Merge rdma branch 'for-rc' into 'for-next'

These did not seem worth sending as a dedicated rc PR during the last week
of the cycle.

* ko-rdma/for-rc:
  RDMA/ipoib: Drain RCU callbacks during module teardown
  RDMA/mlx5: Drain RCU callbacks during module teardown
  RDMA/core: Wait for RCU callbacks before unloading ib_core
  RDMA/irdma: Prevent overflows in memory contiguity checks
  RDMA/siw: publish QP after initialization
  RDMA/hns: Fix potential integer overflow in mhop hem cleanup
  RDMA/core: Fix memory leak in __ib_create_cq() on invalid cqe
  RDMA/mana_ib: initialize err for empty send WR lists
  RDMA/erdma: initialize ret for empty receive WR lists
  RDMA/irdma: Prevent user-triggered null deref on QP create
  RDMA/irdma: Prevent rereg_mr for non-mem regions
  RDMA/cma: Fix hardware address comparison length in netevent callback
  RDMa/mlx5: Avoid frame overflow warning
  IB/mad: Drop unmatched RMPP responses before reassembly

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

drivers/infiniband/core/cma.c

@@ -5272,7 +5272,7 @@ static int cma_netevent_callback(struct notifier_block *self,
 
 	list_for_each_entry(current_id, &ips_node->id_list, id_list_entry) {
 		if (!memcmp(current_id->id.route.addr.dev_addr.dst_dev_addr,
-			   neigh->ha, ETH_ALEN))
+			   neigh->ha, neigh->dev->addr_len))
 			continue;
 		cma_id_get(current_id);
 		if (!queue_work(cma_wq, &current_id->id.net_work))

drivers/infiniband/core/device.c

@@ -3332,6 +3332,7 @@ static void __exit ib_core_cleanup(void)
 	/* Make sure that any pending umem accounting work is done. */
 	destroy_workqueue(ib_wq);
 	destroy_workqueue(ib_unreg_wq);
+	rcu_barrier();
 	WARN_ON(!xa_empty(&clients));
 	WARN_ON(!xa_empty(&devices));
 }

drivers/infiniband/core/mad.c

@@ -2031,6 +2031,24 @@ void ib_mark_mad_done(struct ib_mad_send_wr_private *mad_send_wr)
 		change_mad_state(mad_send_wr, IB_MAD_STATE_EARLY_RESP);
 }
 
+static bool is_kernel_rmpp_data_response(struct ib_mad_agent_private *agent,
+					 struct ib_mad_recv_wc *mad_recv_wc)
+{
+	const struct ib_mad_hdr *mad_hdr = &mad_recv_wc->recv_buf.mad->mad_hdr;
+	struct ib_rmpp_mad *rmpp_mad;
+
+	if (!ib_mad_kernel_rmpp_agent(&agent->agent) ||
+	    !ib_response_mad(mad_hdr) ||
+	    !ib_is_mad_class_rmpp(mad_hdr->mgmt_class))
+		return false;
+
+	rmpp_mad = (struct ib_rmpp_mad *)mad_recv_wc->recv_buf.mad;
+
+	return (ib_get_rmpp_flags(&rmpp_mad->rmpp_hdr) &
+		IB_MGMT_RMPP_FLAG_ACTIVE) &&
+	       rmpp_mad->rmpp_hdr.rmpp_type == IB_MGMT_RMPP_TYPE_DATA;
+}
+
 static void ib_mad_complete_recv(struct ib_mad_agent_private *mad_agent_priv,
 				 struct ib_mad_recv_wc *mad_recv_wc)
 {
@@ -2050,6 +2068,18 @@ static void ib_mad_complete_recv(struct ib_mad_agent_private *mad_agent_priv,
 	}
 
 	list_add(&mad_recv_wc->recv_buf.list, &mad_recv_wc->rmpp_list);
+	if (is_kernel_rmpp_data_response(mad_agent_priv, mad_recv_wc)) {
+		spin_lock_irqsave(&mad_agent_priv->lock, flags);
+		mad_send_wr = ib_find_send_mad(mad_agent_priv, mad_recv_wc);
+		spin_unlock_irqrestore(&mad_agent_priv->lock, flags);
+
+		if (!mad_send_wr) {
+			ib_free_recv_mad(mad_recv_wc);
+			deref_mad_agent(mad_agent_priv);
+			return;
+		}
+	}
+
 	if (ib_mad_kernel_rmpp_agent(&mad_agent_priv->agent)) {
 		mad_recv_wc = ib_process_rmpp_recv_wc(mad_agent_priv,
 						      mad_recv_wc);

drivers/infiniband/core/verbs.c

@@ -2214,13 +2214,13 @@ struct ib_cq *__ib_create_cq(struct ib_device *device,
 	struct ib_cq *cq;
 	int ret;
 
+	if (WARN_ON_ONCE(!cq_attr->cqe))
+		return ERR_PTR(-EINVAL);
+
 	cq = rdma_zalloc_drv_obj(device, ib_cq);
 	if (!cq)
 		return ERR_PTR(-ENOMEM);
 
