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

Pull rdma updates from Doug Ledford:
 "This is the complete update for the rdma stack for this release cycle.

  Most of it is typical driver and core updates, but there is the
  entirely new VMWare pvrdma driver. You may have noticed that there
  were changes in DaveM's pull request to the bnxt Ethernet driver to
  support a RoCE RDMA driver. The bnxt_re driver was tentatively set to
  be pulled in this release cycle, but it simply wasn't ready in time
  and was dropped (a few review comments still to address, and some
  multi-arch build issues like prefetch() not working across all
  arches).

  Summary:

   - shared mlx5 updates with net stack (will drop out on merge if
     Dave's tree has already been merged)

   - driver updates: cxgb4, hfi1, hns-roce, i40iw, mlx4, mlx5, qedr, rxe

   - debug cleanups

   - new connection rejection helpers

   - SRP updates

   - various misc fixes

   - new paravirt driver from vmware"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (210 commits)
  IB: Add vmw_pvrdma driver
  IB/mlx4: fix improper return value
  IB/ocrdma: fix bad initialization
  infiniband: nes: return value of skb_linearize should be handled
  MAINTAINERS: Update Intel RDMA RNIC driver maintainers
  MAINTAINERS: Remove Mitesh Ahuja from emulex maintainers
  IB/core: fix unmap_sg argument
  qede: fix general protection fault may occur on probe
  IB/mthca: Replace pci_pool_alloc by pci_pool_zalloc
  mlx5, calc_sq_size(): Make a debug message more informative
  mlx5: Remove a set-but-not-used variable
  mlx5: Use { } instead of { 0 } to init struct
  IB/srp: Make writing the add_target sysfs attr interruptible
  IB/srp: Make mapping failures easier to debug
  IB/srp: Make login failures easier to debug
  IB/srp: Introduce a local variable in srp_add_one()
  IB/srp: Fix CONFIG_DYNAMIC_DEBUG=n build
  IB/multicast: Check ib_find_pkey() return value
  IPoIB: Avoid reading an uninitialized member variable
  IB/mad: Fix an array index check
  ...

MAINTAINERS

@@ -6515,10 +6515,7 @@ F:	drivers/net/ethernet/intel/*/
 
 INTEL RDMA RNIC DRIVER
 M:     Faisal Latif <faisal.latif@intel.com>
-R:     Chien Tin Tung <chien.tin.tung@intel.com>
-R:     Mustafa Ismail <mustafa.ismail@intel.com>
-R:     Shiraz Saleem <shiraz.saleem@intel.com>
-R:     Tatyana Nikolova <tatyana.e.nikolova@intel.com>
+M:     Shiraz Saleem <shiraz.saleem@intel.com>
 L:     linux-rdma@vger.kernel.org
 S:     Supported
 F:     drivers/infiniband/hw/i40iw/
@@ -11078,7 +11075,6 @@ F:	drivers/net/ethernet/emulex/benet/
 EMULEX ONECONNECT ROCE DRIVER
 M:	Selvin Xavier <selvin.xavier@avagotech.com>
 M:	Devesh Sharma <devesh.sharma@avagotech.com>
-M:	Mitesh Ahuja <mitesh.ahuja@avagotech.com>
 L:	linux-rdma@vger.kernel.org
 W:	http://www.emulex.com
 S:	Supported
@@ -13129,6 +13125,13 @@ S:	Maintained
 F:	drivers/scsi/vmw_pvscsi.c
 F:	drivers/scsi/vmw_pvscsi.h
 
+VMWARE PVRDMA DRIVER
+M:	Adit Ranadive <aditr@vmware.com>
+M:	VMware PV-Drivers <pv-drivers@vmware.com>
+L:	linux-rdma@vger.kernel.org
+S:	Maintained
+F:	drivers/infiniband/hw/vmw_pvrdma/
+
 VOLTAGE AND CURRENT REGULATOR FRAMEWORK
 M:	Liam Girdwood <lgirdwood@gmail.com>
 M:	Mark Brown <broonie@kernel.org>

drivers/infiniband/Kconfig

@@ -73,6 +73,7 @@ source "drivers/infiniband/hw/mlx4/Kconfig"
 source "drivers/infiniband/hw/mlx5/Kconfig"
 source "drivers/infiniband/hw/nes/Kconfig"
 source "drivers/infiniband/hw/ocrdma/Kconfig"
+source "drivers/infiniband/hw/vmw_pvrdma/Kconfig"
 source "drivers/infiniband/hw/usnic/Kconfig"
 source "drivers/infiniband/hw/hns/Kconfig"
 

drivers/infiniband/core/agent.c

@@ -156,7 +156,6 @@ int ib_agent_port_open(struct ib_device *device, int port_num)
 	/* Create new device info */
 	port_priv = kzalloc(sizeof *port_priv, GFP_KERNEL);
 	if (!port_priv) {
-		dev_err(&device->dev, "No memory for ib_agent_port_private\n");
 		ret = -ENOMEM;
 		goto error1;
 	}

drivers/infiniband/core/cache.c

@@ -770,12 +770,8 @@ static int _gid_table_setup_one(struct ib_device *ib_dev)
 	int err = 0;
 
 	table = kcalloc(ib_dev->phys_port_cnt, sizeof(*table), GFP_KERNEL);
-
-	if (!table) {
-		pr_warn("failed to allocate ib gid cache for %s\n",
-			ib_dev->name);
+	if (!table)
 		return -ENOMEM;
-	}
 
 	for (port = 0; port < ib_dev->phys_port_cnt; port++) {
 		u8 rdma_port = port + rdma_start_port(ib_dev);
@@ -1170,14 +1166,13 @@ int ib_cache_setup_one(struct ib_device *device)
 					  GFP_KERNEL);
 	if (!device->cache.pkey_cache ||
 	    !device->cache.lmc_cache) {
-		pr_warn("Couldn't allocate cache for %s\n", device->name);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto free;
 	}
 
 	err = gid_table_setup_one(device);
 	if (err)
-		/* Allocated memory will be cleaned in the release function */
-		return err;
+		goto free;
 
 	for (p = 0; p <= rdma_end_port(device) - rdma_start_port(device); ++p)
 		ib_cache_update(device, p + rdma_start_port(device));
@@ -1192,6 +1187,9 @@ int ib_cache_setup_one(struct ib_device *device)
 
 err:
 	gid_table_cleanup_one(device);
+free:
+	kfree(device->cache.pkey_cache);
+	kfree(device->cache.lmc_cache);
 	return err;
 }
 

drivers/infiniband/core/cm.c

@@ -57,6 +57,54 @@ MODULE_AUTHOR("Sean Hefty");
 MODULE_DESCRIPTION("InfiniBand CM");
 MODULE_LICENSE("Dual BSD/GPL");
 
+static const char * const ibcm_rej_reason_strs[] = {
+	[IB_CM_REJ_NO_QP]			= "no QP",
+	[IB_CM_REJ_NO_EEC]			= "no EEC",
+	[IB_CM_REJ_NO_RESOURCES]		= "no resources",
+	[IB_CM_REJ_TIMEOUT]			= "timeout",
+	[IB_CM_REJ_UNSUPPORTED]			= "unsupported",
+	[IB_CM_REJ_INVALID_COMM_ID]		= "invalid comm ID",
+	[IB_CM_REJ_INVALID_COMM_INSTANCE]	= "invalid comm instance",
+	[IB_CM_REJ_INVALID_SERVICE_ID]		= "invalid service ID",
+	[IB_CM_REJ_INVALID_TRANSPORT_TYPE]	= "invalid transport type",
+	[IB_CM_REJ_STALE_CONN]			= "stale conn",
+	[IB_CM_REJ_RDC_NOT_EXIST]		= "RDC not exist",
+	[IB_CM_REJ_INVALID_GID]			= "invalid GID",
+	[IB_CM_REJ_INVALID_LID]			= "invalid LID",
+	[IB_CM_REJ_INVALID_SL]			= "invalid SL",
+	[IB_CM_REJ_INVALID_TRAFFIC_CLASS]	= "invalid traffic class",
+	[IB_CM_REJ_INVALID_HOP_LIMIT]		= "invalid hop limit",
+	[IB_CM_REJ_INVALID_PACKET_RATE]		= "invalid packet rate",
+	[IB_CM_REJ_INVALID_ALT_GID]		= "invalid alt GID",
+	[IB_CM_REJ_INVALID_ALT_LID]		= "invalid alt LID",
+	[IB_CM_REJ_INVALID_ALT_SL]		= "invalid alt SL",
+	[IB_CM_REJ_INVALID_ALT_TRAFFIC_CLASS]	= "invalid alt traffic class",
+	[IB_CM_REJ_INVALID_ALT_HOP_LIMIT]	= "invalid alt hop limit",
+	[IB_CM_REJ_INVALID_ALT_PACKET_RATE]	= "invalid alt packet rate",
+	[IB_CM_REJ_PORT_CM_REDIRECT]		= "port CM redirect",
+	[IB_CM_REJ_PORT_REDIRECT]		= "port redirect",
+	[IB_CM_REJ_INVALID_MTU]			= "invalid MTU",
+	[IB_CM_REJ_INSUFFICIENT_RESP_RESOURCES]	= "insufficient resp resources",
+	[IB_CM_REJ_CONSUMER_DEFINED]		= "consumer defined",
+	[IB_CM_REJ_INVALID_RNR_RETRY]		= "invalid RNR retry",
+	[IB_CM_REJ_DUPLICATE_LOCAL_COMM_ID]	= "duplicate local comm ID",
+	[IB_CM_REJ_INVALID_CLASS_VERSION]	= "invalid class version",
+	[IB_CM_REJ_INVALID_FLOW_LABEL]		= "invalid flow label",
+	[IB_CM_REJ_INVALID_ALT_FLOW_LABEL]	= "invalid alt flow label",
+};
+
+const char *__attribute_const__ ibcm_reject_msg(int reason)
+{
+	size_t index = reason;
+
+	if (index < ARRAY_SIZE(ibcm_rej_reason_strs) &&
+	    ibcm_rej_reason_strs[index])
+		return ibcm_rej_reason_strs[index];
+	else
+		return "unrecognized reason";
+}
+EXPORT_SYMBOL(ibcm_reject_msg);
+
 static void cm_add_one(struct ib_device *device);
 static void cm_remove_one(struct ib_device *device, void *client_data);
 
@@ -1582,6 +1630,7 @@ static struct cm_id_private * cm_match_req(struct cm_work *work,
 	struct cm_id_private *listen_cm_id_priv, *cur_cm_id_priv;
 	struct cm_timewait_info *timewait_info;
 	struct cm_req_msg *req_msg;
+	struct ib_cm_id *cm_id;
 
 	req_msg = (struct cm_req_msg *)work->mad_recv_wc->recv_buf.mad;
 
@@ -1603,10 +1652,18 @@ static struct cm_id_private * cm_match_req(struct cm_work *work,
 	timewait_info = cm_insert_remote_qpn(cm_id_priv->timewait_info);
 	if (timewait_info) {
 		cm_cleanup_timewait(cm_id_priv->timewait_info);
+		cur_cm_id_priv = cm_get_id(timewait_info->work.local_id,
+					   timewait_info->work.remote_id);
+
 		spin_unlock_irq(&cm.lock);
 		cm_issue_rej(work->port, work->mad_recv_wc,
 			     IB_CM_REJ_STALE_CONN, CM_MSG_RESPONSE_REQ,
 			     NULL, 0);
+		if (cur_cm_id_priv) {
+			cm_id = &cur_cm_id_priv->id;
+			ib_send_cm_dreq(cm_id, NULL, 0);
+			cm_deref_id(cur_cm_id_priv);
+		}
 		return NULL;
 	}
 
@@ -1984,6 +2041,9 @@ static int cm_rep_handler(struct cm_work *work)
 	struct cm_id_private *cm_id_priv;
 	struct cm_rep_msg *rep_msg;
 	int ret;
+	struct cm_id_private *cur_cm_id_priv;
+	struct ib_cm_id *cm_id;
+	struct cm_timewait_info *timewait_info;
 
 	rep_msg = (struct cm_rep_msg *)work->mad_recv_wc->recv_buf.mad;
 	cm_id_priv = cm_acquire_id(rep_msg->remote_comm_id, 0);
@@ -2018,16 +2078,26 @@ static int cm_rep_handler(struct cm_work *work)
 		goto error;
 	}
 	/* Check for a stale connection. */
-	if (cm_insert_remote_qpn(cm_id_priv->timewait_info)) {
+	timewait_info = cm_insert_remote_qpn(cm_id_priv->timewait_info);
+	if (timewait_info) {
 		rb_erase(&cm_id_priv->timewait_info->remote_id_node,
 			 &cm.remote_id_table);
 		cm_id_priv->timewait_info->inserted_remote_id = 0;
+		cur_cm_id_priv = cm_get_id(timewait_info->work.local_id,
+					   timewait_info->work.remote_id);
+
 		spin_unlock(&cm.lock);
 		spin_unlock_irq(&cm_id_priv->lock);
 		cm_issue_rej(work->port, work->mad_recv_wc,
 			     IB_CM_REJ_STALE_CONN, CM_MSG_RESPONSE_REP,
 			     NULL, 0);
 		ret = -EINVAL;
+		if (cur_cm_id_priv) {
+			cm_id = &cur_cm_id_priv->id;
+			ib_send_cm_dreq(cm_id, NULL, 0);
+			cm_deref_id(cur_cm_id_priv);
+		}
+
 		goto error;
 	}
 	spin_unlock(&cm.lock);

drivers/infiniband/core/cma.c

@@ -101,6 +101,49 @@ const char *__attribute_const__ rdma_event_msg(enum rdma_cm_event_type event)
 }
 EXPORT_SYMBOL(rdma_event_msg);
 
+const char *__attribute_const__ rdma_reject_msg(struct rdma_cm_id *id,
+						int reason)
+{
+	if (rdma_ib_or_roce(id->device, id->port_num))
+		return ibcm_reject_msg(reason);
+
+	if (rdma_protocol_iwarp(id->device, id->port_num))
+		return iwcm_reject_msg(reason);
+
+	WARN_ON_ONCE(1);
+	return "unrecognized transport";
+}
+EXPORT_SYMBOL(rdma_reject_msg);
+
+bool rdma_is_consumer_reject(struct rdma_cm_id *id, int reason)
+{
+	if (rdma_ib_or_roce(id->device, id->port_num))
+		return reason == IB_CM_REJ_CONSUMER_DEFINED;
+
+	if (rdma_protocol_iwarp(id->device, id->port_num))
+		return reason == -ECONNREFUSED;
+
+	WARN_ON_ONCE(1);
+	return false;
+}
+EXPORT_SYMBOL(rdma_is_consumer_reject);
+
+const void *rdma_consumer_reject_data(struct rdma_cm_id *id,
+				      struct rdma_cm_event *ev, u8 *data_len)
+{
+	const void *p;
+
+	if (rdma_is_consumer_reject(id, ev->status)) {
+		*data_len = ev->param.conn.private_data_len;
+		p = ev->param.conn.private_data;
+	} else {
+		*data_len = 0;
+		p = NULL;
+	}
+	return p;
+}
+EXPORT_SYMBOL(rdma_consumer_reject_data);
+
 static void cma_add_one(struct ib_device *device);
 static void cma_remove_one(struct ib_device *device, void *client_data);
 

drivers/infiniband/core/core_priv.h

@@ -72,9 +72,6 @@ void ib_device_unregister_sysfs(struct ib_device *device);
 void ib_cache_setup(void);
 void ib_cache_cleanup(void);
 
-int ib_resolve_eth_dmac(struct ib_qp *qp,
-			struct ib_qp_attr *qp_attr, int *qp_attr_mask);
-
 typedef void (*roce_netdev_callback)(struct ib_device *device, u8 port,
 	      struct net_device *idev, void *cookie);
 

drivers/infiniband/core/device.c

@@ -254,11 +254,8 @@ static int add_client_context(struct ib_device *device, struct ib_client *client
 	unsigned long flags;
 
 	context = kmalloc(sizeof *context, GFP_KERNEL);
-	if (!context) {
-		pr_warn("Couldn't allocate client context for %s/%s\n",
-			device->name, client->name);
+	if (!context)
 		return -ENOMEM;
-	}
 
 	context->client = client;
 	context->data   = NULL;

drivers/infiniband/core/fmr_pool.c

@@ -247,7 +247,6 @@ struct ib_fmr_pool *ib_create_fmr_pool(struct ib_pd             *pd,
 			kmalloc(IB_FMR_HASH_SIZE * sizeof *pool->cache_bucket,
 				GFP_KERNEL);
 		if (!pool->cache_bucket) {
-			pr_warn(PFX "Failed to allocate cache in pool\n");
 			ret = -ENOMEM;
 			goto out_free_pool;
 		}

drivers/infiniband/core/iwcm.c

@@ -59,6 +59,27 @@ MODULE_AUTHOR("Tom Tucker");
 MODULE_DESCRIPTION("iWARP CM");
 MODULE_LICENSE("Dual BSD/GPL");
 
+static const char * const iwcm_rej_reason_strs[] = {
+	[ECONNRESET]			= "reset by remote host",
+	[ECONNREFUSED]			= "refused by remote application",
+	[ETIMEDOUT]			= "setup timeout",
+};
+
+const char *__attribute_const__ iwcm_reject_msg(int reason)
+{
+	size_t index;
+
+	/* iWARP uses negative errnos */
+	index = -reason;
+
+	if (index < ARRAY_SIZE(iwcm_rej_reason_strs) &&
+	    iwcm_rej_reason_strs[index])
+		return iwcm_rej_reason_strs[index];
+	else
+		return "unrecognized reason";
+}
+EXPORT_SYMBOL(iwcm_reject_msg);
+
 static struct ibnl_client_cbs iwcm_nl_cb_table[] = {
 	[RDMA_NL_IWPM_REG_PID] = {.dump = iwpm_register_pid_cb},
 	[RDMA_NL_IWPM_ADD_MAPPING] = {.dump = iwpm_add_mapping_cb},

drivers/infiniband/core/iwpm_msg.c

@@ -604,7 +604,6 @@ int iwpm_remote_info_cb(struct sk_buff *skb, struct netlink_callback *cb)
 	}
 	rem_info = kzalloc(sizeof(struct iwpm_remote_info), GFP_ATOMIC);
 	if (!rem_info) {
-		pr_err("%s: Unable to allocate a remote info\n", __func__);
 		ret = -ENOMEM;
 		return ret;
 	}

drivers/infiniband/core/iwpm_util.c

@@ -62,7 +62,6 @@ int iwpm_init(u8 nl_client)
 					sizeof(struct hlist_head), GFP_KERNEL);
 		if (!iwpm_hash_bucket) {
 			ret = -ENOMEM;
-			pr_err("%s Unable to create mapinfo hash table\n", __func__);
 			goto init_exit;
 		}
 		iwpm_reminfo_bucket = kzalloc(IWPM_REMINFO_HASH_SIZE *
@@ -70,7 +69,6 @@ int iwpm_init(u8 nl_client)
 		if (!iwpm_reminfo_bucket) {
 			kfree(iwpm_hash_bucket);
 			ret = -ENOMEM;
-			pr_err("%s Unable to create reminfo hash table\n", __func__);
 			goto init_exit;
 		}
 	}
@@ -128,10 +126,9 @@ int iwpm_create_mapinfo(struct sockaddr_storage *local_sockaddr,
 	if (!iwpm_valid_client(nl_client))
 		return ret;
 	map_info = kzalloc(sizeof(struct iwpm_mapping_info), GFP_KERNEL);
-	if (!map_info) {
-		pr_err("%s: Unable to allocate a mapping info\n", __func__);
+	if (!map_info)
 		return -ENOMEM;
-	}
+
 	memcpy(&map_info->local_sockaddr, local_sockaddr,
 	       sizeof(struct sockaddr_storage));
 	memcpy(&map_info->mapped_sockaddr, mapped_sockaddr,
@@ -309,10 +306,9 @@ struct iwpm_nlmsg_request *iwpm_get_nlmsg_request(__u32 nlmsg_seq,
 	unsigned long flags;
 
 	nlmsg_request = kzalloc(sizeof(struct iwpm_nlmsg_request), gfp);
-	if (!nlmsg_request) {
-		pr_err("%s Unable to allocate a nlmsg_request\n", __func__);
+	if (!nlmsg_request)
 		return NULL;
-	}
+
 	spin_lock_irqsave(&iwpm_nlmsg_req_lock, flags);
 	list_add_tail(&nlmsg_request->inprocess_list, &iwpm_nlmsg_req_list);
 	spin_unlock_irqrestore(&iwpm_nlmsg_req_lock, flags);

drivers/infiniband/core/mad.c

@@ -769,7 +769,7 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv,
 	 * If we are at the start of the LID routed part, don't update the
 	 * hop_ptr or hop_cnt.  See section 14.2.2, Vol 1 IB spec.
 	 */
-	if (opa && smp->class_version == OPA_SMP_CLASS_VERSION) {
+	if (opa && smp->class_version == OPA_SM_CLASS_VERSION) {
 		u32 opa_drslid;
 
 		if ((opa_get_smp_direction(opa_smp)
@@ -816,7 +816,6 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv,
 	local = kmalloc(sizeof *local, GFP_ATOMIC);
 	if (!local) {
 		ret = -ENOMEM;
-		dev_err(&device->dev, "No memory for ib_mad_local_private\n");
 		goto out;
 	}
 	local->mad_priv = NULL;
@@ -824,7 +823,6 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv,
 	mad_priv = alloc_mad_private(mad_size, GFP_ATOMIC);
 	if (!mad_priv) {
 		ret = -ENOMEM;
-		dev_err(&device->dev, "No memory for local response MAD\n");
 		kfree(local);
 		goto out;
 	}
@@ -947,9 +945,6 @@ static int alloc_send_rmpp_list(struct ib_mad_send_wr_private *send_wr,
 	for (left = send_buf->data_len + pad; left > 0; left -= seg_size) {
 		seg = kmalloc(sizeof (*seg) + seg_size, gfp_mask);
 		if (!seg) {
-			dev_err(&send_buf->mad_agent->device->dev,
-				"alloc_send_rmpp_segs: RMPP mem alloc failed for len %zd, gfp %#x\n",
-				sizeof (*seg) + seg_size, gfp_mask);
 			free_send_rmpp_list(send_wr);
 			return -ENOMEM;
 		}
@@ -1362,12 +1357,7 @@ static int allocate_method_table(struct ib_mad_mgmt_method_table **method)
 {
 	/* Allocate management method table */
 	*method = kzalloc(sizeof **method, GFP_ATOMIC);
-	if (!*method) {
-		pr_err("No memory for ib_mad_mgmt_method_table\n");
-		return -ENOMEM;
-	}
-
-	return 0;
+	return (*method) ? 0 : (-ENOMEM);
 }
 
 /*
@@ -1458,8 +1448,6 @@ static int add_nonoui_reg_req(struct ib_mad_reg_req *mad_reg_req,
 		/* Allocate management class table for "new" class version */
 		*class = kzalloc(sizeof **class, GFP_ATOMIC);
 		if (!*class) {
-			dev_err(&agent_priv->agent.device->dev,
-				"No memory for ib_mad_mgmt_class_table\n");
 			ret = -ENOMEM;
 			goto error1;
 		}
@@ -1524,22 +1512,16 @@ static int add_oui_reg_req(struct ib_mad_reg_req *mad_reg_req,
 	if (!*vendor_table) {
 		/* Allocate mgmt vendor class table for "new" class version */
 		vendor = kzalloc(sizeof *vendor, GFP_ATOMIC);
-		if (!vendor) {
-			dev_err(&agent_priv->agent.device->dev,
-				"No memory for ib_mad_mgmt_vendor_class_table\n");
+		if (!vendor)
 			goto error1;
-		}
 
 		*vendor_table = vendor;
 	}
 	if (!(*vendor_table)->vendor_class[vclass]) {
 		/* Allocate table for this management vendor class */
 		vendor_class = kzalloc(sizeof *vendor_class, GFP_ATOMIC);
-		if (!vendor_class) {
-			dev_err(&agent_priv->agent.device->dev,
-				"No memory for ib_mad_mgmt_vendor_class\n");
+		if (!vendor_class)
 			goto error2;
-		}
 
 		(*vendor_table)->vendor_class[vclass] = vendor_class;
 	}
@@ -1746,7 +1728,7 @@ find_mad_agent(struct ib_mad_port_private *port_priv,
 			if (!class)
 				goto out;
 			if (convert_mgmt_class(mad_hdr->mgmt_class) >=
-			    IB_MGMT_MAX_METHODS)
+			    ARRAY_SIZE(class->method_table))
 				goto out;
 			method = class->method_table[convert_mgmt_class(
 							mad_hdr->mgmt_class)];
@@ -2167,7 +2149,7 @@ handle_smi(struct ib_mad_port_private *port_priv,
 	struct ib_mad_hdr *mad_hdr = (struct ib_mad_hdr *)recv->mad;
 
 	if (opa && mad_hdr->base_version == OPA_MGMT_BASE_VERSION &&
-	    mad_hdr->class_version == OPA_SMI_CLASS_VERSION)
+	    mad_hdr->class_version == OPA_SM_CLASS_VERSION)
 		return handle_opa_smi(port_priv, qp_info, wc, port_num, recv,
 				      response);
 
@@ -2238,11 +2220,8 @@ static void ib_mad_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 
 	mad_size = recv->mad_size;
 	response = alloc_mad_private(mad_size, GFP_KERNEL);
-	if (!response) {
-		dev_err(&port_priv->device->dev,
-			"%s: no memory for response buffer\n", __func__);
+	if (!response)
 		goto out;
-	}
 
 	if (rdma_cap_ib_switch(port_priv->device))
 		port_num = wc->port_num;
@@ -2869,8 +2848,6 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 			mad_priv = alloc_mad_private(port_mad_size(qp_info->port_priv),
 						     GFP_ATOMIC);
 			if (!mad_priv) {
-				dev_err(&qp_info->port_priv->device->dev,
-					"No memory for receive buffer\n");
 				ret = -ENOMEM;
 				break;
 			}
@@ -2961,11 +2938,8 @@ static int ib_mad_port_start(struct ib_mad_port_private *port_priv)
 	u16 pkey_index;
 
 	attr = kmalloc(sizeof *attr, GFP_KERNEL);
-	if (!attr) {
-		dev_err(&port_priv->device->dev,
-			"Couldn't kmalloc ib_qp_attr\n");
+	if (!attr)
 		return -ENOMEM;
-	}
 
 	ret = ib_find_pkey(port_priv->device, port_priv->port_num,
 			   IB_DEFAULT_PKEY_FULL, &pkey_index);
@@ -3135,10 +3109,8 @@ static int ib_mad_port_open(struct ib_device *device,
 
 	/* Create new device info */
 	port_priv = kzalloc(sizeof *port_priv, GFP_KERNEL);
-	if (!port_priv) {
-		dev_err(&device->dev, "No memory for ib_mad_port_private\n");
+	if (!port_priv)
 		return -ENOMEM;
-	}
 
 	port_priv->device = device;
 	port_priv->port_num = port_num;

drivers/infiniband/core/multicast.c

@@ -518,8 +518,11 @@ static void join_handler(int status, struct ib_sa_mcmember_rec *rec,
 		process_join_error(group, status);
 	else {
 		int mgids_changed, is_mgid0;
-		ib_find_pkey(group->port->dev->device, group->port->port_num,
-			     be16_to_cpu(rec->pkey), &pkey_index);
+
+		if (ib_find_pkey(group->port->dev->device,
+				 group->port->port_num, be16_to_cpu(rec->pkey),
+				 &pkey_index))
+			pkey_index = MCAST_INVALID_PKEY_INDEX;
 
 		spin_lock_irq(&group->port->lock);
 		if (group->state == MCAST_BUSY &&

drivers/infiniband/core/roce_gid_mgmt.c

@@ -304,10 +304,9 @@ static void enum_netdev_ipv4_ips(struct ib_device *ib_dev,
 	for_ifa(in_dev) {
 		struct sin_list *entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
 
-		if (!entry) {
-			pr_warn("roce_gid_mgmt: couldn't allocate entry for IPv4 update\n");
+		if (!entry)
 			continue;
-		}
+
 		entry->ip.sin_family = AF_INET;
 		entry->ip.sin_addr.s_addr = ifa->ifa_address;
 		list_add_tail(&entry->list, &sin_list);
@@ -348,10 +347,8 @@ static void enum_netdev_ipv6_ips(struct ib_device *ib_dev,
 	list_for_each_entry(ifp, &in6_dev->addr_list, if_list) {
 		struct sin6_list *entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
 
-		if (!entry) {
-			pr_warn("roce_gid_mgmt: couldn't allocate entry for IPv6 update\n");
+		if (!entry)
 			continue;
-		}
 
 		entry->sin6.sin6_family = AF_INET6;
 		entry->sin6.sin6_addr = ifp->addr;
@@ -447,10 +444,8 @@ static int netdev_upper_walk(struct net_device *upper, void *data)
 	struct upper_list *entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
 	struct list_head *upper_list = data;
 
-	if (!entry) {
-		pr_info("roce_gid_mgmt: couldn't allocate entry to delete ndev\n");
+	if (!entry)
 		return 0;
-	}
 
 	list_add_tail(&entry->list, upper_list);
 	dev_hold(upper);
@@ -559,10 +554,8 @@ static int netdevice_queue_work(struct netdev_event_work_cmd *cmds,
 	struct netdev_event_work *ndev_work =
 		kmalloc(sizeof(*ndev_work), GFP_KERNEL);
 
-	if (!ndev_work) {
-		pr_warn("roce_gid_mgmt: can't allocate work for netdevice_event\n");
+	if (!ndev_work)
 		return NOTIFY_DONE;
-	}
 
 	memcpy(ndev_work->cmds, cmds, sizeof(ndev_work->cmds));
 	for (i = 0; i < ARRAY_SIZE(ndev_work->cmds) && ndev_work->cmds[i].cb; i++) {
@@ -696,10 +689,8 @@ static int addr_event(struct notifier_block *this, unsigned long event,
 	}
 
 	work = kmalloc(sizeof(*work), GFP_ATOMIC);
-	if (!work) {
-		pr_warn("roce_gid_mgmt: Couldn't allocate work for addr_event\n");
+	if (!work)
 		return NOTIFY_DONE;
-	}
 
 	INIT_WORK(&work->work, update_gid_event_work_handler);
 

drivers/infiniband/core/ucm.c

@@ -1104,8 +1104,11 @@ static ssize_t ib_ucm_write(struct file *filp, const char __user *buf,
 	struct ib_ucm_cmd_hdr hdr;
 	ssize_t result;
 
-	if (WARN_ON_ONCE(!ib_safe_file_access(filp)))
+	if (!ib_safe_file_access(filp)) {
+		pr_err_once("ucm_write: process %d (%s) changed security contexts after opening file descriptor, this is not allowed.\n",
+			    task_tgid_vnr(current), current->comm);
 		return -EACCES;
+	}
 
 	if (len < sizeof(hdr))
 		return -EINVAL;

drivers/infiniband/core/ucma.c

@@ -1584,8 +1584,11 @@ static ssize_t ucma_write(struct file *filp, const char __user *buf,
 	struct rdma_ucm_cmd_hdr hdr;
 	ssize_t ret;
 
-	if (WARN_ON_ONCE(!ib_safe_file_access(filp)))
+	if (!ib_safe_file_access(filp)) {
+		pr_err_once("ucma_write: process %d (%s) changed security contexts after opening file descriptor, this is not allowed.\n",
+			    task_tgid_vnr(current), current->comm);
 		return -EACCES;
+	}
 
 	if (len < sizeof(hdr))
 		return -EINVAL;

drivers/infiniband/core/umem.c

@@ -51,7 +51,7 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d
 
 	if (umem->nmap > 0)
 		ib_dma_unmap_sg(dev, umem->sg_head.sgl,
-				umem->nmap,
+				umem->npages,
 				DMA_BIDIRECTIONAL);
 
 	for_each_sg(umem->sg_head.sgl, sg, umem->npages, i) {

drivers/infiniband/core/uverbs.h

@@ -289,5 +289,6 @@ IB_UVERBS_DECLARE_EX_CMD(modify_wq);
 IB_UVERBS_DECLARE_EX_CMD(destroy_wq);
 IB_UVERBS_DECLARE_EX_CMD(create_rwq_ind_table);
 IB_UVERBS_DECLARE_EX_CMD(destroy_rwq_ind_table);
+IB_UVERBS_DECLARE_EX_CMD(modify_qp);
 
 #endif /* UVERBS_H */

drivers/infiniband/core/uverbs_cmd.c

@@ -2328,94 +2328,88 @@ static int modify_qp_mask(enum ib_qp_type qp_type, int mask)
 	}
 }
 
-ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file,
-			    struct ib_device *ib_dev,
-			    const char __user *buf, int in_len,
-			    int out_len)
+static int modify_qp(struct ib_uverbs_file *file,
+		     struct ib_uverbs_ex_modify_qp *cmd, struct ib_udata *udata)
 {
-	struct ib_uverbs_modify_qp cmd;
-	struct ib_udata            udata;
-	struct ib_qp              *qp;
-	struct ib_qp_attr         *attr;
-	int                        ret;
-
-	if (copy_from_user(&cmd, buf, sizeof cmd))
-		return -EFAULT;
-
-	INIT_UDATA(&udata, buf + sizeof cmd, NULL, in_len - sizeof cmd,
-		   out_len);
+	struct ib_qp_attr *attr;
+	struct ib_qp *qp;
+	int ret;
 
 	attr = kmalloc(sizeof *attr, GFP_KERNEL);
 	if (!attr)
 		return -ENOMEM;
 
-	qp = idr_read_qp(cmd.qp_handle, file->ucontext);
+	qp = idr_read_qp(cmd->base.qp_handle, file->ucontext);
 	if (!qp) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	attr->qp_state 		  = cmd.qp_state;
-	attr->cur_qp_state 	  = cmd.cur_qp_state;
-	attr->path_mtu 		  = cmd.path_mtu;
-	attr->path_mig_state 	  = cmd.path_mig_state;
-	attr->qkey 		  = cmd.qkey;
-	attr->rq_psn 		  = cmd.rq_psn;
-	attr->sq_psn 		  = cmd.sq_psn;
-	attr->dest_qp_num 	  = cmd.dest_qp_num;
-	attr->qp_access_flags 	  = cmd.qp_access_flags;
-	attr->pkey_index 	  = cmd.pkey_index;
-	attr->alt_pkey_index 	  = cmd.alt_pkey_index;
-	attr->en_sqd_async_notify = cmd.en_sqd_async_notify;
-	attr->max_rd_atomic 	  = cmd.max_rd_atomic;
-	attr->max_dest_rd_atomic  = cmd.max_dest_rd_atomic;
-	attr->min_rnr_timer 	  = cmd.min_rnr_timer;
-	attr->port_num 		  = cmd.port_num;
-	attr->timeout 		  = cmd.timeout;
-	attr->retry_cnt 	  = cmd.retry_cnt;
-	attr->rnr_retry 	  = cmd.rnr_retry;
-	attr->alt_port_num 	  = cmd.alt_port_num;
-	attr->alt_timeout 	  = cmd.alt_timeout;
-
-	memcpy(attr->ah_attr.grh.dgid.raw, cmd.dest.dgid, 16);
-	attr->ah_attr.grh.flow_label        = cmd.dest.flow_label;
-	attr->ah_attr.grh.sgid_index        = cmd.dest.sgid_index;
-	attr->ah_attr.grh.hop_limit         = cmd.dest.hop_limit;
-	attr->ah_attr.grh.traffic_class     = cmd.dest.traffic_class;
-	attr->ah_attr.dlid 	    	    = cmd.dest.dlid;
-	attr->ah_attr.sl   	    	    = cmd.dest.sl;
-	attr->ah_attr.src_path_bits 	    = cmd.dest.src_path_bits;
-	attr->ah_attr.static_rate   	    = cmd.dest.static_rate;
-	attr->ah_attr.ah_flags 	    	    = cmd.dest.is_global ? IB_AH_GRH : 0;
-	attr->ah_attr.port_num 	    	    = cmd.dest.port_num;
-
-	memcpy(attr->alt_ah_attr.grh.dgid.raw, cmd.alt_dest.dgid, 16);
-	attr->alt_ah_attr.grh.flow_label    = cmd.alt_dest.flow_label;
-	attr->alt_ah_attr.grh.sgid_index    = cmd.alt_dest.sgid_index;
-	attr->alt_ah_attr.grh.hop_limit     = cmd.alt_dest.hop_limit;
-	attr->alt_ah_attr.grh.traffic_class = cmd.alt_dest.traffic_class;
-	attr->alt_ah_attr.dlid 	    	    = cmd.alt_dest.dlid;
-	attr->alt_ah_attr.sl   	    	    = cmd.alt_dest.sl;
-	attr->alt_ah_attr.src_path_bits     = cmd.alt_dest.src_path_bits;
-	attr->alt_ah_attr.static_rate       = cmd.alt_dest.static_rate;
-	attr->alt_ah_attr.ah_flags 	    = cmd.alt_dest.is_global ? IB_AH_GRH : 0;
-	attr->alt_ah_attr.port_num 	    = cmd.alt_dest.port_num;
+	attr->qp_state		  = cmd->base.qp_state;
+	attr->cur_qp_state	  = cmd->base.cur_qp_state;
+	attr->path_mtu		  = cmd->base.path_mtu;
+	attr->path_mig_state	  = cmd->base.path_mig_state;
+	attr->qkey		  = cmd->base.qkey;
+	attr->rq_psn		  = cmd->base.rq_psn;
+	attr->sq_psn		  = cmd->base.sq_psn;
+	attr->dest_qp_num	  = cmd->base.dest_qp_num;
+	attr->qp_access_flags	  = cmd->base.qp_access_flags;
+	attr->pkey_index	  = cmd->base.pkey_index;
+	attr->alt_pkey_index	  = cmd->base.alt_pkey_index;
+	attr->en_sqd_async_notify = cmd->base.en_sqd_async_notify;
+	attr->max_rd_atomic	  = cmd->base.max_rd_atomic;
+	attr->max_dest_rd_atomic  = cmd->base.max_dest_rd_atomic;
+	attr->min_rnr_timer	  = cmd->base.min_rnr_timer;
+	attr->port_num		  = cmd->base.port_num;
+	attr->timeout		  = cmd->base.timeout;
+	attr->retry_cnt		  = cmd->base.retry_cnt;
+	attr->rnr_retry		  = cmd->base.rnr_retry;
+	attr->alt_port_num	  = cmd->base.alt_port_num;
+	attr->alt_timeout	  = cmd->base.alt_timeout;
+	attr->rate_limit	  = cmd->rate_limit;
+
+	memcpy(attr->ah_attr.grh.dgid.raw, cmd->base.dest.dgid, 16);
+	attr->ah_attr.grh.flow_label	= cmd->base.dest.flow_label;
+	attr->ah_attr.grh.sgid_index	= cmd->base.dest.sgid_index;
+	attr->ah_attr.grh.hop_limit	= cmd->base.dest.hop_limit;
+	attr->ah_attr.grh.traffic_class	= cmd->base.dest.traffic_class;
+	attr->ah_attr.dlid		= cmd->base.dest.dlid;
+	attr->ah_attr.sl		= cmd->base.dest.sl;
+	attr->ah_attr.src_path_bits	= cmd->base.dest.src_path_bits;
+	attr->ah_attr.static_rate	= cmd->base.dest.static_rate;
+	attr->ah_attr.ah_flags		= cmd->base.dest.is_global ?
+					  IB_AH_GRH : 0;
+	attr->ah_attr.port_num		= cmd->base.dest.port_num;
+
+	memcpy(attr->alt_ah_attr.grh.dgid.raw, cmd->base.alt_dest.dgid, 16);
+	attr->alt_ah_attr.grh.flow_label    = cmd->base.alt_dest.flow_label;
+	attr->alt_ah_attr.grh.sgid_index    = cmd->base.alt_dest.sgid_index;
+	attr->alt_ah_attr.grh.hop_limit     = cmd->base.alt_dest.hop_limit;
+	attr->alt_ah_attr.grh.traffic_class = cmd->base.alt_dest.traffic_class;
+	attr->alt_ah_attr.dlid		    = cmd->base.alt_dest.dlid;
+	attr->alt_ah_attr.sl		    = cmd->base.alt_dest.sl;
+	attr->alt_ah_attr.src_path_bits	    = cmd->base.alt_dest.src_path_bits;
+	attr->alt_ah_attr.static_rate	    = cmd->base.alt_dest.static_rate;
+	attr->alt_ah_attr.ah_flags	    = cmd->base.alt_dest.is_global ?
+					      IB_AH_GRH : 0;
+	attr->alt_ah_attr.port_num	    = cmd->base.alt_dest.port_num;
 
 	if (qp->real_qp == qp) {
-		ret = ib_resolve_eth_dmac(qp, attr, &cmd.attr_mask);
-		if (ret)
-			goto release_qp;
+		if (cmd->base.attr_mask & IB_QP_AV) {
+			ret = ib_resolve_eth_dmac(qp->device, &attr->ah_attr);
+			if (ret)
+				goto release_qp;
+		}
 		ret = qp->device->modify_qp(qp, attr,
-			modify_qp_mask(qp->qp_type, cmd.attr_mask), &udata);
+					    modify_qp_mask(qp->qp_type,
+							   cmd->base.attr_mask),
+					    udata);
 	} else {
-		ret = ib_modify_qp(qp, attr, modify_qp_mask(qp->qp_type, cmd.attr_mask));
+		ret = ib_modify_qp(qp, attr,
+				   modify_qp_mask(qp->qp_type,
+						  cmd->base.attr_mask));
 	}
 
-	if (ret)
-		goto release_qp;
-
-	ret = in_len;
-
 release_qp:
 	put_qp_read(qp);
 
@@ -2425,6 +2419,68 @@ out:
 	return ret;
 }
 
+ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file,
+			    struct ib_device *ib_dev,
+			    const char __user *buf, int in_len,
+			    int out_len)
+{
+	struct ib_uverbs_ex_modify_qp cmd = {};
+	struct ib_udata udata;
+	int ret;
+
+	if (copy_from_user(&cmd.base, buf, sizeof(cmd.base)))
+		return -EFAULT;
+
+	if (cmd.base.attr_mask &
+	    ~((IB_USER_LEGACY_LAST_QP_ATTR_MASK << 1) - 1))
+		return -EOPNOTSUPP;
+
+	INIT_UDATA(&udata, buf + sizeof(cmd.base), NULL,
+		   in_len - sizeof(cmd.base), out_len);
+
+	ret = modify_qp(file, &cmd, &udata);
+	if (ret)
+		return ret;
+
+	return in_len;
+}
+
+int ib_uverbs_ex_modify_qp(struct ib_uverbs_file *file,
+			   struct ib_device *ib_dev,
+			   struct ib_udata *ucore,
+			   struct ib_udata *uhw)
+{
+	struct ib_uverbs_ex_modify_qp cmd = {};
+	int ret;
+
+	/*
+	 * Last bit is reserved for extending the attr_mask by
+	 * using another field.
+	 */
+	BUILD_BUG_ON(IB_USER_LAST_QP_ATTR_MASK == (1 << 31));
+
+	if (ucore->inlen < sizeof(cmd.base))
+		return -EINVAL;
+
+	ret = ib_copy_from_udata(&cmd, ucore, min(sizeof(cmd), ucore->inlen));
+	if (ret)
+		return ret;
+
+	if (cmd.base.attr_mask &
+	    ~((IB_USER_LAST_QP_ATTR_MASK << 1) - 1))
+		return -EOPNOTSUPP;
+
+	if (ucore->inlen > sizeof(cmd)) {
+		if (ib_is_udata_cleared(ucore, sizeof(cmd),
+					ucore->inlen - sizeof(cmd)))
+			return -EOPNOTSUPP;
+	}
+
+	ret = modify_qp(file, &cmd, uhw);
+
+	return ret;
+}
+
 ssize_t ib_uverbs_destroy_qp(struct ib_uverbs_file *file,
 			     struct ib_device *ib_dev,
 			     const char __user *buf, int in_len,
@@ -2875,6 +2931,7 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file,
 	struct ib_ah			*ah;
 	struct ib_ah_attr		attr;
 	int ret;
+	struct ib_udata                   udata;
 
 	if (out_len < sizeof resp)
 		return -ENOSPC;
@@ -2882,6 +2939,10 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file,
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;
 
+	INIT_UDATA(&udata, buf + sizeof(cmd),
+		   (unsigned long)cmd.response + sizeof(resp),
+		   in_len - sizeof(cmd), out_len - sizeof(resp));
+
 	uobj = kmalloc(sizeof *uobj, GFP_KERNEL);
 	if (!uobj)
 		return -ENOMEM;
@@ -2908,12 +2969,16 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file,
 	memset(&attr.dmac, 0, sizeof(attr.dmac));
 	memcpy(attr.grh.dgid.raw, cmd.attr.grh.dgid, 16);
 
-	ah = ib_create_ah(pd, &attr);
+	ah = pd->device->create_ah(pd, &attr, &udata);
+
 	if (IS_ERR(ah)) {
 		ret = PTR_ERR(ah);
 		goto err_put;
 	}
 
+	ah->device  = pd->device;
+	ah->pd      = pd;
+	atomic_inc(&pd->usecnt);
 	ah->uobject  = uobj;
 	uobj->object = ah;
 
@@ -3124,8 +3189,10 @@ static int kern_spec_to_ib_spec(struct ib_uverbs_flow_spec *kern_spec,
 	kern_spec_val = (void *)kern_spec +
 		sizeof(struct ib_uverbs_flow_spec_hdr);
 	kern_spec_mask = kern_spec_val + kern_filter_sz;
+	if (ib_spec->type == (IB_FLOW_SPEC_INNER | IB_FLOW_SPEC_VXLAN_TUNNEL))
+		return -EINVAL;
 
-	switch (ib_spec->type) {
+	switch (ib_spec->type & ~IB_FLOW_SPEC_INNER) {
 	case IB_FLOW_SPEC_ETH:
 		ib_filter_sz = offsetof(struct ib_flow_eth_filter, real_sz);
 		actual_filter_sz = spec_filter_size(kern_spec_mask,
@@ -3175,6 +3242,21 @@ static int kern_spec_to_ib_spec(struct ib_uverbs_flow_spec *kern_spec,
 		memcpy(&ib_spec->tcp_udp.val, kern_spec_val, actual_filter_sz);
 		memcpy(&ib_spec->tcp_udp.mask, kern_spec_mask, actual_filter_sz);
 		break;
+	case IB_FLOW_SPEC_VXLAN_TUNNEL:
+		ib_filter_sz = offsetof(struct ib_flow_tunnel_filter, real_sz);
+		actual_filter_sz = spec_filter_size(kern_spec_mask,
+						    kern_filter_sz,
+						    ib_filter_sz);
+		if (actual_filter_sz <= 0)
+			return -EINVAL;
+		ib_spec->tunnel.size = sizeof(struct ib_flow_spec_tunnel);
+		memcpy(&ib_spec->tunnel.val, kern_spec_val, actual_filter_sz);
+		memcpy(&ib_spec->tunnel.mask, kern_spec_mask, actual_filter_sz);
+
+		if ((ntohl(ib_spec->tunnel.mask.tunnel_id)) >= BIT(24) ||
+		    (ntohl(ib_spec->tunnel.val.tunnel_id)) >= BIT(24))
+			return -EINVAL;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -3745,7 +3827,6 @@ int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file,
 		err = PTR_ERR(flow_id);
 		goto err_free;
 	}
-	flow_id->qp = qp;
 	flow_id->uobject = uobj;
 	uobj->object = flow_id;
 

drivers/infiniband/core/uverbs_main.c

@@ -137,6 +137,7 @@ static int (*uverbs_ex_cmd_table[])(struct ib_uverbs_file *file,
 	[IB_USER_VERBS_EX_CMD_DESTROY_WQ]       = ib_uverbs_ex_destroy_wq,
 	[IB_USER_VERBS_EX_CMD_CREATE_RWQ_IND_TBL] = ib_uverbs_ex_create_rwq_ind_table,
 	[IB_USER_VERBS_EX_CMD_DESTROY_RWQ_IND_TBL] = ib_uverbs_ex_destroy_rwq_ind_table,
+	[IB_USER_VERBS_EX_CMD_MODIFY_QP]        = ib_uverbs_ex_modify_qp,
 };
 
 static void ib_uverbs_add_one(struct ib_device *device);
@@ -746,8 +747,11 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf,
 	int srcu_key;
 	ssize_t ret;
 
-	if (WARN_ON_ONCE(!ib_safe_file_access(filp)))
+	if (!ib_safe_file_access(filp)) {
+		pr_err_once("uverbs_write: process %d (%s) changed security contexts after opening file descriptor, this is not allowed.\n",
+			    task_tgid_vnr(current), current->comm);
 		return -EACCES;
+	}
 
 	if (count < sizeof hdr)
 		return -EINVAL;

drivers/infiniband/core/verbs.c

@@ -315,7 +315,7 @@ struct ib_ah *ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr)
 {
 	struct ib_ah *ah;
 
-	ah = pd->device->create_ah(pd, ah_attr);
+	ah = pd->device->create_ah(pd, ah_attr, NULL);
 
 	if (!IS_ERR(ah)) {
 		ah->device  = pd->device;
@@ -328,7 +328,7 @@ struct ib_ah *ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr)
 }
 EXPORT_SYMBOL(ib_create_ah);
 
-static int ib_get_header_version(const union rdma_network_hdr *hdr)
+int ib_get_rdma_header_version(const union rdma_network_hdr *hdr)
 {
 	const struct iphdr *ip4h = (struct iphdr *)&hdr->roce4grh;
 	struct iphdr ip4h_checked;
@@ -359,6 +359,7 @@ static int ib_get_header_version(const union rdma_network_hdr *hdr)
 		return 4;
 	return 6;
 }
+EXPORT_SYMBOL(ib_get_rdma_header_version);
 
 static enum rdma_network_type ib_get_net_type_by_grh(struct ib_device *device,
 						     u8 port_num,
@@ -369,7 +370,7 @@ static enum rdma_network_type ib_get_net_type_by_grh(struct ib_device *device,
 	if (rdma_protocol_ib(device, port_num))
 		return RDMA_NETWORK_IB;
 
