Merge tag 'mlx5-updates-2021-10-25' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2021-10-25

Misc updates for mlx5 driver:

1) Misc updates and cleanups:
 - Don't write directly to netdev->dev_addr, From Jakub Kicinski
 - Remove unnecessary checks for slow path flag in tc module
 - Fix unused function warning of mlx5i_flow_type_mask
 - Bridge, support replacing existing FDB entry

2) Sub Functions, Reduction in memory usage:
 - Reduce flow counters bulk query buffer size
 - Implement max_macs devlink parameter
 - Add devlink vendor params to control Event Queue sizes
 - Added SF life cycle trace points by Parav/

3) From Aya, Firmware health buffer reporting improvements
 - Print health buffer by log level and more missing information
 - Periodic update of host time to firmware
====================

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

21 files changed, 676 insertions, 79 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index bdb271b604d9..79c15ee62cde 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -16,7 +16,7 @@ mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \
 		fs_counters.o fs_ft_pool.o rl.o lag/lag.o dev.o events.o wq.o lib/gid.o \
 		lib/devcom.o lib/pci_vsc.o lib/dm.o lib/fs_ttc.o diag/fs_tracepoint.o \
-		diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o \
+		diag/fw_tracer.o diag/crdump.o devlink.o devlink_res.o diag/rsc_dump.o \
 		fw_reset.o qos.o lib/tout.o
 
 #
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 1c98652b244a..fc78c745ead1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -752,6 +752,68 @@ static void mlx5_devlink_auxdev_params_unregister(struct devlink *devlink)
 	mlx5_devlink_eth_param_unregister(devlink);
 }
 
+static int mlx5_devlink_max_uc_list_validate(struct devlink *devlink, u32 id,
+					     union devlink_param_value val,
+					     struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+
+	/* At least one unicast mac is needed */
+	if (val.vu32 == 0) {
+		NL_SET_ERR_MSG_MOD(extack, "max_macs value must be greater than 0");
+		return -EINVAL;
+	}
+	/* Check if its power of 2 or not */
+	if (!is_power_of_2(val.vu32)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Only power of 2 values are supported for max_macs");
+		return -EOPNOTSUPP;
+	}
+
+	if (ilog2(val.vu32) >
+	    MLX5_CAP_GEN_MAX(dev, log_max_current_uc_list)) {
+		NL_SET_ERR_MSG_MOD(extack, "max_macs value is out of the supported range");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static const struct devlink_param max_uc_list_param =
+	DEVLINK_PARAM_GENERIC(MAX_MACS, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, mlx5_devlink_max_uc_list_validate);
+
+static int mlx5_devlink_max_uc_list_param_register(struct devlink *devlink)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	union devlink_param_value value;
+	int err;
+
+	if (!MLX5_CAP_GEN(dev, log_max_current_uc_list_wr_supported))
+		return 0;
+
+	err = devlink_param_register(devlink, &max_uc_list_param);
+	if (err)
+		return err;
+
+	value.vu32 = 1 << MLX5_CAP_GEN(dev, log_max_current_uc_list);
+	devlink_param_driverinit_value_set(devlink,
+					   DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
+					   value);
+	return 0;
+}
+
+static void
+mlx5_devlink_max_uc_list_param_unregister(struct devlink *devlink)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+
+	if (!MLX5_CAP_GEN(dev, log_max_current_uc_list_wr_supported))
+		return;
+
+	devlink_param_unregister(devlink, &max_uc_list_param);
+}
+
 #define MLX5_TRAP_DROP(_id, _group_id)					\
 	DEVLINK_TRAP_GENERIC(DROP, DROP, _id,				\
 			     DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id, \
@@ -815,11 +877,17 @@ int mlx5_devlink_register(struct devlink *devlink)
 	if (err)
 		goto traps_reg_err;
 
+	err = mlx5_devlink_max_uc_list_param_register(devlink);
+	if (err)
+		goto uc_list_reg_err;
+
 	if (!mlx5_core_is_mp_slave(dev))
 		devlink_set_features(devlink, DEVLINK_F_RELOAD);
 
 	return 0;
 
+uc_list_reg_err:
+	mlx5_devlink_traps_unregister(devlink);
 traps_reg_err:
 	mlx5_devlink_auxdev_params_unregister(devlink);
 auxdev_reg_err:
@@ -830,6 +898,7 @@ auxdev_reg_err:
 
 void mlx5_devlink_unregister(struct devlink *devlink)
 {
+	mlx5_devlink_max_uc_list_param_unregister(devlink);
 	mlx5_devlink_traps_unregister(devlink);
 	mlx5_devlink_auxdev_params_unregister(devlink);
 	devlink_params_unregister(devlink, mlx5_devlink_params,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
index 30bf4882779b..674415fd0b3a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
@@ -6,6 +6,14 @@
 
 #include <net/devlink.h>
 
+enum mlx5_devlink_resource_id {
+	MLX5_DL_RES_COMP_EQ = 1,
+	MLX5_DL_RES_ASYNC_EQ,
+
+	__MLX5_ID_RES_MAX,
+	MLX5_ID_RES_MAX = __MLX5_ID_RES_MAX - 1,
+};
+
 enum mlx5_devlink_param_id {
 	MLX5_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
 	MLX5_DEVLINK_PARAM_ID_FLOW_STEERING_MODE,
@@ -31,6 +39,10 @@ int mlx5_devlink_trap_get_num_active(struct mlx5_core_dev *dev);
 int mlx5_devlink_traps_get_action(struct mlx5_core_dev *dev, int trap_id,
 				  enum devlink_trap_action *action);
 
