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

Pull rdma fixes from Jason Gunthorpe:
 "Several regression fixes from work that landed in the merge window,
  particularly in the mlx5 driver:

   - Various static checker and warning fixes

   - General bug fixes in rvt, qedr, hns, mlx5 and hfi1

   - Several regression fixes related to the ECE and QP changes in last
     cycle

   - Fixes for a few long standing crashers in CMA, uverbs ioctl, and
     xrc"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (25 commits)
  IB/hfi1: Add atomic triggered sleep/wakeup
  IB/hfi1: Correct -EBUSY handling in tx code
  IB/hfi1: Fix module use count flaw due to leftover module put calls
  IB/hfi1: Restore kfree in dummy_netdev cleanup
  IB/mad: Fix use after free when destroying MAD agent
  RDMA/mlx5: Protect from kernel crash if XRC_TGT doesn't have udata
  RDMA/counter: Query a counter before release
  RDMA/mad: Fix possible memory leak in ib_mad_post_receive_mads()
  RDMA/mlx5: Fix integrity enabled QP creation
  RDMA/mlx5: Remove ECE limitation from the RAW_PACKET QPs
  RDMA/mlx5: Fix remote gid value in query QP
  RDMA/mlx5: Don't access ib_qp fields in internal destroy QP path
  RDMA/core: Check that type_attrs is not NULL prior access
  RDMA/hns: Fix an cmd queue issue when resetting
  RDMA/hns: Fix a calltrace when registering MR from userspace
  RDMA/mlx5: Add missed RST2INIT and INIT2INIT steps during ECE handshake
  RDMA/cma: Protect bind_list and listen_list while finding matching cm id
  RDMA/qedr: Fix KASAN: use-after-free in ucma_event_handler+0x532
  RDMA/efa: Set maximum pkeys device attribute
  RDMA/rvt: Fix potential memory leak caused by rvt_alloc_rq
  ...

drivers/infiniband/core/cm.c

@@ -918,6 +918,7 @@ static void cm_free_work(struct cm_work *work)
 
 static void cm_queue_work_unlock(struct cm_id_private *cm_id_priv,
 				 struct cm_work *work)
+	__releases(&cm_id_priv->lock)
 {
 	bool immediate;
 

drivers/infiniband/core/cma.c

@@ -1624,6 +1624,8 @@ static struct rdma_id_private *cma_find_listener(
 {
 	struct rdma_id_private *id_priv, *id_priv_dev;
 
+	lockdep_assert_held(&lock);
+
 	if (!bind_list)
 		return ERR_PTR(-EINVAL);
 
@@ -1670,6 +1672,7 @@ cma_ib_id_from_event(struct ib_cm_id *cm_id,
 		}
 	}
 
+	mutex_lock(&lock);
 	/*
 	 * Net namespace might be getting deleted while route lookup,
 	 * cm_id lookup is in progress. Therefore, perform netdevice
@@ -1711,6 +1714,7 @@ cma_ib_id_from_event(struct ib_cm_id *cm_id,
 	id_priv = cma_find_listener(bind_list, cm_id, ib_event, req, *net_dev);
 err:
 	rcu_read_unlock();
+	mutex_unlock(&lock);
 	if (IS_ERR(id_priv) && *net_dev) {
 		dev_put(*net_dev);
 		*net_dev = NULL;
@@ -2492,6 +2496,8 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv,
 	struct net *net = id_priv->id.route.addr.dev_addr.net;
 	int ret;
 
+	lockdep_assert_held(&lock);
+
 	if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1))
 		return;
 
@@ -3342,6 +3348,8 @@ static void cma_bind_port(struct rdma_bind_list *bind_list,
 	u64 sid, mask;
 	__be16 port;
 
+	lockdep_assert_held(&lock);
+
 	addr = cma_src_addr(id_priv);
 	port = htons(bind_list->port);
 
@@ -3370,6 +3378,8 @@ static int cma_alloc_port(enum rdma_ucm_port_space ps,
 	struct rdma_bind_list *bind_list;
 	int ret;
 
+	lockdep_assert_held(&lock);
+
 	bind_list = kzalloc(sizeof *bind_list, GFP_KERNEL);
 	if (!bind_list)
 		return -ENOMEM;
@@ -3396,6 +3406,8 @@ static int cma_port_is_unique(struct rdma_bind_list *bind_list,
 	struct sockaddr  *saddr = cma_src_addr(id_priv);
 	__be16 dport = cma_port(daddr);
 
+	lockdep_assert_held(&lock);
+
 	hlist_for_each_entry(cur_id, &bind_list->owners, node) {
 		struct sockaddr  *cur_daddr = cma_dst_addr(cur_id);
 		struct sockaddr  *cur_saddr = cma_src_addr(cur_id);
@@ -3435,6 +3447,8 @@ static int cma_alloc_any_port(enum rdma_ucm_port_space ps,
 	unsigned int rover;
 	struct net *net = id_priv->id.route.addr.dev_addr.net;
 
+	lockdep_assert_held(&lock);
+
 	inet_get_local_port_range(net, &low, &high);
 	remaining = (high - low) + 1;
 	rover = prandom_u32() % remaining + low;
@@ -3482,6 +3496,8 @@ static int cma_check_port(struct rdma_bind_list *bind_list,
 	struct rdma_id_private *cur_id;
 	struct sockaddr *addr, *cur_addr;
 
