mlx4: Replace the mlx4_interface.event callback with a notifier

Use a notifier to implement mlx4_dispatch_event() in preparation to
switch mlx4_en and mlx4_ib to be an auxiliary device.

A problem is that if the mlx4_interface.event callback was replaced with
something as mlx4_adrv.event then the implementation of
mlx4_dispatch_event() would need to acquire a lock on a given device
before executing this callback. That is necessary because otherwise
there is no guarantee that the associated driver cannot get unbound when
the callback is running. However, taking this lock is not possible
because mlx4_dispatch_event() can be invoked from the hardirq context.
Using an atomic notifier allows the driver to accurately record when it
wants to receive these events and solves this problem.

A handler registration is done by both mlx4_en and mlx4_ib at the end of
their mlx4_interface.add callback. This matches the current situation
when mlx4_add_device() would enable events for a given device
immediately after this callback, by adding the device on the
mlx4_priv.list.
Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Tested-by: Leon Romanovsky <leonro@nvidia.com>
Acked-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/infiniband/hw/mlx4/main.c

@@ -82,6 +82,8 @@ static const char mlx4_ib_version[] =
 static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init);
 static enum rdma_link_layer mlx4_ib_port_link_layer(struct ib_device *device,
 						    u32 port_num);
+static int mlx4_ib_event(struct notifier_block *this, unsigned long event,
+			 void *param);
 
 static struct workqueue_struct *wq;
 
@@ -2836,6 +2838,12 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 				do_slave_init(ibdev, j, 1);
 		}
 	}
+
+	/* register mlx4 core notifier */
+	ibdev->mlx_nb.notifier_call = mlx4_ib_event;
+	err = mlx4_register_event_notifier(dev, &ibdev->mlx_nb);
+	WARN(err, "failed to register mlx4 event notifier (%d)", err);
+
 	return ibdev;
 
 err_notif:
@@ -2953,6 +2961,8 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
 	int p;
 	int i;
 
+	mlx4_unregister_event_notifier(dev, &ibdev->mlx_nb);
+
 	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
 		devlink_port_type_clear(mlx4_get_devlink_port(dev, i));
 	ibdev->ib_active = false;
@@ -3173,11 +3183,13 @@ void mlx4_sched_ib_sl2vl_update_work(struct mlx4_ib_dev *ibdev,
 	}
 }
 
-static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
-			  enum mlx4_dev_event event, void *param)
+static int mlx4_ib_event(struct notifier_block *this, unsigned long event,
+			 void *param)
 {
+	struct mlx4_ib_dev *ibdev =
+		container_of(this, struct mlx4_ib_dev, mlx_nb);
+	struct mlx4_dev *dev = ibdev->dev;
 	struct ib_event ibev;
-	struct mlx4_ib_dev *ibdev = to_mdev((struct ib_device *) ibdev_ptr);
 	struct mlx4_eqe *eqe = NULL;
 	struct ib_event_work *ew;
 	int p = 0;
@@ -3187,11 +3199,11 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 	    (event == MLX4_DEV_EVENT_PORT_DOWN))) {
 		ew = kmalloc(sizeof(*ew), GFP_ATOMIC);
 		if (!ew)
-			return;
+			return NOTIFY_DONE;
 		INIT_WORK(&ew->work, handle_bonded_port_state_event);
 		ew->ib_dev = ibdev;
 		queue_work(wq, &ew->work);
-		return;
+		return NOTIFY_DONE;
 	}
 
 	switch (event) {
@@ -3208,7 +3220,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 	switch (event) {
 	case MLX4_DEV_EVENT_PORT_UP:
 		if (p > ibdev->num_ports)
-			return;
+			return NOTIFY_DONE;
 		if (!mlx4_is_slave(dev) &&
 		    rdma_port_get_link_layer(&ibdev->ib_dev, p) ==
 			IB_LINK_LAYER_INFINIBAND) {
@@ -3223,7 +3235,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 
 	case MLX4_DEV_EVENT_PORT_DOWN:
 		if (p > ibdev->num_ports)
-			return;
+			return NOTIFY_DONE;
 		ibev.event = IB_EVENT_PORT_ERR;
 		break;
 
@@ -3236,7 +3248,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 	case MLX4_DEV_EVENT_PORT_MGMT_CHANGE:
 		ew = kmalloc(sizeof *ew, GFP_ATOMIC);
 		if (!ew)
-			return;
+			return NOTIFY_DONE;
 
