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

Pull rdma fixes from Doug Ledford:
 "Third set of -rc fixes for 4.13 cycle

   - small set of miscellanous fixes

   - a reasonably sizable set of IPoIB fixes that deal with multiple
     long standing issues"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma:
  IB/hns: checking for IS_ERR() instead of NULL
  RDMA/mlx5: Fix existence check for extended address vector
  IB/uverbs: Fix device cleanup
  RDMA/uverbs: Prevent leak of reserved field
  IB/core: Fix race condition in resolving IP to MAC
  IB/ipoib: Notify on modify QP failure only when relevant
  Revert "IB/core: Allow QP state transition from reset to error"
  IB/ipoib: Remove double pointer assigning
  IB/ipoib: Clean error paths in add port
  IB/ipoib: Add get statistics support to SRIOV VF
  IB/ipoib: Add multicast packets statistics
  IB/ipoib: Set IPOIB_NEIGH_TBL_FLUSH after flushed completion initialization
  IB/ipoib: Prevent setting negative values to max_nonsrq_conn_qp
  IB/ipoib: Make sure no in-flight joins while leaving that mcast
  IB/ipoib: Use cancel_delayed_work_sync when needed
  IB/ipoib: Fix race between light events and interface restart

drivers/infiniband/core/addr.c

@@ -61,6 +61,7 @@ struct addr_req {
 	void (*callback)(int status, struct sockaddr *src_addr,
 			 struct rdma_dev_addr *addr, void *context);
 	unsigned long timeout;
+	struct delayed_work work;
 	int status;
 	u32 seq;
 };
@@ -295,7 +296,7 @@ int rdma_translate_ip(const struct sockaddr *addr,
 }
 EXPORT_SYMBOL(rdma_translate_ip);
 
-static void set_timeout(unsigned long time)
+static void set_timeout(struct delayed_work *delayed_work, unsigned long time)
 {
 	unsigned long delay;
 
@@ -303,7 +304,7 @@ static void set_timeout(unsigned long time)
 	if ((long)delay < 0)
 		delay = 0;
 
-	mod_delayed_work(addr_wq, &work, delay);
+	mod_delayed_work(addr_wq, delayed_work, delay);
 }
 
 static void queue_req(struct addr_req *req)
@@ -318,8 +319,7 @@ static void queue_req(struct addr_req *req)
 
 	list_add(&req->list, &temp_req->list);
 
-	if (req_list.next == &req->list)
-		set_timeout(req->timeout);
+	set_timeout(&req->work, req->timeout);
 	mutex_unlock(&lock);
 }
 
@@ -574,6 +574,37 @@ static int addr_resolve(struct sockaddr *src_in,
 	return ret;
 }
 
+static void process_one_req(struct work_struct *_work)
+{
+	struct addr_req *req;
+	struct sockaddr *src_in, *dst_in;
+
+	mutex_lock(&lock);
+	req = container_of(_work, struct addr_req, work.work);
+
+	if (req->status == -ENODATA) {
+		src_in = (struct sockaddr *)&req->src_addr;
+		dst_in = (struct sockaddr *)&req->dst_addr;
+		req->status = addr_resolve(src_in, dst_in, req->addr,
+					   true, req->seq);
+		if (req->status && time_after_eq(jiffies, req->timeout)) {
+			req->status = -ETIMEDOUT;
+		} else if (req->status == -ENODATA) {
+			/* requeue the work for retrying again */
+			set_timeout(&req->work, req->timeout);
+			mutex_unlock(&lock);
+			return;
+		}
+	}
+	list_del(&req->list);
+	mutex_unlock(&lock);
+
+	req->callback(req->status, (struct sockaddr *)&req->src_addr,
+		req->addr, req->context);
+	put_client(req->client);
+	kfree(req);
+}
+
 static void process_req(struct work_struct *work)
 {
 	struct addr_req *req, *temp_req;
@@ -591,20 +622,23 @@ static void process_req(struct work_struct *work)
 						   true, req->seq);
 			if (req->status && time_after_eq(jiffies, req->timeout))
 				req->status = -ETIMEDOUT;
-			else if (req->status == -ENODATA)
+			else if (req->status == -ENODATA) {
+				set_timeout(&req->work, req->timeout);
 				continue;
 			}
+		}
 		list_move_tail(&req->list, &done_list);
 	}
 
