Merge branch 'net-mlx5-preserve-speed-and-state-across-vport-modify-commands'

Tariq Toukan says:

====================
net/mlx5: Preserve speed and state across vport modify commands

The firmware vport modify command bundles both admin state and max tx
speed in a single operation, which requires each side to preserve the
other field when it only intends to change one.

When modifying max tx speed, the driver already queries the current
admin state and passes it back to avoid overwriting it. However, this
query and the subsequent modify were not atomic, a state change
between the two could cause the modify to overwrite the new state with
a stale value. The fix holds esw->state_lock across the query-modify
sequence.

When support for setting max tx speed via the vport modify command was
introduced, the existing admin state modify path was not updated to
preserve the current speed. As a result, the firmware interprets the
zero speed field as an intentional reset. The fix adds a speed query
before the state modify and passes the result back in the command.

To support that, mlx5_query_vport_max_tx_speed() had to be fixed first:
it was returning zero whenever the vport was DOWN, which was correct
for the query_port_speed verb but would defeat the purpose of querying
before a state modify. The DOWN-to-zero logic is moved to the
verb-layer caller so the function returns the raw firmware value.

Patch #1  holds esw->state_lock across the state query and modify in
          the speed modify path
Patch #2  moves the vport DOWN zero mapping to the verb-layer caller
          so the query returns the raw firmware value
Patch #3  queries current max tx speed before modifying vport state to
          preserve it
====================

Link: https://patch.msgid.link/20260816065015.3280733-1-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/infiniband/hw/mlx5/main.c

@@ -1631,14 +1631,15 @@ static int mlx5_ib_query_port_speed_from_vport(struct mlx5_core_dev *mdev,
 					       u32 port_num)
 {
 	u32 max_tx_speed;
+	u8 vport_state;
 	int err;
 
 	err = mlx5_query_vport_max_tx_speed(mdev, op_mod, vport, other_vport,
-					    &max_tx_speed);
+					    &max_tx_speed, &vport_state);
 	if (err)
 		return err;
 
-	if (max_tx_speed == 0)
+	if (vport_state == VPORT_STATE_DOWN || max_tx_speed == 0)
 		/* Value 0 indicates field not supported, fallback */
 		return mlx5_ib_query_port_speed_from_port(dev, port_num,
 							  speed);

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

@@ -689,11 +689,13 @@ static int mlx5e_rep_open(struct net_device *dev)
 	if (err)
 		goto unlock;
 
+	mutex_lock(&rep->esw->state_lock);
 	if (!mlx5_modify_vport_admin_state(priv->mdev,
 					   MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
 					   rep->vport, 1,
 					   MLX5_VPORT_ADMIN_STATE_UP))
 		netif_carrier_on(dev);
+	mutex_unlock(&rep->esw->state_lock);
 
 unlock:
 	mutex_unlock(&priv->state_lock);
@@ -708,10 +710,12 @@ static int mlx5e_rep_close(struct net_device *dev)
 	int ret;
 
 	mutex_lock(&priv->state_lock);
+	mutex_lock(&rep->esw->state_lock);
 	mlx5_modify_vport_admin_state(priv->mdev,
 				      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
 				      rep->vport, 1,
 				      MLX5_VPORT_ADMIN_STATE_DOWN);
+	mutex_unlock(&rep->esw->state_lock);
 	ret = mlx5e_close_locked(dev);
 	mutex_unlock(&priv->state_lock);
 	return ret;
@@ -783,22 +787,25 @@ static int mlx5e_rep_change_carrier(struct net_device *dev, bool new_carrier)
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
-	int err;
+	int err = 0;
 
+	mutex_lock(&rep->esw->state_lock);
 	if (new_carrier) {
 		err = mlx5_modify_vport_admin_state(priv->mdev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
 						    rep->vport, 1, MLX5_VPORT_ADMIN_STATE_UP);
 		if (err)
-			return err;
+			goto unlock;
 		netif_carrier_on(dev);
 	} else {
 		err = mlx5_modify_vport_admin_state(priv->mdev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
 						    rep->vport, 1, MLX5_VPORT_ADMIN_STATE_DOWN);
 		if (err)
-			return err;
+			goto unlock;
 		netif_carrier_off(dev);
 	}
-	return 0;
+unlock:
+	mutex_unlock(&rep->esw->state_lock);
+	return err;
 }
 
 static const struct net_device_ops mlx5e_netdev_ops_rep = {
@@ -1339,9 +1346,12 @@ static int mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 
 	mlx5e_rep_tc_enable(priv);
 