+void mlx5_devlink_res_register(struct mlx5_core_dev *dev);
+void mlx5_devlink_res_unregister(struct mlx5_core_dev *dev);
+size_t mlx5_devlink_res_size(struct mlx5_core_dev *dev, enum mlx5_devlink_resource_id id);
+
 struct devlink *mlx5_devlink_alloc(struct device *dev);
 void mlx5_devlink_free(struct devlink *devlink);
 int mlx5_devlink_register(struct devlink *devlink);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c
new file mode 100644
index 000000000000..549d23745942
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. */
+
+#include "devlink.h"
+#include "mlx5_core.h"
+
+enum {
+	MLX5_EQ_MIN_SIZE = 64,
+	MLX5_EQ_MAX_SIZE = 4096,
+	MLX5_NUM_ASYNC_EQE = 4096,
+	MLX5_COMP_EQ_SIZE = 1024,
+};
+
+static int comp_eq_res_register(struct mlx5_core_dev *dev)
+{
+	struct devlink_resource_size_params comp_eq_size;
+	struct devlink *devlink = priv_to_devlink(dev);
+
+	devlink_resource_size_params_init(&comp_eq_size, MLX5_EQ_MIN_SIZE,
+					  MLX5_EQ_MAX_SIZE, 1, DEVLINK_RESOURCE_UNIT_ENTRY);
+	return devlink_resource_register(devlink, "io_eq_size", MLX5_COMP_EQ_SIZE,
+					 MLX5_DL_RES_COMP_EQ,
+					 DEVLINK_RESOURCE_ID_PARENT_TOP,
+					 &comp_eq_size);
+}
+
+static int async_eq_resource_register(struct mlx5_core_dev *dev)
+{
+	struct devlink_resource_size_params async_eq_size;
+	struct devlink *devlink = priv_to_devlink(dev);
+
+	devlink_resource_size_params_init(&async_eq_size, MLX5_EQ_MIN_SIZE,
+					  MLX5_EQ_MAX_SIZE, 1, DEVLINK_RESOURCE_UNIT_ENTRY);
+	return devlink_resource_register(devlink, "event_eq_size",
+					 MLX5_NUM_ASYNC_EQE, MLX5_DL_RES_ASYNC_EQ,
+					 DEVLINK_RESOURCE_ID_PARENT_TOP,
+					 &async_eq_size);
+}
+
+void mlx5_devlink_res_register(struct mlx5_core_dev *dev)
+{
+	int err;
+
+	err = comp_eq_res_register(dev);
+	if (err)
+		goto err_msg;
+
+	err = async_eq_resource_register(dev);
+	if (err)
+		goto err;
+	return;
+err:
+	devlink_resources_unregister(priv_to_devlink(dev), NULL);
+err_msg:
+	mlx5_core_err(dev, "Failed to register resources, err = %d\n", err);
+}
+
+void mlx5_devlink_res_unregister(struct mlx5_core_dev *dev)
+{
+	devlink_resources_unregister(priv_to_devlink(dev), NULL);
+}
+
+static const size_t default_vals[MLX5_ID_RES_MAX + 1] = {
+	[MLX5_DL_RES_COMP_EQ] = MLX5_COMP_EQ_SIZE,
+	[MLX5_DL_RES_ASYNC_EQ] = MLX5_NUM_ASYNC_EQE,
+};
+
+size_t mlx5_devlink_res_size(struct mlx5_core_dev *dev, enum mlx5_devlink_resource_id id)
+{
+	struct devlink *devlink = priv_to_devlink(dev);
+	u64 size;
+	int err;
+
+	err = devlink_resource_size_get(devlink, id, &size);
+	if (!err)
+		return size;
+	mlx5_core_err(dev, "Failed to get param. using default. err = %d, id = %u\n",
+		      err, id);
+	return default_vals[id];
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c
index d1d7e4b9f7ad..1046b7ea5c88 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c
@@ -509,13 +509,6 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample,
 	if (IS_ERR_OR_NULL(tc_psample))
 		return ERR_PTR(-EOPNOTSUPP);
 
-	/* If slow path flag is set, eg. when the neigh is invalid for encap,
-	 * don't offload sample action.
-	 */
-	esw = tc_psample->esw;
-	if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH)
-		return mlx5_eswitch_add_offloaded_rule(esw, spec, attr);
-
 	sample_flow = kzalloc(sizeof(*sample_flow), GFP_KERNEL);
 	if (!sample_flow)
 		return ERR_PTR(-ENOMEM);
@@ -527,6 +520,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample,
 	 * Only match the fte id instead of the same match in the
 	 * original flow table.
 	 */
+	esw = tc_psample->esw;
 	if (MLX5_CAP_GEN(esw->dev, reg_c_preserve) ||
 	    attr->action & MLX5_FLOW_CONTEXT_ACTION_DECAP) {
 		struct mlx5_flow_table *ft;
@@ -634,15 +628,6 @@ mlx5e_tc_sample_unoffload(struct mlx5e_tc_psample *tc_psample,
 	if (IS_ERR_OR_NULL(tc_psample))
 		return;
 
-	/* If slow path flag is set, sample action is not offloaded.
-	 * No need to delete sample rule.
-	 */
-	esw = tc_psample->esw;
-	if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) {
-		mlx5_eswitch_del_offloaded_rule(esw, rule, attr);
-		return;
-	}
-
 	/* The following delete order can't be changed, otherwise,
 	 * will hit fw syndromes.
 	 */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 0ff36c83714b..f3dec58026d9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4432,13 +4432,17 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16
 static void mlx5e_set_netdev_dev_addr(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	u8 addr[ETH_ALEN];
 
-	mlx5_query_mac_address(priv->mdev, netdev->dev_addr);
-	if (is_zero_ether_addr(netdev->dev_addr) &&
+	mlx5_query_mac_address(priv->mdev, addr);
+	if (is_zero_ether_addr(addr) &&
 	    !MLX5_CAP_GEN(priv->mdev, vport_group_manager)) {
 		eth_hw_addr_random(netdev);
 		mlx5_core_info(priv->mdev, "Assigned random MAC address %pM\n", netdev->dev_addr);
+		return;
 	}
+
+	eth_hw_addr_set(netdev, addr);
 }
 
 static int mlx5e_vxlan_set_port(struct net_device *netdev, unsigned int table,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 792e0d6aa861..31e69067284b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -19,6 +19,7 @@
 #include "lib/clock.h"
 #include "diag/fw_tracer.h"
 #include "mlx5_irq.h"
+#include "devlink.h"
 
 enum {
 	MLX5_EQE_OWNER_INIT_VAL	= 0x1,
@@ -646,7 +647,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 
 	param = (struct mlx5_eq_param) {
 		.irq_index = MLX5_IRQ_EQ_CTRL,
-		.nent = MLX5_NUM_ASYNC_EQE,
+		.nent = mlx5_devlink_res_size(dev, MLX5_DL_RES_ASYNC_EQ),
 	};
 
 	gather_async_events_mask(dev, param.mask);
@@ -807,7 +808,7 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 
 	INIT_LIST_HEAD(&table->comp_eqs_list);
 	ncomp_eqs = table->num_comp_eqs;
-	nent = MLX5_COMP_EQ_SIZE;
+	nent = mlx5_devlink_res_size(dev, MLX5_DL_RES_COMP_EQ);
 	for (i = 0; i < ncomp_eqs; i++) {
 		struct mlx5_eq_param param = {};
 		int vecidx = i;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
index 588622ba38c1..f690f430f40f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
@@ -888,14 +888,20 @@ mlx5_esw_bridge_fdb_entry_cleanup(struct mlx5_esw_bridge_fdb_entry *entry,
 	kvfree(entry);
 }
 
+static void
+mlx5_esw_bridge_fdb_entry_notify_and_cleanup(struct mlx5_esw_bridge_fdb_entry *entry,
+					     struct mlx5_esw_bridge *bridge)
+{
+	mlx5_esw_bridge_fdb_del_notify(entry);
+	mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge);
+}
+
 static void mlx5_esw_bridge_fdb_flush(struct mlx5_esw_bridge *bridge)
 {
 	struct mlx5_esw_bridge_fdb_entry *entry, *tmp;
 
