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

Pull rdma fixes from Doug Ledford:

 - Smattering of miscellanous fixes

 - A five patch series for i40iw that had a patch (5/5) that was larger
   than I would like, but I took it because it's needed for large scale
   users

 - An 8 patch series for bnxt_re that landed right as I was leaving on
   PTO and so had to wait until now...they are all appropriate fixes for
   -rc IMO

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (22 commits)
  bnxt_re: Don't issue cmd to delete GID for QP1 GID entry before the QP is destroyed
  bnxt_re: Fix memory leak in FRMR path
  bnxt_re: Remove RTNL lock dependency in bnxt_re_query_port
  bnxt_re: Fix race between the netdev register and unregister events
  bnxt_re: Free up devices in module_exit path
  bnxt_re: Fix compare and swap atomic operands
  bnxt_re: Stop issuing further cmds to FW once a cmd times out
  bnxt_re: Fix update of qplib_qp.mtu when modified
  i40iw: Add support for port reuse on active side connections
  i40iw: Add missing VLAN priority
  i40iw: Call i40iw_cm_disconn on modify QP to disconnect
  i40iw: Prevent multiple netdev event notifier registrations
  i40iw: Fail open if there are no available MSI-X vectors
  RDMA/vmw_pvrdma: Fix reporting correct opcodes for completion
  IB/bnxt_re: Fix frame stack compilation warning
  IB/mlx5: fix debugfs cleanup
  IB/ocrdma: fix incorrect fall-through on switch statement
  IB/ipoib: Suppress the retry related completion errors
  iw_cxgb4: remove the stid on listen create failure
  iw_cxgb4: drop listen destroy replies if no ep found
  ...

Author: torvalds

drivers/infiniband/core/verbs.c

@@ -1646,7 +1646,7 @@ static bool is_valid_mcast_lid(struct ib_qp *qp, u16 lid)
 	 */
 	if (!ib_query_qp(qp, &attr, IB_QP_STATE | IB_QP_PORT, &init_attr)) {
 		if (attr.qp_state >= IB_QPS_INIT) {
-			if (qp->device->get_link_layer(qp->device, attr.port_num) !=
+			if (rdma_port_get_link_layer(qp->device, attr.port_num) !=
 			    IB_LINK_LAYER_INFINIBAND)
 				return true;
 			goto lid_check;
@@ -1655,7 +1655,7 @@ static bool is_valid_mcast_lid(struct ib_qp *qp, u16 lid)
 
 	/* Can't get a quick answer, iterate over all ports */
 	for (port = 0; port < qp->device->phys_port_cnt; port++)
-		if (qp->device->get_link_layer(qp->device, port) !=
+		if (rdma_port_get_link_layer(qp->device, port) !=
 		    IB_LINK_LAYER_INFINIBAND)
 			num_eth_ports++;
 

drivers/infiniband/hw/bnxt_re/bnxt_re.h

@@ -93,11 +93,13 @@ struct bnxt_re_dev {
 	struct ib_device		ibdev;
 	struct list_head		list;
 	unsigned long			flags;
-#define BNXT_RE_FLAG_NETDEV_REGISTERED	0
-#define BNXT_RE_FLAG_IBDEV_REGISTERED	1
-#define BNXT_RE_FLAG_GOT_MSIX		2
-#define BNXT_RE_FLAG_RCFW_CHANNEL_EN	8
-#define BNXT_RE_FLAG_QOS_WORK_REG	16
+#define BNXT_RE_FLAG_NETDEV_REGISTERED		0
+#define BNXT_RE_FLAG_IBDEV_REGISTERED		1
+#define BNXT_RE_FLAG_GOT_MSIX			2
+#define BNXT_RE_FLAG_HAVE_L2_REF		3
+#define BNXT_RE_FLAG_RCFW_CHANNEL_EN		4
+#define BNXT_RE_FLAG_QOS_WORK_REG		5
+#define BNXT_RE_FLAG_TASK_IN_PROG		6
 	struct net_device		*netdev;
 	unsigned int			version, major, minor;
 	struct bnxt_en_dev		*en_dev;
@@ -108,6 +110,8 @@ struct bnxt_re_dev {
 
 	struct delayed_work		worker;
 	u8				cur_prio_map;
+	u8				active_speed;
+	u8				active_width;
 
