Merge tag 'mlx5-fixes-2023-08-07' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5 fixes 2023-08-07

This series provides bug fixes to mlx5 driver.

* tag 'mlx5-fixes-2023-08-07' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
  net/mlx5e: Add capability check for vnic counters
  net/mlx5: Reload auxiliary devices in pci error handlers
  net/mlx5: Skip clock update work when device is in error state
  net/mlx5: LAG, Check correct bucket when modifying LAG
  net/mlx5e: Unoffload post act rule when handling FIB events
  net/mlx5: Fix devlink controller number for ECVF
  net/mlx5: Allow 0 for total host VFs
  net/mlx5: Return correct EC_VF function ID
  net/mlx5: DR, Fix wrong allocation of modify hdr pattern
  net/mlx5e: TC, Fix internal port memory leak
  net/mlx5e: Take RTNL lock when needed before calling xdp_set_features()
====================

Link: https://lore.kernel.org/r/20230807212607.50883-1-saeed@kernel.orgSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c

@@ -2,6 +2,7 @@
 /* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. */
 
 #include "reporter_vnic.h"
+#include "en_stats.h"
 #include "devlink.h"
 
 #define VNIC_ENV_GET64(vnic_env_stats, c) \
@@ -36,48 +37,64 @@ int mlx5_reporter_vnic_diagnose_counters(struct mlx5_core_dev *dev,
 	if (err)
 		return err;
 
-	err = devlink_fmsg_u64_pair_put(fmsg, "total_error_queues",
-					VNIC_ENV_GET64(&vnic, total_error_queues));
+	if (MLX5_CAP_GEN(dev, vnic_env_queue_counters)) {
+		err = devlink_fmsg_u32_pair_put(fmsg, "total_error_queues",
+						VNIC_ENV_GET(&vnic, total_error_queues));
 		if (err)
 			return err;
 
-	err = devlink_fmsg_u64_pair_put(fmsg, "send_queue_priority_update_flow",
-					VNIC_ENV_GET64(&vnic, send_queue_priority_update_flow));
+		err = devlink_fmsg_u32_pair_put(fmsg, "send_queue_priority_update_flow",
+						VNIC_ENV_GET(&vnic,
+							     send_queue_priority_update_flow));
 		if (err)
 			return err;
+	}
 
-	err = devlink_fmsg_u64_pair_put(fmsg, "comp_eq_overrun",
-					VNIC_ENV_GET64(&vnic, comp_eq_overrun));
+	if (MLX5_CAP_GEN(dev, eq_overrun_count)) {
+		err = devlink_fmsg_u32_pair_put(fmsg, "comp_eq_overrun",
+						VNIC_ENV_GET(&vnic, comp_eq_overrun));
 		if (err)
 			return err;
 
-	err = devlink_fmsg_u64_pair_put(fmsg, "async_eq_overrun",
-					VNIC_ENV_GET64(&vnic, async_eq_overrun));
+		err = devlink_fmsg_u32_pair_put(fmsg, "async_eq_overrun",
+						VNIC_ENV_GET(&vnic, async_eq_overrun));
 		if (err)
 			return err;
+	}
 
-	err = devlink_fmsg_u64_pair_put(fmsg, "cq_overrun",
-					VNIC_ENV_GET64(&vnic, cq_overrun));
+	if (MLX5_CAP_GEN(dev, vnic_env_cq_overrun)) {
+		err = devlink_fmsg_u32_pair_put(fmsg, "cq_overrun",
+						VNIC_ENV_GET(&vnic, cq_overrun));
 		if (err)
 			return err;
+	}
 
-	err = devlink_fmsg_u64_pair_put(fmsg, "invalid_command",
-					VNIC_ENV_GET64(&vnic, invalid_command));
+	if (MLX5_CAP_GEN(dev, invalid_command_count)) {
+		err = devlink_fmsg_u32_pair_put(fmsg, "invalid_command",
+						VNIC_ENV_GET(&vnic, invalid_command));
 		if (err)
 			return err;
+	}
 