-	if (MLX5_CAP_GEN(mdev, uplink_follow))
+	if (MLX5_CAP_GEN(mdev, uplink_follow)) {
+		mutex_lock(&mdev->priv.eswitch->state_lock);
 		mlx5_modify_vport_admin_state(mdev, MLX5_VPORT_STATE_OP_MOD_UPLINK,
 					      0, 0, MLX5_VPORT_ADMIN_STATE_AUTO);
+		mutex_unlock(&mdev->priv.eswitch->state_lock);
+	}
 	mlx5_lag_add_netdev(mdev, netdev);
 	priv->events_nb.notifier_call = uplink_rep_async_event;
 	mlx5_notifier_register(mdev, &priv->events_nb);

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

@@ -9,6 +9,28 @@ int mlx5_esw_adj_vport_modify(struct mlx5_core_dev *dev, u16 vport,
 {
 	u32 in[MLX5_ST_SZ_DW(modify_vport_state_in)] = {};
 
+	lockdep_assert_held(&dev->priv.eswitch->state_lock);
+
+	if (MLX5_CAP_ESW(dev, esw_vport_state_max_tx_speed)) {
+		u8 op_mod = MLX5_VPORT_STATE_OP_MOD_ESW_VPORT;
+		struct mlx5_vport *esw_vport;
+		u32 speed = 0;
+		int err;
+
+		err = mlx5_query_vport_max_tx_speed(dev, op_mod, vport,
+						    true, &speed, NULL);
+		if (err) {
+			esw_vport = mlx5_eswitch_get_vport(dev->priv.eswitch,
+							   vport);
+			speed = IS_ERR(esw_vport) ? 0 :
+				esw_vport->agg_max_tx_speed;
+			mlx5_core_dbg(dev,
+				      "Failed to query vport %d max tx speed, err=%d, using cached %u\n",
+				      vport, err, speed);
+		}
+		MLX5_SET(modify_vport_state_in, in, max_tx_speed, speed);
+	}
+
 	MLX5_SET(modify_vport_state_in, in, opcode,
 		 MLX5_CMD_OP_MODIFY_VPORT_STATE);
 	MLX5_SET(modify_vport_state_in, in, op_mod,

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

@@ -2567,6 +2567,7 @@ static void mlx5_esw_fdb_active(struct mlx5_eswitch *esw)
 	mlx5_esw_fdb_drop_destroy(esw);
 	mlx5_mpfs_enable(esw->dev);
 
+	mutex_lock(&esw->state_lock);
 	mlx5_esw_for_each_vf_vport(esw, i, vport, U16_MAX) {
 		if (!vport->adjacent)
 			continue;
@@ -2574,6 +2575,7 @@ static void mlx5_esw_fdb_active(struct mlx5_eswitch *esw)
 			  vport->vport);
 		mlx5_esw_adj_vport_modify(esw->dev, vport->vport, true);
 	}
+	mutex_unlock(&esw->state_lock);
 
 	esw->offloads_inactive = false;
 	esw_warn(esw->dev, "MPFS/FDB active\n");
@@ -2587,6 +2589,7 @@ static void mlx5_esw_fdb_inactive(struct mlx5_eswitch *esw)
 	mlx5_mpfs_disable(esw->dev);
 	mlx5_esw_fdb_drop_create(esw);
 
+	mutex_lock(&esw->state_lock);
 	mlx5_esw_for_each_vf_vport(esw, i, vport, U16_MAX) {
 		if (!vport->adjacent)
 			continue;
@@ -2595,6 +2598,7 @@ static void mlx5_esw_fdb_inactive(struct mlx5_eswitch *esw)
 
 		mlx5_esw_adj_vport_modify(esw->dev, vport->vport, false);
 	}
+	mutex_unlock(&esw->state_lock);
 
 	esw->offloads_inactive = true;
 	esw_warn(esw->dev, "MPFS/FDB inactive\n");

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

@@ -1471,6 +1471,7 @@ static void mlx5_lag_modify_device_vports_speed(struct mlx5_core_dev *mdev,
 	if (!MLX5_CAP_ESW(mdev, esw_vport_state_max_tx_speed))
 		return;
 