+	lockdep_assert_held(&lock);
+
 	addr = cma_src_addr(id_priv);
 	hlist_for_each_entry(cur_id, &bind_list->owners, node) {
 		if (id_priv == cur_id)
@@ -3512,6 +3528,8 @@ static int cma_use_port(enum rdma_ucm_port_space ps,
 	unsigned short snum;
 	int ret;
 
+	lockdep_assert_held(&lock);
+
 	snum = ntohs(cma_port(cma_src_addr(id_priv)));
 	if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
 		return -EACCES;

drivers/infiniband/core/counters.c

@@ -202,7 +202,7 @@ static int __rdma_counter_unbind_qp(struct ib_qp *qp)
 	return ret;
 }
 
-static void counter_history_stat_update(const struct rdma_counter *counter)
+static void counter_history_stat_update(struct rdma_counter *counter)
 {
 	struct ib_device *dev = counter->device;
 	struct rdma_port_counter *port_counter;
@@ -212,6 +212,8 @@ static void counter_history_stat_update(const struct rdma_counter *counter)
 	if (!port_counter->hstats)
 		return;
 
+	rdma_counter_query_stats(counter);
+
 	for (i = 0; i < counter->stats->num_counters; i++)
 		port_counter->hstats->value[i] += counter->stats->value[i];
 }

drivers/infiniband/core/mad.c

@@ -509,10 +509,10 @@ static void unregister_mad_agent(struct ib_mad_agent_private *mad_agent_priv)
 	xa_erase(&ib_mad_clients, mad_agent_priv->agent.hi_tid);
 
 	flush_workqueue(port_priv->wq);
-	ib_cancel_rmpp_recvs(mad_agent_priv);
 
 	deref_mad_agent(mad_agent_priv);
 	wait_for_completion(&mad_agent_priv->comp);
+	ib_cancel_rmpp_recvs(mad_agent_priv);
 
 	ib_mad_agent_security_cleanup(&mad_agent_priv->agent);
 
@@ -2718,6 +2718,7 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 						 DMA_FROM_DEVICE);
 		if (unlikely(ib_dma_mapping_error(qp_info->port_priv->device,
 						  sg_list.addr))) {
+			kfree(mad_priv);
 			ret = -ENOMEM;
 			break;
 		}

drivers/infiniband/core/rdma_core.c

@@ -470,40 +470,46 @@ static struct ib_uobject *
 alloc_begin_fd_uobject(const struct uverbs_api_object *obj,
 		       struct uverbs_attr_bundle *attrs)
 {
-	const struct uverbs_obj_fd_type *fd_type =
-		container_of(obj->type_attrs, struct uverbs_obj_fd_type, type);
+	const struct uverbs_obj_fd_type *fd_type;
 	int new_fd;
-	struct ib_uobject *uobj;
+	struct ib_uobject *uobj, *ret;
 	struct file *filp;
 
+	uobj = alloc_uobj(attrs, obj);
+	if (IS_ERR(uobj))
+		return uobj;
+
+	fd_type =
+		container_of(obj->type_attrs, struct uverbs_obj_fd_type, type);
 	if (WARN_ON(fd_type->fops->release != &uverbs_uobject_fd_release &&
-		    fd_type->fops->release != &uverbs_async_event_release))
-		return ERR_PTR(-EINVAL);
+		    fd_type->fops->release != &uverbs_async_event_release)) {
+		ret = ERR_PTR(-EINVAL);
+		goto err_fd;
+	}
 
 	new_fd = get_unused_fd_flags(O_CLOEXEC);
-	if (new_fd < 0)
-		return ERR_PTR(new_fd);
-
-	uobj = alloc_uobj(attrs, obj);
-	if (IS_ERR(uobj))
+	if (new_fd < 0) {
+		ret = ERR_PTR(new_fd);
 		goto err_fd;
+	}
 
 	/* Note that uverbs_uobject_fd_release() is called during abort */
 	filp = anon_inode_getfile(fd_type->name, fd_type->fops, NULL,
 				  fd_type->flags);
 	if (IS_ERR(filp)) {
-		uverbs_uobject_put(uobj);
-		uobj = ERR_CAST(filp);
-		goto err_fd;
+		ret = ERR_CAST(filp);
+		goto err_getfile;
 	}
 	uobj->object = filp;
 
 	uobj->id = new_fd;
 	return uobj;
 
-err_fd:
+err_getfile:
 	put_unused_fd(new_fd);
-	return uobj;
+err_fd:
+	uverbs_uobject_put(uobj);
+	return ret;
 }
 
 struct ib_uobject *rdma_alloc_begin_uobject(const struct uverbs_api_object *obj,

drivers/infiniband/hw/efa/efa_verbs.c

@@ -212,6 +212,7 @@ int efa_query_device(struct ib_device *ibdev,
 	props->max_send_sge = dev_attr->max_sq_sge;
 	props->max_recv_sge = dev_attr->max_rq_sge;
 	props->max_sge_rd = dev_attr->max_wr_rdma_sge;
+	props->max_pkeys = 1;
 
 	if (udata && udata->outlen) {
 		resp.max_sq_sge = dev_attr->max_sq_sge;

drivers/infiniband/hw/hfi1/debugfs.c

@@ -985,15 +985,10 @@ static ssize_t qsfp2_debugfs_read(struct file *file, char __user *buf,
 static int __i2c_debugfs_open(struct inode *in, struct file *fp, u32 target)
 {
 	struct hfi1_pportdata *ppd;
-	int ret;
 
 	ppd = private2ppd(fp);
 