-	list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) {
-		mlx5_esw_bridge_fdb_del_notify(entry);
-		mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge);
-	}
+	list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list)
+		mlx5_esw_bridge_fdb_entry_notify_and_cleanup(entry, bridge);
 }
 
 static struct mlx5_esw_bridge_vlan *
@@ -1065,10 +1071,8 @@ static void mlx5_esw_bridge_vlan_flush(struct mlx5_esw_bridge_vlan *vlan,
 	struct mlx5_eswitch *esw = bridge->br_offloads->esw;
 	struct mlx5_esw_bridge_fdb_entry *entry, *tmp;
 
-	list_for_each_entry_safe(entry, tmp, &vlan->fdb_list, vlan_list) {
-		mlx5_esw_bridge_fdb_del_notify(entry);
-		mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge);
-	}
+	list_for_each_entry_safe(entry, tmp, &vlan->fdb_list, vlan_list)
+		mlx5_esw_bridge_fdb_entry_notify_and_cleanup(entry, bridge);
 
 	if (vlan->pkt_reformat_pop)
 		mlx5_esw_bridge_vlan_pop_cleanup(vlan, esw);
@@ -1128,6 +1132,17 @@ mlx5_esw_bridge_port_vlan_lookup(u16 vid, u16 vport_num, u16 esw_owner_vhca_id,
 }
 
 static struct mlx5_esw_bridge_fdb_entry *
+mlx5_esw_bridge_fdb_lookup(struct mlx5_esw_bridge *bridge,
+			   const unsigned char *addr, u16 vid)
+{
+	struct mlx5_esw_bridge_fdb_key key = {};
+
+	ether_addr_copy(key.addr, addr);
+	key.vid = vid;
+	return rhashtable_lookup_fast(&bridge->fdb_ht, &key, fdb_ht_params);
+}
+
+static struct mlx5_esw_bridge_fdb_entry *
 mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
 			       const unsigned char *addr, u16 vid, bool added_by_user, bool peer,
 			       struct mlx5_eswitch *esw, struct mlx5_esw_bridge *bridge)
@@ -1145,6 +1160,10 @@ mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, u16 esw_ow
 			return ERR_CAST(vlan);
 	}
 
+	entry = mlx5_esw_bridge_fdb_lookup(bridge, addr, vid);
+	if (entry)
+		mlx5_esw_bridge_fdb_entry_notify_and_cleanup(entry, bridge);
+
 	entry = kvzalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
 		return ERR_PTR(-ENOMEM);
@@ -1444,7 +1463,6 @@ void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16
 				     struct switchdev_notifier_fdb_info *fdb_info)
 {
 	struct mlx5_esw_bridge_fdb_entry *entry;
-	struct mlx5_esw_bridge_fdb_key key;
 	struct mlx5_esw_bridge_port *port;
 	struct mlx5_esw_bridge *bridge;
 
@@ -1453,13 +1471,11 @@ void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16
 		return;
 
 	bridge = port->bridge;
-	ether_addr_copy(key.addr, fdb_info->addr);
-	key.vid = fdb_info->vid;
-	entry = rhashtable_lookup_fast(&bridge->fdb_ht, &key, fdb_ht_params);
+	entry = mlx5_esw_bridge_fdb_lookup(bridge, fdb_info->addr, fdb_info->vid);
 	if (!entry) {
 		esw_debug(br_offloads->esw->dev,
 			  "FDB entry with specified key not found (MAC=%pM,vid=%u,vport=%u)\n",
-			  key.addr, key.vid, vport_num);
+			  fdb_info->addr, fdb_info->vid, vport_num);
 		return;
 	}
 
@@ -1501,7 +1517,6 @@ void mlx5_esw_bridge_fdb_remove(struct net_device *dev, u16 vport_num, u16 esw_o
 {
 	struct mlx5_eswitch *esw = br_offloads->esw;
 	struct mlx5_esw_bridge_fdb_entry *entry;
-	struct mlx5_esw_bridge_fdb_key key;
 	struct mlx5_esw_bridge_port *port;
 	struct mlx5_esw_bridge *bridge;
 
@@ -1510,18 +1525,15 @@ void mlx5_esw_bridge_fdb_remove(struct net_device *dev, u16 vport_num, u16 esw_o
 		return;
 
 	bridge = port->bridge;
-	ether_addr_copy(key.addr, fdb_info->addr);
-	key.vid = fdb_info->vid;
-	entry = rhashtable_lookup_fast(&bridge->fdb_ht, &key, fdb_ht_params);
+	entry = mlx5_esw_bridge_fdb_lookup(bridge, fdb_info->addr, fdb_info->vid);
 	if (!entry) {
 		esw_warn(esw->dev,
 			 "FDB entry with specified key not found (MAC=%pM,vid=%u,vport=%u)\n",
-			 key.addr, key.vid, vport_num);
+			 fdb_info->addr, fdb_info->vid, vport_num);
 		return;
 	}
 
-	mlx5_esw_bridge_fdb_del_notify(entry);
-	mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge);
+	mlx5_esw_bridge_fdb_entry_notify_and_cleanup(entry, bridge);
 }
 
 void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads)
@@ -1537,13 +1549,11 @@ void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads)
 			if (entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER)
 				continue;
 
-			if (time_after(lastuse, entry->lastuse)) {
+			if (time_after(lastuse, entry->lastuse))
 				mlx5_esw_bridge_fdb_entry_refresh(entry);
-			} else if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_PEER) &&
-				   time_is_before_jiffies(entry->lastuse + bridge->ageing_time)) {
-				mlx5_esw_bridge_fdb_del_notify(entry);
-				mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge);
-			}
+			else if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_PEER) &&
+				 time_is_before_jiffies(entry->lastuse + bridge->ageing_time))
+				mlx5_esw_bridge_fdb_entry_notify_and_cleanup(entry, bridge);
 		}
 	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index f542a36be62c..60c9df1bc912 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -40,6 +40,7 @@
 #define MLX5_FC_STATS_PERIOD msecs_to_jiffies(1000)
 /* Max number of counters to query in bulk read is 32K */
 #define MLX5_SW_MAX_COUNTERS_BULK BIT(15)
+#define MLX5_SF_NUM_COUNTERS_BULK 6
 #define MLX5_FC_POOL_MAX_THRESHOLD BIT(18)
 #define MLX5_FC_POOL_USED_BUFF_RATIO 10
 
