Merge branch 'mlx5-misc-fixes-2025-08-25'

Mark Bloch says:

====================
mlx5 misc fixes 2025-08-25

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

v1: https://lore.kernel.org/[email protected]
====================

Link: https://patch.msgid.link/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: kuba-moo

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

@@ -160,7 +160,7 @@ static int mlx5_devlink_reload_fw_activate(struct devlink *devlink, struct netli
 	if (err)
 		return err;
 
-	mlx5_unload_one_devl_locked(dev, true);
+	mlx5_sync_reset_unload_flow(dev, true);
 	err = mlx5_health_wait_pci_up(dev);
 	if (err)
 		NL_SET_ERR_MSG_MOD(extack, "FW activate aborted, PCI reads fail after reset");

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

@@ -575,7 +575,6 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 		if (err)
 			return err;
 	}
-	priv->dcbx.xoff = xoff;
 
 	/* Apply the settings */
 	if (update_buffer) {
@@ -584,6 +583,8 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 			return err;
 	}
 
+	priv->dcbx.xoff = xoff;
+
 	if (update_prio2buffer)
 		err = mlx5e_port_set_priority2buffer(priv->mdev, prio2buffer);
 

drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h

@@ -66,11 +66,23 @@ struct mlx5e_port_buffer {
 	struct mlx5e_bufferx_reg  buffer[MLX5E_MAX_NETWORK_BUFFER];
 };
 
+#ifdef CONFIG_MLX5_CORE_EN_DCB
 int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 				    u32 change, unsigned int mtu,
 				    struct ieee_pfc *pfc,
 				    u32 *buffer_size,
 				    u8 *prio2buffer);
+#else
+static inline int
+mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
+				u32 change, unsigned int mtu,
+				void *pfc,
+				u32 *buffer_size,
+				u8 *prio2buffer)
+{
+	return 0;
+}
+#endif
 
 int mlx5e_port_query_buffer(struct mlx5e_priv *priv,
 			    struct mlx5e_port_buffer *port_buffer);

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

@@ -49,6 +49,7 @@
 #include "en.h"
 #include "en/dim.h"
 #include "en/txrx.h"
+#include "en/port_buffer.h"
 #include "en_tc.h"
 #include "en_rep.h"
 #include "en_accel/ipsec.h"
@@ -138,6 +139,8 @@ void mlx5e_update_carrier(struct mlx5e_priv *priv)
 	if (up) {
 		netdev_info(priv->netdev, "Link up\n");
 		netif_carrier_on(priv->netdev);
+		mlx5e_port_manual_buffer_config(priv, 0, priv->netdev->mtu,
+						NULL, NULL, NULL);
 	} else {
 		netdev_info(priv->netdev, "Link down\n");
 		netif_carrier_off(priv->netdev);
@@ -3040,9 +3043,11 @@ int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv)
 	struct mlx5e_params *params = &priv->channels.params;
 	struct net_device *netdev = priv->netdev;
 	struct mlx5_core_dev *mdev = priv->mdev;
-	u16 mtu;
+	u16 mtu, prev_mtu;
 	int err;
 
+	mlx5e_query_mtu(mdev, params, &prev_mtu);
+
 	err = mlx5e_set_mtu(mdev, params, params->sw_mtu);
 	if (err)
 		return err;
@@ -3052,6 +3057,18 @@ int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv)
 		netdev_warn(netdev, "%s: VPort MTU %d is different than netdev mtu %d\n",
 			    __func__, mtu, params->sw_mtu);
 
+	if (mtu != prev_mtu && MLX5_BUFFER_SUPPORTED(mdev)) {
+		err = mlx5e_port_manual_buffer_config(priv, 0, mtu,
+						      NULL, NULL, NULL);
+		if (err) {
+			netdev_warn(netdev, "%s: Failed to set Xon/Xoff values with MTU %d (err %d), setting back to previous MTU %d\n",
+				    __func__, mtu, err, prev_mtu);
+
+			mlx5e_set_mtu(mdev, params, prev_mtu);
+			return err;
+		}
+	}
+
 	params->sw_mtu = mtu;
 	return 0;
 }

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

@@ -3734,6 +3734,13 @@ static int mlx5_fs_mode_validate(struct devlink *devlink, u32 id,
 	char *value = val.vstr;
 	u8 eswitch_mode;
 
+	eswitch_mode = mlx5_eswitch_mode(dev);
+	if (eswitch_mode == MLX5_ESWITCH_OFFLOADS) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Changing fs mode is not supported when eswitch offloads enabled.");
+		return -EOPNOTSUPP;
+	}
+
 	if (!strcmp(value, "dmfs"))
 		return 0;
 
@@ -3759,14 +3766,6 @@ static int mlx5_fs_mode_validate(struct devlink *devlink, u32 id,
 		return -EINVAL;
 	}
 
-	eswitch_mode = mlx5_eswitch_mode(dev);
-	if (eswitch_mode == MLX5_ESWITCH_OFFLOADS) {
-		NL_SET_ERR_MSG_FMT_MOD(extack,
-				       "Moving to %s is not supported when eswitch offloads enabled.",
-				       value);
-		return -EOPNOTSUPP;
-	}
-
 	return 0;
 }
 

