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: Jakub Kicinski <kuba@kernel.org>

6 files changed, 49 insertions, 22 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 63fb7912b032..b742e04deec1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -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 = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
index 1c1b62ee84bb..b561107e0df1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
@@ -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);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 6b9267c19e00..6ac4c092a591 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -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);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index 9459e56ee90a..718cf09c28ce 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -424,6 +424,7 @@ int mlx5_blocking_notifier_register(struct mlx5_core_dev *dev, struct notifier_b
 
 	return blocking_notifier_chain_register(&events->sw_nh, nb);
 }
+EXPORT_SYMBOL(mlx5_blocking_notifier_register);
 
 int mlx5_blocking_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb)
 {
@@ -431,6 +432,7 @@ int mlx5_blocking_notifier_unregister(struct mlx5_core_dev *dev, struct notifier
 
 	return blocking_notifier_chain_unregister(&events->sw_nh, nb);
 }
+EXPORT_SYMBOL(mlx5_blocking_notifier_unregister);
 
 int mlx5_blocking_notifier_call_chain(struct mlx5_core_dev *dev, unsigned int event,
 				      void *data)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
index 55bd7c4c021e..ccf12f7db6f0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
@@ -84,11 +84,6 @@ static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev)
 	return devlink_net(priv_to_devlink(dev));
 }
 
-static inline void mlx5_uplink_netdev_set(struct mlx5_core_dev *mdev, struct net_device *netdev)
-{
-	mdev->mlx5e_res.uplink_netdev = netdev;
-}
-
 static inline struct net_device *mlx5_uplink_netdev_get(struct mlx5_core_dev *mdev)
 {
 	return mdev->mlx5e_res.uplink_netdev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 9441588ac524..0de9180e4f6b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -336,6 +336,24 @@ static u16 to_fw_pkey_sz(struct mlx5_core_dev *dev, u32 size)
 	}
 }
 
+void mlx5_core_uplink_netdev_set(struct mlx5_core_dev *dev, struct net_device *netdev)
+{
+	mutex_lock(&dev->mlx5e_res.uplink_netdev_lock);
+	dev->mlx5e_res.uplink_netdev = netdev;
+	mlx5_blocking_notifier_call_chain(dev, MLX5_DRIVER_EVENT_UPLINK_NETDEV,
+					  netdev);
+	mutex_unlock(&dev->mlx5e_res.uplink_netdev_lock);
+}
+
+void mlx5_core_uplink_netdev_event_replay(struct mlx5_core_dev *dev)
+{
+	mutex_lock(&dev->mlx5e_res.uplink_netdev_lock);
+	mlx5_blocking_notifier_call_chain(dev, MLX5_DRIVER_EVENT_UPLINK_NETDEV,
+					  dev->mlx5e_res.uplink_netdev);
+	mutex_unlock(&dev->mlx5e_res.uplink_netdev_lock);
+}
+EXPORT_SYMBOL(mlx5_core_uplink_netdev_event_replay);
+
 static int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev,
 				   enum mlx5_cap_type cap_type,
 				   enum mlx5_cap_mode cap_mode)
@@ -1609,6 +1627,7 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 	lockdep_register_key(&dev->lock_key);
 	mutex_init(&dev->intf_state_mutex);
 	lockdep_set_class(&dev->intf_state_mutex, &dev->lock_key);
+	mutex_init(&dev->mlx5e_res.uplink_netdev_lock);
 
 	mutex_init(&priv->bfregs.reg_head.lock);
 	mutex_init(&priv->bfregs.wc_head.lock);
@@ -1697,6 +1716,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
 	mutex_destroy(&priv->alloc_mutex);
 	mutex_destroy(&priv->bfregs.wc_head.lock);
 	mutex_destroy(&priv->bfregs.reg_head.lock);
+	mutex_destroy(&dev->mlx5e_res.uplink_netdev_lock);
 	mutex_destroy(&dev->intf_state_mutex);
 	lockdep_unregister_key(&dev->lock_key);
 }