Normalize the name of uplink vport number
  net/mlx5: Provide an alternative VF upper bound for ECPF
  net/mlx5: Add host params change event
  net/mlx5: Add query host params command
  net/mlx5: Update enable HCA dependency
  net/mlx5: Introduce Mellanox SmartNIC and modify page management logic
  IB/mlx5: Use unified register/load function for uplink and VF vports
  net/mlx5: Use consistent vport num argument type
  net/mlx5: Use void pointer as the type in address_of macro
  net/mlx5: Align ODP capability function with netdev coding style
  mlx5: use RCU lock in mlx5_eq_cq_get()
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

drivers/infiniband/hw/mlx5/ib_rep.c

@@ -3,10 +3,11 @@
  * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
  */
 
+#include <linux/mlx5/vport.h>
 #include "ib_rep.h"
 #include "srq.h"
 
-static const struct mlx5_ib_profile rep_profile = {
+static const struct mlx5_ib_profile vf_rep_profile = {
 	STAGE_CREATE(MLX5_IB_STAGE_INIT,
 		     mlx5_ib_stage_init_init,
 		     mlx5_ib_stage_init_cleanup),
@@ -45,31 +46,17 @@ static const struct mlx5_ib_profile rep_profile = {
 		     NULL),
 };
 
-static int
-mlx5_ib_nic_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
-{
-	struct mlx5_ib_dev *ibdev;
-
-	ibdev = mlx5_ib_rep_to_dev(rep);
-	if (!__mlx5_ib_add(ibdev, ibdev->profile))
-		return -EINVAL;
-	return 0;
-}
-
-static void
-mlx5_ib_nic_rep_unload(struct mlx5_eswitch_rep *rep)
-{
-	struct mlx5_ib_dev *ibdev;
-
-	ibdev = mlx5_ib_rep_to_dev(rep);
-	__mlx5_ib_remove(ibdev, ibdev->profile, MLX5_IB_STAGE_MAX);
-}
-
 static int
 mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 {
+	const struct mlx5_ib_profile *profile;
 	struct mlx5_ib_dev *ibdev;
 
+	if (rep->vport == MLX5_VPORT_UPLINK)
+		profile = &uplink_rep_profile;
+	else
+		profile = &vf_rep_profile;
+
 	ibdev = ib_alloc_device(mlx5_ib_dev, ib_dev);
 	if (!ibdev)
 		return -ENOMEM;
@@ -78,7 +65,7 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	ibdev->mdev = dev;
 	ibdev->num_ports = max(MLX5_CAP_GEN(dev, num_ports),
 			       MLX5_CAP_GEN(dev, num_vhca_ports));
-	if (!__mlx5_ib_add(ibdev, &rep_profile)) {
+	if (!__mlx5_ib_add(ibdev, profile)) {
 		ib_dealloc_device(&ibdev->ib_dev);
 		return -EINVAL;
 	}
@@ -107,15 +94,14 @@ static void *mlx5_ib_vport_get_proto_dev(struct mlx5_eswitch_rep *rep)
 	return mlx5_ib_rep_to_dev(rep);
 }
 
-static void mlx5_ib_rep_register_vf_vports(struct mlx5_ib_dev *dev)
+void mlx5_ib_register_vport_reps(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_eswitch *esw   = dev->mdev->priv.eswitch;
-	int total_vfs = MLX5_TOTAL_VPORTS(dev->mdev);
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	int total_vports = MLX5_TOTAL_VPORTS(mdev);
+	struct mlx5_eswitch_rep_if rep_if = {};
 	int vport;
 
-	for (vport = 1; vport < total_vfs; vport++) {
-		struct mlx5_eswitch_rep_if rep_if = {};
-
+	for (vport = 0; vport < total_vports; vport++) {
 		rep_if.load = mlx5_ib_vport_rep_load;
 		rep_if.unload = mlx5_ib_vport_rep_unload;
 		rep_if.get_proto_dev = mlx5_ib_vport_get_proto_dev;
@@ -123,39 +109,16 @@ static void mlx5_ib_rep_register_vf_vports(struct mlx5_ib_dev *dev)
 	}
 }
 
-static void mlx5_ib_rep_unregister_vf_vports(struct mlx5_ib_dev *dev)
+void mlx5_ib_unregister_vport_reps(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_eswitch *esw   = dev->mdev->priv.eswitch;
-	int total_vfs = MLX5_TOTAL_VPORTS(dev->mdev);
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	int total_vports = MLX5_TOTAL_VPORTS(mdev);
 	int vport;
 
-	for (vport = 1; vport < total_vfs; vport++)
+	for (vport = total_vports - 1; vport >= 0; vport--)
 		mlx5_eswitch_unregister_vport_rep(esw, vport, REP_IB);
 }
 