-	ret = acquire_chip_resource(ppd->dd, i2c_target(target), 0);
-	if (ret) /* failed - release the module */
-		module_put(THIS_MODULE);
-
-	return ret;
+	return acquire_chip_resource(ppd->dd, i2c_target(target), 0);
 }
 
 static int i2c1_debugfs_open(struct inode *in, struct file *fp)
@@ -1013,7 +1008,6 @@ static int __i2c_debugfs_release(struct inode *in, struct file *fp, u32 target)
 	ppd = private2ppd(fp);
 
 	release_chip_resource(ppd->dd, i2c_target(target));
-	module_put(THIS_MODULE);
 
 	return 0;
 }
@@ -1031,18 +1025,10 @@ static int i2c2_debugfs_release(struct inode *in, struct file *fp)
 static int __qsfp_debugfs_open(struct inode *in, struct file *fp, u32 target)
 {
 	struct hfi1_pportdata *ppd;
-	int ret;
-
-	if (!try_module_get(THIS_MODULE))
-		return -ENODEV;
 
 	ppd = private2ppd(fp);
 
-	ret = acquire_chip_resource(ppd->dd, i2c_target(target), 0);
-	if (ret) /* failed - release the module */
-		module_put(THIS_MODULE);
-
-	return ret;
+	return acquire_chip_resource(ppd->dd, i2c_target(target), 0);
 }
 
 static int qsfp1_debugfs_open(struct inode *in, struct file *fp)
@@ -1062,7 +1048,6 @@ static int __qsfp_debugfs_release(struct inode *in, struct file *fp, u32 target)
 	ppd = private2ppd(fp);
 
 	release_chip_resource(ppd->dd, i2c_target(target));
-	module_put(THIS_MODULE);
 
 	return 0;
 }

drivers/infiniband/hw/hfi1/iowait.h

@@ -399,7 +399,7 @@ static inline void iowait_get_priority(struct iowait *w)
  * @wait_head: the wait queue
  *
  * This function is called to insert an iowait struct into a
- * wait queue after a resource (eg, sdma decriptor or pio
+ * wait queue after a resource (eg, sdma descriptor or pio
  * buffer) is run out.
  */
 static inline void iowait_queue(bool pkts_sent, struct iowait *w,

drivers/infiniband/hw/hfi1/ipoib.h

@@ -67,6 +67,9 @@ struct hfi1_ipoib_circ_buf {
  * @sde: sdma engine
  * @tx_list: tx request list
  * @sent_txreqs: count of txreqs posted to sdma
+ * @stops: count of stops of queue
+ * @ring_full: ring has been filled
+ * @no_desc: descriptor shortage seen
  * @flow: tracks when list needs to be flushed for a flow change
  * @q_idx: ipoib Tx queue index
  * @pkts_sent: indicator packets have been sent from this queue
@@ -80,6 +83,9 @@ struct hfi1_ipoib_txq {
 	struct sdma_engine *sde;
 	struct list_head tx_list;
 	u64 sent_txreqs;
+	atomic_t stops;
+	atomic_t ring_full;
+	atomic_t no_desc;
 	union hfi1_ipoib_flow flow;
 	u8 q_idx;
 	bool pkts_sent;

drivers/infiniband/hw/hfi1/ipoib_tx.c

@@ -55,23 +55,48 @@ static u64 hfi1_ipoib_txreqs(const u64 sent, const u64 completed)
 	return sent - completed;
 }
 
-static void hfi1_ipoib_check_queue_depth(struct hfi1_ipoib_txq *txq)
+static u64 hfi1_ipoib_used(struct hfi1_ipoib_txq *txq)
 {
-	if (unlikely(hfi1_ipoib_txreqs(++txq->sent_txreqs,
-				       atomic64_read(&txq->complete_txreqs)) >=
-	    min_t(unsigned int, txq->priv->netdev->tx_queue_len,
-		  txq->tx_ring.max_items - 1)))
+	return hfi1_ipoib_txreqs(txq->sent_txreqs,
+				 atomic64_read(&txq->complete_txreqs));
+}
+
+static void hfi1_ipoib_stop_txq(struct hfi1_ipoib_txq *txq)
+{
+	if (atomic_inc_return(&txq->stops) == 1)
 		netif_stop_subqueue(txq->priv->netdev, txq->q_idx);
 }
 
+static void hfi1_ipoib_wake_txq(struct hfi1_ipoib_txq *txq)
+{
+	if (atomic_dec_and_test(&txq->stops))
+		netif_wake_subqueue(txq->priv->netdev, txq->q_idx);
+}
+
+static uint hfi1_ipoib_ring_hwat(struct hfi1_ipoib_txq *txq)
+{
+	return min_t(uint, txq->priv->netdev->tx_queue_len,
+		     txq->tx_ring.max_items - 1);
+}
+
+static uint hfi1_ipoib_ring_lwat(struct hfi1_ipoib_txq *txq)
+{
+	return min_t(uint, txq->priv->netdev->tx_queue_len,
+		     txq->tx_ring.max_items) >> 1;
+}
+
+static void hfi1_ipoib_check_queue_depth(struct hfi1_ipoib_txq *txq)
+{
+	++txq->sent_txreqs;
+	if (hfi1_ipoib_used(txq) >= hfi1_ipoib_ring_hwat(txq) &&
+	    !atomic_xchg(&txq->ring_full, 1))
+		hfi1_ipoib_stop_txq(txq);
+}
+
 static void hfi1_ipoib_check_queue_stopped(struct hfi1_ipoib_txq *txq)
 {
 	struct net_device *dev = txq->priv->netdev;
 
