Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull rdma updates from Jason Gunthorpe:
 "A more active cycle than most of the recent past, with a few large,
  long discussed works this time.

  The RNBD block driver has been posted for nearly two years now, and
  flowing through RDMA due to it also introducing a new ULP.

  The removal of FMR has been a recurring discussion theme for a long
  time.

  And the usual smattering of features and bug fixes.

  Summary:

   - Various small driver bugs fixes in rxe, mlx5, hfi1, and efa

   - Continuing driver cleanups in bnxt_re, hns

   - Big cleanup of mlx5 QP creation flows

   - More consistent use of src port and flow label when LAG is used and
     a mlx5 implementation

   - Additional set of cleanups for IB CM

   - 'RNBD' network block driver and target. This is a network block
     RDMA device specific to ionos's cloud environment. It brings strong
     multipath and resiliency capabilities.

   - Accelerated IPoIB for HFI1

   - QP/WQ/SRQ ioctl migration for uverbs, and support for multiple
     async fds

   - Support for exchanging the new IBTA defiend ECE data during RDMA CM
     exchanges

   - Removal of the very old and insecure FMR interface from all ULPs
     and drivers. FRWR should be preferred for at least a decade now"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (247 commits)
  RDMA/cm: Spurious WARNING triggered in cm_destroy_id()
  RDMA/mlx5: Return ECE DC support
  RDMA/mlx5: Don't rely on FW to set zeros in ECE response
  RDMA/mlx5: Return an error if copy_to_user fails
  IB/hfi1: Use free_netdev() in hfi1_netdev_free()
  RDMA/hns: Uninitialized variable in modify_qp_init_to_rtr()
  RDMA/core: Move and rename trace_cm_id_create()
  IB/hfi1: Fix hfi1_netdev_rx_init() error handling
  RDMA: Remove 'max_map_per_fmr'
  RDMA: Remove 'max_fmr'
  RDMA/core: Remove FMR device ops
  RDMA/rdmavt: Remove FMR memory registration
  RDMA/mthca: Remove FMR support for memory registration
  RDMA/mlx4: Remove FMR support for memory registration
  RDMA/i40iw: Remove FMR leftovers
  RDMA/bnxt_re: Remove FMR leftovers
  RDMA/mlx5: Remove FMR leftovers
  RDMA/core: Remove FMR pool API
  RDMA/rds: Remove FMR support for memory registration
  RDMA/srp: Remove support for FMR memory registration
  ...

4 files changed, 35 insertions, 31 deletions

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index ceec24d45185..3cfb682b91b0 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -86,7 +86,7 @@ struct workqueue_struct *ipoib_workqueue;
 
 struct ib_sa_client ipoib_sa_client;
 
-static void ipoib_add_one(struct ib_device *device);
+static int ipoib_add_one(struct ib_device *device);
 static void ipoib_remove_one(struct ib_device *device, void *client_data);
 static void ipoib_neigh_reclaim(struct rcu_head *rp);
 static struct net_device *ipoib_get_net_dev_by_params(
@@ -479,9 +479,6 @@ static struct net_device *ipoib_get_net_dev_by_params(
 	if (ret)
 		return NULL;
 
-	if (!dev_list)
-		return NULL;
-
 	/* See if we can find a unique device matching the L2 parameters */
 	matches = __ipoib_get_net_dev_by_params(dev_list, port, pkey_index,
 						gid, NULL, &net_dev);
@@ -529,6 +526,7 @@ int ipoib_set_mode(struct net_device *dev, const char *buf)
 			   "will cause multicast packet drops\n");
 		netdev_update_features(dev);
 		dev_set_mtu(dev, ipoib_cm_max_mtu(dev));
+		netif_set_real_num_tx_queues(dev, 1);
 		rtnl_unlock();
 		priv->tx_wr.wr.send_flags &= ~IB_SEND_IP_CSUM;
 