+	mutex_lock(&esw->state_lock);
 	mlx5_esw_for_each_vport(esw, i, vport) {
 		if (!vport)
 			continue;
@@ -1490,6 +1491,7 @@ static void mlx5_lag_modify_device_vports_speed(struct mlx5_core_dev *mdev,
 				      "Failed to set vport %d speed %d, err=%d\n",
 				      vport->vport, speed, ret);
 	}
+	mutex_unlock(&esw->state_lock);
 }
 
 void mlx5_lag_set_vports_agg_speed(struct mlx5_lag *ldev)

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

@@ -89,6 +89,34 @@ int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
 {
 	u32 in[MLX5_ST_SZ_DW(modify_vport_state_in)] = {};
 
+#ifdef CONFIG_MLX5_ESWITCH
+	lockdep_assert_held(&mdev->priv.eswitch->state_lock);
+#endif
+
+	if (MLX5_CAP_ESW(mdev, esw_vport_state_max_tx_speed) &&
+	    opmod == MLX5_VPORT_STATE_OP_MOD_ESW_VPORT &&
+	    vport != MLX5_VPORT_UPLINK) {
+		u32 speed = 0;
+		int err;
+
+		err = mlx5_query_vport_max_tx_speed(mdev, opmod, vport,
+						    other_vport, &speed, NULL);
+		if (err) {
+#ifdef CONFIG_MLX5_ESWITCH
+			struct mlx5_vport *esw_vport;
+
+			esw_vport = mlx5_eswitch_get_vport(mdev->priv.eswitch,
+							   vport);
+			speed = IS_ERR(esw_vport) ? 0 :
+				esw_vport->agg_max_tx_speed;
+#endif
+			mlx5_core_dbg(mdev,
+				      "Failed to query vport %d max tx speed, err=%d, using cached %u\n",
+				      vport, err, speed);
+		}
+		MLX5_SET(modify_vport_state_in, in, max_tx_speed, speed);
+	}
+
 	MLX5_SET(modify_vport_state_in, in, opcode,
 		 MLX5_CMD_OP_MODIFY_VPORT_STATE);
 	MLX5_SET(modify_vport_state_in, in, op_mod, opmod);
@@ -106,6 +134,10 @@ int mlx5_modify_vport_max_tx_speed(struct mlx5_core_dev *mdev, u8 opmod,
 	u8 admin_state;
 	int err;
 
+#ifdef CONFIG_MLX5_ESWITCH
+	lockdep_assert_held(&mdev->priv.eswitch->state_lock);
+#endif
+
 	err = mlx5_query_vport_admin_state(mdev, opmod, vport, other_vport,
 					   &admin_state);
 	if (err)
@@ -123,11 +155,11 @@ int mlx5_modify_vport_max_tx_speed(struct mlx5_core_dev *mdev, u8 opmod,
 }
 
 int mlx5_query_vport_max_tx_speed(struct mlx5_core_dev *mdev, u8 op_mod,
-				  u16 vport, u8 other_vport, u32 *max_tx_speed)
+				  u16 vport, u8 other_vport,
+				  u32 *max_tx_speed, u8 *state)
 {
 	u32 out[MLX5_ST_SZ_DW(query_vport_state_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(query_vport_state_in)] = {};
-	u32 state;
 	int err;
 
 	MLX5_SET(query_vport_state_in, in, opcode,
@@ -140,13 +172,9 @@ int mlx5_query_vport_max_tx_speed(struct mlx5_core_dev *mdev, u8 op_mod,
 	if (err)
 		return err;
 
-	state = MLX5_GET(query_vport_state_out, out, state);
-	if (state == VPORT_STATE_DOWN) {
-		*max_tx_speed = 0;
-		return 0;
-	}
-
 	*max_tx_speed = MLX5_GET(query_vport_state_out, out, max_tx_speed);
+	if (state)
+		*state = MLX5_GET(query_vport_state_out, out, state);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mlx5_query_vport_max_tx_speed);

include/linux/mlx5/vport.h

@@ -61,7 +61,8 @@ 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 other_vport, u8 state);
 int mlx5_query_vport_max_tx_speed(struct mlx5_core_dev *mdev, u8 op_mod,
-				  u16 vport, u8 other_vport, u32 *max_tx_speed);
+				  u16 vport, u8 other_vport,
+				  u32 *max_tx_speed, u8 *state);
 int mlx5_modify_vport_max_tx_speed(struct mlx5_core_dev *mdev, u8 opmod,
 				   u16 vport, u8 other_vport, u16 max_tx_speed);
 int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev,