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

Pull rdma fixes from Jason Gunthorpe:
 "The good news is people are testing rc1 in the RDMA world - the bad
  news is testing of the for-next area is not as good as I had hoped, as
  we really should have caught at least the rdma_connect_locked() issue
  before now.

  Notable merge window regressions that didn't get caught/fixed in time
  for rc1:

   - Fix in kernel users of rxe, they were broken by the rapid fix to
     undo the uABI breakage in rxe from another patch

   - EFA userspace needs to read the GID table but was broken with the
     new GID table logic

   - Fix user triggerable deadlock in mlx5 using devlink reload

   - Fix deadlock in several ULPs using rdma_connect from the CM handler
     callbacks

   - Memory leak in qedr"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  RDMA/qedr: Fix memory leak in iWARP CM
  RDMA: Add rdma_connect_locked()
  RDMA/uverbs: Fix false error in query gid IOCTL
  RDMA/mlx5: Fix devlink deadlock on net namespace deletion
  RDMA/rxe: Fix small problem in network_type patch

drivers/infiniband/core/cma.c

@@ -405,10 +405,10 @@ static int cma_comp_exch(struct rdma_id_private *id_priv,
 	/*
 	 * The FSM uses a funny double locking where state is protected by both
 	 * the handler_mutex and the spinlock. State is not allowed to change
-	 * away from a handler_mutex protected value without also holding
+	 * to/from a handler_mutex protected value without also holding
 	 * handler_mutex.
 	 */
-	if (comp == RDMA_CM_CONNECT)
+	if (comp == RDMA_CM_CONNECT || exch == RDMA_CM_CONNECT)
 		lockdep_assert_held(&id_priv->handler_mutex);
 
 	spin_lock_irqsave(&id_priv->lock, flags);
@@ -4038,17 +4038,23 @@ static int cma_connect_iw(struct rdma_id_private *id_priv,
 	return ret;
 }
 
-int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
+/**
+ * rdma_connect_locked - Initiate an active connection request.
+ * @id: Connection identifier to connect.
+ * @conn_param: Connection information used for connected QPs.
+ *
+ * Same as rdma_connect() but can only be called from the
+ * RDMA_CM_EVENT_ROUTE_RESOLVED handler callback.
+ */
+int rdma_connect_locked(struct rdma_cm_id *id,
+			struct rdma_conn_param *conn_param)
 {
 	struct rdma_id_private *id_priv =
 		container_of(id, struct rdma_id_private, id);
 	int ret;
 
-	mutex_lock(&id_priv->handler_mutex);
-	if (!cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_CONNECT)) {
-		ret = -EINVAL;
-		goto err_unlock;
-	}
+	if (!cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_CONNECT))
+		return -EINVAL;
 
 	if (!id->qp) {
 		id_priv->qp_num = conn_param->qp_num;
@@ -4066,11 +4072,33 @@ int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
 		ret = -ENOSYS;
 	if (ret)
 		goto err_state;
-	mutex_unlock(&id_priv->handler_mutex);
 	return 0;
 err_state:
 	cma_comp_exch(id_priv, RDMA_CM_CONNECT, RDMA_CM_ROUTE_RESOLVED);
-err_unlock:
+	return ret;
+}
+EXPORT_SYMBOL(rdma_connect_locked);
+
+/**
+ * rdma_connect - Initiate an active connection request.
+ * @id: Connection identifier to connect.
+ * @conn_param: Connection information used for connected QPs.
+ *
+ * Users must have resolved a route for the rdma_cm_id to connect with by having
+ * called rdma_resolve_route before calling this routine.
+ *
+ * This call will either connect to a remote QP or obtain remote QP information
+ * for unconnected rdma_cm_id's.  The actual operation is based on the
+ * rdma_cm_id's port space.
+ */
+int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
+{
+	struct rdma_id_private *id_priv =
+		container_of(id, struct rdma_id_private, id);
+	int ret;
+
+	mutex_lock(&id_priv->handler_mutex);
+	ret = rdma_connect_locked(id, conn_param);
 	mutex_unlock(&id_priv->handler_mutex);
 	return ret;
 }

drivers/infiniband/core/uverbs_std_types_device.c

@@ -401,9 +401,6 @@ static int UVERBS_HANDLER(UVERBS_METHOD_QUERY_GID_ENTRY)(
 	if (!rdma_is_port_valid(ib_dev, port_num))
 		return -EINVAL;
 