-	grh_version = ib_get_header_version((union rdma_network_hdr *)grh);
+	grh_version = ib_get_rdma_header_version((union rdma_network_hdr *)grh);
 
 	if (grh_version == 4)
 		return RDMA_NETWORK_IPV4;
@@ -415,9 +416,9 @@ static int get_sgid_index_from_eth(struct ib_device *device, u8 port_num,
 				     &context, gid_index);
 }
 
-static int get_gids_from_rdma_hdr(union rdma_network_hdr *hdr,
-				  enum rdma_network_type net_type,
-				  union ib_gid *sgid, union ib_gid *dgid)
+int ib_get_gids_from_rdma_hdr(const union rdma_network_hdr *hdr,
+			      enum rdma_network_type net_type,
+			      union ib_gid *sgid, union ib_gid *dgid)
 {
 	struct sockaddr_in  src_in;
 	struct sockaddr_in  dst_in;
@@ -447,6 +448,7 @@ static int get_gids_from_rdma_hdr(union rdma_network_hdr *hdr,
 		return -EINVAL;
 	}
 }
+EXPORT_SYMBOL(ib_get_gids_from_rdma_hdr);
 
 int ib_init_ah_from_wc(struct ib_device *device, u8 port_num,
 		       const struct ib_wc *wc, const struct ib_grh *grh,
@@ -469,8 +471,8 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num,
 			net_type = ib_get_net_type_by_grh(device, port_num, grh);
 		gid_type = ib_network_to_gid_type(net_type);
 	}
-	ret = get_gids_from_rdma_hdr((union rdma_network_hdr *)grh, net_type,
-				     &sgid, &dgid);
+	ret = ib_get_gids_from_rdma_hdr((union rdma_network_hdr *)grh, net_type,
+					&sgid, &dgid);
 	if (ret)
 		return ret;
 
@@ -1014,6 +1016,7 @@ static const struct {
 						 IB_QP_QKEY),
 				 [IB_QPT_GSI] = (IB_QP_CUR_STATE		|
 						 IB_QP_QKEY),
+				 [IB_QPT_RAW_PACKET] = IB_QP_RATE_LIMIT,
 			 }
 		}
 	},
@@ -1047,6 +1050,7 @@ static const struct {
 						IB_QP_QKEY),
 				[IB_QPT_GSI] = (IB_QP_CUR_STATE			|
 						IB_QP_QKEY),
+				[IB_QPT_RAW_PACKET] = IB_QP_RATE_LIMIT,
 			}
 		},
 		[IB_QPS_SQD]   = {
@@ -1196,66 +1200,66 @@ int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
 }
 EXPORT_SYMBOL(ib_modify_qp_is_ok);
 
-int ib_resolve_eth_dmac(struct ib_qp *qp,
-			struct ib_qp_attr *qp_attr, int *qp_attr_mask)
+int ib_resolve_eth_dmac(struct ib_device *device,
+			struct ib_ah_attr *ah_attr)
 {
 	int           ret = 0;
 
-	if (*qp_attr_mask & IB_QP_AV) {
-		if (qp_attr->ah_attr.port_num < rdma_start_port(qp->device) ||
-		    qp_attr->ah_attr.port_num > rdma_end_port(qp->device))
-			return -EINVAL;
-
-		if (!rdma_cap_eth_ah(qp->device, qp_attr->ah_attr.port_num))
-			return 0;
-
-		if (rdma_link_local_addr((struct in6_addr *)qp_attr->ah_attr.grh.dgid.raw)) {
-			rdma_get_ll_mac((struct in6_addr *)qp_attr->ah_attr.grh.dgid.raw,
-					qp_attr->ah_attr.dmac);
-		} else {
-			union ib_gid		sgid;
-			struct ib_gid_attr	sgid_attr;
-			int			ifindex;
-			int			hop_limit;
-
-			ret = ib_query_gid(qp->device,
-					   qp_attr->ah_attr.port_num,
-					   qp_attr->ah_attr.grh.sgid_index,
-					   &sgid, &sgid_attr);
-
-			if (ret || !sgid_attr.ndev) {
-				if (!ret)
-					ret = -ENXIO;
-				goto out;
-			}
+	if (ah_attr->port_num < rdma_start_port(device) ||
+	    ah_attr->port_num > rdma_end_port(device))
+		return -EINVAL;
 
-			ifindex = sgid_attr.ndev->ifindex;
+	if (!rdma_cap_eth_ah(device, ah_attr->port_num))
+		return 0;
 
-			ret = rdma_addr_find_l2_eth_by_grh(&sgid,
-							   &qp_attr->ah_attr.grh.dgid,
-							   qp_attr->ah_attr.dmac,
-							   NULL, &ifindex, &hop_limit);
+	if (rdma_link_local_addr((struct in6_addr *)ah_attr->grh.dgid.raw)) {
+		rdma_get_ll_mac((struct in6_addr *)ah_attr->grh.dgid.raw,
+				ah_attr->dmac);
+	} else {
+		union ib_gid		sgid;
+		struct ib_gid_attr	sgid_attr;
+		int			ifindex;
+		int			hop_limit;
+
+		ret = ib_query_gid(device,
+				   ah_attr->port_num,
+				   ah_attr->grh.sgid_index,
+				   &sgid, &sgid_attr);
+
+		if (ret || !sgid_attr.ndev) {
+			if (!ret)
+				ret = -ENXIO;
+			goto out;
+		}
 
-			dev_put(sgid_attr.ndev);
+		ifindex = sgid_attr.ndev->ifindex;
 
-			qp_attr->ah_attr.grh.hop_limit = hop_limit;
-		}
+		ret = rdma_addr_find_l2_eth_by_grh(&sgid,
+						   &ah_attr->grh.dgid,
+						   ah_attr->dmac,
+						   NULL, &ifindex, &hop_limit);
+
+		dev_put(sgid_attr.ndev);
+
+		ah_attr->grh.hop_limit = hop_limit;
 	}
 out:
 	return ret;
 }
 EXPORT_SYMBOL(ib_resolve_eth_dmac);
 
-
 int ib_modify_qp(struct ib_qp *qp,
 		 struct ib_qp_attr *qp_attr,
 		 int qp_attr_mask)
 {
-	int ret;
 
-	ret = ib_resolve_eth_dmac(qp, qp_attr, &qp_attr_mask);
-	if (ret)
-		return ret;
+	if (qp_attr_mask & IB_QP_AV) {
+		int ret;
+
+		ret = ib_resolve_eth_dmac(qp->device, &qp_attr->ah_attr);
+		if (ret)
+			return ret;
+	}
 
 	return qp->device->modify_qp(qp->real_qp, qp_attr, qp_attr_mask, NULL);
 }
@@ -1734,8 +1738,10 @@ struct ib_flow *ib_create_flow(struct ib_qp *qp,
 		return ERR_PTR(-ENOSYS);
 
 	flow_id = qp->device->create_flow(qp, flow_attr, domain);
-	if (!IS_ERR(flow_id))
+	if (!IS_ERR(flow_id)) {
 		atomic_inc(&qp->usecnt);
+		flow_id->qp = qp;
+	}
 	return flow_id;
 }
 EXPORT_SYMBOL(ib_create_flow);

drivers/infiniband/hw/Makefile

@@ -7,6 +7,7 @@ obj-$(CONFIG_MLX4_INFINIBAND)		+= mlx4/
 obj-$(CONFIG_MLX5_INFINIBAND)		+= mlx5/
 obj-$(CONFIG_INFINIBAND_NES)		+= nes/
 obj-$(CONFIG_INFINIBAND_OCRDMA)		+= ocrdma/
+obj-$(CONFIG_INFINIBAND_VMWARE_PVRDMA)	+= vmw_pvrdma/
 obj-$(CONFIG_INFINIBAND_USNIC)		+= usnic/
 obj-$(CONFIG_INFINIBAND_HFI1)		+= hfi1/
 obj-$(CONFIG_INFINIBAND_HNS)		+= hns/

drivers/infiniband/hw/cxgb3/cxio_dbg.c

@@ -45,10 +45,9 @@ void cxio_dump_tpt(struct cxio_rdev *rdev, u32 stag)
 	int size = 32;
 
 	m = kmalloc(sizeof(*m) + size, GFP_ATOMIC);
-	if (!m) {
-		PDBG("%s couldn't allocate memory.\n", __func__);
+	if (!m)
 		return;
-	}
+
 	m->mem_id = MEM_PMRX;
 	m->addr = (stag>>8) * 32 + rdev->rnic_info.tpt_base;
 	m->len = size;
@@ -82,10 +81,9 @@ void cxio_dump_pbl(struct cxio_rdev *rdev, u32 pbl_addr, uint len, u8 shift)
 	size = npages * sizeof(u64);
 
 	m = kmalloc(sizeof(*m) + size, GFP_ATOMIC);
-	if (!m) {
-		PDBG("%s couldn't allocate memory.\n", __func__);
+	if (!m)
 		return;
-	}
+
 	m->mem_id = MEM_PMRX;
 	m->addr = pbl_addr;
 	m->len = size;
@@ -144,10 +142,9 @@ void cxio_dump_rqt(struct cxio_rdev *rdev, u32 hwtid, int nents)
 	int rc;
 
 	m = kmalloc(sizeof(*m) + size, GFP_ATOMIC);
-	if (!m) {
-		PDBG("%s couldn't allocate memory.\n", __func__);
+	if (!m)
 		return;
-	}
+
 	m->mem_id = MEM_PMRX;
 	m->addr = ((hwtid)<<10) + rdev->rnic_info.rqt_base;
 	m->len = size;
@@ -177,10 +174,9 @@ void cxio_dump_tcb(struct cxio_rdev *rdev, u32 hwtid)
 	int rc;
 
 	m = kmalloc(sizeof(*m) + size, GFP_ATOMIC);
-	if (!m) {
-		PDBG("%s couldn't allocate memory.\n", __func__);
+	if (!m)
 		return;
-	}
+
 	m->mem_id = MEM_CM;
 	m->addr = hwtid * size;
 	m->len = size;

drivers/infiniband/hw/cxgb3/iwch_provider.c

@@ -62,7 +62,8 @@
 #include "common.h"
 
 static struct ib_ah *iwch_ah_create(struct ib_pd *pd,
-				    struct ib_ah_attr *ah_attr)
+				    struct ib_ah_attr *ah_attr,
+				    struct ib_udata *udata)
 {
 	return ERR_PTR(-ENOSYS);
 }

drivers/infiniband/hw/cxgb4/device.c

@@ -828,8 +828,10 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
 	}
 	rdev->status_page = (struct t4_dev_status_page *)
 			    __get_free_page(GFP_KERNEL);
-	if (!rdev->status_page)
+	if (!rdev->status_page) {
+		err = -ENOMEM;
 		goto destroy_ocqp_pool;
+	}
 	rdev->status_page->qp_start = rdev->lldi.vr->qp.start;
 	rdev->status_page->qp_size = rdev->lldi.vr->qp.size;
 	rdev->status_page->cq_start = rdev->lldi.vr->cq.start;
@@ -841,8 +843,6 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
 		if (rdev->wr_log) {
 			rdev->wr_log_size = 1 << c4iw_wr_log_size_order;
 			atomic_set(&rdev->wr_log_idx, 0);
-		} else {
-			pr_err(MOD "error allocating wr_log. Logging disabled\n");
 		}
 	}
 
@@ -1424,8 +1424,6 @@ static void recover_queues(struct uld_ctx *ctx)
 
 	qp_list.qps = kzalloc(count * sizeof *qp_list.qps, GFP_ATOMIC);
 	if (!qp_list.qps) {
-		printk(KERN_ERR MOD "%s: Fatal error - DB overflow recovery failed\n",
-		       pci_name(ctx->lldi.pdev));
 		spin_unlock_irq(&ctx->dev->lock);
 		return;
 	}

drivers/infiniband/hw/cxgb4/provider.c

@@ -59,7 +59,9 @@ module_param(fastreg_support, int, 0644);
 MODULE_PARM_DESC(fastreg_support, "Advertise fastreg support (default=1)");
 
 static struct ib_ah *c4iw_ah_create(struct ib_pd *pd,
-				    struct ib_ah_attr *ah_attr)
+				    struct ib_ah_attr *ah_attr,
+				    struct ib_udata *udata)
+
 {
 	return ERR_PTR(-ENOSYS);
 }

drivers/infiniband/hw/hfi1/affinity.c

@@ -125,6 +125,7 @@ int node_affinity_init(void)
 				cpumask_weight(topology_sibling_cpumask(
 					cpumask_first(&node_affinity.proc.mask)
 					));
+	node_affinity.num_possible_nodes = num_possible_nodes();
 	node_affinity.num_online_nodes = num_online_nodes();
 	node_affinity.num_online_cpus = num_online_cpus();
 
@@ -135,7 +136,7 @@ int node_affinity_init(void)
 	 */
 	init_real_cpu_mask();
 
-	hfi1_per_node_cntr = kcalloc(num_possible_nodes(),
+	hfi1_per_node_cntr = kcalloc(node_affinity.num_possible_nodes,
 				     sizeof(*hfi1_per_node_cntr), GFP_KERNEL);
 	if (!hfi1_per_node_cntr)
 		return -ENOMEM;

drivers/infiniband/hw/hfi1/affinity.h

@@ -70,14 +70,6 @@ struct cpu_mask_set {
 	uint gen;
 };
 
-struct hfi1_affinity {
-	struct cpu_mask_set def_intr;
-	struct cpu_mask_set rcv_intr;
-	struct cpumask real_cpu_mask;
-	/* spin lock to protect affinity struct */
-	spinlock_t lock;
-};
-
 struct hfi1_msix_entry;
 
 /* Initialize non-HT cpu cores mask */
@@ -115,6 +107,7 @@ struct hfi1_affinity_node_list {
 	struct cpumask real_cpu_mask;
 	struct cpu_mask_set proc;
 	int num_core_siblings;
+	int num_possible_nodes;
 	int num_online_nodes;
 	int num_online_cpus;
 	struct mutex lock; /* protects affinity nodes */

drivers/infiniband/hw/hfi1/chip.c

@@ -8477,7 +8477,10 @@ static int do_8051_command(
 	 */
 	if (type == HCMD_WRITE_LCB_CSR) {
 		in_data |= ((*out_data) & 0xffffffffffull) << 8;
-		reg = ((((*out_data) >> 40) & 0xff) <<
+		/* must preserve COMPLETED - it is tied to hardware */
+		reg = read_csr(dd, DC_DC8051_CFG_EXT_DEV_0);
+		reg &= DC_DC8051_CFG_EXT_DEV_0_COMPLETED_SMASK;
+		reg |= ((((*out_data) >> 40) & 0xff) <<
 				DC_DC8051_CFG_EXT_DEV_0_RETURN_CODE_SHIFT)
 		      | ((((*out_data) >> 48) & 0xffff) <<
 				DC_DC8051_CFG_EXT_DEV_0_RSP_DATA_SHIFT);
@@ -9556,11 +9559,11 @@ int bringup_serdes(struct hfi1_pportdata *ppd)
 	if (HFI1_CAP_IS_KSET(EXTENDED_PSN))
 		add_rcvctrl(dd, RCV_CTRL_RCV_EXTENDED_PSN_ENABLE_SMASK);
 
-	guid = ppd->guid;
+	guid = ppd->guids[HFI1_PORT_GUID_INDEX];
 	if (!guid) {
 		if (dd->base_guid)
 			guid = dd->base_guid + ppd->port - 1;
-		ppd->guid = guid;
+		ppd->guids[HFI1_PORT_GUID_INDEX] = guid;
 	}
 
 	/* Set linkinit_reason on power up per OPA spec */

drivers/infiniband/hw/hfi1/chip_registers.h

@@ -415,6 +415,9 @@
 #define ASIC_CFG_SBUS_REQUEST_DATA_IN_SHIFT 32
 #define ASIC_CFG_SBUS_REQUEST_RECEIVER_ADDR_SHIFT 0
 #define ASIC_CFG_SCRATCH (ASIC + 0x000000000020)
+#define ASIC_CFG_SCRATCH_1 (ASIC_CFG_SCRATCH + 0x08)
+#define ASIC_CFG_SCRATCH_2 (ASIC_CFG_SCRATCH + 0x10)
+#define ASIC_CFG_SCRATCH_3 (ASIC_CFG_SCRATCH + 0x18)
 #define ASIC_CFG_THERM_POLL_EN (ASIC + 0x000000000050)
 #define ASIC_EEP_ADDR_CMD (ASIC + 0x000000000308)
 #define ASIC_EEP_ADDR_CMD_EP_ADDR_MASK 0xFFFFFFull

drivers/infiniband/hw/hfi1/debugfs.c

@@ -541,6 +541,114 @@ static ssize_t asic_flags_write(struct file *file, const char __user *buf,
 	return ret;
 }
 
+/* read the dc8051 memory */
+static ssize_t dc8051_memory_read(struct file *file, char __user *buf,
+				  size_t count, loff_t *ppos)
+{
+	struct hfi1_pportdata *ppd = private2ppd(file);
+	ssize_t rval;
+	void *tmp;
+	loff_t start, end;
+
+	/* the checks below expect the position to be positive */
+	if (*ppos < 0)
+		return -EINVAL;
+
+	tmp = kzalloc(DC8051_DATA_MEM_SIZE, GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
+	/*
+	 * Fill in the requested portion of the temporary buffer from the
+	 * 8051 memory.  The 8051 memory read is done in terms of 8 bytes.
+	 * Adjust start and end to fit.  Skip reading anything if out of
+	 * range.
+	 */
+	start = *ppos & ~0x7;	/* round down */
+	if (start < DC8051_DATA_MEM_SIZE) {
+		end = (*ppos + count + 7) & ~0x7; /* round up */
+		if (end > DC8051_DATA_MEM_SIZE)
+			end = DC8051_DATA_MEM_SIZE;
+		rval = read_8051_data(ppd->dd, start, end - start,
+				      (u64 *)(tmp + start));
+		if (rval)
+			goto done;
+	}
+
+	rval = simple_read_from_buffer(buf, count, ppos, tmp,
+				       DC8051_DATA_MEM_SIZE);
+done:
+	kfree(tmp);
+	return rval;
+}
+
+static ssize_t debugfs_lcb_read(struct file *file, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	struct hfi1_pportdata *ppd = private2ppd(file);
+	struct hfi1_devdata *dd = ppd->dd;
+	unsigned long total, csr_off;
+	u64 data;
+
+	if (*ppos < 0)
+		return -EINVAL;
+	/* only read 8 byte quantities */
+	if ((count % 8) != 0)
+		return -EINVAL;
+	/* offset must be 8-byte aligned */
+	if ((*ppos % 8) != 0)
+		return -EINVAL;
+	/* do nothing if out of range or zero count */
+	if (*ppos >= (LCB_END - LCB_START) || !count)
+		return 0;
+	/* reduce count if needed */
+	if (*ppos + count > LCB_END - LCB_START)
+		count = (LCB_END - LCB_START) - *ppos;
+
+	csr_off = LCB_START + *ppos;
+	for (total = 0; total < count; total += 8, csr_off += 8) {
+		if (read_lcb_csr(dd, csr_off, (u64 *)&data))
+			break; /* failed */
+		if (put_user(data, (unsigned long __user *)(buf + total)))
+			break;
+	}
+	*ppos += total;
+	return total;
+}
+
+static ssize_t debugfs_lcb_write(struct file *file, const char __user *buf,
+				 size_t count, loff_t *ppos)
+{
+	struct hfi1_pportdata *ppd = private2ppd(file);
+	struct hfi1_devdata *dd = ppd->dd;
+	unsigned long total, csr_off, data;
+
+	if (*ppos < 0)
+		return -EINVAL;
+	/* only write 8 byte quantities */
+	if ((count % 8) != 0)
+		return -EINVAL;
+	/* offset must be 8-byte aligned */
+	if ((*ppos % 8) != 0)
+		return -EINVAL;
+	/* do nothing if out of range or zero count */
+	if (*ppos >= (LCB_END - LCB_START) || !count)
+		return 0;
+	/* reduce count if needed */
+	if (*ppos + count > LCB_END - LCB_START)
+		count = (LCB_END - LCB_START) - *ppos;
+
+	csr_off = LCB_START + *ppos;
+	for (total = 0; total < count; total += 8, csr_off += 8) {
+		if (get_user(data, (unsigned long __user *)(buf + total)))
+			break;
+		if (write_lcb_csr(dd, csr_off, data))
+			break; /* failed */
+	}
+	*ppos += total;
+	return total;
+}
+
 /*
  * read the per-port QSFP data for ppd
  */
@@ -931,6 +1039,8 @@ static const struct counter_info port_cntr_ops[] = {
 	DEBUGFS_XOPS("qsfp2", qsfp2_debugfs_read, qsfp2_debugfs_write,
 		     qsfp2_debugfs_open, qsfp2_debugfs_release),
 	DEBUGFS_OPS("asic_flags", asic_flags_read, asic_flags_write),
+	DEBUGFS_OPS("dc8051_memory", dc8051_memory_read, NULL),
+	DEBUGFS_OPS("lcb", debugfs_lcb_read, debugfs_lcb_write),
 };
 
 static void *_sdma_cpu_list_seq_start(struct seq_file *s, loff_t *pos)

drivers/infiniband/hw/hfi1/driver.c

@@ -795,8 +795,7 @@ static inline void process_rcv_qp_work(struct hfi1_packet *packet)
 				hfi1_schedule_send(qp);
 			spin_unlock_irqrestore(&qp->s_lock, flags);
 		}
-		if (atomic_dec_and_test(&qp->refcount))
-			wake_up(&qp->wait);
+		rvt_put_qp(qp);
 	}
 }
 

drivers/infiniband/hw/hfi1/eprom.c

@@ -207,6 +207,40 @@ done_asic:
 /* magic character sequence that trails an image */
 #define IMAGE_TRAIL_MAGIC "egamiAPO"
 
+/* EPROM file types */
+#define HFI1_EFT_PLATFORM_CONFIG 2
+
+/* segment size - 128 KiB */
+#define SEG_SIZE (128 * 1024)
+
+struct hfi1_eprom_footer {
+	u32 oprom_size;		/* size of the oprom, in bytes */
+	u16 num_table_entries;
+	u16 version;		/* version of this footer */
+	u32 magic;		/* must be last */
+};
+
+struct hfi1_eprom_table_entry {
+	u32 type;		/* file type */
+	u32 offset;		/* file offset from start of EPROM */
+	u32 size;		/* file size, in bytes */
+};
+
+/*
+ * Calculate the max number of table entries that will fit within a directory
+ * buffer of size 'dir_size'.
+ */
+#define MAX_TABLE_ENTRIES(dir_size) \
+	(((dir_size) - sizeof(struct hfi1_eprom_footer)) / \
+		sizeof(struct hfi1_eprom_table_entry))
+
+#define DIRECTORY_SIZE(n) (sizeof(struct hfi1_eprom_footer) + \
+	(sizeof(struct hfi1_eprom_table_entry) * (n)))
+
+#define MAGIC4(a, b, c, d) ((d) << 24 | (c) << 16 | (b) << 8 | (a))
+#define FOOTER_MAGIC MAGIC4('e', 'p', 'r', 'm')
+#define FOOTER_VERSION 1
+
 /*
  * Read all of partition 1.  The actual file is at the front.  Adjust
  * the returned size if a trailing image magic is found.
@@ -241,6 +275,167 @@ static int read_partition_platform_config(struct hfi1_devdata *dd, void **data,
 	return 0;
 }
 
+/*
+ * The segment magic has been checked.  There is a footer and table of
+ * contents present.
+ *
+ * directory is a u32 aligned buffer of size EP_PAGE_SIZE.
+ */
+static int read_segment_platform_config(struct hfi1_devdata *dd,
+					void *directory, void **data, u32 *size)
+{
+	struct hfi1_eprom_footer *footer;
+	struct hfi1_eprom_table_entry *table;
+	struct hfi1_eprom_table_entry *entry;
+	void *buffer = NULL;
+	void *table_buffer = NULL;
+	int ret, i;
+	u32 directory_size;
+	u32 seg_base, seg_offset;
+	u32 bytes_available, ncopied, to_copy;
+
+	/* the footer is at the end of the directory */
+	footer = (struct hfi1_eprom_footer *)
+			(directory + EP_PAGE_SIZE - sizeof(*footer));
+
+	/* make sure the structure version is supported */
+	if (footer->version != FOOTER_VERSION)
+		return -EINVAL;
+
+	/* oprom size cannot be larger than a segment */
+	if (footer->oprom_size >= SEG_SIZE)
+		return -EINVAL;
+
+	/* the file table must fit in a segment with the oprom */
+	if (footer->num_table_entries >
+			MAX_TABLE_ENTRIES(SEG_SIZE - footer->oprom_size))
+		return -EINVAL;
+
+	/* find the file table start, which precedes the footer */
+	directory_size = DIRECTORY_SIZE(footer->num_table_entries);
+	if (directory_size <= EP_PAGE_SIZE) {
+		/* the file table fits into the directory buffer handed in */
+		table = (struct hfi1_eprom_table_entry *)
+				(directory + EP_PAGE_SIZE - directory_size);
+	} else {
+		/* need to allocate and read more */
+		table_buffer = kmalloc(directory_size, GFP_KERNEL);
+		if (!table_buffer)
+			return -ENOMEM;
+		ret = read_length(dd, SEG_SIZE - directory_size,
+				  directory_size, table_buffer);
+		if (ret)
+			goto done;
+		table = table_buffer;
+	}
+
+	/* look for the platform configuration file in the table */
+	for (entry = NULL, i = 0; i < footer->num_table_entries; i++) {
+		if (table[i].type == HFI1_EFT_PLATFORM_CONFIG) {
+			entry = &table[i];
+			break;
+		}
+	}
+	if (!entry) {
+		ret = -ENOENT;
+		goto done;
+	}
+
+	/*
+	 * Sanity check on the configuration file size - it should never
+	 * be larger than 4 KiB.
+	 */
+	if (entry->size > (4 * 1024)) {
+		dd_dev_err(dd, "Bad configuration file size 0x%x\n",
+			   entry->size);
+		ret = -EINVAL;
+		goto done;
+	}
+
+	/* check for bogus offset and size that wrap when added together */
+	if (entry->offset + entry->size < entry->offset) {
+		dd_dev_err(dd,
+			   "Bad configuration file start + size 0x%x+0x%x\n",
+			   entry->offset, entry->size);
+		ret = -EINVAL;
+		goto done;
+	}
+
+	/* allocate the buffer to return */
+	buffer = kmalloc(entry->size, GFP_KERNEL);
+	if (!buffer) {
+		ret = -ENOMEM;
+		goto done;
+	}
+
+	/*
+	 * Extract the file by looping over segments until it is fully read.
+	 */
+	seg_offset = entry->offset % SEG_SIZE;
+	seg_base = entry->offset - seg_offset;
+	ncopied = 0;
+	while (ncopied < entry->size) {
+		/* calculate data bytes available in this segment */
+
+		/* start with the bytes from the current offset to the end */
+		bytes_available = SEG_SIZE - seg_offset;
+		/* subtract off footer and table from segment 0 */
+		if (seg_base == 0) {
+			/*
+			 * Sanity check: should not have a starting point
+			 * at or within the directory.
+			 */
+			if (bytes_available <= directory_size) {
+				dd_dev_err(dd,
+					   "Bad configuration file - offset 0x%x within footer+table\n",
+					   entry->offset);
+				ret = -EINVAL;
+				goto done;
+			}
+			bytes_available -= directory_size;
+		}
+
+		/* calculate bytes wanted */
+		to_copy = entry->size - ncopied;
+
+		/* max out at the available bytes in this segment */
+		if (to_copy > bytes_available)
+			to_copy = bytes_available;
+
+		/*
+		 * Read from the EPROM.
+		 *
+		 * The sanity check for entry->offset is done in read_length().
+		 * The EPROM offset is validated against what the hardware
+		 * addressing supports.  In addition, if the offset is larger
+		 * than the actual EPROM, it silently wraps.  It will work
+		 * fine, though the reader may not get what they expected
+		 * from the EPROM.
+		 */
+		ret = read_length(dd, seg_base + seg_offset, to_copy,
+				  buffer + ncopied);
+		if (ret)
+			goto done;
+
+		ncopied += to_copy;
+
+		/* set up for next segment */
+		seg_offset = footer->oprom_size;
+		seg_base += SEG_SIZE;
+	}
+
+	/* success */
+	ret = 0;
+	*data = buffer;
+	*size = entry->size;
+
+done:
+	kfree(table_buffer);
+	if (ret)
+		kfree(buffer);
+	return ret;
+}
+
 /*
  * Read the platform configuration file from the EPROM.
  *
@@ -253,6 +448,7 @@ static int read_partition_platform_config(struct hfi1_devdata *dd, void **data,
  *   -EBUSY   - not able to acquire access to the EPROM
  *   -ENOENT  - no recognizable file written
  *   -ENOMEM  - buffer could not be allocated
+ *   -EINVAL  - invalid EPROM contentents found
  */
 int eprom_read_platform_config(struct hfi1_devdata *dd, void **data, u32 *size)
 {
@@ -266,21 +462,20 @@ int eprom_read_platform_config(struct hfi1_devdata *dd, void **data, u32 *size)
 	if (ret)
 		return -EBUSY;
 
-	/* read the last page of P0 for the EPROM format magic */
-	ret = read_length(dd, P1_START - EP_PAGE_SIZE, EP_PAGE_SIZE, directory);
+	/* read the last page of the segment for the EPROM format magic */
+	ret = read_length(dd, SEG_SIZE - EP_PAGE_SIZE, EP_PAGE_SIZE, directory);
 	if (ret)
 		goto done;
 
-	/* last dword of P0 contains a magic indicator */
-	if (directory[EP_PAGE_DWORDS - 1] == 0) {
+	/* last dword of the segment contains a magic value */
+	if (directory[EP_PAGE_DWORDS - 1] == FOOTER_MAGIC) {
+		/* segment format */
+		ret = read_segment_platform_config(dd, directory, data, size);
+	} else {
 		/* partition format */
 		ret = read_partition_platform_config(dd, data, size);
-		goto done;
 	}
 
-	/* nothing recognized */
-	ret = -ENOENT;
-
 done:
 	release_chip_resource(dd, CR_EPROM);
 	return ret;

drivers/infiniband/hw/hfi1/firmware.c

@@ -239,6 +239,16 @@ static const u8 all_fabric_serdes_broadcast = 0xe1;
 const u8 pcie_serdes_broadcast[2] = { 0xe2, 0xe3 };
 static const u8 all_pcie_serdes_broadcast = 0xe0;
 
+static const u32 platform_config_table_limits[PLATFORM_CONFIG_TABLE_MAX] = {
+	0,
+	SYSTEM_TABLE_MAX,
+	PORT_TABLE_MAX,
+	RX_PRESET_TABLE_MAX,
+	TX_PRESET_TABLE_MAX,
+	QSFP_ATTEN_TABLE_MAX,
+	VARIABLE_SETTINGS_TABLE_MAX
+};
+
 /* forwards */
 static void dispose_one_firmware(struct firmware_details *fdet);
 static int load_fabric_serdes_firmware(struct hfi1_devdata *dd,
@@ -263,11 +273,13 @@ static int __read_8051_data(struct hfi1_devdata *dd, u32 addr, u64 *result)
 	u64 reg;
 	int count;
 
-	/* start the read at the given address */
-	reg = ((addr & DC_DC8051_CFG_RAM_ACCESS_CTRL_ADDRESS_MASK)
-			<< DC_DC8051_CFG_RAM_ACCESS_CTRL_ADDRESS_SHIFT)
-		| DC_DC8051_CFG_RAM_ACCESS_CTRL_READ_ENA_SMASK;
+	/* step 1: set the address, clear enable */
+	reg = (addr & DC_DC8051_CFG_RAM_ACCESS_CTRL_ADDRESS_MASK)
+			<< DC_DC8051_CFG_RAM_ACCESS_CTRL_ADDRESS_SHIFT;
 	write_csr(dd, DC_DC8051_CFG_RAM_ACCESS_CTRL, reg);
+	/* step 2: enable */
+	write_csr(dd, DC_DC8051_CFG_RAM_ACCESS_CTRL,
+		  reg | DC_DC8051_CFG_RAM_ACCESS_CTRL_READ_ENA_SMASK);
 
 	/* wait until ACCESS_COMPLETED is set */
 	count = 0;
@@ -707,6 +719,9 @@ static int obtain_firmware(struct hfi1_devdata *dd)
 				       &dd->pcidev->dev);
 		if (err) {
 			platform_config = NULL;
+			dd_dev_err(dd,
+				   "%s: No default platform config file found\n",
+				   __func__);
 			goto done;
 		}
 		dd->platform_config.data = platform_config->data;
@@ -1761,8 +1776,17 @@ int parse_platform_config(struct hfi1_devdata *dd)
 	u32 record_idx = 0, table_type = 0, table_length_dwords = 0;
 	int ret = -EINVAL; /* assume failure */
 
+	/*
+	 * For integrated devices that did not fall back to the default file,
+	 * the SI tuning information for active channels is acquired from the
+	 * scratch register bitmap, thus there is no platform config to parse.
+	 * Skip parsing in these situations.
+	 */
+	if (is_integrated(dd) && !platform_config_load)
+		return 0;
+
 	if (!dd->platform_config.data) {
-		dd_dev_info(dd, "%s: Missing config file\n", __func__);
+		dd_dev_err(dd, "%s: Missing config file\n", __func__);
 		goto bail;
 	}
 	ptr = (u32 *)dd->platform_config.data;
@@ -1770,7 +1794,7 @@ int parse_platform_config(struct hfi1_devdata *dd)
 	magic_num = *ptr;
 	ptr++;
 	if (magic_num != PLATFORM_CONFIG_MAGIC_NUM) {
-		dd_dev_info(dd, "%s: Bad config file\n", __func__);
+		dd_dev_err(dd, "%s: Bad config file\n", __func__);
 		goto bail;
 	}
 
@@ -1797,9 +1821,9 @@ int parse_platform_config(struct hfi1_devdata *dd)
 		header1 = *ptr;
 		header2 = *(ptr + 1);
 		if (header1 != ~header2) {
-			dd_dev_info(dd, "%s: Failed validation at offset %ld\n",
-				    __func__, (ptr - (u32 *)
-					       dd->platform_config.data));
+			dd_dev_err(dd, "%s: Failed validation at offset %ld\n",
+				   __func__, (ptr - (u32 *)
+					      dd->platform_config.data));
 			goto bail;
 		}
 
@@ -1841,11 +1865,11 @@ int parse_platform_config(struct hfi1_devdata *dd)
 							table_length_dwords;
 				break;
 			default:
-				dd_dev_info(dd,
-					    "%s: Unknown data table %d, offset %ld\n",
-					    __func__, table_type,
-					    (ptr - (u32 *)
-					     dd->platform_config.data));
+				dd_dev_err(dd,
+					   "%s: Unknown data table %d, offset %ld\n",
+					   __func__, table_type,
+					   (ptr - (u32 *)
+					    dd->platform_config.data));
 				goto bail; /* We don't trust this file now */
 			}
 			pcfgcache->config_tables[table_type].table = ptr;
@@ -1865,11 +1889,11 @@ int parse_platform_config(struct hfi1_devdata *dd)
 			case PLATFORM_CONFIG_VARIABLE_SETTINGS_TABLE:
 				break;
 			default:
-				dd_dev_info(dd,
-					    "%s: Unknown meta table %d, offset %ld\n",
-					    __func__, table_type,
-					    (ptr -
-					     (u32 *)dd->platform_config.data));
+				dd_dev_err(dd,
+					   "%s: Unknown meta table %d, offset %ld\n",
+					   __func__, table_type,
+					   (ptr -
+					    (u32 *)dd->platform_config.data));
 				goto bail; /* We don't trust this file now */
 			}
 			pcfgcache->config_tables[table_type].table_metadata =
@@ -1884,10 +1908,9 @@ int parse_platform_config(struct hfi1_devdata *dd)
 		/* Jump the table */
 		ptr += table_length_dwords;
 		if (crc != *ptr) {
-			dd_dev_info(dd, "%s: Failed CRC check at offset %ld\n",
-				    __func__, (ptr -
-					       (u32 *)
-					       dd->platform_config.data));
+			dd_dev_err(dd, "%s: Failed CRC check at offset %ld\n",
+				   __func__, (ptr -
+				   (u32 *)dd->platform_config.data));
 			goto bail;
 		}
 		/* Jump the CRC DWORD */
@@ -1901,6 +1924,84 @@ bail:
 	return ret;
 }
 
+static void get_integrated_platform_config_field(
+		struct hfi1_devdata *dd,
+		enum platform_config_table_type_encoding table_type,
+		int field_index, u32 *data)
+{
+	struct hfi1_pportdata *ppd = dd->pport;
+	u8 *cache = ppd->qsfp_info.cache;
+	u32 tx_preset = 0;
+
+	switch (table_type) {
+	case PLATFORM_CONFIG_SYSTEM_TABLE:
+		if (field_index == SYSTEM_TABLE_QSFP_POWER_CLASS_MAX)
+			*data = ppd->max_power_class;
+		else if (field_index == SYSTEM_TABLE_QSFP_ATTENUATION_DEFAULT_25G)
+			*data = ppd->default_atten;
+		break;
+	case PLATFORM_CONFIG_PORT_TABLE:
+		if (field_index == PORT_TABLE_PORT_TYPE)
+			*data = ppd->port_type;
+		else if (field_index == PORT_TABLE_LOCAL_ATTEN_25G)
+			*data = ppd->local_atten;
+		else if (field_index == PORT_TABLE_REMOTE_ATTEN_25G)
+			*data = ppd->remote_atten;
+		break;
+	case PLATFORM_CONFIG_RX_PRESET_TABLE:
+		if (field_index == RX_PRESET_TABLE_QSFP_RX_CDR_APPLY)
+			*data = (ppd->rx_preset & QSFP_RX_CDR_APPLY_SMASK) >>
+				QSFP_RX_CDR_APPLY_SHIFT;
+		else if (field_index == RX_PRESET_TABLE_QSFP_RX_EMP_APPLY)
+			*data = (ppd->rx_preset & QSFP_RX_EMP_APPLY_SMASK) >>
+				QSFP_RX_EMP_APPLY_SHIFT;
+		else if (field_index == RX_PRESET_TABLE_QSFP_RX_AMP_APPLY)
+			*data = (ppd->rx_preset & QSFP_RX_AMP_APPLY_SMASK) >>
+				QSFP_RX_AMP_APPLY_SHIFT;
+		else if (field_index == RX_PRESET_TABLE_QSFP_RX_CDR)
+			*data = (ppd->rx_preset & QSFP_RX_CDR_SMASK) >>
+				QSFP_RX_CDR_SHIFT;
+		else if (field_index == RX_PRESET_TABLE_QSFP_RX_EMP)
+			*data = (ppd->rx_preset & QSFP_RX_EMP_SMASK) >>
+				QSFP_RX_EMP_SHIFT;
+		else if (field_index == RX_PRESET_TABLE_QSFP_RX_AMP)
+			*data = (ppd->rx_preset & QSFP_RX_AMP_SMASK) >>
+				QSFP_RX_AMP_SHIFT;
+		break;
+	case PLATFORM_CONFIG_TX_PRESET_TABLE:
+		if (cache[QSFP_EQ_INFO_OFFS] & 0x4)
+			tx_preset = ppd->tx_preset_eq;
+		else
+			tx_preset = ppd->tx_preset_noeq;
+		if (field_index == TX_PRESET_TABLE_PRECUR)
+			*data = (tx_preset & TX_PRECUR_SMASK) >>
+				TX_PRECUR_SHIFT;
+		else if (field_index == TX_PRESET_TABLE_ATTN)
+			*data = (tx_preset & TX_ATTN_SMASK) >>
+				TX_ATTN_SHIFT;
+		else if (field_index == TX_PRESET_TABLE_POSTCUR)
+			*data = (tx_preset & TX_POSTCUR_SMASK) >>
+				TX_POSTCUR_SHIFT;
+		else if (field_index == TX_PRESET_TABLE_QSFP_TX_CDR_APPLY)
+			*data = (tx_preset & QSFP_TX_CDR_APPLY_SMASK) >>
+				QSFP_TX_CDR_APPLY_SHIFT;
+		else if (field_index == TX_PRESET_TABLE_QSFP_TX_EQ_APPLY)
+			*data = (tx_preset & QSFP_TX_EQ_APPLY_SMASK) >>
+				QSFP_TX_EQ_APPLY_SHIFT;
+		else if (field_index == TX_PRESET_TABLE_QSFP_TX_CDR)
+			*data = (tx_preset & QSFP_TX_CDR_SMASK) >>
+				QSFP_TX_CDR_SHIFT;
+		else if (field_index == TX_PRESET_TABLE_QSFP_TX_EQ)
+			*data = (tx_preset & QSFP_TX_EQ_SMASK) >>
+				QSFP_TX_EQ_SHIFT;
+		break;
+	case PLATFORM_CONFIG_QSFP_ATTEN_TABLE:
+	case PLATFORM_CONFIG_VARIABLE_SETTINGS_TABLE:
+	default:
+		break;
+	}
+}
+
 static int get_platform_fw_field_metadata(struct hfi1_devdata *dd, int table,
 					  int field, u32 *field_len_bits,
 					  u32 *field_start_bits)
@@ -1976,6 +2077,15 @@ int get_platform_config_field(struct hfi1_devdata *dd,
 	else
 		return -EINVAL;
 
+	if (is_integrated(dd) && !platform_config_load) {
+		/*
+		 * Use saved configuration from ppd for integrated platforms
+		 */
+		get_integrated_platform_config_field(dd, table_type,
+						     field_index, data);
+		return 0;
+	}
+
 	ret = get_platform_fw_field_metadata(dd, table_type, field_index,
 					     &field_len_bits,
 					     &field_start_bits);

drivers/infiniband/hw/hfi1/hfi.h

@@ -492,6 +492,9 @@ struct rvt_sge_state;
 #define HFI1_MIN_VLS_SUPPORTED 1
 #define HFI1_MAX_VLS_SUPPORTED 8
 
+#define HFI1_GUIDS_PER_PORT  5
+#define HFI1_PORT_GUID_INDEX 0
+
 static inline void incr_cntr64(u64 *cntr)
 {
 	if (*cntr < (u64)-1LL)
@@ -559,11 +562,20 @@ struct hfi1_pportdata {
 	struct kobject vl2mtu_kobj;
 
 	/* PHY support */
-	u32 port_type;
 	struct qsfp_data qsfp_info;
+	/* Values for SI tuning of SerDes */
+	u32 port_type;
+	u32 tx_preset_eq;
+	u32 tx_preset_noeq;
+	u32 rx_preset;
+	u8  local_atten;
+	u8  remote_atten;
+	u8  default_atten;
+	u8  max_power_class;
+
+	/* GUIDs for this interface, in host order, guids[0] is a port guid */
+	u64 guids[HFI1_GUIDS_PER_PORT];
 
-	/* GUID for this interface, in host order */
-	u64 guid;
 	/* GUID for peer interface, in host order */
 	u64 neighbor_guid;
 
@@ -826,32 +838,29 @@ struct hfi1_devdata {
 	u8 __iomem *kregend;
 	/* physical address of chip for io_remap, etc. */
 	resource_size_t physaddr;
-	/* receive context data */
-	struct hfi1_ctxtdata **rcd;
+	/* Per VL data. Enough for all VLs but not all elements are set/used. */
+	struct per_vl_data vld[PER_VL_SEND_CONTEXTS];
 	/* send context data */
 	struct send_context_info *send_contexts;
 	/* map hardware send contexts to software index */
 	u8 *hw_to_sw;
 	/* spinlock for allocating and releasing send context resources */
 	spinlock_t sc_lock;
-	/* Per VL data. Enough for all VLs but not all elements are set/used. */
-	struct per_vl_data vld[PER_VL_SEND_CONTEXTS];
 	/* lock for pio_map */
 	spinlock_t pio_map_lock;
+	/* Send Context initialization lock. */
+	spinlock_t sc_init_lock;
+	/* lock for sdma_map */
+	spinlock_t                          sde_map_lock;
 	/* array of kernel send contexts */
 	struct send_context **kernel_send_context;
 	/* array of vl maps */
 	struct pio_vl_map __rcu *pio_map;
-	/* seqlock for sc2vl */
-	seqlock_t sc2vl_lock;
-	u64 sc2vl[4];
-	/* Send Context initialization lock. */
-	spinlock_t sc_init_lock;
+	/* default flags to last descriptor */
+	u64 default_desc1;
 
 	/* fields common to all SDMA engines */
 
-	/* default flags to last descriptor */
-	u64 default_desc1;
 	volatile __le64                    *sdma_heads_dma; /* DMA'ed by chip */
 	dma_addr_t                          sdma_heads_phys;
 	void                               *sdma_pad_dma; /* DMA'ed by chip */
@@ -862,8 +871,6 @@ struct hfi1_devdata {
 	u32                                 chip_sdma_engines;
 	/* num used */
 	u32                                 num_sdma;
-	/* lock for sdma_map */
-	spinlock_t                          sde_map_lock;
 	/* array of engines sized by num_sdma */
 	struct sdma_engine                 *per_sdma;
 	/* array of vl maps */
@@ -872,14 +879,11 @@ struct hfi1_devdata {
 	wait_queue_head_t		  sdma_unfreeze_wq;
 	atomic_t			  sdma_unfreeze_count;
 
+	u32 lcb_access_count;		/* count of LCB users */
+
 	/* common data between shared ASIC HFIs in this OS */
 	struct hfi1_asic_data *asic_data;
 
-	/* hfi1_pportdata, points to array of (physical) port-specific
-	 * data structs, indexed by pidx (0..n-1)
-	 */
-	struct hfi1_pportdata *pport;
-
 	/* mem-mapped pointer to base of PIO buffers */
 	void __iomem *piobase;
 	/*
@@ -896,20 +900,13 @@ struct hfi1_devdata {
 	/* send context numbers and sizes for each type */
 	struct sc_config_sizes sc_sizes[SC_MAX];
 
-	u32 lcb_access_count;		/* count of LCB users */
-
 	char *boardname; /* human readable board info */
 
-	/* device (not port) flags, basically device capabilities */
-	u32 flags;
-
 	/* reset value */
 	u64 z_int_counter;
 	u64 z_rcv_limit;
 	u64 z_send_schedule;
-	/* percpu int_counter */
-	u64 __percpu *int_counter;
-	u64 __percpu *rcv_limit;
+
 	u64 __percpu *send_schedule;
 	/* number of receive contexts in use by the driver */
 	u32 num_rcv_contexts;
@@ -924,6 +921,7 @@ struct hfi1_devdata {
 	/* base receive interrupt timeout, in CSR units */
 	u32 rcv_intr_timeout_csr;
 
+	u32 freezelen; /* max length of freezemsg */
 	u64 __iomem *egrtidbase;
 	spinlock_t sendctrl_lock; /* protect changes to SendCtrl */
 	spinlock_t rcvctrl_lock; /* protect changes to RcvCtrl */
@@ -945,7 +943,6 @@ struct hfi1_devdata {
 	 * IB link status cheaply
 	 */
 	struct hfi1_status *status;
-	u32 freezelen; /* max length of freezemsg */
 
 	/* revision register shadow */
 	u64 revision;
@@ -973,6 +970,8 @@ struct hfi1_devdata {
 	u16 rcvegrbufsize_shift;
 	/* both sides of the PCIe link are gen3 capable */
 	u8 link_gen3_capable;
+	/* default link down value (poll/sleep) */
+	u8 link_default;
 	/* localbus width (1, 2,4,8,16,32) from config space  */
 	u32 lbus_width;
 	/* localbus speed in MHz */
@@ -1008,8 +1007,6 @@ struct hfi1_devdata {
 	u8 hfi1_id;
 	/* implementation code */
 	u8 icode;
-	/* default link down value (poll/sleep) */
-	u8 link_default;
 	/* vAU of this device */
 	u8 vau;
 	/* vCU of this device */
@@ -1020,27 +1017,17 @@ struct hfi1_devdata {
 	u16 vl15_init;
 
 	/* Misc small ints */
-	/* Number of physical ports available */
-	u8 num_pports;
-	/* Lowest context number which can be used by user processes */
-	u8 first_user_ctxt;
 	u8 n_krcv_queues;
 	u8 qos_shift;
-	u8 qpn_mask;
 
-	u16 rhf_offset; /* offset of RHF within receive header entry */
 	u16 irev;	/* implementation revision */
 	u16 dc8051_ver; /* 8051 firmware version */
 
+	spinlock_t hfi1_diag_trans_lock; /* protect diag observer ops */
 	struct platform_config platform_config;
 	struct platform_config_cache pcfg_cache;
 
 	struct diag_client *diag_client;
-	spinlock_t hfi1_diag_trans_lock; /* protect diag observer ops */
-
-	u8 psxmitwait_supported;
-	/* cycle length of PS* counters in HW (in picoseconds) */
-	u16 psxmitwait_check_rate;
 
 	/* MSI-X information */
 	struct hfi1_msix_entry *msix_entries;
@@ -1055,6 +1042,9 @@ struct hfi1_devdata {
 
 	struct rcv_array_data rcv_entries;
 
+	/* cycle length of PS* counters in HW (in picoseconds) */
+	u16 psxmitwait_check_rate;
+
 	/*
 	 * 64 bit synthetic counters
 	 */
@@ -1085,11 +1075,11 @@ struct hfi1_devdata {
 	struct err_info_rcvport err_info_rcvport;
 	struct err_info_constraint err_info_rcv_constraint;
 	struct err_info_constraint err_info_xmit_constraint;
-	u8 err_info_uncorrectable;
-	u8 err_info_fmconfig;
 
 	atomic_t drop_packet;
 	u8 do_drop;
+	u8 err_info_uncorrectable;
+	u8 err_info_fmconfig;
 