-void mlx5_ib_register_vport_reps(struct mlx5_ib_dev *dev)
-{
-	struct mlx5_eswitch *esw = dev->mdev->priv.eswitch;
-	struct mlx5_eswitch_rep_if rep_if = {};
-
-	rep_if.load = mlx5_ib_nic_rep_load;
-	rep_if.unload = mlx5_ib_nic_rep_unload;
-	rep_if.get_proto_dev = mlx5_ib_vport_get_proto_dev;
-	rep_if.priv = dev;
-
-	mlx5_eswitch_register_vport_rep(esw, 0, &rep_if, REP_IB);
-
-	mlx5_ib_rep_register_vf_vports(dev);
-}
-
-void mlx5_ib_unregister_vport_reps(struct mlx5_ib_dev *dev)
-{
-	struct mlx5_eswitch *esw   = dev->mdev->priv.eswitch;
-
-	mlx5_ib_rep_unregister_vf_vports(dev); /* VFs vports */
-	mlx5_eswitch_unregister_vport_rep(esw, 0, REP_IB); /* UPLINK PF*/
-}
-
 u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw)
 {
 	return mlx5_eswitch_mode(esw);

drivers/infiniband/hw/mlx5/ib_rep.h

@@ -10,14 +10,16 @@
 #include "mlx5_ib.h"
 
 #ifdef CONFIG_MLX5_ESWITCH
+extern const struct mlx5_ib_profile uplink_rep_profile;
+
 u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw);
 struct mlx5_ib_dev *mlx5_ib_get_rep_ibdev(struct mlx5_eswitch *esw,
 					  int vport_index);
 struct mlx5_ib_dev *mlx5_ib_get_uplink_ibdev(struct mlx5_eswitch *esw);
 struct mlx5_eswitch_rep *mlx5_ib_vport_rep(struct mlx5_eswitch *esw,
 					   int vport_index);
-void mlx5_ib_register_vport_reps(struct mlx5_ib_dev *dev);
-void mlx5_ib_unregister_vport_reps(struct mlx5_ib_dev *dev);
+void mlx5_ib_register_vport_reps(struct mlx5_core_dev *mdev);
+void mlx5_ib_unregister_vport_reps(struct mlx5_core_dev *mdev);
 int create_flow_rule_vport_sq(struct mlx5_ib_dev *dev,
 			      struct mlx5_ib_sq *sq);
 struct net_device *mlx5_ib_get_rep_netdev(struct mlx5_eswitch *esw,
@@ -48,8 +50,8 @@ struct mlx5_eswitch_rep *mlx5_ib_vport_rep(struct mlx5_eswitch *esw,
 	return NULL;
 }
 
-static inline void mlx5_ib_register_vport_reps(struct mlx5_ib_dev *dev) {}
-static inline void mlx5_ib_unregister_vport_reps(struct mlx5_ib_dev *dev) {}
+static inline void mlx5_ib_register_vport_reps(struct mlx5_core_dev *mdev) {}
+static inline void mlx5_ib_unregister_vport_reps(struct mlx5_core_dev *mdev) {}
 static inline int create_flow_rule_vport_sq(struct mlx5_ib_dev *dev,
 					    struct mlx5_ib_sq *sq)
 {

drivers/infiniband/hw/mlx5/main.c

@@ -331,8 +331,8 @@ void mlx5_ib_put_native_port_mdev(struct mlx5_ib_dev *ibdev, u8 port_num)
 	spin_unlock(&port->mp.mpi_lock);
 }
 
-static int translate_eth_proto_oper(u32 eth_proto_oper, u8 *active_speed,
-				    u8 *active_width)
+static int translate_eth_legacy_proto_oper(u32 eth_proto_oper, u8 *active_speed,
+					   u8 *active_width)
 {
 	switch (eth_proto_oper) {
 	case MLX5E_PROT_MASK(MLX5E_1000BASE_CX_SGMII):
@@ -389,10 +389,66 @@ static int translate_eth_proto_oper(u32 eth_proto_oper, u8 *active_speed,
 	return 0;
 }
 