 	/* FP Notification Queue (CQ & SRQ) */
 	struct tasklet_struct		nq_task;

drivers/infiniband/hw/bnxt_re/ib_verbs.c

@@ -259,14 +259,9 @@ int bnxt_re_query_port(struct ib_device *ibdev, u8 port_num,
 	port_attr->sm_sl = 0;
 	port_attr->subnet_timeout = 0;
 	port_attr->init_type_reply = 0;
-	/* call the underlying netdev's ethtool hooks to query speed settings
-	 * for which we acquire rtnl_lock _only_ if it's registered with
-	 * IB stack to avoid race in the NETDEV_UNREG path
-	 */
-	if (test_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags))
-		if (ib_get_eth_speed(ibdev, port_num, &port_attr->active_speed,
-				     &port_attr->active_width))
-			return -EINVAL;
+	port_attr->active_speed = rdev->active_speed;
+	port_attr->active_width = rdev->active_width;
+
 	return 0;
 }
 
@@ -319,6 +314,7 @@ int bnxt_re_del_gid(struct ib_device *ibdev, u8 port_num,
 	struct bnxt_re_gid_ctx *ctx, **ctx_tbl;
 	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
 	struct bnxt_qplib_sgid_tbl *sgid_tbl = &rdev->qplib_res.sgid_tbl;
+	struct bnxt_qplib_gid *gid_to_del;
 
 	/* Delete the entry from the hardware */
 	ctx = *context;
@@ -328,11 +324,25 @@ int bnxt_re_del_gid(struct ib_device *ibdev, u8 port_num,
 	if (sgid_tbl && sgid_tbl->active) {
 		if (ctx->idx >= sgid_tbl->max)
 			return -EINVAL;
+		gid_to_del = &sgid_tbl->tbl[ctx->idx];
+		/* DEL_GID is called in WQ context(netdevice_event_work_handler)
+		 * or via the ib_unregister_device path. In the former case QP1
+		 * may not be destroyed yet, in which case just return as FW
+		 * needs that entry to be present and will fail it's deletion.
+		 * We could get invoked again after QP1 is destroyed OR get an
+		 * ADD_GID call with a different GID value for the same index
+		 * where we issue MODIFY_GID cmd to update the GID entry -- TBD
+		 */
+		if (ctx->idx == 0 &&
+		    rdma_link_local_addr((struct in6_addr *)gid_to_del) &&
+		    ctx->refcnt == 1 && rdev->qp1_sqp) {
+			dev_dbg(rdev_to_dev(rdev),
+				"Trying to delete GID0 while QP1 is alive\n");
+			return -EFAULT;
+		}
 		ctx->refcnt--;
 		if (!ctx->refcnt) {
-			rc = bnxt_qplib_del_sgid(sgid_tbl,
-						 &sgid_tbl->tbl[ctx->idx],
-						 true);
+			rc = bnxt_qplib_del_sgid(sgid_tbl, gid_to_del, true);
 			if (rc) {
 				dev_err(rdev_to_dev(rdev),
 					"Failed to remove GID: %#x", rc);
@@ -816,6 +826,8 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp)
 
 		kfree(rdev->sqp_ah);
 		kfree(rdev->qp1_sqp);
+		rdev->qp1_sqp = NULL;
+		rdev->sqp_ah = NULL;
 	}
 
 	if (!IS_ERR_OR_NULL(qp->rumem))
@@ -1436,11 +1448,14 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr,
 		qp->qplib_qp.modify_flags |=
 				CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU;
 		qp->qplib_qp.path_mtu = __from_ib_mtu(qp_attr->path_mtu);
+		qp->qplib_qp.mtu = ib_mtu_enum_to_int(qp_attr->path_mtu);
 	} else if (qp_attr->qp_state == IB_QPS_RTR) {
 		qp->qplib_qp.modify_flags |=
 			CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU;
 		qp->qplib_qp.path_mtu =
 			__from_ib_mtu(iboe_get_mtu(rdev->netdev->mtu));
+		qp->qplib_qp.mtu =
+			ib_mtu_enum_to_int(iboe_get_mtu(rdev->netdev->mtu));
 	}
 
 	if (qp_attr_mask & IB_QP_TIMEOUT) {
@@ -1551,43 +1566,46 @@ int bnxt_re_query_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr,
 {
 	struct bnxt_re_qp *qp = container_of(ib_qp, struct bnxt_re_qp, ib_qp);
 	struct bnxt_re_dev *rdev = qp->rdev;
-	struct bnxt_qplib_qp qplib_qp;
+	struct bnxt_qplib_qp *qplib_qp;
 	int rc;
 