@@ -146,8 +147,12 @@ static void mlx5_fc_stats_remove(struct mlx5_core_dev *dev,
 
 static int get_max_bulk_query_len(struct mlx5_core_dev *dev)
 {
-	return min_t(int, MLX5_SW_MAX_COUNTERS_BULK,
-			  (1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk)));
+	int num_counters_bulk = mlx5_core_is_sf(dev) ?
+					MLX5_SF_NUM_COUNTERS_BULK :
+					MLX5_SW_MAX_COUNTERS_BULK;
+
+	return min_t(int, num_counters_bulk,
+		     (1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk)));
 }
 
 static void update_counter_cache(int index, u32 *bulk_raw_data,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 6a4dd7f78958..64f1abc4dc36 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -36,6 +36,7 @@
 #include <linux/vmalloc.h>
 #include <linux/hardirq.h>
 #include <linux/mlx5/driver.h>
+#include <linux/kern_levels.h>
 #include "mlx5_core.h"
 #include "lib/eq.h"
 #include "lib/mlx5.h"
@@ -74,6 +75,11 @@ enum  {
 	MLX5_SENSOR_FW_SYND_RFR		= 5,
 };
 
+enum {
+	MLX5_SEVERITY_MASK		= 0x7,
+	MLX5_SEVERITY_VALID_MASK	= 0x8,
+};
+
 u8 mlx5_get_nic_state(struct mlx5_core_dev *dev)
 {
 	return (ioread32be(&dev->iseg->cmdq_addr_l_sz) >> 8) & 7;
@@ -98,12 +104,19 @@ static bool sensor_pci_not_working(struct mlx5_core_dev *dev)
 	return (ioread32be(&h->fw_ver) == 0xffffffff);
 }
 
+static int mlx5_health_get_rfr(u8 rfr_severity)
+{
+	return rfr_severity >> MLX5_RFR_BIT_OFFSET;
+}
+
 static bool sensor_fw_synd_rfr(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
 	struct health_buffer __iomem *h = health->health;
-	u32 rfr = ioread32be(&h->rfr) >> MLX5_RFR_OFFSET;
 	u8 synd = ioread8(&h->synd);
+	u8 rfr;
+
+	rfr = mlx5_health_get_rfr(ioread8(&h->rfr_severity));
 
 	if (rfr && synd)
 		mlx5_core_dbg(dev, "FW requests reset, synd: %d\n", synd);
@@ -366,35 +379,69 @@ static const char *hsynd_str(u8 synd)
 	}
 }
 
+static const char *mlx5_loglevel_str(int level)
+{
+	switch (level) {
+	case LOGLEVEL_EMERG:
+		return "EMERGENCY";
+	case LOGLEVEL_ALERT:
+		return "ALERT";
+	case LOGLEVEL_CRIT:
+		return "CRITICAL";
+	case LOGLEVEL_ERR:
+		return "ERROR";
+	case LOGLEVEL_WARNING:
+		return "WARNING";
+	case LOGLEVEL_NOTICE:
+		return "NOTICE";
+	case LOGLEVEL_INFO:
+		return "INFO";
+	case LOGLEVEL_DEBUG:
+		return "DEBUG";
+	}
+	return "Unknown log level";
+}
+
+static int mlx5_health_get_severity(u8 rfr_severity)
+{
+	return rfr_severity & MLX5_SEVERITY_VALID_MASK ?
+	       rfr_severity & MLX5_SEVERITY_MASK : LOGLEVEL_ERR;
+}
+
 static void print_health_info(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
 	struct health_buffer __iomem *h = health->health;
-	char fw_str[18];
-	u32 fw;
+	u8 rfr_severity;
+	int severity;
 	int i;
 
 	/* If the syndrome is 0, the device is OK and no need to print buffer */
 	if (!ioread8(&h->synd))
 		return;
 
+	rfr_severity = ioread8(&h->rfr_severity);
+	severity  = mlx5_health_get_severity(rfr_severity);
+	mlx5_log(dev, severity, "Health issue observed, %s, severity(%d) %s:\n",
+		 hsynd_str(ioread8(&h->synd)), severity, mlx5_loglevel_str(severity));
+
 	for (i = 0; i < ARRAY_SIZE(h->assert_var); i++)
-		mlx5_core_err(dev, "assert_var[%d] 0x%08x\n", i,
-			      ioread32be(h->assert_var + i));
-
-	mlx5_core_err(dev, "assert_exit_ptr 0x%08x\n",
-		      ioread32be(&h->assert_exit_ptr));
-	mlx5_core_err(dev, "assert_callra 0x%08x\n",
-		      ioread32be(&h->assert_callra));
-	sprintf(fw_str, "%d.%d.%d", fw_rev_maj(dev), fw_rev_min(dev), fw_rev_sub(dev));
-	mlx5_core_err(dev, "fw_ver %s\n", fw_str);
-	mlx5_core_err(dev, "hw_id 0x%08x\n", ioread32be(&h->hw_id));
-	mlx5_core_err(dev, "irisc_index %d\n", ioread8(&h->irisc_index));
-	mlx5_core_err(dev, "synd 0x%x: %s\n", ioread8(&h->synd),
-		      hsynd_str(ioread8(&h->synd)));
-	mlx5_core_err(dev, "ext_synd 0x%04x\n", ioread16be(&h->ext_synd));
-	fw = ioread32be(&h->fw_ver);
-	mlx5_core_err(dev, "raw fw_ver 0x%08x\n", fw);
+		mlx5_log(dev, severity, "assert_var[%d] 0x%08x\n", i,
+			 ioread32be(h->assert_var + i));
+
+	mlx5_log(dev, severity, "assert_exit_ptr 0x%08x\n", ioread32be(&h->assert_exit_ptr));
+	mlx5_log(dev, severity, "assert_callra 0x%08x\n", ioread32be(&h->assert_callra));
+	mlx5_log(dev, severity, "fw_ver %d.%d.%d", fw_rev_maj(dev), fw_rev_min(dev),
+		 fw_rev_sub(dev));
+	mlx5_log(dev, severity, "time %u\n", ioread32be(&h->time));
+	mlx5_log(dev, severity, "hw_id 0x%08x\n", ioread32be(&h->hw_id));
+	mlx5_log(dev, severity, "rfr %d\n", mlx5_health_get_rfr(rfr_severity));
+	mlx5_log(dev, severity, "severity %d (%s)\n", severity, mlx5_loglevel_str(severity));
+	mlx5_log(dev, severity, "irisc_index %d\n", ioread8(&h->irisc_index));
+	mlx5_log(dev, severity, "synd 0x%x: %s\n", ioread8(&h->synd),
+		 hsynd_str(ioread8(&h->synd)));
+	mlx5_log(dev, severity, "ext_synd 0x%04x\n", ioread16be(&h->ext_synd));
+	mlx5_log(dev, severity, "raw fw_ver 0x%08x\n", ioread32be(&h->fw_ver));
 }
 
 static int
@@ -443,6 +490,7 @@ mlx5_fw_reporter_heath_buffer_data_put(struct mlx5_core_dev *dev,
 {
 	struct mlx5_core_health *health = &dev->priv.health;
 	struct health_buffer __iomem *h = health->health;
+	u8 rfr_severity;
 	int err;
 	int i;
 
