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

Pull rdma updates from Jason Gunthorpe:
 "This has been a smaller cycle with many of the commits being smallish
  code fixes and improvements across the drivers.

   - Driver updates for bnxt_re, cxgb4, hfi1, hns, mlx5, nes, qedr, and
     rxe

   - Memory window support in hns

   - mlx5 user API 'flow mutate/steering' allows accessing the full
     packet mangling and matching machinery from user space

   - Support inter-working with verbs API calls in the 'devx' mlx5 user
     API, and provide options to use devx with less privilege

   - Modernize the use of syfs and the device interface to use attribute
     groups and cdev properly for uverbs, and clean up some of the core
     code's device list management

   - More progress on net namespaces for RDMA devices

   - Consolidate driver BAR mmapping support into core code helpers and
     rework how RDMA holds poitners to mm_struct for get_user_pages
     cases

   - First pass to use 'dev_name' instead of ib_device->name

   - Device renaming for RDMA devices"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (242 commits)
  IB/mlx5: Add support for extended atomic operations
  RDMA/core: Fix comment for hw stats init for port == 0
  RDMA/core: Refactor ib_register_device() function
  RDMA/core: Fix unwinding flow in case of error to register device
  ib_srp: Remove WARN_ON in srp_terminate_io()
  IB/mlx5: Allow scatter to CQE without global signaled WRs
  IB/mlx5: Verify that driver supports user flags
  IB/mlx5: Support scatter to CQE for DC transport type
  RDMA/drivers: Use core provided API for registering device attributes
  RDMA/core: Allow existing drivers to set one sysfs group per device
  IB/rxe: Remove unnecessary enum values
  RDMA/umad: Use kernel API to allocate umad indexes
  RDMA/uverbs: Use kernel API to allocate uverbs indexes
  RDMA/core: Increase total number of RDMA ports across all devices
  IB/mlx4: Add port and TID to MAD debug print
  IB/mlx4: Enable debug print of SMPs
  RDMA/core: Rename ports_parent to ports_kobj
  RDMA/core: Do not expose unsupported counters
  IB/mlx4: Refer to the device kobject instead of ports_parent
  RDMA/nldev: Allow IB device rename through RDMA netlink
  ...

10 files changed, 86 insertions, 42 deletions

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 3d5424f335cb..0428e01e8f69 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -1438,11 +1438,15 @@ static void ipoib_cm_skb_reap(struct work_struct *work)
 		spin_unlock_irqrestore(&priv->lock, flags);
 		netif_tx_unlock_bh(dev);
 
-		if (skb->protocol == htons(ETH_P_IP))
+		if (skb->protocol == htons(ETH_P_IP)) {
+			memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
+		}
 #if IS_ENABLED(CONFIG_IPV6)
-		else if (skb->protocol == htons(ETH_P_IPV6))
+		else if (skb->protocol == htons(ETH_P_IPV6)) {
+			memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+		}
 #endif
 		dev_kfree_skb_any(skb);
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 8baa75a705c5..8710214594d8 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -243,7 +243,8 @@ static int ipoib_change_mtu(struct net_device *dev, int new_mtu)
 		return 0;
 	}
 
-	if (new_mtu > IPOIB_UD_MTU(priv->max_ib_mtu))
+	if (new_mtu < (ETH_MIN_MTU + IPOIB_ENCAP_LEN) ||
+	    new_mtu > IPOIB_UD_MTU(priv->max_ib_mtu))
 		return -EINVAL;
 
 	priv->admin_mtu = new_mtu;
@@ -1880,6 +1881,8 @@ static int ipoib_parent_init(struct net_device *ndev)
 	       sizeof(union ib_gid));
 
 	SET_NETDEV_DEV(priv->dev, priv->ca->dev.parent);
+	priv->dev->dev_port = priv->port - 1;
+	/* Let's set this one too for backwards compatibility. */
 	priv->dev->dev_id = priv->port - 1;
 
 	return 0;
@@ -2385,6 +2388,35 @@ int ipoib_add_pkey_attr(struct net_device *dev)
 	return device_create_file(&dev->dev, &dev_attr_pkey);
 }
 