-	/* If the queue is already running just return */
-	if (likely(!__netif_subqueue_stopped(dev, txq->q_idx)))
-		return;
-
 	/* If shutting down just return as queue state is irrelevant */
 	if (unlikely(dev->reg_state != NETREG_REGISTERED))
 		return;
@@ -86,11 +111,9 @@ static void hfi1_ipoib_check_queue_stopped(struct hfi1_ipoib_txq *txq)
 	 * Use the minimum of the current tx_queue_len or the rings max txreqs
 	 * to protect against ring overflow.
 	 */
-	if (hfi1_ipoib_txreqs(txq->sent_txreqs,
-			      atomic64_read(&txq->complete_txreqs))
-	    < min_t(unsigned int, dev->tx_queue_len,
-		    txq->tx_ring.max_items) >> 1)
-		netif_wake_subqueue(dev, txq->q_idx);
+	if (hfi1_ipoib_used(txq) < hfi1_ipoib_ring_lwat(txq) &&
+	    atomic_xchg(&txq->ring_full, 0))
+		hfi1_ipoib_wake_txq(txq);
 }
 
 static void hfi1_ipoib_free_tx(struct ipoib_txreq *tx, int budget)
@@ -364,11 +387,12 @@ static struct ipoib_txreq *hfi1_ipoib_send_dma_common(struct net_device *dev,
 	if (unlikely(!tx))
 		return ERR_PTR(-ENOMEM);
 
-	/* so that we can test if the sdma decriptors are there */
+	/* so that we can test if the sdma descriptors are there */
 	tx->txreq.num_desc = 0;
 	tx->priv = priv;
 	tx->txq = txp->txq;
 	tx->skb = skb;
+	INIT_LIST_HEAD(&tx->txreq.list);
 
 	hfi1_ipoib_build_ib_tx_headers(tx, txp);
 
@@ -469,6 +493,7 @@ static int hfi1_ipoib_send_dma_single(struct net_device *dev,
 
 	ret = hfi1_ipoib_submit_tx(txq, tx);
 	if (likely(!ret)) {
+tx_ok:
 		trace_sdma_output_ibhdr(tx->priv->dd,
 					&tx->sdma_hdr.hdr,
 					ib_is_sc5(txp->flow.sc5));
@@ -478,20 +503,8 @@ static int hfi1_ipoib_send_dma_single(struct net_device *dev,
 
 	txq->pkts_sent = false;
 
-	if (ret == -EBUSY) {
-		list_add_tail(&tx->txreq.list, &txq->tx_list);
-
-		trace_sdma_output_ibhdr(tx->priv->dd,
-					&tx->sdma_hdr.hdr,
-					ib_is_sc5(txp->flow.sc5));
-		hfi1_ipoib_check_queue_depth(txq);
-		return NETDEV_TX_OK;
-	}
-
-	if (ret == -ECOMM) {
-		hfi1_ipoib_check_queue_depth(txq);
-		return NETDEV_TX_OK;
-	}
+	if (ret == -EBUSY || ret == -ECOMM)
+		goto tx_ok;
 
 	sdma_txclean(priv->dd, &tx->txreq);
 	dev_kfree_skb_any(skb);
@@ -509,9 +522,17 @@ static int hfi1_ipoib_send_dma_list(struct net_device *dev,
 	struct ipoib_txreq *tx;
 
 	/* Has the flow change ? */
-	if (txq->flow.as_int != txp->flow.as_int)
-		(void)hfi1_ipoib_flush_tx_list(dev, txq);
-
+	if (txq->flow.as_int != txp->flow.as_int) {
+		int ret;
+
+		ret = hfi1_ipoib_flush_tx_list(dev, txq);
+		if (unlikely(ret)) {
+			if (ret == -EBUSY)
+				++dev->stats.tx_dropped;
+			dev_kfree_skb_any(skb);
+			return NETDEV_TX_OK;
+		}
+	}
 	tx = hfi1_ipoib_send_dma_common(dev, skb, txp);
 	if (IS_ERR(tx)) {
 		int ret = PTR_ERR(tx);
@@ -610,10 +631,14 @@ static int hfi1_ipoib_sdma_sleep(struct sdma_engine *sde,
 			return -EAGAIN;
 		}
 