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

@@ -6,13 +6,15 @@
 #include "fw_reset.h"
 #include "diag/fw_tracer.h"
 #include "lib/tout.h"
+#include "sf/sf.h"
 
 enum {
 	MLX5_FW_RESET_FLAGS_RESET_REQUESTED,
 	MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST,
 	MLX5_FW_RESET_FLAGS_PENDING_COMP,
 	MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS,
-	MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED
+	MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED,
+	MLX5_FW_RESET_FLAGS_UNLOAD_EVENT,
 };
 
 struct mlx5_fw_reset {
@@ -219,7 +221,7 @@ int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev)
 	return mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL0, 0, 0, false);
 }
 
-static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unloaded)
+static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev)
 {
 	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
 	struct devlink *devlink = priv_to_devlink(dev);
@@ -228,8 +230,7 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unload
 	if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) {
 		complete(&fw_reset->done);
 	} else {
-		if (!unloaded)
-			mlx5_unload_one(dev, false);
+		mlx5_sync_reset_unload_flow(dev, false);
 		if (mlx5_health_wait_pci_up(dev))
 			mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n");
 		else
@@ -272,7 +273,7 @@ static void mlx5_sync_reset_reload_work(struct work_struct *work)
 
 	mlx5_sync_reset_clear_reset_requested(dev, false);
 	mlx5_enter_error_state(dev, true);
-	mlx5_fw_reset_complete_reload(dev, false);
+	mlx5_fw_reset_complete_reload(dev);
 }
 
 #define MLX5_RESET_POLL_INTERVAL	(HZ / 10)
@@ -428,6 +429,11 @@ static bool mlx5_is_reset_now_capable(struct mlx5_core_dev *dev,
 		return false;
 	}
 
+	if (!mlx5_core_is_ecpf(dev) && !mlx5_sf_table_empty(dev)) {
+		mlx5_core_warn(dev, "SFs should be removed before reset\n");
+		return false;
+	}
+
 #if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)
 	if (reset_method != MLX5_MFRL_REG_PCI_RESET_METHOD_HOT_RESET) {
 		err = mlx5_check_hotplug_interrupt(dev, bridge);
@@ -586,6 +592,65 @@ static int mlx5_sync_pci_reset(struct mlx5_core_dev *dev, u8 reset_method)
 	return err;
 }
 
+void mlx5_sync_reset_unload_flow(struct mlx5_core_dev *dev, bool locked)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+	unsigned long timeout;
+	int poll_freq = 20;
+	bool reset_action;
+	u8 rst_state;
+	int err;
+
+	if (locked)
+		mlx5_unload_one_devl_locked(dev, false);
+	else
+		mlx5_unload_one(dev, false);
+
+	if (!test_bit(MLX5_FW_RESET_FLAGS_UNLOAD_EVENT, &fw_reset->reset_flags))
+		return;
+
+	mlx5_set_fw_rst_ack(dev);
+	mlx5_core_warn(dev, "Sync Reset Unload done, device reset expected\n");
+
+	reset_action = false;
+	timeout = jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, RESET_UNLOAD));
+	do {
+		rst_state = mlx5_get_fw_rst_state(dev);
+		if (rst_state == MLX5_FW_RST_STATE_TOGGLE_REQ ||
+		    rst_state == MLX5_FW_RST_STATE_IDLE) {
+			reset_action = true;
+			break;
+		}
+		if (rst_state == MLX5_FW_RST_STATE_DROP_MODE) {
+			mlx5_core_info(dev, "Sync Reset Drop mode ack\n");
+			mlx5_set_fw_rst_ack(dev);
+			poll_freq = 1000;
+		}
+		msleep(poll_freq);
+	} while (!time_after(jiffies, timeout));
+
+	if (!reset_action) {
+		mlx5_core_err(dev, "Got timeout waiting for sync reset action, state = %u\n",
+			      rst_state);
+		fw_reset->ret = -ETIMEDOUT;
+		goto done;
+	}
+
+	mlx5_core_warn(dev, "Sync Reset, got reset action. rst_state = %u\n",
+		       rst_state);
+	if (rst_state == MLX5_FW_RST_STATE_TOGGLE_REQ) {
+		err = mlx5_sync_pci_reset(dev, fw_reset->reset_method);
+		if (err) {
+			mlx5_core_warn(dev, "mlx5_sync_pci_reset failed, err %d\n",
+				       err);
+			fw_reset->ret = err;
+		}
+	}
+
+done:
+	clear_bit(MLX5_FW_RESET_FLAGS_UNLOAD_EVENT, &fw_reset->reset_flags);
+}
+
 static void mlx5_sync_reset_now_event(struct work_struct *work)
 {
 	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
@@ -613,17 +678,13 @@ static void mlx5_sync_reset_now_event(struct work_struct *work)
 	mlx5_enter_error_state(dev, true);
 done:
 	fw_reset->ret = err;
-	mlx5_fw_reset_complete_reload(dev, false);
+	mlx5_fw_reset_complete_reload(dev);
 }
 
 static void mlx5_sync_reset_unload_event(struct work_struct *work)
 {
 	struct mlx5_fw_reset *fw_reset;
 	struct mlx5_core_dev *dev;
-	unsigned long timeout;
-	int poll_freq = 20;
-	bool reset_action;
-	u8 rst_state;
 	int err;
 
 	fw_reset = container_of(work, struct mlx5_fw_reset, reset_unload_work);
@@ -632,6 +693,7 @@ static void mlx5_sync_reset_unload_event(struct work_struct *work)
 	if (mlx5_sync_reset_clear_reset_requested(dev, false))
 		return;
 