-	if (!rdma_ib_or_roce(ib_dev, port_num))
-		return -EOPNOTSUPP;
-
 	gid_attr = rdma_get_gid_attr(ib_dev, port_num, gid_index);
 	if (IS_ERR(gid_attr))
 		return PTR_ERR(gid_attr);

drivers/infiniband/hw/mlx5/main.c

@@ -3305,7 +3305,8 @@ static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
 	int err;
 
 	dev->port[port_num].roce.nb.notifier_call = mlx5_netdev_event;
-	err = register_netdevice_notifier(&dev->port[port_num].roce.nb);
+	err = register_netdevice_notifier_net(mlx5_core_net(dev->mdev),
+					      &dev->port[port_num].roce.nb);
 	if (err) {
 		dev->port[port_num].roce.nb.notifier_call = NULL;
 		return err;
@@ -3317,7 +3318,8 @@ static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
 static void mlx5_remove_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
 {
 	if (dev->port[port_num].roce.nb.notifier_call) {
-		unregister_netdevice_notifier(&dev->port[port_num].roce.nb);
+		unregister_netdevice_notifier_net(mlx5_core_net(dev->mdev),
+						  &dev->port[port_num].roce.nb);
 		dev->port[port_num].roce.nb.notifier_call = NULL;
 	}
 }

drivers/infiniband/hw/qedr/qedr_iw_cm.c

@@ -727,6 +727,7 @@ int qedr_iw_destroy_listen(struct iw_cm_id *cm_id)
 						    listener->qed_handle);
 
 	cm_id->rem_ref(cm_id);
+	kfree(listener);
 	return rc;
 }
 

drivers/infiniband/sw/rxe/rxe_av.c

@@ -16,15 +16,24 @@ void rxe_init_av(struct rdma_ah_attr *attr, struct rxe_av *av)
 
 int rxe_av_chk_attr(struct rxe_dev *rxe, struct rdma_ah_attr *attr)
 {
+	const struct ib_global_route *grh = rdma_ah_read_grh(attr);
 	struct rxe_port *port;
+	int type;
 
 	port = &rxe->port;
 
 	if (rdma_ah_get_ah_flags(attr) & IB_AH_GRH) {
-		u8 sgid_index = rdma_ah_read_grh(attr)->sgid_index;
+		if (grh->sgid_index > port->attr.gid_tbl_len) {
+			pr_warn("invalid sgid index = %d\n",
+					grh->sgid_index);
+			return -EINVAL;
+		}
 
-		if (sgid_index > port->attr.gid_tbl_len) {
-			pr_warn("invalid sgid index = %d\n", sgid_index);
+		type = rdma_gid_attr_network_type(grh->sgid_attr);
+		if (type < RDMA_NETWORK_IPV4 ||
+		    type > RDMA_NETWORK_IPV6) {
+			pr_warn("invalid network type for rdma_rxe = %d\n",
+					type);
 			return -EINVAL;
 		}
 	}
@@ -65,11 +74,29 @@ void rxe_av_to_attr(struct rxe_av *av, struct rdma_ah_attr *attr)
 void rxe_av_fill_ip_info(struct rxe_av *av, struct rdma_ah_attr *attr)
 {
 	const struct ib_gid_attr *sgid_attr = attr->grh.sgid_attr;
+	int ibtype;
+	int type;
 
 	rdma_gid2ip((struct sockaddr *)&av->sgid_addr, &sgid_attr->gid);
 	rdma_gid2ip((struct sockaddr *)&av->dgid_addr,
 		    &rdma_ah_read_grh(attr)->dgid);
-	av->network_type = rdma_gid_attr_network_type(sgid_attr);
+
+	ibtype = rdma_gid_attr_network_type(sgid_attr);
+
+	switch (ibtype) {
+	case RDMA_NETWORK_IPV4:
+		type = RXE_NETWORK_TYPE_IPV4;
+		break;
+	case RDMA_NETWORK_IPV6:
+		type = RXE_NETWORK_TYPE_IPV4;
+		break;
+	default:
+		/* not reached - checked in rxe_av_chk_attr */
+		type = 0;
+		break;
+	}
+
+	av->network_type = type;
 }
 
 struct rxe_av *rxe_get_av(struct rxe_pkt_info *pkt)

drivers/infiniband/sw/rxe/rxe_net.c

@@ -442,7 +442,7 @@ struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av,
 	if (IS_ERR(attr))
 		return NULL;
 
-	if (av->network_type == RXE_NETWORK_TYPE_IPV6)
+	if (av->network_type == RXE_NETWORK_TYPE_IPV4)
 		hdr_len = ETH_HLEN + sizeof(struct udphdr) +
 			sizeof(struct iphdr);
 	else

drivers/infiniband/ulp/iser/iser_verbs.c

@@ -620,7 +620,7 @@ static void iser_route_handler(struct rdma_cm_id *cma_id)
 	conn_param.private_data	= (void *)&req_hdr;
 	conn_param.private_data_len = sizeof(struct iser_cm_hdr);
 