-		netif_stop_subqueue(txq->priv->netdev, txq->q_idx);
-
-		if (list_empty(&txq->wait.list))
+		if (list_empty(&txreq->list))
+			/* came from non-list submit */
+			list_add_tail(&txreq->list, &txq->tx_list);
+		if (list_empty(&txq->wait.list)) {
+			if (!atomic_xchg(&txq->no_desc, 1))
+				hfi1_ipoib_stop_txq(txq);
 			iowait_queue(pkts_sent, wait->iow, &sde->dmawait);
+		}
 
 		write_sequnlock(&sde->waitlock);
 		return -EBUSY;
@@ -648,9 +673,9 @@ static void hfi1_ipoib_flush_txq(struct work_struct *work)
 	struct net_device *dev = txq->priv->netdev;
 
 	if (likely(dev->reg_state == NETREG_REGISTERED) &&
-	    likely(__netif_subqueue_stopped(dev, txq->q_idx)) &&
 	    likely(!hfi1_ipoib_flush_tx_list(dev, txq)))
-		netif_wake_subqueue(dev, txq->q_idx);
+		if (atomic_xchg(&txq->no_desc, 0))
+			hfi1_ipoib_wake_txq(txq);
 }
 
 int hfi1_ipoib_txreq_init(struct hfi1_ipoib_dev_priv *priv)
@@ -704,6 +729,9 @@ int hfi1_ipoib_txreq_init(struct hfi1_ipoib_dev_priv *priv)
 		txq->sde = NULL;
 		INIT_LIST_HEAD(&txq->tx_list);
 		atomic64_set(&txq->complete_txreqs, 0);
+		atomic_set(&txq->stops, 0);
+		atomic_set(&txq->ring_full, 0);
+		atomic_set(&txq->no_desc, 0);
 		txq->q_idx = i;
 		txq->flow.tx_queue = 0xff;
 		txq->flow.sc5 = 0xff;
@@ -769,7 +797,7 @@ static void hfi1_ipoib_drain_tx_list(struct hfi1_ipoib_txq *txq)
 		atomic64_inc(complete_txreqs);
 	}
 
-	if (hfi1_ipoib_txreqs(txq->sent_txreqs, atomic64_read(complete_txreqs)))
+	if (hfi1_ipoib_used(txq))
 		dd_dev_warn(txq->priv->dd,
 			    "txq %d not empty found %llu requests\n",
 			    txq->q_idx,

drivers/infiniband/hw/hfi1/netdev_rx.c

@@ -373,7 +373,7 @@ void hfi1_netdev_free(struct hfi1_devdata *dd)
 {
 	if (dd->dummy_netdev) {
 		dd_dev_info(dd, "hfi1 netdev freed\n");
-		free_netdev(dd->dummy_netdev);
+		kfree(dd->dummy_netdev);
 		dd->dummy_netdev = NULL;
 	}
 }

drivers/infiniband/hw/hfi1/verbs_txreq.h

@@ -91,7 +91,7 @@ static inline struct verbs_txreq *get_txreq(struct hfi1_ibdev *dev,
 	tx->mr = NULL;
 	tx->sde = priv->s_sde;
 	tx->psc = priv->s_sendcontext;
-	/* so that we can test if the sdma decriptors are there */
+	/* so that we can test if the sdma descriptors are there */
 	tx->txreq.num_desc = 0;
 	/* Set the header type */
 	tx->phdr.hdr.hdr_type = priv->hdr_type;

drivers/infiniband/hw/hns/hns_roce_device.h

@@ -898,13 +898,14 @@ struct hns_roce_hw {
 	int (*set_mac)(struct hns_roce_dev *hr_dev, u8 phy_port, u8 *addr);
 	void (*set_mtu)(struct hns_roce_dev *hr_dev, u8 phy_port,
 			enum ib_mtu mtu);
-	int (*write_mtpt)(void *mb_buf, struct hns_roce_mr *mr,
-			  unsigned long mtpt_idx);
+	int (*write_mtpt)(struct hns_roce_dev *hr_dev, void *mb_buf,
+			  struct hns_roce_mr *mr, unsigned long mtpt_idx);
 	int (*rereg_write_mtpt)(struct hns_roce_dev *hr_dev,
 				struct hns_roce_mr *mr, int flags, u32 pdn,
 				int mr_access_flags, u64 iova, u64 size,
 				void *mb_buf);
-	int (*frmr_write_mtpt)(void *mb_buf, struct hns_roce_mr *mr);
+	int (*frmr_write_mtpt)(struct hns_roce_dev *hr_dev, void *mb_buf,
+			       struct hns_roce_mr *mr);
 	int (*mw_write_mtpt)(void *mb_buf, struct hns_roce_mw *mw);
 	void (*write_cqc)(struct hns_roce_dev *hr_dev,
 			  struct hns_roce_cq *hr_cq, void *mb_buf, u64 *mtts,

drivers/infiniband/hw/hns/hns_roce_hw_v1.c

@@ -1756,10 +1756,10 @@ static void hns_roce_v1_set_mtu(struct hns_roce_dev *hr_dev, u8 phy_port,
 		   val);
 }
 
-static int hns_roce_v1_write_mtpt(void *mb_buf, struct hns_roce_mr *mr,
+static int hns_roce_v1_write_mtpt(struct hns_roce_dev *hr_dev, void *mb_buf,
+				  struct hns_roce_mr *mr,
 				  unsigned long mtpt_idx)
 {
-	struct hns_roce_dev *hr_dev = to_hr_dev(mr->ibmr.device);
 	u64 pages[HNS_ROCE_MAX_INNER_MTPT_NUM] = { 0 };
 	struct ib_device *ibdev = &hr_dev->ib_dev;
 	struct hns_roce_v1_mpt_entry *mpt_entry;

drivers/infiniband/hw/hns/hns_roce_hw_v2.c

@@ -910,7 +910,7 @@ static int hns_roce_v2_rst_process_cmd(struct hns_roce_dev *hr_dev)
 	instance_stage = handle->rinfo.instance_state;
 	reset_stage = handle->rinfo.reset_state;
 	reset_cnt = ops->ae_dev_reset_cnt(handle);
-	hw_resetting = ops->get_hw_reset_stat(handle);
+	hw_resetting = ops->get_cmdq_stat(handle);
 	sw_resetting = ops->ae_dev_resetting(handle);
 
 	if (reset_cnt != hr_dev->reset_cnt)
@@ -2529,10 +2529,10 @@ static int hns_roce_v2_set_mac(struct hns_roce_dev *hr_dev, u8 phy_port,
 	return hns_roce_cmq_send(hr_dev, &desc, 1);
 }
 