@@ -475,9 +523,19 @@ mlx5_fw_reporter_heath_buffer_data_put(struct mlx5_core_dev *dev,
 					ioread32be(&h->assert_callra));
 	if (err)
 		return err;
+	err = devlink_fmsg_u32_pair_put(fmsg, "time", ioread32be(&h->time));
+	if (err)
+		return err;
 	err = devlink_fmsg_u32_pair_put(fmsg, "hw_id", ioread32be(&h->hw_id));
 	if (err)
 		return err;
+	rfr_severity = ioread8(&h->rfr_severity);
+	err = devlink_fmsg_u8_pair_put(fmsg, "rfr", mlx5_health_get_rfr(rfr_severity));
+	if (err)
+		return err;
+	err = devlink_fmsg_u8_pair_put(fmsg, "severity", mlx5_health_get_severity(rfr_severity));
+	if (err)
+		return err;
 	err = devlink_fmsg_u8_pair_put(fmsg, "irisc_index",
 				       ioread8(&h->irisc_index));
 	if (err)
@@ -694,6 +752,31 @@ void mlx5_trigger_health_work(struct mlx5_core_dev *dev)
 	spin_unlock_irqrestore(&health->wq_lock, flags);
 }
 
+#define MLX5_MSEC_PER_HOUR (MSEC_PER_SEC * 60 * 60)
+static void mlx5_health_log_ts_update(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	u32 out[MLX5_ST_SZ_DW(mrtc_reg)] = {};
+	u32 in[MLX5_ST_SZ_DW(mrtc_reg)] = {};
+	struct mlx5_core_health *health;
+	struct mlx5_core_dev *dev;
+	struct mlx5_priv *priv;
+	u64 now_us;
+
+	health = container_of(dwork, struct mlx5_core_health, update_fw_log_ts_work);
+	priv = container_of(health, struct mlx5_priv, health);
+	dev = container_of(priv, struct mlx5_core_dev, priv);
+
+	now_us =  ktime_to_us(ktime_get_real());
+
+	MLX5_SET(mrtc_reg, in, time_h, now_us >> 32);
+	MLX5_SET(mrtc_reg, in, time_l, now_us & 0xFFFFFFFF);
+	mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), MLX5_REG_MRTC, 0, 1);
+
+	queue_delayed_work(health->wq, &health->update_fw_log_ts_work,
+			   msecs_to_jiffies(MLX5_MSEC_PER_HOUR));
+}
+
 static void poll_health(struct timer_list *t)
 {
 	struct mlx5_core_dev *dev = from_timer(dev, t, priv.health.timer);
@@ -776,6 +859,7 @@ void mlx5_drain_health_wq(struct mlx5_core_dev *dev)
 	spin_lock_irqsave(&health->wq_lock, flags);
 	set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
 	spin_unlock_irqrestore(&health->wq_lock, flags);
+	cancel_delayed_work_sync(&health->update_fw_log_ts_work);
 	cancel_work_sync(&health->report_work);
 	cancel_work_sync(&health->fatal_report_work);
 }
@@ -791,6 +875,7 @@ void mlx5_health_cleanup(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
 
+	cancel_delayed_work_sync(&health->update_fw_log_ts_work);
 	destroy_workqueue(health->wq);
 	mlx5_fw_reporters_destroy(dev);
 }
@@ -816,6 +901,9 @@ int mlx5_health_init(struct mlx5_core_dev *dev)
 	spin_lock_init(&health->wq_lock);
 	INIT_WORK(&health->fatal_report_work, mlx5_fw_fatal_reporter_err_work);
 	INIT_WORK(&health->report_work, mlx5_fw_reporter_err_work);
+	INIT_DELAYED_WORK(&health->update_fw_log_ts_work, mlx5_health_log_ts_update);
+	if (mlx5_core_is_pf(dev))
+		queue_delayed_work(health->wq, &health->update_fw_log_ts_work, 0);
 
 	return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
index ee0eb4a4b819..962d41418ce7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
@@ -33,11 +33,6 @@
 #include "en.h"
 #include "ipoib.h"
 
-static u32 mlx5i_flow_type_mask(u32 flow_type)
-{
-	return flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS);
-}
-
 static void mlx5i_get_drvinfo(struct net_device *dev,
 			      struct ethtool_drvinfo *drvinfo)
 {
@@ -223,6 +218,11 @@ static int mlx5i_get_link_ksettings(struct net_device *netdev,
 }
 
 #ifdef CONFIG_MLX5_EN_RXNFC
+static u32 mlx5i_flow_type_mask(u32 flow_type)
+{
+	return flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS);
+}
+
 static int mlx5i_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 {
 	struct mlx5e_priv *priv = mlx5i_epriv(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index f8446395163a..079ee9e8da10 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -484,10 +484,23 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx)
 	return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_ODP);
 }
 
+static int max_uc_list_get_devlink_param(struct mlx5_core_dev *dev)
+{
+	struct devlink *devlink = priv_to_devlink(dev);
+	union devlink_param_value val;
+	int err;
+
+	err = devlink_param_driverinit_value_get(devlink,
+						 DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
+						 &val);
+	return err ? 0 : val.vu32;
+}
+
 static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 {
 	struct mlx5_profile *prof = &dev->profile;
 	void *set_hca_cap;
+	u32 max_uc_list;
 	int err;
 
 	err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL);
@@ -561,6 +574,11 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 	if (MLX5_CAP_GEN(dev, roce_rw_supported))
 		MLX5_SET(cmd_hca_cap, set_hca_cap, roce, mlx5_is_roce_init_enabled(dev));
 
+	max_uc_list = max_uc_list_get_devlink_param(dev);
+	if (max_uc_list)
+		MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_current_uc_list,
+			 ilog2(max_uc_list));
+
 	return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE);
 }
 
@@ -922,6 +940,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 	dev->hv_vhca = mlx5_hv_vhca_create(dev);
 	dev->rsc_dump = mlx5_rsc_dump_create(dev);
 
+	mlx5_devlink_res_register(dev);
+
 	return 0;
 
 err_sf_table_cleanup:
@@ -957,6 +977,7 @@ err_devcom:
 
 static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 {
+	mlx5_devlink_res_unregister(dev);
 	mlx5_rsc_dump_destroy(dev);
 	mlx5_hv_vhca_destroy(dev->hv_vhca);
 	mlx5_fw_tracer_destroy(dev->tracer);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 230eab7e3bc9..bb677329ea08 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -97,6 +97,30 @@ do {								\
 			     __func__, __LINE__, current->pid,	\
 			     ##__VA_ARGS__)
 