 	/*
 	 * Software counters for the status bits defined by the
@@ -1112,40 +1102,60 @@ struct hfi1_devdata {
 	u64 sw_cce_err_status_aggregate;
 	/* Software counter that aggregates all bypass packet rcv errors */
 	u64 sw_rcv_bypass_packet_errors;
-	/* receive interrupt functions */
-	rhf_rcv_function_ptr *rhf_rcv_function_map;
+	/* receive interrupt function */
 	rhf_rcv_function_ptr normal_rhf_rcv_functions[8];
 
+	/* Save the enabled LCB error bits */
+	u64 lcb_err_en;
+
 	/*
 	 * Capability to have different send engines simply by changing a
 	 * pointer value.
 	 */
-	send_routine process_pio_send;
+	send_routine process_pio_send ____cacheline_aligned_in_smp;
 	send_routine process_dma_send;
 	void (*pio_inline_send)(struct hfi1_devdata *dd, struct pio_buf *pbuf,
 				u64 pbc, const void *from, size_t count);
+	/* hfi1_pportdata, points to array of (physical) port-specific
+	 * data structs, indexed by pidx (0..n-1)
+	 */
+	struct hfi1_pportdata *pport;
+	/* receive context data */
+	struct hfi1_ctxtdata **rcd;
+	u64 __percpu *int_counter;
+	/* device (not port) flags, basically device capabilities */
+	u16 flags;
+	/* Number of physical ports available */
+	u8 num_pports;
+	/* Lowest context number which can be used by user processes */
+	u8 first_user_ctxt;
+	/* adding a new field here would make it part of this cacheline */
+
+	/* seqlock for sc2vl */
+	seqlock_t sc2vl_lock ____cacheline_aligned_in_smp;
+	u64 sc2vl[4];
+	/* receive interrupt functions */
+	rhf_rcv_function_ptr *rhf_rcv_function_map;
+	u64 __percpu *rcv_limit;
+	u16 rhf_offset; /* offset of RHF within receive header entry */
+	/* adding a new field here would make it part of this cacheline */
 
 	/* OUI comes from the HW. Used everywhere as 3 separate bytes. */
 	u8 oui1;
 	u8 oui2;
 	u8 oui3;
+	u8 dc_shutdown;
+
 	/* Timer and counter used to detect RcvBufOvflCnt changes */
 	struct timer_list rcverr_timer;
-	u32 rcv_ovfl_cnt;
 
 	wait_queue_head_t event_queue;
 
-	/* Save the enabled LCB error bits */
-	u64 lcb_err_en;
-	u8 dc_shutdown;
-
 	/* receive context tail dummy address */
 	__le64 *rcvhdrtail_dummy_kvaddr;
 	dma_addr_t rcvhdrtail_dummy_dma;
 
-	bool eprom_available;	/* true if EPROM is available for this device */
-	bool aspm_supported;	/* Does HW support ASPM */
-	bool aspm_enabled;	/* ASPM state: enabled/disabled */
+	u32 rcv_ovfl_cnt;
 	/* Serialize ASPM enable/disable between multiple verbs contexts */
 	spinlock_t aspm_lock;
 	/* Number of verbs contexts which have disabled ASPM */
@@ -1155,8 +1165,11 @@ struct hfi1_devdata {
 	/* Used to wait for outstanding user space clients before dev removal */
 	struct completion user_comp;
 
-	struct hfi1_affinity *affinity;
+	bool eprom_available;	/* true if EPROM is available for this device */
+	bool aspm_supported;	/* Does HW support ASPM */
+	bool aspm_enabled;	/* ASPM state: enabled/disabled */
 	struct rhashtable sdma_rht;
+
 	struct kobject kobj;
 };
 
@@ -1603,6 +1616,17 @@ static inline u16 hfi1_get_pkey(struct hfi1_ibport *ibp, unsigned index)
 	return ret;
 }
 
+/*
+ * Return the indexed GUID from the port GUIDs table.
+ */
+static inline __be64 get_sguid(struct hfi1_ibport *ibp, unsigned int index)
+{
+	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
+
+	WARN_ON(index >= HFI1_GUIDS_PER_PORT);
+	return cpu_to_be64(ppd->guids[index]);
+}
+
 /*
  * Called by readers of cc_state only, must call under rcu_read_lock().
  */
@@ -1982,6 +2006,12 @@ static inline u32 qsfp_resource(struct hfi1_devdata *dd)
 	return i2c_target(dd->hfi1_id);
 }
 
+/* Is this device integrated or discrete? */
+static inline bool is_integrated(struct hfi1_devdata *dd)
+{
+	return dd->pcidev->device == PCI_DEVICE_ID_INTEL1;
+}
+
 int hfi1_tempsense_rd(struct hfi1_devdata *dd, struct hfi1_temp *temp);
 
 #define DD_DEV_ENTRY(dd)       __string(dev, dev_name(&(dd)->pcidev->dev))

drivers/infiniband/hw/hfi1/iowait.h

@@ -64,6 +64,7 @@ struct sdma_engine;
 /**
  * struct iowait - linkage for delayed progress/waiting
  * @list: used to add/insert into QP/PQ wait lists
+ * @lock: uses to record the list head lock
  * @tx_head: overflow list of sdma_txreq's
  * @sleep: no space callback
  * @wakeup: space callback wakeup
@@ -91,6 +92,11 @@ struct sdma_engine;
  * so sleeping is not allowed.
  *
  * The wait_dma member along with the iow
+ *
+ * The lock field is used by waiters to record
+ * the seqlock_t that guards the list head.
+ * Waiters explicity know that, but the destroy
+ * code that unwaits QPs does not.
  */
 
 struct iowait {
@@ -103,6 +109,7 @@ struct iowait {
 		unsigned seq);
 	void (*wakeup)(struct iowait *wait, int reason);
 	void (*sdma_drained)(struct iowait *wait);
+	seqlock_t *lock;
 	struct work_struct iowork;
 	wait_queue_head_t wait_dma;
 	wait_queue_head_t wait_pio;
@@ -141,6 +148,7 @@ static inline void iowait_init(
 	void (*sdma_drained)(struct iowait *wait))
 {
 	wait->count = 0;
+	wait->lock = NULL;
 	INIT_LIST_HEAD(&wait->list);
 	INIT_LIST_HEAD(&wait->tx_head);
 	INIT_WORK(&wait->iowork, func);

drivers/infiniband/hw/hfi1/mad.c

@@ -128,7 +128,7 @@ static void send_trap(struct hfi1_ibport *ibp, void *data, unsigned len)
 	smp = send_buf->mad;
 	smp->base_version = OPA_MGMT_BASE_VERSION;
 	smp->mgmt_class = IB_MGMT_CLASS_SUBN_LID_ROUTED;
-	smp->class_version = OPA_SMI_CLASS_VERSION;
+	smp->class_version = OPA_SM_CLASS_VERSION;
 	smp->method = IB_MGMT_METHOD_TRAP;
 	ibp->rvp.tid++;
 	smp->tid = cpu_to_be64(ibp->rvp.tid);
@@ -336,20 +336,20 @@ static int __subn_get_opa_nodeinfo(struct opa_smp *smp, u32 am, u8 *data,
 	ni = (struct opa_node_info *)data;
 
 	/* GUID 0 is illegal */
-	if (am || pidx >= dd->num_pports || dd->pport[pidx].guid == 0) {
+	if (am || pidx >= dd->num_pports || ibdev->node_guid == 0 ||
+	    get_sguid(to_iport(ibdev, port), HFI1_PORT_GUID_INDEX) == 0) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
 
-	ni->port_guid = cpu_to_be64(dd->pport[pidx].guid);
+	ni->port_guid = get_sguid(to_iport(ibdev, port), HFI1_PORT_GUID_INDEX);
 	ni->base_version = OPA_MGMT_BASE_VERSION;
-	ni->class_version = OPA_SMI_CLASS_VERSION;
+	ni->class_version = OPA_SM_CLASS_VERSION;
 	ni->node_type = 1;     /* channel adapter */
 	ni->num_ports = ibdev->phys_port_cnt;
 	/* This is already in network order */
 	ni->system_image_guid = ib_hfi1_sys_image_guid;
-	/* Use first-port GUID as node */
-	ni->node_guid = cpu_to_be64(dd->pport->guid);
+	ni->node_guid = ibdev->node_guid;
 	ni->partition_cap = cpu_to_be16(hfi1_get_npkeys(dd));
 	ni->device_id = cpu_to_be16(dd->pcidev->device);
 	ni->revision = cpu_to_be32(dd->minrev);
@@ -373,19 +373,20 @@ static int subn_get_nodeinfo(struct ib_smp *smp, struct ib_device *ibdev,
 
 	/* GUID 0 is illegal */
 	if (smp->attr_mod || pidx >= dd->num_pports ||
-	    dd->pport[pidx].guid == 0)
+	    ibdev->node_guid == 0 ||
+	    get_sguid(to_iport(ibdev, port), HFI1_PORT_GUID_INDEX) == 0) {
 		smp->status |= IB_SMP_INVALID_FIELD;
-	else
-		nip->port_guid = cpu_to_be64(dd->pport[pidx].guid);
+		return reply((struct ib_mad_hdr *)smp);
+	}
 
+	nip->port_guid = get_sguid(to_iport(ibdev, port), HFI1_PORT_GUID_INDEX);
 	nip->base_version = OPA_MGMT_BASE_VERSION;
-	nip->class_version = OPA_SMI_CLASS_VERSION;
+	nip->class_version = OPA_SM_CLASS_VERSION;
 	nip->node_type = 1;     /* channel adapter */
 	nip->num_ports = ibdev->phys_port_cnt;
 	/* This is already in network order */
 	nip->sys_guid = ib_hfi1_sys_image_guid;
-	 /* Use first-port GUID as node */
-	nip->node_guid = cpu_to_be64(dd->pport->guid);
+	nip->node_guid = ibdev->node_guid;
 	nip->partition_cap = cpu_to_be16(hfi1_get_npkeys(dd));
 	nip->device_id = cpu_to_be16(dd->pcidev->device);
 	nip->revision = cpu_to_be32(dd->minrev);
@@ -2302,7 +2303,7 @@ static int pma_get_opa_classportinfo(struct opa_pma_mad *pmp,
 		pmp->mad_hdr.status |= IB_SMP_INVALID_FIELD;
 
 	p->base_version = OPA_MGMT_BASE_VERSION;
-	p->class_version = OPA_SMI_CLASS_VERSION;
+	p->class_version = OPA_SM_CLASS_VERSION;
 	/*
 	 * Expected response time is 4.096 usec. * 2^18 == 1.073741824 sec.
 	 */
@@ -4022,7 +4023,7 @@ static int process_subn_opa(struct ib_device *ibdev, int mad_flags,
 
 	am = be32_to_cpu(smp->attr_mod);
 	attr_id = smp->attr_id;
-	if (smp->class_version != OPA_SMI_CLASS_VERSION) {
+	if (smp->class_version != OPA_SM_CLASS_VERSION) {
 		smp->status |= IB_SMP_UNSUP_VERSION;
 		ret = reply((struct ib_mad_hdr *)smp);
 		return ret;
@@ -4232,7 +4233,7 @@ static int process_perf_opa(struct ib_device *ibdev, u8 port,
 
 	*out_mad = *in_mad;
 
-	if (pmp->mad_hdr.class_version != OPA_SMI_CLASS_VERSION) {
+	if (pmp->mad_hdr.class_version != OPA_SM_CLASS_VERSION) {
 		pmp->mad_hdr.status |= IB_SMP_UNSUP_VERSION;
 		return reply((struct ib_mad_hdr *)pmp);
 	}

drivers/infiniband/hw/hfi1/mmu_rb.c

@@ -81,7 +81,7 @@ static void do_remove(struct mmu_rb_handler *handler,
 		      struct list_head *del_list);
 static void handle_remove(struct work_struct *work);
 
-static struct mmu_notifier_ops mn_opts = {
+static const struct mmu_notifier_ops mn_opts = {
 	.invalidate_page = mmu_notifier_page,
 	.invalidate_range_start = mmu_notifier_range_start,
 };

drivers/infiniband/hw/hfi1/pio.c

@@ -758,6 +758,7 @@ struct send_context *sc_alloc(struct hfi1_devdata *dd, int type,
 	sc->hw_context = hw_context;
 	cr_group_addresses(sc, &dma);
 	sc->credits = sci->credits;
+	sc->size = sc->credits * PIO_BLOCK_SIZE;
 
 /* PIO Send Memory Address details */
 #define PIO_ADDR_CONTEXT_MASK 0xfful
@@ -1242,6 +1243,7 @@ int sc_enable(struct send_context *sc)
 	sc->free = 0;
 	sc->alloc_free = 0;
 	sc->fill = 0;
+	sc->fill_wrap = 0;
 	sc->sr_head = 0;
 	sc->sr_tail = 0;
 	sc->flags = 0;
@@ -1385,7 +1387,7 @@ struct pio_buf *sc_buffer_alloc(struct send_context *sc, u32 dw_len,
 	unsigned long flags;
 	unsigned long avail;
 	unsigned long blocks = dwords_to_blocks(dw_len);
-	unsigned long start_fill;
+	u32 fill_wrap;
 	int trycount = 0;
 	u32 head, next;
 
@@ -1410,9 +1412,7 @@ retry:
 			(sc->fill - sc->alloc_free);
 		if (blocks > avail) {
 			/* still no room, actively update */
-			spin_unlock_irqrestore(&sc->alloc_lock, flags);
 			sc_release_update(sc);
-			spin_lock_irqsave(&sc->alloc_lock, flags);
 			sc->alloc_free = ACCESS_ONCE(sc->free);
 			trycount++;
 			goto retry;
@@ -1428,8 +1428,11 @@ retry:
 	head = sc->sr_head;
 
 	/* "allocate" the buffer */
-	start_fill = sc->fill;
 	sc->fill += blocks;
+	fill_wrap = sc->fill_wrap;
+	sc->fill_wrap += blocks;
+	if (sc->fill_wrap >= sc->credits)
+		sc->fill_wrap = sc->fill_wrap - sc->credits;
 
 	/*
 	 * Fill the parts that the releaser looks at before moving the head.
@@ -1458,11 +1461,8 @@ retry:
 	spin_unlock_irqrestore(&sc->alloc_lock, flags);
 
 	/* finish filling in the buffer outside the lock */
-	pbuf->start = sc->base_addr + ((start_fill % sc->credits)
-							* PIO_BLOCK_SIZE);
-	pbuf->size = sc->credits * PIO_BLOCK_SIZE;
-	pbuf->end = sc->base_addr + pbuf->size;
-	pbuf->block_count = blocks;
+	pbuf->start = sc->base_addr + fill_wrap * PIO_BLOCK_SIZE;
+	pbuf->end = sc->base_addr + sc->size;
 	pbuf->qw_written = 0;
 	pbuf->carry_bytes = 0;
 	pbuf->carry.val64 = 0;
@@ -1573,6 +1573,7 @@ static void sc_piobufavail(struct send_context *sc)
 		qp = iowait_to_qp(wait);
 		priv = qp->priv;
 		list_del_init(&priv->s_iowait.list);
+		priv->s_iowait.lock = NULL;
 		/* refcount held until actual wake up */
 		qps[n++] = qp;
 	}
@@ -2028,29 +2029,17 @@ freesc15:
 int init_credit_return(struct hfi1_devdata *dd)
 {
 	int ret;
-	int num_numa;
 	int i;
 
-	num_numa = num_online_nodes();
-	/* enforce the expectation that the numas are compact */
-	for (i = 0; i < num_numa; i++) {
-		if (!node_online(i)) {
-			dd_dev_err(dd, "NUMA nodes are not compact\n");
-			ret = -EINVAL;
-			goto done;
-		}
-	}
-
 	dd->cr_base = kcalloc(
-		num_numa,
+		node_affinity.num_possible_nodes,
 		sizeof(struct credit_return_base),
 		GFP_KERNEL);
 	if (!dd->cr_base) {
-		dd_dev_err(dd, "Unable to allocate credit return base\n");
 		ret = -ENOMEM;
 		goto done;
 	}
-	for (i = 0; i < num_numa; i++) {
+	for_each_node_with_cpus(i) {
 		int bytes = TXE_NUM_CONTEXTS * sizeof(struct credit_return);
 
 		set_dev_node(&dd->pcidev->dev, i);
@@ -2077,14 +2066,11 @@ done:
 
 void free_credit_return(struct hfi1_devdata *dd)
 {
-	int num_numa;
 	int i;
 
 	if (!dd->cr_base)
 		return;
-
-	num_numa = num_online_nodes();
-	for (i = 0; i < num_numa; i++) {
+	for (i = 0; i < node_affinity.num_possible_nodes; i++) {
 		if (dd->cr_base[i].va) {
 			dma_free_coherent(&dd->pcidev->dev,
 					  TXE_NUM_CONTEXTS *

drivers/infiniband/hw/hfi1/pio.h

@@ -83,53 +83,55 @@ struct pio_buf {
 	void *arg;		/* argument for cb */
 	void __iomem *start;	/* buffer start address */
 	void __iomem *end;	/* context end address */
-	unsigned long size;	/* context size, in bytes */
 	unsigned long sent_at;	/* buffer is sent when <= free */
-	u32 block_count;	/* size of buffer, in blocks */
-	u32 qw_written;		/* QW written so far */
-	u32 carry_bytes;	/* number of valid bytes in carry */
 	union mix carry;	/* pending unwritten bytes */
+	u16 qw_written;		/* QW written so far */
+	u8 carry_bytes;	/* number of valid bytes in carry */
 };
 
 /* cache line aligned pio buffer array */
 union pio_shadow_ring {
 	struct pio_buf pbuf;
-	u64 unused[16];		/* cache line spacer */
 } ____cacheline_aligned;
 
 /* per-NUMA send context */
 struct send_context {
 	/* read-only after init */
 	struct hfi1_devdata *dd;		/* device */
-	void __iomem *base_addr;	/* start of PIO memory */
 	union pio_shadow_ring *sr;	/* shadow ring */
+	void __iomem *base_addr;	/* start of PIO memory */
+	u32 __percpu *buffers_allocated;/* count of buffers allocated */
+	u32 size;			/* context size, in bytes */
 
-	volatile __le64 *hw_free;	/* HW free counter */
-	struct work_struct halt_work;	/* halted context work queue entry */
-	unsigned long flags;		/* flags */
 	int node;			/* context home node */
-	int type;			/* context type */
-	u32 sw_index;			/* software index number */
-	u32 hw_context;			/* hardware context number */
-	u32 credits;			/* number of blocks in context */
 	u32 sr_size;			/* size of the shadow ring */
-	u32 group;			/* credit return group */
+	u16 flags;			/* flags */
+	u8  type;			/* context type */
+	u8  sw_index;			/* software index number */
+	u8  hw_context;			/* hardware context number */
+	u8  group;			/* credit return group */
+
 	/* allocator fields */
 	spinlock_t alloc_lock ____cacheline_aligned_in_smp;
+	u32 sr_head;			/* shadow ring head */
 	unsigned long fill;		/* official alloc count */
 	unsigned long alloc_free;	/* copy of free (less cache thrash) */
-	u32 sr_head;			/* shadow ring head */
+	u32 fill_wrap;			/* tracks fill within ring */
+	u32 credits;			/* number of blocks in context */
+	/* adding a new field here would make it part of this cacheline */
+
 	/* releaser fields */
 	spinlock_t release_lock ____cacheline_aligned_in_smp;
-	unsigned long free;		/* official free count */
 	u32 sr_tail;			/* shadow ring tail */
+	unsigned long free;		/* official free count */
+	volatile __le64 *hw_free;	/* HW free counter */
 	/* list for PIO waiters */
 	struct list_head piowait  ____cacheline_aligned_in_smp;
 	spinlock_t credit_ctrl_lock ____cacheline_aligned_in_smp;
-	u64 credit_ctrl;		/* cache for credit control */
 	u32 credit_intr_count;		/* count of credit intr users */
-	u32 __percpu *buffers_allocated;/* count of buffers allocated */
+	u64 credit_ctrl;		/* cache for credit control */
 	wait_queue_head_t halt_wait;    /* wait until kernel sees interrupt */
+	struct work_struct halt_work;	/* halted context work queue entry */
 };
 
 /* send context flags */

drivers/infiniband/hw/hfi1/pio_copy.c

@@ -129,8 +129,8 @@ void pio_copy(struct hfi1_devdata *dd, struct pio_buf *pbuf, u64 pbc,
 				dest += sizeof(u64);
 			}
 
-			dest -= pbuf->size;
-			dend -= pbuf->size;
+			dest -= pbuf->sc->size;
+			dend -= pbuf->sc->size;
 		}
 
 		/* write 8-byte non-SOP, non-wrap chunk data */
@@ -361,8 +361,8 @@ void seg_pio_copy_start(struct pio_buf *pbuf, u64 pbc,
 				dest += sizeof(u64);
 			}
 
-			dest -= pbuf->size;
-			dend -= pbuf->size;
+			dest -= pbuf->sc->size;
+			dend -= pbuf->sc->size;
 		}
 
 		/* write 8-byte non-SOP, non-wrap chunk data */
@@ -458,8 +458,8 @@ static void mid_copy_mix(struct pio_buf *pbuf, const void *from, size_t nbytes)
 			dest += sizeof(u64);
 		}
 
-		dest -= pbuf->size;
-		dend -= pbuf->size;
+		dest -= pbuf->sc->size;
+		dend -= pbuf->sc->size;
 	}
 
 	/* write 8-byte non-SOP, non-wrap chunk data */
@@ -492,7 +492,7 @@ static void mid_copy_mix(struct pio_buf *pbuf, const void *from, size_t nbytes)
 		 */
 		/* adjust if we have wrapped */
 		if (dest >= pbuf->end)
-			dest -= pbuf->size;
+			dest -= pbuf->sc->size;
 		/* jump to the SOP range if within the first block */
 		else if (pbuf->qw_written < PIO_BLOCK_QWS)
 			dest += SOP_DISTANCE;
@@ -584,8 +584,8 @@ static void mid_copy_straight(struct pio_buf *pbuf,
 			dest += sizeof(u64);
 		}
 
-		dest -= pbuf->size;
-		dend -= pbuf->size;
+		dest -= pbuf->sc->size;
+		dend -= pbuf->sc->size;
 	}
 
 	/* write 8-byte non-SOP, non-wrap chunk data */
@@ -666,7 +666,7 @@ void seg_pio_copy_mid(struct pio_buf *pbuf, const void *from, size_t nbytes)
 			 */
 			/* adjust if we've wrapped */
 			if (dest >= pbuf->end)
-				dest -= pbuf->size;
+				dest -= pbuf->sc->size;
 			/* jump to SOP range if within the first block */
 			else if (pbuf->qw_written < PIO_BLOCK_QWS)
 				dest += SOP_DISTANCE;
@@ -719,7 +719,7 @@ void seg_pio_copy_end(struct pio_buf *pbuf)
 	 */
 	/* adjust if we have wrapped */
 	if (dest >= pbuf->end)
-		dest -= pbuf->size;
+		dest -= pbuf->sc->size;
 	/* jump to the SOP range if within the first block */
 	else if (pbuf->qw_written < PIO_BLOCK_QWS)
 		dest += SOP_DISTANCE;

drivers/infiniband/hw/hfi1/platform.c

@@ -49,6 +49,90 @@
 #include "efivar.h"
 #include "eprom.h"
 
+static int validate_scratch_checksum(struct hfi1_devdata *dd)
+{
+	u64 checksum = 0, temp_scratch = 0;
+	int i, j, version;
+
+	temp_scratch = read_csr(dd, ASIC_CFG_SCRATCH);
+	version = (temp_scratch & BITMAP_VERSION_SMASK) >> BITMAP_VERSION_SHIFT;
+
+	/* Prevent power on default of all zeroes from passing checksum */
+	if (!version)
+		return 0;
+
+	/*
+	 * ASIC scratch 0 only contains the checksum and bitmap version as
+	 * fields of interest, both of which are handled separately from the
+	 * loop below, so skip it
+	 */
+	checksum += version;
+	for (i = 1; i < ASIC_NUM_SCRATCH; i++) {
+		temp_scratch = read_csr(dd, ASIC_CFG_SCRATCH + (8 * i));
+		for (j = sizeof(u64); j != 0; j -= 2) {
+			checksum += (temp_scratch & 0xFFFF);
+			temp_scratch >>= 16;
+		}
+	}
+
+	while (checksum >> 16)
+		checksum = (checksum & CHECKSUM_MASK) + (checksum >> 16);
+
+	temp_scratch = read_csr(dd, ASIC_CFG_SCRATCH);
+	temp_scratch &= CHECKSUM_SMASK;
+	temp_scratch >>= CHECKSUM_SHIFT;
+
+	if (checksum + temp_scratch == 0xFFFF)
+		return 1;
+	return 0;
+}
+
+static void save_platform_config_fields(struct hfi1_devdata *dd)
+{
+	struct hfi1_pportdata *ppd = dd->pport;
+	u64 temp_scratch = 0, temp_dest = 0;
+
+	temp_scratch = read_csr(dd, ASIC_CFG_SCRATCH_1);
+
+	temp_dest = temp_scratch &
+		    (dd->hfi1_id ? PORT1_PORT_TYPE_SMASK :
+		     PORT0_PORT_TYPE_SMASK);
+	ppd->port_type = temp_dest >>
+			 (dd->hfi1_id ? PORT1_PORT_TYPE_SHIFT :
+			  PORT0_PORT_TYPE_SHIFT);
+
+	temp_dest = temp_scratch &
+		    (dd->hfi1_id ? PORT1_LOCAL_ATTEN_SMASK :
+		     PORT0_LOCAL_ATTEN_SMASK);
+	ppd->local_atten = temp_dest >>
+			   (dd->hfi1_id ? PORT1_LOCAL_ATTEN_SHIFT :
+			    PORT0_LOCAL_ATTEN_SHIFT);
+
+	temp_dest = temp_scratch &
+		    (dd->hfi1_id ? PORT1_REMOTE_ATTEN_SMASK :
+		     PORT0_REMOTE_ATTEN_SMASK);
+	ppd->remote_atten = temp_dest >>
+			    (dd->hfi1_id ? PORT1_REMOTE_ATTEN_SHIFT :
+			     PORT0_REMOTE_ATTEN_SHIFT);
+
+	temp_dest = temp_scratch &
+		    (dd->hfi1_id ? PORT1_DEFAULT_ATTEN_SMASK :
+		     PORT0_DEFAULT_ATTEN_SMASK);
+	ppd->default_atten = temp_dest >>
+			     (dd->hfi1_id ? PORT1_DEFAULT_ATTEN_SHIFT :
+			      PORT0_DEFAULT_ATTEN_SHIFT);
+
+	temp_scratch = read_csr(dd, dd->hfi1_id ? ASIC_CFG_SCRATCH_3 :
+				ASIC_CFG_SCRATCH_2);
+
+	ppd->tx_preset_eq = (temp_scratch & TX_EQ_SMASK) >> TX_EQ_SHIFT;
+	ppd->tx_preset_noeq = (temp_scratch & TX_NO_EQ_SMASK) >> TX_NO_EQ_SHIFT;
+	ppd->rx_preset = (temp_scratch & RX_SMASK) >> RX_SHIFT;
+
+	ppd->max_power_class = (temp_scratch & QSFP_MAX_POWER_SMASK) >>
+				QSFP_MAX_POWER_SHIFT;
+}
+
 void get_platform_config(struct hfi1_devdata *dd)
 {
 	int ret = 0;
@@ -56,38 +140,49 @@ void get_platform_config(struct hfi1_devdata *dd)
 	u8 *temp_platform_config = NULL;
 	u32 esize;
 
-	ret = eprom_read_platform_config(dd, (void **)&temp_platform_config,
-					 &esize);
-	if (!ret) {
-		/* success */
-		size = esize;
-		goto success;
+	if (is_integrated(dd)) {
+		if (validate_scratch_checksum(dd)) {
+			save_platform_config_fields(dd);
+			return;
+		}
+		dd_dev_err(dd, "%s: Config bitmap corrupted/uninitialized\n",
+			   __func__);
+		dd_dev_err(dd,
+			   "%s: Please update your BIOS to support active channels\n",
+			   __func__);
+	} else {
+		ret = eprom_read_platform_config(dd,
+						 (void **)&temp_platform_config,
+						 &esize);
+		if (!ret) {
+			/* success */
+			dd->platform_config.data = temp_platform_config;
+			dd->platform_config.size = esize;
+			return;
+		}
+		/* fail, try EFI variable */
+
+		ret = read_hfi1_efi_var(dd, "configuration", &size,
+					(void **)&temp_platform_config);
+		if (!ret) {
+			dd->platform_config.data = temp_platform_config;
+			dd->platform_config.size = size;
+			return;
+		}
 	}
-	/* fail, try EFI variable */
-
-	ret = read_hfi1_efi_var(dd, "configuration", &size,
-				(void **)&temp_platform_config);
-	if (!ret)
-		goto success;
-
-	dd_dev_info(dd,
-		    "%s: Failed to get platform config from UEFI, falling back to request firmware\n",
-		    __func__);
+	dd_dev_err(dd,
+		   "%s: Failed to get platform config, falling back to sub-optimal default file\n",
+		   __func__);
 	/* fall back to request firmware */
 	platform_config_load = 1;
-	return;
-
-success:
-	dd->platform_config.data = temp_platform_config;
-	dd->platform_config.size = size;
 }
 
 void free_platform_config(struct hfi1_devdata *dd)
 {
 	if (!platform_config_load) {
 		/*
-		 * was loaded from EFI, release memory
-		 * allocated by read_efi_var
+		 * was loaded from EFI or the EPROM, release memory
+		 * allocated by read_efi_var/eprom_read_platform_config
 		 */
 		kfree(dd->platform_config.data);
 	}
@@ -100,12 +195,16 @@ void free_platform_config(struct hfi1_devdata *dd)
 void get_port_type(struct hfi1_pportdata *ppd)
 {
 	int ret;
+	u32 temp;
 
 	ret = get_platform_config_field(ppd->dd, PLATFORM_CONFIG_PORT_TABLE, 0,
-					PORT_TABLE_PORT_TYPE, &ppd->port_type,
+					PORT_TABLE_PORT_TYPE, &temp,
 					4);
-	if (ret)
+	if (ret) {
 		ppd->port_type = PORT_TYPE_UNKNOWN;
+		return;
+	}
+	ppd->port_type = temp;
 }
 
 int set_qsfp_tx(struct hfi1_pportdata *ppd, int on)
@@ -538,6 +637,38 @@ static void apply_tx_lanes(struct hfi1_pportdata *ppd, u8 field_id,
 	}
 }
 
+/*
+ * Return a special SerDes setting for low power AOC cables.  The power class
+ * threshold and setting being used were all found by empirical testing.
+ *
+ * Summary of the logic:
+ *
+ * if (QSFP and QSFP_TYPE == AOC and QSFP_POWER_CLASS < 4)
+ *     return 0xe
+ * return 0; // leave at default
+ */
+static u8 aoc_low_power_setting(struct hfi1_pportdata *ppd)
+{
+	u8 *cache = ppd->qsfp_info.cache;
+	int power_class;
+
+	/* QSFP only */
+	if (ppd->port_type != PORT_TYPE_QSFP)
+		return 0; /* leave at default */
+
+	/* active optical cables only */
+	switch ((cache[QSFP_MOD_TECH_OFFS] & 0xF0) >> 4) {
+	case 0x0 ... 0x9: /* fallthrough */
+	case 0xC: /* fallthrough */
+	case 0xE:
+		/* active AOC */
+		power_class = get_qsfp_power_class(cache[QSFP_MOD_PWR_OFFS]);
+		if (power_class < QSFP_POWER_CLASS_4)
+			return 0xe;
+	}
+	return 0; /* leave at default */
+}
+
 static void apply_tunings(
 		struct hfi1_pportdata *ppd, u32 tx_preset_index,
 		u8 tuning_method, u32 total_atten, u8 limiting_active)
@@ -606,7 +737,17 @@ static void apply_tunings(
 		tx_preset_index, TX_PRESET_TABLE_POSTCUR, &tx_preset, 4);
 	postcur = tx_preset;
 
-	config_data = precur | (attn << 8) | (postcur << 16);
+	/*
+	 * NOTES:
+	 * o The aoc_low_power_setting is applied to all lanes even
+	 *   though only lane 0's value is examined by the firmware.
+	 * o A lingering low power setting after a cable swap does
+	 *   not occur.  On cable unplug the 8051 is reset and
+	 *   restarted on cable insert.  This resets all settings to
+	 *   their default, erasing any previous low power setting.
+	 */
+	config_data = precur | (attn << 8) | (postcur << 16) |
+			(aoc_low_power_setting(ppd) << 24);
 
 	apply_tx_lanes(ppd, TX_EQ_SETTINGS, config_data,
 		       "Applying TX settings");

drivers/infiniband/hw/hfi1/platform.h

@@ -168,16 +168,6 @@ struct platform_config_cache {
 	struct platform_config_data config_tables[PLATFORM_CONFIG_TABLE_MAX];
 };
 
-static const u32 platform_config_table_limits[PLATFORM_CONFIG_TABLE_MAX] = {
-	0,
-	SYSTEM_TABLE_MAX,
-	PORT_TABLE_MAX,
-	RX_PRESET_TABLE_MAX,
-	TX_PRESET_TABLE_MAX,
-	QSFP_ATTEN_TABLE_MAX,
-	VARIABLE_SETTINGS_TABLE_MAX
-};
-
 /* This section defines default values and encodings for the
  * fields defined for each table above
  */
@@ -295,6 +285,123 @@ enum link_tuning_encoding {
 	OPA_UNKNOWN_TUNING
 };
 
+/*
+ * Shifts and masks for the link SI tuning values stuffed into the ASIC scratch
+ * registers for integrated platforms
+ */
+#define PORT0_PORT_TYPE_SHIFT		0
+#define PORT0_LOCAL_ATTEN_SHIFT		4
+#define PORT0_REMOTE_ATTEN_SHIFT	10
+#define PORT0_DEFAULT_ATTEN_SHIFT	32
+
+#define PORT1_PORT_TYPE_SHIFT		16
+#define PORT1_LOCAL_ATTEN_SHIFT		20
+#define PORT1_REMOTE_ATTEN_SHIFT	26
+#define PORT1_DEFAULT_ATTEN_SHIFT	40
+
+#define PORT0_PORT_TYPE_MASK		0xFUL
+#define PORT0_LOCAL_ATTEN_MASK		0x3FUL
+#define PORT0_REMOTE_ATTEN_MASK		0x3FUL
+#define PORT0_DEFAULT_ATTEN_MASK	0xFFUL
+
+#define PORT1_PORT_TYPE_MASK		0xFUL
+#define PORT1_LOCAL_ATTEN_MASK		0x3FUL
+#define PORT1_REMOTE_ATTEN_MASK		0x3FUL
+#define PORT1_DEFAULT_ATTEN_MASK	0xFFUL
+
+#define PORT0_PORT_TYPE_SMASK		(PORT0_PORT_TYPE_MASK << \
+					 PORT0_PORT_TYPE_SHIFT)
+#define PORT0_LOCAL_ATTEN_SMASK		(PORT0_LOCAL_ATTEN_MASK << \
+					 PORT0_LOCAL_ATTEN_SHIFT)
+#define PORT0_REMOTE_ATTEN_SMASK	(PORT0_REMOTE_ATTEN_MASK << \
+					 PORT0_REMOTE_ATTEN_SHIFT)
+#define PORT0_DEFAULT_ATTEN_SMASK	(PORT0_DEFAULT_ATTEN_MASK << \
+					 PORT0_DEFAULT_ATTEN_SHIFT)
+
+#define PORT1_PORT_TYPE_SMASK		(PORT1_PORT_TYPE_MASK << \
+					 PORT1_PORT_TYPE_SHIFT)
+#define PORT1_LOCAL_ATTEN_SMASK		(PORT1_LOCAL_ATTEN_MASK << \
+					 PORT1_LOCAL_ATTEN_SHIFT)
+#define PORT1_REMOTE_ATTEN_SMASK	(PORT1_REMOTE_ATTEN_MASK << \
+					 PORT1_REMOTE_ATTEN_SHIFT)
+#define PORT1_DEFAULT_ATTEN_SMASK	(PORT1_DEFAULT_ATTEN_MASK << \
+					 PORT1_DEFAULT_ATTEN_SHIFT)
+
+#define QSFP_MAX_POWER_SHIFT		0
+#define TX_NO_EQ_SHIFT			4
+#define TX_EQ_SHIFT			25
+#define RX_SHIFT			46
+
+#define QSFP_MAX_POWER_MASK		0xFUL
+#define TX_NO_EQ_MASK			0x1FFFFFUL
+#define TX_EQ_MASK			0x1FFFFFUL
+#define RX_MASK				0xFFFFUL
+
+#define QSFP_MAX_POWER_SMASK		(QSFP_MAX_POWER_MASK << \
+					 QSFP_MAX_POWER_SHIFT)
+#define TX_NO_EQ_SMASK			(TX_NO_EQ_MASK << TX_NO_EQ_SHIFT)
+#define TX_EQ_SMASK			(TX_EQ_MASK << TX_EQ_SHIFT)
+#define RX_SMASK			(RX_MASK << RX_SHIFT)
+
+#define TX_PRECUR_SHIFT			0
+#define TX_ATTN_SHIFT			4
+#define QSFP_TX_CDR_APPLY_SHIFT		9
+#define QSFP_TX_EQ_APPLY_SHIFT		10
+#define QSFP_TX_CDR_SHIFT		11
+#define QSFP_TX_EQ_SHIFT		12
+#define TX_POSTCUR_SHIFT		16
+
+#define TX_PRECUR_MASK			0xFUL
+#define TX_ATTN_MASK			0x1FUL
+#define QSFP_TX_CDR_APPLY_MASK		0x1UL
+#define QSFP_TX_EQ_APPLY_MASK		0x1UL
+#define QSFP_TX_CDR_MASK		0x1UL
+#define QSFP_TX_EQ_MASK			0xFUL
+#define TX_POSTCUR_MASK			0x1FUL
+
+#define TX_PRECUR_SMASK			(TX_PRECUR_MASK << TX_PRECUR_SHIFT)
+#define TX_ATTN_SMASK			(TX_ATTN_MASK << TX_ATTN_SHIFT)
+#define QSFP_TX_CDR_APPLY_SMASK		(QSFP_TX_CDR_APPLY_MASK << \
+					 QSFP_TX_CDR_APPLY_SHIFT)
+#define QSFP_TX_EQ_APPLY_SMASK		(QSFP_TX_EQ_APPLY_MASK << \
+					 QSFP_TX_EQ_APPLY_SHIFT)
+#define QSFP_TX_CDR_SMASK		(QSFP_TX_CDR_MASK << QSFP_TX_CDR_SHIFT)
+#define QSFP_TX_EQ_SMASK		(QSFP_TX_EQ_MASK << QSFP_TX_EQ_SHIFT)
+#define TX_POSTCUR_SMASK		(TX_POSTCUR_MASK << TX_POSTCUR_SHIFT)
+
+#define QSFP_RX_CDR_APPLY_SHIFT		0
+#define QSFP_RX_EMP_APPLY_SHIFT		1
+#define QSFP_RX_AMP_APPLY_SHIFT		2
+#define QSFP_RX_CDR_SHIFT		3
+#define QSFP_RX_EMP_SHIFT		4
+#define QSFP_RX_AMP_SHIFT		8
+
+#define QSFP_RX_CDR_APPLY_MASK		0x1UL
+#define QSFP_RX_EMP_APPLY_MASK		0x1UL
+#define QSFP_RX_AMP_APPLY_MASK		0x1UL
+#define QSFP_RX_CDR_MASK		0x1UL
+#define QSFP_RX_EMP_MASK		0xFUL
+#define QSFP_RX_AMP_MASK		0x3UL
+
+#define QSFP_RX_CDR_APPLY_SMASK		(QSFP_RX_CDR_APPLY_MASK << \
+					 QSFP_RX_CDR_APPLY_SHIFT)
+#define QSFP_RX_EMP_APPLY_SMASK		(QSFP_RX_EMP_APPLY_MASK << \
+					 QSFP_RX_EMP_APPLY_SHIFT)
+#define QSFP_RX_AMP_APPLY_SMASK		(QSFP_RX_AMP_APPLY_MASK << \
+					 QSFP_RX_AMP_APPLY_SHIFT)
+#define QSFP_RX_CDR_SMASK		(QSFP_RX_CDR_MASK << QSFP_RX_CDR_SHIFT)
+#define QSFP_RX_EMP_SMASK		(QSFP_RX_EMP_MASK << QSFP_RX_EMP_SHIFT)
+#define QSFP_RX_AMP_SMASK		(QSFP_RX_AMP_MASK << QSFP_RX_AMP_SHIFT)
+
+#define BITMAP_VERSION			1
+#define BITMAP_VERSION_SHIFT		44
+#define BITMAP_VERSION_MASK		0xFUL
+#define BITMAP_VERSION_SMASK		(BITMAP_VERSION_MASK << \
+					 BITMAP_VERSION_SHIFT)
+#define CHECKSUM_SHIFT			48
+#define CHECKSUM_MASK			0xFFFFUL
+#define CHECKSUM_SMASK			(CHECKSUM_MASK << CHECKSUM_SHIFT)
+
 /* platform.c */
 void get_platform_config(struct hfi1_devdata *dd);
 void free_platform_config(struct hfi1_devdata *dd);

drivers/infiniband/hw/hfi1/qp.c

@@ -196,15 +196,18 @@ static void flush_tx_list(struct rvt_qp *qp)
 static void flush_iowait(struct rvt_qp *qp)
 {
 	struct hfi1_qp_priv *priv = qp->priv;
-	struct hfi1_ibdev *dev = to_idev(qp->ibqp.device);
 	unsigned long flags;
+	seqlock_t *lock = priv->s_iowait.lock;
 
-	write_seqlock_irqsave(&dev->iowait_lock, flags);
+	if (!lock)
+		return;
+	write_seqlock_irqsave(lock, flags);
 	if (!list_empty(&priv->s_iowait.list)) {
 		list_del_init(&priv->s_iowait.list);
+		priv->s_iowait.lock = NULL;
 		rvt_put_qp(qp);
 	}
-	write_sequnlock_irqrestore(&dev->iowait_lock, flags);
+	write_sequnlock_irqrestore(lock, flags);
 }
 
 static inline int opa_mtu_enum_to_int(int mtu)
@@ -543,6 +546,7 @@ static int iowait_sleep(
 			ibp->rvp.n_dmawait++;
 			qp->s_flags |= RVT_S_WAIT_DMA_DESC;
 			list_add_tail(&priv->s_iowait.list, &sde->dmawait);
+			priv->s_iowait.lock = &dev->iowait_lock;
 			trace_hfi1_qpsleep(qp, RVT_S_WAIT_DMA_DESC);
 			rvt_get_qp(qp);
 		}
@@ -964,6 +968,7 @@ void notify_error_qp(struct rvt_qp *qp)
 	if (!list_empty(&priv->s_iowait.list) && !(qp->s_flags & RVT_S_BUSY)) {
 		qp->s_flags &= ~RVT_S_ANY_WAIT_IO;
 		list_del_init(&priv->s_iowait.list);
+		priv->s_iowait.lock = NULL;
 		rvt_put_qp(qp);
 	}
 	write_sequnlock(&dev->iowait_lock);

drivers/infiniband/hw/hfi1/rc.c

@@ -276,7 +276,7 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp,
 				rvt_get_mr(ps->s_txreq->mr);
 			qp->s_ack_rdma_sge.sge = e->rdma_sge;
 			qp->s_ack_rdma_sge.num_sge = 1;
-			qp->s_cur_sge = &qp->s_ack_rdma_sge;
+			ps->s_txreq->ss = &qp->s_ack_rdma_sge;
 			if (len > pmtu) {
 				len = pmtu;
 				qp->s_ack_state = OP(RDMA_READ_RESPONSE_FIRST);
@@ -290,7 +290,7 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp,
 			bth2 = mask_psn(qp->s_ack_rdma_psn++);
 		} else {
 			/* COMPARE_SWAP or FETCH_ADD */
-			qp->s_cur_sge = NULL;
+			ps->s_txreq->ss = NULL;
 			len = 0;
 			qp->s_ack_state = OP(ATOMIC_ACKNOWLEDGE);
 			ohdr->u.at.aeth = hfi1_compute_aeth(qp);
@@ -306,7 +306,7 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp,
 		qp->s_ack_state = OP(RDMA_READ_RESPONSE_MIDDLE);
 		/* FALLTHROUGH */
 	case OP(RDMA_READ_RESPONSE_MIDDLE):
-		qp->s_cur_sge = &qp->s_ack_rdma_sge;
+		ps->s_txreq->ss = &qp->s_ack_rdma_sge;
 		ps->s_txreq->mr = qp->s_ack_rdma_sge.sge.mr;
 		if (ps->s_txreq->mr)
 			rvt_get_mr(ps->s_txreq->mr);
@@ -335,7 +335,7 @@ normal:
 		 */
 		qp->s_ack_state = OP(SEND_ONLY);
 		qp->s_flags &= ~RVT_S_ACK_PENDING;
-		qp->s_cur_sge = NULL;
+		ps->s_txreq->ss = NULL;
 		if (qp->s_nak_state)
 			ohdr->u.aeth =
 				cpu_to_be32((qp->r_msn & HFI1_MSN_MASK) |
@@ -351,7 +351,7 @@ normal:
 	qp->s_rdma_ack_cnt++;
 	qp->s_hdrwords = hwords;
 	ps->s_txreq->sde = priv->s_sde;
-	qp->s_cur_size = len;
+	ps->s_txreq->s_cur_size = len;
 	hfi1_make_ruc_header(qp, ohdr, bth0, bth2, middle, ps);
 	/* pbc */
 	ps->s_txreq->hdr_dwords = qp->s_hdrwords + 2;
@@ -801,8 +801,8 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	qp->s_len -= len;
 	qp->s_hdrwords = hwords;
 	ps->s_txreq->sde = priv->s_sde;
-	qp->s_cur_sge = ss;
-	qp->s_cur_size = len;
+	ps->s_txreq->ss = ss;
+	ps->s_txreq->s_cur_size = len;
 	hfi1_make_ruc_header(
 		qp,
 		ohdr,
@@ -1146,8 +1146,6 @@ void hfi1_rc_send_complete(struct rvt_qp *qp, struct ib_header *hdr)
 {
 	struct ib_other_headers *ohdr;
 	struct rvt_swqe *wqe;
-	struct ib_wc wc;
-	unsigned i;
 	u32 opcode;
 	u32 psn;
 
@@ -1195,22 +1193,8 @@ void hfi1_rc_send_complete(struct rvt_qp *qp, struct ib_header *hdr)
 		qp->s_last = s_last;
 		/* see post_send() */
 		barrier();
-		for (i = 0; i < wqe->wr.num_sge; i++) {
-			struct rvt_sge *sge = &wqe->sg_list[i];
-
-			rvt_put_mr(sge->mr);
-		}
-		/* Post a send completion queue entry if requested. */
-		if (!(qp->s_flags & RVT_S_SIGNAL_REQ_WR) ||
-		    (wqe->wr.send_flags & IB_SEND_SIGNALED)) {
-			memset(&wc, 0, sizeof(wc));
-			wc.wr_id = wqe->wr.wr_id;
-			wc.status = IB_WC_SUCCESS;
-			wc.opcode = ib_hfi1_wc_opcode[wqe->wr.opcode];
-			wc.byte_len = wqe->length;
-			wc.qp = &qp->ibqp;
-			rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.send_cq), &wc, 0);
-		}
+		rvt_put_swqe(wqe);
+		rvt_qp_swqe_complete(qp, wqe, IB_WC_SUCCESS);
 	}
 	/*
 	 * If we were waiting for sends to complete before re-sending,
@@ -1240,9 +1224,6 @@ static struct rvt_swqe *do_rc_completion(struct rvt_qp *qp,
 					 struct rvt_swqe *wqe,
 					 struct hfi1_ibport *ibp)
 {
-	struct ib_wc wc;
-	unsigned i;
-
 	lockdep_assert_held(&qp->s_lock);
 	/*
 	 * Don't decrement refcount and don't generate a
@@ -1253,28 +1234,14 @@ static struct rvt_swqe *do_rc_completion(struct rvt_qp *qp,
 	    cmp_psn(qp->s_sending_psn, qp->s_sending_hpsn) > 0) {
 		u32 s_last;
 
