Commit 9245b518 authored by Jakub Kicinski's avatar Jakub Kicinski
Browse files

Merge tag 'mlx5-next-netdev-deadlock' of...

Merge tag 'mlx5-next-netdev-deadlock' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux

Saeed Mahameed says:

====================
mlx5-next-netdev-deadlock

This series from Jiri solves a deadlock when removing a network namespace
with mlx5 devlink instance being in it.
The deadlock is between:
1) mlx5_ib->unregister_netdevice_notifier()
AND
2) mlx5_core->devlink_reload->cleanup_net()

To slove this introduced mlx5 netdev added/removed events to track uplink
netdev to be used for register_netdevice_notifier_dev_net() purposes.

* tag 'mlx5-next-netdev-deadlock' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux:
  RDMA/mlx5: Track netdev to avoid deadlock during netdev notifier unregister
  net/mlx5e: Propagate an internal event in case uplink netdev changes
  net/mlx5e: Fix trap event handling
  net/mlx5: Introduce CQE error syndrome
====================

Link: https://lore.kernel.org/r/20230208005626.72930-1-saeed@kernel.org


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parents 3ca11619 dca55da0
Loading
Loading
Loading
Loading
+54 −24
Original line number Diff line number Diff line
@@ -3012,26 +3012,63 @@ static void mlx5_eth_lag_cleanup(struct mlx5_ib_dev *dev)
	}
}

static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u32 port_num)
static void mlx5_netdev_notifier_register(struct mlx5_roce *roce,
					  struct net_device *netdev)
{
	int err;

	dev->port[port_num].roce.nb.notifier_call = mlx5_netdev_event;
	err = register_netdevice_notifier(&dev->port[port_num].roce.nb);
	if (err) {
		dev->port[port_num].roce.nb.notifier_call = NULL;
		return err;
	if (roce->tracking_netdev)
		return;
	roce->tracking_netdev = netdev;
	roce->nb.notifier_call = mlx5_netdev_event;
	err = register_netdevice_notifier_dev_net(netdev, &roce->nb, &roce->nn);
	WARN_ON(err);
}

	return 0;
static void mlx5_netdev_notifier_unregister(struct mlx5_roce *roce)
{
	if (!roce->tracking_netdev)
		return;
	unregister_netdevice_notifier_dev_net(roce->tracking_netdev, &roce->nb,
					      &roce->nn);
	roce->tracking_netdev = NULL;
}

static int mlx5e_mdev_notifier_event(struct notifier_block *nb,
				     unsigned long event, void *data)
{
	struct mlx5_roce *roce = container_of(nb, struct mlx5_roce, mdev_nb);
	struct net_device *netdev = data;

	switch (event) {
	case MLX5_DRIVER_EVENT_UPLINK_NETDEV:
		if (netdev)
			mlx5_netdev_notifier_register(roce, netdev);
		else
			mlx5_netdev_notifier_unregister(roce);
		break;
	default:
		return NOTIFY_DONE;
	}

	return NOTIFY_OK;
}

static void mlx5_remove_netdev_notifier(struct mlx5_ib_dev *dev, u32 port_num)
static void mlx5_mdev_netdev_track(struct mlx5_ib_dev *dev, u32 port_num)
{
	if (dev->port[port_num].roce.nb.notifier_call) {
		unregister_netdevice_notifier(&dev->port[port_num].roce.nb);
		dev->port[port_num].roce.nb.notifier_call = NULL;
	struct mlx5_roce *roce = &dev->port[port_num].roce;

	roce->mdev_nb.notifier_call = mlx5e_mdev_notifier_event;
	mlx5_blocking_notifier_register(dev->mdev, &roce->mdev_nb);
	mlx5_core_uplink_netdev_event_replay(dev->mdev);
}

static void mlx5_mdev_netdev_untrack(struct mlx5_ib_dev *dev, u32 port_num)
{
	struct mlx5_roce *roce = &dev->port[port_num].roce;

	mlx5_blocking_notifier_unregister(dev->mdev, &roce->mdev_nb);
	mlx5_netdev_notifier_unregister(roce);
}

static int mlx5_enable_eth(struct mlx5_ib_dev *dev)
@@ -3138,7 +3175,7 @@ static void mlx5_ib_unbind_slave_port(struct mlx5_ib_dev *ibdev,
	if (mpi->mdev_events.notifier_call)
		mlx5_notifier_unregister(mpi->mdev, &mpi->mdev_events);
	mpi->mdev_events.notifier_call = NULL;
	mlx5_remove_netdev_notifier(ibdev, port_num);
	mlx5_mdev_netdev_untrack(ibdev, port_num);
	spin_lock(&port->mp.mpi_lock);

	comps = mpi->mdev_refcnt;
@@ -3196,12 +3233,7 @@ static bool mlx5_ib_bind_slave_port(struct mlx5_ib_dev *ibdev,
	if (err)
		goto unbind;

	err = mlx5_add_netdev_notifier(ibdev, port_num);
	if (err) {
		mlx5_ib_err(ibdev, "failed adding netdev notifier for port %u\n",
			    port_num + 1);
		goto unbind;
	}
	mlx5_mdev_netdev_track(ibdev, port_num);

	mpi->mdev_events.notifier_call = mlx5_ib_event_slave_port;
	mlx5_notifier_register(mpi->mdev, &mpi->mdev_events);
@@ -3909,9 +3941,7 @@ static int mlx5_ib_roce_init(struct mlx5_ib_dev *dev)
		port_num = mlx5_core_native_port_num(dev->mdev) - 1;