+static inline void mlx5_printk(struct mlx5_core_dev *dev, int level, const char *format, ...)
+{
+	struct device *device = dev->device;
+	struct va_format vaf;
+	va_list args;
+
+	if (WARN_ONCE(level < LOGLEVEL_EMERG || level > LOGLEVEL_DEBUG,
+		      "Level %d is out of range, set to default level\n", level))
+		level = LOGLEVEL_DEFAULT;
+
+	va_start(args, format);
+	vaf.fmt = format;
+	vaf.va = &args;
+
+	dev_printk_emit(level, device, "%s %s: %pV", dev_driver_string(device), dev_name(device),
+			&vaf);
+	va_end(args);
+}
+
+#define mlx5_log(__dev, level, format, ...)			\
+	mlx5_printk(__dev, level, "%s:%d:(pid %d): " format,	\
+		    __func__, __LINE__, current->pid,		\
+		    ##__VA_ARGS__)
+
 static inline struct device *mlx5_core_dma_dev(struct mlx5_core_dev *dev)
 {
 	return &dev->pdev->dev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
index 871c2fbe18d3..f37db7cc32a6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
@@ -9,6 +9,8 @@
 #include "sf/sf.h"
 #include "sf/mlx5_ifc_vhca_event.h"
 #include "ecpf.h"
+#define CREATE_TRACE_POINTS
+#include "diag/dev_tracepoint.h"
 
 struct mlx5_sf_dev_table {
 	struct xarray devices;
@@ -66,13 +68,18 @@ static void mlx5_sf_dev_release(struct device *device)
 	kfree(sf_dev);
 }
 
-static void mlx5_sf_dev_remove(struct mlx5_sf_dev *sf_dev)
+static void mlx5_sf_dev_remove(struct mlx5_core_dev *dev, struct mlx5_sf_dev *sf_dev)
 {
+	int id;
+
+	id = sf_dev->adev.id;
+	trace_mlx5_sf_dev_del(dev, sf_dev, id);
+
 	auxiliary_device_delete(&sf_dev->adev);
 	auxiliary_device_uninit(&sf_dev->adev);
 }
 
-static void mlx5_sf_dev_add(struct mlx5_core_dev *dev, u16 sf_index, u32 sfnum)
+static void mlx5_sf_dev_add(struct mlx5_core_dev *dev, u16 sf_index, u16 fn_id, u32 sfnum)
 {
 	struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table;
 	struct mlx5_sf_dev *sf_dev;
@@ -100,6 +107,7 @@ static void mlx5_sf_dev_add(struct mlx5_core_dev *dev, u16 sf_index, u32 sfnum)
 	sf_dev->adev.dev.groups = sf_attr_groups;
 	sf_dev->sfnum = sfnum;
 	sf_dev->parent_mdev = dev;
+	sf_dev->fn_id = fn_id;
 
 	if (!table->max_sfs) {
 		mlx5_adev_idx_free(id);
@@ -109,6 +117,8 @@ static void mlx5_sf_dev_add(struct mlx5_core_dev *dev, u16 sf_index, u32 sfnum)
 	}
 	sf_dev->bar_base_addr = table->base_address + (sf_index * table->sf_bar_length);
 
+	trace_mlx5_sf_dev_add(dev, sf_dev, id);
+
 	err = auxiliary_device_init(&sf_dev->adev);
 	if (err) {
 		mlx5_adev_idx_free(id);
@@ -128,7 +138,7 @@ static void mlx5_sf_dev_add(struct mlx5_core_dev *dev, u16 sf_index, u32 sfnum)
 	return;
 
 xa_err:
-	mlx5_sf_dev_remove(sf_dev);
+	mlx5_sf_dev_remove(dev, sf_dev);
 add_err:
 	mlx5_core_err(dev, "SF DEV: fail device add for index=%d sfnum=%d err=%d\n",
 		      sf_index, sfnum, err);
@@ -139,7 +149,7 @@ static void mlx5_sf_dev_del(struct mlx5_core_dev *dev, struct mlx5_sf_dev *sf_de
 	struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table;
 
 	xa_erase(&table->devices, sf_index);
-	mlx5_sf_dev_remove(sf_dev);
+	mlx5_sf_dev_remove(dev, sf_dev);
 }
 
 static int
@@ -178,7 +188,8 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_
 		break;
 	case MLX5_VHCA_STATE_ACTIVE:
 		if (!sf_dev)
-			mlx5_sf_dev_add(table->dev, sf_index, event->sw_function_id);
+			mlx5_sf_dev_add(table->dev, sf_index, event->function_id,
+					event->sw_function_id);
 		break;
 	default:
 		break;
@@ -260,7 +271,7 @@ static void mlx5_sf_dev_destroy_all(struct mlx5_sf_dev_table *table)
 
 	xa_for_each(&table->devices, index, sf_dev) {
 		xa_erase(&table->devices, index);
-		mlx5_sf_dev_remove(sf_dev);
+		mlx5_sf_dev_remove(table->dev, sf_dev);
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h
index 149fd9e698cf..2a66a427ef15 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h
@@ -16,6 +16,7 @@ struct mlx5_sf_dev {
 	struct mlx5_core_dev *mdev;
 	phys_addr_t bar_base_addr;
 	u32 sfnum;
+	u16 fn_id;
 };
 
 void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/diag/dev_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/diag/dev_tracepoint.h
new file mode 100644
index 000000000000..7f7c9af5deed
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/diag/dev_tracepoint.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mlx5
+
+#if !defined(_MLX5_SF_DEV_TP_) || defined(TRACE_HEADER_MULTI_READ)
+#define _MLX5_SF_DEV_TP_
+
+#include <linux/tracepoint.h>
+#include <linux/mlx5/driver.h>
+#include "../../dev/dev.h"
+
+DECLARE_EVENT_CLASS(mlx5_sf_dev_template,
+		    TP_PROTO(const struct mlx5_core_dev *dev,
+			     const struct mlx5_sf_dev *sfdev,
+			     int aux_id),
+		    TP_ARGS(dev, sfdev, aux_id),
+		    TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+				     __field(const struct mlx5_sf_dev*, sfdev)
+				     __field(int, aux_id)
+				     __field(u16, hw_fn_id)
+				     __field(u32, sfnum)
+		    ),
+		    TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+				   __entry->sfdev = sfdev;
+				   __entry->aux_id = aux_id;
+				   __entry->hw_fn_id = sfdev->fn_id;
+				   __entry->sfnum = sfdev->sfnum;
+		    ),
+		    TP_printk("(%s) sfdev=%pK aux_id=%d hw_id=0x%x sfnum=%u\n",
+			      __get_str(devname), __entry->sfdev,
+			      __entry->aux_id, __entry->hw_fn_id,
+			      __entry->sfnum)
+);
+
+DEFINE_EVENT(mlx5_sf_dev_template, mlx5_sf_dev_add,
+	     TP_PROTO(const struct mlx5_core_dev *dev,
+		      const struct mlx5_sf_dev *sfdev,
+		      int aux_id),
+	     TP_ARGS(dev, sfdev, aux_id)
+	     );
+
+DEFINE_EVENT(mlx5_sf_dev_template, mlx5_sf_dev_del,
+	     TP_PROTO(const struct mlx5_core_dev *dev,
+		      const struct mlx5_sf_dev *sfdev,
+		      int aux_id),
+	     TP_ARGS(dev, sfdev, aux_id)
+	     );
+
+#endif /* _MLX5_SF_DEV_TP_ */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH sf/dev/diag
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE dev_tracepoint
+#include <trace/define_trace.h>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
index e1bb3acf45e6..3be659cd91f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
@@ -8,6 +8,8 @@
 #include "mlx5_ifc_vhca_event.h"
 #include "vhca_event.h"
 #include "ecpf.h"
+#define CREATE_TRACE_POINTS
+#include "diag/sf_tracepoint.h"
 
 struct mlx5_sf {
 	struct devlink_port dl_port;
@@ -112,6 +114,7 @@ static void mlx5_sf_free(struct mlx5_sf_table *table, struct mlx5_sf *sf)
 {
 	mlx5_sf_id_erase(table, sf);
 	mlx5_sf_hw_table_sf_free(table->dev, sf->controller, sf->id);
+	trace_mlx5_sf_free(table->dev, sf->port_index, sf->controller, sf->hw_fn_id);
 	kfree(sf);
 }
 
@@ -209,6 +212,7 @@ static int mlx5_sf_activate(struct mlx5_core_dev *dev, struct mlx5_sf *sf,
 		return err;
 
 	sf->hw_state = MLX5_VHCA_STATE_ACTIVE;
+	trace_mlx5_sf_activate(dev, sf->port_index, sf->controller, sf->hw_fn_id);
 	return 0;
 }
 
@@ -224,6 +228,7 @@ static int mlx5_sf_deactivate(struct mlx5_core_dev *dev, struct mlx5_sf *sf)
 		return err;
 
 	sf->hw_state = MLX5_VHCA_STATE_TEARDOWN_REQUEST;
+	trace_mlx5_sf_deactivate(dev, sf->port_index, sf->controller, sf->hw_fn_id);
 	return 0;
 }
 
@@ -293,6 +298,7 @@ static int mlx5_sf_add(struct mlx5_core_dev *dev, struct mlx5_sf_table *table,
 	if (err)
 		goto esw_err;
 	*new_port_index = sf->port_index;
+	trace_mlx5_sf_add(dev, sf->port_index, sf->controller, sf->hw_fn_id, new_attr->sfnum);
 	return 0;
 