-	memset(&qplib_qp, 0, sizeof(struct bnxt_qplib_qp));
-	qplib_qp.id = qp->qplib_qp.id;
-	qplib_qp.ah.host_sgid_index = qp->qplib_qp.ah.host_sgid_index;
+	qplib_qp = kzalloc(sizeof(*qplib_qp), GFP_KERNEL);
+	if (!qplib_qp)
+		return -ENOMEM;
+
+	qplib_qp->id = qp->qplib_qp.id;
+	qplib_qp->ah.host_sgid_index = qp->qplib_qp.ah.host_sgid_index;
 
-	rc = bnxt_qplib_query_qp(&rdev->qplib_res, &qplib_qp);
+	rc = bnxt_qplib_query_qp(&rdev->qplib_res, qplib_qp);
 	if (rc) {
 		dev_err(rdev_to_dev(rdev), "Failed to query HW QP");
-		return rc;
+		goto out;
 	}
-	qp_attr->qp_state = __to_ib_qp_state(qplib_qp.state);
-	qp_attr->en_sqd_async_notify = qplib_qp.en_sqd_async_notify ? 1 : 0;
-	qp_attr->qp_access_flags = __to_ib_access_flags(qplib_qp.access);
-	qp_attr->pkey_index = qplib_qp.pkey_index;
-	qp_attr->qkey = qplib_qp.qkey;
+	qp_attr->qp_state = __to_ib_qp_state(qplib_qp->state);
+	qp_attr->en_sqd_async_notify = qplib_qp->en_sqd_async_notify ? 1 : 0;
+	qp_attr->qp_access_flags = __to_ib_access_flags(qplib_qp->access);
+	qp_attr->pkey_index = qplib_qp->pkey_index;
+	qp_attr->qkey = qplib_qp->qkey;
 	qp_attr->ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE;
-	rdma_ah_set_grh(&qp_attr->ah_attr, NULL, qplib_qp.ah.flow_label,
-			qplib_qp.ah.host_sgid_index,
-			qplib_qp.ah.hop_limit,
-			qplib_qp.ah.traffic_class);
-	rdma_ah_set_dgid_raw(&qp_attr->ah_attr, qplib_qp.ah.dgid.data);
-	rdma_ah_set_sl(&qp_attr->ah_attr, qplib_qp.ah.sl);
-	ether_addr_copy(qp_attr->ah_attr.roce.dmac, qplib_qp.ah.dmac);
-	qp_attr->path_mtu = __to_ib_mtu(qplib_qp.path_mtu);
-	qp_attr->timeout = qplib_qp.timeout;
-	qp_attr->retry_cnt = qplib_qp.retry_cnt;
-	qp_attr->rnr_retry = qplib_qp.rnr_retry;
-	qp_attr->min_rnr_timer = qplib_qp.min_rnr_timer;
-	qp_attr->rq_psn = qplib_qp.rq.psn;
-	qp_attr->max_rd_atomic = qplib_qp.max_rd_atomic;
-	qp_attr->sq_psn = qplib_qp.sq.psn;
-	qp_attr->max_dest_rd_atomic = qplib_qp.max_dest_rd_atomic;
-	qp_init_attr->sq_sig_type = qplib_qp.sig_type ? IB_SIGNAL_ALL_WR :
-							IB_SIGNAL_REQ_WR;
-	qp_attr->dest_qp_num = qplib_qp.dest_qpn;
+	rdma_ah_set_grh(&qp_attr->ah_attr, NULL, qplib_qp->ah.flow_label,
+			qplib_qp->ah.host_sgid_index,
+			qplib_qp->ah.hop_limit,
+			qplib_qp->ah.traffic_class);
+	rdma_ah_set_dgid_raw(&qp_attr->ah_attr, qplib_qp->ah.dgid.data);
+	rdma_ah_set_sl(&qp_attr->ah_attr, qplib_qp->ah.sl);
+	ether_addr_copy(qp_attr->ah_attr.roce.dmac, qplib_qp->ah.dmac);
+	qp_attr->path_mtu = __to_ib_mtu(qplib_qp->path_mtu);
+	qp_attr->timeout = qplib_qp->timeout;
+	qp_attr->retry_cnt = qplib_qp->retry_cnt;
+	qp_attr->rnr_retry = qplib_qp->rnr_retry;
+	qp_attr->min_rnr_timer = qplib_qp->min_rnr_timer;
+	qp_attr->rq_psn = qplib_qp->rq.psn;
+	qp_attr->max_rd_atomic = qplib_qp->max_rd_atomic;
+	qp_attr->sq_psn = qplib_qp->sq.psn;
+	qp_attr->max_dest_rd_atomic = qplib_qp->max_dest_rd_atomic;
+	qp_init_attr->sq_sig_type = qplib_qp->sig_type ? IB_SIGNAL_ALL_WR :
+							 IB_SIGNAL_REQ_WR;
+	qp_attr->dest_qp_num = qplib_qp->dest_qpn;
 