+/*
+ * We erroneously exposed the iface's port number in the dev_id
+ * sysfs field long after dev_port was introduced for that purpose[1],
+ * and we need to stop everyone from relying on that.
+ * Let's overload the shower routine for the dev_id file here
+ * to gently bring the issue up.
+ *
+ * [1] https://www.spinics.net/lists/netdev/msg272123.html
+ */
+static ssize_t dev_id_show(struct device *dev,
+			   struct device_attribute *attr, char *buf)
+{
+	struct net_device *ndev = to_net_dev(dev);
+
+	if (ndev->dev_id == ndev->dev_port)
+		netdev_info_once(ndev,
+			"\"%s\" wants to know my dev_id. Should it look at dev_port instead? See Documentation/ABI/testing/sysfs-class-net for more info.\n",
+			current->comm);
+
+	return sprintf(buf, "%#x\n", ndev->dev_id);
+}
+static DEVICE_ATTR_RO(dev_id);
+
+int ipoib_intercept_dev_id_attr(struct net_device *dev)
+{
+	device_remove_file(&dev->dev, &dev_attr_dev_id);
+	return device_create_file(&dev->dev, &dev_attr_dev_id);
+}
+
 static struct net_device *ipoib_add_port(const char *format,
 					 struct ib_device *hca, u8 port)
 {
@@ -2437,6 +2469,8 @@ static struct net_device *ipoib_add_port(const char *format,
 	 */
 	ndev->priv_destructor = ipoib_intf_free;
 
+	if (ipoib_intercept_dev_id_attr(ndev))
+		goto sysfs_failed;
 	if (ipoib_cm_add_mode_attr(ndev))
 		goto sysfs_failed;
 	if (ipoib_add_pkey_attr(ndev))
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index 9f36ca786df8..1e88213459f2 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -277,7 +277,7 @@ void ipoib_event(struct ib_event_handler *handler,
 		return;
 
 	ipoib_dbg(priv, "Event %d on device %s port %d\n", record->event,
-		  record->device->name, record->element.port_num);
+		  dev_name(&record->device->dev), record->element.port_num);
 
 	if (record->event == IB_EVENT_SM_CHANGE ||
 	    record->event == IB_EVENT_CLIENT_REREGISTER) {
diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c
index 2f6388596f88..96af06cfe0af 100644
--- a/drivers/infiniband/ulp/iser/iser_initiator.c
+++ b/drivers/infiniband/ulp/iser/iser_initiator.c
@@ -589,13 +589,19 @@ void iser_login_rsp(struct ib_cq *cq, struct ib_wc *wc)
 	ib_conn->post_recv_buf_count--;
 }
 
-static inline void
+static inline int
 iser_inv_desc(struct iser_fr_desc *desc, u32 rkey)
 {
-	if (likely(rkey == desc->rsc.mr->rkey))
+	if (likely(rkey == desc->rsc.mr->rkey)) {
 		desc->rsc.mr_valid = 0;
-	else if (likely(rkey == desc->pi_ctx->sig_mr->rkey))
+	} else if (likely(desc->pi_ctx && rkey == desc->pi_ctx->sig_mr->rkey)) {
 		desc->pi_ctx->sig_mr_valid = 0;
+	} else {
+		iser_err("Bogus remote invalidation for rkey %#x\n", rkey);
+		return -EINVAL;
+	}
+
+	return 0;
 }
 
 static int
@@ -623,12 +629,14 @@ iser_check_remote_inv(struct iser_conn *iser_conn,
 
 			if (iser_task->dir[ISER_DIR_IN]) {
 				desc = iser_task->rdma_reg[ISER_DIR_IN].mem_h;
-				iser_inv_desc(desc, rkey);
+				if (unlikely(iser_inv_desc(desc, rkey)))
+					return -EINVAL;
 			}
 