-static int set_mtpt_pbl(struct hns_roce_v2_mpt_entry *mpt_entry,
+static int set_mtpt_pbl(struct hns_roce_dev *hr_dev,
+			struct hns_roce_v2_mpt_entry *mpt_entry,
 			struct hns_roce_mr *mr)
 {
-	struct hns_roce_dev *hr_dev = to_hr_dev(mr->ibmr.device);
 	u64 pages[HNS_ROCE_V2_MAX_INNER_MTPT_NUM] = { 0 };
 	struct ib_device *ibdev = &hr_dev->ib_dev;
 	dma_addr_t pbl_ba;
@@ -2571,7 +2571,8 @@ static int set_mtpt_pbl(struct hns_roce_v2_mpt_entry *mpt_entry,
 	return 0;
 }
 
-static int hns_roce_v2_write_mtpt(void *mb_buf, struct hns_roce_mr *mr,
+static int hns_roce_v2_write_mtpt(struct hns_roce_dev *hr_dev,
+				  void *mb_buf, struct hns_roce_mr *mr,
 				  unsigned long mtpt_idx)
 {
 	struct hns_roce_v2_mpt_entry *mpt_entry;
@@ -2620,7 +2621,7 @@ static int hns_roce_v2_write_mtpt(void *mb_buf, struct hns_roce_mr *mr,
 	if (mr->type == MR_TYPE_DMA)
 		return 0;
 
-	ret = set_mtpt_pbl(mpt_entry, mr);
+	ret = set_mtpt_pbl(hr_dev, mpt_entry, mr);
 
 	return ret;
 }
@@ -2666,15 +2667,15 @@ static int hns_roce_v2_rereg_write_mtpt(struct hns_roce_dev *hr_dev,
 		mr->iova = iova;
 		mr->size = size;
 
-		ret = set_mtpt_pbl(mpt_entry, mr);
+		ret = set_mtpt_pbl(hr_dev, mpt_entry, mr);
 	}
 
 	return ret;
 }
 
-static int hns_roce_v2_frmr_write_mtpt(void *mb_buf, struct hns_roce_mr *mr)
+static int hns_roce_v2_frmr_write_mtpt(struct hns_roce_dev *hr_dev,
+				       void *mb_buf, struct hns_roce_mr *mr)
 {
-	struct hns_roce_dev *hr_dev = to_hr_dev(mr->ibmr.device);
 	struct ib_device *ibdev = &hr_dev->ib_dev;
 	struct hns_roce_v2_mpt_entry *mpt_entry;
 	dma_addr_t pbl_ba = 0;

drivers/infiniband/hw/hns/hns_roce_mr.c

@@ -180,9 +180,10 @@ static int hns_roce_mr_enable(struct hns_roce_dev *hr_dev,
 	}
 
 	if (mr->type != MR_TYPE_FRMR)
-		ret = hr_dev->hw->write_mtpt(mailbox->buf, mr, mtpt_idx);
+		ret = hr_dev->hw->write_mtpt(hr_dev, mailbox->buf, mr,
+					     mtpt_idx);
 	else
-		ret = hr_dev->hw->frmr_write_mtpt(mailbox->buf, mr);
+		ret = hr_dev->hw->frmr_write_mtpt(hr_dev, mailbox->buf, mr);
 	if (ret) {
 		dev_err(dev, "Write mtpt fail!\n");
 		goto err_page;

drivers/infiniband/hw/mlx5/qp.c

@@ -1862,7 +1862,7 @@ static int create_xrc_tgt_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	if (!in)
 		return -ENOMEM;
 
-	if (MLX5_CAP_GEN(mdev, ece_support))
+	if (MLX5_CAP_GEN(mdev, ece_support) && ucmd)
 		MLX5_SET(create_qp_in, in, ece, ucmd->ece_options);
 	qpc = MLX5_ADDR_OF(create_qp_in, in, qpc);
 
@@ -2341,18 +2341,18 @@ static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	unsigned long flags;
 	int err;
 
-	if (qp->ibqp.rwq_ind_tbl) {
+	if (qp->is_rss) {
 		destroy_rss_raw_qp_tir(dev, qp);
 		return;
 	}
 