-	if (WARN_ON_ONCE(!cq_attr->cqe))
-		return ERR_PTR(-EINVAL);
-
 	cq->device = device;
 	cq->comp_handler = comp_handler;
 	cq->event_handler = event_handler;

drivers/infiniband/hw/erdma/erdma_qp.c

@@ -734,7 +734,7 @@ int erdma_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *recv_wr,
 	const struct ib_recv_wr *wr = recv_wr;
 	struct erdma_qp *qp = to_eqp(ibqp);
 	unsigned long flags;
-	int ret;
+	int ret = 0;
 
 	spin_lock_irqsave(&qp->lock, flags);
 

drivers/infiniband/hw/hns/hns_roce_hem.c

@@ -836,7 +836,7 @@ static void hns_roce_cleanup_mhop_hem_table(struct hns_roce_dev *hr_dev,
 					mhop.bt_chunk_size;
 
 	for (i = 0; i < table->num_hem; ++i) {
-		obj = i * buf_chunk_size / table->obj_size;
+		obj = (u64)i * buf_chunk_size / table->obj_size;
 		if (table->hem[i])
 			hns_roce_table_mhop_put(hr_dev, table, obj, 0);
 	}

drivers/infiniband/hw/irdma/verbs.c

@@ -2902,7 +2902,7 @@ static bool irdma_check_mem_contiguous(u64 *arr, u32 npages, u32 pg_size)
 	u32 pg_idx;
 
 	for (pg_idx = 0; pg_idx < npages; pg_idx++) {
-		if ((*arr + (pg_size * pg_idx)) != arr[pg_idx])
+		if ((*arr + ((u64)pg_size * pg_idx)) != arr[pg_idx])
 			return false;
 	}
 
@@ -2935,7 +2935,7 @@ static bool irdma_check_mr_contiguous(struct irdma_pble_alloc *palloc,
 
 	for (i = 0; i < lvl2->leaf_cnt; i++, leaf++) {
 		arr = leaf->addr;
-		if ((*start_addr + (i * pg_size * PBLE_PER_PAGE)) != *arr)
+		if ((*start_addr + ((u64)i * pg_size * PBLE_PER_PAGE)) != *arr)
 			return false;
 		ret = irdma_check_mem_contiguous(arr, leaf->cnt, pg_size);
 		if (!ret)
@@ -3897,6 +3897,9 @@ static struct ib_mr *irdma_rereg_user_mr(struct ib_mr *ib_mr, int flags,
 	if (flags & ~(IB_MR_REREG_TRANS | IB_MR_REREG_PD | IB_MR_REREG_ACCESS))
 		return ERR_PTR(-EOPNOTSUPP);
 
+	if (iwmr->type != IRDMA_MEMREG_TYPE_MEM)
+	     return ERR_PTR(-EINVAL);
+
 	ret = ib_umem_check_rereg(iwmr->region, flags, new_access);
 	if (ret)
 		return ERR_PTR(ret);

drivers/infiniband/hw/mana/wr.c

@@ -144,7 +144,7 @@ static int mana_ib_post_send_ud(struct mana_ib_qp *qp, const struct ib_ud_wr *wr
 int mana_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 		      const struct ib_send_wr **bad_wr)
 {
-	int err;
+	int err = 0;
 	struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp);
 
 	for (; wr; wr = wr->next) {

drivers/infiniband/hw/mlx5/main.c

@@ -5542,6 +5542,7 @@ static int __init mlx5_ib_init(void)
 dd_err:
 	mlx5r_rep_cleanup();
 rep_err:
+	rcu_barrier();
 	mlx5_ib_qp_event_cleanup();
 qp_event_err:
 	destroy_workqueue(mlx5_ib_event_wq);
@@ -5555,6 +5556,7 @@ static void __exit mlx5_ib_cleanup(void)
 	auxiliary_driver_unregister(&mlx5r_driver);
 	auxiliary_driver_unregister(&mlx5r_mp_driver);
 	mlx5r_rep_cleanup();
+	rcu_barrier();
 
 	mlx5_ib_qp_event_cleanup();
 	destroy_workqueue(mlx5_ib_event_wq);

drivers/infiniband/hw/mlx5/wr.c

@@ -840,13 +840,15 @@ static int handle_psv(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	return err;
 }
 
-static int handle_reg_mr_integrity(struct mlx5_ib_dev *dev,
-				   struct mlx5_ib_qp *qp,
-				   const struct ib_send_wr *wr,
-				   struct mlx5_wqe_ctrl_seg **ctrl, void **seg,
-				   int *size, void **cur_edge,
-				   unsigned int *idx, int nreq, u8 fence,
-				   u8 next_fence)
+static noinline_for_stack int handle_reg_mr_integrity(struct mlx5_ib_dev *dev,
+						      struct mlx5_ib_qp *qp,
+						      const struct ib_send_wr *wr,
+						      struct mlx5_wqe_ctrl_seg **ctrl,
+						      void **seg,
+						      int *size, void **cur_edge,
+						      unsigned int *idx, int nreq,
+						      u8 fence,
+						      u8 next_fence)
 {
 	struct mlx5_ib_mr *mr;
 	struct mlx5_ib_mr *pi_mr;

drivers/infiniband/sw/siw/siw_verbs.c

@@ -316,6 +316,7 @@ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs,
 	struct siw_ucontext *uctx =
 		rdma_udata_to_drv_context(udata, struct siw_ucontext,
 					  base_ucontext);
+	struct siw_uresp_create_qp uresp = {};
 	unsigned long flags;
 	int num_sqe, num_rqe, rv = 0;
 	size_t length;
@@ -369,11 +370,6 @@ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs,
 	spin_lock_init(&qp->rq_lock);
 	spin_lock_init(&qp->orq_lock);
 