@@ -540,6 +538,7 @@ int ipoib_set_mode(struct net_device *dev, const char *buf)
 		clear_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
 		netdev_update_features(dev);
 		dev_set_mtu(dev, min(priv->mcast_mtu, dev->mtu));
+		netif_set_real_num_tx_queues(dev, dev->num_tx_queues);
 		rtnl_unlock();
 		ipoib_flush_paths(dev);
 		return (!rtnl_trylock()) ? -EBUSY : 0;
@@ -1860,7 +1859,7 @@ static int ipoib_parent_init(struct net_device *ndev)
 			priv->port);
 		return result;
 	}
-	priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu);
+	priv->max_ib_mtu = rdma_mtu_from_attr(priv->ca, priv->port, &attr);
 
 	result = ib_query_pkey(priv->ca, priv->port, 0, &priv->pkey);
 	if (result) {
@@ -1901,6 +1900,7 @@ static int ipoib_ndo_init(struct net_device *ndev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(ndev);
 	int rc;
+	struct rdma_netdev *rn = netdev_priv(ndev);
 
 	if (priv->parent) {
 		ipoib_child_init(ndev);
@@ -1913,6 +1913,7 @@ static int ipoib_ndo_init(struct net_device *ndev)
 	/* MTU will be reset when mcast join happens */
 	ndev->mtu = IPOIB_UD_MTU(priv->max_ib_mtu);
 	priv->mcast_mtu = priv->admin_mtu = ndev->mtu;
+	rn->mtu = priv->mcast_mtu;
 	ndev->max_mtu = IPOIB_CM_MTU;
 
 	ndev->neigh_priv_len = sizeof(struct ipoib_neigh);
@@ -2074,9 +2075,17 @@ static const struct net_device_ops ipoib_netdev_ops_vf = {
 	.ndo_do_ioctl		 = ipoib_ioctl,
 };
 
+static const struct net_device_ops ipoib_netdev_default_pf = {
+	.ndo_init		 = ipoib_dev_init_default,
+	.ndo_uninit		 = ipoib_dev_uninit_default,
+	.ndo_open		 = ipoib_ib_dev_open_default,
+	.ndo_stop		 = ipoib_ib_dev_stop_default,
+};
+
 void ipoib_setup_common(struct net_device *dev)
 {
 	dev->header_ops		 = &ipoib_header_ops;
+	dev->netdev_ops          = &ipoib_netdev_default_pf;
 
 	ipoib_set_ethtool_ops(dev);
 
@@ -2126,13 +2135,6 @@ static void ipoib_build_priv(struct net_device *dev)
 	INIT_DELAYED_WORK(&priv->neigh_reap_task, ipoib_reap_neigh);
 }
 
-static const struct net_device_ops ipoib_netdev_default_pf = {
-	.ndo_init		 = ipoib_dev_init_default,
-	.ndo_uninit		 = ipoib_dev_uninit_default,
-	.ndo_open		 = ipoib_ib_dev_open_default,
-	.ndo_stop		 = ipoib_ib_dev_stop_default,
-};
-
 static struct net_device *ipoib_alloc_netdev(struct ib_device *hca, u8 port,
 					     const char *name)
 {
@@ -2170,7 +2172,6 @@ int ipoib_intf_init(struct ib_device *hca, u8 port, const char *name,
 		if (rc != -EOPNOTSUPP)
 			goto out;
 
-		dev->netdev_ops = &ipoib_netdev_default_pf;
 		rn->send = ipoib_send;
 		rn->attach_mcast = ipoib_mcast_attach;
 		rn->detach_mcast = ipoib_mcast_detach;
@@ -2516,7 +2517,7 @@ sysfs_failed:
 	return ERR_PTR(-ENOMEM);
 }
 
-static void ipoib_add_one(struct ib_device *device)
+static int ipoib_add_one(struct ib_device *device)
 {
 	struct list_head *dev_list;
 	struct net_device *dev;
@@ -2526,7 +2527,7 @@ static void ipoib_add_one(struct ib_device *device)
 
 	dev_list = kmalloc(sizeof(*dev_list), GFP_KERNEL);
 	if (!dev_list)
-		return;
+		return -ENOMEM;
 
 	INIT_LIST_HEAD(dev_list);
 
@@ -2543,10 +2544,11 @@ static void ipoib_add_one(struct ib_device *device)
 
 	if (!count) {
 		kfree(dev_list);
-		return;
+		return -EOPNOTSUPP;
 	}
 
 	ib_set_client_data(device, &ipoib_client, dev_list);
+	return 0;
 }
 
 static void ipoib_remove_one(struct ib_device *device, void *client_data)
@@ -2554,9 +2556,6 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data)
 	struct ipoib_dev_priv *priv, *tmp, *cpriv, *tcpriv;
 	struct list_head *dev_list = client_data;
 
-	if (!dev_list)
-		return;
-
 	list_for_each_entry_safe(priv, tmp, dev_list, list) {
 		LIST_HEAD(head);
 		ipoib_parent_unregister_pre(priv->dev);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index b9e9562f5034..9bfa514473d5 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -135,12 +135,11 @@ static void ipoib_mcast_free(struct ipoib_mcast *mcast)
 	kfree(mcast);
 }
 