-	if (!list_empty(&req_list)) {
-		req = list_entry(req_list.next, struct addr_req, list);
-		set_timeout(req->timeout);
-	}
 	mutex_unlock(&lock);
 
 	list_for_each_entry_safe(req, temp_req, &done_list, list) {
 		list_del(&req->list);
+		/* It is safe to cancel other work items from this work item
+		 * because at a time there can be only one work item running
+		 * with this single threaded work queue.
+		 */
+		cancel_delayed_work(&req->work);
 		req->callback(req->status, (struct sockaddr *) &req->src_addr,
 			req->addr, req->context);
 		put_client(req->client);
@@ -647,6 +681,7 @@ int rdma_resolve_ip(struct rdma_addr_client *client,
 	req->context = context;
 	req->client = client;
 	atomic_inc(&client->refcount);
+	INIT_DELAYED_WORK(&req->work, process_one_req);
 	req->seq = (u32)atomic_inc_return(&ib_nl_addr_request_seq);
 
 	req->status = addr_resolve(src_in, dst_in, addr, true, req->seq);
@@ -701,7 +736,7 @@ void rdma_addr_cancel(struct rdma_dev_addr *addr)
 			req->status = -ECANCELED;
 			req->timeout = jiffies;
 			list_move(&req->list, &req_list);
-			set_timeout(req->timeout);
+			set_timeout(&req->work, req->timeout);
 			break;
 		}
 	}
@@ -807,9 +842,8 @@ static int netevent_callback(struct notifier_block *self, unsigned long event,
 	if (event == NETEVENT_NEIGH_UPDATE) {
 		struct neighbour *neigh = ctx;
 
-		if (neigh->nud_state & NUD_VALID) {
-			set_timeout(jiffies);
-		}
+		if (neigh->nud_state & NUD_VALID)
+			set_timeout(&work, jiffies);
 	}
 	return 0;
 }
@@ -820,7 +854,7 @@ static struct notifier_block nb = {
 
 int addr_init(void)
 {
-	addr_wq = alloc_workqueue("ib_addr", WQ_MEM_RECLAIM, 0);
+	addr_wq = alloc_ordered_workqueue("ib_addr", WQ_MEM_RECLAIM);
 	if (!addr_wq)
 		return -ENOMEM;
 

drivers/infiniband/core/uverbs_cmd.c

@@ -1153,7 +1153,7 @@ ssize_t ib_uverbs_resize_cq(struct ib_uverbs_file *file,
 			    int out_len)
 {
 	struct ib_uverbs_resize_cq	cmd;
-	struct ib_uverbs_resize_cq_resp	resp;
+	struct ib_uverbs_resize_cq_resp	resp = {};
 	struct ib_udata                 udata;
 	struct ib_cq			*cq;
 	int				ret = -EINVAL;

drivers/infiniband/core/uverbs_main.c

@@ -250,6 +250,7 @@ void ib_uverbs_release_file(struct kref *ref)
 	if (atomic_dec_and_test(&file->device->refcount))
 		ib_uverbs_comp_dev(file->device);
 
+	kobject_put(&file->device->kobj);
 	kfree(file);
 }
 
@@ -917,7 +918,6 @@ static int ib_uverbs_open(struct inode *inode, struct file *filp)
 static int ib_uverbs_close(struct inode *inode, struct file *filp)
 {
 	struct ib_uverbs_file *file = filp->private_data;
-	struct ib_uverbs_device *dev = file->device;
 
 	mutex_lock(&file->cleanup_mutex);
 	if (file->ucontext) {
@@ -939,7 +939,6 @@ static int ib_uverbs_close(struct inode *inode, struct file *filp)
 			 ib_uverbs_release_async_event_file);
 
 	kref_put(&file->ref, ib_uverbs_release_file);
-	kobject_put(&dev->kobj);
 