 esw_err:
@@ -442,6 +448,8 @@ static int mlx5_sf_vhca_event(struct notifier_block *nb, unsigned long opcode, v
 	update = mlx5_sf_state_update_check(sf, event->new_vhca_state);
 	if (update)
 		sf->hw_state = event->new_vhca_state;
+	trace_mlx5_sf_update_state(table->dev, sf->port_index, sf->controller,
+				   sf->hw_fn_id, sf->hw_state);
 sf_err:
 	mutex_unlock(&table->sf_state_lock);
 	mlx5_sf_table_put(table);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/sf_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/sf_tracepoint.h
new file mode 100644
index 000000000000..8bf1cd90930d
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/sf_tracepoint.h
@@ -0,0 +1,173 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mlx5
+
+#if !defined(_MLX5_SF_TP_) || defined(TRACE_HEADER_MULTI_READ)
+#define _MLX5_SF_TP_
+
+#include <linux/tracepoint.h>
+#include <linux/mlx5/driver.h>
+#include "sf/vhca_event.h"
+
+TRACE_EVENT(mlx5_sf_add,
+	    TP_PROTO(const struct mlx5_core_dev *dev,
+		     unsigned int port_index,
+		     u32 controller,
+		     u16 hw_fn_id,
+		     u32 sfnum),
+	    TP_ARGS(dev, port_index, controller, hw_fn_id, sfnum),
+	    TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+			     __field(unsigned int, port_index)
+			     __field(u32, controller)
+			     __field(u16, hw_fn_id)
+			     __field(u32, sfnum)
+			    ),
+	    TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+		    __entry->port_index = port_index;
+		    __entry->controller = controller;
+		    __entry->hw_fn_id = hw_fn_id;
+		    __entry->sfnum = sfnum;
+	    ),
+	    TP_printk("(%s) port_index=%u controller=%u hw_id=0x%x sfnum=%u\n",
+		      __get_str(devname), __entry->port_index, __entry->controller,
+		      __entry->hw_fn_id, __entry->sfnum)
+);
+
+TRACE_EVENT(mlx5_sf_free,
+	    TP_PROTO(const struct mlx5_core_dev *dev,
+		     unsigned int port_index,
+		     u32 controller,
+		     u16 hw_fn_id),
+	    TP_ARGS(dev, port_index, controller, hw_fn_id),
+	    TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+			     __field(unsigned int, port_index)
+			     __field(u32, controller)
+			     __field(u16, hw_fn_id)
+			    ),
+	    TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+		    __entry->port_index = port_index;
+		    __entry->controller = controller;
+		    __entry->hw_fn_id = hw_fn_id;
+	    ),
+	    TP_printk("(%s) port_index=%u controller=%u hw_id=0x%x\n",
+		      __get_str(devname), __entry->port_index, __entry->controller,
+		      __entry->hw_fn_id)
+);
+
+TRACE_EVENT(mlx5_sf_hwc_alloc,
+	    TP_PROTO(const struct mlx5_core_dev *dev,
+		     u32 controller,
+		     u16 hw_fn_id,
+		     u32 sfnum),
+	    TP_ARGS(dev, controller, hw_fn_id, sfnum),
+	    TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+			     __field(u32, controller)
+			     __field(u16, hw_fn_id)
+			     __field(u32, sfnum)
+			    ),
+	    TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+		    __entry->controller = controller;
+		    __entry->hw_fn_id = hw_fn_id;
+		    __entry->sfnum = sfnum;
+	    ),
+	    TP_printk("(%s) controller=%u hw_id=0x%x sfnum=%u\n",
+		      __get_str(devname), __entry->controller, __entry->hw_fn_id,
+		      __entry->sfnum)
+);
+
+TRACE_EVENT(mlx5_sf_hwc_free,
+	    TP_PROTO(const struct mlx5_core_dev *dev,
+		     u16 hw_fn_id),
+	    TP_ARGS(dev, hw_fn_id),
+	    TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+			     __field(u16, hw_fn_id)
+			    ),
+	    TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+		    __entry->hw_fn_id = hw_fn_id;
+	    ),
+	    TP_printk("(%s) hw_id=0x%x\n", __get_str(devname), __entry->hw_fn_id)
+);
+
+TRACE_EVENT(mlx5_sf_hwc_deferred_free,
+	    TP_PROTO(const struct mlx5_core_dev *dev,
+		     u16 hw_fn_id),
+	    TP_ARGS(dev, hw_fn_id),
+	    TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+			     __field(u16, hw_fn_id)
+			    ),
+	    TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+		    __entry->hw_fn_id = hw_fn_id;
+	    ),
+	    TP_printk("(%s) hw_id=0x%x\n", __get_str(devname), __entry->hw_fn_id)
+);
+
+DECLARE_EVENT_CLASS(mlx5_sf_state_template,
+		    TP_PROTO(const struct mlx5_core_dev *dev,
+			     u32 port_index,
+			     u32 controller,
+			     u16 hw_fn_id),
+		    TP_ARGS(dev, port_index, controller, hw_fn_id),
+		    TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+				     __field(unsigned int, port_index)
+				     __field(u32, controller)
+				     __field(u16, hw_fn_id)),
+		    TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+				   __entry->port_index = port_index;
+				   __entry->controller = controller;
+				   __entry->hw_fn_id = hw_fn_id;
+		    ),
+		    TP_printk("(%s) port_index=%u controller=%u hw_id=0x%x\n",
+			      __get_str(devname), __entry->port_index, __entry->controller,
+			      __entry->hw_fn_id)
+);
+
+DEFINE_EVENT(mlx5_sf_state_template, mlx5_sf_activate,
+	     TP_PROTO(const struct mlx5_core_dev *dev,
+		      u32 port_index,
+		      u32 controller,
+		      u16 hw_fn_id),
+	     TP_ARGS(dev, port_index, controller, hw_fn_id)
+	     );
+
+DEFINE_EVENT(mlx5_sf_state_template, mlx5_sf_deactivate,
+	     TP_PROTO(const struct mlx5_core_dev *dev,
+		      u32 port_index,
+		      u32 controller,
+		      u16 hw_fn_id),
+	     TP_ARGS(dev, port_index, controller, hw_fn_id)
+	     );
+
+TRACE_EVENT(mlx5_sf_update_state,
+	    TP_PROTO(const struct mlx5_core_dev *dev,
+		     unsigned int port_index,
+		     u32 controller,
+		     u16 hw_fn_id,
+		     u8 state),
+	    TP_ARGS(dev, port_index, controller, hw_fn_id, state),
+	    TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+			     __field(unsigned int, port_index)
+			     __field(u32, controller)
+			     __field(u16, hw_fn_id)
+			     __field(u8, state)
+			    ),
+	    TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+		    __entry->port_index = port_index;
+		    __entry->controller = controller;
+		    __entry->hw_fn_id = hw_fn_id;
+		    __entry->state = state;
+	    ),
+	    TP_printk("(%s) port_index=%u controller=%u hw_id=0x%x state=%u\n",
+		      __get_str(devname), __entry->port_index, __entry->controller,
+		      __entry->hw_fn_id, __entry->state)
+);
+
+#endif /* _MLX5_SF_TP_ */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH sf/diag
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE sf_tracepoint
+#include <trace/define_trace.h>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/vhca_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/vhca_tracepoint.h
new file mode 100644
index 000000000000..fd814a190b8b
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/vhca_tracepoint.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mlx5
+
+#if !defined(_MLX5_SF_VHCA_TP_) || defined(TRACE_HEADER_MULTI_READ)
+#define _MLX5_SF_VHCA_TP_
+
+#include <linux/tracepoint.h>
+#include <linux/mlx5/driver.h>
+#include "sf/vhca_event.h"
+
+TRACE_EVENT(mlx5_sf_vhca_event,
+	    TP_PROTO(const struct mlx5_core_dev *dev,
+		     const struct mlx5_vhca_state_event *event),
+	    TP_ARGS(dev, event),
+	    TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+			     __field(u16, hw_fn_id)
+			     __field(u32, sfnum)
+			     __field(u8, vhca_state)
+			    ),
+	    TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+		    __entry->hw_fn_id = event->function_id;
+		    __entry->sfnum = event->sw_function_id;
+		    __entry->vhca_state = event->new_vhca_state;
+	    ),
+	    TP_printk("(%s) hw_id=0x%x sfnum=%u vhca_state=%d\n",
+		      __get_str(devname), __entry->hw_fn_id,
+		      __entry->sfnum, __entry->vhca_state)
+);
+
+#endif /* _MLX5_SF_VHCA_TP_ */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH sf/diag
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE vhca_tracepoint
+#include <trace/define_trace.h>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
index d9c69123c1ab..252d6017387d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
@@ -8,6 +8,7 @@
 #include "ecpf.h"
 #include "mlx5_core.h"
 #include "eswitch.h"
+#include "diag/sf_tracepoint.h"
 
 struct mlx5_sf_hw {
 	u32 usr_sfnum;
@@ -142,6 +143,7 @@ int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 controller, u32 usr
 			goto vhca_err;
 	}
 
+	trace_mlx5_sf_hwc_alloc(dev, controller, hw_fn_id, usr_sfnum);
 	mutex_unlock(&table->table_lock);
 	return sw_id;
 
@@ -172,6 +174,7 @@ static void mlx5_sf_hw_table_hwc_sf_free(struct mlx5_core_dev *dev,
 	mlx5_cmd_dealloc_sf(dev, hwc->start_fn_id + idx);
 	hwc->sfs[idx].allocated = false;
 	hwc->sfs[idx].pending_delete = false;
+	trace_mlx5_sf_hwc_free(dev, hwc->start_fn_id + idx);
 }
 
 void mlx5_sf_hw_table_sf_deferred_free(struct mlx5_core_dev *dev, u32 controller, u16 id)
@@ -195,6 +198,7 @@ void mlx5_sf_hw_table_sf_deferred_free(struct mlx5_core_dev *dev, u32 controller
 		hwc->sfs[id].allocated = false;
 	} else {
 		hwc->sfs[id].pending_delete = true;
+		trace_mlx5_sf_hwc_deferred_free(dev, hw_fn_id);
 	}
 err:
 	mutex_unlock(&table->table_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c
index 28b14b05086f..d908fba968f0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c
@@ -6,6 +6,8 @@
 #include "mlx5_core.h"
 #include "vhca_event.h"
 #include "ecpf.h"
+#define CREATE_TRACE_POINTS
+#include "diag/vhca_tracepoint.h"
 
 struct mlx5_vhca_state_notifier {
 	struct mlx5_core_dev *dev;
@@ -82,6 +84,7 @@ mlx5_vhca_event_notify(struct mlx5_core_dev *dev, struct mlx5_vhca_state_event *
 					 vhca_state_context.vhca_state);
 
 	mlx5_vhca_event_arm(dev, event->function_id);
+	trace_mlx5_sf_vhca_event(dev, event);
 
 	blocking_notifier_call_chain(&dev->priv.vhca_state_notifier->n_head, 0, event);
 }