 	qp_attr->cap.max_send_wr = qp->qplib_qp.sq.max_wqe;
 	qp_attr->cap.max_send_sge = qp->qplib_qp.sq.max_sge;
@@ -1596,7 +1614,9 @@ int bnxt_re_query_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr,
 	qp_attr->cap.max_inline_data = qp->qplib_qp.max_inline_data;
 	qp_init_attr->cap = qp_attr->cap;
 
-	return 0;
+out:
+	kfree(qplib_qp);
+	return rc;
 }
 
 /* Routine for sending QP1 packets for RoCE V1 an V2
@@ -1908,6 +1928,7 @@ static int bnxt_re_build_atomic_wqe(struct ib_send_wr *wr,
 	switch (wr->opcode) {
 	case IB_WR_ATOMIC_CMP_AND_SWP:
 		wqe->type = BNXT_QPLIB_SWQE_TYPE_ATOMIC_CMP_AND_SWP;
+		wqe->atomic.cmp_data = atomic_wr(wr)->compare_add;
 		wqe->atomic.swap_data = atomic_wr(wr)->swap;
 		break;
 	case IB_WR_ATOMIC_FETCH_AND_ADD:
@@ -3062,7 +3083,7 @@ int bnxt_re_dereg_mr(struct ib_mr *ib_mr)
 		return rc;
 	}
 
-	if (mr->npages && mr->pages) {
+	if (mr->pages) {
 		rc = bnxt_qplib_free_fast_reg_page_list(&rdev->qplib_res,
 							&mr->qplib_frpl);
 		kfree(mr->pages);

drivers/infiniband/hw/bnxt_re/main.c

@@ -1161,6 +1161,8 @@ static int bnxt_re_ib_reg(struct bnxt_re_dev *rdev)
 		}
 	}
 	set_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags);
+	ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed,
+			 &rdev->active_width);
 	bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, IB_EVENT_PORT_ACTIVE);
 	bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, IB_EVENT_GID_CHANGE);
 
@@ -1255,10 +1257,14 @@ static void bnxt_re_task(struct work_struct *work)
 		else if (netif_carrier_ok(rdev->netdev))
 			bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1,
 					       IB_EVENT_PORT_ACTIVE);
+		ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed,
+				 &rdev->active_width);
 		break;
 	default:
 		break;
 	}
+	smp_mb__before_atomic();
+	clear_bit(BNXT_RE_FLAG_TASK_IN_PROG, &rdev->flags);
 	kfree(re_work);
 }
 
@@ -1317,6 +1323,11 @@ static int bnxt_re_netdev_event(struct notifier_block *notifier,
 		break;
 
 	case NETDEV_UNREGISTER:
+		/* netdev notifier will call NETDEV_UNREGISTER again later since
+		 * we are still holding the reference to the netdev
+		 */
+		if (test_bit(BNXT_RE_FLAG_TASK_IN_PROG, &rdev->flags))
+			goto exit;
 		bnxt_re_ib_unreg(rdev, false);
 		bnxt_re_remove_one(rdev);
 		bnxt_re_dev_unreg(rdev);
@@ -1335,6 +1346,7 @@ static int bnxt_re_netdev_event(struct notifier_block *notifier,
 			re_work->vlan_dev = (real_dev == netdev ?
 					     NULL : netdev);
 			INIT_WORK(&re_work->work, bnxt_re_task);
+			set_bit(BNXT_RE_FLAG_TASK_IN_PROG, &rdev->flags);
 			queue_work(bnxt_re_wq, &re_work->work);
 		}
 	}
@@ -1375,6 +1387,22 @@ static int __init bnxt_re_mod_init(void)
 