 			if (iser_task->dir[ISER_DIR_OUT]) {
 				desc = iser_task->rdma_reg[ISER_DIR_OUT].mem_h;
-				iser_inv_desc(desc, rkey);
+				if (unlikely(iser_inv_desc(desc, rkey)))
+					return -EINVAL;
 			}
 		} else {
 			iser_err("failed to get task for itt=%d\n", hdr->itt);
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index b686a4aaffe8..946b623ba5eb 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -55,7 +55,7 @@ static void iser_event_handler(struct ib_event_handler *handler,
 {
 	iser_err("async event %s (%d) on device %s port %d\n",
 		 ib_event_msg(event->event), event->event,
-		 event->device->name, event->element.port_num);
+		dev_name(&event->device->dev), event->element.port_num);
 }
 
 /**
@@ -85,7 +85,7 @@ static int iser_create_device_ib_res(struct iser_device *device)
 	max_cqe = min(ISER_MAX_CQ_LEN, ib_dev->attrs.max_cqe);
 
 	iser_info("using %d CQs, device %s supports %d vectors max_cqe %d\n",
-		  device->comps_used, ib_dev->name,
+		  device->comps_used, dev_name(&ib_dev->dev),
 		  ib_dev->num_comp_vectors, max_cqe);
 
 	device->pd = ib_alloc_pd(ib_dev,
@@ -468,7 +468,8 @@ static int iser_create_ib_conn_res(struct ib_conn *ib_conn)
 			iser_conn->max_cmds =
 				ISER_GET_MAX_XMIT_CMDS(ib_dev->attrs.max_qp_wr);
 			iser_dbg("device %s supports max_send_wr %d\n",
-				 device->ib_device->name, ib_dev->attrs.max_qp_wr);
+				 dev_name(&device->ib_device->dev),
+				 ib_dev->attrs.max_qp_wr);
 		}
 	}
 
@@ -764,7 +765,7 @@ static void iser_addr_handler(struct rdma_cm_id *cma_id)
 		      IB_DEVICE_SIGNATURE_HANDOVER)) {
 			iser_warn("T10-PI requested but not supported on %s, "
 				  "continue without T10-PI\n",
-				  ib_conn->device->ib_device->name);
+				  dev_name(&ib_conn->device->ib_device->dev));
 			ib_conn->pi_support = false;
 		} else {
 			ib_conn->pi_support = true;
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index f39670c5c25c..e3dd13798d79 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -262,7 +262,7 @@ isert_alloc_comps(struct isert_device *device)
 
 	isert_info("Using %d CQs, %s supports %d vectors support "
 		   "pi_capable %d\n",
-		   device->comps_used, device->ib_device->name,
+		   device->comps_used, dev_name(&device->ib_device->dev),
 		   device->ib_device->num_comp_vectors,
 		   device->pi_capable);
 
diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.c
index 267da8215e08..31cd361416ac 100644
--- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.c
+++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.c
@@ -351,7 +351,8 @@ static uint32_t opa_vnic_get_dlid(struct opa_vnic_adapter *adapter,
 			if (unlikely(!dlid))
 				v_warn("Null dlid in MAC address\n");
 		} else if (def_port != OPA_VNIC_INVALID_PORT) {
-			dlid = info->vesw.u_ucast_dlid[def_port];
+			if (def_port < OPA_VESW_MAX_NUM_DEF_PORT)
+				dlid = info->vesw.u_ucast_dlid[def_port];
 		}
 	}
 
diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c
index 15711dcc6f58..d119d9afa845 100644
--- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c
+++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c
@@ -888,7 +888,8 @@ static void opa_vnic_event(struct ib_event_handler *handler,
 		return;
 
 	c_dbg("OPA_VNIC received event %d on device %s port %d\n",
-	      record->event, record->device->name, record->element.port_num);
+	      record->event, dev_name(&record->device->dev),
+	      record->element.port_num);
 
 	if (record->event == IB_EVENT_PORT_ERR)
 		idr_for_each(&port->vport_idr, vema_disable_vport, NULL);
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 0b34e909505f..eed0eb3bb04c 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -1330,17 +1330,8 @@ static void srp_terminate_io(struct srp_rport *rport)
 {
 	struct srp_target_port *target = rport->lld_data;
 	struct srp_rdma_ch *ch;
-	struct Scsi_Host *shost = target->scsi_host;
-	struct scsi_device *sdev;
 	int i, j;
 