-		for (i = 0; i < wqe->wr.num_sge; i++) {
-			struct rvt_sge *sge = &wqe->sg_list[i];
-
-			rvt_put_mr(sge->mr);
-		}
+		rvt_put_swqe(wqe);
 		s_last = qp->s_last;
 		if (++s_last >= qp->s_size)
 			s_last = 0;
 		qp->s_last = s_last;
 		/* see post_send() */
 		barrier();
-		/* Post a send completion queue entry if requested. */
-		if (!(qp->s_flags & RVT_S_SIGNAL_REQ_WR) ||
-		    (wqe->wr.send_flags & IB_SEND_SIGNALED)) {
-			memset(&wc, 0, sizeof(wc));
-			wc.wr_id = wqe->wr.wr_id;
-			wc.status = IB_WC_SUCCESS;
-			wc.opcode = ib_hfi1_wc_opcode[wqe->wr.opcode];
-			wc.byte_len = wqe->length;
-			wc.qp = &qp->ibqp;
-			rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.send_cq), &wc, 0);
-		}
+		rvt_qp_swqe_complete(qp, wqe, IB_WC_SUCCESS);
 	} else {
 		struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 
@@ -2295,7 +2262,7 @@ send_last:
 		hfi1_copy_sge(&qp->r_sge, data, tlen, 1, copy_last);
 		rvt_put_ss(&qp->r_sge);
 		qp->r_msn++;
-		if (!test_and_clear_bit(RVT_R_WRID_VALID, &qp->r_aflags))
+		if (!__test_and_clear_bit(RVT_R_WRID_VALID, &qp->r_aflags))
 			break;
 		wc.wr_id = qp->r_wr_id;
 		wc.status = IB_WC_SUCCESS;
@@ -2410,8 +2377,7 @@ send_last:
 			 * Update the next expected PSN.  We add 1 later
 			 * below, so only add the remainder here.
 			 */
-			if (len > pmtu)
-				qp->r_psn += (len - 1) / pmtu;
+			qp->r_psn += rvt_div_mtu(qp, len - 1);
 		} else {
 			e->rdma_sge.mr = NULL;
 			e->rdma_sge.vaddr = NULL;

drivers/infiniband/hw/hfi1/ruc.c

@@ -239,16 +239,6 @@ bail:
 	return ret;
 }
 
-static __be64 get_sguid(struct hfi1_ibport *ibp, unsigned index)
-{
-	if (!index) {
-		struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
-
-		return cpu_to_be64(ppd->guid);
-	}
-	return ibp->guids[index - 1];
-}
-
 static int gid_ok(union ib_gid *gid, __be64 gid_prefix, __be64 id)
 {
 	return (gid->global.interface_id == id &&
@@ -699,9 +689,9 @@ u32 hfi1_make_grh(struct hfi1_ibport *ibp, struct ib_grh *hdr,
 	/* The SGID is 32-bit aligned. */
 	hdr->sgid.global.subnet_prefix = ibp->rvp.gid_prefix;
 	hdr->sgid.global.interface_id =
-		grh->sgid_index && grh->sgid_index < ARRAY_SIZE(ibp->guids) ?
-		ibp->guids[grh->sgid_index - 1] :
-			cpu_to_be64(ppd_from_ibp(ibp)->guid);
+		grh->sgid_index < HFI1_GUIDS_PER_PORT ?
+		get_sguid(ibp, grh->sgid_index) :
+		get_sguid(ibp, HFI1_PORT_GUID_INDEX);
 	hdr->dgid = grh->dgid;
 
 	/* GRH header size in 32-bit words. */
@@ -777,8 +767,8 @@ void hfi1_make_ruc_header(struct rvt_qp *qp, struct ib_other_headers *ohdr,
 	u32 bth1;
 
 	/* Construct the header. */
-	extra_bytes = -qp->s_cur_size & 3;
-	nwords = (qp->s_cur_size + extra_bytes) >> 2;
+	extra_bytes = -ps->s_txreq->s_cur_size & 3;
+	nwords = (ps->s_txreq->s_cur_size + extra_bytes) >> 2;
 	lrh0 = HFI1_LRH_BTH;
 	if (unlikely(qp->remote_ah_attr.ah_flags & IB_AH_GRH)) {
 		qp->s_hdrwords += hfi1_make_grh(ibp,
@@ -952,7 +942,6 @@ void hfi1_send_complete(struct rvt_qp *qp, struct rvt_swqe *wqe,
 			enum ib_wc_status status)
 {
 	u32 old_last, last;
-	unsigned i;
 
 	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_OR_FLUSH_SEND))
 		return;
@@ -964,32 +953,13 @@ void hfi1_send_complete(struct rvt_qp *qp, struct rvt_swqe *wqe,
 	qp->s_last = last;
 	/* See post_send() */
 	barrier();
-	for (i = 0; i < wqe->wr.num_sge; i++) {
-		struct rvt_sge *sge = &wqe->sg_list[i];
-
-		rvt_put_mr(sge->mr);
-	}
+	rvt_put_swqe(wqe);
 	if (qp->ibqp.qp_type == IB_QPT_UD ||
 	    qp->ibqp.qp_type == IB_QPT_SMI ||
 	    qp->ibqp.qp_type == IB_QPT_GSI)
 		atomic_dec(&ibah_to_rvtah(wqe->ud_wr.ah)->refcount);
 
-	/* See ch. 11.2.4.1 and 10.7.3.1 */
-	if (!(qp->s_flags & RVT_S_SIGNAL_REQ_WR) ||
-	    (wqe->wr.send_flags & IB_SEND_SIGNALED) ||
-	    status != IB_WC_SUCCESS) {
-		struct ib_wc wc;
-
-		memset(&wc, 0, sizeof(wc));
-		wc.wr_id = wqe->wr.wr_id;
-		wc.status = status;
-		wc.opcode = ib_hfi1_wc_opcode[wqe->wr.opcode];
-		wc.qp = &qp->ibqp;
-		if (status == IB_WC_SUCCESS)
-			wc.byte_len = wqe->length;
-		rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.send_cq), &wc,
-			     status != IB_WC_SUCCESS);
-	}
+	rvt_qp_swqe_complete(qp, wqe, status);
 
 	if (qp->s_acked == old_last)
 		qp->s_acked = last;

drivers/infiniband/hw/hfi1/sdma.c

@@ -375,7 +375,7 @@ static inline void complete_tx(struct sdma_engine *sde,
 			   sde->head_sn, tx->sn);
 	sde->head_sn++;
 #endif
-	sdma_txclean(sde->dd, tx);
+	__sdma_txclean(sde->dd, tx);
 	if (complete)
 		(*complete)(tx, res);
 	if (wait && iowait_sdma_dec(wait))
@@ -1643,7 +1643,7 @@ static inline u8 ahg_mode(struct sdma_txreq *tx)
 }
 
 /**
- * sdma_txclean() - clean tx of mappings, descp *kmalloc's
+ * __sdma_txclean() - clean tx of mappings, descp *kmalloc's
  * @dd: hfi1_devdata for unmapping
  * @tx: tx request to clean
  *
@@ -1653,7 +1653,7 @@ static inline u8 ahg_mode(struct sdma_txreq *tx)
  * The code can be called multiple times without issue.
  *
  */
-void sdma_txclean(
+void __sdma_txclean(
 	struct hfi1_devdata *dd,
 	struct sdma_txreq *tx)
 {
@@ -3065,7 +3065,7 @@ static int _extend_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx)
 		tx->descp[i] = tx->descs[i];
 	return 0;
 enomem:
-	sdma_txclean(dd, tx);
+	__sdma_txclean(dd, tx);
 	return -ENOMEM;
 }
 
@@ -3094,14 +3094,14 @@ int ext_coal_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx,
 
 	rval = _extend_sdma_tx_descs(dd, tx);
 	if (rval) {
-		sdma_txclean(dd, tx);
+		__sdma_txclean(dd, tx);
 		return rval;
 	}
 
 	/* If coalesce buffer is allocated, copy data into it */
 	if (tx->coalesce_buf) {
 		if (type == SDMA_MAP_NONE) {
-			sdma_txclean(dd, tx);
+			__sdma_txclean(dd, tx);
 			return -EINVAL;
 		}
 
@@ -3109,7 +3109,7 @@ int ext_coal_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx,
 			kvaddr = kmap(page);
 			kvaddr += offset;
 		} else if (WARN_ON(!kvaddr)) {
-			sdma_txclean(dd, tx);
+			__sdma_txclean(dd, tx);
 			return -EINVAL;
 		}
 
@@ -3139,7 +3139,7 @@ int ext_coal_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx,
 				      DMA_TO_DEVICE);
 
 		if (unlikely(dma_mapping_error(&dd->pcidev->dev, addr))) {
-			sdma_txclean(dd, tx);
+			__sdma_txclean(dd, tx);
 			return -ENOSPC;
 		}
 
@@ -3181,7 +3181,7 @@ int _pad_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx)
 	if ((unlikely(tx->num_desc == tx->desc_limit))) {
 		rval = _extend_sdma_tx_descs(dd, tx);
 		if (rval) {
-			sdma_txclean(dd, tx);
+			__sdma_txclean(dd, tx);
 			return rval;
 		}
 	}

drivers/infiniband/hw/hfi1/sdma.h

@@ -667,7 +667,13 @@ int ext_coal_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx,
 			   int type, void *kvaddr, struct page *page,
 			   unsigned long offset, u16 len);
 int _pad_sdma_tx_descs(struct hfi1_devdata *, struct sdma_txreq *);
-void sdma_txclean(struct hfi1_devdata *, struct sdma_txreq *);
+void __sdma_txclean(struct hfi1_devdata *, struct sdma_txreq *);
+
+static inline void sdma_txclean(struct hfi1_devdata *dd, struct sdma_txreq *tx)
+{
+	if (tx->num_desc)
+		__sdma_txclean(dd, tx);
+}
 
 /* helpers used by public routines */
 static inline void _sdma_close_tx(struct hfi1_devdata *dd,
@@ -753,7 +759,7 @@ static inline int sdma_txadd_page(
 		       DMA_TO_DEVICE);
 
 	if (unlikely(dma_mapping_error(&dd->pcidev->dev, addr))) {
-		sdma_txclean(dd, tx);
+		__sdma_txclean(dd, tx);
 		return -ENOSPC;
 	}
 
@@ -834,7 +840,7 @@ static inline int sdma_txadd_kvaddr(
 		       DMA_TO_DEVICE);
 
 	if (unlikely(dma_mapping_error(&dd->pcidev->dev, addr))) {
-		sdma_txclean(dd, tx);
+		__sdma_txclean(dd, tx);
 		return -ENOSPC;
 	}
 

drivers/infiniband/hw/hfi1/uc.c

@@ -258,8 +258,8 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	qp->s_len -= len;
 	qp->s_hdrwords = hwords;
 	ps->s_txreq->sde = priv->s_sde;
-	qp->s_cur_sge = &qp->s_sge;
-	qp->s_cur_size = len;
+	ps->s_txreq->ss = &qp->s_sge;
+	ps->s_txreq->s_cur_size = len;
 	hfi1_make_ruc_header(qp, ohdr, bth0 | (qp->s_state << 24),
 			     mask_psn(qp->s_psn++), middle, ps);
 	/* pbc */

drivers/infiniband/hw/hfi1/ud.c

@@ -354,8 +354,8 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 
 	/* header size in 32-bit words LRH+BTH+DETH = (8+12+8)/4. */
 	qp->s_hdrwords = 7;
-	qp->s_cur_size = wqe->length;
-	qp->s_cur_sge = &qp->s_sge;
+	ps->s_txreq->s_cur_size = wqe->length;
+	ps->s_txreq->ss = &qp->s_sge;
 	qp->s_srate = ah_attr->static_rate;
 	qp->srate_mbps = ib_rate_to_mbps(qp->s_srate);
 	qp->s_wqe = wqe;

drivers/infiniband/hw/hfi1/user_sdma.c

@@ -115,6 +115,7 @@ MODULE_PARM_DESC(sdma_comp_size, "Size of User SDMA completion ring. Default: 12
 #define KDETH_HCRC_LOWER_MASK     0xff
 
 #define AHG_KDETH_INTR_SHIFT 12
+#define AHG_KDETH_SH_SHIFT   13
 
 #define PBC2LRH(x) ((((x) & 0xfff) << 2) - 4)
 #define LRH2PBC(x) ((((x) >> 2) + 1) & 0xfff)
@@ -144,8 +145,9 @@ MODULE_PARM_DESC(sdma_comp_size, "Size of User SDMA completion ring. Default: 12
 #define KDETH_OM_LARGE     64
 #define KDETH_OM_MAX_SIZE  (1 << ((KDETH_OM_LARGE / KDETH_OM_SMALL) + 1))
 
-/* Last packet in the request */
-#define TXREQ_FLAGS_REQ_LAST_PKT BIT(0)
+/* Tx request flag bits */
+#define TXREQ_FLAGS_REQ_ACK   BIT(0)      /* Set the ACK bit in the header */
+#define TXREQ_FLAGS_REQ_DISABLE_SH BIT(1) /* Disable header suppression */
 
 /* SDMA request flag bits */
 #define SDMA_REQ_FOR_THREAD 1
@@ -943,8 +945,13 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts)
 		tx->busycount = 0;
 		INIT_LIST_HEAD(&tx->list);
 
+		/*
+		 * For the last packet set the ACK request
+		 * and disable header suppression.
+		 */
 		if (req->seqnum == req->info.npkts - 1)
-			tx->flags |= TXREQ_FLAGS_REQ_LAST_PKT;
+			tx->flags |= (TXREQ_FLAGS_REQ_ACK |
+				      TXREQ_FLAGS_REQ_DISABLE_SH);
 
 		/*
 		 * Calculate the payload size - this is min of the fragment
@@ -963,11 +970,22 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts)
 			}
 
 			datalen = compute_data_length(req, tx);
+
+			/*
+			 * Disable header suppression for the payload <= 8DWS.
+			 * If there is an uncorrectable error in the receive
+			 * data FIFO when the received payload size is less than
+			 * or equal to 8DWS then the RxDmaDataFifoRdUncErr is
+			 * not reported.There is set RHF.EccErr if the header
+			 * is not suppressed.
+			 */
 			if (!datalen) {
 				SDMA_DBG(req,
 					 "Request has data but pkt len is 0");
 				ret = -EFAULT;
 				goto free_tx;
+			} else if (datalen <= 32) {
+				tx->flags |= TXREQ_FLAGS_REQ_DISABLE_SH;
 			}
 		}
 
@@ -990,6 +1008,10 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts)
 						LRH2PBC(lrhlen);
 					tx->hdr.pbc[0] = cpu_to_le16(pbclen);
 				}
+				ret = check_header_template(req, &tx->hdr,
+							    lrhlen, datalen);
+				if (ret)
+					goto free_tx;
 				ret = sdma_txinit_ahg(&tx->txreq,
 						      SDMA_TXREQ_F_AHG_COPY,
 						      sizeof(tx->hdr) + datalen,
@@ -1351,7 +1373,7 @@ static int set_txreq_header(struct user_sdma_request *req,
 				req->seqnum));
 
 	/* Set ACK request on last packet */
-	if (unlikely(tx->flags & TXREQ_FLAGS_REQ_LAST_PKT))
+	if (unlikely(tx->flags & TXREQ_FLAGS_REQ_ACK))
 		hdr->bth[2] |= cpu_to_be32(1UL << 31);
 
 	/* Set the new offset */
@@ -1384,8 +1406,8 @@ static int set_txreq_header(struct user_sdma_request *req,
 		/* Set KDETH.TID based on value for this TID */
 		KDETH_SET(hdr->kdeth.ver_tid_offset, TID,
 			  EXP_TID_GET(tidval, IDX));
-		/* Clear KDETH.SH only on the last packet */
-		if (unlikely(tx->flags & TXREQ_FLAGS_REQ_LAST_PKT))
+		/* Clear KDETH.SH when DISABLE_SH flag is set */
+		if (unlikely(tx->flags & TXREQ_FLAGS_REQ_DISABLE_SH))
 			KDETH_SET(hdr->kdeth.ver_tid_offset, SH, 0);
 		/*
 		 * Set the KDETH.OFFSET and KDETH.OM based on size of
@@ -1429,7 +1451,7 @@ static int set_txreq_header_ahg(struct user_sdma_request *req,
 	/* BTH.PSN and BTH.A */
 	val32 = (be32_to_cpu(hdr->bth[2]) + req->seqnum) &
 		(HFI1_CAP_IS_KSET(EXTENDED_PSN) ? 0x7fffffff : 0xffffff);
-	if (unlikely(tx->flags & TXREQ_FLAGS_REQ_LAST_PKT))
+	if (unlikely(tx->flags & TXREQ_FLAGS_REQ_ACK))
 		val32 |= 1UL << 31;
 	AHG_HEADER_SET(req->ahg, diff, 6, 0, 16, cpu_to_be16(val32 >> 16));
 	AHG_HEADER_SET(req->ahg, diff, 6, 16, 16, cpu_to_be16(val32 & 0xffff));
@@ -1468,19 +1490,23 @@ static int set_txreq_header_ahg(struct user_sdma_request *req,
 		AHG_HEADER_SET(req->ahg, diff, 7, 0, 16,
 			       ((!!(req->omfactor - KDETH_OM_SMALL)) << 15 |
 				((req->tidoffset / req->omfactor) & 0x7fff)));
-		/* KDETH.TIDCtrl, KDETH.TID */
+		/* KDETH.TIDCtrl, KDETH.TID, KDETH.Intr, KDETH.SH */
 		val = cpu_to_le16(((EXP_TID_GET(tidval, CTRL) & 0x3) << 10) |
-					(EXP_TID_GET(tidval, IDX) & 0x3ff));
-		/* Clear KDETH.SH on last packet */
-		if (unlikely(tx->flags & TXREQ_FLAGS_REQ_LAST_PKT)) {
-			val |= cpu_to_le16(KDETH_GET(hdr->kdeth.ver_tid_offset,
-						     INTR) <<
-					   AHG_KDETH_INTR_SHIFT);
-			val &= cpu_to_le16(~(1U << 13));
-			AHG_HEADER_SET(req->ahg, diff, 7, 16, 14, val);
+				   (EXP_TID_GET(tidval, IDX) & 0x3ff));
+
+		if (unlikely(tx->flags & TXREQ_FLAGS_REQ_DISABLE_SH)) {
+			val |= cpu_to_le16((KDETH_GET(hdr->kdeth.ver_tid_offset,
+						      INTR) <<
+					    AHG_KDETH_INTR_SHIFT));
 		} else {
-			AHG_HEADER_SET(req->ahg, diff, 7, 16, 12, val);
+			val |= KDETH_GET(hdr->kdeth.ver_tid_offset, SH) ?
+			       cpu_to_le16(0x1 << AHG_KDETH_SH_SHIFT) :
+			       cpu_to_le16((KDETH_GET(hdr->kdeth.ver_tid_offset,
+						      INTR) <<
+					     AHG_KDETH_INTR_SHIFT));
 		}
+
+		AHG_HEADER_SET(req->ahg, diff, 7, 16, 14, val);
 	}
 
 	trace_hfi1_sdma_user_header_ahg(pq->dd, pq->ctxt, pq->subctxt,

drivers/infiniband/hw/hfi1/verbs.c

@@ -296,22 +296,6 @@ static inline int wss_exceeds_threshold(void)
 	return atomic_read(&wss.total_count) >= wss.threshold;
 }
 
-/*
- * Translate ib_wr_opcode into ib_wc_opcode.
- */
-const enum ib_wc_opcode ib_hfi1_wc_opcode[] = {
-	[IB_WR_RDMA_WRITE] = IB_WC_RDMA_WRITE,
-	[IB_WR_RDMA_WRITE_WITH_IMM] = IB_WC_RDMA_WRITE,
-	[IB_WR_SEND] = IB_WC_SEND,
-	[IB_WR_SEND_WITH_IMM] = IB_WC_SEND,
-	[IB_WR_RDMA_READ] = IB_WC_RDMA_READ,
-	[IB_WR_ATOMIC_CMP_AND_SWP] = IB_WC_COMP_SWAP,
-	[IB_WR_ATOMIC_FETCH_AND_ADD] = IB_WC_FETCH_ADD,
-	[IB_WR_SEND_WITH_INV] = IB_WC_SEND,
-	[IB_WR_LOCAL_INV] = IB_WC_LOCAL_INV,
-	[IB_WR_REG_MR] = IB_WC_REG_MR
-};
-
 /*
  * Length of header by opcode, 0 --> not supported
  */
@@ -694,6 +678,7 @@ static void mem_timer(unsigned long data)
 		qp = iowait_to_qp(wait);
 		priv = qp->priv;
 		list_del_init(&priv->s_iowait.list);
+		priv->s_iowait.lock = NULL;
 		/* refcount held until actual wake up */
 		if (!list_empty(list))
 			mod_timer(&dev->mem_timer, jiffies + 1);
@@ -769,6 +754,7 @@ static int wait_kmem(struct hfi1_ibdev *dev,
 				mod_timer(&dev->mem_timer, jiffies + 1);
 			qp->s_flags |= RVT_S_WAIT_KMEM;
 			list_add_tail(&priv->s_iowait.list, &dev->memwait);
+			priv->s_iowait.lock = &dev->iowait_lock;
 			trace_hfi1_qpsleep(qp, RVT_S_WAIT_KMEM);
 			rvt_get_qp(qp);
 		}
@@ -788,10 +774,10 @@ static int wait_kmem(struct hfi1_ibdev *dev,
  */
 static noinline int build_verbs_ulp_payload(
 	struct sdma_engine *sde,
-	struct rvt_sge_state *ss,
 	u32 length,
 	struct verbs_txreq *tx)
 {
+	struct rvt_sge_state *ss = tx->ss;
 	struct rvt_sge *sg_list = ss->sg_list;
 	struct rvt_sge sge = ss->sge;
 	u8 num_sge = ss->num_sge;
@@ -835,7 +821,6 @@ bail_txadd:
 /* New API */
 static int build_verbs_tx_desc(
 	struct sdma_engine *sde,
-	struct rvt_sge_state *ss,
 	u32 length,
 	struct verbs_txreq *tx,
 	struct hfi1_ahg_info *ahg_info,
@@ -879,9 +864,9 @@ static int build_verbs_tx_desc(
 			goto bail_txadd;
 	}
 
-	/* add the ulp payload - if any.  ss can be NULL for acks */
-	if (ss)
-		ret = build_verbs_ulp_payload(sde, ss, length, tx);
+	/* add the ulp payload - if any. tx->ss can be NULL for acks */
+	if (tx->ss)
+		ret = build_verbs_ulp_payload(sde, length, tx);
 bail_txadd:
 	return ret;
 }
@@ -892,8 +877,7 @@ int hfi1_verbs_send_dma(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 	struct hfi1_qp_priv *priv = qp->priv;
 	struct hfi1_ahg_info *ahg_info = priv->s_ahg;
 	u32 hdrwords = qp->s_hdrwords;
-	struct rvt_sge_state *ss = qp->s_cur_sge;
-	u32 len = qp->s_cur_size;
+	u32 len = ps->s_txreq->s_cur_size;
 	u32 plen = hdrwords + ((len + 3) >> 2) + 2; /* includes pbc */
 	struct hfi1_ibdev *dev = ps->dev;
 	struct hfi1_pportdata *ppd = ps->ppd;
@@ -918,7 +902,7 @@ int hfi1_verbs_send_dma(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 					 plen);
 		}
 		tx->wqe = qp->s_wqe;
-		ret = build_verbs_tx_desc(tx->sde, ss, len, tx, ahg_info, pbc);
+		ret = build_verbs_tx_desc(tx->sde, len, tx, ahg_info, pbc);
 		if (unlikely(ret))
 			goto bail_build;
 	}
@@ -980,6 +964,7 @@ static int pio_wait(struct rvt_qp *qp,
 			qp->s_flags |= flag;
 			was_empty = list_empty(&sc->piowait);
 			list_add_tail(&priv->s_iowait.list, &sc->piowait);
+			priv->s_iowait.lock = &dev->iowait_lock;
 			trace_hfi1_qpsleep(qp, RVT_S_WAIT_PIO);
 			rvt_get_qp(qp);
 			/* counting: only call wantpiobuf_intr if first user */
@@ -1008,8 +993,8 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 {
 	struct hfi1_qp_priv *priv = qp->priv;
 	u32 hdrwords = qp->s_hdrwords;
-	struct rvt_sge_state *ss = qp->s_cur_sge;
-	u32 len = qp->s_cur_size;
+	struct rvt_sge_state *ss = ps->s_txreq->ss;
+	u32 len = ps->s_txreq->s_cur_size;
 	u32 dwords = (len + 3) >> 2;
 	u32 plen = hdrwords + dwords + 2; /* includes pbc */
 	struct hfi1_pportdata *ppd = ps->ppd;
@@ -1237,7 +1222,7 @@ static inline send_routine get_send_routine(struct rvt_qp *qp,
 		u8 op = get_opcode(h);
 
 		if (piothreshold &&
-		    qp->s_cur_size <= min(piothreshold, qp->pmtu) &&
+		    tx->s_cur_size <= min(piothreshold, qp->pmtu) &&
 		    (BIT(op & OPMASK) & pio_opmask[op >> 5]) &&
 		    iowait_sdma_pending(&priv->s_iowait) == 0 &&
 		    !sdma_txreq_built(&tx->txreq))
@@ -1483,15 +1468,11 @@ static int hfi1_get_guid_be(struct rvt_dev_info *rdi, struct rvt_ibport *rvp,
 			    int guid_index, __be64 *guid)
 {
 	struct hfi1_ibport *ibp = container_of(rvp, struct hfi1_ibport, rvp);
-	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 
-	if (guid_index == 0)
-		*guid = cpu_to_be64(ppd->guid);
-	else if (guid_index < HFI1_GUIDS_PER_PORT)
-		*guid = ibp->guids[guid_index - 1];
-	else
+	if (guid_index >= HFI1_GUIDS_PER_PORT)
 		return -EINVAL;
 
+	*guid = get_sguid(ibp, guid_index);
 	return 0;
 }
 
@@ -1610,6 +1591,154 @@ static void hfi1_get_dev_fw_str(struct ib_device *ibdev, char *str,
 		 dc8051_ver_min(ver));
 }
 
+static const char * const driver_cntr_names[] = {
+	/* must be element 0*/
+	"DRIVER_KernIntr",
+	"DRIVER_ErrorIntr",
+	"DRIVER_Tx_Errs",
+	"DRIVER_Rcv_Errs",
+	"DRIVER_HW_Errs",
+	"DRIVER_NoPIOBufs",
+	"DRIVER_CtxtsOpen",
+	"DRIVER_RcvLen_Errs",
+	"DRIVER_EgrBufFull",
+	"DRIVER_EgrHdrFull"
+};
+
+static const char **dev_cntr_names;
+static const char **port_cntr_names;
+static int num_driver_cntrs = ARRAY_SIZE(driver_cntr_names);
+static int num_dev_cntrs;
+static int num_port_cntrs;
+static int cntr_names_initialized;
+
+/*
+ * Convert a list of names separated by '\n' into an array of NULL terminated
+ * strings. Optionally some entries can be reserved in the array to hold extra
+ * external strings.
+ */
+static int init_cntr_names(const char *names_in,
+			   const int names_len,
+			   int num_extra_names,
+			   int *num_cntrs,
+			   const char ***cntr_names)
+{
+	char *names_out, *p, **q;
+	int i, n;
+
+	n = 0;
+	for (i = 0; i < names_len; i++)
+		if (names_in[i] == '\n')
+			n++;
+
+	names_out = kmalloc((n + num_extra_names) * sizeof(char *) + names_len,
+			    GFP_KERNEL);
+	if (!names_out) {
+		*num_cntrs = 0;
+		*cntr_names = NULL;
+		return -ENOMEM;
+	}
+
+	p = names_out + (n + num_extra_names) * sizeof(char *);
+	memcpy(p, names_in, names_len);
+
+	q = (char **)names_out;
+	for (i = 0; i < n; i++) {
+		q[i] = p;
+		p = strchr(p, '\n');
+		*p++ = '\0';
+	}
+
+	*num_cntrs = n;
+	*cntr_names = (const char **)names_out;
+	return 0;
+}
+
+static struct rdma_hw_stats *alloc_hw_stats(struct ib_device *ibdev,
+					    u8 port_num)
+{
+	int i, err;
+
+	if (!cntr_names_initialized) {
+		struct hfi1_devdata *dd = dd_from_ibdev(ibdev);
+
+		err = init_cntr_names(dd->cntrnames,
+				      dd->cntrnameslen,
+				      num_driver_cntrs,
+				      &num_dev_cntrs,
+				      &dev_cntr_names);
+		if (err)
+			return NULL;
+
+		for (i = 0; i < num_driver_cntrs; i++)
+			dev_cntr_names[num_dev_cntrs + i] =
+				driver_cntr_names[i];
+
+		err = init_cntr_names(dd->portcntrnames,
+				      dd->portcntrnameslen,
+				      0,
+				      &num_port_cntrs,
+				      &port_cntr_names);
+		if (err) {
+			kfree(dev_cntr_names);
+			dev_cntr_names = NULL;
+			return NULL;
+		}
+		cntr_names_initialized = 1;
+	}
+
+	if (!port_num)
+		return rdma_alloc_hw_stats_struct(
+				dev_cntr_names,
+				num_dev_cntrs + num_driver_cntrs,
+				RDMA_HW_STATS_DEFAULT_LIFESPAN);
+	else
+		return rdma_alloc_hw_stats_struct(
+				port_cntr_names,
+				num_port_cntrs,
+				RDMA_HW_STATS_DEFAULT_LIFESPAN);
+}
+
+static u64 hfi1_sps_ints(void)
+{
+	unsigned long flags;
+	struct hfi1_devdata *dd;
+	u64 sps_ints = 0;
+
+	spin_lock_irqsave(&hfi1_devs_lock, flags);
+	list_for_each_entry(dd, &hfi1_dev_list, list) {
+		sps_ints += get_all_cpu_total(dd->int_counter);
+	}
+	spin_unlock_irqrestore(&hfi1_devs_lock, flags);
+	return sps_ints;
+}
+
+static int get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats,
+			u8 port, int index)
+{
+	u64 *values;
+	int count;
+
+	if (!port) {
+		u64 *stats = (u64 *)&hfi1_stats;
+		int i;
+
+		hfi1_read_cntrs(dd_from_ibdev(ibdev), NULL, &values);
+		values[num_dev_cntrs] = hfi1_sps_ints();
+		for (i = 1; i < num_driver_cntrs; i++)
+			values[num_dev_cntrs + i] = stats[i];
+		count = num_dev_cntrs + num_driver_cntrs;
+	} else {
+		struct hfi1_ibport *ibp = to_iport(ibdev, port);
+
+		hfi1_read_portcntrs(ppd_from_ibp(ibp), NULL, &values);
+		count = num_port_cntrs;
+	}
+
+	memcpy(stats->value, values, count * sizeof(u64));
+	return count;
+}
+
 /**
  * hfi1_register_ib_device - register our device with the infiniband core
  * @dd: the device data structure
@@ -1620,6 +1749,7 @@ int hfi1_register_ib_device(struct hfi1_devdata *dd)
 	struct hfi1_ibdev *dev = &dd->verbs_dev;
 	struct ib_device *ibdev = &dev->rdi.ibdev;
 	struct hfi1_pportdata *ppd = dd->pport;
+	struct hfi1_ibport *ibp = &ppd->ibport_data;
 	unsigned i;
 	int ret;
 	size_t lcpysz = IB_DEVICE_NAME_MAX;
@@ -1632,6 +1762,7 @@ int hfi1_register_ib_device(struct hfi1_devdata *dd)
 	setup_timer(&dev->mem_timer, mem_timer, (unsigned long)dev);
 
 	seqlock_init(&dev->iowait_lock);
+	seqlock_init(&dev->txwait_lock);
 	INIT_LIST_HEAD(&dev->txwait);
 	INIT_LIST_HEAD(&dev->memwait);
 
@@ -1639,20 +1770,24 @@ int hfi1_register_ib_device(struct hfi1_devdata *dd)
 	if (ret)
 		goto err_verbs_txreq;
 
+	/* Use first-port GUID as node guid */
+	ibdev->node_guid = get_sguid(ibp, HFI1_PORT_GUID_INDEX);
+
 	/*
 	 * The system image GUID is supposed to be the same for all
 	 * HFIs in a single system but since there can be other
 	 * device types in the system, we can't be sure this is unique.
 	 */
 	if (!ib_hfi1_sys_image_guid)
-		ib_hfi1_sys_image_guid = cpu_to_be64(ppd->guid);
+		ib_hfi1_sys_image_guid = ibdev->node_guid;
 	lcpysz = strlcpy(ibdev->name, class_name(), lcpysz);
 	strlcpy(ibdev->name + lcpysz, "_%d", IB_DEVICE_NAME_MAX - lcpysz);
 	ibdev->owner = THIS_MODULE;
-	ibdev->node_guid = cpu_to_be64(ppd->guid);
 	ibdev->phys_port_cnt = dd->num_pports;
 	ibdev->dma_device = &dd->pcidev->dev;
 	ibdev->modify_device = modify_device;
+	ibdev->alloc_hw_stats = alloc_hw_stats;
+	ibdev->get_hw_stats = get_hw_stats;
 
 	/* keep process mad in the driver */
 	ibdev->process_mad = hfi1_process_mad;
@@ -1767,6 +1902,10 @@ void hfi1_unregister_ib_device(struct hfi1_devdata *dd)
 
 	del_timer_sync(&dev->mem_timer);
 	verbs_txreq_exit(dev);
+
+	kfree(dev_cntr_names);
+	kfree(port_cntr_names);
+	cntr_names_initialized = 0;
 }
 
 void hfi1_cnp_rcv(struct hfi1_packet *packet)

drivers/infiniband/hw/hfi1/verbs.h

@@ -73,7 +73,6 @@ struct hfi1_packet;
 #include "iowait.h"
 
 #define HFI1_MAX_RDMA_ATOMIC     16
-#define HFI1_GUIDS_PER_PORT	5
 
 /*
  * Increment this value if any changes that break userspace ABI
@@ -169,8 +168,6 @@ struct hfi1_ibport {
 	struct rvt_qp __rcu *qp[2];
 	struct rvt_ibport rvp;
 
-	__be64 guids[HFI1_GUIDS_PER_PORT	- 1];	/* writable GUIDs */
-
 	/* the first 16 entries are sl_to_vl for !OPA */
 	u8 sl_to_sc[32];
 	u8 sc_to_sl[32];
@@ -180,18 +177,19 @@ struct hfi1_ibdev {
 	struct rvt_dev_info rdi; /* Must be first */
 
 	/* QP numbers are shared by all IB ports */
-	/* protect wait lists */
-	seqlock_t iowait_lock;
+	/* protect txwait list */
+	seqlock_t txwait_lock ____cacheline_aligned_in_smp;
 	struct list_head txwait;        /* list for wait verbs_txreq */
 	struct list_head memwait;       /* list for wait kernel memory */
-	struct list_head txreq_free;
 	struct kmem_cache *verbs_txreq_cache;
-	struct timer_list mem_timer;
+	u64 n_txwait;
+	u64 n_kmem_wait;
 
+	/* protect iowait lists */
+	seqlock_t iowait_lock ____cacheline_aligned_in_smp;
 	u64 n_piowait;
 	u64 n_piodrain;
-	u64 n_txwait;
-	u64 n_kmem_wait;
+	struct timer_list mem_timer;
 
 #ifdef CONFIG_DEBUG_FS
 	/* per HFI debugfs */

drivers/infiniband/hw/hfi1/verbs_txreq.c

@@ -72,22 +72,22 @@ void hfi1_put_txreq(struct verbs_txreq *tx)
 	kmem_cache_free(dev->verbs_txreq_cache, tx);
 
 	do {
-		seq = read_seqbegin(&dev->iowait_lock);
+		seq = read_seqbegin(&dev->txwait_lock);
 		if (!list_empty(&dev->txwait)) {
 			struct iowait *wait;
 
-			write_seqlock_irqsave(&dev->iowait_lock, flags);
+			write_seqlock_irqsave(&dev->txwait_lock, flags);
 			wait = list_first_entry(&dev->txwait, struct iowait,
 						list);
 			qp = iowait_to_qp(wait);
 			priv = qp->priv;
 			list_del_init(&priv->s_iowait.list);
 			/* refcount held until actual wake up */
-			write_sequnlock_irqrestore(&dev->iowait_lock, flags);
+			write_sequnlock_irqrestore(&dev->txwait_lock, flags);
 			hfi1_qp_wakeup(qp, RVT_S_WAIT_TX);
 			break;
 		}
-	} while (read_seqretry(&dev->iowait_lock, seq));
+	} while (read_seqretry(&dev->txwait_lock, seq));
 }
 
 struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev,
@@ -96,7 +96,7 @@ struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev,
 {
 	struct verbs_txreq *tx = ERR_PTR(-EBUSY);
 
-	write_seqlock(&dev->iowait_lock);
+	write_seqlock(&dev->txwait_lock);
 	if (ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK) {
 		struct hfi1_qp_priv *priv;
 
@@ -108,13 +108,14 @@ struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev,
 			dev->n_txwait++;
 			qp->s_flags |= RVT_S_WAIT_TX;
 			list_add_tail(&priv->s_iowait.list, &dev->txwait);
+			priv->s_iowait.lock = &dev->txwait_lock;
 			trace_hfi1_qpsleep(qp, RVT_S_WAIT_TX);
 			rvt_get_qp(qp);
 		}
 		qp->s_flags &= ~RVT_S_BUSY;
 	}
 out:
-	write_sequnlock(&dev->iowait_lock);
+	write_sequnlock(&dev->txwait_lock);
 	return tx;
 }
 

drivers/infiniband/hw/hfi1/verbs_txreq.h

@@ -65,6 +65,7 @@ struct verbs_txreq {
 	struct sdma_engine     *sde;
 	struct send_context     *psc;
 	u16                     hdr_dwords;
+	u16			s_cur_size;
 };
 
 struct hfi1_ibdev;

drivers/infiniband/hw/hns/hns_roce_ah.c

@@ -39,7 +39,8 @@
 #define HNS_ROCE_VLAN_SL_BIT_MASK	7
 #define HNS_ROCE_VLAN_SL_SHIFT		13
 
-struct ib_ah *hns_roce_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *ah_attr)
+struct ib_ah *hns_roce_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *ah_attr,
+				 struct ib_udata *udata)
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(ibpd->device);
 	struct device *dev = &hr_dev->pdev->dev;

drivers/infiniband/hw/hns/hns_roce_alloc.c

@@ -61,9 +61,10 @@ int hns_roce_bitmap_alloc(struct hns_roce_bitmap *bitmap, unsigned long *obj)
 	return ret;
 }
 
-void hns_roce_bitmap_free(struct hns_roce_bitmap *bitmap, unsigned long obj)
+void hns_roce_bitmap_free(struct hns_roce_bitmap *bitmap, unsigned long obj,
+			  int rr)
 {
-	hns_roce_bitmap_free_range(bitmap, obj, 1);
+	hns_roce_bitmap_free_range(bitmap, obj, 1, rr);
 }
 
 int hns_roce_bitmap_alloc_range(struct hns_roce_bitmap *bitmap, int cnt,
@@ -106,7 +107,8 @@ int hns_roce_bitmap_alloc_range(struct hns_roce_bitmap *bitmap, int cnt,
 }
 
 void hns_roce_bitmap_free_range(struct hns_roce_bitmap *bitmap,
-				unsigned long obj, int cnt)
+				unsigned long obj, int cnt,
+				int rr)
 {
 	int i;
 
@@ -116,7 +118,8 @@ void hns_roce_bitmap_free_range(struct hns_roce_bitmap *bitmap,
 	for (i = 0; i < cnt; i++)
 		clear_bit(obj + i, bitmap->table);
 
-	bitmap->last = min(bitmap->last, obj);
+	if (!rr)
+		bitmap->last = min(bitmap->last, obj);
 	bitmap->top = (bitmap->top + bitmap->max + bitmap->reserved_top)
 		       & bitmap->mask;
 	spin_unlock(&bitmap->lock);

drivers/infiniband/hw/hns/hns_roce_cmd.c

@@ -216,10 +216,10 @@ static int __hns_roce_cmd_mbox_wait(struct hns_roce_dev *hr_dev, u64 in_param,
 		goto out;
 
 	/*
-	* It is timeout when wait_for_completion_timeout return 0
-	* The return value is the time limit set in advance
-	* how many seconds showing
-	*/
+	 * It is timeout when wait_for_completion_timeout return 0
+	 * The return value is the time limit set in advance
+	 * how many seconds showing
+	 */
 	if (!wait_for_completion_timeout(&context->done,
 					 msecs_to_jiffies(timeout))) {
 		dev_err(dev, "[cmd]wait_for_completion_timeout timeout\n");

drivers/infiniband/hw/hns/hns_roce_cmd.h

@@ -34,6 +34,7 @@
 #define _HNS_ROCE_CMD_H
 
 #define HNS_ROCE_MAILBOX_SIZE		4096
+#define HNS_ROCE_CMD_TIMEOUT_MSECS	10000
 
 enum {
 	/* TPT commands */
@@ -57,17 +58,6 @@ enum {
 	HNS_ROCE_CMD_QUERY_QP		= 0x22,
 };
 
-enum {
-	HNS_ROCE_CMD_TIME_CLASS_A	= 10000,
-	HNS_ROCE_CMD_TIME_CLASS_B	= 10000,
-	HNS_ROCE_CMD_TIME_CLASS_C	= 10000,
-};
-
-struct hns_roce_cmd_mailbox {
-	void		       *buf;
-	dma_addr_t		dma;
-};
-
 int hns_roce_cmd_mbox(struct hns_roce_dev *hr_dev, u64 in_param, u64 out_param,
 		      unsigned long in_modifier, u8 op_modifier, u16 op,
 		      unsigned long timeout);

drivers/infiniband/hw/hns/hns_roce_common.h

@@ -57,6 +57,32 @@
 #define roce_set_bit(origin, shift, val) \
 	roce_set_field((origin), (1ul << (shift)), (shift), (val))
 
+/*
+ * roce_hw_index_cmp_lt - Compare two hardware index values in hisilicon
+ *                        SOC, check if a is less than b.
+ * @a: hardware index value
+ * @b: hardware index value
+ * @bits: the number of bits of a and b, range: 0~31.
+ *
+ * Hardware index increases continuously till max value, and then restart
+ * from zero, again and again. Because the bits of reg field is often
+ * limited, the reg field can only hold the low bits of the hardware index
+ * in hisilicon SOC.
+ * In some scenes we need to compare two values(a,b) getted from two reg
+ * fields in this driver, for example:
+ * If a equals 0xfffe, b equals 0x1 and bits equals 16, we think b has
+ * incresed from 0xffff to 0x1 and a is less than b.
+ * If a equals 0xfffe, b equals 0x0xf001 and bits equals 16, we think a
+ * is bigger than b.
+ *
+ * Return true on a less than b, otherwise false.
+ */
+#define roce_hw_index_mask(bits)	((1ul << (bits)) - 1)
+#define roce_hw_index_shift(bits)	(32 - (bits))
+#define roce_hw_index_cmp_lt(a, b, bits) \
+	((int)((((a) - (b)) & roce_hw_index_mask(bits)) << \
+		roce_hw_index_shift(bits)) < 0)
+
 #define ROCEE_GLB_CFG_ROCEE_DB_SQ_MODE_S 3
 #define ROCEE_GLB_CFG_ROCEE_DB_OTH_MODE_S 4
 
@@ -245,16 +271,26 @@
 #define ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_M   \
 	(((1UL << 28) - 1) << ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_S)
 
+#define ROCEE_SDB_PTR_CMP_BITS 28
+
 #define ROCEE_SDB_INV_CNT_SDB_INV_CNT_S 0
 #define ROCEE_SDB_INV_CNT_SDB_INV_CNT_M   \
 	(((1UL << 16) - 1) << ROCEE_SDB_INV_CNT_SDB_INV_CNT_S)
 
+#define ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_S	0
+#define ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_M	\
+	(((1UL << 16) - 1) << ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_S)
+
+#define ROCEE_SDB_CNT_CMP_BITS 16
+
+#define ROCEE_TSP_BP_ST_QH_FIFO_ENTRY_S	20
+
+#define ROCEE_CNT_CLR_CE_CNT_CLR_CE_S 0
+
 /*************ROCEE_REG DEFINITION****************/
 #define ROCEE_VENDOR_ID_REG			0x0
 #define ROCEE_VENDOR_PART_ID_REG		0x4
 
-#define ROCEE_HW_VERSION_REG			0x8
-
 #define ROCEE_SYS_IMAGE_GUID_L_REG		0xC
 #define ROCEE_SYS_IMAGE_GUID_H_REG		0x10
 
@@ -318,7 +354,11 @@
 
 #define ROCEE_SDB_ISSUE_PTR_REG			0x758
 #define ROCEE_SDB_SEND_PTR_REG			0x75C
+#define ROCEE_CAEP_CQE_WCMD_EMPTY		0x850
+#define ROCEE_SCAEP_WR_CQE_CNT			0x8D0
 #define ROCEE_SDB_INV_CNT_REG			0x9A4
+#define ROCEE_SDB_RETRY_CNT_REG			0x9AC
+#define ROCEE_TSP_BP_ST_REG			0x9EC
 #define ROCEE_ECC_UCERR_ALM0_REG		0xB34
 #define ROCEE_ECC_CERR_ALM0_REG			0xB40
 

drivers/infiniband/hw/hns/hns_roce_cq.c

@@ -35,7 +35,7 @@
 #include "hns_roce_device.h"
 #include "hns_roce_cmd.h"
 #include "hns_roce_hem.h"
-#include "hns_roce_user.h"
+#include <rdma/hns-abi.h>
 #include "hns_roce_common.h"
 
 static void hns_roce_ib_cq_comp(struct hns_roce_cq *hr_cq)
@@ -77,7 +77,7 @@ static int hns_roce_sw2hw_cq(struct hns_roce_dev *dev,
 			     unsigned long cq_num)
 {
 	return hns_roce_cmd_mbox(dev, mailbox->dma, 0, cq_num, 0,
-			    HNS_ROCE_CMD_SW2HW_CQ, HNS_ROCE_CMD_TIME_CLASS_A);
+			    HNS_ROCE_CMD_SW2HW_CQ, HNS_ROCE_CMD_TIMEOUT_MSECS);
 }
 
 static int hns_roce_cq_alloc(struct hns_roce_dev *hr_dev, int nent,
@@ -166,7 +166,7 @@ err_put:
 	hns_roce_table_put(hr_dev, &cq_table->table, hr_cq->cqn);
 
 err_out:
-	hns_roce_bitmap_free(&cq_table->bitmap, hr_cq->cqn);
+	hns_roce_bitmap_free(&cq_table->bitmap, hr_cq->cqn, BITMAP_NO_RR);
 	return ret;
 }
 
@@ -176,11 +176,10 @@ static int hns_roce_hw2sw_cq(struct hns_roce_dev *dev,
 {
 	return hns_roce_cmd_mbox(dev, 0, mailbox ? mailbox->dma : 0, cq_num,
 				 mailbox ? 0 : 1, HNS_ROCE_CMD_HW2SW_CQ,
-				 HNS_ROCE_CMD_TIME_CLASS_A);
+				 HNS_ROCE_CMD_TIMEOUT_MSECS);
 }
 
-static void hns_roce_free_cq(struct hns_roce_dev *hr_dev,
-			     struct hns_roce_cq *hr_cq)
+void hns_roce_free_cq(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq)
 {
 	struct hns_roce_cq_table *cq_table = &hr_dev->cq_table;
 	struct device *dev = &hr_dev->pdev->dev;
@@ -204,7 +203,7 @@ static void hns_roce_free_cq(struct hns_roce_dev *hr_dev,
 	spin_unlock_irq(&cq_table->lock);
 
 	hns_roce_table_put(hr_dev, &cq_table->table, hr_cq->cqn);
-	hns_roce_bitmap_free(&cq_table->bitmap, hr_cq->cqn);
+	hns_roce_bitmap_free(&cq_table->bitmap, hr_cq->cqn, BITMAP_NO_RR);
 }
 
 static int hns_roce_ib_get_cq_umem(struct hns_roce_dev *hr_dev,
@@ -349,6 +348,15 @@ struct ib_cq *hns_roce_ib_create_cq(struct ib_device *ib_dev,
 		goto err_mtt;
 	}
 
+	/*
+	 * For the QP created by kernel space, tptr value should be initialized
+	 * to zero; For the QP created by user space, it will cause synchronous
+	 * problems if tptr is set to zero here, so we initialze it in user
+	 * space.
+	 */
+	if (!context)
+		*hr_cq->tptr_addr = 0;
+
 	/* Get created cq handler and carry out event */
 	hr_cq->comp = hns_roce_ib_cq_comp;
 	hr_cq->event = hns_roce_ib_cq_event;
@@ -383,19 +391,25 @@ int hns_roce_ib_destroy_cq(struct ib_cq *ib_cq)
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(ib_cq->device);
 	struct hns_roce_cq *hr_cq = to_hr_cq(ib_cq);
+	int ret = 0;
 
-	hns_roce_free_cq(hr_dev, hr_cq);
-	hns_roce_mtt_cleanup(hr_dev, &hr_cq->hr_buf.hr_mtt);
+	if (hr_dev->hw->destroy_cq) {
+		ret = hr_dev->hw->destroy_cq(ib_cq);
+	} else {
+		hns_roce_free_cq(hr_dev, hr_cq);
+		hns_roce_mtt_cleanup(hr_dev, &hr_cq->hr_buf.hr_mtt);
 
-	if (ib_cq->uobject)
-		ib_umem_release(hr_cq->umem);
-	else
-		/* Free the buff of stored cq */
-		hns_roce_ib_free_cq_buf(hr_dev, &hr_cq->hr_buf, ib_cq->cqe);
+		if (ib_cq->uobject)
+			ib_umem_release(hr_cq->umem);
+		else
+			/* Free the buff of stored cq */
+			hns_roce_ib_free_cq_buf(hr_dev, &hr_cq->hr_buf,
+						ib_cq->cqe);
 
-	kfree(hr_cq);
+		kfree(hr_cq);
+	}
 
-	return 0;
+	return ret;
 }
 
 void hns_roce_cq_completion(struct hns_roce_dev *hr_dev, u32 cqn)

drivers/infiniband/hw/hns/hns_roce_device.h

@@ -37,6 +37,8 @@
 
 #define DRV_NAME "hns_roce"
 
+#define HNS_ROCE_HW_VER1	('h' << 24 | 'i' << 16 | '0' << 8 | '6')
+
 #define MAC_ADDR_OCTET_NUM			6
 #define HNS_ROCE_MAX_MSG_LEN			0x80000000
 
@@ -54,6 +56,12 @@
 #define HNS_ROCE_MAX_INNER_MTPT_NUM		0x7
 #define HNS_ROCE_MAX_MTPT_PBL_NUM		0x100000
 
+#define HNS_ROCE_EACH_FREE_CQ_WAIT_MSECS	20
+#define HNS_ROCE_MAX_FREE_CQ_WAIT_CNT	\
+	(5000 / HNS_ROCE_EACH_FREE_CQ_WAIT_MSECS)
+#define HNS_ROCE_CQE_WCMD_EMPTY_BIT		0x2
+#define HNS_ROCE_MIN_CQE_CNT			16
+
 #define HNS_ROCE_MAX_IRQ_NUM			34
 
 #define HNS_ROCE_COMP_VEC_NUM			32
@@ -70,6 +78,9 @@
 #define HNS_ROCE_MAX_GID_NUM			16
 #define HNS_ROCE_GID_SIZE			16
 