-	base = (qp->ibqp.qp_type == IB_QPT_RAW_PACKET ||
+	base = (qp->type == IB_QPT_RAW_PACKET ||
 		qp->flags & IB_QP_CREATE_SOURCE_QPN) ?
-	       &qp->raw_packet_qp.rq.base :
-	       &qp->trans_qp.base;
+		       &qp->raw_packet_qp.rq.base :
+		       &qp->trans_qp.base;
 
 	if (qp->state != IB_QPS_RESET) {
-		if (qp->ibqp.qp_type != IB_QPT_RAW_PACKET &&
+		if (qp->type != IB_QPT_RAW_PACKET &&
 		    !(qp->flags & IB_QP_CREATE_SOURCE_QPN)) {
 			err = mlx5_core_qp_modify(dev, MLX5_CMD_OP_2RST_QP, 0,
 						  NULL, &base->mqp, NULL);
@@ -2368,8 +2368,8 @@ static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 				     base->mqp.qpn);
 	}
 
-	get_cqs(qp->ibqp.qp_type, qp->ibqp.send_cq, qp->ibqp.recv_cq,
-		&send_cq, &recv_cq);
+	get_cqs(qp->type, qp->ibqp.send_cq, qp->ibqp.recv_cq, &send_cq,
+		&recv_cq);
 
 	spin_lock_irqsave(&dev->reset_flow_resource_lock, flags);
 	mlx5_ib_lock_cqs(send_cq, recv_cq);
@@ -2391,7 +2391,7 @@ static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	mlx5_ib_unlock_cqs(send_cq, recv_cq);
 	spin_unlock_irqrestore(&dev->reset_flow_resource_lock, flags);
 
-	if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET ||
+	if (qp->type == IB_QPT_RAW_PACKET ||
 	    qp->flags & IB_QP_CREATE_SOURCE_QPN) {
 		destroy_raw_packet_qp(dev, qp);
 	} else {
@@ -2668,6 +2668,9 @@ static int process_create_flags(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	if (qp_type == IB_QPT_RAW_PACKET && attr->rwq_ind_tbl)
 		return (create_flags) ? -EINVAL : 0;
 
+	process_create_flag(dev, &create_flags,
+			    IB_QP_CREATE_INTEGRITY_EN,
+			    MLX5_CAP_GEN(mdev, sho), qp);
 	process_create_flag(dev, &create_flags,
 			    IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK,
 			    MLX5_CAP_GEN(mdev, block_lb_mc), qp);
@@ -2873,7 +2876,6 @@ static int mlx5_ib_destroy_dct(struct mlx5_ib_qp *mqp)
 static int check_ucmd_data(struct mlx5_ib_dev *dev,
 			   struct mlx5_create_qp_params *params)
 {
-	struct ib_qp_init_attr *attr = params->attr;
 	struct ib_udata *udata = params->udata;
 	size_t size, last;
 	int ret;
@@ -2885,14 +2887,7 @@ static int check_ucmd_data(struct mlx5_ib_dev *dev,
 		 */
 		last = sizeof(struct mlx5_ib_create_qp_rss);
 	else
-		/* IB_QPT_RAW_PACKET doesn't have ECE data */
-		switch (attr->qp_type) {
-		case IB_QPT_RAW_PACKET:
-			last = offsetof(struct mlx5_ib_create_qp, ece_options);
-			break;
-		default:
-			last = offsetof(struct mlx5_ib_create_qp, reserved);
-		}
+		last = offsetof(struct mlx5_ib_create_qp, reserved);
 
 	if (udata->inlen <= last)
 		return 0;
@@ -2907,7 +2902,7 @@ static int check_ucmd_data(struct mlx5_ib_dev *dev,
 	if (!ret)
 		mlx5_ib_dbg(
 			dev,
-			"udata is not cleared, inlen = %lu, ucmd = %lu, last = %lu, size = %lu\n",
+			"udata is not cleared, inlen = %zu, ucmd = %zu, last = %zu, size = %zu\n",
 			udata->inlen, params->ucmd_size, last, size);
 	return ret ? 0 : -EINVAL;
 }
@@ -3002,10 +2997,18 @@ struct ib_qp *mlx5_ib_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attr,
 	return &qp->ibqp;
 
 destroy_qp:
-	if (qp->type == MLX5_IB_QPT_DCT)
+	if (qp->type == MLX5_IB_QPT_DCT) {
 		mlx5_ib_destroy_dct(qp);
-	else
+	} else {
+		/*
+		 * The two lines below are temp solution till QP allocation
+		 * will be moved to be under IB/core responsiblity.
+		 */
+		qp->ibqp.send_cq = attr->send_cq;
+		qp->ibqp.recv_cq = attr->recv_cq;
 		destroy_qp_common(dev, qp, udata);
+	}
+
 	qp = NULL;
 free_qp:
 	kfree(qp);
@@ -4162,8 +4165,6 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 
 		if (udata->outlen < min_resp_len)
 			return -EINVAL;
-		resp.response_length = min_resp_len;
-
 		/*
 		 * If we don't have enough space for the ECE options,
 		 * simply indicate it with resp.response_length.
@@ -4384,8 +4385,7 @@ static void to_rdma_ah_attr(struct mlx5_ib_dev *ibdev,
 				MLX5_GET(ads, path, src_addr_index),
 				MLX5_GET(ads, path, hop_limit),
 				MLX5_GET(ads, path, tclass));
-		memcpy(ah_attr, MLX5_ADDR_OF(ads, path, rgid_rip),
-		       MLX5_FLD_SZ_BYTES(ads, rgid_rip));
+		rdma_ah_set_dgid_raw(ah_attr, MLX5_ADDR_OF(ads, path, rgid_rip));
 	}
 }
 