-	rv = siw_qp_add(sdev, qp);
-	if (rv)
-		goto err_atomic;
-
-
 	/* All queue indices are derived from modulo operations
 	 * on a free running 'get' (consumer) and 'put' (producer)
 	 * unsigned counter. Having queue sizes at power of two
@@ -391,14 +387,14 @@ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs,
 
 	if (qp->sendq == NULL) {
 		rv = -ENOMEM;
-		goto err_out_xa;
+		goto err_out;
 	}
 	if (attrs->sq_sig_type != IB_SIGNAL_REQ_WR) {
 		if (attrs->sq_sig_type == IB_SIGNAL_ALL_WR)
 			qp->attrs.flags |= SIW_SIGNAL_ALL_WR;
 		else {
 			rv = -EINVAL;
-			goto err_out_xa;
+			goto err_out;
 		}
 	}
 	qp->pd = pd;
@@ -424,7 +420,7 @@ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs,
 
 		if (qp->recvq == NULL) {
 			rv = -ENOMEM;
-			goto err_out_xa;
+			goto err_out;
 		}
 		qp->attrs.rq_size = num_rqe;
 	}
@@ -439,11 +435,8 @@ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs,
 	qp->attrs.state = SIW_QP_STATE_IDLE;
 
 	if (udata) {
-		struct siw_uresp_create_qp uresp = {};
-
 		uresp.num_sqe = num_sqe;
 		uresp.num_rqe = num_rqe;
-		uresp.qp_id = qp_id(qp);
 
 		if (qp->sendq) {
 			length = num_sqe * sizeof(struct siw_sqe);
@@ -452,7 +445,7 @@ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs,
 						      length, &uresp.sq_key);
 			if (!qp->sq_entry) {
 				rv = -ENOMEM;
-				goto err_out_xa;
+				goto err_out;
 			}
 		}
 
@@ -464,9 +457,23 @@ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs,
 			if (!qp->rq_entry) {
 				uresp.sq_key = SIW_INVAL_UOBJ_KEY;
 				rv = -ENOMEM;
-				goto err_out_xa;
+				goto err_out;
 			}
 		}
+	}
+	qp->tx_cpu = siw_get_tx_cpu(sdev);
+	if (qp->tx_cpu < 0) {
+		rv = -EINVAL;
+		goto err_out;
+	}
+	init_completion(&qp->qp_free);
+
+	rv = siw_qp_add(sdev, qp);
+	if (rv)
+		goto err_out_tx;
+
+	if (udata) {
+		uresp.qp_id = qp_id(qp);
 
 		if (udata->outlen < sizeof(uresp)) {
 			rv = -EINVAL;
@@ -476,22 +483,19 @@ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs,
 		if (rv)
 			goto err_out_xa;
 	}
-	qp->tx_cpu = siw_get_tx_cpu(sdev);
-	if (qp->tx_cpu < 0) {
-		rv = -EINVAL;
-		goto err_out_xa;
-	}
+
 	INIT_LIST_HEAD(&qp->devq);
 	spin_lock_irqsave(&sdev->lock, flags);
 	list_add_tail(&qp->devq, &sdev->qp_list);
 	spin_unlock_irqrestore(&sdev->lock, flags);
 
-	init_completion(&qp->qp_free);
-
 	return 0;
 
 err_out_xa:
 	xa_erase(&sdev->qp_xa, qp_id(qp));
+err_out_tx:
+	siw_put_tx_cpu(qp->tx_cpu);
+err_out:
 	if (uctx) {
 		rdma_user_mmap_entry_remove(qp->sq_entry);
 		rdma_user_mmap_entry_remove(qp->rq_entry);

drivers/infiniband/ulp/ipoib/ipoib_main.c

@@ -2783,6 +2783,7 @@ static int __init ipoib_init_module(void)
 err_sa:
 	ib_sa_unregister_client(&ipoib_sa_client);
 	destroy_workqueue(ipoib_workqueue);
+	rcu_barrier();
 
 err_fs:
 	ipoib_unregister_debugfs();
@@ -2800,6 +2801,7 @@ static void __exit ipoib_cleanup_module(void)
 	ib_sa_unregister_client(&ipoib_sa_client);
 	ipoib_unregister_debugfs();
 	destroy_workqueue(ipoib_workqueue);
+	rcu_barrier();
 }
 
 module_init(ipoib_init_module);