Merge branch 'mlx5-misc-fixes-2024-07-30'

Tariq Toukan says:

====================
mlx5 misc fixes 2024-07-30

This patchset provides misc bug fixes from the team to the mlx5 core and
Eth drivers.
====================

Link: https://patch.msgid.link/20240730061638.1831002-1-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Author: kuba-moo

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

@@ -932,6 +932,7 @@ mlx5_tc_ct_entry_replace_rule(struct mlx5_tc_ct_priv *ct_priv,
 	mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, zone_rule->attr, mh);
 	mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id);
 err_mod_hdr:
+	*attr = *old_attr;
 	kfree(old_attr);
 err_attr:
 	kvfree(spec);

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c

@@ -51,9 +51,10 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
 		    MLX5_CAP_FLOWTABLE_NIC_RX(mdev, decap))
 			caps |= MLX5_IPSEC_CAP_PACKET_OFFLOAD;
 
-		if ((MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) &&
-		     MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level)) ||
-		    MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level))
+		if (IS_ENABLED(CONFIG_MLX5_CLS_ACT) &&
+		    ((MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) &&
+		      MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level)) ||
+		     MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level)))
 			caps |= MLX5_IPSEC_CAP_PRIO;
 
 		if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev,

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

@@ -1409,7 +1409,12 @@ static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 	if (!an_changes && link_modes == eproto.admin)
 		goto out;
 
-	mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext);
+	err = mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext);
+	if (err) {
+		netdev_err(priv->netdev, "%s: failed to set ptys reg: %d\n", __func__, err);
+		goto out;
+	}
+
 	mlx5_toggle_port_link(mdev);
 
 out:

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

@@ -207,6 +207,7 @@ int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev)
 static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unloaded)
 {
 	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+	struct devlink *devlink = priv_to_devlink(dev);
 
 	/* if this is the driver that initiated the fw reset, devlink completed the reload */
 	if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) {
@@ -218,9 +219,11 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unload
 			mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n");
 		else
 			mlx5_load_one(dev, true);
-		devlink_remote_reload_actions_performed(priv_to_devlink(dev), 0,
+		devl_lock(devlink);
+		devlink_remote_reload_actions_performed(devlink, 0,
 							BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) |
 							BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE));
+		devl_unlock(devlink);
 	}
 }
 

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

@@ -48,6 +48,7 @@ static struct mlx5_irq *
 irq_pool_request_irq(struct mlx5_irq_pool *pool, struct irq_affinity_desc *af_desc)
 {
 	struct irq_affinity_desc auto_desc = {};
+	struct mlx5_irq *irq;
 	u32 irq_index;
 	int err;
 
@@ -64,9 +65,12 @@ irq_pool_request_irq(struct mlx5_irq_pool *pool, struct irq_affinity_desc *af_de
 		else
 			cpu_get(pool, cpumask_first(&af_desc->mask));
 	}
-	return mlx5_irq_alloc(pool, irq_index,
-			      cpumask_empty(&auto_desc.mask) ? af_desc : &auto_desc,
-			      NULL);
+	irq = mlx5_irq_alloc(pool, irq_index,
+			     cpumask_empty(&auto_desc.mask) ? af_desc : &auto_desc,
+			     NULL);
+	if (IS_ERR(irq))
+		xa_erase(&pool->irqs, irq_index);
+	return irq;
 }
 
 /* Looking for the IRQ with the smallest refcount that fits req_mask.

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

@@ -1538,7 +1538,7 @@ u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev,
 		goto unlock;
 
 	for (i = 0; i < ldev->ports; i++) {
-		if (ldev->pf[MLX5_LAG_P1].netdev == slave) {
+		if (ldev->pf[i].netdev == slave) {
 			port = i;
 			break;
 		}

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

@@ -2142,7 +2142,6 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev)
 	/* Panic tear down fw command will stop the PCI bus communication
 	 * with the HCA, so the health poll is no longer needed.
 	 */
-	mlx5_drain_health_wq(dev);
 	mlx5_stop_health_poll(dev, false);
 
 	ret = mlx5_cmd_fast_teardown_hca(dev);
@@ -2177,6 +2176,7 @@ static void shutdown(struct pci_dev *pdev)
 
 	mlx5_core_info(dev, "Shutdown was called\n");
 	set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state);
+	mlx5_drain_health_wq(dev);
 	err = mlx5_try_fast_unload(dev);
 	if (err)
 		mlx5_unload_one(dev, false);

drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c

@@ -112,6 +112,7 @@ static void mlx5_sf_dev_shutdown(struct auxiliary_device *adev)
 	struct mlx5_core_dev *mdev = sf_dev->mdev;
 
 	set_bit(MLX5_BREAK_FW_WAIT, &mdev->intf_state);
+	mlx5_drain_health_wq(mdev);
 	mlx5_unload_one(mdev, false);
 }
 

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

@@ -7,7 +7,7 @@
 /* don't try to optimize STE allocation if the stack is too constaraining */
 #define DR_RULE_MAX_STES_OPTIMIZED 0
 #else
-#define DR_RULE_MAX_STES_OPTIMIZED 5
+#define DR_RULE_MAX_STES_OPTIMIZED 2
 #endif
 #define DR_RULE_MAX_STE_CHAIN_OPTIMIZED (DR_RULE_MAX_STES_OPTIMIZED + DR_ACTION_MAX_STES)