+#define BITMAP_NO_RR				0
+#define BITMAP_RR				1
+
 #define MR_TYPE_MR				0x00
 #define MR_TYPE_DMA				0x03
 
@@ -196,9 +207,9 @@ struct hns_roce_bitmap {
 /* Order = 0: bitmap is biggest, order = max bitmap is least (only a bit) */
 /* Every bit repesent to a partner free/used status in bitmap */
 /*
-* Initial, bits of other bitmap are all 0 except that a bit of max_order is 1
-* Bit = 1 represent to idle and available; bit = 0: not available
-*/
+ * Initial, bits of other bitmap are all 0 except that a bit of max_order is 1
+ * Bit = 1 represent to idle and available; bit = 0: not available
+ */
 struct hns_roce_buddy {
 	/* Members point to every order level bitmap */
 	unsigned long **bits;
@@ -296,7 +307,7 @@ struct hns_roce_cq {
 	u32				cq_depth;
 	u32				cons_index;
 	void __iomem			*cq_db_l;
-	void __iomem			*tptr_addr;
+	u16				*tptr_addr;
 	unsigned long			cqn;
 	u32				vector;
 	atomic_t			refcount;
@@ -360,29 +371,34 @@ struct hns_roce_cmdq {
 	struct mutex		hcr_mutex;
 	struct semaphore	poll_sem;
 	/*
-	* Event mode: cmd register mutex protection,
-	* ensure to not exceed max_cmds and user use limit region
-	*/
+	 * Event mode: cmd register mutex protection,
+	 * ensure to not exceed max_cmds and user use limit region
+	 */
 	struct semaphore	event_sem;
 	int			max_cmds;
 	spinlock_t		context_lock;
 	int			free_head;
 	struct hns_roce_cmd_context *context;
 	/*
-	* Result of get integer part
-	* which max_comds compute according a power of 2
-	*/
+	 * Result of get integer part
+	 * which max_comds compute according a power of 2
+	 */
 	u16			token_mask;
 	/*
-	* Process whether use event mode, init default non-zero
-	* After the event queue of cmd event ready,
-	* can switch into event mode
-	* close device, switch into poll mode(non event mode)
-	*/
+	 * Process whether use event mode, init default non-zero
+	 * After the event queue of cmd event ready,
+	 * can switch into event mode
+	 * close device, switch into poll mode(non event mode)
+	 */
 	u8			use_events;
 	u8			toggle;
 };
 
+struct hns_roce_cmd_mailbox {
+	void		       *buf;
+	dma_addr_t		dma;
+};
+
 struct hns_roce_dev;
 
 struct hns_roce_qp {
@@ -424,8 +440,6 @@ struct hns_roce_ib_iboe {
 	struct net_device      *netdevs[HNS_ROCE_MAX_PORTS];
 	struct notifier_block	nb;
 	struct notifier_block	nb_inet;
-	/* 16 GID is shared by 6 port in v1 engine. */
-	union ib_gid		gid_table[HNS_ROCE_MAX_GID_NUM];
 	u8			phy_port[HNS_ROCE_MAX_PORTS];
 };
 
@@ -519,6 +533,8 @@ struct hns_roce_hw {
 			 struct ib_recv_wr **bad_recv_wr);
 	int (*req_notify_cq)(struct ib_cq *ibcq, enum ib_cq_notify_flags flags);
 	int (*poll_cq)(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc);
+	int (*dereg_mr)(struct hns_roce_dev *hr_dev, struct hns_roce_mr *mr);
+	int (*destroy_cq)(struct ib_cq *ibcq);
 	void	*priv;
 };
 
@@ -553,6 +569,8 @@ struct hns_roce_dev {
 
 	int			cmd_mod;
 	int			loop_idc;
+	dma_addr_t		tptr_dma_addr; /*only for hw v1*/
+	u32			tptr_size; /*only for hw v1*/
 	struct hns_roce_hw	*hw;
 };
 
@@ -657,7 +675,8 @@ void hns_roce_cleanup_cq_table(struct hns_roce_dev *hr_dev);
 void hns_roce_cleanup_qp_table(struct hns_roce_dev *hr_dev);
 
 int hns_roce_bitmap_alloc(struct hns_roce_bitmap *bitmap, unsigned long *obj);
-void hns_roce_bitmap_free(struct hns_roce_bitmap *bitmap, unsigned long obj);
+void hns_roce_bitmap_free(struct hns_roce_bitmap *bitmap, unsigned long obj,
+			 int rr);
 int hns_roce_bitmap_init(struct hns_roce_bitmap *bitmap, u32 num, u32 mask,
 			 u32 reserved_bot, u32 resetrved_top);
 void hns_roce_bitmap_cleanup(struct hns_roce_bitmap *bitmap);
@@ -665,9 +684,11 @@ void hns_roce_cleanup_bitmap(struct hns_roce_dev *hr_dev);
 int hns_roce_bitmap_alloc_range(struct hns_roce_bitmap *bitmap, int cnt,
 				int align, unsigned long *obj);
 void hns_roce_bitmap_free_range(struct hns_roce_bitmap *bitmap,
-				unsigned long obj, int cnt);
+				unsigned long obj, int cnt,
+				int rr);
 
-struct ib_ah *hns_roce_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr);
+struct ib_ah *hns_roce_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
+				 struct ib_udata *udata);
 int hns_roce_query_ah(struct ib_ah *ibah, struct ib_ah_attr *ah_attr);
 int hns_roce_destroy_ah(struct ib_ah *ah);
 
@@ -681,6 +702,10 @@ struct ib_mr *hns_roce_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				   u64 virt_addr, int access_flags,
 				   struct ib_udata *udata);
 int hns_roce_dereg_mr(struct ib_mr *ibmr);
+int hns_roce_hw2sw_mpt(struct hns_roce_dev *hr_dev,
+		       struct hns_roce_cmd_mailbox *mailbox,
+		       unsigned long mpt_index);
+unsigned long key_to_hw_index(u32 key);
 
 void hns_roce_buf_free(struct hns_roce_dev *hr_dev, u32 size,
 		       struct hns_roce_buf *buf);
@@ -717,6 +742,7 @@ struct ib_cq *hns_roce_ib_create_cq(struct ib_device *ib_dev,
 				    struct ib_udata *udata);
 
 int hns_roce_ib_destroy_cq(struct ib_cq *ib_cq);
+void hns_roce_free_cq(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq);
 
 void hns_roce_cq_completion(struct hns_roce_dev *hr_dev, u32 cqn);
 void hns_roce_cq_event(struct hns_roce_dev *hr_dev, u32 cqn, int event_type);

drivers/infiniband/hw/hns/hns_roce_eq.c

@@ -371,9 +371,9 @@ static int hns_roce_aeq_ovf_int(struct hns_roce_dev *hr_dev,
 	int i = 0;
 
 	/**
-	* AEQ overflow ECC mult bit err CEQ overflow alarm
-	* must clear interrupt, mask irq, clear irq, cancel mask operation
-	*/
+	 * AEQ overflow ECC mult bit err CEQ overflow alarm
+	 * must clear interrupt, mask irq, clear irq, cancel mask operation
+	 */
 	aeshift_val = roce_read(hr_dev, ROCEE_CAEP_AEQC_AEQE_SHIFT_REG);
 
 	if (roce_get_bit(aeshift_val,

drivers/infiniband/hw/hns/hns_roce_hem.c

@@ -80,9 +80,9 @@ struct hns_roce_hem *hns_roce_alloc_hem(struct hns_roce_dev *hr_dev, int npages,
 			--order;
 
 		/*
-		* Alloc memory one time. If failed, don't alloc small block
-		* memory, directly return fail.
-		*/
+		 * Alloc memory one time. If failed, don't alloc small block
+		 * memory, directly return fail.
+		 */
 		mem = &chunk->mem[chunk->npages];
 		buf = dma_alloc_coherent(&hr_dev->pdev->dev, PAGE_SIZE << order,
 				&sg_dma_address(mem), gfp_mask);

drivers/infiniband/hw/hns/hns_roce_hw_v1.c

@@ -32,6 +32,7 @@
 
 #include <linux/platform_device.h>
 #include <linux/acpi.h>
+#include <linux/etherdevice.h>
 #include <rdma/ib_umem.h>
 #include "hns_roce_common.h"
 #include "hns_roce_device.h"
@@ -72,6 +73,8 @@ int hns_roce_v1_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 	int nreq = 0;
 	u32 ind = 0;
 	int ret = 0;
+	u8 *smac;
+	int loopback;
 
 	if (unlikely(ibqp->qp_type != IB_QPT_GSI &&
 		ibqp->qp_type != IB_QPT_RC)) {
@@ -129,6 +132,14 @@ int hns_roce_v1_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 				       UD_SEND_WQE_U32_8_DMAC_5_M,
 				       UD_SEND_WQE_U32_8_DMAC_5_S,
 				       ah->av.mac[5]);
+
+			smac = (u8 *)hr_dev->dev_addr[qp->port];
+			loopback = ether_addr_equal_unaligned(ah->av.mac,
+							      smac) ? 1 : 0;
+			roce_set_bit(ud_sq_wqe->u32_8,
+				     UD_SEND_WQE_U32_8_LOOPBACK_INDICATOR_S,
+				     loopback);
+
 			roce_set_field(ud_sq_wqe->u32_8,
 				       UD_SEND_WQE_U32_8_OPERATION_TYPE_M,
 				       UD_SEND_WQE_U32_8_OPERATION_TYPE_S,
@@ -284,6 +295,8 @@ out:
 		roce_set_field(sq_db.u32_4, SQ_DOORBELL_U32_4_SQ_HEAD_M,
 			       SQ_DOORBELL_U32_4_SQ_HEAD_S,
 			      (qp->sq.head & ((qp->sq.wqe_cnt << 1) - 1)));
+		roce_set_field(sq_db.u32_4, SQ_DOORBELL_U32_4_SL_M,
+			       SQ_DOORBELL_U32_4_SL_S, qp->sl);
 		roce_set_field(sq_db.u32_4, SQ_DOORBELL_U32_4_PORT_M,
 			       SQ_DOORBELL_U32_4_PORT_S, qp->phy_port);
 		roce_set_field(sq_db.u32_8, SQ_DOORBELL_U32_8_QPN_M,
@@ -611,6 +624,213 @@ ext_sdb_buf_fail_out:
 	return ret;
 }
 
+static struct hns_roce_qp *hns_roce_v1_create_lp_qp(struct hns_roce_dev *hr_dev,
+						    struct ib_pd *pd)
+{
+	struct device *dev = &hr_dev->pdev->dev;
+	struct ib_qp_init_attr init_attr;
+	struct ib_qp *qp;
+
+	memset(&init_attr, 0, sizeof(struct ib_qp_init_attr));
+	init_attr.qp_type		= IB_QPT_RC;
+	init_attr.sq_sig_type		= IB_SIGNAL_ALL_WR;
+	init_attr.cap.max_recv_wr	= HNS_ROCE_MIN_WQE_NUM;
+	init_attr.cap.max_send_wr	= HNS_ROCE_MIN_WQE_NUM;
+
+	qp = hns_roce_create_qp(pd, &init_attr, NULL);
+	if (IS_ERR(qp)) {
+		dev_err(dev, "Create loop qp for mr free failed!");
+		return NULL;
+	}
+
+	return to_hr_qp(qp);
+}
+
+static int hns_roce_v1_rsv_lp_qp(struct hns_roce_dev *hr_dev)
+{
+	struct hns_roce_caps *caps = &hr_dev->caps;
+	struct device *dev = &hr_dev->pdev->dev;
+	struct ib_cq_init_attr cq_init_attr;
+	struct hns_roce_free_mr *free_mr;
+	struct ib_qp_attr attr = { 0 };
+	struct hns_roce_v1_priv *priv;
+	struct hns_roce_qp *hr_qp;
+	struct ib_cq *cq;
+	struct ib_pd *pd;
+	u64 subnet_prefix;
+	int attr_mask = 0;
+	int i;
+	int ret;
+	u8 phy_port;
+	u8 sl;
+
+	priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv;
+	free_mr = &priv->free_mr;
+
+	/* Reserved cq for loop qp */
+	cq_init_attr.cqe		= HNS_ROCE_MIN_WQE_NUM * 2;
+	cq_init_attr.comp_vector	= 0;
+	cq = hns_roce_ib_create_cq(&hr_dev->ib_dev, &cq_init_attr, NULL, NULL);
+	if (IS_ERR(cq)) {
+		dev_err(dev, "Create cq for reseved loop qp failed!");
+		return -ENOMEM;
+	}
+	free_mr->mr_free_cq = to_hr_cq(cq);
+	free_mr->mr_free_cq->ib_cq.device		= &hr_dev->ib_dev;
+	free_mr->mr_free_cq->ib_cq.uobject		= NULL;
+	free_mr->mr_free_cq->ib_cq.comp_handler		= NULL;
+	free_mr->mr_free_cq->ib_cq.event_handler	= NULL;
+	free_mr->mr_free_cq->ib_cq.cq_context		= NULL;
+	atomic_set(&free_mr->mr_free_cq->ib_cq.usecnt, 0);
+
+	pd = hns_roce_alloc_pd(&hr_dev->ib_dev, NULL, NULL);
+	if (IS_ERR(pd)) {
+		dev_err(dev, "Create pd for reseved loop qp failed!");
+		ret = -ENOMEM;
+		goto alloc_pd_failed;
+	}
+	free_mr->mr_free_pd = to_hr_pd(pd);
+	free_mr->mr_free_pd->ibpd.device  = &hr_dev->ib_dev;
+	free_mr->mr_free_pd->ibpd.uobject = NULL;
+	atomic_set(&free_mr->mr_free_pd->ibpd.usecnt, 0);
+
+	attr.qp_access_flags	= IB_ACCESS_REMOTE_WRITE;
+	attr.pkey_index		= 0;
+	attr.min_rnr_timer	= 0;
+	/* Disable read ability */
+	attr.max_dest_rd_atomic = 0;
+	attr.max_rd_atomic	= 0;
+	/* Use arbitrary values as rq_psn and sq_psn */
+	attr.rq_psn		= 0x0808;
+	attr.sq_psn		= 0x0808;
+	attr.retry_cnt		= 7;
+	attr.rnr_retry		= 7;
+	attr.timeout		= 0x12;
+	attr.path_mtu		= IB_MTU_256;
+	attr.ah_attr.ah_flags		= 1;
+	attr.ah_attr.static_rate	= 3;
+	attr.ah_attr.grh.sgid_index	= 0;
+	attr.ah_attr.grh.hop_limit	= 1;
+	attr.ah_attr.grh.flow_label	= 0;
+	attr.ah_attr.grh.traffic_class	= 0;
+
+	subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
+	for (i = 0; i < HNS_ROCE_V1_RESV_QP; i++) {
+		free_mr->mr_free_qp[i] = hns_roce_v1_create_lp_qp(hr_dev, pd);
+		if (IS_ERR(free_mr->mr_free_qp[i])) {
+			dev_err(dev, "Create loop qp failed!\n");
+			goto create_lp_qp_failed;
+		}
+		hr_qp = free_mr->mr_free_qp[i];
+
+		sl = i / caps->num_ports;
+
+		if (caps->num_ports == HNS_ROCE_MAX_PORTS)
+			phy_port = (i >= HNS_ROCE_MAX_PORTS) ? (i - 2) :
+				(i % caps->num_ports);
+		else
+			phy_port = i % caps->num_ports;
+
+		hr_qp->port		= phy_port + 1;
+		hr_qp->phy_port		= phy_port;
+		hr_qp->ibqp.qp_type	= IB_QPT_RC;
+		hr_qp->ibqp.device	= &hr_dev->ib_dev;
+		hr_qp->ibqp.uobject	= NULL;
+		atomic_set(&hr_qp->ibqp.usecnt, 0);
+		hr_qp->ibqp.pd		= pd;
+		hr_qp->ibqp.recv_cq	= cq;
+		hr_qp->ibqp.send_cq	= cq;
+
+		attr.ah_attr.port_num	= phy_port + 1;
+		attr.ah_attr.sl		= sl;
+		attr.port_num		= phy_port + 1;
+
+		attr.dest_qp_num	= hr_qp->qpn;
+		memcpy(attr.ah_attr.dmac, hr_dev->dev_addr[phy_port],
+		       MAC_ADDR_OCTET_NUM);
+
+		memcpy(attr.ah_attr.grh.dgid.raw,
+			&subnet_prefix, sizeof(u64));
+		memcpy(&attr.ah_attr.grh.dgid.raw[8],
+		       hr_dev->dev_addr[phy_port], 3);
+		memcpy(&attr.ah_attr.grh.dgid.raw[13],
+		       hr_dev->dev_addr[phy_port] + 3, 3);
+		attr.ah_attr.grh.dgid.raw[11] = 0xff;
+		attr.ah_attr.grh.dgid.raw[12] = 0xfe;
+		attr.ah_attr.grh.dgid.raw[8] ^= 2;
+
+		attr_mask |= IB_QP_PORT;
+
+		ret = hr_dev->hw->modify_qp(&hr_qp->ibqp, &attr, attr_mask,
+					    IB_QPS_RESET, IB_QPS_INIT);
+		if (ret) {
+			dev_err(dev, "modify qp failed(%d)!\n", ret);
+			goto create_lp_qp_failed;
+		}
+
+		ret = hr_dev->hw->modify_qp(&hr_qp->ibqp, &attr, attr_mask,
+					    IB_QPS_INIT, IB_QPS_RTR);
+		if (ret) {
+			dev_err(dev, "modify qp failed(%d)!\n", ret);
+			goto create_lp_qp_failed;
+		}
+
+		ret = hr_dev->hw->modify_qp(&hr_qp->ibqp, &attr, attr_mask,
+					    IB_QPS_RTR, IB_QPS_RTS);
+		if (ret) {
+			dev_err(dev, "modify qp failed(%d)!\n", ret);
+			goto create_lp_qp_failed;
+		}
+	}
+
+	return 0;
+
+create_lp_qp_failed:
+	for (i -= 1; i >= 0; i--) {
+		hr_qp = free_mr->mr_free_qp[i];
+		if (hns_roce_v1_destroy_qp(&hr_qp->ibqp))
+			dev_err(dev, "Destroy qp %d for mr free failed!\n", i);
+	}
+
+	if (hns_roce_dealloc_pd(pd))
+		dev_err(dev, "Destroy pd for create_lp_qp failed!\n");
+
+alloc_pd_failed:
+	if (hns_roce_ib_destroy_cq(cq))
+		dev_err(dev, "Destroy cq for create_lp_qp failed!\n");
+
+	return -EINVAL;
+}
+
+static void hns_roce_v1_release_lp_qp(struct hns_roce_dev *hr_dev)
+{
+	struct device *dev = &hr_dev->pdev->dev;
+	struct hns_roce_free_mr *free_mr;
+	struct hns_roce_v1_priv *priv;
+	struct hns_roce_qp *hr_qp;
+	int ret;
+	int i;
+
+	priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv;
+	free_mr = &priv->free_mr;
+
+	for (i = 0; i < HNS_ROCE_V1_RESV_QP; i++) {
+		hr_qp = free_mr->mr_free_qp[i];
+		ret = hns_roce_v1_destroy_qp(&hr_qp->ibqp);
+		if (ret)
+			dev_err(dev, "Destroy qp %d for mr free failed(%d)!\n",
+				i, ret);
+	}
+
+	ret = hns_roce_ib_destroy_cq(&free_mr->mr_free_cq->ib_cq);
+	if (ret)
+		dev_err(dev, "Destroy cq for mr_free failed(%d)!\n", ret);
+
+	ret = hns_roce_dealloc_pd(&free_mr->mr_free_pd->ibpd);
+	if (ret)
+		dev_err(dev, "Destroy pd for mr_free failed(%d)!\n", ret);
+}
+
 static int hns_roce_db_init(struct hns_roce_dev *hr_dev)
 {
 	struct device *dev = &hr_dev->pdev->dev;
@@ -648,6 +868,223 @@ static int hns_roce_db_init(struct hns_roce_dev *hr_dev)
 	return 0;
 }
 
+void hns_roce_v1_recreate_lp_qp_work_fn(struct work_struct *work)
+{
+	struct hns_roce_recreate_lp_qp_work *lp_qp_work;
+	struct hns_roce_dev *hr_dev;
+
+	lp_qp_work = container_of(work, struct hns_roce_recreate_lp_qp_work,
+				  work);
+	hr_dev = to_hr_dev(lp_qp_work->ib_dev);
+
+	hns_roce_v1_release_lp_qp(hr_dev);
+
+	if (hns_roce_v1_rsv_lp_qp(hr_dev))
+		dev_err(&hr_dev->pdev->dev, "create reserver qp failed\n");
+
+	if (lp_qp_work->comp_flag)
+		complete(lp_qp_work->comp);
+
+	kfree(lp_qp_work);
+}
+
+static int hns_roce_v1_recreate_lp_qp(struct hns_roce_dev *hr_dev)
+{
+	struct device *dev = &hr_dev->pdev->dev;
+	struct hns_roce_recreate_lp_qp_work *lp_qp_work;
+	struct hns_roce_free_mr *free_mr;
+	struct hns_roce_v1_priv *priv;
+	struct completion comp;
+	unsigned long end =
+	  msecs_to_jiffies(HNS_ROCE_V1_RECREATE_LP_QP_TIMEOUT_MSECS) + jiffies;
+
+	priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv;
+	free_mr = &priv->free_mr;
+
+	lp_qp_work = kzalloc(sizeof(struct hns_roce_recreate_lp_qp_work),
+			     GFP_KERNEL);
+
+	INIT_WORK(&(lp_qp_work->work), hns_roce_v1_recreate_lp_qp_work_fn);
+
+	lp_qp_work->ib_dev = &(hr_dev->ib_dev);
+	lp_qp_work->comp = &comp;
+	lp_qp_work->comp_flag = 1;
+
+	init_completion(lp_qp_work->comp);
+
+	queue_work(free_mr->free_mr_wq, &(lp_qp_work->work));
+
+	while (time_before_eq(jiffies, end)) {
+		if (try_wait_for_completion(&comp))
+			return 0;
+		msleep(HNS_ROCE_V1_RECREATE_LP_QP_WAIT_VALUE);
+	}
+
+	lp_qp_work->comp_flag = 0;
+	if (try_wait_for_completion(&comp))
+		return 0;
+
+	dev_warn(dev, "recreate lp qp failed 20s timeout and return failed!\n");
+	return -ETIMEDOUT;
+}
+
+static int hns_roce_v1_send_lp_wqe(struct hns_roce_qp *hr_qp)
+{
+	struct hns_roce_dev *hr_dev = to_hr_dev(hr_qp->ibqp.device);
+	struct device *dev = &hr_dev->pdev->dev;
+	struct ib_send_wr send_wr, *bad_wr;
+	int ret;
+
+	memset(&send_wr, 0, sizeof(send_wr));
+	send_wr.next	= NULL;
+	send_wr.num_sge	= 0;
+	send_wr.send_flags = 0;
+	send_wr.sg_list	= NULL;
+	send_wr.wr_id	= (unsigned long long)&send_wr;
+	send_wr.opcode	= IB_WR_RDMA_WRITE;
+
+	ret = hns_roce_v1_post_send(&hr_qp->ibqp, &send_wr, &bad_wr);
+	if (ret) {
+		dev_err(dev, "Post write wqe for mr free failed(%d)!", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void hns_roce_v1_mr_free_work_fn(struct work_struct *work)
+{
+	struct hns_roce_mr_free_work *mr_work;
+	struct ib_wc wc[HNS_ROCE_V1_RESV_QP];
+	struct hns_roce_free_mr *free_mr;
+	struct hns_roce_cq *mr_free_cq;
+	struct hns_roce_v1_priv *priv;
+	struct hns_roce_dev *hr_dev;
+	struct hns_roce_mr *hr_mr;
+	struct hns_roce_qp *hr_qp;
+	struct device *dev;
+	unsigned long end =
+		msecs_to_jiffies(HNS_ROCE_V1_FREE_MR_TIMEOUT_MSECS) + jiffies;
+	int i;
+	int ret;
+	int ne;
+
+	mr_work = container_of(work, struct hns_roce_mr_free_work, work);
+	hr_mr = (struct hns_roce_mr *)mr_work->mr;
+	hr_dev = to_hr_dev(mr_work->ib_dev);
+	dev = &hr_dev->pdev->dev;
+
+	priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv;
+	free_mr = &priv->free_mr;
+	mr_free_cq = free_mr->mr_free_cq;
+
+	for (i = 0; i < HNS_ROCE_V1_RESV_QP; i++) {
+		hr_qp = free_mr->mr_free_qp[i];
+		ret = hns_roce_v1_send_lp_wqe(hr_qp);
+		if (ret) {
+			dev_err(dev,
+			     "Send wqe (qp:0x%lx) for mr free failed(%d)!\n",
+			     hr_qp->qpn, ret);
+			goto free_work;
+		}
+	}
+
+	ne = HNS_ROCE_V1_RESV_QP;
+	do {
+		ret = hns_roce_v1_poll_cq(&mr_free_cq->ib_cq, ne, wc);
+		if (ret < 0) {
+			dev_err(dev,
+			   "(qp:0x%lx) starts, Poll cqe failed(%d) for mr 0x%x free! Remain %d cqe\n",
+			   hr_qp->qpn, ret, hr_mr->key, ne);
+			goto free_work;
+		}
+		ne -= ret;
+		msleep(HNS_ROCE_V1_FREE_MR_WAIT_VALUE);
+	} while (ne && time_before_eq(jiffies, end));
+
+	if (ne != 0)
+		dev_err(dev,
+			"Poll cqe for mr 0x%x free timeout! Remain %d cqe\n",
+			hr_mr->key, ne);
+
+free_work:
+	if (mr_work->comp_flag)
+		complete(mr_work->comp);
+	kfree(mr_work);
+}
+
+int hns_roce_v1_dereg_mr(struct hns_roce_dev *hr_dev, struct hns_roce_mr *mr)
+{
+	struct device *dev = &hr_dev->pdev->dev;
+	struct hns_roce_mr_free_work *mr_work;
+	struct hns_roce_free_mr *free_mr;
+	struct hns_roce_v1_priv *priv;
+	struct completion comp;
+	unsigned long end =
+		msecs_to_jiffies(HNS_ROCE_V1_FREE_MR_TIMEOUT_MSECS) + jiffies;
+	unsigned long start = jiffies;
+	int npages;
+	int ret = 0;
+
+	priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv;
+	free_mr = &priv->free_mr;
+
+	if (mr->enabled) {
+		if (hns_roce_hw2sw_mpt(hr_dev, NULL, key_to_hw_index(mr->key)
+				       & (hr_dev->caps.num_mtpts - 1)))
+			dev_warn(dev, "HW2SW_MPT failed!\n");
+	}
+
+	mr_work = kzalloc(sizeof(*mr_work), GFP_KERNEL);
+	if (!mr_work) {
+		ret = -ENOMEM;
+		goto free_mr;
+	}
+
+	INIT_WORK(&(mr_work->work), hns_roce_v1_mr_free_work_fn);
+
+	mr_work->ib_dev = &(hr_dev->ib_dev);
+	mr_work->comp = &comp;
+	mr_work->comp_flag = 1;
+	mr_work->mr = (void *)mr;
+	init_completion(mr_work->comp);
+
+	queue_work(free_mr->free_mr_wq, &(mr_work->work));
+
+	while (time_before_eq(jiffies, end)) {
+		if (try_wait_for_completion(&comp))
+			goto free_mr;
+		msleep(HNS_ROCE_V1_FREE_MR_WAIT_VALUE);
+	}
+
+	mr_work->comp_flag = 0;
+	if (try_wait_for_completion(&comp))
+		goto free_mr;
+
+	dev_warn(dev, "Free mr work 0x%x over 50s and failed!\n", mr->key);
+	ret = -ETIMEDOUT;
+
+free_mr:
+	dev_dbg(dev, "Free mr 0x%x use 0x%x us.\n",
+		mr->key, jiffies_to_usecs(jiffies) - jiffies_to_usecs(start));
+
+	if (mr->size != ~0ULL) {
+		npages = ib_umem_page_count(mr->umem);
+		dma_free_coherent(dev, npages * 8, mr->pbl_buf,
+				  mr->pbl_dma_addr);
+	}
+
+	hns_roce_bitmap_free(&hr_dev->mr_table.mtpt_bitmap,
+			     key_to_hw_index(mr->key), 0);
+
+	if (mr->umem)
+		ib_umem_release(mr->umem);
+
+	kfree(mr);
+
+	return ret;
+}
+
 static void hns_roce_db_free(struct hns_roce_dev *hr_dev)
 {
 	struct device *dev = &hr_dev->pdev->dev;
@@ -849,6 +1286,85 @@ static void hns_roce_bt_free(struct hns_roce_dev *hr_dev)
 		priv->bt_table.qpc_buf.buf, priv->bt_table.qpc_buf.map);
 }
 
+static int hns_roce_tptr_init(struct hns_roce_dev *hr_dev)
+{
+	struct device *dev = &hr_dev->pdev->dev;
+	struct hns_roce_buf_list *tptr_buf;
+	struct hns_roce_v1_priv *priv;
+
+	priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv;
+	tptr_buf = &priv->tptr_table.tptr_buf;
+
+	/*
+	 * This buffer will be used for CQ's tptr(tail pointer), also
+	 * named ci(customer index). Every CQ will use 2 bytes to save
+	 * cqe ci in hip06. Hardware will read this area to get new ci
+	 * when the queue is almost full.
+	 */
+	tptr_buf->buf = dma_alloc_coherent(dev, HNS_ROCE_V1_TPTR_BUF_SIZE,
+					   &tptr_buf->map, GFP_KERNEL);
+	if (!tptr_buf->buf)
+		return -ENOMEM;
+
+	hr_dev->tptr_dma_addr = tptr_buf->map;
+	hr_dev->tptr_size = HNS_ROCE_V1_TPTR_BUF_SIZE;
+
+	return 0;
+}
+
+static void hns_roce_tptr_free(struct hns_roce_dev *hr_dev)
+{
+	struct device *dev = &hr_dev->pdev->dev;
+	struct hns_roce_buf_list *tptr_buf;
+	struct hns_roce_v1_priv *priv;
+
+	priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv;
+	tptr_buf = &priv->tptr_table.tptr_buf;
+
+	dma_free_coherent(dev, HNS_ROCE_V1_TPTR_BUF_SIZE,
+			  tptr_buf->buf, tptr_buf->map);
+}
+
+static int hns_roce_free_mr_init(struct hns_roce_dev *hr_dev)
+{
+	struct device *dev = &hr_dev->pdev->dev;
+	struct hns_roce_free_mr *free_mr;
+	struct hns_roce_v1_priv *priv;
+	int ret = 0;
+
+	priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv;
+	free_mr = &priv->free_mr;
+
+	free_mr->free_mr_wq = create_singlethread_workqueue("hns_roce_free_mr");
+	if (!free_mr->free_mr_wq) {
+		dev_err(dev, "Create free mr workqueue failed!\n");
+		return -ENOMEM;
+	}
+
+	ret = hns_roce_v1_rsv_lp_qp(hr_dev);
+	if (ret) {
+		dev_err(dev, "Reserved loop qp failed(%d)!\n", ret);
+		flush_workqueue(free_mr->free_mr_wq);
+		destroy_workqueue(free_mr->free_mr_wq);
+	}
+
+	return ret;
+}
+
+static void hns_roce_free_mr_free(struct hns_roce_dev *hr_dev)
+{
+	struct hns_roce_free_mr *free_mr;
+	struct hns_roce_v1_priv *priv;
+
+	priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv;
+	free_mr = &priv->free_mr;
+
+	flush_workqueue(free_mr->free_mr_wq);
+	destroy_workqueue(free_mr->free_mr_wq);
+
+	hns_roce_v1_release_lp_qp(hr_dev);
+}
+
 /**
  * hns_roce_v1_reset - reset RoCE
  * @hr_dev: RoCE device struct pointer
@@ -898,6 +1414,38 @@ int hns_roce_v1_reset(struct hns_roce_dev *hr_dev, bool dereset)
 	return ret;
 }
 
+static int hns_roce_des_qp_init(struct hns_roce_dev *hr_dev)
+{
+	struct device *dev = &hr_dev->pdev->dev;
+	struct hns_roce_v1_priv *priv;
+	struct hns_roce_des_qp *des_qp;
+
+	priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv;
+	des_qp = &priv->des_qp;
+
+	des_qp->requeue_flag = 1;
+	des_qp->qp_wq = create_singlethread_workqueue("hns_roce_destroy_qp");
+	if (!des_qp->qp_wq) {
+		dev_err(dev, "Create destroy qp workqueue failed!\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void hns_roce_des_qp_free(struct hns_roce_dev *hr_dev)
+{
+	struct hns_roce_v1_priv *priv;
+	struct hns_roce_des_qp *des_qp;
+
+	priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv;
+	des_qp = &priv->des_qp;
+
+	des_qp->requeue_flag = 0;
+	flush_workqueue(des_qp->qp_wq);
+	destroy_workqueue(des_qp->qp_wq);
+}
+
 void hns_roce_v1_profile(struct hns_roce_dev *hr_dev)
 {
 	int i = 0;
@@ -906,12 +1454,11 @@ void hns_roce_v1_profile(struct hns_roce_dev *hr_dev)
 	hr_dev->vendor_id = le32_to_cpu(roce_read(hr_dev, ROCEE_VENDOR_ID_REG));
 	hr_dev->vendor_part_id = le32_to_cpu(roce_read(hr_dev,
 					     ROCEE_VENDOR_PART_ID_REG));
-	hr_dev->hw_rev = le32_to_cpu(roce_read(hr_dev, ROCEE_HW_VERSION_REG));
-
 	hr_dev->sys_image_guid = le32_to_cpu(roce_read(hr_dev,
 					     ROCEE_SYS_IMAGE_GUID_L_REG)) |
 				((u64)le32_to_cpu(roce_read(hr_dev,
 					    ROCEE_SYS_IMAGE_GUID_H_REG)) << 32);
+	hr_dev->hw_rev		= HNS_ROCE_HW_VER1;
 
 	caps->num_qps		= HNS_ROCE_V1_MAX_QP_NUM;
 	caps->max_wqes		= HNS_ROCE_V1_MAX_WQE_NUM;
@@ -1001,18 +1548,44 @@ int hns_roce_v1_init(struct hns_roce_dev *hr_dev)
 		goto error_failed_raq_init;
 	}
 
-	hns_roce_port_enable(hr_dev, HNS_ROCE_PORT_UP);
-
 	ret = hns_roce_bt_init(hr_dev);
 	if (ret) {
 		dev_err(dev, "bt init failed!\n");
 		goto error_failed_bt_init;
 	}
 
+	ret = hns_roce_tptr_init(hr_dev);
+	if (ret) {
+		dev_err(dev, "tptr init failed!\n");
+		goto error_failed_tptr_init;
+	}
+
+	ret = hns_roce_des_qp_init(hr_dev);
+	if (ret) {
+		dev_err(dev, "des qp init failed!\n");
+		goto error_failed_des_qp_init;
+	}
+
+	ret = hns_roce_free_mr_init(hr_dev);
+	if (ret) {
+		dev_err(dev, "free mr init failed!\n");
+		goto error_failed_free_mr_init;
+	}
+
+	hns_roce_port_enable(hr_dev, HNS_ROCE_PORT_UP);
+
 	return 0;
 
+error_failed_free_mr_init:
+	hns_roce_des_qp_free(hr_dev);
+
+error_failed_des_qp_init:
+	hns_roce_tptr_free(hr_dev);
+
+error_failed_tptr_init:
+	hns_roce_bt_free(hr_dev);
+
 error_failed_bt_init:
-	hns_roce_port_enable(hr_dev, HNS_ROCE_PORT_DOWN);
 	hns_roce_raq_free(hr_dev);
 
 error_failed_raq_init:
@@ -1022,8 +1595,11 @@ error_failed_raq_init:
 
 void hns_roce_v1_exit(struct hns_roce_dev *hr_dev)
 {
-	hns_roce_bt_free(hr_dev);
 	hns_roce_port_enable(hr_dev, HNS_ROCE_PORT_DOWN);
+	hns_roce_free_mr_free(hr_dev);
+	hns_roce_des_qp_free(hr_dev);
+	hns_roce_tptr_free(hr_dev);
+	hns_roce_bt_free(hr_dev);
 	hns_roce_raq_free(hr_dev);
 	hns_roce_db_free(hr_dev);
 }
@@ -1061,6 +1637,14 @@ void hns_roce_v1_set_mac(struct hns_roce_dev *hr_dev, u8 phy_port, u8 *addr)
 	u32 *p;
 	u32 val;
 
+	/*
+	 * When mac changed, loopback may fail
+	 * because of smac not equal to dmac.
+	 * We Need to release and create reserved qp again.
+	 */
+	if (hr_dev->hw->dereg_mr && hns_roce_v1_recreate_lp_qp(hr_dev))
+		dev_warn(&hr_dev->pdev->dev, "recreate lp qp timeout!\n");
+
 	p = (u32 *)(&addr[0]);
 	reg_smac_l = *p;
 	roce_raw_write(reg_smac_l, hr_dev->reg_base + ROCEE_SMAC_L_0_REG +
@@ -1293,9 +1877,9 @@ static void __hns_roce_v1_cq_clean(struct hns_roce_cq *hr_cq, u32 qpn,
 	}
 
 	/*
-	* Now backwards through the CQ, removing CQ entries
-	* that match our QP by overwriting them with next entries.
-	*/
+	 * Now backwards through the CQ, removing CQ entries
+	 * that match our QP by overwriting them with next entries.
+	 */
 	while ((int) --prod_index - (int) hr_cq->cons_index >= 0) {
 		cqe = get_cqe(hr_cq, prod_index & hr_cq->ib_cq.cqe);
 		if ((roce_get_field(cqe->cqe_byte_16, CQE_BYTE_16_LOCAL_QPN_M,
@@ -1317,9 +1901,9 @@ static void __hns_roce_v1_cq_clean(struct hns_roce_cq *hr_cq, u32 qpn,
 	if (nfreed) {
 		hr_cq->cons_index += nfreed;
 		/*
-		* Make sure update of buffer contents is done before
-		* updating consumer index.
-		*/
+		 * Make sure update of buffer contents is done before
+		 * updating consumer index.
+		 */
 		wmb();
 
 		hns_roce_v1_cq_set_ci(hr_cq, hr_cq->cons_index);
@@ -1339,14 +1923,21 @@ void hns_roce_v1_write_cqc(struct hns_roce_dev *hr_dev,
 			   dma_addr_t dma_handle, int nent, u32 vector)
 {
 	struct hns_roce_cq_context *cq_context = NULL;
-	void __iomem *tptr_addr;
+	struct hns_roce_buf_list *tptr_buf;
+	struct hns_roce_v1_priv *priv;
+	dma_addr_t tptr_dma_addr;
+	int offset;
+
+	priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv;
+	tptr_buf = &priv->tptr_table.tptr_buf;
 
 	cq_context = mb_buf;
 	memset(cq_context, 0, sizeof(*cq_context));
 
-	tptr_addr = 0;
-	hr_dev->priv_addr = tptr_addr;
-	hr_cq->tptr_addr = tptr_addr;
+	/* Get the tptr for this CQ. */
+	offset = hr_cq->cqn * HNS_ROCE_V1_TPTR_ENTRY_SIZE;
+	tptr_dma_addr = tptr_buf->map + offset;
+	hr_cq->tptr_addr = (u16 *)(tptr_buf->buf + offset);
 
 	/* Register cq_context members */
 	roce_set_field(cq_context->cqc_byte_4,
@@ -1390,10 +1981,10 @@ void hns_roce_v1_write_cqc(struct hns_roce_dev *hr_dev,
 	roce_set_field(cq_context->cqc_byte_20,
 		       CQ_CONTEXT_CQC_BYTE_20_CQE_TPTR_ADDR_H_M,
 		       CQ_CONTEXT_CQC_BYTE_20_CQE_TPTR_ADDR_H_S,
-		       (u64)tptr_addr >> 44);
+		       tptr_dma_addr >> 44);
 	cq_context->cqc_byte_20 = cpu_to_le32(cq_context->cqc_byte_20);
 
-	cq_context->cqe_tptr_addr_l = (u32)((u64)tptr_addr >> 12);
+	cq_context->cqe_tptr_addr_l = (u32)(tptr_dma_addr >> 12);
 
 	roce_set_field(cq_context->cqc_byte_32,
 		       CQ_CONTEXT_CQC_BYTE_32_CUR_CQE_BA1_H_M,
@@ -1407,7 +1998,7 @@ void hns_roce_v1_write_cqc(struct hns_roce_dev *hr_dev,
 	roce_set_bit(cq_context->cqc_byte_32,
 		     CQ_CQNTEXT_CQC_BYTE_32_TYPE_OF_COMPLETION_NOTIFICATION_S,
 		     0);
-	/*The initial value of cq's ci is 0 */
+	/* The initial value of cq's ci is 0 */
 	roce_set_field(cq_context->cqc_byte_32,
 		       CQ_CONTEXT_CQC_BYTE_32_CQ_CONS_IDX_M,
 		       CQ_CONTEXT_CQC_BYTE_32_CQ_CONS_IDX_S, 0);
@@ -1424,9 +2015,9 @@ int hns_roce_v1_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
 	notification_flag = (flags & IB_CQ_SOLICITED_MASK) ==
 			    IB_CQ_SOLICITED ? CQ_DB_REQ_NOT : CQ_DB_REQ_NOT_SOL;
 	/*
-	* flags = 0; Notification Flag = 1, next
-	* flags = 1; Notification Flag = 0, solocited
-	*/
+	 * flags = 0; Notification Flag = 1, next
+	 * flags = 1; Notification Flag = 0, solocited
+	 */
 	doorbell[0] = hr_cq->cons_index & ((hr_cq->cq_depth << 1) - 1);
 	roce_set_bit(doorbell[1], ROCEE_DB_OTHERS_H_ROCEE_DB_OTH_HW_SYNS_S, 1);
 	roce_set_field(doorbell[1], ROCEE_DB_OTHERS_H_ROCEE_DB_OTH_CMD_M,
@@ -1581,10 +2172,10 @@ static int hns_roce_v1_poll_one(struct hns_roce_cq *hr_cq,
 		wq = &(*cur_qp)->sq;
 		if ((*cur_qp)->sq_signal_bits) {
 			/*
-			* If sg_signal_bit is 1,
-			* firstly tail pointer updated to wqe
-			* which current cqe correspond to
-			*/
+			 * If sg_signal_bit is 1,
+			 * firstly tail pointer updated to wqe
+			 * which current cqe correspond to
+			 */
 			wqe_ctr = (u16)roce_get_field(cqe->cqe_byte_4,
 						      CQE_BYTE_4_WQE_INDEX_M,
 						      CQE_BYTE_4_WQE_INDEX_S);
@@ -1659,8 +2250,14 @@ int hns_roce_v1_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
 			break;
 	}
 
-	if (npolled)
+	if (npolled) {
+		*hr_cq->tptr_addr = hr_cq->cons_index &
+			((hr_cq->cq_depth << 1) - 1);
+
+		/* Memroy barrier */
+		wmb();
 		hns_roce_v1_cq_set_ci(hr_cq, hr_cq->cons_index);
+	}
 
 	spin_unlock_irqrestore(&hr_cq->lock, flags);
 
@@ -1799,12 +2396,12 @@ static int hns_roce_v1_qp_modify(struct hns_roce_dev *hr_dev,
 	if (op[cur_state][new_state] == HNS_ROCE_CMD_2RST_QP)
 		return hns_roce_cmd_mbox(hr_dev, 0, 0, hr_qp->qpn, 2,
 					 HNS_ROCE_CMD_2RST_QP,
-					 HNS_ROCE_CMD_TIME_CLASS_A);
+					 HNS_ROCE_CMD_TIMEOUT_MSECS);
 
 	if (op[cur_state][new_state] == HNS_ROCE_CMD_2ERR_QP)
 		return hns_roce_cmd_mbox(hr_dev, 0, 0, hr_qp->qpn, 2,
 					 HNS_ROCE_CMD_2ERR_QP,
-					 HNS_ROCE_CMD_TIME_CLASS_A);
+					 HNS_ROCE_CMD_TIMEOUT_MSECS);
 
 	mailbox = hns_roce_alloc_cmd_mailbox(hr_dev);
 	if (IS_ERR(mailbox))
@@ -1814,7 +2411,7 @@ static int hns_roce_v1_qp_modify(struct hns_roce_dev *hr_dev,
 
 	ret = hns_roce_cmd_mbox(hr_dev, mailbox->dma, 0, hr_qp->qpn, 0,
 				op[cur_state][new_state],
-				HNS_ROCE_CMD_TIME_CLASS_C);
+				HNS_ROCE_CMD_TIMEOUT_MSECS);
 
 	hns_roce_free_cmd_mailbox(hr_dev, mailbox);
 	return ret;
@@ -2000,11 +2597,11 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
 	}
 
 	/*
-	*Reset to init
-	*	Mandatory param:
-	*	IB_QP_STATE | IB_QP_PKEY_INDEX | IB_QP_PORT | IB_QP_ACCESS_FLAGS
-	*	Optional param: NA
-	*/
+	 * Reset to init
+	 *	Mandatory param:
+	 *	IB_QP_STATE | IB_QP_PKEY_INDEX | IB_QP_PORT | IB_QP_ACCESS_FLAGS
+	 *	Optional param: NA
+	 */
 	if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) {
 		roce_set_field(context->qpc_bytes_4,
 			       QP_CONTEXT_QPC_BYTES_4_TRANSPORT_SERVICE_TYPE_M,
@@ -2172,24 +2769,14 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
 			     QP_CONTEXT_QPC_BYTE_32_SIGNALING_TYPE_S,
 			     hr_qp->sq_signal_bits);
 
-		for (port = 0; port < hr_dev->caps.num_ports; port++) {
-			smac = (u8 *)hr_dev->dev_addr[port];
-			dev_dbg(dev, "smac: %2x: %2x: %2x: %2x: %2x: %2x\n",
-				smac[0], smac[1], smac[2], smac[3], smac[4],
-				smac[5]);
-			if ((dmac[0] == smac[0]) && (dmac[1] == smac[1]) &&
-			    (dmac[2] == smac[2]) && (dmac[3] == smac[3]) &&
-			    (dmac[4] == smac[4]) && (dmac[5] == smac[5])) {
-				roce_set_bit(context->qpc_bytes_32,
-				    QP_CONTEXT_QPC_BYTE_32_LOOPBACK_INDICATOR_S,
-				    1);
-				break;
-			}
-		}
-
-		if (hr_dev->loop_idc == 0x1)
+		port = (attr_mask & IB_QP_PORT) ? (attr->port_num - 1) :
+			hr_qp->port;
+		smac = (u8 *)hr_dev->dev_addr[port];
+		/* when dmac equals smac or loop_idc is 1, it should loopback */
+		if (ether_addr_equal_unaligned(dmac, smac) ||
+		    hr_dev->loop_idc == 0x1)
 			roce_set_bit(context->qpc_bytes_32,
-				QP_CONTEXT_QPC_BYTE_32_LOOPBACK_INDICATOR_S, 1);
+			      QP_CONTEXT_QPC_BYTE_32_LOOPBACK_INDICATOR_S, 1);
 
 		roce_set_bit(context->qpc_bytes_32,
 			     QP_CONTEXT_QPC_BYTE_32_GLOBAL_HEADER_S,
@@ -2509,7 +3096,7 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
 	/* Every status migrate must change state */
 	roce_set_field(context->qpc_bytes_144,
 		       QP_CONTEXT_QPC_BYTES_144_QP_STATE_M,
-		       QP_CONTEXT_QPC_BYTES_144_QP_STATE_S, attr->qp_state);
+		       QP_CONTEXT_QPC_BYTES_144_QP_STATE_S, new_state);
 
 	/* SW pass context to HW */
 	ret = hns_roce_v1_qp_modify(hr_dev, &hr_qp->mtt,
@@ -2522,9 +3109,9 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
 	}
 
 	/*
-	* Use rst2init to instead of init2init with drv,
-	* need to hw to flash RQ HEAD by DB again
-	*/
+	 * Use rst2init to instead of init2init with drv,
+	 * need to hw to flash RQ HEAD by DB again
+	 */
 	if (cur_state == IB_QPS_INIT && new_state == IB_QPS_INIT) {
 		/* Memory barrier */
 		wmb();
@@ -2619,7 +3206,7 @@ static int hns_roce_v1_query_qpc(struct hns_roce_dev *hr_dev,
 
 	ret = hns_roce_cmd_mbox(hr_dev, 0, mailbox->dma, hr_qp->qpn, 0,
 				HNS_ROCE_CMD_QUERY_QP,
-				HNS_ROCE_CMD_TIME_CLASS_A);
+				HNS_ROCE_CMD_TIMEOUT_MSECS);
 	if (!ret)
 		memcpy(hr_context, mailbox->buf, sizeof(*hr_context));
 	else
@@ -2630,8 +3217,78 @@ static int hns_roce_v1_query_qpc(struct hns_roce_dev *hr_dev,
 	return ret;
 }
 