-	err = devlink_fmsg_u64_pair_put(fmsg, "quota_exceeded_command",
-					VNIC_ENV_GET64(&vnic, quota_exceeded_command));
+	if (MLX5_CAP_GEN(dev, quota_exceeded_count)) {
+		err = devlink_fmsg_u32_pair_put(fmsg, "quota_exceeded_command",
+						VNIC_ENV_GET(&vnic, quota_exceeded_command));
 		if (err)
 			return err;
+	}
 
+	if (MLX5_CAP_GEN(dev, nic_receive_steering_discard)) {
 		err = devlink_fmsg_u64_pair_put(fmsg, "nic_receive_steering_discard",
-					VNIC_ENV_GET64(&vnic, nic_receive_steering_discard));
+						VNIC_ENV_GET64(&vnic,
+							       nic_receive_steering_discard));
 		if (err)
 			return err;
+	}
 
+	if (MLX5_CAP_GEN(dev, vnic_env_cnt_steering_fail)) {
 		err = devlink_fmsg_u64_pair_put(fmsg, "generated_pkt_steering_fail",
-					VNIC_ENV_GET64(&vnic, generated_pkt_steering_fail));
+						VNIC_ENV_GET64(&vnic,
+							       generated_pkt_steering_fail));
 		if (err)
 			return err;
 
@@ -85,6 +102,7 @@ int mlx5_reporter_vnic_diagnose_counters(struct mlx5_core_dev *dev,
 						VNIC_ENV_GET64(&vnic, handled_pkt_steering_fail));
 		if (err)
 			return err;
+	}
 
 	err = devlink_fmsg_obj_nest_end(fmsg);
 	if (err)

drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c

@@ -1461,10 +1461,12 @@ static void mlx5e_invalidate_encap(struct mlx5e_priv *priv,
 		attr = mlx5e_tc_get_encap_attr(flow);
 		esw_attr = attr->esw_attr;
 
-		if (flow_flag_test(flow, SLOW))
+		if (flow_flag_test(flow, SLOW)) {
 			mlx5e_tc_unoffload_from_slow_path(esw, flow);
-		else
+		} else {
 			mlx5e_tc_unoffload_fdb_rules(esw, flow, flow->attr);
+			mlx5e_tc_unoffload_flow_post_acts(flow);
+		}
 
 		mlx5e_tc_detach_mod_hdr(priv, flow, attr);
 		attr->modify_hdr = NULL;

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

@@ -5266,6 +5266,7 @@ void mlx5e_destroy_q_counters(struct mlx5e_priv *priv)
 static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
 			  struct net_device *netdev)
 {
+	const bool take_rtnl = netdev->reg_state == NETREG_REGISTERED;
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_flow_steering *fs;
 	int err;
@@ -5294,9 +5295,19 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
 		mlx5_core_err(mdev, "TLS initialization failed, %d\n", err);
 
 	mlx5e_health_create_reporters(priv);
+
+	/* If netdev is already registered (e.g. move from uplink to nic profile),
+	 * RTNL lock must be held before triggering netdev notifiers.
+	 */
+	if (take_rtnl)
+		rtnl_lock();
+
 	/* update XDP supported features */
 	mlx5e_set_xdp_feature(netdev);
 
+	if (take_rtnl)
+		rtnl_unlock();
+
 	return 0;
 }
 

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

@@ -1943,9 +1943,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5_flow_attr *attr = flow->attr;
-	struct mlx5_esw_flow_attr *esw_attr;
 
-	esw_attr = attr->esw_attr;
 	mlx5e_put_flow_tunnel_id(flow);
 
 	remove_unready_flow(flow);
@@ -1966,12 +1964,6 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 
 	mlx5_tc_ct_match_del(get_ct_priv(priv), &flow->attr->ct_attr);
 
-	if (esw_attr->int_port)
-		mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(priv), esw_attr->int_port);
-
-	if (esw_attr->dest_int_port)
-		mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(priv), esw_attr->dest_int_port);
-
 	if (flow_flag_test(flow, L3_TO_L2_DECAP))
 		mlx5e_detach_decap(priv, flow);
 
@@ -4268,6 +4260,7 @@ static void
 mlx5_free_flow_attr_actions(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr)
 {
 	struct mlx5_core_dev *counter_dev = get_flow_counter_dev(flow);
+	struct mlx5_esw_flow_attr *esw_attr;
 
 	if (!attr)
 		return;
@@ -4285,6 +4278,18 @@ mlx5_free_flow_attr_actions(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *a
 		mlx5e_tc_detach_mod_hdr(flow->priv, flow, attr);
 	}
 