+static int translate_eth_ext_proto_oper(u32 eth_proto_oper, u8 *active_speed,
+					u8 *active_width)
+{
+	switch (eth_proto_oper) {
+	case MLX5E_PROT_MASK(MLX5E_SGMII_100M):
+	case MLX5E_PROT_MASK(MLX5E_1000BASE_X_SGMII):
+		*active_width = IB_WIDTH_1X;
+		*active_speed = IB_SPEED_SDR;
+		break;
+	case MLX5E_PROT_MASK(MLX5E_5GBASE_R):
+		*active_width = IB_WIDTH_1X;
+		*active_speed = IB_SPEED_DDR;
+		break;
+	case MLX5E_PROT_MASK(MLX5E_10GBASE_XFI_XAUI_1):
+		*active_width = IB_WIDTH_1X;
+		*active_speed = IB_SPEED_QDR;
+		break;
+	case MLX5E_PROT_MASK(MLX5E_40GBASE_XLAUI_4_XLPPI_4):
+		*active_width = IB_WIDTH_4X;
+		*active_speed = IB_SPEED_QDR;
+		break;
+	case MLX5E_PROT_MASK(MLX5E_25GAUI_1_25GBASE_CR_KR):
+		*active_width = IB_WIDTH_1X;
+		*active_speed = IB_SPEED_EDR;
+		break;
+	case MLX5E_PROT_MASK(MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2):
+	case MLX5E_PROT_MASK(MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR):
+		*active_width = IB_WIDTH_1X;
+		*active_speed = IB_SPEED_HDR;
+		break;
+	case MLX5E_PROT_MASK(MLX5E_100GAUI_2_100GBASE_CR2_KR2):
+		*active_width = IB_WIDTH_2X;
+		*active_speed = IB_SPEED_HDR;
+		break;
+	case MLX5E_PROT_MASK(MLX5E_200GAUI_4_200GBASE_CR4_KR4):
+		*active_width = IB_WIDTH_4X;
+		*active_speed = IB_SPEED_HDR;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int translate_eth_proto_oper(u32 eth_proto_oper, u8 *active_speed,
+				    u8 *active_width, bool ext)
+{
+	return ext ?
+		translate_eth_ext_proto_oper(eth_proto_oper, active_speed,
+					     active_width) :
+		translate_eth_legacy_proto_oper(eth_proto_oper, active_speed,
+						active_width);
+}
+
 static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 				struct ib_port_attr *props)
 {
 	struct mlx5_ib_dev *dev = to_mdev(device);
+	u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {0};
 	struct mlx5_core_dev *mdev;
 	struct net_device *ndev, *upper;
 	enum ib_mtu ndev_ib_mtu;
@@ -400,6 +456,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 	u16 qkey_viol_cntr;
 	u32 eth_prot_oper;
 	u8 mdev_port_num;
+	bool ext;
 	int err;
 
 	mdev = mlx5_ib_get_native_port_mdev(dev, port_num, &mdev_port_num);
@@ -416,16 +473,18 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 	/* Possible bad flows are checked before filling out props so in case
 	 * of an error it will still be zeroed out.
 	 */
-	err = mlx5_query_port_eth_proto_oper(mdev, &eth_prot_oper,
-					     mdev_port_num);
+	err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN,
+				   mdev_port_num);
 	if (err)
 		goto out;
+	ext = MLX5_CAP_PCAM_FEATURE(dev->mdev, ptys_extended_ethernet);
+	eth_prot_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_oper);
 
 	props->active_width     = IB_WIDTH_4X;
 	props->active_speed     = IB_SPEED_QDR;
 
 	translate_eth_proto_oper(eth_prot_oper, &props->active_speed,
-				 &props->active_width);
+				 &props->active_width, ext);
 
 	props->port_cap_flags |= IB_PORT_CM_SUP;
 	props->ip_gids = true;
@@ -6435,7 +6494,7 @@ static const struct mlx5_ib_profile pf_profile = {
 		     mlx5_ib_stage_delay_drop_cleanup),
 };
 
-static const struct mlx5_ib_profile nic_rep_profile = {
+const struct mlx5_ib_profile uplink_rep_profile = {
 	STAGE_CREATE(MLX5_IB_STAGE_INIT,
 		     mlx5_ib_stage_init_init,
 		     mlx5_ib_stage_init_cleanup),
@@ -6528,6 +6587,12 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 
 	printk_once(KERN_INFO "%s", mlx5_version);
 
+	if (MLX5_ESWITCH_MANAGER(mdev) &&
+	    mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) {
+		mlx5_ib_register_vport_reps(mdev);
+		return mdev;
+	}
+
 	port_type_cap = MLX5_CAP_GEN(mdev, port_type);
 	ll = mlx5_port_type_cap_to_rdma_ll(port_type_cap);
 
@@ -6542,14 +6607,6 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	dev->num_ports = max(MLX5_CAP_GEN(mdev, num_ports),
 			     MLX5_CAP_GEN(mdev, num_vhca_ports));
 
-	if (MLX5_ESWITCH_MANAGER(mdev) &&
-	    mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) {
-		dev->rep = mlx5_ib_vport_rep(mdev->priv.eswitch, 0);
-		dev->profile = &nic_rep_profile;
-		mlx5_ib_register_vport_reps(dev);
-		return dev;
-	}
-
 	return __mlx5_ib_add(dev, &pf_profile);
 }
 
@@ -6558,6 +6615,11 @@ static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context)
 	struct mlx5_ib_multiport_info *mpi;
 	struct mlx5_ib_dev *dev;
 