-int hns_roce_v1_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
-			 int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr)
+static int hns_roce_v1_q_sqp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
+			     int qp_attr_mask,
+			     struct ib_qp_init_attr *qp_init_attr)
+{
+	struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device);
+	struct hns_roce_qp *hr_qp = to_hr_qp(ibqp);
+	struct hns_roce_sqp_context context;
+	u32 addr;
+
+	mutex_lock(&hr_qp->mutex);
+
+	if (hr_qp->state == IB_QPS_RESET) {
+		qp_attr->qp_state = IB_QPS_RESET;
+		goto done;
+	}
+
+	addr = ROCEE_QP1C_CFG0_0_REG +
+		hr_qp->port * sizeof(struct hns_roce_sqp_context);
+	context.qp1c_bytes_4 = roce_read(hr_dev, addr);
+	context.sq_rq_bt_l = roce_read(hr_dev, addr + 1);
+	context.qp1c_bytes_12 = roce_read(hr_dev, addr + 2);
+	context.qp1c_bytes_16 = roce_read(hr_dev, addr + 3);
+	context.qp1c_bytes_20 = roce_read(hr_dev, addr + 4);
+	context.cur_rq_wqe_ba_l = roce_read(hr_dev, addr + 5);
+	context.qp1c_bytes_28 = roce_read(hr_dev, addr + 6);
+	context.qp1c_bytes_32 = roce_read(hr_dev, addr + 7);
+	context.cur_sq_wqe_ba_l = roce_read(hr_dev, addr + 8);
+	context.qp1c_bytes_40 = roce_read(hr_dev, addr + 9);
+
+	hr_qp->state = roce_get_field(context.qp1c_bytes_4,
+				      QP1C_BYTES_4_QP_STATE_M,
+				      QP1C_BYTES_4_QP_STATE_S);
+	qp_attr->qp_state	= hr_qp->state;
+	qp_attr->path_mtu	= IB_MTU_256;
+	qp_attr->path_mig_state	= IB_MIG_ARMED;
+	qp_attr->qkey		= QKEY_VAL;
+	qp_attr->rq_psn		= 0;
+	qp_attr->sq_psn		= 0;
+	qp_attr->dest_qp_num	= 1;
+	qp_attr->qp_access_flags = 6;
+
+	qp_attr->pkey_index = roce_get_field(context.qp1c_bytes_20,
+					     QP1C_BYTES_20_PKEY_IDX_M,
+					     QP1C_BYTES_20_PKEY_IDX_S);
+	qp_attr->port_num = hr_qp->port + 1;
+	qp_attr->sq_draining = 0;
+	qp_attr->max_rd_atomic = 0;
+	qp_attr->max_dest_rd_atomic = 0;
+	qp_attr->min_rnr_timer = 0;
+	qp_attr->timeout = 0;
+	qp_attr->retry_cnt = 0;
+	qp_attr->rnr_retry = 0;
+	qp_attr->alt_timeout = 0;
+
+done:
+	qp_attr->cur_qp_state = qp_attr->qp_state;
+	qp_attr->cap.max_recv_wr = hr_qp->rq.wqe_cnt;
+	qp_attr->cap.max_recv_sge = hr_qp->rq.max_gs;
+	qp_attr->cap.max_send_wr = hr_qp->sq.wqe_cnt;
+	qp_attr->cap.max_send_sge = hr_qp->sq.max_gs;
+	qp_attr->cap.max_inline_data = 0;
+	qp_init_attr->cap = qp_attr->cap;
+	qp_init_attr->create_flags = 0;
+
+	mutex_unlock(&hr_qp->mutex);
+
+	return 0;
+}
+
+static int hns_roce_v1_q_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
+			    int qp_attr_mask,
+			    struct ib_qp_init_attr *qp_init_attr)
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device);
 	struct hns_roce_qp *hr_qp = to_hr_qp(ibqp);
@@ -2725,9 +3382,7 @@ int hns_roce_v1_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
 	qp_attr->pkey_index = roce_get_field(context->qpc_bytes_12,
 			      QP_CONTEXT_QPC_BYTES_12_P_KEY_INDEX_M,
 			      QP_CONTEXT_QPC_BYTES_12_P_KEY_INDEX_S);
-	qp_attr->port_num = (u8)roce_get_field(context->qpc_bytes_156,
-			     QP_CONTEXT_QPC_BYTES_156_PORT_NUM_M,
-			     QP_CONTEXT_QPC_BYTES_156_PORT_NUM_S) + 1;
+	qp_attr->port_num = hr_qp->port + 1;
 	qp_attr->sq_draining = 0;
 	qp_attr->max_rd_atomic = roce_get_field(context->qpc_bytes_156,
 				 QP_CONTEXT_QPC_BYTES_156_INITIATOR_DEPTH_M,
@@ -2767,134 +3422,397 @@ out:
 	return ret;
 }
 
-static void hns_roce_v1_destroy_qp_common(struct hns_roce_dev *hr_dev,
-					  struct hns_roce_qp *hr_qp,
-					  int is_user)
+int hns_roce_v1_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
+			 int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr)
+{
+	struct hns_roce_qp *hr_qp = to_hr_qp(ibqp);
+
+	return hr_qp->doorbell_qpn <= 1 ?
+		hns_roce_v1_q_sqp(ibqp, qp_attr, qp_attr_mask, qp_init_attr) :
+		hns_roce_v1_q_qp(ibqp, qp_attr, qp_attr_mask, qp_init_attr);
+}
+
+static int check_qp_db_process_status(struct hns_roce_dev *hr_dev,
+				      struct hns_roce_qp *hr_qp,
+				      u32 sdb_issue_ptr,
+				      u32 *sdb_inv_cnt,
+				      u32 *wait_stage)
 {
-	u32 sdbinvcnt;
-	unsigned long end = 0;
-	u32 sdbinvcnt_val;
-	u32 sdbsendptr_val;
-	u32 sdbisusepr_val;
-	struct hns_roce_cq *send_cq, *recv_cq;
 	struct device *dev = &hr_dev->pdev->dev;
+	u32 sdb_retry_cnt, old_retry;
+	u32 sdb_send_ptr, old_send;
+	u32 success_flags = 0;
+	u32 cur_cnt, old_cnt;
+	unsigned long end;
+	u32 send_ptr;
+	u32 inv_cnt;
+	u32 tsp_st;
+
+	if (*wait_stage > HNS_ROCE_V1_DB_STAGE2 ||
+	    *wait_stage < HNS_ROCE_V1_DB_STAGE1) {
+		dev_err(dev, "QP(0x%lx) db status wait stage(%d) error!\n",
+			hr_qp->qpn, *wait_stage);
+		return -EINVAL;
+	}
 
-	if (hr_qp->ibqp.qp_type == IB_QPT_RC) {
-		if (hr_qp->state != IB_QPS_RESET) {
-			/*
-			* Set qp to ERR,
-			* waiting for hw complete processing all dbs
-			*/
-			if (hns_roce_v1_qp_modify(hr_dev, NULL,
-					to_hns_roce_state(
-						(enum ib_qp_state)hr_qp->state),
-						HNS_ROCE_QP_STATE_ERR, NULL,
-						hr_qp))
-				dev_err(dev, "modify QP %06lx to ERR failed.\n",
-					hr_qp->qpn);
-
-			/* Record issued doorbell */
-			sdbisusepr_val = roce_read(hr_dev,
-					 ROCEE_SDB_ISSUE_PTR_REG);
-			/*
-			* Query db process status,
-			* until hw process completely
-			*/
-			end = msecs_to_jiffies(
-			      HNS_ROCE_QP_DESTROY_TIMEOUT_MSECS) + jiffies;
-			do {
-				sdbsendptr_val = roce_read(hr_dev,
+	/* Calculate the total timeout for the entire verification process */
+	end = msecs_to_jiffies(HNS_ROCE_V1_CHECK_DB_TIMEOUT_MSECS) + jiffies;
+
+	if (*wait_stage == HNS_ROCE_V1_DB_STAGE1) {
+		/* Query db process status, until hw process completely */
+		sdb_send_ptr = roce_read(hr_dev, ROCEE_SDB_SEND_PTR_REG);
+		while (roce_hw_index_cmp_lt(sdb_send_ptr, sdb_issue_ptr,
+					    ROCEE_SDB_PTR_CMP_BITS)) {
+			if (!time_before(jiffies, end)) {
+				dev_dbg(dev, "QP(0x%lx) db process stage1 timeout. issue 0x%x send 0x%x.\n",
+					hr_qp->qpn, sdb_issue_ptr,
+					sdb_send_ptr);
+				return 0;
+			}
+
+			msleep(HNS_ROCE_V1_CHECK_DB_SLEEP_MSECS);
+			sdb_send_ptr = roce_read(hr_dev,
 						 ROCEE_SDB_SEND_PTR_REG);
-				if (!time_before(jiffies, end)) {
-					dev_err(dev, "destroy qp(0x%lx) timeout!!!",
-						hr_qp->qpn);
-					break;
-				}
-			} while ((short)(roce_get_field(sdbsendptr_val,
-					ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_M,
-					ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_S) -
-				roce_get_field(sdbisusepr_val,
-					ROCEE_SDB_ISSUE_PTR_SDB_ISSUE_PTR_M,
-					ROCEE_SDB_ISSUE_PTR_SDB_ISSUE_PTR_S)
-				) < 0);
+		}
 
-			/* Get list pointer */
-			sdbinvcnt = roce_read(hr_dev, ROCEE_SDB_INV_CNT_REG);
+		if (roce_get_field(sdb_issue_ptr,
+				   ROCEE_SDB_ISSUE_PTR_SDB_ISSUE_PTR_M,
+				   ROCEE_SDB_ISSUE_PTR_SDB_ISSUE_PTR_S) ==
+		    roce_get_field(sdb_send_ptr,
+				   ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_M,
+				   ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_S)) {
+			old_send = roce_read(hr_dev, ROCEE_SDB_SEND_PTR_REG);
+			old_retry = roce_read(hr_dev, ROCEE_SDB_RETRY_CNT_REG);
 
-			/* Query db's list status, until hw reversal */
 			do {
-				sdbinvcnt_val = roce_read(hr_dev,
-						ROCEE_SDB_INV_CNT_REG);
+				tsp_st = roce_read(hr_dev, ROCEE_TSP_BP_ST_REG);
+				if (roce_get_bit(tsp_st,
+					ROCEE_TSP_BP_ST_QH_FIFO_ENTRY_S) == 1) {
+					*wait_stage = HNS_ROCE_V1_DB_WAIT_OK;
+					return 0;
+				}
+
 				if (!time_before(jiffies, end)) {
-					dev_err(dev, "destroy qp(0x%lx) timeout!!!",
-						hr_qp->qpn);
-					dev_err(dev, "SdbInvCnt = 0x%x\n",
-						sdbinvcnt_val);
-					break;
+					dev_dbg(dev, "QP(0x%lx) db process stage1 timeout when send ptr equals issue ptr.\n"
+						     "issue 0x%x send 0x%x.\n",
+						hr_qp->qpn, sdb_issue_ptr,
+						sdb_send_ptr);
+					return 0;
+				}
+
+				msleep(HNS_ROCE_V1_CHECK_DB_SLEEP_MSECS);
+
+				sdb_send_ptr = roce_read(hr_dev,
+							ROCEE_SDB_SEND_PTR_REG);
+				sdb_retry_cnt =	roce_read(hr_dev,
+						       ROCEE_SDB_RETRY_CNT_REG);
+				cur_cnt = roce_get_field(sdb_send_ptr,
+					ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_M,
+					ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_S) +
+					roce_get_field(sdb_retry_cnt,
+					ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_M,
+					ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_S);
+				if (!roce_get_bit(tsp_st,
+					ROCEE_CNT_CLR_CE_CNT_CLR_CE_S)) {
+					old_cnt = roce_get_field(old_send,
+					ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_M,
+					ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_S) +
+					roce_get_field(old_retry,
+					ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_M,
+					ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_S);
+					if (cur_cnt - old_cnt > SDB_ST_CMP_VAL)
+						success_flags = 1;
+				} else {
+					old_cnt = roce_get_field(old_send,
+					ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_M,
+					ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_S);
+					if (cur_cnt - old_cnt > SDB_ST_CMP_VAL)
+						success_flags = 1;
+					else {
+					    send_ptr = roce_get_field(old_send,
+					    ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_M,
+					    ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_S) +
+					    roce_get_field(sdb_retry_cnt,
+					    ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_M,
+					    ROCEE_SDB_RETRY_CNT_SDB_RETRY_CT_S);
+					    roce_set_field(old_send,
+					    ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_M,
+					    ROCEE_SDB_SEND_PTR_SDB_SEND_PTR_S,
+						send_ptr);
+					}
 				}
-			} while ((short)(roce_get_field(sdbinvcnt_val,
-				  ROCEE_SDB_INV_CNT_SDB_INV_CNT_M,
-				  ROCEE_SDB_INV_CNT_SDB_INV_CNT_S) -
-				  (sdbinvcnt + SDB_INV_CNT_OFFSET)) < 0);
-
-			/* Modify qp to reset before destroying qp */
-			if (hns_roce_v1_qp_modify(hr_dev, NULL,
-					to_hns_roce_state(
-					(enum ib_qp_state)hr_qp->state),
-					HNS_ROCE_QP_STATE_RST, NULL, hr_qp))
-				dev_err(dev, "modify QP %06lx to RESET failed.\n",
-					hr_qp->qpn);
+			} while (!success_flags);
 		}
+
+		*wait_stage = HNS_ROCE_V1_DB_STAGE2;
+
+		/* Get list pointer */
+		*sdb_inv_cnt = roce_read(hr_dev, ROCEE_SDB_INV_CNT_REG);
+		dev_dbg(dev, "QP(0x%lx) db process stage2. inv cnt = 0x%x.\n",
+			hr_qp->qpn, *sdb_inv_cnt);
+	}
+
+	if (*wait_stage == HNS_ROCE_V1_DB_STAGE2) {
+		/* Query db's list status, until hw reversal */
+		inv_cnt = roce_read(hr_dev, ROCEE_SDB_INV_CNT_REG);
+		while (roce_hw_index_cmp_lt(inv_cnt,
+					    *sdb_inv_cnt + SDB_INV_CNT_OFFSET,
+					    ROCEE_SDB_CNT_CMP_BITS)) {
+			if (!time_before(jiffies, end)) {
+				dev_dbg(dev, "QP(0x%lx) db process stage2 timeout. inv cnt 0x%x.\n",
+					hr_qp->qpn, inv_cnt);
+				return 0;
+			}
+
+			msleep(HNS_ROCE_V1_CHECK_DB_SLEEP_MSECS);
+			inv_cnt = roce_read(hr_dev, ROCEE_SDB_INV_CNT_REG);
+		}
+
+		*wait_stage = HNS_ROCE_V1_DB_WAIT_OK;
+	}
+
+	return 0;
+}
+
+static int check_qp_reset_state(struct hns_roce_dev *hr_dev,
+				struct hns_roce_qp *hr_qp,
+				struct hns_roce_qp_work *qp_work_entry,
+				int *is_timeout)
+{
+	struct device *dev = &hr_dev->pdev->dev;
+	u32 sdb_issue_ptr;
+	int ret;
+
+	if (hr_qp->state != IB_QPS_RESET) {
+		/* Set qp to ERR, waiting for hw complete processing all dbs */
+		ret = hns_roce_v1_modify_qp(&hr_qp->ibqp, NULL, 0, hr_qp->state,
+					    IB_QPS_ERR);
+		if (ret) {
+			dev_err(dev, "Modify QP(0x%lx) to ERR failed!\n",
+				hr_qp->qpn);
+			return ret;
+		}
+
+		/* Record issued doorbell */
+		sdb_issue_ptr = roce_read(hr_dev, ROCEE_SDB_ISSUE_PTR_REG);
+		qp_work_entry->sdb_issue_ptr = sdb_issue_ptr;
+		qp_work_entry->db_wait_stage = HNS_ROCE_V1_DB_STAGE1;
+
+		/* Query db process status, until hw process completely */
+		ret = check_qp_db_process_status(hr_dev, hr_qp, sdb_issue_ptr,
+						 &qp_work_entry->sdb_inv_cnt,
+						 &qp_work_entry->db_wait_stage);
+		if (ret) {
+			dev_err(dev, "Check QP(0x%lx) db process status failed!\n",
+				hr_qp->qpn);
+			return ret;
+		}
+
+		if (qp_work_entry->db_wait_stage != HNS_ROCE_V1_DB_WAIT_OK) {
+			qp_work_entry->sche_cnt = 0;
+			*is_timeout = 1;
+			return 0;
+		}
+
+		/* Modify qp to reset before destroying qp */
+		ret = hns_roce_v1_modify_qp(&hr_qp->ibqp, NULL, 0, hr_qp->state,
+					    IB_QPS_RESET);
+		if (ret) {
+			dev_err(dev, "Modify QP(0x%lx) to RST failed!\n",
+				hr_qp->qpn);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static void hns_roce_v1_destroy_qp_work_fn(struct work_struct *work)
+{
+	struct hns_roce_qp_work *qp_work_entry;
+	struct hns_roce_v1_priv *priv;
+	struct hns_roce_dev *hr_dev;
+	struct hns_roce_qp *hr_qp;
+	struct device *dev;
+	int ret;
+
+	qp_work_entry = container_of(work, struct hns_roce_qp_work, work);
+	hr_dev = to_hr_dev(qp_work_entry->ib_dev);
+	dev = &hr_dev->pdev->dev;
+	priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv;
+	hr_qp = qp_work_entry->qp;
+
+	dev_dbg(dev, "Schedule destroy QP(0x%lx) work.\n", hr_qp->qpn);
+
+	qp_work_entry->sche_cnt++;
+
+	/* Query db process status, until hw process completely */
+	ret = check_qp_db_process_status(hr_dev, hr_qp,
+					 qp_work_entry->sdb_issue_ptr,
+					 &qp_work_entry->sdb_inv_cnt,
+					 &qp_work_entry->db_wait_stage);
+	if (ret) {
+		dev_err(dev, "Check QP(0x%lx) db process status failed!\n",
+			hr_qp->qpn);
+		return;
+	}
+
+	if (qp_work_entry->db_wait_stage != HNS_ROCE_V1_DB_WAIT_OK &&
+	    priv->des_qp.requeue_flag) {
+		queue_work(priv->des_qp.qp_wq, work);
+		return;
+	}
+
+	/* Modify qp to reset before destroying qp */
+	ret = hns_roce_v1_modify_qp(&hr_qp->ibqp, NULL, 0, hr_qp->state,
+				    IB_QPS_RESET);
+	if (ret) {
+		dev_err(dev, "Modify QP(0x%lx) to RST failed!\n", hr_qp->qpn);
+		return;
+	}
+
+	hns_roce_qp_remove(hr_dev, hr_qp);
+	hns_roce_qp_free(hr_dev, hr_qp);
+
+	if (hr_qp->ibqp.qp_type == IB_QPT_RC) {
+		/* RC QP, release QPN */
+		hns_roce_release_range_qp(hr_dev, hr_qp->qpn, 1);
+		kfree(hr_qp);
+	} else
+		kfree(hr_to_hr_sqp(hr_qp));
+
+	kfree(qp_work_entry);
+
+	dev_dbg(dev, "Accomplished destroy QP(0x%lx) work.\n", hr_qp->qpn);
+}
+
+int hns_roce_v1_destroy_qp(struct ib_qp *ibqp)
+{
+	struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device);
+	struct hns_roce_qp *hr_qp = to_hr_qp(ibqp);
+	struct device *dev = &hr_dev->pdev->dev;
+	struct hns_roce_qp_work qp_work_entry;
+	struct hns_roce_qp_work *qp_work;
+	struct hns_roce_v1_priv *priv;
+	struct hns_roce_cq *send_cq, *recv_cq;
+	int is_user = !!ibqp->pd->uobject;
+	int is_timeout = 0;
+	int ret;
+
+	ret = check_qp_reset_state(hr_dev, hr_qp, &qp_work_entry, &is_timeout);
+	if (ret) {
+		dev_err(dev, "QP reset state check failed(%d)!\n", ret);
+		return ret;
 	}
 
 	send_cq = to_hr_cq(hr_qp->ibqp.send_cq);
 	recv_cq = to_hr_cq(hr_qp->ibqp.recv_cq);
 
 	hns_roce_lock_cqs(send_cq, recv_cq);
-
 	if (!is_user) {
 		__hns_roce_v1_cq_clean(recv_cq, hr_qp->qpn, hr_qp->ibqp.srq ?
 				       to_hr_srq(hr_qp->ibqp.srq) : NULL);
 		if (send_cq != recv_cq)
 			__hns_roce_v1_cq_clean(send_cq, hr_qp->qpn, NULL);
 	}
-
-	hns_roce_qp_remove(hr_dev, hr_qp);
-
 	hns_roce_unlock_cqs(send_cq, recv_cq);
 
-	hns_roce_qp_free(hr_dev, hr_qp);
+	if (!is_timeout) {
+		hns_roce_qp_remove(hr_dev, hr_qp);
+		hns_roce_qp_free(hr_dev, hr_qp);
 
-	/* Not special_QP, free their QPN */
-	if ((hr_qp->ibqp.qp_type == IB_QPT_RC) ||
-	    (hr_qp->ibqp.qp_type == IB_QPT_UC) ||
-	    (hr_qp->ibqp.qp_type == IB_QPT_UD))
-		hns_roce_release_range_qp(hr_dev, hr_qp->qpn, 1);
+		/* RC QP, release QPN */
+		if (hr_qp->ibqp.qp_type == IB_QPT_RC)
+			hns_roce_release_range_qp(hr_dev, hr_qp->qpn, 1);
+	}
 
 	hns_roce_mtt_cleanup(hr_dev, &hr_qp->mtt);
 
-	if (is_user) {
+	if (is_user)
 		ib_umem_release(hr_qp->umem);
-	} else {
+	else {
 		kfree(hr_qp->sq.wrid);
 		kfree(hr_qp->rq.wrid);
+
 		hns_roce_buf_free(hr_dev, hr_qp->buff_size, &hr_qp->hr_buf);
 	}
+
+	if (!is_timeout) {
+		if (hr_qp->ibqp.qp_type == IB_QPT_RC)
+			kfree(hr_qp);
+		else
+			kfree(hr_to_hr_sqp(hr_qp));
+	} else {
+		qp_work = kzalloc(sizeof(*qp_work), GFP_KERNEL);
+		if (!qp_work)
+			return -ENOMEM;
+
+		INIT_WORK(&qp_work->work, hns_roce_v1_destroy_qp_work_fn);
+		qp_work->ib_dev	= &hr_dev->ib_dev;
+		qp_work->qp		= hr_qp;
+		qp_work->db_wait_stage	= qp_work_entry.db_wait_stage;
+		qp_work->sdb_issue_ptr	= qp_work_entry.sdb_issue_ptr;
+		qp_work->sdb_inv_cnt	= qp_work_entry.sdb_inv_cnt;
+		qp_work->sche_cnt	= qp_work_entry.sche_cnt;
+
+		priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv;
+		queue_work(priv->des_qp.qp_wq, &qp_work->work);
+		dev_dbg(dev, "Begin destroy QP(0x%lx) work.\n", hr_qp->qpn);
+	}
+
+	return 0;
 }
 
-int hns_roce_v1_destroy_qp(struct ib_qp *ibqp)
+int hns_roce_v1_destroy_cq(struct ib_cq *ibcq)
 {
-	struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device);
-	struct hns_roce_qp *hr_qp = to_hr_qp(ibqp);
+	struct hns_roce_dev *hr_dev = to_hr_dev(ibcq->device);
+	struct hns_roce_cq *hr_cq = to_hr_cq(ibcq);
+	struct device *dev = &hr_dev->pdev->dev;
+	u32 cqe_cnt_ori;
+	u32 cqe_cnt_cur;
+	u32 cq_buf_size;
+	int wait_time = 0;
+	int ret = 0;
 
-	hns_roce_v1_destroy_qp_common(hr_dev, hr_qp, !!ibqp->pd->uobject);
+	hns_roce_free_cq(hr_dev, hr_cq);
 
-	if (hr_qp->ibqp.qp_type == IB_QPT_GSI)
-		kfree(hr_to_hr_sqp(hr_qp));
-	else
-		kfree(hr_qp);
+	/*
+	 * Before freeing cq buffer, we need to ensure that the outstanding CQE
+	 * have been written by checking the CQE counter.
+	 */
+	cqe_cnt_ori = roce_read(hr_dev, ROCEE_SCAEP_WR_CQE_CNT);
+	while (1) {
+		if (roce_read(hr_dev, ROCEE_CAEP_CQE_WCMD_EMPTY) &
+		    HNS_ROCE_CQE_WCMD_EMPTY_BIT)
+			break;
 
-	return 0;
+		cqe_cnt_cur = roce_read(hr_dev, ROCEE_SCAEP_WR_CQE_CNT);
+		if ((cqe_cnt_cur - cqe_cnt_ori) >= HNS_ROCE_MIN_CQE_CNT)
+			break;
+
+		msleep(HNS_ROCE_EACH_FREE_CQ_WAIT_MSECS);
+		if (wait_time > HNS_ROCE_MAX_FREE_CQ_WAIT_CNT) {
+			dev_warn(dev, "Destroy cq 0x%lx timeout!\n",
+				hr_cq->cqn);
+			ret = -ETIMEDOUT;
+			break;
+		}
+		wait_time++;
+	}
+
+	hns_roce_mtt_cleanup(hr_dev, &hr_cq->hr_buf.hr_mtt);
+
+	if (ibcq->uobject)
+		ib_umem_release(hr_cq->umem);
+	else {
+		/* Free the buff of stored cq */
+		cq_buf_size = (ibcq->cqe + 1) * hr_dev->caps.cq_entry_sz;
+		hns_roce_buf_free(hr_dev, cq_buf_size, &hr_cq->hr_buf.hr_buf);
+	}
+
+	kfree(hr_cq);
+
+	return ret;
 }
 
 struct hns_roce_v1_priv hr_v1_priv;
@@ -2917,5 +3835,7 @@ struct hns_roce_hw hns_roce_hw_v1 = {
 	.post_recv = hns_roce_v1_post_recv,
 	.req_notify_cq = hns_roce_v1_req_notify_cq,
 	.poll_cq = hns_roce_v1_poll_cq,
+	.dereg_mr = hns_roce_v1_dereg_mr,
+	.destroy_cq = hns_roce_v1_destroy_cq,
 	.priv = &hr_v1_priv,
 };

drivers/infiniband/hw/hns/hns_roce_hw_v1.h

@@ -58,6 +58,7 @@
 #define HNS_ROCE_V1_PHY_UAR_NUM				8
 
 #define HNS_ROCE_V1_GID_NUM				16
+#define HNS_ROCE_V1_RESV_QP				8
 
 #define HNS_ROCE_V1_NUM_COMP_EQE			0x8000
 #define HNS_ROCE_V1_NUM_ASYNC_EQE			0x400
@@ -102,8 +103,22 @@
 #define HNS_ROCE_V1_EXT_ODB_ALFUL	\
 	(HNS_ROCE_V1_EXT_ODB_DEPTH - HNS_ROCE_V1_DB_RSVD)
 
+#define HNS_ROCE_V1_DB_WAIT_OK				0
+#define HNS_ROCE_V1_DB_STAGE1				1
+#define HNS_ROCE_V1_DB_STAGE2				2
+#define HNS_ROCE_V1_CHECK_DB_TIMEOUT_MSECS		10000
+#define HNS_ROCE_V1_CHECK_DB_SLEEP_MSECS		20
+#define HNS_ROCE_V1_FREE_MR_TIMEOUT_MSECS		50000
+#define HNS_ROCE_V1_RECREATE_LP_QP_TIMEOUT_MSECS	10000
+#define HNS_ROCE_V1_FREE_MR_WAIT_VALUE			5
+#define HNS_ROCE_V1_RECREATE_LP_QP_WAIT_VALUE		20
+
 #define HNS_ROCE_BT_RSV_BUF_SIZE			(1 << 17)
 
+#define HNS_ROCE_V1_TPTR_ENTRY_SIZE			2
+#define HNS_ROCE_V1_TPTR_BUF_SIZE	\
+	(HNS_ROCE_V1_TPTR_ENTRY_SIZE * HNS_ROCE_V1_MAX_CQ_NUM)
+
 #define HNS_ROCE_ODB_POLL_MODE				0
 
 #define HNS_ROCE_SDB_NORMAL_MODE			0
@@ -140,6 +155,7 @@
 #define SQ_PSN_SHIFT					8
 #define QKEY_VAL					0x80010000
 #define SDB_INV_CNT_OFFSET				8
+#define SDB_ST_CMP_VAL					8
 
 struct hns_roce_cq_context {
 	u32 cqc_byte_4;
@@ -436,6 +452,8 @@ struct hns_roce_ud_send_wqe {
 #define UD_SEND_WQE_U32_8_DMAC_5_M   \
 	(((1UL << 8) - 1) << UD_SEND_WQE_U32_8_DMAC_5_S)
 
+#define UD_SEND_WQE_U32_8_LOOPBACK_INDICATOR_S 22
+
 #define UD_SEND_WQE_U32_8_OPERATION_TYPE_S 16
 #define UD_SEND_WQE_U32_8_OPERATION_TYPE_M   \
 	(((1UL << 4) - 1) << UD_SEND_WQE_U32_8_OPERATION_TYPE_S)
@@ -480,13 +498,17 @@ struct hns_roce_sqp_context {
 	u32 qp1c_bytes_12;
 	u32 qp1c_bytes_16;
 	u32 qp1c_bytes_20;
-	u32 qp1c_bytes_28;
 	u32 cur_rq_wqe_ba_l;
+	u32 qp1c_bytes_28;
 	u32 qp1c_bytes_32;
 	u32 cur_sq_wqe_ba_l;
 	u32 qp1c_bytes_40;
 };
 
+#define QP1C_BYTES_4_QP_STATE_S 0
+#define QP1C_BYTES_4_QP_STATE_M   \
+	(((1UL << 3) - 1) << QP1C_BYTES_4_QP_STATE_S)
+
 #define QP1C_BYTES_4_SQ_WQE_SHIFT_S 8
 #define QP1C_BYTES_4_SQ_WQE_SHIFT_M   \
 	(((1UL << 4) - 1) << QP1C_BYTES_4_SQ_WQE_SHIFT_S)
@@ -952,6 +974,10 @@ struct hns_roce_sq_db {
 #define SQ_DOORBELL_U32_4_SQ_HEAD_M   \
 	(((1UL << 15) - 1) << SQ_DOORBELL_U32_4_SQ_HEAD_S)
 
+#define SQ_DOORBELL_U32_4_SL_S 16
+#define SQ_DOORBELL_U32_4_SL_M   \
+	(((1UL << 2) - 1) << SQ_DOORBELL_U32_4_SL_S)
+
 #define SQ_DOORBELL_U32_4_PORT_S 18
 #define SQ_DOORBELL_U32_4_PORT_M  (((1UL << 3) - 1) << SQ_DOORBELL_U32_4_PORT_S)
 
@@ -979,12 +1005,58 @@ struct hns_roce_bt_table {
 	struct hns_roce_buf_list cqc_buf;
 };
 
+struct hns_roce_tptr_table {
+	struct hns_roce_buf_list tptr_buf;
+};
+
+struct hns_roce_qp_work {
+	struct	work_struct work;
+	struct	ib_device *ib_dev;
+	struct	hns_roce_qp *qp;
+	u32	db_wait_stage;
+	u32	sdb_issue_ptr;
+	u32	sdb_inv_cnt;
+	u32	sche_cnt;
+};
+
+struct hns_roce_des_qp {
+	struct workqueue_struct	*qp_wq;
+	int	requeue_flag;
+};
+
+struct hns_roce_mr_free_work {
+	struct	work_struct work;
+	struct	ib_device *ib_dev;
+	struct	completion *comp;
+	int	comp_flag;
+	void	*mr;
+};
+
+struct hns_roce_recreate_lp_qp_work {
+	struct	work_struct work;
+	struct	ib_device *ib_dev;
+	struct	completion *comp;
+	int	comp_flag;
+};
+
+struct hns_roce_free_mr {
+	struct workqueue_struct *free_mr_wq;
+	struct hns_roce_qp *mr_free_qp[HNS_ROCE_V1_RESV_QP];
+	struct hns_roce_cq *mr_free_cq;
+	struct hns_roce_pd *mr_free_pd;
+};
+
 struct hns_roce_v1_priv {
 	struct hns_roce_db_table  db_table;
 	struct hns_roce_raq_table raq_table;
 	struct hns_roce_bt_table  bt_table;
+	struct hns_roce_tptr_table tptr_table;
+	struct hns_roce_des_qp des_qp;
+	struct hns_roce_free_mr free_mr;
 };
 
 int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset);
+int hns_roce_v1_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc);
+int hns_roce_v1_destroy_qp(struct ib_qp *ibqp);
 
 #endif

drivers/infiniband/hw/hns/hns_roce_main.c

@@ -35,51 +35,12 @@
 #include <rdma/ib_addr.h>
 #include <rdma/ib_smi.h>
 #include <rdma/ib_user_verbs.h>
+#include <rdma/ib_cache.h>
 #include "hns_roce_common.h"
 #include "hns_roce_device.h"
-#include "hns_roce_user.h"
+#include <rdma/hns-abi.h>
 #include "hns_roce_hem.h"
 
-/**
- * hns_roce_addrconf_ifid_eui48 - Get default gid.
- * @eui: eui.
- * @vlan_id:  gid
- * @dev:  net device
- * Description:
- *    MAC convert to GID
- *        gid[0..7] = fe80 0000 0000 0000
- *        gid[8] = mac[0] ^ 2
- *        gid[9] = mac[1]
- *        gid[10] = mac[2]
- *        gid[11] = ff        (VLAN ID high byte (4 MS bits))
- *        gid[12] = fe        (VLAN ID low byte)
- *        gid[13] = mac[3]
- *        gid[14] = mac[4]
- *        gid[15] = mac[5]
- */
-static void hns_roce_addrconf_ifid_eui48(u8 *eui, u16 vlan_id,
-					 struct net_device *dev)
-{
-	memcpy(eui, dev->dev_addr, 3);
-	memcpy(eui + 5, dev->dev_addr + 3, 3);
-	if (vlan_id < 0x1000) {
-		eui[3] = vlan_id >> 8;
-		eui[4] = vlan_id & 0xff;
-	} else {
-		eui[3] = 0xff;
-		eui[4] = 0xfe;
-	}
-	eui[0] ^= 2;
-}
-
-static void hns_roce_make_default_gid(struct net_device *dev, union ib_gid *gid)
-{
-	memset(gid, 0, sizeof(*gid));
-	gid->raw[0] = 0xFE;
-	gid->raw[1] = 0x80;
-	hns_roce_addrconf_ifid_eui48(&gid->raw[8], 0xffff, dev);
-}
-
 /**
  * hns_get_gid_index - Get gid index.
  * @hr_dev: pointer to structure hns_roce_dev.
@@ -96,30 +57,6 @@ int hns_get_gid_index(struct hns_roce_dev *hr_dev, u8 port, int gid_index)
 	return gid_index * hr_dev->caps.num_ports + port;
 }
 
-static int hns_roce_set_gid(struct hns_roce_dev *hr_dev, u8 port, int gid_index,
-		     union ib_gid *gid)
-{
-	struct device *dev = &hr_dev->pdev->dev;
-	u8 gid_idx = 0;
-
-	if (gid_index >= hr_dev->caps.gid_table_len[port]) {
-		dev_err(dev, "gid_index %d illegal, port %d gid range: 0~%d\n",
-			gid_index, port, hr_dev->caps.gid_table_len[port] - 1);
-		return -EINVAL;
-	}
-
-	gid_idx = hns_get_gid_index(hr_dev, port, gid_index);
-
-	if (!memcmp(gid, &hr_dev->iboe.gid_table[gid_idx], sizeof(*gid)))
-		return -EINVAL;
-
-	memcpy(&hr_dev->iboe.gid_table[gid_idx], gid, sizeof(*gid));
-
-	hr_dev->hw->set_gid(hr_dev, port, gid_index, gid);
-
-	return 0;
-}
-
 static void hns_roce_set_mac(struct hns_roce_dev *hr_dev, u8 port, u8 *addr)
 {
 	u8 phy_port;
@@ -135,27 +72,44 @@ static void hns_roce_set_mac(struct hns_roce_dev *hr_dev, u8 port, u8 *addr)
 	hr_dev->hw->set_mac(hr_dev, phy_port, addr);
 }
 
-static void hns_roce_set_mtu(struct hns_roce_dev *hr_dev, u8 port, int mtu)
+static int hns_roce_add_gid(struct ib_device *device, u8 port_num,
+			    unsigned int index, const union ib_gid *gid,
+			    const struct ib_gid_attr *attr, void **context)
 {
-	u8 phy_port = hr_dev->iboe.phy_port[port];
-	enum ib_mtu tmp;
+	struct hns_roce_dev *hr_dev = to_hr_dev(device);
+	u8 port = port_num - 1;
+	unsigned long flags;
+
+	if (port >= hr_dev->caps.num_ports)
+		return -EINVAL;
+
+	spin_lock_irqsave(&hr_dev->iboe.lock, flags);
 
-	tmp = iboe_get_mtu(mtu);
-	if (!tmp)
-		tmp = IB_MTU_256;
+	hr_dev->hw->set_gid(hr_dev, port, index, (union ib_gid *)gid);
 
-	hr_dev->hw->set_mtu(hr_dev, phy_port, tmp);
+	spin_unlock_irqrestore(&hr_dev->iboe.lock, flags);
+
+	return 0;
 }
 
-static void hns_roce_update_gids(struct hns_roce_dev *hr_dev, int port)
+static int hns_roce_del_gid(struct ib_device *device, u8 port_num,
+			    unsigned int index, void **context)
 {
-	struct ib_event event;
+	struct hns_roce_dev *hr_dev = to_hr_dev(device);
+	union ib_gid zgid = { {0} };
+	u8 port = port_num - 1;
+	unsigned long flags;
+
+	if (port >= hr_dev->caps.num_ports)
+		return -EINVAL;
+
+	spin_lock_irqsave(&hr_dev->iboe.lock, flags);
 
-	/* Refresh gid in ib_cache */
-	event.device = &hr_dev->ib_dev;
-	event.element.port_num = port + 1;
-	event.event = IB_EVENT_GID_CHANGE;
-	ib_dispatch_event(&event);
+	hr_dev->hw->set_gid(hr_dev, port, index, &zgid);
+
+	spin_unlock_irqrestore(&hr_dev->iboe.lock, flags);
+
+	return 0;
 }
 
 static int handle_en_event(struct hns_roce_dev *hr_dev, u8 port,
@@ -163,9 +117,6 @@ static int handle_en_event(struct hns_roce_dev *hr_dev, u8 port,
 {
 	struct device *dev = &hr_dev->pdev->dev;
 	struct net_device *netdev;
-	unsigned long flags;
-	union ib_gid gid;
-	int ret = 0;
 
 	netdev = hr_dev->iboe.netdevs[port];
 	if (!netdev) {
@@ -173,7 +124,7 @@ static int handle_en_event(struct hns_roce_dev *hr_dev, u8 port,
 		return -ENODEV;
 	}
 
-	spin_lock_irqsave(&hr_dev->iboe.lock, flags);
+	spin_lock_bh(&hr_dev->iboe.lock);
 
 	switch (event) {
 	case NETDEV_UP:
@@ -181,23 +132,19 @@ static int handle_en_event(struct hns_roce_dev *hr_dev, u8 port,
 	case NETDEV_REGISTER:
 	case NETDEV_CHANGEADDR:
 		hns_roce_set_mac(hr_dev, port, netdev->dev_addr);
-		hns_roce_make_default_gid(netdev, &gid);
-		ret = hns_roce_set_gid(hr_dev, port, 0, &gid);
-		if (!ret)
-			hns_roce_update_gids(hr_dev, port);
 		break;
 	case NETDEV_DOWN:
 		/*
-		* In v1 engine, only support all ports closed together.
-		*/
+		 * In v1 engine, only support all ports closed together.
+		 */
 		break;
 	default:
 		dev_dbg(dev, "NETDEV event = 0x%x!\n", (u32)(event));
 		break;
 	}
 
-	spin_unlock_irqrestore(&hr_dev->iboe.lock, flags);
-	return ret;
+	spin_unlock_bh(&hr_dev->iboe.lock);
+	return 0;
 }
 
 static int hns_roce_netdev_event(struct notifier_block *self,
@@ -224,118 +171,17 @@ static int hns_roce_netdev_event(struct notifier_block *self,
 	return NOTIFY_DONE;
 }
 
-static void hns_roce_addr_event(int event, struct net_device *event_netdev,
-				struct hns_roce_dev *hr_dev, union ib_gid *gid)
+static int hns_roce_setup_mtu_mac(struct hns_roce_dev *hr_dev)
 {
-	struct hns_roce_ib_iboe *iboe = NULL;
-	int gid_table_len = 0;
-	unsigned long flags;
-	union ib_gid zgid;
-	u8 gid_idx = 0;
-	u8 port = 0;
-	int i = 0;
-	int free;
-	struct net_device *real_dev = rdma_vlan_dev_real_dev(event_netdev) ?
-				      rdma_vlan_dev_real_dev(event_netdev) :
-				      event_netdev;
-
-	if (event != NETDEV_UP && event != NETDEV_DOWN)
-		return;
-
-	iboe = &hr_dev->iboe;
-	while (port < hr_dev->caps.num_ports) {
-		if (real_dev == iboe->netdevs[port])
-			break;
-		port++;
-	}
-
-	if (port >= hr_dev->caps.num_ports) {
-		dev_dbg(&hr_dev->pdev->dev, "can't find netdev\n");
-		return;
-	}
-
-	memset(zgid.raw, 0, sizeof(zgid.raw));
-	free = -1;
-	gid_table_len = hr_dev->caps.gid_table_len[port];
-
-	spin_lock_irqsave(&hr_dev->iboe.lock, flags);
-
-	for (i = 0; i < gid_table_len; i++) {
-		gid_idx = hns_get_gid_index(hr_dev, port, i);
-		if (!memcmp(gid->raw, iboe->gid_table[gid_idx].raw,
-			    sizeof(gid->raw)))
-			break;
-		if (free < 0 && !memcmp(zgid.raw,
-			iboe->gid_table[gid_idx].raw, sizeof(zgid.raw)))
-			free = i;
-	}
-
-	if (i >= gid_table_len) {
-		if (free < 0) {
-			spin_unlock_irqrestore(&hr_dev->iboe.lock, flags);
-			dev_dbg(&hr_dev->pdev->dev,
-				"gid_index overflow, port(%d)\n", port);
-			return;
-		}
-		if (!hns_roce_set_gid(hr_dev, port, free, gid))
-			hns_roce_update_gids(hr_dev, port);
-	} else if (event == NETDEV_DOWN) {
-		if (!hns_roce_set_gid(hr_dev, port, i, &zgid))
-			hns_roce_update_gids(hr_dev, port);
-	}
-
-	spin_unlock_irqrestore(&hr_dev->iboe.lock, flags);
-}
-
-static int hns_roce_inet_event(struct notifier_block *self, unsigned long event,
-			       void *ptr)
-{
-	struct in_ifaddr *ifa = ptr;
-	struct hns_roce_dev *hr_dev;
-	struct net_device *dev = ifa->ifa_dev->dev;
-	union ib_gid gid;
-
-	ipv6_addr_set_v4mapped(ifa->ifa_address, (struct in6_addr *)&gid);
-
-	hr_dev = container_of(self, struct hns_roce_dev, iboe.nb_inet);
-
-	hns_roce_addr_event(event, dev, hr_dev, &gid);
-
-	return NOTIFY_DONE;
-}
-
-static int hns_roce_setup_mtu_gids(struct hns_roce_dev *hr_dev)
-{
-	struct in_ifaddr *ifa_list = NULL;
-	union ib_gid gid = {{0} };
-	u32 ipaddr = 0;
-	int index = 0;
-	int ret = 0;
-	u8 i = 0;
+	u8 i;
 
 	for (i = 0; i < hr_dev->caps.num_ports; i++) {
-		hns_roce_set_mtu(hr_dev, i,
-				 ib_mtu_enum_to_int(hr_dev->caps.max_mtu));
+		hr_dev->hw->set_mtu(hr_dev, hr_dev->iboe.phy_port[i],
+				    hr_dev->caps.max_mtu);
 		hns_roce_set_mac(hr_dev, i, hr_dev->iboe.netdevs[i]->dev_addr);
-
-		if (hr_dev->iboe.netdevs[i]->ip_ptr) {
-			ifa_list = hr_dev->iboe.netdevs[i]->ip_ptr->ifa_list;
-			index = 1;
-			while (ifa_list) {
-				ipaddr = ifa_list->ifa_address;
-				ipv6_addr_set_v4mapped(ipaddr,
-						       (struct in6_addr *)&gid);
-				ret = hns_roce_set_gid(hr_dev, i, index, &gid);
-				if (ret)
-					break;
-				index++;
-				ifa_list = ifa_list->ifa_next;
-			}
-			hns_roce_update_gids(hr_dev, i);
-		}
 	}
 
-	return ret;
+	return 0;
 }
 
 static int hns_roce_query_device(struct ib_device *ib_dev,
@@ -444,31 +290,6 @@ static enum rdma_link_layer hns_roce_get_link_layer(struct ib_device *device,
 static int hns_roce_query_gid(struct ib_device *ib_dev, u8 port_num, int index,
 			      union ib_gid *gid)
 {
-	struct hns_roce_dev *hr_dev = to_hr_dev(ib_dev);
-	struct device *dev = &hr_dev->pdev->dev;
-	u8 gid_idx = 0;
-	u8 port;
-
-	if (port_num < 1 || port_num > hr_dev->caps.num_ports ||
-	    index >= hr_dev->caps.gid_table_len[port_num - 1]) {
-		dev_err(dev,
-			"port_num %d index %d illegal! correct range: port_num 1~%d index 0~%d!\n",
-			port_num, index, hr_dev->caps.num_ports,
-			hr_dev->caps.gid_table_len[port_num - 1] - 1);
-		return -EINVAL;
-	}
-
-	port = port_num - 1;
-	gid_idx = hns_get_gid_index(hr_dev, port, index);
-	if (gid_idx >= HNS_ROCE_MAX_GID_NUM) {
-		dev_err(dev, "port_num %d index %d illegal! total gid num %d!\n",
-			port_num, index, HNS_ROCE_MAX_GID_NUM);
-		return -EINVAL;
-	}
-
-	memcpy(gid->raw, hr_dev->iboe.gid_table[gid_idx].raw,
-	       HNS_ROCE_GID_SIZE);
-
 	return 0;
 }
 
@@ -549,6 +370,8 @@ static int hns_roce_dealloc_ucontext(struct ib_ucontext *ibcontext)
 static int hns_roce_mmap(struct ib_ucontext *context,
 			 struct vm_area_struct *vma)
 {
+	struct hns_roce_dev *hr_dev = to_hr_dev(context->device);
+
 	if (((vma->vm_end - vma->vm_start) % PAGE_SIZE) != 0)
 		return -EINVAL;
 
@@ -558,10 +381,15 @@ static int hns_roce_mmap(struct ib_ucontext *context,
 				       to_hr_ucontext(context)->uar.pfn,
 				       PAGE_SIZE, vma->vm_page_prot))
 			return -EAGAIN;
-
-	} else {
+	} else if (vma->vm_pgoff == 1 && hr_dev->hw_rev == HNS_ROCE_HW_VER1) {
+		/* vm_pgoff: 1 -- TPTR */
+		if (io_remap_pfn_range(vma, vma->vm_start,
+				       hr_dev->tptr_dma_addr >> PAGE_SHIFT,
+				       hr_dev->tptr_size,
+				       vma->vm_page_prot))
+			return -EAGAIN;
+	} else
 		return -EINVAL;
-	}
 
 	return 0;
 }
@@ -605,7 +433,7 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev)
 	spin_lock_init(&iboe->lock);
 
 	ib_dev = &hr_dev->ib_dev;
-	strlcpy(ib_dev->name, "hisi_%d", IB_DEVICE_NAME_MAX);
+	strlcpy(ib_dev->name, "hns_%d", IB_DEVICE_NAME_MAX);
 
 	ib_dev->owner			= THIS_MODULE;
 	ib_dev->node_type		= RDMA_NODE_IB_CA;
@@ -639,6 +467,8 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev)
 	ib_dev->get_link_layer		= hns_roce_get_link_layer;
 	ib_dev->get_netdev		= hns_roce_get_netdev;
 	ib_dev->query_gid		= hns_roce_query_gid;
+	ib_dev->add_gid			= hns_roce_add_gid;
+	ib_dev->del_gid			= hns_roce_del_gid;
 	ib_dev->query_pkey		= hns_roce_query_pkey;
 	ib_dev->alloc_ucontext		= hns_roce_alloc_ucontext;
 	ib_dev->dealloc_ucontext	= hns_roce_dealloc_ucontext;
@@ -681,32 +511,22 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev)
 		return ret;
 	}
 
-	ret = hns_roce_setup_mtu_gids(hr_dev);
+	ret = hns_roce_setup_mtu_mac(hr_dev);
 	if (ret) {
-		dev_err(dev, "roce_setup_mtu_gids failed!\n");
-		goto error_failed_setup_mtu_gids;
+		dev_err(dev, "setup_mtu_mac failed!\n");
+		goto error_failed_setup_mtu_mac;
 	}
 
 	iboe->nb.notifier_call = hns_roce_netdev_event;
 	ret = register_netdevice_notifier(&iboe->nb);
 	if (ret) {
 		dev_err(dev, "register_netdevice_notifier failed!\n");
-		goto error_failed_setup_mtu_gids;
-	}
-
-	iboe->nb_inet.notifier_call = hns_roce_inet_event;
-	ret = register_inetaddr_notifier(&iboe->nb_inet);
-	if (ret) {
-		dev_err(dev, "register inet addr notifier failed!\n");
-		goto error_failed_register_inetaddr_notifier;
+		goto error_failed_setup_mtu_mac;
 	}
 
 	return 0;
 
-error_failed_register_inetaddr_notifier:
-	unregister_netdevice_notifier(&iboe->nb);
-
-error_failed_setup_mtu_gids:
+error_failed_setup_mtu_mac:
 	ib_unregister_device(ib_dev);
 
 	return ret;
@@ -940,10 +760,10 @@ err_unmap_mtt:
 }
 
 /**
-* hns_roce_setup_hca - setup host channel adapter
-* @hr_dev: pointer to hns roce device
-* Return : int
-*/
+ * hns_roce_setup_hca - setup host channel adapter
+ * @hr_dev: pointer to hns roce device
+ * Return : int
+ */
 static int hns_roce_setup_hca(struct hns_roce_dev *hr_dev)
 {
 	int ret;
@@ -1008,11 +828,11 @@ err_uar_table_free:
 }
 