 	return 0;
 }

drivers/infiniband/core/verbs.c

@@ -895,7 +895,6 @@ static const struct {
 } qp_state_table[IB_QPS_ERR + 1][IB_QPS_ERR + 1] = {
 	[IB_QPS_RESET] = {
 		[IB_QPS_RESET] = { .valid = 1 },
-		[IB_QPS_ERR] =   { .valid = 1 },
 		[IB_QPS_INIT]  = {
 			.valid = 1,
 			.req_param = {

drivers/infiniband/hw/hns/hns_roce_hw_v1.c

@@ -733,7 +733,7 @@ static int hns_roce_v1_rsv_lp_qp(struct hns_roce_dev *hr_dev)
 			continue;
 
 		free_mr->mr_free_qp[i] = hns_roce_v1_create_lp_qp(hr_dev, pd);
-		if (IS_ERR(free_mr->mr_free_qp[i])) {
+		if (!free_mr->mr_free_qp[i]) {
 			dev_err(dev, "Create loop qp failed!\n");
 			goto create_lp_qp_failed;
 		}

drivers/infiniband/hw/mlx5/odp.c

@@ -939,7 +939,7 @@ static int mlx5_ib_mr_initiator_pfault_handler(
 
 	if (qp->ibqp.qp_type != IB_QPT_RC) {
 		av = *wqe;
-		if (av->dqp_dct & be32_to_cpu(MLX5_WQE_AV_EXT))
+		if (av->dqp_dct & cpu_to_be32(MLX5_EXTENDED_UD_AV))
 			*wqe += sizeof(struct mlx5_av);
 		else
 			*wqe += sizeof(struct mlx5_base_av);

drivers/infiniband/ulp/ipoib/ipoib.h

@@ -336,6 +336,7 @@ struct ipoib_dev_priv {
 	unsigned long flags;
 
 	struct rw_semaphore vlan_rwsem;
+	struct mutex mcast_mutex;
 
 	struct rb_root  path_tree;
 	struct list_head path_list;

drivers/infiniband/ulp/ipoib/ipoib_cm.c

@@ -511,7 +511,6 @@ static int ipoib_cm_rx_handler(struct ib_cm_id *cm_id,
 	case IB_CM_REQ_RECEIVED:
 		return ipoib_cm_req_handler(cm_id, event);
 	case IB_CM_DREQ_RECEIVED:
-		p = cm_id->context;
 		ib_send_cm_drep(cm_id, NULL, 0);
 		/* Fall through */
 	case IB_CM_REJ_RECEIVED:

drivers/infiniband/ulp/ipoib/ipoib_ethtool.c

@@ -52,7 +52,8 @@ static const struct ipoib_stats ipoib_gstrings_stats[] = {
 	IPOIB_NETDEV_STAT(tx_bytes),
 	IPOIB_NETDEV_STAT(tx_errors),
 	IPOIB_NETDEV_STAT(rx_dropped),
-	IPOIB_NETDEV_STAT(tx_dropped)
+	IPOIB_NETDEV_STAT(tx_dropped),
+	IPOIB_NETDEV_STAT(multicast),
 };
 
 #define IPOIB_GLOBAL_STATS_LEN	ARRAY_SIZE(ipoib_gstrings_stats)

drivers/infiniband/ulp/ipoib/ipoib_ib.c

@@ -256,6 +256,8 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 
 	++dev->stats.rx_packets;
 	dev->stats.rx_bytes += skb->len;
+	if (skb->pkt_type == PACKET_MULTICAST)
+		dev->stats.multicast++;
 
 	skb->dev = dev;
 	if ((dev->features & NETIF_F_RXCSUM) &&
@@ -709,6 +711,27 @@ static int recvs_pending(struct net_device *dev)
 	return pending;
 }
 