 		INIT_WORK(&ew->work, handle_port_mgmt_change_event);
 		memcpy(&ew->ib_eqe, eqe, sizeof *eqe);
@@ -3246,7 +3258,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 			queue_work(wq, &ew->work);
 		else
 			handle_port_mgmt_change_event(&ew->work);
-		return;
+		return NOTIFY_DONE;
 
 	case MLX4_DEV_EVENT_SLAVE_INIT:
 		/* here, p is the slave id */
@@ -3262,7 +3274,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 								       1);
 			}
 		}
-		return;
+		return NOTIFY_DONE;
 
 	case MLX4_DEV_EVENT_SLAVE_SHUTDOWN:
 		if (mlx4_is_master(dev)) {
@@ -3278,22 +3290,22 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 		}
 		/* here, p is the slave id */
 		do_slave_init(ibdev, p, 0);
-		return;
+		return NOTIFY_DONE;
 
 	default:
-		return;
+		return NOTIFY_DONE;
 	}
 
-	ibev.device	      = ibdev_ptr;
+	ibev.device	      = &ibdev->ib_dev;
 	ibev.element.port_num = mlx4_is_bonded(ibdev->dev) ? 1 : (u8)p;
 
 	ib_dispatch_event(&ibev);
+	return NOTIFY_DONE;
 }
 
 static struct mlx4_interface mlx4_ib_interface = {
 	.add		= mlx4_ib_add,
 	.remove		= mlx4_ib_remove,
-	.event		= mlx4_ib_event,
 	.protocol	= MLX4_PROT_IB_IPV6,
 	.flags		= MLX4_INTFF_BONDING
 };

drivers/infiniband/hw/mlx4/mlx4_ib.h

@@ -38,6 +38,7 @@
 #include <linux/list.h>
 #include <linux/mutex.h>
 #include <linux/idr.h>
+#include <linux/notifier.h>
 
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_umem.h>
@@ -644,6 +645,7 @@ struct mlx4_ib_dev {
 	spinlock_t		reset_flow_resource_lock;
 	struct list_head		qp_list;
 	struct mlx4_ib_diag_counters diag_counters[MLX4_DIAG_COUNTERS_TYPES];
+	struct notifier_block	mlx_nb;
 };
 
 struct ib_event_work {

drivers/net/ethernet/mellanox/mlx4/en_main.c

@@ -183,10 +183,12 @@ static void mlx4_en_get_profile(struct mlx4_en_dev *mdev)
 	}
 }
 
-static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr,
-			  enum mlx4_dev_event event, void *param)
+static int mlx4_en_event(struct notifier_block *this, unsigned long event,
+			 void *param)
 {
-	struct mlx4_en_dev *mdev = (struct mlx4_en_dev *) endev_ptr;
+	struct mlx4_en_dev *mdev =
+		container_of(this, struct mlx4_en_dev, mlx_nb);
+	struct mlx4_dev *dev = mdev->dev;
 	struct mlx4_en_priv *priv;
 	int port;
 
@@ -205,7 +207,7 @@ static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr,
 	case MLX4_DEV_EVENT_PORT_UP:
 	case MLX4_DEV_EVENT_PORT_DOWN:
 		if (!mdev->pndev[port])
-			return;
+			return NOTIFY_DONE;
 		priv = netdev_priv(mdev->pndev[port]);
 		/* To prevent races, we poll the link state in a separate
 		  task rather than changing it here */
@@ -224,10 +226,12 @@ static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr,
 	default:
 		if (port < 1 || port > dev->caps.num_ports ||
 		    !mdev->pndev[port])
-			return;
-		mlx4_warn(mdev, "Unhandled event %d for port %d\n", event,
+			return NOTIFY_DONE;
+		mlx4_warn(mdev, "Unhandled event %d for port %d\n", (int)event,
 			  port);
 	}
+
+	return NOTIFY_DONE;
 }
 
 static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr)
@@ -235,6 +239,8 @@ static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr)
 	struct mlx4_en_dev *mdev = endev_ptr;
 	int i;
 
+	mlx4_unregister_event_notifier(dev, &mdev->mlx_nb);
+
 	mutex_lock(&mdev->state_lock);
 	mdev->device_up = false;
 	mutex_unlock(&mdev->state_lock);
@@ -276,7 +282,7 @@ static void mlx4_en_activate(struct mlx4_dev *dev, void *ctx)
 static void *mlx4_en_add(struct mlx4_dev *dev)
 {
 	struct mlx4_en_dev *mdev;
-	int i;
+	int err, i;
 
 	printk_once(KERN_INFO "%s", mlx4_en_version);
 
@@ -339,6 +345,11 @@ static void *mlx4_en_add(struct mlx4_dev *dev)
 	mutex_init(&mdev->state_lock);
 	mdev->device_up = true;
 