+	if (MLX5_ESWITCH_MANAGER(mdev) && context == mdev) {
+		mlx5_ib_unregister_vport_reps(mdev);
+		return;
+	}
+
 	if (mlx5_core_is_mp_slave(mdev)) {
 		mpi = context;
 		mutex_lock(&mlx5_ib_multiport_mutex);
@@ -6569,10 +6631,7 @@ static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context)
 	}
 
 	dev = context;
-	if (dev->profile == &nic_rep_profile)
-		mlx5_ib_unregister_vport_reps(dev);
-	else
-		__mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX);
+	__mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX);
 
 	ib_dealloc_device((struct ib_device *)dev);
 }

drivers/net/ethernet/mellanox/mlx5/core/Makefile

@@ -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

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";
 	}
 }

drivers/net/ethernet/mellanox/mlx5/core/ecpf.c

+/* 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;
+}

drivers/net/ethernet/mellanox/mlx5/core/ecpf.h

+/* 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__ */

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;
 }
 

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);

drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c

@@ -695,13 +695,14 @@ 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;
@@ -885,7 +886,7 @@ 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;
@@ -899,16 +900,16 @@ 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__);
@@ -916,24 +917,17 @@ 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:

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);
@@ -1132,7 +1132,7 @@ 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);
@@ -1219,7 +1219,7 @@ 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)
@@ -1368,7 +1368,7 @@ 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;
@@ -1395,7 +1395,7 @@ 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 */
@@ -1427,7 +1427,7 @@ 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;
@@ -1580,7 +1580,7 @@ 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 */
@@ -1616,7 +1616,7 @@ 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);
@@ -1735,7 +1735,7 @@ 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",
@@ -1748,7 +1748,7 @@ 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;
@@ -1784,7 +1784,7 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	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:
@@ -1804,7 +1804,7 @@ 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 */

drivers/net/ethernet/mellanox/mlx5/core/en_tc.c

@@ -1834,7 +1834,7 @@ 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,
@@ -2724,7 +2724,7 @@ 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);
@@ -2849,7 +2849,7 @@ 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;

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;
 }
 

drivers/net/ethernet/mellanox/mlx5/core/eswitch.c

@@ -40,8 +40,6 @@
 #include "eswitch.h"
 #include "fs_core.h"
 
-#define UPLINK_VPORT 0xFFFF
-
 enum {
 	MLX5_ACTION_NONE = 0,
 	MLX5_ACTION_ADD  = 1,
@@ -52,7 +50,7 @@ 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 */
@@ -115,7 +113,7 @@ 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 +150,7 @@ 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 +186,7 @@ __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 +213,7 @@ __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 +222,7 @@ 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 +235,7 @@ 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];
@@ -377,7 +375,7 @@ 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,
@@ -409,7 +407,7 @@ static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 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,
@@ -438,7 +436,7 @@ static void update_allmulti_vports(struct mlx5_eswitch *esw,
 				   struct esw_mc_addr *esw_mc)
 {
 	u8 *mac = vaddr->node.addr;
-	u32 vport_idx = 0;
+	u16 vport_idx = 0;
 
 	for (vport_idx = 0; vport_idx < esw->total_vports; vport_idx++) {
 		struct mlx5_vport *vport = &esw->vports[vport_idx];
@@ -485,7 +483,7 @@ 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 +497,7 @@ 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 +523,7 @@ 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;
@@ -564,7 +562,7 @@ 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];
 	bool is_uc = list_type == MLX5_NVPRT_LIST_TYPE_UC;
@@ -599,7 +597,7 @@ 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];
 	bool is_uc = list_type == MLX5_NVPRT_LIST_TYPE_UC;
@@ -686,7 +684,7 @@ static void esw_update_vport_addr_list(struct mlx5_eswitch *esw,
 /* 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 l2addr_node *node;
@@ -721,7 +719,7 @@ 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 esw_mc_addr *allmulti_addr = &esw->mc_promisc;
@@ -736,7 +734,7 @@ 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);
@@ -764,7 +762,7 @@ static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num,
 }
 
 /* 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];
 	int promisc_all = 0;
@@ -1633,7 +1631,7 @@ 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, nvfs + MLX5_SPECIAL_VPORTS);
 	}
 
 	if (err)

drivers/net/ethernet/mellanox/mlx5/core/eswitch.h

@@ -49,8 +49,6 @@
 #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) \

drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c

@@ -46,6 +46,11 @@ enum {
 	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)]
 
@@ -359,15 +364,15 @@ 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
@@ -409,7 +414,7 @@ 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;
 		}
@@ -469,7 +474,7 @@ 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;
@@ -904,8 +909,8 @@ 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.
@@ -999,7 +1004,8 @@ 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)) {
@@ -1048,7 +1054,7 @@ 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;
@@ -1062,7 +1068,7 @@ 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)) {
@@ -1082,16 +1088,15 @@ 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;
@@ -1227,7 +1232,7 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw)
 		ether_addr_copy(rep->hw_id, hw_id);
 	}
 