+static void check_qp_movement_and_print(struct ipoib_dev_priv *priv,
+					struct ib_qp *qp,
+					enum ib_qp_state new_state)
+{
+	struct ib_qp_attr qp_attr;
+	struct ib_qp_init_attr query_init_attr;
+	int ret;
+
+	ret = ib_query_qp(qp, &qp_attr, IB_QP_STATE, &query_init_attr);
+	if (ret) {
+		ipoib_warn(priv, "%s: Failed to query QP\n", __func__);
+		return;
+	}
+	/* print according to the new-state and the previous state.*/
+	if (new_state == IB_QPS_ERR && qp_attr.qp_state == IB_QPS_RESET)
+		ipoib_dbg(priv, "Failed modify QP, IB_QPS_RESET to IB_QPS_ERR, acceptable\n");
+	else
+		ipoib_warn(priv, "Failed to modify QP to state: %d from state: %d\n",
+			   new_state, qp_attr.qp_state);
+}
+
 int ipoib_ib_dev_stop_default(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
@@ -728,7 +751,7 @@ int ipoib_ib_dev_stop_default(struct net_device *dev)
 	 */
 	qp_attr.qp_state = IB_QPS_ERR;
 	if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE))
-		ipoib_warn(priv, "Failed to modify QP to ERROR state\n");
+		check_qp_movement_and_print(priv, priv->qp, IB_QPS_ERR);
 
 	/* Wait for all sends and receives to complete */
 	begin = jiffies;

drivers/infiniband/ulp/ipoib/ipoib_main.c

@@ -1560,6 +1560,7 @@ static void ipoib_flush_neighs(struct ipoib_dev_priv *priv)
 	int i, wait_flushed = 0;
 
 	init_completion(&priv->ntbl.flushed);
+	set_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags);
 
 	spin_lock_irqsave(&priv->lock, flags);
 
@@ -1604,7 +1605,6 @@ static void ipoib_neigh_hash_uninit(struct net_device *dev)
 
 	ipoib_dbg(priv, "ipoib_neigh_hash_uninit\n");
 	init_completion(&priv->ntbl.deleted);
-	set_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags);
 
 	/* Stop GC if called at init fail need to cancel work */
 	stopped = test_and_set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
@@ -1847,6 +1847,7 @@ static const struct net_device_ops ipoib_netdev_ops_vf = {
 	.ndo_tx_timeout		 = ipoib_timeout,
 	.ndo_set_rx_mode	 = ipoib_set_mcast_list,
 	.ndo_get_iflink		 = ipoib_get_iflink,
+	.ndo_get_stats64	 = ipoib_get_stats,
 };
 
 void ipoib_setup_common(struct net_device *dev)
@@ -1877,6 +1878,7 @@ static void ipoib_build_priv(struct net_device *dev)
 	priv->dev = dev;
 	spin_lock_init(&priv->lock);
 	init_rwsem(&priv->vlan_rwsem);
+	mutex_init(&priv->mcast_mutex);
 
 	INIT_LIST_HEAD(&priv->path_list);
 	INIT_LIST_HEAD(&priv->child_intfs);
@@ -2173,14 +2175,14 @@ static struct net_device *ipoib_add_port(const char *format,
 	priv->dev->dev_id = port - 1;
 
 	result = ib_query_port(hca, port, &attr);
-	if (!result)
-		priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu);
-	else {
+	if (result) {
 		printk(KERN_WARNING "%s: ib_query_port %d failed\n",
 		       hca->name, port);
 		goto device_init_failed;
 	}
 
+	priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu);
+
 	/* MTU will be reset when mcast join happens */
 	priv->dev->mtu  = IPOIB_UD_MTU(priv->max_ib_mtu);
 	priv->mcast_mtu  = priv->admin_mtu = priv->dev->mtu;
@@ -2211,12 +2213,14 @@ static struct net_device *ipoib_add_port(const char *format,
 		printk(KERN_WARNING "%s: ib_query_gid port %d failed (ret = %d)\n",
 		       hca->name, port, result);
 		goto device_init_failed;
-	} else
-		memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, sizeof (union ib_gid));
+	}
+
+	memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw,
+	       sizeof(union ib_gid));
 	set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags);
 