		/* Register only for native ports */
		err = mlx5_add_netdev_notifier(dev, port_num);
		if (err)
			return err;
		mlx5_mdev_netdev_track(dev, port_num);

		err = mlx5_enable_eth(dev);
		if (err)
@@ -3920,7 +3950,7 @@ static int mlx5_ib_roce_init(struct mlx5_ib_dev *dev)

	return 0;
cleanup:
	mlx5_remove_netdev_notifier(dev, port_num);
	mlx5_mdev_netdev_untrack(dev, port_num);
	return err;
}

@@ -3938,7 +3968,7 @@ static void mlx5_ib_roce_cleanup(struct mlx5_ib_dev *dev)
		mlx5_disable_eth(dev);

		port_num = mlx5_core_native_port_num(dev->mdev) - 1;
		mlx5_remove_netdev_notifier(dev, port_num);
		mlx5_mdev_netdev_untrack(dev, port_num);
	}
}

+3 −0
Original line number Diff line number Diff line
@@ -832,6 +832,9 @@ struct mlx5_roce {
	rwlock_t		netdev_lock;
	struct net_device	*netdev;
	struct notifier_block	nb;
	struct netdev_net_notifier nn;
	struct notifier_block	mdev_nb;
	struct net_device	*tracking_netdev;
	atomic_t		tx_port_affinity;
	enum ib_port_state last_port_state;
	struct mlx5_ib_dev	*dev;
+12 −12
Original line number Diff line number Diff line
@@ -268,9 +268,10 @@ static int mlx5_devlink_trap_action_set(struct devlink *devlink,
					struct netlink_ext_ack *extack)
{
	struct mlx5_core_dev *dev = devlink_priv(devlink);
	struct mlx5_devlink_trap_event_ctx trap_event_ctx;
	enum devlink_trap_action action_orig;
	struct mlx5_devlink_trap *dl_trap;
	int err = 0;
	int err;

	if (is_mdev_switchdev_mode(dev)) {
		NL_SET_ERR_MSG_MOD(extack, "Devlink traps can't be set in switchdev mode");
@@ -280,26 +281,25 @@ static int mlx5_devlink_trap_action_set(struct devlink *devlink,
	dl_trap = mlx5_find_trap_by_id(dev, trap->id);
	if (!dl_trap) {
		mlx5_core_err(dev, "Devlink trap: Set action on invalid trap id 0x%x", trap->id);
		err = -EINVAL;
		goto out;
		return -EINVAL;
	}

	if (action != DEVLINK_TRAP_ACTION_DROP && action != DEVLINK_TRAP_ACTION_TRAP) {
		err = -EOPNOTSUPP;
		goto out;
	}
	if (action != DEVLINK_TRAP_ACTION_DROP && action != DEVLINK_TRAP_ACTION_TRAP)
		return -EOPNOTSUPP;

	if (action == dl_trap->trap.action)
		goto out;
		return 0;

	action_orig = dl_trap->trap.action;
	dl_trap->trap.action = action;
	trap_event_ctx.trap = &dl_trap->trap;
	trap_event_ctx.err = 0;
	err = mlx5_blocking_notifier_call_chain(dev, MLX5_DRIVER_EVENT_TYPE_TRAP,
						&dl_trap->trap);
	if (err)
						&trap_event_ctx);
	if (err == NOTIFY_BAD)
		dl_trap->trap.action = action_orig;
out:
	return err;

	return trap_event_ctx.err;
}

static const struct devlink_ops mlx5_devlink_ops = {
+5 −0
Original line number Diff line number Diff line
@@ -24,6 +24,11 @@ struct mlx5_devlink_trap {
	struct list_head list;
};

struct mlx5_devlink_trap_event_ctx {
	struct mlx5_trap_ctx *trap;
	int err;
};

struct mlx5_core_dev;
void mlx5_devlink_trap_report(struct mlx5_core_dev *dev, int trap_id, struct sk_buff *skb,
			      struct devlink_port *dl_port);
+10 −5
Original line number Diff line number Diff line
@@ -181,17 +181,21 @@ static void mlx5e_disable_async_events(struct mlx5e_priv *priv)
static int blocking_event(struct notifier_block *nb, unsigned long event, void *data)
{
	struct mlx5e_priv *priv = container_of(nb, struct mlx5e_priv, blocking_events_nb);
	struct mlx5_devlink_trap_event_ctx *trap_event_ctx = data;
	int err;

	switch (event) {
	case MLX5_DRIVER_EVENT_TYPE_TRAP:
		err = mlx5e_handle_trap_event(priv, data);
		err = mlx5e_handle_trap_event(priv, trap_event_ctx->trap);
		if (err) {
			trap_event_ctx->err = err;
			return NOTIFY_BAD;
		}
		break;
	default:
		netdev_warn(priv->netdev, "Sync event: Unknown event %ld\n", event);
		err = -EINVAL;
		return NOTIFY_DONE;
	}
	return err;
	return NOTIFY_OK;
}

static void mlx5e_enable_blocking_events(struct mlx5e_priv *priv)
@@ -5984,7 +5988,7 @@ static int mlx5e_probe(struct auxiliary_device *adev,
	}

	mlx5e_dcbnl_init_app(priv);
	mlx5_uplink_netdev_set(mdev, netdev);
	mlx5_core_uplink_netdev_set(mdev, netdev);
	mlx5e_params_print_info(mdev, &priv->channels.params);
	return 0;

@@ -6008,6 +6012,7 @@ static void mlx5e_remove(struct auxiliary_device *adev)
	struct mlx5e_priv *priv = mlx5e_dev->priv;
	pm_message_t state = {};

	mlx5_core_uplink_netdev_set(priv->mdev, NULL);
	mlx5e_dcbnl_delete_app(priv);
	unregister_netdev(priv->netdev);
	mlx5e_suspend(adev, state);
Loading