-	offloads->vport_reps[0].vport = FDB_UPLINK_VPORT;
+	offloads->vport_reps[0].vport = MLX5_VPORT_UPLINK;
 
 	return 0;
 }
@@ -1407,11 +1412,11 @@ 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;
 
@@ -1811,7 +1816,7 @@ void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw,
 	struct mlx5_esw_offload *offloads = &esw->offloads;
 	struct mlx5_eswitch_rep *rep;
 
-	if (vport == FDB_UPLINK_VPORT)
+	if (vport == MLX5_VPORT_UPLINK)
 		vport = UPLINK_REP_INDEX;
 
 	rep = &offloads->vport_reps[vport];

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:

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"

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");
@@ -461,27 +462,25 @@ static int handle_hca_cap_atomic(struct mlx5_core_dev *dev)
 
 static int handle_hca_cap_odp(struct mlx5_core_dev *dev)
 {
-	void *set_ctx;
 	void *set_hca_cap;
-	int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in);
+	void *set_ctx;
+	int set_sz;
 	int err;
 
-	if (!MLX5_CAP_GEN(dev, pg))
+	if (!IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING) ||
+	    !MLX5_CAP_GEN(dev, pg))
 		return 0;
 
 	err = mlx5_core_get_caps(dev, MLX5_CAP_ODP);
 	if (err)
 		return err;
 
-	/**
-	 * If all bits are cleared we shouldn't try to set it
-	 * or we might fail while trying to access a reserved bit.
-	 */
 	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;
@@ -492,13 +491,13 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev)
 
 	/* 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_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_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)));
+		 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);
 
@@ -579,6 +578,33 @@ static int handle_hca_cap(struct mlx5_core_dev *dev)
 	return err;
 }
 
+static int set_hca_cap(struct mlx5_core_dev *dev)
+{
+	struct pci_dev *pdev = dev->pdev;
+	int err;
+
+	err = handle_hca_cap(dev);
+	if (err) {
+		dev_err(&pdev->dev, "handle_hca_cap failed\n");
+		goto out;
+	}
+
+	err = handle_hca_cap_atomic(dev);
+	if (err) {
+		dev_err(&pdev->dev, "handle_hca_cap_atomic failed\n");
+		goto out;
+	}
+
+	err = handle_hca_cap_odp(dev);
+	if (err) {
+		dev_err(&pdev->dev, "handle_hca_cap_odp failed\n");
+		goto out;
+	}
+
+out:
+	return err;
+}
+
 static int set_hca_ctrl(struct mlx5_core_dev *dev)
 {
 	struct mlx5_reg_host_endianness he_in;
@@ -614,6 +640,8 @@ 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));
 }
 
@@ -624,6 +652,8 @@ 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));
 }
 
@@ -901,6 +931,7 @@ 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",
@@ -966,21 +997,9 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto reclaim_boot_pages;
 	}
 
-	err = handle_hca_cap(dev);
-	if (err) {
-		dev_err(&pdev->dev, "handle_hca_cap failed\n");
-		goto reclaim_boot_pages;
-	}
-
-	err = handle_hca_cap_atomic(dev);
-	if (err) {
-		dev_err(&pdev->dev, "handle_hca_cap_atomic failed\n");
-		goto reclaim_boot_pages;
-	}
-
-	err = handle_hca_cap_odp(dev);
+	err = set_hca_cap(dev);
 	if (err) {
-		dev_err(&pdev->dev, "handle_hca_cap_odp failed\n");
+		dev_err(&pdev->dev, "set_hca_cap failed\n");
 		goto reclaim_boot_pages;
 	}
 
@@ -1072,6 +1091,12 @@ 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 {
@@ -1089,6 +1114,9 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	return 0;
 
 err_reg_dev:
+	mlx5_ec_cleanup(dev);
+
+err_ec:
 	mlx5_sriov_detach(dev);
 
 err_sriov:
@@ -1163,6 +1191,7 @@ 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);

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);
 

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 @@ static int alloc_system_page(struct mlx5_core_dev *dev, u16 func_id)
 	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 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
 	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 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
 	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 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
 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);
 	}

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;

drivers/net/ethernet/mellanox/mlx5/core/sriov.c

@@ -147,7 +147,7 @@ static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev)
 	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");
 }
 

drivers/net/ethernet/mellanox/mlx5/core/vport.c

@@ -255,7 +255,7 @@ 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 +373,7 @@ 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 +526,7 @@ 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 +827,7 @@ 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)

include/linux/mlx5/device.h

@@ -67,7 +67,7 @@
 #define MLX5_UN_SZ_BYTES(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 8)
 #define MLX5_UN_SZ_DW(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 32)
 #define MLX5_BYTE_OFF(typ, fld) (__mlx5_bit_off(typ, fld) / 8)
-#define MLX5_ADDR_OF(typ, p, fld) ((char *)(p) + MLX5_BYTE_OFF(typ, fld))
+#define MLX5_ADDR_OF(typ, p, fld) ((void *)((uint8_t *)(p) + MLX5_BYTE_OFF(typ, fld)))
 
 /* insert a value to a struct */
 #define MLX5_SET(typ, p, fld, v) do { \
@@ -342,6 +342,8 @@ enum mlx5_event {
 	MLX5_EVENT_TYPE_PAGE_FAULT	   = 0xc,
 	MLX5_EVENT_TYPE_NIC_VPORT_CHANGE   = 0xd,
 
+	MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE = 0xe,
+
 	MLX5_EVENT_TYPE_DCT_DRAINED        = 0x1c,
 
 	MLX5_EVENT_TYPE_FPGA_ERROR         = 0x20,
@@ -591,7 +593,7 @@ struct mlx5_eqe_cmd {
 };
 
 struct mlx5_eqe_page_req {
-	u8		rsvd0[2];
+	__be16		ec_function;
 	__be16		func_id;
 	__be32		num_pages;
 	__be32		rsvd1[5];

include/linux/mlx5/driver.h

@@ -523,6 +523,7 @@ struct mlx5_priv {
 	atomic_t		reg_pages;
 	struct list_head	free_list;
 	int			vfs_pages;
+	int			peer_pf_pages;
 
 	struct mlx5_core_health health;
 
@@ -653,6 +654,7 @@ struct mlx5_core_dev {
 		u32 mcam[MLX5_ST_SZ_DW(mcam_reg)];
 		u32 fpga[MLX5_ST_SZ_DW(fpga_cap)];
 		u32 qcam[MLX5_ST_SZ_DW(qcam_reg)];
+		u8  embedded_cpu;
 	} caps;
 	u64			sys_image_guid;
 	phys_addr_t		iseg_base;
@@ -923,7 +925,7 @@ void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev);
 void mlx5_pagealloc_start(struct mlx5_core_dev *dev);
 void mlx5_pagealloc_stop(struct mlx5_core_dev *dev);
 void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id,
-				 s32 npages);
+				 s32 npages, bool ec_function);
 int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot);
 int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev);
 void mlx5_register_debugfs(void);
@@ -1073,11 +1075,24 @@ static inline int mlx5_core_is_pf(struct mlx5_core_dev *dev)
 	return !(dev->priv.pci_dev_data & MLX5_PCI_DEV_IS_VF);
 }
 
-#define MLX5_TOTAL_VPORTS(mdev) (1 + pci_sriov_get_totalvfs((mdev)->pdev))
-#define MLX5_VPORT_MANAGER(mdev) \
-	(MLX5_CAP_GEN(mdev, vport_group_manager) && \
-	 (MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && \
-	 mlx5_core_is_pf(mdev))
+static inline bool mlx5_core_is_ecpf(struct mlx5_core_dev *dev)
+{
+	return dev->caps.embedded_cpu;
+}
+
+static inline bool mlx5_core_is_ecpf_esw_manager(struct mlx5_core_dev *dev)
+{
+	return dev->caps.embedded_cpu && MLX5_CAP_GEN(dev, eswitch_manager);
+}
+
+#define MLX5_HOST_PF_MAX_VFS	(127u)
+static inline u16 mlx5_core_max_vfs(struct mlx5_core_dev *dev)
+{
+	if (mlx5_core_is_ecpf_esw_manager(dev))
+		return MLX5_HOST_PF_MAX_VFS;
+	else
+		return pci_sriov_get_totalvfs(dev->pdev);
+}
 
 static inline int mlx5_get_gid_table_len(u16 param)
 {

include/linux/mlx5/mlx5_ifc.h

@@ -142,6 +142,7 @@ enum {
 	MLX5_CMD_OP_QUERY_XRQ_DC_PARAMS_ENTRY     = 0x725,
 	MLX5_CMD_OP_SET_XRQ_DC_PARAMS_ENTRY       = 0x726,
 	MLX5_CMD_OP_QUERY_XRQ_ERROR_PARAMS        = 0x727,
+	MLX5_CMD_OP_QUERY_HOST_PARAMS             = 0x740,
 	MLX5_CMD_OP_QUERY_VPORT_STATE             = 0x750,
 	MLX5_CMD_OP_MODIFY_VPORT_STATE            = 0x751,
 	MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT       = 0x752,
@@ -4441,7 +4442,8 @@ struct mlx5_ifc_query_pages_out_bits {
 
 	u8         syndrome[0x20];
 
-	u8         reserved_at_40[0x10];
+	u8         embedded_cpu_function[0x1];
+	u8         reserved_at_41[0xf];
 	u8         function_id[0x10];
 
 	u8         num_pages[0x20];
@@ -4460,7 +4462,8 @@ struct mlx5_ifc_query_pages_in_bits {
 	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_at_40[0x10];
+	u8         embedded_cpu_function[0x1];
+	u8         reserved_at_41[0xf];
 	u8         function_id[0x10];
 
 	u8         reserved_at_60[0x20];
@@ -5880,7 +5883,8 @@ struct mlx5_ifc_manage_pages_in_bits {
 	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_at_40[0x10];
+	u8         embedded_cpu_function[0x1];
+	u8         reserved_at_41[0xf];
 	u8         function_id[0x10];
 
 	u8         input_num_entries[0x20];
@@ -6058,7 +6062,8 @@ struct mlx5_ifc_enable_hca_in_bits {
 	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_at_40[0x10];
+	u8         embedded_cpu_function[0x1];
+	u8         reserved_at_41[0xf];
 	u8         function_id[0x10];
 
 	u8         reserved_at_60[0x20];
@@ -6102,7 +6107,8 @@ struct mlx5_ifc_disable_hca_in_bits {
 	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_at_40[0x10];
+	u8         embedded_cpu_function[0x1];
+	u8         reserved_at_41[0xf];
 	u8         function_id[0x10];
 
 	u8         reserved_at_60[0x20];
@@ -7820,21 +7826,23 @@ struct mlx5_ifc_ptys_reg_bits {
 	u8         proto_mask[0x3];
 
 	u8         an_status[0x4];
-	u8         reserved_at_24[0x3c];
+	u8         reserved_at_24[0x1c];
+
+	u8         ext_eth_proto_capability[0x20];
 
 	u8         eth_proto_capability[0x20];
 
 	u8         ib_link_width_capability[0x10];
 	u8         ib_proto_capability[0x10];
 
-	u8         reserved_at_a0[0x20];
+	u8         ext_eth_proto_admin[0x20];
 
 	u8         eth_proto_admin[0x20];
 
 	u8         ib_link_width_admin[0x10];
 	u8         ib_proto_admin[0x10];
 
-	u8         reserved_at_100[0x20];
+	u8         ext_eth_proto_oper[0x20];
 
 	u8         eth_proto_oper[0x20];
 
@@ -8283,7 +8291,9 @@ struct mlx5_ifc_mpegc_reg_bits {
 struct mlx5_ifc_pcam_enhanced_features_bits {
 	u8         reserved_at_0[0x6d];
 	u8         rx_icrc_encapsulated_counter[0x1];
-	u8	   reserved_at_6e[0x8];
+	u8	   reserved_at_6e[0x4];
+	u8         ptys_extended_ethernet[0x1];
+	u8	   reserved_at_73[0x3];
 	u8         pfcc_mask[0x1];
 	u8         reserved_at_77[0x3];
 	u8         per_lane_error_counters[0x1];
@@ -8749,7 +8759,8 @@ struct mlx5_ifc_initial_seg_bits {
 	u8         initializing[0x1];
 	u8         reserved_at_fe1[0x4];
 	u8         nic_interface_supported[0x3];
-	u8         reserved_at_fe8[0x18];
+	u8         embedded_cpu[0x1];
+	u8         reserved_at_fe9[0x17];
 
 	struct mlx5_ifc_health_buffer_bits health_buffer;
 
@@ -9516,4 +9527,44 @@ struct mlx5_ifc_mtrc_ctrl_bits {
 	u8         reserved_at_80[0x180];
 };
 
+struct mlx5_ifc_host_params_context_bits {
+	u8         host_number[0x8];
+	u8         reserved_at_8[0x8];
+	u8         host_num_of_vfs[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         host_pci_bus[0x10];
+
+	u8         reserved_at_40[0x10];
+	u8         host_pci_device[0x10];
+
+	u8         reserved_at_60[0x10];
+	u8         host_pci_function[0x10];
+
+	u8         reserved_at_80[0x180];
+};
+
+struct mlx5_ifc_query_host_params_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_query_host_params_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+
+	struct mlx5_ifc_host_params_context_bits host_params_context;
+
+	u8         reserved_at_280[0x180];
+};
+
 #endif /* MLX5_IFC_H */

include/linux/mlx5/port.h

@@ -92,6 +92,22 @@ enum mlx5e_link_mode {
 	MLX5E_LINK_MODES_NUMBER,
 };
 
+enum mlx5e_ext_link_mode {
+	MLX5E_SGMII_100M			= 0,
+	MLX5E_1000BASE_X_SGMII			= 1,
+	MLX5E_5GBASE_R				= 3,
+	MLX5E_10GBASE_XFI_XAUI_1		= 4,
+	MLX5E_40GBASE_XLAUI_4_XLPPI_4		= 5,
+	MLX5E_25GAUI_1_25GBASE_CR_KR		= 6,
+	MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2	= 7,
+	MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR	= 8,
+	MLX5E_CAUI_4_100GBASE_CR4_KR4		= 9,
+	MLX5E_100GAUI_2_100GBASE_CR2_KR2	= 10,
+	MLX5E_200GAUI_4_200GBASE_CR4_KR4	= 12,
+	MLX5E_400GAUI_8				= 15,
+	MLX5E_EXT_LINK_MODES_NUMBER,
+};
+
 enum mlx5e_connector_type {
 	MLX5E_PORT_UNKNOWN	= 0,
 	MLX5E_PORT_NONE			= 1,
@@ -106,31 +122,23 @@ enum mlx5e_connector_type {
 };
 
 #define MLX5E_PROT_MASK(link_mode) (1 << link_mode)
+#define MLX5_GET_ETH_PROTO(reg, out, ext, field)	\
+	(ext ? MLX5_GET(reg, out, ext_##field) :	\
+	MLX5_GET(reg, out, field))
 
 int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps);
 int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys,
 			 int ptys_size, int proto_mask, u8 local_port);
-int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev,
-			      u32 *proto_cap, int proto_mask);
-int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev,
-				u32 *proto_admin, int proto_mask);
 int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev,
 				    u8 *link_width_oper, u8 local_port);
 int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev,
 				  u8 *proto_oper, u8 local_port);
-int mlx5_query_port_eth_proto_oper(struct mlx5_core_dev *dev,
-				   u32 *proto_oper, u8 local_port);
-int mlx5_set_port_ptys(struct mlx5_core_dev *dev, bool an_disable,
-		       u32 proto_admin, int proto_mask);
 void mlx5_toggle_port_link(struct mlx5_core_dev *dev);
 int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
 			       enum mlx5_port_status status);
 int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
 				 enum mlx5_port_status *status);
 int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration);
-void mlx5_query_port_autoneg(struct mlx5_core_dev *dev, int proto_mask,
-			     u8 *an_status,
-			     u8 *an_disable_cap, u8 *an_disable_admin);
 
 int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port);
 void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu, u8 port);

include/linux/mlx5/vport.h

@@ -36,12 +36,25 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/device.h>
 
+#define MLX5_VPORT_PF_PLACEHOLDER (1u)
+#define MLX5_SPECIAL_VPORTS (MLX5_VPORT_PF_PLACEHOLDER)
+#define MLX5_TOTAL_VPORTS(mdev) (MLX5_SPECIAL_VPORTS +	mlx5_core_max_vfs(mdev))
+
+#define MLX5_VPORT_MANAGER(mdev)					\
+	(MLX5_CAP_GEN(mdev, vport_group_manager) &&			\
+	 (MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) &&	\
+	 mlx5_core_is_pf(mdev))
+
 enum {
 	MLX5_CAP_INLINE_MODE_L2,
 	MLX5_CAP_INLINE_MODE_VPORT_CONTEXT,
 	MLX5_CAP_INLINE_MODE_NOT_REQUIRED,
 };
 
+enum {
+	MLX5_VPORT_UPLINK		= 0xffff
+};
+
 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);
@@ -60,7 +73,7 @@ int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev,
 					   u64 *system_image_guid);
 int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *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 mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev,
 					u16 *qkey_viol_cntr);
 int mlx5_query_hca_vport_gid(struct mlx5_core_dev *dev, u8 other_vport,
@@ -78,7 +91,7 @@ int mlx5_query_hca_vport_system_image_guid(struct mlx5_core_dev *dev,
 int mlx5_query_hca_vport_node_guid(struct mlx5_core_dev *dev,
 				   u64 *node_guid);
 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);
@@ -87,7 +100,7 @@ int mlx5_modify_nic_vport_mac_list(struct mlx5_core_dev *dev,
 				   u8 addr_list[][ETH_ALEN],
 				   int list_size);
 int mlx5_query_nic_vport_promisc(struct mlx5_core_dev *mdev,
-				 u32 vport,
+				 u16 vport,
 				 int *promisc_uc,
 				 int *promisc_mc,
 				 int *promisc_all);
@@ -96,7 +109,7 @@ int mlx5_modify_nic_vport_promisc(struct mlx5_core_dev *mdev,
 				  int promisc_mc,
 				  int promisc_all);
 int mlx5_query_nic_vport_vlans(struct mlx5_core_dev *dev,
-			       u32 vport,
+			       u16 vport,
 			       u16 vlans[],
 			       int *size);
 int mlx5_modify_nic_vport_vlans(struct mlx5_core_dev *dev,