 	result = ipoib_dev_init(priv->dev, hca, port);
-	if (result < 0) {
+	if (result) {
 		printk(KERN_WARNING "%s: failed to initialize port %d (ret = %d)\n",
 		       hca->name, port, result);
 		goto device_init_failed;
@@ -2365,6 +2369,7 @@ static int __init ipoib_init_module(void)
 	ipoib_sendq_size = max3(ipoib_sendq_size, 2 * MAX_SEND_CQE, IPOIB_MIN_QUEUE_SIZE);
 #ifdef CONFIG_INFINIBAND_IPOIB_CM
 	ipoib_max_conn_qp = min(ipoib_max_conn_qp, IPOIB_CM_MAX_CONN_QP);
+	ipoib_max_conn_qp = max(ipoib_max_conn_qp, 0);
 #endif
 
 	/*

drivers/infiniband/ulp/ipoib/ipoib_multicast.c

@@ -684,15 +684,10 @@ void ipoib_mcast_start_thread(struct net_device *dev)
 int ipoib_mcast_stop_thread(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
-	unsigned long flags;
 
 	ipoib_dbg_mcast(priv, "stopping multicast thread\n");
 
-	spin_lock_irqsave(&priv->lock, flags);
-	cancel_delayed_work(&priv->mcast_task);
-	spin_unlock_irqrestore(&priv->lock, flags);
-
-	flush_workqueue(priv->wq);
+	cancel_delayed_work_sync(&priv->mcast_task);
 
 	return 0;
 }
@@ -748,6 +743,14 @@ void ipoib_mcast_remove_list(struct list_head *remove_list)
 {
 	struct ipoib_mcast *mcast, *tmcast;
 
+	/*
+	 * make sure the in-flight joins have finished before we attempt
+	 * to leave
+	 */
+	list_for_each_entry_safe(mcast, tmcast, remove_list, list)
+		if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
+			wait_for_completion(&mcast->done);
+
 	list_for_each_entry_safe(mcast, tmcast, remove_list, list) {
 		ipoib_mcast_leave(mcast->dev, mcast);
 		ipoib_mcast_free(mcast);
@@ -838,6 +841,7 @@ void ipoib_mcast_dev_flush(struct net_device *dev)
 	struct ipoib_mcast *mcast, *tmcast;
 	unsigned long flags;
 
+	mutex_lock(&priv->mcast_mutex);
 	ipoib_dbg_mcast(priv, "flushing multicast list\n");
 
 	spin_lock_irqsave(&priv->lock, flags);
@@ -856,15 +860,8 @@ void ipoib_mcast_dev_flush(struct net_device *dev)
 
 	spin_unlock_irqrestore(&priv->lock, flags);
 
-	/*
-	 * make sure the in-flight joins have finished before we attempt
-	 * to leave
-	 */
-	list_for_each_entry_safe(mcast, tmcast, &remove_list, list)
-		if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
-			wait_for_completion(&mcast->done);
-
 	ipoib_mcast_remove_list(&remove_list);
+	mutex_unlock(&priv->mcast_mutex);
 }
 
 static int ipoib_mcast_addr_is_valid(const u8 *addr, const u8 *broadcast)
@@ -982,14 +979,6 @@ void ipoib_mcast_restart_task(struct work_struct *work)
 	netif_addr_unlock(dev);
 	local_irq_restore(flags);
 
-	/*
-	 * make sure the in-flight joins have finished before we attempt
-	 * to leave
-	 */
-	list_for_each_entry_safe(mcast, tmcast, &remove_list, list)
-		if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
-			wait_for_completion(&mcast->done);
-
 	ipoib_mcast_remove_list(&remove_list);
 
 	/*

include/linux/mlx5/qp.h

@@ -212,7 +212,6 @@ struct mlx5_wqe_ctrl_seg {
 #define MLX5_WQE_CTRL_OPCODE_MASK 0xff
 #define MLX5_WQE_CTRL_WQE_INDEX_MASK 0x00ffff00
 #define MLX5_WQE_CTRL_WQE_INDEX_SHIFT 8
-#define MLX5_WQE_AV_EXT 0x80000000
 
 enum {
 	MLX5_ETH_WQE_L3_INNER_CSUM      = 1 << 4,