-	ret = rdma_connect(cma_id, &conn_param);
+	ret = rdma_connect_locked(cma_id, &conn_param);
 	if (ret) {
 		iser_err("failure connecting: %d\n", ret);
 		goto failure;

drivers/infiniband/ulp/rtrs/rtrs-clt.c

@@ -1674,9 +1674,9 @@ static int rtrs_rdma_route_resolved(struct rtrs_clt_con *con)
 	uuid_copy(&msg.sess_uuid, &sess->s.uuid);
 	uuid_copy(&msg.paths_uuid, &clt->paths_uuid);
 
-	err = rdma_connect(con->c.cm_id, &param);
+	err = rdma_connect_locked(con->c.cm_id, &param);
 	if (err)
-		rtrs_err(clt, "rdma_connect(): %d\n", err);
+		rtrs_err(clt, "rdma_connect_locked(): %d\n", err);
 
 	return err;
 }

drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h

@@ -90,9 +90,4 @@ int mlx5_create_encryption_key(struct mlx5_core_dev *mdev,
 			       u32 key_type, u32 *p_key_id);
 void mlx5_destroy_encryption_key(struct mlx5_core_dev *mdev, u32 key_id);
 
-static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev)
-{
-	return devlink_net(priv_to_devlink(dev));
-}
-
 #endif

drivers/nvme/host/rdma.c

@@ -1890,10 +1890,10 @@ static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue)
 		priv.hsqsize = cpu_to_le16(queue->ctrl->ctrl.sqsize);
 	}
 
-	ret = rdma_connect(queue->cm_id, &param);
+	ret = rdma_connect_locked(queue->cm_id, &param);
 	if (ret) {
 		dev_err(ctrl->ctrl.device,
-			"rdma_connect failed (%d).\n", ret);
+			"rdma_connect_locked failed (%d).\n", ret);
 		goto out_destroy_queue_ib;
 	}
 

include/linux/mlx5/driver.h

@@ -1213,4 +1213,22 @@ static inline bool mlx5_is_roce_enabled(struct mlx5_core_dev *dev)
 	return val.vbool;
 }
 
+/**
+ * mlx5_core_net - Provide net namespace of the mlx5_core_dev
+ * @dev: mlx5 core device
+ *
+ * mlx5_core_net() returns the net namespace of mlx5 core device.
+ * This can be called only in below described limited context.
+ * (a) When a devlink instance for mlx5_core is registered and
+ *     when devlink reload operation is disabled.
+ *     or
+ * (b) during devlink reload reload_down() and reload_up callbacks
+ *     where it is ensured that devlink instance's net namespace is
+ *     stable.
+ */
+static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev)
+{
+	return devlink_net(priv_to_devlink(dev));
+}
+
 #endif /* MLX5_DRIVER_H */

include/rdma/rdma_cm.h

@@ -227,19 +227,9 @@ void rdma_destroy_qp(struct rdma_cm_id *id);
 int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr,
 		       int *qp_attr_mask);
 
-/**
- * rdma_connect - Initiate an active connection request.
- * @id: Connection identifier to connect.
- * @conn_param: Connection information used for connected QPs.
- *
- * Users must have resolved a route for the rdma_cm_id to connect with
- * by having called rdma_resolve_route before calling this routine.
- *
- * This call will either connect to a remote QP or obtain remote QP
- * information for unconnected rdma_cm_id's.  The actual operation is
- * based on the rdma_cm_id's port space.
- */
 int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param);
+int rdma_connect_locked(struct rdma_cm_id *id,
+			struct rdma_conn_param *conn_param);
 
 int rdma_connect_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,
 		     struct rdma_ucm_ece *ece);

net/rds/ib_cm.c

@@ -956,9 +956,10 @@ int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id, bool isv6)
 	rds_ib_cm_fill_conn_param(conn, &conn_param, &dp,
 				  conn->c_proposed_version,
 				  UINT_MAX, UINT_MAX, isv6);
-	ret = rdma_connect(cm_id, &conn_param);
+	ret = rdma_connect_locked(cm_id, &conn_param);
 	if (ret)
-		rds_ib_conn_error(conn, "rdma_connect failed (%d)\n", ret);
+		rds_ib_conn_error(conn, "rdma_connect_locked failed (%d)\n",
+				  ret);
 
 out:
 	/* Beware - returning non-zero tells the rdma_cm to destroy