+	if (mlx5e_is_eswitch_flow(flow)) {
+		esw_attr = attr->esw_attr;
+
+		if (esw_attr->int_port)
+			mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(flow->priv),
+					      esw_attr->int_port);
+
+		if (esw_attr->dest_int_port)
+			mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(flow->priv),
+					      esw_attr->dest_int_port);
+	}
+
 	mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), attr);
 
 	free_branch_attr(flow, attr->branch_true);

drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c

@@ -60,7 +60,7 @@ static struct devlink_port *mlx5_esw_dl_port_alloc(struct mlx5_eswitch *esw, u16
 	}  else if (mlx5_core_is_ec_vf_vport(esw->dev, vport_num)) {
 		memcpy(dl_port->attrs.switch_id.id, ppid.id, ppid.id_len);
 		dl_port->attrs.switch_id.id_len = ppid.id_len;
-		devlink_port_attrs_pci_vf_set(dl_port, controller_num, pfnum,
+		devlink_port_attrs_pci_vf_set(dl_port, 0, pfnum,
 					      vport_num - 1, false);
 	}
 	return dl_port;

drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c

@@ -574,7 +574,7 @@ static int __mlx5_lag_modify_definers_destinations(struct mlx5_lag *ldev,
 	for (i = 0; i < ldev->ports; i++) {
 		for (j = 0; j < ldev->buckets; j++) {
 			idx = i * ldev->buckets + j;
-			if (ldev->v2p_map[i] == ports[i])
+			if (ldev->v2p_map[idx] == ports[idx])
 				continue;
 
 			dest.vport.vhca_id = MLX5_CAP_GEN(ldev->pf[ports[idx] - 1].dev,

drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c

@@ -227,10 +227,15 @@ static void mlx5_timestamp_overflow(struct work_struct *work)
 	clock = container_of(timer, struct mlx5_clock, timer);
 	mdev = container_of(clock, struct mlx5_core_dev, clock);
 
+	if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
+		goto out;
+
 	write_seqlock_irqsave(&clock->lock, flags);
 	timecounter_read(&timer->tc);
 	mlx5_update_clock_info_page(mdev);
 	write_sequnlock_irqrestore(&clock->lock, flags);
+
+out:
 	schedule_delayed_work(&timer->overflow_work, timer->overflow_period);
 }
 

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

@@ -1989,7 +1989,7 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev,
 
 	mlx5_enter_error_state(dev, false);
 	mlx5_error_sw_reset(dev);
-	mlx5_unload_one(dev, true);
+	mlx5_unload_one(dev, false);
 	mlx5_drain_health_wq(dev);
 	mlx5_pci_disable_device(dev);
 

drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h

@@ -361,7 +361,7 @@ static inline bool mlx5_core_is_ec_vf_vport(const struct mlx5_core_dev *dev, u16
 
 static inline int mlx5_vport_to_func_id(const struct mlx5_core_dev *dev, u16 vport, bool ec_vf_func)
 {
-	return ec_vf_func ? vport - mlx5_core_ec_vf_vport_base(dev)
+	return ec_vf_func ? vport - mlx5_core_ec_vf_vport_base(dev) + 1
 			  : vport;
 }
 

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

@@ -285,7 +285,6 @@ static u16 mlx5_get_max_vfs(struct mlx5_core_dev *dev)
 		host_total_vfs = MLX5_GET(query_esw_functions_out, out,
 					  host_params_context.host_total_vfs);
 		kvfree(out);
-		if (host_total_vfs)
 		return host_total_vfs;
 	}
 

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c

@@ -82,7 +82,7 @@ dr_ptrn_alloc_pattern(struct mlx5dr_ptrn_mgr *mgr,
 	u32 chunk_size;
 	u32 index;
 
-	chunk_size = ilog2(num_of_actions);
+	chunk_size = ilog2(roundup_pow_of_two(num_of_actions));
 	/* HW modify action index granularity is at least 64B */
 	chunk_size = max_t(u32, chunk_size, DR_CHUNK_SIZE_8);