 /**
-* hns_roce_probe - RoCE driver entrance
-* @pdev: pointer to platform device
-* Return : int
-*
-*/
+ * hns_roce_probe - RoCE driver entrance
+ * @pdev: pointer to platform device
+ * Return : int
+ *
+ */
 static int hns_roce_probe(struct platform_device *pdev)
 {
 	int ret;
@@ -1023,9 +843,6 @@ static int hns_roce_probe(struct platform_device *pdev)
 	if (!hr_dev)
 		return -ENOMEM;
 
-	memset((u8 *)hr_dev + sizeof(struct ib_device), 0,
-		sizeof(struct hns_roce_dev) - sizeof(struct ib_device));
-
 	hr_dev->pdev = pdev;
 	platform_set_drvdata(pdev, hr_dev);
 
@@ -1125,9 +942,9 @@ error_failed_get_cfg:
 }
 
 /**
-* hns_roce_remove - remove RoCE device
-* @pdev: pointer to platform device
-*/
+ * hns_roce_remove - remove RoCE device
+ * @pdev: pointer to platform device
+ */
 static int hns_roce_remove(struct platform_device *pdev)
 {
 	struct hns_roce_dev *hr_dev = platform_get_drvdata(pdev);

drivers/infiniband/hw/hns/hns_roce_mr.c

@@ -42,7 +42,7 @@ static u32 hw_index_to_key(unsigned long ind)
 	return (u32)(ind >> 24) | (ind << 8);
 }
 
-static unsigned long key_to_hw_index(u32 key)
+unsigned long key_to_hw_index(u32 key)
 {
 	return (key << 24) | (key >> 8);
 }
@@ -53,16 +53,16 @@ static int hns_roce_sw2hw_mpt(struct hns_roce_dev *hr_dev,
 {
 	return hns_roce_cmd_mbox(hr_dev, mailbox->dma, 0, mpt_index, 0,
 				 HNS_ROCE_CMD_SW2HW_MPT,
-				 HNS_ROCE_CMD_TIME_CLASS_B);
+				 HNS_ROCE_CMD_TIMEOUT_MSECS);
 }
 
-static int hns_roce_hw2sw_mpt(struct hns_roce_dev *hr_dev,
+int hns_roce_hw2sw_mpt(struct hns_roce_dev *hr_dev,
 			      struct hns_roce_cmd_mailbox *mailbox,
 			      unsigned long mpt_index)
 {
 	return hns_roce_cmd_mbox(hr_dev, 0, mailbox ? mailbox->dma : 0,
 				 mpt_index, !mailbox, HNS_ROCE_CMD_HW2SW_MPT,
-				 HNS_ROCE_CMD_TIME_CLASS_B);
+				 HNS_ROCE_CMD_TIMEOUT_MSECS);
 }
 
 static int hns_roce_buddy_alloc(struct hns_roce_buddy *buddy, int order,
@@ -137,11 +137,13 @@ static int hns_roce_buddy_init(struct hns_roce_buddy *buddy, int max_order)
 
 	for (i = 0; i <= buddy->max_order; ++i) {
 		s = BITS_TO_LONGS(1 << (buddy->max_order - i));
-		buddy->bits[i] = kmalloc_array(s, sizeof(long), GFP_KERNEL);
-		if (!buddy->bits[i])
-			goto err_out_free;
-
-		bitmap_zero(buddy->bits[i], 1 << (buddy->max_order - i));
+		buddy->bits[i] = kcalloc(s, sizeof(long), GFP_KERNEL |
+					 __GFP_NOWARN);
+		if (!buddy->bits[i]) {
+			buddy->bits[i] = vzalloc(s * sizeof(long));
+			if (!buddy->bits[i])
+				goto err_out_free;
+		}
 	}
 
 	set_bit(0, buddy->bits[buddy->max_order]);
@@ -151,7 +153,7 @@ static int hns_roce_buddy_init(struct hns_roce_buddy *buddy, int max_order)
 
 err_out_free:
 	for (i = 0; i <= buddy->max_order; ++i)
-		kfree(buddy->bits[i]);
+		kvfree(buddy->bits[i]);
 
 err_out:
 	kfree(buddy->bits);
@@ -164,7 +166,7 @@ static void hns_roce_buddy_cleanup(struct hns_roce_buddy *buddy)
 	int i;
 
 	for (i = 0; i <= buddy->max_order; ++i)
-		kfree(buddy->bits[i]);
+		kvfree(buddy->bits[i]);
 
 	kfree(buddy->bits);
 	kfree(buddy->num_free);
@@ -287,7 +289,7 @@ static void hns_roce_mr_free(struct hns_roce_dev *hr_dev,
 	}
 
 	hns_roce_bitmap_free(&hr_dev->mr_table.mtpt_bitmap,
-			     key_to_hw_index(mr->key));
+			     key_to_hw_index(mr->key), BITMAP_NO_RR);
 }
 
 static int hns_roce_mr_enable(struct hns_roce_dev *hr_dev,
@@ -605,13 +607,20 @@ err_free:
 
 int hns_roce_dereg_mr(struct ib_mr *ibmr)
 {
+	struct hns_roce_dev *hr_dev = to_hr_dev(ibmr->device);
 	struct hns_roce_mr *mr = to_hr_mr(ibmr);
+	int ret = 0;
 
-	hns_roce_mr_free(to_hr_dev(ibmr->device), mr);
-	if (mr->umem)
-		ib_umem_release(mr->umem);
+	if (hr_dev->hw->dereg_mr) {
+		ret = hr_dev->hw->dereg_mr(hr_dev, mr);
+	} else {
+		hns_roce_mr_free(hr_dev, mr);
 
-	kfree(mr);
+		if (mr->umem)
+			ib_umem_release(mr->umem);
 
-	return 0;
+		kfree(mr);
+	}
+
+	return ret;
 }

drivers/infiniband/hw/hns/hns_roce_pd.c

@@ -40,7 +40,7 @@ static int hns_roce_pd_alloc(struct hns_roce_dev *hr_dev, unsigned long *pdn)
 
 static void hns_roce_pd_free(struct hns_roce_dev *hr_dev, unsigned long pdn)
 {
-	hns_roce_bitmap_free(&hr_dev->pd_bitmap, pdn);
+	hns_roce_bitmap_free(&hr_dev->pd_bitmap, pdn, BITMAP_NO_RR);
 }
 
 int hns_roce_init_pd_table(struct hns_roce_dev *hr_dev)
@@ -121,7 +121,8 @@ int hns_roce_uar_alloc(struct hns_roce_dev *hr_dev, struct hns_roce_uar *uar)
 
 void hns_roce_uar_free(struct hns_roce_dev *hr_dev, struct hns_roce_uar *uar)
 {
-	hns_roce_bitmap_free(&hr_dev->uar_table.bitmap, uar->index);
+	hns_roce_bitmap_free(&hr_dev->uar_table.bitmap, uar->index,
+			     BITMAP_NO_RR);
 }
 
 int hns_roce_init_uar_table(struct hns_roce_dev *hr_dev)

drivers/infiniband/hw/hns/hns_roce_qp.c

@@ -37,7 +37,7 @@
 #include "hns_roce_common.h"
 #include "hns_roce_device.h"
 #include "hns_roce_hem.h"
-#include "hns_roce_user.h"
+#include <rdma/hns-abi.h>
 
 #define SQP_NUM				(2 * HNS_ROCE_MAX_PORTS)
 
@@ -250,7 +250,7 @@ void hns_roce_release_range_qp(struct hns_roce_dev *hr_dev, int base_qpn,
 	if (base_qpn < SQP_NUM)
 		return;
 
-	hns_roce_bitmap_free_range(&qp_table->bitmap, base_qpn, cnt);
+	hns_roce_bitmap_free_range(&qp_table->bitmap, base_qpn, cnt, BITMAP_RR);
 }
 
 static int hns_roce_set_rq_size(struct hns_roce_dev *hr_dev,

drivers/infiniband/hw/i40iw/i40iw.h

@@ -112,9 +112,12 @@
 #define I40IW_DRV_OPT_MCAST_LOGPORT_MAP    0x00000800
 
 #define IW_HMC_OBJ_TYPE_NUM ARRAY_SIZE(iw_hmc_obj_types)
-#define IW_CFG_FPM_QP_COUNT		32768
-#define I40IW_MAX_PAGES_PER_FMR		512
-#define I40IW_MIN_PAGES_PER_FMR		1
+#define IW_CFG_FPM_QP_COUNT               32768
+#define I40IW_MAX_PAGES_PER_FMR           512
+#define I40IW_MIN_PAGES_PER_FMR           1
+#define I40IW_CQP_COMPL_RQ_WQE_FLUSHED    2
+#define I40IW_CQP_COMPL_SQ_WQE_FLUSHED    3
+#define I40IW_CQP_COMPL_RQ_SQ_WQE_FLUSHED 4
 
 #define I40IW_MTU_TO_MSS		40
 #define I40IW_DEFAULT_MSS		1460
@@ -210,6 +213,12 @@ struct i40iw_msix_vector {
 	u32 ceq_id;
 };
 
+struct l2params_work {
+	struct work_struct work;
+	struct i40iw_device *iwdev;
+	struct i40iw_l2params l2params;
+};
+
 #define I40IW_MSIX_TABLE_SIZE   65
 
 struct virtchnl_work {
@@ -227,6 +236,7 @@ struct i40iw_device {
 	struct net_device *netdev;
 	wait_queue_head_t vchnl_waitq;
 	struct i40iw_sc_dev sc_dev;
+	struct i40iw_sc_vsi vsi;
 	struct i40iw_handler *hdl;
 	struct i40e_info *ldev;
 	struct i40e_client *client;
@@ -280,7 +290,6 @@ struct i40iw_device {
 	u32 sd_type;
 	struct workqueue_struct *param_wq;
 	atomic_t params_busy;
-	u32 mss;
 	enum init_completion_state init_state;
 	u16 mac_ip_table_idx;
 	atomic_t vchnl_msgs;
@@ -297,6 +306,14 @@ struct i40iw_device {
 	u32 mr_stagmask;
 	u32 mpa_version;
 	bool dcb;
+	bool closing;
+	bool reset;
+	u32 used_pds;
+	u32 used_cqs;
+	u32 used_mrs;
+	u32 used_qps;
+	wait_queue_head_t close_wq;
+	atomic64_t use_count;
 };
 
 struct i40iw_ib_device {
@@ -498,7 +515,7 @@ u32 i40iw_initialize_hw_resources(struct i40iw_device *iwdev);
 
 int i40iw_register_rdma_device(struct i40iw_device *iwdev);
 void i40iw_port_ibevent(struct i40iw_device *iwdev);
-int i40iw_cm_disconn(struct i40iw_qp *);
+void i40iw_cm_disconn(struct i40iw_qp *iwqp);
 void i40iw_cm_disconn_worker(void *);
 int mini_cm_recv_pkt(struct i40iw_cm_core *, struct i40iw_device *,
 		     struct sk_buff *);
@@ -508,20 +525,26 @@ enum i40iw_status_code i40iw_handle_cqp_op(struct i40iw_device *iwdev,
 enum i40iw_status_code i40iw_add_mac_addr(struct i40iw_device *iwdev,
 					  u8 *mac_addr, u8 *mac_index);
 int i40iw_modify_qp(struct ib_qp *, struct ib_qp_attr *, int, struct ib_udata *);
+void i40iw_cq_wq_destroy(struct i40iw_device *iwdev, struct i40iw_sc_cq *cq);
 
 void i40iw_rem_pdusecount(struct i40iw_pd *iwpd, struct i40iw_device *iwdev);
 void i40iw_add_pdusecount(struct i40iw_pd *iwpd);
+void i40iw_rem_devusecount(struct i40iw_device *iwdev);
+void i40iw_add_devusecount(struct i40iw_device *iwdev);
 void i40iw_hw_modify_qp(struct i40iw_device *iwdev, struct i40iw_qp *iwqp,
 			struct i40iw_modify_qp_info *info, bool wait);
 
+void i40iw_qp_suspend_resume(struct i40iw_sc_dev *dev,
+			     struct i40iw_sc_qp *qp,
+			     bool suspend);
 enum i40iw_status_code i40iw_manage_qhash(struct i40iw_device *iwdev,
 					  struct i40iw_cm_info *cminfo,
 					  enum i40iw_quad_entry_type etype,
 					  enum i40iw_quad_hash_manage_type mtype,
 					  void *cmnode,
 					  bool wait);
-void i40iw_receive_ilq(struct i40iw_sc_dev *dev, struct i40iw_puda_buf *rbuf);
-void i40iw_free_sqbuf(struct i40iw_sc_dev *dev, void *bufp);
+void i40iw_receive_ilq(struct i40iw_sc_vsi *vsi, struct i40iw_puda_buf *rbuf);
+void i40iw_free_sqbuf(struct i40iw_sc_vsi *vsi, void *bufp);
 void i40iw_free_qp_resources(struct i40iw_device *iwdev,
 			     struct i40iw_qp *iwqp,
 			     u32 qp_num);

drivers/infiniband/hw/i40iw/i40iw_cm.c

@@ -68,13 +68,13 @@ static void i40iw_disconnect_worker(struct work_struct *work);
 
 /**
  * i40iw_free_sqbuf - put back puda buffer if refcount = 0
- * @dev: FPK device
+ * @vsi: pointer to vsi structure
  * @buf: puda buffer to free
  */
-void i40iw_free_sqbuf(struct i40iw_sc_dev *dev, void *bufp)
+void i40iw_free_sqbuf(struct i40iw_sc_vsi *vsi, void *bufp)
 {
 	struct i40iw_puda_buf *buf = (struct i40iw_puda_buf *)bufp;
-	struct i40iw_puda_rsrc *ilq = dev->ilq;
+	struct i40iw_puda_rsrc *ilq = vsi->ilq;
 
 	if (!atomic_dec_return(&buf->refcount))
 		i40iw_puda_ret_bufpool(ilq, buf);
@@ -221,6 +221,7 @@ static void i40iw_get_addr_info(struct i40iw_cm_node *cm_node,
 	memcpy(cm_info->rem_addr, cm_node->rem_addr, sizeof(cm_info->rem_addr));
 	cm_info->loc_port = cm_node->loc_port;
 	cm_info->rem_port = cm_node->rem_port;
+	cm_info->user_pri = cm_node->user_pri;
 }
 
 /**
@@ -271,6 +272,7 @@ static int i40iw_send_cm_event(struct i40iw_cm_node *cm_node,
 		event.provider_data = (void *)cm_node;
 		event.private_data = (void *)cm_node->pdata_buf;
 		event.private_data_len = (u8)cm_node->pdata.size;
+		event.ird = cm_node->ird_size;
 		break;
 	case IW_CM_EVENT_CONNECT_REPLY:
 		i40iw_get_cmevent_info(cm_node, cm_id, &event);
@@ -335,13 +337,13 @@ static struct i40iw_cm_event *i40iw_create_event(struct i40iw_cm_node *cm_node,
  */
 static void i40iw_free_retrans_entry(struct i40iw_cm_node *cm_node)
 {
-	struct i40iw_sc_dev *dev = cm_node->dev;
+	struct i40iw_device *iwdev = cm_node->iwdev;
 	struct i40iw_timer_entry *send_entry;
 
 	send_entry = cm_node->send_entry;
 	if (send_entry) {
 		cm_node->send_entry = NULL;
-		i40iw_free_sqbuf(dev, (void *)send_entry->sqbuf);
+		i40iw_free_sqbuf(&iwdev->vsi, (void *)send_entry->sqbuf);
 		kfree(send_entry);
 		atomic_dec(&cm_node->ref_count);
 	}
@@ -360,15 +362,6 @@ static void i40iw_cleanup_retrans_entry(struct i40iw_cm_node *cm_node)
 	spin_unlock_irqrestore(&cm_node->retrans_list_lock, flags);
 }
 
-static bool is_remote_ne020_or_chelsio(struct i40iw_cm_node *cm_node)
-{
-	if ((cm_node->rem_mac[0] == 0x0) &&
-	    (((cm_node->rem_mac[1] == 0x12) && (cm_node->rem_mac[2] == 0x55)) ||
-	     ((cm_node->rem_mac[1] == 0x07 && (cm_node->rem_mac[2] == 0x43)))))
-		return true;
-	return false;
-}
-
 /**
  * i40iw_form_cm_frame - get a free packet and build frame
  * @cm_node: connection's node ionfo to use in frame
@@ -384,7 +377,7 @@ static struct i40iw_puda_buf *i40iw_form_cm_frame(struct i40iw_cm_node *cm_node,
 						  u8 flags)
 {
 	struct i40iw_puda_buf *sqbuf;
-	struct i40iw_sc_dev *dev = cm_node->dev;
+	struct i40iw_sc_vsi *vsi = &cm_node->iwdev->vsi;
 	u8 *buf;
 
 	struct tcphdr *tcph;
@@ -396,8 +389,9 @@ static struct i40iw_puda_buf *i40iw_form_cm_frame(struct i40iw_cm_node *cm_node,
 	u32 opts_len = 0;
 	u32 pd_len = 0;
 	u32 hdr_len = 0;
+	u16 vtag;
 
-	sqbuf = i40iw_puda_get_bufpool(dev->ilq);
+	sqbuf = i40iw_puda_get_bufpool(vsi->ilq);
 	if (!sqbuf)
 		return NULL;
 	buf = sqbuf->mem.va;
@@ -408,11 +402,8 @@ static struct i40iw_puda_buf *i40iw_form_cm_frame(struct i40iw_cm_node *cm_node,
 	if (hdr)
 		hdr_len = hdr->size;
 
-	if (pdata) {
+	if (pdata)
 		pd_len = pdata->size;
-		if (!is_remote_ne020_or_chelsio(cm_node))
-			pd_len += MPA_ZERO_PAD_LEN;
-	}
 
 	if (cm_node->vlan_id < VLAN_TAG_PRESENT)
 		eth_hlen += 4;
@@ -445,7 +436,8 @@ static struct i40iw_puda_buf *i40iw_form_cm_frame(struct i40iw_cm_node *cm_node,
 		ether_addr_copy(ethh->h_source, cm_node->loc_mac);
 		if (cm_node->vlan_id < VLAN_TAG_PRESENT) {
 			((struct vlan_ethhdr *)ethh)->h_vlan_proto = htons(ETH_P_8021Q);
-			((struct vlan_ethhdr *)ethh)->h_vlan_TCI = htons(cm_node->vlan_id);
+			vtag = (cm_node->user_pri << VLAN_PRIO_SHIFT) | cm_node->vlan_id;
+			((struct vlan_ethhdr *)ethh)->h_vlan_TCI = htons(vtag);
 
 			((struct vlan_ethhdr *)ethh)->h_vlan_encapsulated_proto = htons(ETH_P_IP);
 		} else {
@@ -454,7 +446,7 @@ static struct i40iw_puda_buf *i40iw_form_cm_frame(struct i40iw_cm_node *cm_node,
 
 		iph->version = IPVERSION;
 		iph->ihl = 5;	/* 5 * 4Byte words, IP headr len */
-		iph->tos = 0;
+		iph->tos = cm_node->tos;
 		iph->tot_len = htons(packetsize);
 		iph->id = htons(++cm_node->tcp_cntxt.loc_id);
 
@@ -474,13 +466,15 @@ static struct i40iw_puda_buf *i40iw_form_cm_frame(struct i40iw_cm_node *cm_node,
 		ether_addr_copy(ethh->h_source, cm_node->loc_mac);
 		if (cm_node->vlan_id < VLAN_TAG_PRESENT) {
 			((struct vlan_ethhdr *)ethh)->h_vlan_proto = htons(ETH_P_8021Q);
-			((struct vlan_ethhdr *)ethh)->h_vlan_TCI = htons(cm_node->vlan_id);
+			vtag = (cm_node->user_pri << VLAN_PRIO_SHIFT) | cm_node->vlan_id;
+			((struct vlan_ethhdr *)ethh)->h_vlan_TCI = htons(vtag);
 			((struct vlan_ethhdr *)ethh)->h_vlan_encapsulated_proto = htons(ETH_P_IPV6);
 		} else {
 			ethh->h_proto = htons(ETH_P_IPV6);
 		}
 		ip6h->version = 6;
-		ip6h->flow_lbl[0] = 0;
+		ip6h->priority = cm_node->tos >> 4;
+		ip6h->flow_lbl[0] = cm_node->tos << 4;
 		ip6h->flow_lbl[1] = 0;
 		ip6h->flow_lbl[2] = 0;
 		ip6h->payload_len = htons(packetsize - sizeof(*ip6h));
@@ -1065,7 +1059,7 @@ int i40iw_schedule_cm_timer(struct i40iw_cm_node *cm_node,
 			    int send_retrans,
 			    int close_when_complete)
 {
-	struct i40iw_sc_dev *dev = cm_node->dev;
+	struct i40iw_sc_vsi *vsi = &cm_node->iwdev->vsi;
 	struct i40iw_cm_core *cm_core = cm_node->cm_core;
 	struct i40iw_timer_entry *new_send;
 	int ret = 0;
@@ -1074,7 +1068,7 @@ int i40iw_schedule_cm_timer(struct i40iw_cm_node *cm_node,
 
 	new_send = kzalloc(sizeof(*new_send), GFP_ATOMIC);
 	if (!new_send) {
-		i40iw_free_sqbuf(cm_node->dev, (void *)sqbuf);
+		i40iw_free_sqbuf(vsi, (void *)sqbuf);
 		return -ENOMEM;
 	}
 	new_send->retrycount = I40IW_DEFAULT_RETRYS;
@@ -1089,7 +1083,7 @@ int i40iw_schedule_cm_timer(struct i40iw_cm_node *cm_node,
 		new_send->timetosend += (HZ / 10);
 		if (cm_node->close_entry) {
 			kfree(new_send);
-			i40iw_free_sqbuf(cm_node->dev, (void *)sqbuf);
+			i40iw_free_sqbuf(vsi, (void *)sqbuf);
 			i40iw_pr_err("already close entry\n");
 			return -EINVAL;
 		}
@@ -1104,7 +1098,7 @@ int i40iw_schedule_cm_timer(struct i40iw_cm_node *cm_node,
 		new_send->timetosend = jiffies + I40IW_RETRY_TIMEOUT;
 
 		atomic_inc(&sqbuf->refcount);
-		i40iw_puda_send_buf(dev->ilq, sqbuf);
+		i40iw_puda_send_buf(vsi->ilq, sqbuf);
 		if (!send_retrans) {
 			i40iw_cleanup_retrans_entry(cm_node);
 			if (close_when_complete)
@@ -1201,6 +1195,7 @@ static void i40iw_cm_timer_tick(unsigned long pass)
 	struct i40iw_cm_node *cm_node;
 	struct i40iw_timer_entry *send_entry, *close_entry;
 	struct list_head *list_core_temp;
+	struct i40iw_sc_vsi *vsi;
 	struct list_head *list_node;
 	struct i40iw_cm_core *cm_core = (struct i40iw_cm_core *)pass;
 	u32 settimer = 0;
@@ -1276,9 +1271,10 @@ static void i40iw_cm_timer_tick(unsigned long pass)
 		cm_node->cm_core->stats_pkt_retrans++;
 		spin_unlock_irqrestore(&cm_node->retrans_list_lock, flags);
 
+		vsi = &cm_node->iwdev->vsi;
 		dev = cm_node->dev;
 		atomic_inc(&send_entry->sqbuf->refcount);
-		i40iw_puda_send_buf(dev->ilq, send_entry->sqbuf);
+		i40iw_puda_send_buf(vsi->ilq, send_entry->sqbuf);
 		spin_lock_irqsave(&cm_node->retrans_list_lock, flags);
 		if (send_entry->send_retrans) {
 			send_entry->retranscount--;
@@ -1379,10 +1375,11 @@ int i40iw_send_syn(struct i40iw_cm_node *cm_node, u32 sendack)
 static void i40iw_send_ack(struct i40iw_cm_node *cm_node)
 {
 	struct i40iw_puda_buf *sqbuf;
+	struct i40iw_sc_vsi *vsi = &cm_node->iwdev->vsi;
 
 	sqbuf = i40iw_form_cm_frame(cm_node, NULL, NULL, NULL, SET_ACK);
 	if (sqbuf)
-		i40iw_puda_send_buf(cm_node->dev->ilq, sqbuf);
+		i40iw_puda_send_buf(vsi->ilq, sqbuf);
 	else
 		i40iw_pr_err("no sqbuf\n");
 }
@@ -1564,9 +1561,15 @@ static enum i40iw_status_code i40iw_del_multiple_qhash(
 		memcpy(cm_info->loc_addr, child_listen_node->loc_addr,
 		       sizeof(cm_info->loc_addr));
 		cm_info->vlan_id = child_listen_node->vlan_id;
-		ret = i40iw_manage_qhash(iwdev, cm_info,
-					 I40IW_QHASH_TYPE_TCP_SYN,
-					 I40IW_QHASH_MANAGE_TYPE_DELETE, NULL, false);
+		if (child_listen_node->qhash_set) {
+			ret = i40iw_manage_qhash(iwdev, cm_info,
+						 I40IW_QHASH_TYPE_TCP_SYN,
+						 I40IW_QHASH_MANAGE_TYPE_DELETE,
+						 NULL, false);
+			child_listen_node->qhash_set = false;
+		} else {
+			ret = I40IW_SUCCESS;
+		}
 		i40iw_debug(&iwdev->sc_dev,
 			    I40IW_DEBUG_CM,
 			    "freed pointer = %p\n",
@@ -1591,9 +1594,10 @@ static enum i40iw_status_code i40iw_del_multiple_qhash(
 static struct net_device *i40iw_netdev_vlan_ipv6(u32 *addr, u16 *vlan_id, u8 *mac)
 {
 	struct net_device *ip_dev = NULL;
-#if IS_ENABLED(CONFIG_IPV6)
 	struct in6_addr laddr6;
 
+	if (!IS_ENABLED(CONFIG_IPV6))
+		return NULL;
 	i40iw_copy_ip_htonl(laddr6.in6_u.u6_addr32, addr);
 	if (vlan_id)
 		*vlan_id = I40IW_NO_VLAN;
@@ -1610,7 +1614,6 @@ static struct net_device *i40iw_netdev_vlan_ipv6(u32 *addr, u16 *vlan_id, u8 *ma
 		}
 	}
 	rcu_read_unlock();
-#endif
 	return ip_dev;
 }
 
@@ -1646,7 +1649,7 @@ static enum i40iw_status_code i40iw_add_mqh_6(struct i40iw_device *iwdev,
 {
 	struct net_device *ip_dev;
 	struct inet6_dev *idev;
-	struct inet6_ifaddr *ifp;
+	struct inet6_ifaddr *ifp, *tmp;
 	enum i40iw_status_code ret = 0;
 	struct i40iw_cm_listener *child_listen_node;
 	unsigned long flags;
@@ -1661,7 +1664,7 @@ static enum i40iw_status_code i40iw_add_mqh_6(struct i40iw_device *iwdev,
 				i40iw_pr_err("idev == NULL\n");
 				break;
 			}
-			list_for_each_entry(ifp, &idev->addr_list, if_list) {
+			list_for_each_entry_safe(ifp, tmp, &idev->addr_list, if_list) {
 				i40iw_debug(&iwdev->sc_dev,
 					    I40IW_DEBUG_CM,
 					    "IP=%pI6, vlan_id=%d, MAC=%pM\n",
@@ -1675,7 +1678,6 @@ static enum i40iw_status_code i40iw_add_mqh_6(struct i40iw_device *iwdev,
 					    "Allocating child listener %p\n",
 					    child_listen_node);
 				if (!child_listen_node) {
-					i40iw_pr_err("listener memory allocation\n");
 					ret = I40IW_ERR_NO_MEMORY;
 					goto exit;
 				}
@@ -1695,6 +1697,7 @@ static enum i40iw_status_code i40iw_add_mqh_6(struct i40iw_device *iwdev,
 							 I40IW_QHASH_MANAGE_TYPE_ADD,
 							 NULL, true);
 				if (!ret) {
+					child_listen_node->qhash_set = true;
 					spin_lock_irqsave(&iwdev->cm_core.listen_list_lock, flags);
 					list_add(&child_listen_node->child_listen_list,
 						 &cm_parent_listen_node->child_listen_list);
@@ -1751,7 +1754,6 @@ static enum i40iw_status_code i40iw_add_mqh_4(
 					    "Allocating child listener %p\n",
 					    child_listen_node);
 				if (!child_listen_node) {
-					i40iw_pr_err("listener memory allocation\n");
 					in_dev_put(idev);
 					ret = I40IW_ERR_NO_MEMORY;
 					goto exit;
@@ -1773,6 +1775,7 @@ static enum i40iw_status_code i40iw_add_mqh_4(
 							 NULL,
 							 true);
 				if (!ret) {
+					child_listen_node->qhash_set = true;
 					spin_lock_irqsave(&iwdev->cm_core.listen_list_lock, flags);
 					list_add(&child_listen_node->child_listen_list,
 						 &cm_parent_listen_node->child_listen_list);
@@ -1880,6 +1883,7 @@ static int i40iw_dec_refcnt_listen(struct i40iw_cm_core *cm_core,
 			nfo.loc_port = listener->loc_port;
 			nfo.ipv4 = listener->ipv4;
 			nfo.vlan_id = listener->vlan_id;
+			nfo.user_pri = listener->user_pri;
 
 			if (!list_empty(&listener->child_listen_list)) {
 				i40iw_del_multiple_qhash(listener->iwdev, &nfo, listener);
@@ -2138,6 +2142,20 @@ static struct i40iw_cm_node *i40iw_make_cm_node(
 	/* set our node specific transport info */
 	cm_node->ipv4 = cm_info->ipv4;
 	cm_node->vlan_id = cm_info->vlan_id;
+	if ((cm_node->vlan_id == I40IW_NO_VLAN) && iwdev->dcb)
+		cm_node->vlan_id = 0;
+	cm_node->tos = cm_info->tos;
+	cm_node->user_pri = cm_info->user_pri;
+	if (listener) {
+		if (listener->tos != cm_info->tos)
+			i40iw_debug(&iwdev->sc_dev, I40IW_DEBUG_DCB,
+				    "application TOS[%d] and remote client TOS[%d] mismatch\n",
+				     listener->tos, cm_info->tos);
+		cm_node->tos = max(listener->tos, cm_info->tos);
+		cm_node->user_pri = rt_tos2priority(cm_node->tos);
+		i40iw_debug(&iwdev->sc_dev, I40IW_DEBUG_DCB, "listener: TOS:[%d] UP:[%d]\n",
+			    cm_node->tos, cm_node->user_pri);
+	}
 	memcpy(cm_node->loc_addr, cm_info->loc_addr, sizeof(cm_node->loc_addr));
 	memcpy(cm_node->rem_addr, cm_info->rem_addr, sizeof(cm_node->rem_addr));
 	cm_node->loc_port = cm_info->loc_port;
@@ -2162,7 +2180,7 @@ static struct i40iw_cm_node *i40iw_make_cm_node(
 			I40IW_CM_DEFAULT_RCV_WND_SCALED >> I40IW_CM_DEFAULT_RCV_WND_SCALE;
 	ts = current_kernel_time();
 	cm_node->tcp_cntxt.loc_seq_num = ts.tv_nsec;
-	cm_node->tcp_cntxt.mss = iwdev->mss;
+	cm_node->tcp_cntxt.mss = iwdev->vsi.mss;
 
 	cm_node->iwdev = iwdev;
 	cm_node->dev = &iwdev->sc_dev;
@@ -2236,7 +2254,7 @@ static void i40iw_rem_ref_cm_node(struct i40iw_cm_node *cm_node)
 		i40iw_dec_refcnt_listen(cm_core, cm_node->listener, 0, true);
 	} else {
 		if (!i40iw_listen_port_in_use(cm_core, cm_node->loc_port) &&
-		    cm_node->apbvt_set && cm_node->iwdev) {
+		    cm_node->apbvt_set) {
 			i40iw_manage_apbvt(cm_node->iwdev,
 					   cm_node->loc_port,
 					   I40IW_MANAGE_APBVT_DEL);
@@ -2861,7 +2879,7 @@ static struct i40iw_cm_node *i40iw_create_cm_node(
 	/* create a CM connection node */
 	cm_node = i40iw_make_cm_node(cm_core, iwdev, cm_info, NULL);
 	if (!cm_node)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	/* set our node side to client (active) side */
 	cm_node->tcp_cntxt.client = 1;
 	cm_node->tcp_cntxt.rcv_wscale = I40IW_CM_DEFAULT_RCV_WND_SCALE;
@@ -2874,7 +2892,8 @@ static struct i40iw_cm_node *i40iw_create_cm_node(
 						cm_node->vlan_id,
 						I40IW_CM_LISTENER_ACTIVE_STATE);
 		if (!loopback_remotelistener) {
-			i40iw_create_event(cm_node, I40IW_CM_EVENT_ABORTED);
+			i40iw_rem_ref_cm_node(cm_node);
+			return ERR_PTR(-ECONNREFUSED);
 		} else {
 			loopback_cm_info = *cm_info;
 			loopback_cm_info.loc_port = cm_info->rem_port;
@@ -2887,7 +2906,7 @@ static struct i40iw_cm_node *i40iw_create_cm_node(
 								 loopback_remotelistener);
 			if (!loopback_remotenode) {
 				i40iw_rem_ref_cm_node(cm_node);
-				return NULL;
+				return ERR_PTR(-ENOMEM);
 			}
 			cm_core->stats_loopbacks++;
 			loopback_remotenode->loopbackpartner = cm_node;
@@ -3041,10 +3060,10 @@ static int i40iw_cm_close(struct i40iw_cm_node *cm_node)
 /**
  * i40iw_receive_ilq - recv an ETHERNET packet, and process it
  * through CM
- * @dev: FPK dev struct
+ * @vsi: pointer to the vsi structure
  * @rbuf: receive buffer
  */
-void i40iw_receive_ilq(struct i40iw_sc_dev *dev, struct i40iw_puda_buf *rbuf)
+void i40iw_receive_ilq(struct i40iw_sc_vsi *vsi, struct i40iw_puda_buf *rbuf)
 {
 	struct i40iw_cm_node *cm_node;
 	struct i40iw_cm_listener *listener;
@@ -3052,9 +3071,11 @@ void i40iw_receive_ilq(struct i40iw_sc_dev *dev, struct i40iw_puda_buf *rbuf)
 	struct ipv6hdr *ip6h;
 	struct tcphdr *tcph;
 	struct i40iw_cm_info cm_info;
+	struct i40iw_sc_dev *dev = vsi->dev;
 	struct i40iw_device *iwdev = (struct i40iw_device *)dev->back_dev;
 	struct i40iw_cm_core *cm_core = &iwdev->cm_core;
 	struct vlan_ethhdr *ethh;
+	u16 vtag;
 
 	/* if vlan, then maclen = 18 else 14 */
 	iph = (struct iphdr *)rbuf->iph;
@@ -3068,7 +3089,9 @@ void i40iw_receive_ilq(struct i40iw_sc_dev *dev, struct i40iw_puda_buf *rbuf)
 	ethh = (struct vlan_ethhdr *)rbuf->mem.va;
 
 	if (ethh->h_vlan_proto == htons(ETH_P_8021Q)) {
-		cm_info.vlan_id = ntohs(ethh->h_vlan_TCI) & VLAN_VID_MASK;
+		vtag = ntohs(ethh->h_vlan_TCI);
+		cm_info.user_pri = (vtag & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+		cm_info.vlan_id = vtag & VLAN_VID_MASK;
 		i40iw_debug(cm_core->dev,
 			    I40IW_DEBUG_CM,
 			    "%s vlan_id=%d\n",
@@ -3083,6 +3106,7 @@ void i40iw_receive_ilq(struct i40iw_sc_dev *dev, struct i40iw_puda_buf *rbuf)
 		cm_info.loc_addr[0] = ntohl(iph->daddr);
 		cm_info.rem_addr[0] = ntohl(iph->saddr);
 		cm_info.ipv4 = true;
+		cm_info.tos = iph->tos;
 	} else {
 		ip6h = (struct ipv6hdr *)rbuf->iph;
 		i40iw_copy_ip_ntohl(cm_info.loc_addr,
@@ -3090,6 +3114,7 @@ void i40iw_receive_ilq(struct i40iw_sc_dev *dev, struct i40iw_puda_buf *rbuf)
 		i40iw_copy_ip_ntohl(cm_info.rem_addr,
 				    ip6h->saddr.in6_u.u6_addr32);
 		cm_info.ipv4 = false;
+		cm_info.tos = (ip6h->priority << 4) | (ip6h->flow_lbl[0] >> 4);
 	}
 	cm_info.loc_port = ntohs(tcph->dest);
 	cm_info.rem_port = ntohs(tcph->source);
@@ -3309,6 +3334,8 @@ static void i40iw_cm_init_tsa_conn(struct i40iw_qp *iwqp,
 
 	ctx_info->tcp_info_valid = true;
 	ctx_info->iwarp_info_valid = true;
+	ctx_info->add_to_qoslist = true;
+	ctx_info->user_pri = cm_node->user_pri;
 
 	i40iw_init_tcp_ctx(cm_node, &tcp_info, iwqp);
 	if (cm_node->snd_mark_en) {
@@ -3320,33 +3347,47 @@ static void i40iw_cm_init_tsa_conn(struct i40iw_qp *iwqp,
 	cm_node->state = I40IW_CM_STATE_OFFLOADED;
 	tcp_info.tcp_state = I40IW_TCP_STATE_ESTABLISHED;
 	tcp_info.src_mac_addr_idx = iwdev->mac_ip_table_idx;
+	tcp_info.tos = cm_node->tos;
 
 	dev->iw_priv_qp_ops->qp_setctx(&iwqp->sc_qp, (u64 *)(iwqp->host_ctx.va), ctx_info);
 
 	/* once tcp_info is set, no need to do it again */
 	ctx_info->tcp_info_valid = false;
 	ctx_info->iwarp_info_valid = false;
+	ctx_info->add_to_qoslist = false;
 }
 
 /**
  * i40iw_cm_disconn - when a connection is being closed
  * @iwqp: associate qp for the connection
  */
-int i40iw_cm_disconn(struct i40iw_qp *iwqp)
+void i40iw_cm_disconn(struct i40iw_qp *iwqp)
 {
 	struct disconn_work *work;
 	struct i40iw_device *iwdev = iwqp->iwdev;
 	struct i40iw_cm_core *cm_core = &iwdev->cm_core;
+	unsigned long flags;
 
 	work = kzalloc(sizeof(*work), GFP_ATOMIC);
 	if (!work)
-		return -ENOMEM;	/* Timer will clean up */
-
+		return;	/* Timer will clean up */
+
+	spin_lock_irqsave(&iwdev->qptable_lock, flags);
+	if (!iwdev->qp_table[iwqp->ibqp.qp_num]) {
+		spin_unlock_irqrestore(&iwdev->qptable_lock, flags);
+		i40iw_debug(&iwdev->sc_dev, I40IW_DEBUG_CM,
+			    "%s qp_id %d is already freed\n",
+			     __func__, iwqp->ibqp.qp_num);
+		kfree(work);
+		return;
+	}
 	i40iw_add_ref(&iwqp->ibqp);
+	spin_unlock_irqrestore(&iwdev->qptable_lock, flags);
+
 	work->iwqp = iwqp;
 	INIT_WORK(&work->work, i40iw_disconnect_worker);
 	queue_work(cm_core->disconn_wq, &work->work);
-	return 0;
+	return;
 }
 
 /**
@@ -3432,7 +3473,7 @@ static void i40iw_cm_disconn_true(struct i40iw_qp *iwqp)
 		 *terminate-handler to issue cm_disconn which can re-free
 		 *a QP even after its refcnt=0.
 		 */
-		del_timer(&iwqp->terminate_timer);
+		i40iw_terminate_del_timer(qp);
 		if (!iwqp->flush_issued) {
 			iwqp->flush_issued = 1;
 			issue_flush = 1;
@@ -3462,7 +3503,7 @@ static void i40iw_cm_disconn_true(struct i40iw_qp *iwqp)
 		/* Flush the queues */
 		i40iw_flush_wqes(iwdev, iwqp);
 
-		if (qp->term_flags) {
+		if (qp->term_flags && iwqp->ibqp.event_handler) {
 			ibevent.device = iwqp->ibqp.device;
 			ibevent.event = (qp->eventtype == TERM_EVENT_QP_FATAL) ?
 					IB_EVENT_QP_FATAL : IB_EVENT_QP_ACCESS_ERR;
@@ -3571,7 +3612,7 @@ int i40iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	iwqp->cm_node = (void *)cm_node;
 	cm_node->iwqp = iwqp;
 
-	buf_len = conn_param->private_data_len + I40IW_MAX_IETF_SIZE + MPA_ZERO_PAD_LEN;
+	buf_len = conn_param->private_data_len + I40IW_MAX_IETF_SIZE;
 
 	status = i40iw_allocate_dma_mem(dev->hw, &iwqp->ietf_mem, buf_len, 1);
 
@@ -3605,18 +3646,10 @@ int i40iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 		iwqp->lsmm_mr = ibmr;
 		if (iwqp->page)
 			iwqp->sc_qp.qp_uk.sq_base = kmap(iwqp->page);
-		if (is_remote_ne020_or_chelsio(cm_node))
-			dev->iw_priv_qp_ops->qp_send_lsmm(
-							&iwqp->sc_qp,
+		dev->iw_priv_qp_ops->qp_send_lsmm(&iwqp->sc_qp,
 							iwqp->ietf_mem.va,
 							(accept.size + conn_param->private_data_len),
 							ibmr->lkey);
-		else
-			dev->iw_priv_qp_ops->qp_send_lsmm(
-							&iwqp->sc_qp,
-							iwqp->ietf_mem.va,
-							(accept.size + conn_param->private_data_len + MPA_ZERO_PAD_LEN),
-							ibmr->lkey);
 
 	} else {
 		if (iwqp->page)
@@ -3714,6 +3747,7 @@ int i40iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	struct sockaddr_in6 *raddr6;
 	bool qhash_set = false;
 	int apbvt_set = 0;
+	int err = 0;
 	enum i40iw_status_code status;
 
 	ibqp = i40iw_get_qp(cm_id->device, conn_param->qpn);
@@ -3759,6 +3793,10 @@ int i40iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 		i40iw_netdev_vlan_ipv6(cm_info.loc_addr, &cm_info.vlan_id, NULL);
 	}
 	cm_info.cm_id = cm_id;
+	cm_info.tos = cm_id->tos;
+	cm_info.user_pri = rt_tos2priority(cm_id->tos);
+	i40iw_debug(&iwdev->sc_dev, I40IW_DEBUG_DCB, "%s TOS:[%d] UP:[%d]\n",
+		    __func__, cm_id->tos, cm_info.user_pri);
 	if ((cm_info.ipv4 && (laddr->sin_addr.s_addr != raddr->sin_addr.s_addr)) ||
 	    (!cm_info.ipv4 && memcmp(laddr6->sin6_addr.in6_u.u6_addr32,
 				     raddr6->sin6_addr.in6_u.u6_addr32,
@@ -3790,8 +3828,11 @@ int i40iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 				       conn_param->private_data_len,
 				       (void *)conn_param->private_data,
 				       &cm_info);
-	if (!cm_node)
-		goto err;
+
+	if (IS_ERR(cm_node)) {
+		err = PTR_ERR(cm_node);
+		goto err_out;
+	}
 
 	i40iw_record_ird_ord(cm_node, (u16)conn_param->ird, (u16)conn_param->ord);
 	if (cm_node->send_rdma0_op == SEND_RDMA_READ_ZERO &&
@@ -3805,10 +3846,12 @@ int i40iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	iwqp->cm_id = cm_id;
 	i40iw_add_ref(&iwqp->ibqp);
 
-	if (cm_node->state == I40IW_CM_STATE_SYN_SENT) {
-		if (i40iw_send_syn(cm_node, 0)) {
+	if (cm_node->state != I40IW_CM_STATE_OFFLOADED) {
+		cm_node->state = I40IW_CM_STATE_SYN_SENT;
+		err = i40iw_send_syn(cm_node, 0);
+		if (err) {
 			i40iw_rem_ref_cm_node(cm_node);
-			goto err;
+			goto err_out;
 		}
 	}
 
@@ -3820,24 +3863,25 @@ int i40iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 		    cm_node->cm_id);
 	return 0;
 
-err:
-	if (cm_node) {
-		if (cm_node->ipv4)
-			i40iw_debug(cm_node->dev,
-				    I40IW_DEBUG_CM,
-				    "Api - connect() FAILED: dest addr=%pI4",
-				    cm_node->rem_addr);
-		else
-			i40iw_debug(cm_node->dev, I40IW_DEBUG_CM,
-				    "Api - connect() FAILED: dest addr=%pI6",
-				    cm_node->rem_addr);
-	}
-	i40iw_manage_qhash(iwdev,
-			   &cm_info,
-			   I40IW_QHASH_TYPE_TCP_ESTABLISHED,
-			   I40IW_QHASH_MANAGE_TYPE_DELETE,
-			   NULL,
-			   false);
+err_out:
+	if (cm_info.ipv4)
+		i40iw_debug(&iwdev->sc_dev,
+			    I40IW_DEBUG_CM,
+			    "Api - connect() FAILED: dest addr=%pI4",
+			    cm_info.rem_addr);
+	else
+		i40iw_debug(&iwdev->sc_dev,
+			    I40IW_DEBUG_CM,
+			    "Api - connect() FAILED: dest addr=%pI6",
+			    cm_info.rem_addr);
+
+	if (qhash_set)
+		i40iw_manage_qhash(iwdev,
+				   &cm_info,
+				   I40IW_QHASH_TYPE_TCP_ESTABLISHED,
+				   I40IW_QHASH_MANAGE_TYPE_DELETE,
+				   NULL,
+				   false);
 
 	if (apbvt_set && !i40iw_listen_port_in_use(&iwdev->cm_core,
 						   cm_info.loc_port))
@@ -3846,7 +3890,7 @@ err:
 				   I40IW_MANAGE_APBVT_DEL);
 	cm_id->rem_ref(cm_id);
 	iwdev->cm_core.stats_connect_errs++;
-	return -ENOMEM;
+	return err;
 }
 
 /**
@@ -3904,6 +3948,10 @@ int i40iw_create_listen(struct iw_cm_id *cm_id, int backlog)
 
 	cm_id->provider_data = cm_listen_node;
 