-	/*
-	 * Invoking srp_terminate_io() while srp_queuecommand() is running
-	 * is not safe. Hence the warning statement below.
-	 */
-	shost_for_each_device(sdev, shost)
-		WARN_ON_ONCE(sdev->request_queue->request_fn_active);
-
 	for (i = 0; i < target->ch_count; i++) {
 		ch = &target->ch[i];
 
@@ -3124,7 +3115,8 @@ static ssize_t show_local_ib_device(struct device *dev,
 {
 	struct srp_target_port *target = host_to_target(class_to_shost(dev));
 
-	return sprintf(buf, "%s\n", target->srp_host->srp_dev->dev->name);
+	return sprintf(buf, "%s\n",
+		       dev_name(&target->srp_host->srp_dev->dev->dev));
 }
 
 static ssize_t show_ch_count(struct device *dev, struct device_attribute *attr,
@@ -3987,7 +3979,7 @@ static ssize_t show_ibdev(struct device *dev, struct device_attribute *attr,
 {
 	struct srp_host *host = container_of(dev, struct srp_host, dev);
 
-	return sprintf(buf, "%s\n", host->srp_dev->dev->name);
+	return sprintf(buf, "%s\n", dev_name(&host->srp_dev->dev->dev));
 }
 
 static DEVICE_ATTR(ibdev, S_IRUGO, show_ibdev, NULL);
@@ -4019,7 +4011,8 @@ static struct srp_host *srp_add_port(struct srp_device *device, u8 port)
 
 	host->dev.class = &srp_class;
 	host->dev.parent = device->dev->dev.parent;
-	dev_set_name(&host->dev, "srp-%s-%d", device->dev->name, port);
+	dev_set_name(&host->dev, "srp-%s-%d", dev_name(&device->dev->dev),
+		     port);
 
 	if (device_register(&host->dev))
 		goto free_host;
@@ -4095,7 +4088,7 @@ static void srp_add_one(struct ib_device *device)
 	srp_dev->mr_max_size	= srp_dev->mr_page_size *
 				   srp_dev->max_pages_per_mr;
 	pr_debug("%s: mr_page_shift = %d, device->max_mr_size = %#llx, device->max_fast_reg_page_list_len = %u, max_pages_per_mr = %d, mr_max_size = %#x\n",
-		 device->name, mr_page_shift, attr->max_mr_size,
+		 dev_name(&device->dev), mr_page_shift, attr->max_mr_size,
 		 attr->max_fast_reg_page_list_len,
 		 srp_dev->max_pages_per_mr, srp_dev->mr_max_size);
 
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index f37cbad022a2..2357aa727dcf 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -148,7 +148,7 @@ static void srpt_event_handler(struct ib_event_handler *handler,
 		return;
 
 	pr_debug("ASYNC event= %d on device= %s\n", event->event,
-		 sdev->device->name);
+		 dev_name(&sdev->device->dev));
 
 	switch (event->event) {
 	case IB_EVENT_PORT_ERR:
@@ -1941,7 +1941,8 @@ static void __srpt_close_all_ch(struct srpt_port *sport)
 			if (srpt_disconnect_ch(ch) >= 0)
 				pr_info("Closing channel %s because target %s_%d has been disabled\n",
 					ch->sess_name,
-					sport->sdev->device->name, sport->port);
+					dev_name(&sport->sdev->device->dev),
+					sport->port);
 			srpt_close_ch(ch);
 		}
 	}
@@ -2127,7 +2128,7 @@ static int srpt_cm_req_recv(struct srpt_device *const sdev,
 	if (!sport->enabled) {
 		rej->reason = cpu_to_be32(SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES);
 		pr_info("rejected SRP_LOGIN_REQ because target port %s_%d has not yet been enabled\n",
-			sport->sdev->device->name, port_num);
+			dev_name(&sport->sdev->device->dev), port_num);
 		goto reject;
 	}
 