drivers/infiniband/hw/mlx5/qpc.c

@@ -346,6 +346,9 @@ static int get_ece_from_mbox(void *out, u16 opcode)
 	int ece = 0;
 
 	switch (opcode) {
+	case MLX5_CMD_OP_INIT2INIT_QP:
+		ece = MLX5_GET(init2init_qp_out, out, ece);
+		break;
 	case MLX5_CMD_OP_INIT2RTR_QP:
 		ece = MLX5_GET(init2rtr_qp_out, out, ece);
 		break;
@@ -355,6 +358,9 @@ static int get_ece_from_mbox(void *out, u16 opcode)
 	case MLX5_CMD_OP_RTS2RTS_QP:
 		ece = MLX5_GET(rts2rts_qp_out, out, ece);
 		break;
+	case MLX5_CMD_OP_RST2INIT_QP:
+		ece = MLX5_GET(rst2init_qp_out, out, ece);
+		break;
 	default:
 		break;
 	}
@@ -406,6 +412,7 @@ static int modify_qp_mbox_alloc(struct mlx5_core_dev *dev, u16 opcode, int qpn,
 			return -ENOMEM;
 		MOD_QP_IN_SET_QPC(rst2init_qp, mbox->in, opcode, qpn,
 				  opt_param_mask, qpc, uid);
+		MLX5_SET(rst2init_qp_in, mbox->in, ece, ece);
 		break;
 	case MLX5_CMD_OP_INIT2RTR_QP:
 		if (MBOX_ALLOC(mbox, init2rtr_qp))
@@ -439,6 +446,7 @@ static int modify_qp_mbox_alloc(struct mlx5_core_dev *dev, u16 opcode, int qpn,
 			return -ENOMEM;
 		MOD_QP_IN_SET_QPC(init2init_qp, mbox->in, opcode, qpn,
 				  opt_param_mask, qpc, uid);
+		MLX5_SET(init2init_qp_in, mbox->in, ece, ece);
 		break;
 	default:
 		return -EINVAL;

drivers/infiniband/hw/qedr/qedr_iw_cm.c

@@ -150,8 +150,17 @@ qedr_iw_issue_event(void *context,
 	if (params->cm_info) {
 		event.ird = params->cm_info->ird;
 		event.ord = params->cm_info->ord;
-		event.private_data_len = params->cm_info->private_data_len;
-		event.private_data = (void *)params->cm_info->private_data;
+		/* Only connect_request and reply have valid private data
+		 * the rest of the events this may be left overs from
+		 * connection establishment. CONNECT_REQUEST is issued via
+		 * qedr_iw_mpa_request
+		 */
+		if (event_type == IW_CM_EVENT_CONNECT_REPLY) {
+			event.private_data_len =
+				params->cm_info->private_data_len;
+			event.private_data =
+				(void *)params->cm_info->private_data;
+		}
 	}
 
 	if (ep->cm_id)

drivers/infiniband/sw/rdmavt/qp.c

@@ -1204,7 +1204,7 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd,
 		err = alloc_ud_wq_attr(qp, rdi->dparms.node);
 		if (err) {
 			ret = (ERR_PTR(err));
-			goto bail_driver_priv;
+			goto bail_rq_rvt;
 		}
 
 		if (init_attr->create_flags & IB_QP_CREATE_NETDEV_USE)
@@ -1314,9 +1314,11 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd,
 	rvt_free_qpn(&rdi->qp_dev->qpn_table, qp->ibqp.qp_num);
 
 bail_rq_wq:
-	rvt_free_rq(&qp->r_rq);
 	free_ud_wq_attr(qp);
 
+bail_rq_rvt:
+	rvt_free_rq(&qp->r_rq);
+
 bail_driver_priv:
 	rdi->driver_f.qp_priv_free(rdi, qp);
 

drivers/infiniband/sw/siw/siw_qp_rx.c

@@ -139,7 +139,8 @@ static int siw_rx_pbl(struct siw_rx_stream *srx, int *pbl_idx,
 			break;
 
 		bytes = min(bytes, len);
-		if (siw_rx_kva(srx, (void *)buf_addr, bytes) == bytes) {
+		if (siw_rx_kva(srx, (void *)(uintptr_t)buf_addr, bytes) ==
+		    bytes) {
 			copied += bytes;
 			offset += bytes;
 			len -= bytes;

include/linux/mlx5/mlx5_ifc.h

@@ -4283,7 +4283,8 @@ struct mlx5_ifc_rst2init_qp_out_bits {
 
 	u8         syndrome[0x20];
 
-	u8         reserved_at_40[0x40];
+	u8         reserved_at_40[0x20];
+	u8         ece[0x20];
 };
 
 struct mlx5_ifc_rst2init_qp_in_bits {
@@ -4300,7 +4301,7 @@ struct mlx5_ifc_rst2init_qp_in_bits {
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_at_a0[0x20];
+	u8         ece[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
@@ -6619,7 +6620,8 @@ struct mlx5_ifc_init2init_qp_out_bits {
 
 	u8         syndrome[0x20];
 
-	u8         reserved_at_40[0x40];
+	u8         reserved_at_40[0x20];
+	u8         ece[0x20];
 };
 
 struct mlx5_ifc_init2init_qp_in_bits {
@@ -6636,7 +6638,7 @@ struct mlx5_ifc_init2init_qp_in_bits {
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_at_a0[0x20];
+	u8         ece[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;