-static struct ipoib_mcast *ipoib_mcast_alloc(struct net_device *dev,
-					     int can_sleep)
+static struct ipoib_mcast *ipoib_mcast_alloc(struct net_device *dev)
 {
 	struct ipoib_mcast *mcast;
 
-	mcast = kzalloc(sizeof(*mcast), can_sleep ? GFP_KERNEL : GFP_ATOMIC);
+	mcast = kzalloc(sizeof(*mcast), GFP_ATOMIC);
 	if (!mcast)
 		return NULL;
 
@@ -218,6 +217,7 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast,
 	struct rdma_ah_attr av;
 	int ret;
 	int set_qkey = 0;
+	int mtu;
 
 	mcast->mcmember = *mcmember;
 
@@ -240,13 +240,12 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast,
 		priv->broadcast->mcmember.flow_label = mcmember->flow_label;
 		priv->broadcast->mcmember.hop_limit = mcmember->hop_limit;
 		/* assume if the admin and the mcast are the same both can be changed */
+		mtu = rdma_mtu_enum_to_int(priv->ca,  priv->port,
+					   priv->broadcast->mcmember.mtu);
 		if (priv->mcast_mtu == priv->admin_mtu)
-			priv->admin_mtu =
-			priv->mcast_mtu =
-			IPOIB_UD_MTU(ib_mtu_enum_to_int(priv->broadcast->mcmember.mtu));
-		else
-			priv->mcast_mtu =
-			IPOIB_UD_MTU(ib_mtu_enum_to_int(priv->broadcast->mcmember.mtu));
+			priv->admin_mtu = IPOIB_UD_MTU(mtu);
+		priv->mcast_mtu = IPOIB_UD_MTU(mtu);
+		rn->mtu = priv->mcast_mtu;
 
 		priv->qkey = be32_to_cpu(priv->broadcast->mcmember.qkey);
 		spin_unlock_irq(&priv->lock);
@@ -599,7 +598,7 @@ void ipoib_mcast_join_task(struct work_struct *work)
 	if (!priv->broadcast) {
 		struct ipoib_mcast *broadcast;
 
-		broadcast = ipoib_mcast_alloc(dev, 0);
+		broadcast = ipoib_mcast_alloc(dev);
 		if (!broadcast) {
 			ipoib_warn(priv, "failed to allocate broadcast group\n");
 			/*
@@ -782,7 +781,7 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb)
 			ipoib_dbg_mcast(priv, "setting up send only multicast group for %pI6\n",
 					mgid);
 
-			mcast = ipoib_mcast_alloc(dev, 0);
+			mcast = ipoib_mcast_alloc(dev);
 			if (!mcast) {
 				ipoib_warn(priv, "unable to allocate memory "
 					   "for multicast structure\n");
@@ -936,7 +935,7 @@ void ipoib_mcast_restart_task(struct work_struct *work)
 			ipoib_dbg_mcast(priv, "adding multicast entry for mgid %pI6\n",
 					mgid.raw);
 
-			nmcast = ipoib_mcast_alloc(dev, 0);
+			nmcast = ipoib_mcast_alloc(dev);
 			if (!nmcast) {
 				ipoib_warn(priv, "unable to allocate memory for multicast structure\n");
 				continue;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index b69304d28f06..587252fd6f57 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -206,6 +206,9 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 	if (priv->hca_caps & IB_DEVICE_MANAGED_FLOW_STEERING)
 		init_attr.create_flags |= IB_QP_CREATE_NETIF_QP;
 
+	if (priv->hca_caps & IB_DEVICE_RDMA_NETDEV_OPA)
+		init_attr.create_flags |= IB_QP_CREATE_NETDEV_USE;
+
 	priv->qp = ib_create_qp(priv->pd, &init_attr);
 	if (IS_ERR(priv->qp)) {
 		pr_warn("%s: failed to create QP\n", ca->name);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index 8ac8e18fbe0c..30865605e098 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -97,6 +97,7 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
 {
 	struct net_device *ndev = priv->dev;
 	int result;
+	struct rdma_netdev *rn = netdev_priv(ndev);
 
 	ASSERT_RTNL();
 
@@ -117,6 +118,8 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
 		goto out_early;
 	}
 
+	rn->mtu = priv->mcast_mtu;
+
 	priv->parent = ppriv->dev;
 	priv->pkey = pkey;
 	priv->child_type = type;