Merge mlx5-next into rdma.git for-next

Synchronize the shared mlx5 branch with net:
 - From Jiri: fixe a deadlock in mlx5_ib's netdev notifier unregister.
 - From Mark and Patrisious: add IPsec RoCEv2 support.
 - From Or: Rely on firmware to get special mkeys

* branch mlx5-next:
  RDMA/mlx5: Use query_special_contexts for mkeys
  net/mlx5e: Use query_special_contexts for mkeys
  net/mlx5: Change define name for 0x100 lkey value
  net/mlx5: Expose bits for querying special mkeys
  net/mlx5: Configure IPsec steering for egress RoCEv2 traffic
  net/mlx5: Configure IPsec steering for ingress RoCEv2 traffic
  net/mlx5: Add IPSec priorities in RDMA namespaces
  net/mlx5: Implement new destination type TABLE_TYPE
  net/mlx5: Introduce new destination type TABLE_TYPE
  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

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

1 files changed, 59 insertions, 29 deletions

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 2ccf6a504087..8b664a57123e 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1756,13 +1756,9 @@ static int set_ucontext_resp(struct ib_ucontext *uctx,
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 	struct mlx5_ib_ucontext *context = to_mucontext(uctx);
 	struct mlx5_bfreg_info *bfregi = &context->bfregi;
-	int err;
 
 	if (MLX5_CAP_GEN(dev->mdev, dump_fill_mkey)) {
-		err = mlx5_cmd_dump_fill_mkey(dev->mdev,
-					      &resp->dump_fill_mkey);
-		if (err)
-			return err;
+		resp->dump_fill_mkey = dev->mkeys.dump_fill_mkey;
 		resp->comp_mask |=
 			MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_DUMP_FILL_MKEY;
 	}
@@ -3012,26 +3008,63 @@ 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 void mlx5_remove_netdev_notifier(struct mlx5_ib_dev *dev, u32 port_num)
+static int mlx5e_mdev_notifier_event(struct notifier_block *nb,
+				     unsigned long event, void *data)
 {
-	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 = 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_mdev_netdev_track(struct mlx5_ib_dev *dev, u32 port_num)
+{
+	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 +3171,7 @@ 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 +3229,7 @@ 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);
@@ -3634,6 +3662,10 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 		dev->port[i].roce.last_port_state = IB_PORT_DOWN;
 	}
 
+	err = mlx5r_cmd_query_special_mkeys(dev);
+	if (err)
+		return err;
+
 	err = mlx5_ib_init_multiport_master(dev);
 	if (err)
 		return err;
@@ -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);
 	}
 }