+	set_bit(MLX5_FW_RESET_FLAGS_UNLOAD_EVENT, &fw_reset->reset_flags);
 	mlx5_core_warn(dev, "Sync Reset Unload. Function is forced down.\n");
 
 	err = mlx5_cmd_fast_teardown_hca(dev);
@@ -640,49 +702,7 @@ static void mlx5_sync_reset_unload_event(struct work_struct *work)
 	else
 		mlx5_enter_error_state(dev, true);
 
-	if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags))
-		mlx5_unload_one_devl_locked(dev, false);
-	else
-		mlx5_unload_one(dev, false);
-
-	mlx5_set_fw_rst_ack(dev);
-	mlx5_core_warn(dev, "Sync Reset Unload done, device reset expected\n");
-
-	reset_action = false;
-	timeout = jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, RESET_UNLOAD));
-	do {
-		rst_state = mlx5_get_fw_rst_state(dev);
-		if (rst_state == MLX5_FW_RST_STATE_TOGGLE_REQ ||
-		    rst_state == MLX5_FW_RST_STATE_IDLE) {
-			reset_action = true;
-			break;
-		}
-		if (rst_state == MLX5_FW_RST_STATE_DROP_MODE) {
-			mlx5_core_info(dev, "Sync Reset Drop mode ack\n");
-			mlx5_set_fw_rst_ack(dev);
-			poll_freq = 1000;
-		}
-		msleep(poll_freq);
-	} while (!time_after(jiffies, timeout));
-
-	if (!reset_action) {
-		mlx5_core_err(dev, "Got timeout waiting for sync reset action, state = %u\n",
-			      rst_state);
-		fw_reset->ret = -ETIMEDOUT;
-		goto done;
-	}
-
-	mlx5_core_warn(dev, "Sync Reset, got reset action. rst_state = %u\n", rst_state);
-	if (rst_state == MLX5_FW_RST_STATE_TOGGLE_REQ) {
-		err = mlx5_sync_pci_reset(dev, fw_reset->reset_method);
-		if (err) {
-			mlx5_core_warn(dev, "mlx5_sync_pci_reset failed, err %d\n", err);
-			fw_reset->ret = err;
-		}
-	}
-
-done:
-	mlx5_fw_reset_complete_reload(dev, true);
+	mlx5_fw_reset_complete_reload(dev);
 }
 
 static void mlx5_sync_reset_abort_event(struct work_struct *work)

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

@@ -12,6 +12,7 @@ int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel,
 int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev);
 
 int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev);
+void mlx5_sync_reset_unload_flow(struct mlx5_core_dev *dev, bool locked);
 int mlx5_fw_reset_verify_fw_complete(struct mlx5_core_dev *dev,
 				     struct netlink_ext_ack *extack);
 void mlx5_fw_reset_events_start(struct mlx5_core_dev *dev);

drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c

@@ -518,3 +518,13 @@ void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev)
 	WARN_ON(!xa_empty(&table->function_ids));
 	kfree(table);
 }
+
+bool mlx5_sf_table_empty(const struct mlx5_core_dev *dev)
+{
+	struct mlx5_sf_table *table = dev->priv.sf_table;
+
+	if (!table)
+		return true;
+
+	return xa_empty(&table->function_ids);
+}

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

@@ -17,6 +17,7 @@ void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev);
 
 int mlx5_sf_table_init(struct mlx5_core_dev *dev);
 void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev);
+bool mlx5_sf_table_empty(const struct mlx5_core_dev *dev);
 
 int mlx5_devlink_sf_port_new(struct devlink *devlink,
 			     const struct devlink_port_new_attrs *add_attr,
@@ -61,6 +62,11 @@ static inline void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev)
 {
 }
 
+static inline bool mlx5_sf_table_empty(const struct mlx5_core_dev *dev)
+{
+	return true;
+}
+
 #endif
 
 #endif

drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c

@@ -117,7 +117,7 @@ static int hws_action_get_shared_stc_nic(struct mlx5hws_context *ctx,
 		mlx5hws_err(ctx, "No such stc_type: %d\n", stc_type);
 		pr_warn("HWS: Invalid stc_type: %d\n", stc_type);
 		ret = -EINVAL;
-		goto unlock_and_out;
+		goto free_shared_stc;
 	}
 
 	ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, tbl_type,