+	/* register mlx4 core notifier */
+	mdev->mlx_nb.notifier_call = mlx4_en_event;
+	err = mlx4_register_event_notifier(dev, &mdev->mlx_nb);
+	WARN(err, "failed to register mlx4 event notifier (%d)", err);
+
 	return mdev;
 
 err_mr:
@@ -359,7 +370,6 @@ static void *mlx4_en_add(struct mlx4_dev *dev)
 static struct mlx4_interface mlx4_en_interface = {
 	.add		= mlx4_en_add,
 	.remove		= mlx4_en_remove,
-	.event		= mlx4_en_event,
 	.protocol	= MLX4_PROT_ETH,
 	.activate	= mlx4_en_activate,
 };

drivers/net/ethernet/mellanox/mlx4/intf.c

@@ -183,17 +183,27 @@ void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type,
 			 void *param)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
-	struct mlx4_device_context *dev_ctx;
-	unsigned long flags;
 
-	spin_lock_irqsave(&priv->ctx_lock, flags);
+	atomic_notifier_call_chain(&priv->event_nh, type, param);
+}
 
-	list_for_each_entry(dev_ctx, &priv->ctx_list, list)
-		if (dev_ctx->intf->event)
-			dev_ctx->intf->event(dev, dev_ctx->context, type, param);
+int mlx4_register_event_notifier(struct mlx4_dev *dev,
+				 struct notifier_block *nb)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
 
-	spin_unlock_irqrestore(&priv->ctx_lock, flags);
+	return atomic_notifier_chain_register(&priv->event_nh, nb);
+}
+EXPORT_SYMBOL(mlx4_register_event_notifier);
+
+int mlx4_unregister_event_notifier(struct mlx4_dev *dev,
+				   struct notifier_block *nb)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	return atomic_notifier_chain_unregister(&priv->event_nh, nb);
 }
+EXPORT_SYMBOL(mlx4_unregister_event_notifier);
 
 int mlx4_register_device(struct mlx4_dev *dev)
 {

drivers/net/ethernet/mellanox/mlx4/main.c

@@ -3378,6 +3378,8 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
 	INIT_LIST_HEAD(&priv->ctx_list);
 	spin_lock_init(&priv->ctx_lock);
 
+	ATOMIC_INIT_NOTIFIER_HEAD(&priv->event_nh);
+
 	mutex_init(&priv->port_mutex);
 	mutex_init(&priv->bond_mutex);
 

drivers/net/ethernet/mellanox/mlx4/mlx4.h

@@ -47,6 +47,7 @@
 #include <linux/spinlock.h>
 #include <net/devlink.h>
 #include <linux/rwsem.h>
+#include <linux/notifier.h>
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/driver.h>
@@ -878,6 +879,7 @@ struct mlx4_priv {
 	struct list_head	dev_list;
 	struct list_head	ctx_list;
 	spinlock_t		ctx_lock;
+	struct atomic_notifier_head event_nh;
 
 	int			pci_dev_data;
 	int                     removed;

drivers/net/ethernet/mellanox/mlx4/mlx4_en.h

@@ -49,6 +49,7 @@
 #include <linux/ptp_clock_kernel.h>
 #include <linux/irq.h>
 #include <net/xdp.h>
+#include <linux/notifier.h>
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/qp.h>
@@ -433,6 +434,7 @@ struct mlx4_en_dev {
 	struct ptp_clock	*ptp_clock;
 	struct ptp_clock_info	ptp_clock_info;
 	struct notifier_block	netdev_nb;
+	struct notifier_block	mlx_nb;
 };
 
 

include/linux/mlx4/driver.h

@@ -34,6 +34,7 @@
 #define MLX4_DRIVER_H
 
 #include <net/devlink.h>
+#include <linux/notifier.h>
 #include <linux/mlx4/device.h>
 
 struct mlx4_dev;
@@ -57,8 +58,6 @@ enum {
 struct mlx4_interface {
 	void *			(*add)	 (struct mlx4_dev *dev);
 	void			(*remove)(struct mlx4_dev *dev, void *context);
-	void			(*event) (struct mlx4_dev *dev, void *context,
-					  enum mlx4_dev_event event, void *param);
 	void			(*activate)(struct mlx4_dev *dev, void *context);
 	struct list_head	list;
 	enum mlx4_protocol	protocol;
@@ -87,6 +86,11 @@ struct mlx4_port_map {
 
 int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p);
 
+int mlx4_register_event_notifier(struct mlx4_dev *dev,
+				 struct notifier_block *nb);
+int mlx4_unregister_event_notifier(struct mlx4_dev *dev,
+				   struct notifier_block *nb);
+
 struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port);
 
 #endif /* MLX4_DRIVER_H */