 static void __exit bnxt_re_mod_exit(void)
 {
+	struct bnxt_re_dev *rdev;
+	LIST_HEAD(to_be_deleted);
+
+	mutex_lock(&bnxt_re_dev_lock);
+	/* Free all adapter allocated resources */
+	if (!list_empty(&bnxt_re_dev_list))
+		list_splice_init(&bnxt_re_dev_list, &to_be_deleted);
+	mutex_unlock(&bnxt_re_dev_lock);
+
+	list_for_each_entry(rdev, &to_be_deleted, list) {
+		dev_info(rdev_to_dev(rdev), "Unregistering Device");
+		bnxt_re_dev_stop(rdev);
+		bnxt_re_ib_unreg(rdev, true);
+		bnxt_re_remove_one(rdev);
+		bnxt_re_dev_unreg(rdev);
+	}
 	unregister_netdevice_notifier(&bnxt_re_netdev_notifier);
 	if (bnxt_re_wq)
 		destroy_workqueue(bnxt_re_wq);

drivers/infiniband/hw/bnxt_re/qplib_rcfw.c

@@ -107,6 +107,9 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, struct cmdq_base *req,
 		return -EINVAL;
 	}
 
+	if (test_bit(FIRMWARE_TIMED_OUT, &rcfw->flags))
+		return -ETIMEDOUT;
+
 	/* Cmdq are in 16-byte units, each request can consume 1 or more
 	 * cmdqe
 	 */
@@ -226,6 +229,7 @@ int bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw,
 		/* timed out */
 		dev_err(&rcfw->pdev->dev, "QPLIB: cmdq[%#x]=%#x timedout (%d)msec",
 			cookie, opcode, RCFW_CMD_WAIT_TIME_MS);
+		set_bit(FIRMWARE_TIMED_OUT, &rcfw->flags);
 		return rc;
 	}
 

drivers/infiniband/hw/bnxt_re/qplib_rcfw.h

@@ -162,8 +162,9 @@ struct bnxt_qplib_rcfw {
 	unsigned long		*cmdq_bitmap;
 	u32			bmap_size;
 	unsigned long		flags;
-#define FIRMWARE_INITIALIZED_FLAG	1
+#define FIRMWARE_INITIALIZED_FLAG	BIT(0)
 #define FIRMWARE_FIRST_FLAG		BIT(31)
+#define FIRMWARE_TIMED_OUT		BIT(3)
 	wait_queue_head_t	waitq;
 	int			(*aeq_handler)(struct bnxt_qplib_rcfw *,
 					       struct creq_func_event *);

drivers/infiniband/hw/cxgb4/cm.c

@@ -2333,9 +2333,14 @@ static int close_listsrv_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 	unsigned int stid = GET_TID(rpl);
 	struct c4iw_listen_ep *ep = get_ep_from_stid(dev, stid);
 
+	if (!ep) {
+		pr_debug("%s stid %d lookup failure!\n", __func__, stid);
+		goto out;
+	}
 	pr_debug("%s ep %p\n", __func__, ep);
 	c4iw_wake_up(&ep->com.wr_wait, status2errno(rpl->status));
 	c4iw_put_ep(&ep->com);
+out:
 	return 0;
 }
 
@@ -2594,9 +2599,9 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
 	c4iw_put_ep(&child_ep->com);
 reject:
 	reject_cr(dev, hwtid, skb);
+out:
 	if (parent_ep)
 		c4iw_put_ep(&parent_ep->com);
-out:
 	return 0;
 }
 
@@ -3457,7 +3462,7 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog)
 		cm_id->provider_data = ep;
 		goto out;
 	}
-
+	remove_handle(ep->com.dev, &ep->com.dev->stid_idr, ep->stid);
 	cxgb4_free_stid(ep->com.dev->rdev.lldi.tids, ep->stid,
 			ep->com.local_addr.ss_family);
 fail2:

drivers/infiniband/hw/i40iw/i40iw.h

@@ -201,7 +201,6 @@ enum init_completion_state {
 	CEQ_CREATED,
 	ILQ_CREATED,
 	IEQ_CREATED,
-	INET_NOTIFIER,
 	IP_ADDR_REGISTERED,
 	RDMA_DEV_REGISTERED
 };