@@ -2267,7 +2268,7 @@ static int srpt_cm_req_recv(struct srpt_device *const sdev,
 		rej->reason = cpu_to_be32(
 				SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES);
 		pr_info("rejected SRP_LOGIN_REQ because target %s_%d is not enabled\n",
-			sdev->device->name, port_num);
+			dev_name(&sdev->device->dev), port_num);
 		mutex_unlock(&sport->mutex);
 		goto reject;
 	}
@@ -2708,7 +2709,7 @@ static void srpt_queue_response(struct se_cmd *cmd)
 		break;
 	}
 
-	if (unlikely(WARN_ON_ONCE(state == SRPT_STATE_CMD_RSP_SENT)))
+	if (WARN_ON_ONCE(state == SRPT_STATE_CMD_RSP_SENT))
 		return;
 
 	/* For read commands, transfer the data to the initiator. */
@@ -2842,7 +2843,7 @@ static int srpt_release_sport(struct srpt_port *sport)
 	while (wait_event_timeout(sport->ch_releaseQ,
 				  srpt_ch_list_empty(sport), 5 * HZ) <= 0) {
 		pr_info("%s_%d: waiting for session unregistration ...\n",
-			sport->sdev->device->name, sport->port);
+			dev_name(&sport->sdev->device->dev), sport->port);
 		rcu_read_lock();
 		list_for_each_entry(nexus, &sport->nexus_list, entry) {
 			list_for_each_entry(ch, &nexus->ch_list, list) {
@@ -2932,7 +2933,7 @@ static int srpt_alloc_srq(struct srpt_device *sdev)
 	}
 
 	pr_debug("create SRQ #wr= %d max_allow=%d dev= %s\n", sdev->srq_size,
-		 sdev->device->attrs.max_srq_wr, device->name);
+		 sdev->device->attrs.max_srq_wr, dev_name(&device->dev));
 
 	sdev->ioctx_ring = (struct srpt_recv_ioctx **)
 		srpt_alloc_ioctx_ring(sdev, sdev->srq_size,
@@ -2965,8 +2966,8 @@ static int srpt_use_srq(struct srpt_device *sdev, bool use_srq)
 	} else if (use_srq && !sdev->srq) {
 		ret = srpt_alloc_srq(sdev);
 	}
-	pr_debug("%s(%s): use_srq = %d; ret = %d\n", __func__, device->name,
-		 sdev->use_srq, ret);
+	pr_debug("%s(%s): use_srq = %d; ret = %d\n", __func__,
+		 dev_name(&device->dev), sdev->use_srq, ret);
 	return ret;
 }
 
@@ -3052,7 +3053,7 @@ static void srpt_add_one(struct ib_device *device)
 
 		if (srpt_refresh_port(sport)) {
 			pr_err("MAD registration failed for %s-%d.\n",
-			       sdev->device->name, i);
+			       dev_name(&sdev->device->dev), i);
 			goto err_event;
 		}
 	}
@@ -3063,7 +3064,7 @@ static void srpt_add_one(struct ib_device *device)
 
 out:
 	ib_set_client_data(device, &srpt_client, sdev);
-	pr_debug("added %s.\n", device->name);
+	pr_debug("added %s.\n", dev_name(&device->dev));
 	return;
 
 err_event:
@@ -3078,7 +3079,7 @@ free_dev:
 	kfree(sdev);
 err:
 	sdev = NULL;
-	pr_info("%s(%s) failed.\n", __func__, device->name);
+	pr_info("%s(%s) failed.\n", __func__, dev_name(&device->dev));
 	goto out;
 }
 
@@ -3093,7 +3094,8 @@ static void srpt_remove_one(struct ib_device *device, void *client_data)
 	int i;
 
 	if (!sdev) {
-		pr_info("%s(%s): nothing to do.\n", __func__, device->name);
+		pr_info("%s(%s): nothing to do.\n", __func__,
+			dev_name(&device->dev));
 		return;
 	}