+	cm_listen_node->tos = cm_id->tos;
+	cm_listen_node->user_pri = rt_tos2priority(cm_id->tos);
+	cm_info.user_pri = cm_listen_node->user_pri;
+
 	if (!cm_listen_node->reused_node) {
 		if (wildcard) {
 			if (cm_info.ipv4)
@@ -4124,3 +4172,158 @@ static void i40iw_cm_post_event(struct i40iw_cm_event *event)
 
 	queue_work(event->cm_node->cm_core->event_wq, &event->event_work);
 }
+
+/**
+ * i40iw_qhash_ctrl - enable/disable qhash for list
+ * @iwdev: device pointer
+ * @parent_listen_node: parent listen node
+ * @nfo: cm info node
+ * @ipaddr: Pointer to IPv4 or IPv6 address
+ * @ipv4: flag indicating IPv4 when true
+ * @ifup: flag indicating interface up when true
+ *
+ * Enables or disables the qhash for the node in the child
+ * listen list that matches ipaddr. If no matching IP was found
+ * it will allocate and add a new child listen node to the
+ * parent listen node. The listen_list_lock is assumed to be
+ * held when called.
+ */
+static void i40iw_qhash_ctrl(struct i40iw_device *iwdev,
+			     struct i40iw_cm_listener *parent_listen_node,
+			     struct i40iw_cm_info *nfo,
+			     u32 *ipaddr, bool ipv4, bool ifup)
+{
+	struct list_head *child_listen_list = &parent_listen_node->child_listen_list;
+	struct i40iw_cm_listener *child_listen_node;
+	struct list_head *pos, *tpos;
+	enum i40iw_status_code ret;
+	bool node_allocated = false;
+	enum i40iw_quad_hash_manage_type op =
+		ifup ? I40IW_QHASH_MANAGE_TYPE_ADD : I40IW_QHASH_MANAGE_TYPE_DELETE;
+
+	list_for_each_safe(pos, tpos, child_listen_list) {
+		child_listen_node =
+			list_entry(pos,
+				   struct i40iw_cm_listener,
+				   child_listen_list);
+		if (!memcmp(child_listen_node->loc_addr, ipaddr, ipv4 ? 4 : 16))
+			goto set_qhash;
+	}
+
+	/* if not found then add a child listener if interface is going up */
+	if (!ifup)
+		return;
+	child_listen_node = kzalloc(sizeof(*child_listen_node), GFP_ATOMIC);
+	if (!child_listen_node)
+		return;
+	node_allocated = true;
+	memcpy(child_listen_node, parent_listen_node, sizeof(*child_listen_node));
+
+	memcpy(child_listen_node->loc_addr, ipaddr,  ipv4 ? 4 : 16);
+
+set_qhash:
+	memcpy(nfo->loc_addr,
+	       child_listen_node->loc_addr,
+	       sizeof(nfo->loc_addr));
+	nfo->vlan_id = child_listen_node->vlan_id;
+	ret = i40iw_manage_qhash(iwdev, nfo,
+				 I40IW_QHASH_TYPE_TCP_SYN,
+				 op,
+				 NULL, false);
+	if (!ret) {
+		child_listen_node->qhash_set = ifup;
+		if (node_allocated)
+			list_add(&child_listen_node->child_listen_list,
+				 &parent_listen_node->child_listen_list);
+	} else if (node_allocated) {
+		kfree(child_listen_node);
+	}
+}
+
+/**
+ * i40iw_cm_disconnect_all - disconnect all connected qp's
+ * @iwdev: device pointer
+ */
+void i40iw_cm_disconnect_all(struct i40iw_device *iwdev)
+{
+	struct i40iw_cm_core *cm_core = &iwdev->cm_core;
+	struct list_head *list_core_temp;
+	struct list_head *list_node;
+	struct i40iw_cm_node *cm_node;
+	unsigned long flags;
+	struct list_head connected_list;
+	struct ib_qp_attr attr;
+
+	INIT_LIST_HEAD(&connected_list);
+	spin_lock_irqsave(&cm_core->ht_lock, flags);
+	list_for_each_safe(list_node, list_core_temp, &cm_core->connected_nodes) {
+		cm_node = container_of(list_node, struct i40iw_cm_node, list);
+		atomic_inc(&cm_node->ref_count);
+		list_add(&cm_node->connected_entry, &connected_list);
+	}
+	spin_unlock_irqrestore(&cm_core->ht_lock, flags);
+
+	list_for_each_safe(list_node, list_core_temp, &connected_list) {
+		cm_node = container_of(list_node, struct i40iw_cm_node, connected_entry);
+		attr.qp_state = IB_QPS_ERR;
+		i40iw_modify_qp(&cm_node->iwqp->ibqp, &attr, IB_QP_STATE, NULL);
+		i40iw_rem_ref_cm_node(cm_node);
+	}
+}
+
+/**
+ * i40iw_ifdown_notify - process an ifdown on an interface
+ * @iwdev: device pointer
+ * @ipaddr: Pointer to IPv4 or IPv6 address
+ * @ipv4: flag indicating IPv4 when true
+ * @ifup: flag indicating interface up when true
+ */
+void i40iw_if_notify(struct i40iw_device *iwdev, struct net_device *netdev,
+		     u32 *ipaddr, bool ipv4, bool ifup)
+{
+	struct i40iw_cm_core *cm_core = &iwdev->cm_core;
+	unsigned long flags;
+	struct i40iw_cm_listener *listen_node;
+	static const u32 ip_zero[4] = { 0, 0, 0, 0 };
+	struct i40iw_cm_info nfo;
+	u16 vlan_id = rdma_vlan_dev_vlan_id(netdev);
+	enum i40iw_status_code ret;
+	enum i40iw_quad_hash_manage_type op =
+		ifup ? I40IW_QHASH_MANAGE_TYPE_ADD : I40IW_QHASH_MANAGE_TYPE_DELETE;
+
+	/* Disable or enable qhash for listeners */
+	spin_lock_irqsave(&cm_core->listen_list_lock, flags);
+	list_for_each_entry(listen_node, &cm_core->listen_nodes, list) {
+		if (vlan_id == listen_node->vlan_id &&
+		    (!memcmp(listen_node->loc_addr, ipaddr, ipv4 ? 4 : 16) ||
+		    !memcmp(listen_node->loc_addr, ip_zero, ipv4 ? 4 : 16))) {
+			memcpy(nfo.loc_addr, listen_node->loc_addr,
+			       sizeof(nfo.loc_addr));
+			nfo.loc_port = listen_node->loc_port;
+			nfo.ipv4 = listen_node->ipv4;
+			nfo.vlan_id = listen_node->vlan_id;
+			nfo.user_pri = listen_node->user_pri;
+			if (!list_empty(&listen_node->child_listen_list)) {
+				i40iw_qhash_ctrl(iwdev,
+						 listen_node,
+						 &nfo,
+						 ipaddr, ipv4, ifup);
+			} else if (memcmp(listen_node->loc_addr, ip_zero,
+					  ipv4 ? 4 : 16)) {
+				ret = i40iw_manage_qhash(iwdev,
+							 &nfo,
+							 I40IW_QHASH_TYPE_TCP_SYN,
+							 op,
+							 NULL,
+							 false);
+				if (!ret)
+					listen_node->qhash_set = ifup;
+			}
+		}
+	}
+	spin_unlock_irqrestore(&cm_core->listen_list_lock, flags);
+
+	/* disconnect any connected qp's on ifdown */
+	if (!ifup)
+		i40iw_cm_disconnect_all(iwdev);
+}

drivers/infiniband/hw/i40iw/i40iw_cm.h

@@ -56,8 +56,6 @@
 
 #define I40IW_MAX_IETF_SIZE      32
 
-#define MPA_ZERO_PAD_LEN	4
-
 /* IETF RTR MSG Fields               */
 #define IETF_PEER_TO_PEER       0x8000
 #define IETF_FLPDU_ZERO_LEN     0x4000
@@ -299,6 +297,7 @@ struct i40iw_cm_listener {
 	enum i40iw_cm_listener_state listener_state;
 	u32 reused_node;
 	u8 user_pri;
+	u8 tos;
 	u16 vlan_id;
 	bool qhash_set;
 	bool ipv4;
@@ -341,9 +340,11 @@ struct i40iw_cm_node {
 	int accept_pend;
 	struct list_head timer_entry;
 	struct list_head reset_entry;
+	struct list_head connected_entry;
 	atomic_t passive_state;
 	bool qhash_set;
 	u8 user_pri;
+	u8 tos;
 	bool ipv4;
 	bool snd_mark_en;
 	u16 lsmm_size;
@@ -368,7 +369,8 @@ struct i40iw_cm_info {
 	u32 rem_addr[4];
 	u16 vlan_id;
 	int backlog;
-	u16 user_pri;
+	u8 user_pri;
+	u8 tos;
 	bool ipv4;
 };
 
@@ -445,4 +447,7 @@ int i40iw_arp_table(struct i40iw_device *iwdev,
 		    u8 *mac_addr,
 		    u32 action);
 
+void i40iw_if_notify(struct i40iw_device *iwdev, struct net_device *netdev,
+		     u32 *ipaddr, bool ipv4, bool ifup);
+void i40iw_cm_disconnect_all(struct i40iw_device *iwdev);
 #endif /* I40IW_CM_H */

drivers/infiniband/hw/i40iw/i40iw_ctrl.c

@@ -103,6 +103,7 @@ static enum i40iw_status_code i40iw_cqp_poll_registers(
 		if (newtail != tail) {
 			/* SUCCESS */
 			I40IW_RING_MOVE_TAIL(cqp->sq_ring);
+			cqp->dev->cqp_cmd_stats[OP_COMPLETED_COMMANDS]++;
 			return 0;
 		}
 		udelay(I40IW_SLEEP_COUNT);
@@ -222,6 +223,136 @@ static enum i40iw_status_code i40iw_sc_parse_fpm_query_buf(
 	return 0;
 }
 
+/**
+ * i40iw_fill_qos_list - Change all unknown qs handles to available ones
+ * @qs_list: list of qs_handles to be fixed with valid qs_handles
+ */
+static void i40iw_fill_qos_list(u16 *qs_list)
+{
+	u16 qshandle = qs_list[0];
+	int i;
+
+	for (i = 0; i < I40IW_MAX_USER_PRIORITY; i++) {
+		if (qs_list[i] == QS_HANDLE_UNKNOWN)
+			qs_list[i] = qshandle;
+		else
+			qshandle = qs_list[i];
+	}
+}
+
+/**
+ * i40iw_qp_from_entry - Given entry, get to the qp structure
+ * @entry: Points to list of qp structure
+ */
+static struct i40iw_sc_qp *i40iw_qp_from_entry(struct list_head *entry)
+{
+	if (!entry)
+		return NULL;
+
+	return (struct i40iw_sc_qp *)((char *)entry - offsetof(struct i40iw_sc_qp, list));
+}
+
+/**
+ * i40iw_get_qp - get the next qp from the list given current qp
+ * @head: Listhead of qp's
+ * @qp: current qp
+ */
+static struct i40iw_sc_qp *i40iw_get_qp(struct list_head *head, struct i40iw_sc_qp *qp)
+{
+	struct list_head *entry = NULL;
+	struct list_head *lastentry;
+
+	if (list_empty(head))
+		return NULL;
+
+	if (!qp) {
+		entry = head->next;
+	} else {
+		lastentry = &qp->list;
+		entry = (lastentry != head) ? lastentry->next : NULL;
+	}
+
+	return i40iw_qp_from_entry(entry);
+}
+
+/**
+ * i40iw_change_l2params - given the new l2 parameters, change all qp
+ * @vsi: pointer to the vsi structure
+ * @l2params: New paramaters from l2
+ */
+void i40iw_change_l2params(struct i40iw_sc_vsi *vsi, struct i40iw_l2params *l2params)
+{
+	struct i40iw_sc_dev *dev = vsi->dev;
+	struct i40iw_sc_qp *qp = NULL;
+	bool qs_handle_change = false;
+	bool mss_change = false;
+	unsigned long flags;
+	u16 qs_handle;
+	int i;
+
+	if (vsi->mss != l2params->mss) {
+		mss_change = true;
+		vsi->mss = l2params->mss;
+	}
+
+	i40iw_fill_qos_list(l2params->qs_handle_list);
+	for (i = 0; i < I40IW_MAX_USER_PRIORITY; i++) {
+		qs_handle = l2params->qs_handle_list[i];
+		if (vsi->qos[i].qs_handle != qs_handle)
+			qs_handle_change = true;
+		else if (!mss_change)
+			continue;       /* no MSS nor qs handle change */
+		spin_lock_irqsave(&vsi->qos[i].lock, flags);
+		qp = i40iw_get_qp(&vsi->qos[i].qplist, qp);
+		while (qp) {
+			if (mss_change)
+				i40iw_qp_mss_modify(dev, qp);
+			if (qs_handle_change) {
+				qp->qs_handle = qs_handle;
+				/* issue cqp suspend command */
+				i40iw_qp_suspend_resume(dev, qp, true);
+			}
+			qp = i40iw_get_qp(&vsi->qos[i].qplist, qp);
+		}
+		spin_unlock_irqrestore(&vsi->qos[i].lock, flags);
+		vsi->qos[i].qs_handle = qs_handle;
+	}
+}
+
+/**
+ * i40iw_qp_rem_qos - remove qp from qos lists during destroy qp
+ * @qp: qp to be removed from qos
+ */
+static void i40iw_qp_rem_qos(struct i40iw_sc_qp *qp)
+{
+	struct i40iw_sc_vsi *vsi = qp->vsi;
+	unsigned long flags;
+
+	if (!qp->on_qoslist)
+		return;
+	spin_lock_irqsave(&vsi->qos[qp->user_pri].lock, flags);
+	list_del(&qp->list);
+	spin_unlock_irqrestore(&vsi->qos[qp->user_pri].lock, flags);
+}
+
+/**
+ * i40iw_qp_add_qos - called during setctx fot qp to be added to qos
+ * @qp: qp to be added to qos
+ */
+void i40iw_qp_add_qos(struct i40iw_sc_qp *qp)
+{
+	struct i40iw_sc_vsi *vsi = qp->vsi;
+	unsigned long flags;
+
+	if (qp->on_qoslist)
+		return;
+	spin_lock_irqsave(&vsi->qos[qp->user_pri].lock, flags);
+	qp->qs_handle = vsi->qos[qp->user_pri].qs_handle;
+	list_add(&qp->list, &vsi->qos[qp->user_pri].qplist);
+	qp->on_qoslist = true;
+	spin_unlock_irqrestore(&vsi->qos[qp->user_pri].lock, flags);
+}
+
 /**
  * i40iw_sc_pd_init - initialize sc pd struct
  * @dev: sc device struct
@@ -292,6 +423,9 @@ static enum i40iw_status_code i40iw_sc_cqp_init(struct i40iw_sc_cqp *cqp,
 	info->dev->cqp = cqp;
 
 	I40IW_RING_INIT(cqp->sq_ring, cqp->sq_size);
+	cqp->dev->cqp_cmd_stats[OP_REQUESTED_COMMANDS] = 0;
+	cqp->dev->cqp_cmd_stats[OP_COMPLETED_COMMANDS] = 0;
+
 	i40iw_debug(cqp->dev, I40IW_DEBUG_WQE,
 		    "%s: sq_size[%04d] hw_sq_size[%04d] sq_base[%p] sq_pa[%llxh] cqp[%p] polarity[x%04X]\n",
 		    __func__, cqp->sq_size, cqp->hw_sq_size,
@@ -302,12 +436,10 @@ static enum i40iw_status_code i40iw_sc_cqp_init(struct i40iw_sc_cqp *cqp,
 /**
  * i40iw_sc_cqp_create - create cqp during bringup
  * @cqp: struct for cqp hw
- * @disable_pfpdus: if pfpdu to be disabled
  * @maj_err: If error, major err number
  * @min_err: If error, minor err number
  */
 static enum i40iw_status_code i40iw_sc_cqp_create(struct i40iw_sc_cqp *cqp,
-						  bool disable_pfpdus,
 						  u16 *maj_err,
 						  u16 *min_err)
 {
@@ -326,9 +458,6 @@ static enum i40iw_status_code i40iw_sc_cqp_create(struct i40iw_sc_cqp *cqp,
 	temp = LS_64(cqp->hw_sq_size, I40IW_CQPHC_SQSIZE) |
 	       LS_64(cqp->struct_ver, I40IW_CQPHC_SVER);
 
-	if (disable_pfpdus)
-		temp |= LS_64(1, I40IW_CQPHC_DISABLE_PFPDUS);
-
 	set_64bit_val(cqp->host_ctx, 0, temp);
 	set_64bit_val(cqp->host_ctx, 8, cqp->sq_pa);
 	temp = LS_64(cqp->enabled_vf_count, I40IW_CQPHC_ENABLED_VFS) |
@@ -424,6 +553,7 @@ u64 *i40iw_sc_cqp_get_next_send_wqe(struct i40iw_sc_cqp *cqp, u64 scratch)
 		return NULL;
 	}
 	I40IW_ATOMIC_RING_MOVE_HEAD(cqp->sq_ring, wqe_idx, ret_code);
+	cqp->dev->cqp_cmd_stats[OP_REQUESTED_COMMANDS]++;
 	if (ret_code)
 		return NULL;
 	if (!wqe_idx)
@@ -559,6 +689,8 @@ static enum i40iw_status_code i40iw_sc_ccq_get_cqe_info(
 		      I40IW_RING_GETCURRENT_HEAD(ccq->cq_uk.cq_ring));
 	wmb(); /* write shadow area before tail */
 	I40IW_RING_MOVE_TAIL(cqp->sq_ring);
+	ccq->dev->cqp_cmd_stats[OP_COMPLETED_COMMANDS]++;
+
 	return ret_code;
 }
 
@@ -1051,6 +1183,7 @@ static enum i40iw_status_code i40iw_sc_manage_qhash_table_entry(
 	u64 qw1 = 0;
 	u64 qw2 = 0;
 	u64 temp;
+	struct i40iw_sc_vsi *vsi = info->vsi;
 
 	wqe = i40iw_sc_cqp_get_next_send_wqe(cqp, scratch);
 	if (!wqe)
@@ -1082,7 +1215,7 @@ static enum i40iw_status_code i40iw_sc_manage_qhash_table_entry(
 			      LS_64(info->dest_ip[2], I40IW_CQPSQ_QHASH_ADDR2) |
 			      LS_64(info->dest_ip[3], I40IW_CQPSQ_QHASH_ADDR3));
 	}
-	qw2 = LS_64(cqp->dev->qs_handle, I40IW_CQPSQ_QHASH_QS_HANDLE);
+	qw2 = LS_64(vsi->qos[info->user_pri].qs_handle, I40IW_CQPSQ_QHASH_QS_HANDLE);
 	if (info->vlan_valid)
 		qw2 |= LS_64(info->vlan_id, I40IW_CQPSQ_QHASH_VLANID);
 	set_64bit_val(wqe, 16, qw2);
@@ -2103,6 +2236,7 @@ static enum i40iw_status_code i40iw_sc_qp_init(struct i40iw_sc_qp *qp,
 	u32 offset;
 
 	qp->dev = info->pd->dev;
+	qp->vsi = info->vsi;
 	qp->sq_pa = info->sq_pa;
 	qp->rq_pa = info->rq_pa;
 	qp->hw_host_ctx_pa = info->host_ctx_pa;
@@ -2151,7 +2285,7 @@ static enum i40iw_status_code i40iw_sc_qp_init(struct i40iw_sc_qp *qp,
 	qp->rq_tph_en = info->rq_tph_en;
 	qp->rcv_tph_en = info->rcv_tph_en;
 	qp->xmit_tph_en = info->xmit_tph_en;
-	qp->qs_handle = qp->pd->dev->qs_handle;
+	qp->qs_handle = qp->vsi->qos[qp->user_pri].qs_handle;
 	qp->exception_lan_queue = qp->pd->dev->exception_lan_queue;
 
 	return 0;
@@ -2296,6 +2430,7 @@ static enum i40iw_status_code i40iw_sc_qp_destroy(
 	struct i40iw_sc_cqp *cqp;
 	u64 header;
 
+	i40iw_qp_rem_qos(qp);
 	cqp = qp->pd->dev->cqp;
 	wqe = i40iw_sc_cqp_get_next_send_wqe(cqp, scratch);
 	if (!wqe)
@@ -2443,10 +2578,20 @@ static enum i40iw_status_code i40iw_sc_qp_setctx(
 {
 	struct i40iwarp_offload_info *iw;
 	struct i40iw_tcp_offload_info *tcp;
+	struct i40iw_sc_vsi *vsi;
+	struct i40iw_sc_dev *dev;
 	u64 qw0, qw3, qw7 = 0;
 
 	iw = info->iwarp_info;
 	tcp = info->tcp_info;
+	vsi = qp->vsi;
+	dev = qp->dev;
+	if (info->add_to_qoslist) {
+		qp->user_pri = info->user_pri;
+		i40iw_qp_add_qos(qp);
+		i40iw_debug(qp->dev, I40IW_DEBUG_DCB, "%s qp[%d] UP[%d] qset[%d]\n",
+			    __func__, qp->qp_uk.qp_id, qp->user_pri, qp->qs_handle);
+	}
 	qw0 = LS_64(qp->qp_uk.rq_wqe_size, I40IWQPC_RQWQESIZE) |
 	      LS_64(info->err_rq_idx_valid, I40IWQPC_ERR_RQ_IDX_VALID) |
 	      LS_64(qp->rcv_tph_en, I40IWQPC_RCVTPHEN) |
@@ -2487,16 +2632,14 @@ static enum i40iw_status_code i40iw_sc_qp_setctx(
 		       LS_64(iw->rdmap_ver, I40IWQPC_RDMAP_VER);
 
 		qw7 |= LS_64(iw->pd_id, I40IWQPC_PDIDX);
-		set_64bit_val(qp_ctx, 144, qp->q2_pa);
+		set_64bit_val(qp_ctx,
+			      144,
+			      LS_64(qp->q2_pa, I40IWQPC_Q2ADDR) |
+			      LS_64(vsi->fcn_id, I40IWQPC_STAT_INDEX));
 		set_64bit_val(qp_ctx,
 			      152,
 			      LS_64(iw->last_byte_sent, I40IWQPC_LASTBYTESENT));
 
-		/*
-		* Hard-code IRD_SIZE to hw-limit, 128, in qpctx, i.e matching an
-		*advertisable IRD of 64
-		*/
-		iw->ird_size = I40IW_QPCTX_ENCD_MAXIRD;
 		set_64bit_val(qp_ctx,
 			      160,
 			      LS_64(iw->ord_size, I40IWQPC_ORDSIZE) |
@@ -2507,6 +2650,9 @@ static enum i40iw_status_code i40iw_sc_qp_setctx(
 			      LS_64(iw->bind_en, I40IWQPC_BINDEN) |
 			      LS_64(iw->fast_reg_en, I40IWQPC_FASTREGEN) |
 			      LS_64(iw->priv_mode_en, I40IWQPC_PRIVEN) |
+			      LS_64((((vsi->stats_fcn_id_alloc) &&
+				      (dev->is_pf) && (vsi->fcn_id >= I40IW_FIRST_NON_PF_STAT)) ? 1 : 0),
+				    I40IWQPC_USESTATSINSTANCE) |
 			      LS_64(1, I40IWQPC_IWARPMODE) |
 			      LS_64(iw->rcv_mark_en, I40IWQPC_RCVMARKERS) |
 			      LS_64(iw->align_hdrs, I40IWQPC_ALIGNHDRS) |
@@ -2623,7 +2769,9 @@ static enum i40iw_status_code i40iw_sc_alloc_stag(
 	u64 *wqe;
 	struct i40iw_sc_cqp *cqp;
 	u64 header;
+	enum i40iw_page_size page_size;
 
+	page_size = (info->page_size == 0x200000) ? I40IW_PAGE_SIZE_2M : I40IW_PAGE_SIZE_4K;
 	cqp = dev->cqp;
 	wqe = i40iw_sc_cqp_get_next_send_wqe(cqp, scratch);
 	if (!wqe)
@@ -2643,7 +2791,7 @@ static enum i40iw_status_code i40iw_sc_alloc_stag(
 		 LS_64(1, I40IW_CQPSQ_STAG_MR) |
 		 LS_64(info->access_rights, I40IW_CQPSQ_STAG_ARIGHTS) |
 		 LS_64(info->chunk_size, I40IW_CQPSQ_STAG_LPBLSIZE) |
-		 LS_64(info->page_size, I40IW_CQPSQ_STAG_HPAGESIZE) |
+		 LS_64(page_size, I40IW_CQPSQ_STAG_HPAGESIZE) |
 		 LS_64(info->remote_access, I40IW_CQPSQ_STAG_REMACCENABLED) |
 		 LS_64(info->use_hmc_fcn_index, I40IW_CQPSQ_STAG_USEHMCFNIDX) |
 		 LS_64(info->use_pf_rid, I40IW_CQPSQ_STAG_USEPFRID) |
@@ -2679,7 +2827,9 @@ static enum i40iw_status_code i40iw_sc_mr_reg_non_shared(
 	u32 pble_obj_cnt;
 	bool remote_access;
 	u8 addr_type;
+	enum i40iw_page_size page_size;
 
+	page_size = (info->page_size == 0x200000) ? I40IW_PAGE_SIZE_2M : I40IW_PAGE_SIZE_4K;
 	if (info->access_rights & (I40IW_ACCESS_FLAGS_REMOTEREAD_ONLY |
 				   I40IW_ACCESS_FLAGS_REMOTEWRITE_ONLY))
 		remote_access = true;
@@ -2722,7 +2872,7 @@ static enum i40iw_status_code i40iw_sc_mr_reg_non_shared(
 	header = LS_64(I40IW_CQP_OP_REG_MR, I40IW_CQPSQ_OPCODE) |
 		 LS_64(1, I40IW_CQPSQ_STAG_MR) |
 		 LS_64(info->chunk_size, I40IW_CQPSQ_STAG_LPBLSIZE) |
-		 LS_64(info->page_size, I40IW_CQPSQ_STAG_HPAGESIZE) |
+		 LS_64(page_size, I40IW_CQPSQ_STAG_HPAGESIZE) |
 		 LS_64(info->access_rights, I40IW_CQPSQ_STAG_ARIGHTS) |
 		 LS_64(remote_access, I40IW_CQPSQ_STAG_REMACCENABLED) |
 		 LS_64(addr_type, I40IW_CQPSQ_STAG_VABASEDTO) |
@@ -2937,7 +3087,9 @@ enum i40iw_status_code i40iw_sc_mr_fast_register(
 	u64 temp, header;
 	u64 *wqe;
 	u32 wqe_idx;
+	enum i40iw_page_size page_size;
 
+	page_size = (info->page_size == 0x200000) ? I40IW_PAGE_SIZE_2M : I40IW_PAGE_SIZE_4K;
 	wqe = i40iw_qp_get_next_send_wqe(&qp->qp_uk, &wqe_idx, I40IW_QP_WQE_MIN_SIZE,
 					 0, info->wr_id);
 	if (!wqe)
@@ -2964,7 +3116,7 @@ enum i40iw_status_code i40iw_sc_mr_fast_register(
 		 LS_64(info->stag_idx, I40IWQPSQ_STAGINDEX) |
 		 LS_64(I40IWQP_OP_FAST_REGISTER, I40IWQPSQ_OPCODE) |
 		 LS_64(info->chunk_size, I40IWQPSQ_LPBLSIZE) |
-		 LS_64(info->page_size, I40IWQPSQ_HPAGESIZE) |
+		 LS_64(page_size, I40IWQPSQ_HPAGESIZE) |
 		 LS_64(info->access_rights, I40IWQPSQ_STAGRIGHTS) |
 		 LS_64(info->addr_type, I40IWQPSQ_VABASEDTO) |
 		 LS_64(info->read_fence, I40IWQPSQ_READFENCE) |
@@ -3959,7 +4111,7 @@ enum i40iw_status_code i40iw_process_cqp_cmd(struct i40iw_sc_dev *dev,
 					     struct cqp_commands_info *pcmdinfo)
 {
 	enum i40iw_status_code status = 0;
-	unsigned long	flags;
+	unsigned long flags;
 
 	spin_lock_irqsave(&dev->cqp_lock, flags);
 	if (list_empty(&dev->cqp_cmd_head) && !i40iw_ring_full(dev->cqp))
@@ -3978,7 +4130,7 @@ enum i40iw_status_code i40iw_process_bh(struct i40iw_sc_dev *dev)
 {
 	enum i40iw_status_code status = 0;
 	struct cqp_commands_info *pcmdinfo;
-	unsigned long	flags;
+	unsigned long flags;
 
 	spin_lock_irqsave(&dev->cqp_lock, flags);
 	while (!list_empty(&dev->cqp_cmd_head) && !i40iw_ring_full(dev->cqp)) {
@@ -4055,7 +4207,6 @@ static int i40iw_bld_terminate_hdr(struct i40iw_sc_qp *qp,
 	u16 ddp_seg_len;
 	int copy_len = 0;
 	u8 is_tagged = 0;
-	enum i40iw_flush_opcode flush_code = FLUSH_INVALID;
 	u32 opcode;
 	struct i40iw_terminate_hdr *termhdr;
 
@@ -4228,9 +4379,6 @@ static int i40iw_bld_terminate_hdr(struct i40iw_sc_qp *qp,
 	if (copy_len)
 		memcpy(termhdr + 1, pkt, copy_len);
 
-	if (flush_code && !info->in_rdrsp_wr)
-		qp->sq_flush = (info->sq) ? true : false;
-
 	return sizeof(struct i40iw_terminate_hdr) + copy_len;
 }
 
@@ -4321,286 +4469,370 @@ void i40iw_terminate_received(struct i40iw_sc_qp *qp, struct i40iw_aeqe_info *in
 }
 
 /**
- * i40iw_hw_stat_init - Initiliaze HW stats table
- * @devstat: pestat struct
+ * i40iw_sc_vsi_init - Initialize virtual device
+ * @vsi: pointer to the vsi structure
+ * @info: parameters to initialize vsi
+ **/
+void i40iw_sc_vsi_init(struct i40iw_sc_vsi *vsi, struct i40iw_vsi_init_info *info)
+{
+	int i;
+
+	vsi->dev = info->dev;
+	vsi->back_vsi = info->back_vsi;
+	vsi->mss = info->params->mss;
+	i40iw_fill_qos_list(info->params->qs_handle_list);
+
+	for (i = 0; i < I40IW_MAX_USER_PRIORITY; i++) {
+		vsi->qos[i].qs_handle =
+			info->params->qs_handle_list[i];
+			i40iw_debug(vsi->dev, I40IW_DEBUG_DCB, "qset[%d]: %d\n", i, vsi->qos[i].qs_handle);
+		spin_lock_init(&vsi->qos[i].lock);
+		INIT_LIST_HEAD(&vsi->qos[i].qplist);
+	}
+}
+
+/**
+ * i40iw_hw_stats_init - Initiliaze HW stats table
+ * @stats: pestat struct
  * @fcn_idx: PCI fn id
- * @hw: PF i40iw_hw structure.
  * @is_pf: Is it a PF?
  *
- * Populate the HW stat table with register offset addr for each
- * stat. And start the perioidic stats timer.
+ * Populate the HW stats table with register offset addr for each
+ * stats. And start the perioidic stats timer.
  */
-static void i40iw_hw_stat_init(struct i40iw_dev_pestat *devstat,
-			       u8 fcn_idx,
-			       struct i40iw_hw *hw, bool is_pf)
+void i40iw_hw_stats_init(struct i40iw_vsi_pestat *stats, u8 fcn_idx, bool is_pf)
 {
-	u32 stat_reg_offset;
-	u32 stat_index;
-	struct i40iw_dev_hw_stat_offsets *stat_table =
-		&devstat->hw_stat_offsets;
-	struct i40iw_dev_hw_stats *last_rd_stats = &devstat->last_read_hw_stats;
-
-	devstat->hw = hw;
+	u32 stats_reg_offset;
+	u32 stats_index;
+	struct i40iw_dev_hw_stats_offsets *stats_table =
+		&stats->hw_stats_offsets;
+	struct i40iw_dev_hw_stats *last_rd_stats = &stats->last_read_hw_stats;
 
 	if (is_pf) {
-		stat_table->stat_offset_32[I40IW_HW_STAT_INDEX_IP4RXDISCARD] =
+		stats_table->stats_offset_32[I40IW_HW_STAT_INDEX_IP4RXDISCARD] =
 				I40E_GLPES_PFIP4RXDISCARD(fcn_idx);
-		stat_table->stat_offset_32[I40IW_HW_STAT_INDEX_IP4RXTRUNC] =
+		stats_table->stats_offset_32[I40IW_HW_STAT_INDEX_IP4RXTRUNC] =
 				I40E_GLPES_PFIP4RXTRUNC(fcn_idx);
-		stat_table->stat_offset_32[I40IW_HW_STAT_INDEX_IP4TXNOROUTE] =
+		stats_table->stats_offset_32[I40IW_HW_STAT_INDEX_IP4TXNOROUTE] =
 				I40E_GLPES_PFIP4TXNOROUTE(fcn_idx);
-		stat_table->stat_offset_32[I40IW_HW_STAT_INDEX_IP6RXDISCARD] =
+		stats_table->stats_offset_32[I40IW_HW_STAT_INDEX_IP6RXDISCARD] =
 				I40E_GLPES_PFIP6RXDISCARD(fcn_idx);
-		stat_table->stat_offset_32[I40IW_HW_STAT_INDEX_IP6RXTRUNC] =
+		stats_table->stats_offset_32[I40IW_HW_STAT_INDEX_IP6RXTRUNC] =
 				I40E_GLPES_PFIP6RXTRUNC(fcn_idx);
-		stat_table->stat_offset_32[I40IW_HW_STAT_INDEX_IP6TXNOROUTE] =
+		stats_table->stats_offset_32[I40IW_HW_STAT_INDEX_IP6TXNOROUTE] =
 				I40E_GLPES_PFIP6TXNOROUTE(fcn_idx);
-		stat_table->stat_offset_32[I40IW_HW_STAT_INDEX_TCPRTXSEG] =
+		stats_table->stats_offset_32[I40IW_HW_STAT_INDEX_TCPRTXSEG] =
 				I40E_GLPES_PFTCPRTXSEG(fcn_idx);
-		stat_table->stat_offset_32[I40IW_HW_STAT_INDEX_TCPRXOPTERR] =
+		stats_table->stats_offset_32[I40IW_HW_STAT_INDEX_TCPRXOPTERR] =
 				I40E_GLPES_PFTCPRXOPTERR(fcn_idx);
-		stat_table->stat_offset_32[I40IW_HW_STAT_INDEX_TCPRXPROTOERR] =
+		stats_table->stats_offset_32[I40IW_HW_STAT_INDEX_TCPRXPROTOERR] =
 				I40E_GLPES_PFTCPRXPROTOERR(fcn_idx);
 
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP4RXOCTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP4RXOCTS] =
 				I40E_GLPES_PFIP4RXOCTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP4RXPKTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP4RXPKTS] =
 				I40E_GLPES_PFIP4RXPKTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP4RXFRAGS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP4RXFRAGS] =
 				I40E_GLPES_PFIP4RXFRAGSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP4RXMCPKTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP4RXMCPKTS] =
 				I40E_GLPES_PFIP4RXMCPKTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP4TXOCTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP4TXOCTS] =
 				I40E_GLPES_PFIP4TXOCTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP4TXPKTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP4TXPKTS] =
 				I40E_GLPES_PFIP4TXPKTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP4TXFRAGS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP4TXFRAGS] =
 				I40E_GLPES_PFIP4TXFRAGSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP4TXMCPKTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP4TXMCPKTS] =
 				I40E_GLPES_PFIP4TXMCPKTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP6RXOCTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP6RXOCTS] =
 				I40E_GLPES_PFIP6RXOCTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP6RXPKTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP6RXPKTS] =
 				I40E_GLPES_PFIP6RXPKTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP6RXFRAGS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP6RXFRAGS] =
 				I40E_GLPES_PFIP6RXFRAGSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP6RXMCPKTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP6RXMCPKTS] =
 				I40E_GLPES_PFIP6RXMCPKTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP6TXOCTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP6TXOCTS] =
 				I40E_GLPES_PFIP6TXOCTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP6TXPKTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP6TXPKTS] =
 				I40E_GLPES_PFIP6TXPKTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP6TXPKTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP6TXPKTS] =
 				I40E_GLPES_PFIP6TXPKTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP6TXFRAGS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP6TXFRAGS] =
 				I40E_GLPES_PFIP6TXFRAGSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_TCPRXSEGS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_TCPRXSEGS] =
 				I40E_GLPES_PFTCPRXSEGSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_TCPTXSEG] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_TCPTXSEG] =
 				I40E_GLPES_PFTCPTXSEGLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_RDMARXRDS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_RDMARXRDS] =
 				I40E_GLPES_PFRDMARXRDSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_RDMARXSNDS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_RDMARXSNDS] =
 				I40E_GLPES_PFRDMARXSNDSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_RDMARXWRS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_RDMARXWRS] =
 				I40E_GLPES_PFRDMARXWRSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_RDMATXRDS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_RDMATXRDS] =
 				I40E_GLPES_PFRDMATXRDSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_RDMATXSNDS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_RDMATXSNDS] =
 				I40E_GLPES_PFRDMATXSNDSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_RDMATXWRS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_RDMATXWRS] =
 				I40E_GLPES_PFRDMATXWRSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_RDMAVBND] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_RDMAVBND] =
 				I40E_GLPES_PFRDMAVBNDLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_RDMAVINV] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_RDMAVINV] =
 				I40E_GLPES_PFRDMAVINVLO(fcn_idx);
 	} else {
-		stat_table->stat_offset_32[I40IW_HW_STAT_INDEX_IP4RXDISCARD] =
+		stats_table->stats_offset_32[I40IW_HW_STAT_INDEX_IP4RXDISCARD] =
 				I40E_GLPES_VFIP4RXDISCARD(fcn_idx);
-		stat_table->stat_offset_32[I40IW_HW_STAT_INDEX_IP4RXTRUNC] =
+		stats_table->stats_offset_32[I40IW_HW_STAT_INDEX_IP4RXTRUNC] =
 				I40E_GLPES_VFIP4RXTRUNC(fcn_idx);
-		stat_table->stat_offset_32[I40IW_HW_STAT_INDEX_IP4TXNOROUTE] =
+		stats_table->stats_offset_32[I40IW_HW_STAT_INDEX_IP4TXNOROUTE] =
 				I40E_GLPES_VFIP4TXNOROUTE(fcn_idx);
-		stat_table->stat_offset_32[I40IW_HW_STAT_INDEX_IP6RXDISCARD] =
+		stats_table->stats_offset_32[I40IW_HW_STAT_INDEX_IP6RXDISCARD] =
 				I40E_GLPES_VFIP6RXDISCARD(fcn_idx);
-		stat_table->stat_offset_32[I40IW_HW_STAT_INDEX_IP6RXTRUNC] =
+		stats_table->stats_offset_32[I40IW_HW_STAT_INDEX_IP6RXTRUNC] =
 				I40E_GLPES_VFIP6RXTRUNC(fcn_idx);
-		stat_table->stat_offset_32[I40IW_HW_STAT_INDEX_IP6TXNOROUTE] =
+		stats_table->stats_offset_32[I40IW_HW_STAT_INDEX_IP6TXNOROUTE] =
 				I40E_GLPES_VFIP6TXNOROUTE(fcn_idx);
-		stat_table->stat_offset_32[I40IW_HW_STAT_INDEX_TCPRTXSEG] =
+		stats_table->stats_offset_32[I40IW_HW_STAT_INDEX_TCPRTXSEG] =
 				I40E_GLPES_VFTCPRTXSEG(fcn_idx);
-		stat_table->stat_offset_32[I40IW_HW_STAT_INDEX_TCPRXOPTERR] =
+		stats_table->stats_offset_32[I40IW_HW_STAT_INDEX_TCPRXOPTERR] =
 				I40E_GLPES_VFTCPRXOPTERR(fcn_idx);
-		stat_table->stat_offset_32[I40IW_HW_STAT_INDEX_TCPRXPROTOERR] =
+		stats_table->stats_offset_32[I40IW_HW_STAT_INDEX_TCPRXPROTOERR] =
 				I40E_GLPES_VFTCPRXPROTOERR(fcn_idx);
 
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP4RXOCTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP4RXOCTS] =
 				I40E_GLPES_VFIP4RXOCTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP4RXPKTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP4RXPKTS] =
 				I40E_GLPES_VFIP4RXPKTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP4RXFRAGS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP4RXFRAGS] =
 				I40E_GLPES_VFIP4RXFRAGSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP4RXMCPKTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP4RXMCPKTS] =
 				I40E_GLPES_VFIP4RXMCPKTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP4TXOCTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP4TXOCTS] =
 				I40E_GLPES_VFIP4TXOCTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP4TXPKTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP4TXPKTS] =
 				I40E_GLPES_VFIP4TXPKTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP4TXFRAGS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP4TXFRAGS] =
 				I40E_GLPES_VFIP4TXFRAGSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP4TXMCPKTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP4TXMCPKTS] =
 				I40E_GLPES_VFIP4TXMCPKTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP6RXOCTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP6RXOCTS] =
 				I40E_GLPES_VFIP6RXOCTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP6RXPKTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP6RXPKTS] =
 				I40E_GLPES_VFIP6RXPKTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP6RXFRAGS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP6RXFRAGS] =
 				I40E_GLPES_VFIP6RXFRAGSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP6RXMCPKTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP6RXMCPKTS] =
 				I40E_GLPES_VFIP6RXMCPKTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP6TXOCTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP6TXOCTS] =
 				I40E_GLPES_VFIP6TXOCTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP6TXPKTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP6TXPKTS] =
 				I40E_GLPES_VFIP6TXPKTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP6TXPKTS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP6TXPKTS] =
 				I40E_GLPES_VFIP6TXPKTSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_IP6TXFRAGS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_IP6TXFRAGS] =
 				I40E_GLPES_VFIP6TXFRAGSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_TCPRXSEGS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_TCPRXSEGS] =
 				I40E_GLPES_VFTCPRXSEGSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_TCPTXSEG] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_TCPTXSEG] =
 				I40E_GLPES_VFTCPTXSEGLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_RDMARXRDS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_RDMARXRDS] =
 				I40E_GLPES_VFRDMARXRDSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_RDMARXSNDS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_RDMARXSNDS] =
 				I40E_GLPES_VFRDMARXSNDSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_RDMARXWRS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_RDMARXWRS] =
 				I40E_GLPES_VFRDMARXWRSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_RDMATXRDS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_RDMATXRDS] =
 				I40E_GLPES_VFRDMATXRDSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_RDMATXSNDS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_RDMATXSNDS] =
 				I40E_GLPES_VFRDMATXSNDSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_RDMATXWRS] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_RDMATXWRS] =
 				I40E_GLPES_VFRDMATXWRSLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_RDMAVBND] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_RDMAVBND] =
 				I40E_GLPES_VFRDMAVBNDLO(fcn_idx);
-		stat_table->stat_offset_64[I40IW_HW_STAT_INDEX_RDMAVINV] =
+		stats_table->stats_offset_64[I40IW_HW_STAT_INDEX_RDMAVINV] =
 				I40E_GLPES_VFRDMAVINVLO(fcn_idx);
 	}
 
-	for (stat_index = 0; stat_index < I40IW_HW_STAT_INDEX_MAX_64;
-	     stat_index++) {
-		stat_reg_offset = stat_table->stat_offset_64[stat_index];
-		last_rd_stats->stat_value_64[stat_index] =
-			readq(devstat->hw->hw_addr + stat_reg_offset);
+	for (stats_index = 0; stats_index < I40IW_HW_STAT_INDEX_MAX_64;
+	     stats_index++) {
+		stats_reg_offset = stats_table->stats_offset_64[stats_index];
+		last_rd_stats->stats_value_64[stats_index] =
+			readq(stats->hw->hw_addr + stats_reg_offset);
 	}
 
-	for (stat_index = 0; stat_index < I40IW_HW_STAT_INDEX_MAX_32;
-	     stat_index++) {
-		stat_reg_offset = stat_table->stat_offset_32[stat_index];
-		last_rd_stats->stat_value_32[stat_index] =
-			i40iw_rd32(devstat->hw, stat_reg_offset);
+	for (stats_index = 0; stats_index < I40IW_HW_STAT_INDEX_MAX_32;
+	     stats_index++) {
+		stats_reg_offset = stats_table->stats_offset_32[stats_index];
+		last_rd_stats->stats_value_32[stats_index] =
+			i40iw_rd32(stats->hw, stats_reg_offset);
 	}
 }
 
 /**
- * i40iw_hw_stat_read_32 - Read 32-bit HW stat counters and accommodates for roll-overs.
- * @devstat: pestat struct
- * @index: index in HW stat table which contains offset reg-addr
- * @value: hw stat value
+ * i40iw_hw_stats_read_32 - Read 32-bit HW stats counters and accommodates for roll-overs.
+ * @stat: pestat struct
+ * @index: index in HW stats table which contains offset reg-addr
+ * @value: hw stats value
  */
-static void i40iw_hw_stat_read_32(struct i40iw_dev_pestat *devstat,
-				  enum i40iw_hw_stat_index_32b index,
-				  u64 *value)
+void i40iw_hw_stats_read_32(struct i40iw_vsi_pestat *stats,
+			    enum i40iw_hw_stats_index_32b index,
+			    u64 *value)
 {
-	struct i40iw_dev_hw_stat_offsets *stat_table =
-		&devstat->hw_stat_offsets;
-	struct i40iw_dev_hw_stats *last_rd_stats = &devstat->last_read_hw_stats;
-	struct i40iw_dev_hw_stats *hw_stats = &devstat->hw_stats;
-	u64 new_stat_value = 0;
-	u32 stat_reg_offset = stat_table->stat_offset_32[index];
-
-	new_stat_value = i40iw_rd32(devstat->hw, stat_reg_offset);
+	struct i40iw_dev_hw_stats_offsets *stats_table =
+		&stats->hw_stats_offsets;
+	struct i40iw_dev_hw_stats *last_rd_stats = &stats->last_read_hw_stats;
+	struct i40iw_dev_hw_stats *hw_stats = &stats->hw_stats;
+	u64 new_stats_value = 0;
+	u32 stats_reg_offset = stats_table->stats_offset_32[index];
+
+	new_stats_value = i40iw_rd32(stats->hw, stats_reg_offset);
 	/*roll-over case */
-	if (new_stat_value < last_rd_stats->stat_value_32[index])
-		hw_stats->stat_value_32[index] += new_stat_value;
+	if (new_stats_value < last_rd_stats->stats_value_32[index])
+		hw_stats->stats_value_32[index] += new_stats_value;
 	else
-		hw_stats->stat_value_32[index] +=
-			new_stat_value - last_rd_stats->stat_value_32[index];
-	last_rd_stats->stat_value_32[index] = new_stat_value;
-	*value = hw_stats->stat_value_32[index];
+		hw_stats->stats_value_32[index] +=
+			new_stats_value - last_rd_stats->stats_value_32[index];
+	last_rd_stats->stats_value_32[index] = new_stats_value;
+	*value = hw_stats->stats_value_32[index];
 }
 
 /**
- * i40iw_hw_stat_read_64 - Read HW stat counters (greater than 32-bit) and accommodates for roll-overs.
- * @devstat: pestat struct
- * @index: index in HW stat table which contains offset reg-addr
- * @value: hw stat value
+ * i40iw_hw_stats_read_64 - Read HW stats counters (greater than 32-bit) and accommodates for roll-overs.
+ * @stats: pestat struct
+ * @index: index in HW stats table which contains offset reg-addr
+ * @value: hw stats value
  */
-static void i40iw_hw_stat_read_64(struct i40iw_dev_pestat *devstat,
-				  enum i40iw_hw_stat_index_64b index,
-				  u64 *value)
+void i40iw_hw_stats_read_64(struct i40iw_vsi_pestat *stats,
+			    enum i40iw_hw_stats_index_64b index,
+			    u64 *value)
 {
-	struct i40iw_dev_hw_stat_offsets *stat_table =
-		&devstat->hw_stat_offsets;
-	struct i40iw_dev_hw_stats *last_rd_stats = &devstat->last_read_hw_stats;
-	struct i40iw_dev_hw_stats *hw_stats = &devstat->hw_stats;
-	u64 new_stat_value = 0;
-	u32 stat_reg_offset = stat_table->stat_offset_64[index];
-
-	new_stat_value = readq(devstat->hw->hw_addr + stat_reg_offset);
+	struct i40iw_dev_hw_stats_offsets *stats_table =
+		&stats->hw_stats_offsets;
+	struct i40iw_dev_hw_stats *last_rd_stats = &stats->last_read_hw_stats;
+	struct i40iw_dev_hw_stats *hw_stats = &stats->hw_stats;
+	u64 new_stats_value = 0;
+	u32 stats_reg_offset = stats_table->stats_offset_64[index];
+
+	new_stats_value = readq(stats->hw->hw_addr + stats_reg_offset);
 	/*roll-over case */
-	if (new_stat_value < last_rd_stats->stat_value_64[index])
-		hw_stats->stat_value_64[index] += new_stat_value;
+	if (new_stats_value < last_rd_stats->stats_value_64[index])
+		hw_stats->stats_value_64[index] += new_stats_value;
 	else
-		hw_stats->stat_value_64[index] +=
-			new_stat_value - last_rd_stats->stat_value_64[index];
-	last_rd_stats->stat_value_64[index] = new_stat_value;
-	*value = hw_stats->stat_value_64[index];
+		hw_stats->stats_value_64[index] +=
+			new_stats_value - last_rd_stats->stats_value_64[index];
+	last_rd_stats->stats_value_64[index] = new_stats_value;
+	*value = hw_stats->stats_value_64[index];
 }
 
 /**
- * i40iw_hw_stat_read_all - read all HW stat counters
- * @devstat: pestat struct
- * @stat_values: hw stats structure
+ * i40iw_hw_stats_read_all - read all HW stat counters
+ * @stats: pestat struct
+ * @stats_values: hw stats structure
  *
  * Read all the HW stat counters and populates hw_stats structure
- * of passed-in dev's pestat as well as copy created in stat_values.
+ * of passed-in vsi's pestat as well as copy created in stat_values.
  */
-static void i40iw_hw_stat_read_all(struct i40iw_dev_pestat *devstat,
-				   struct i40iw_dev_hw_stats *stat_values)
+void i40iw_hw_stats_read_all(struct i40iw_vsi_pestat *stats,
+			     struct i40iw_dev_hw_stats *stats_values)
 {
-	u32 stat_index;
-
-	for (stat_index = 0; stat_index < I40IW_HW_STAT_INDEX_MAX_32;
-	     stat_index++)
-		i40iw_hw_stat_read_32(devstat, stat_index,
-				      &stat_values->stat_value_32[stat_index]);
-	for (stat_index = 0; stat_index < I40IW_HW_STAT_INDEX_MAX_64;
-	     stat_index++)
-		i40iw_hw_stat_read_64(devstat, stat_index,
-				      &stat_values->stat_value_64[stat_index]);
+	u32 stats_index;
+	unsigned long flags;
+
+	spin_lock_irqsave(&stats->lock, flags);
+
+	for (stats_index = 0; stats_index < I40IW_HW_STAT_INDEX_MAX_32;
+	     stats_index++)
+		i40iw_hw_stats_read_32(stats, stats_index,
+				       &stats_values->stats_value_32[stats_index]);
+	for (stats_index = 0; stats_index < I40IW_HW_STAT_INDEX_MAX_64;
+	     stats_index++)
+		i40iw_hw_stats_read_64(stats, stats_index,
+				       &stats_values->stats_value_64[stats_index]);
+	spin_unlock_irqrestore(&stats->lock, flags);
 }
 
 /**
- * i40iw_hw_stat_refresh_all - Update all HW stat structs
- * @devstat: pestat struct
- * @stat_values: hw stats structure
+ * i40iw_hw_stats_refresh_all - Update all HW stats structs
+ * @stats: pestat struct
  *
- * Read all the HW stat counters to refresh values in hw_stats structure
+ * Read all the HW stats counters to refresh values in hw_stats structure
  * of passed-in dev's pestat
  */
-static void i40iw_hw_stat_refresh_all(struct i40iw_dev_pestat *devstat)
+void i40iw_hw_stats_refresh_all(struct i40iw_vsi_pestat *stats)
+{
+	u64 stats_value;
+	u32 stats_index;
+	unsigned long flags;
+
+	spin_lock_irqsave(&stats->lock, flags);
+
+	for (stats_index = 0; stats_index < I40IW_HW_STAT_INDEX_MAX_32;
+	     stats_index++)
+		i40iw_hw_stats_read_32(stats, stats_index, &stats_value);
+	for (stats_index = 0; stats_index < I40IW_HW_STAT_INDEX_MAX_64;
+	     stats_index++)
+		i40iw_hw_stats_read_64(stats, stats_index, &stats_value);
+	spin_unlock_irqrestore(&stats->lock, flags);
+}
+
+/**
+ * i40iw_get_fcn_id - Return the function id
+ * @dev: pointer to the device
+ */
+static u8 i40iw_get_fcn_id(struct i40iw_sc_dev *dev)
+{
+	u8 fcn_id = I40IW_INVALID_FCN_ID;
+	u8 i;
+
+	for (i = I40IW_FIRST_NON_PF_STAT; i < I40IW_MAX_STATS_COUNT; i++)
+		if (!dev->fcn_id_array[i]) {
+			fcn_id = i;
+			dev->fcn_id_array[i] = true;
+			break;
+		}
+	return fcn_id;
+}
+
+/**
+ * i40iw_vsi_stats_init - Initialize the vsi statistics
+ * @vsi: pointer to the vsi structure
+ * @info: The info structure used for initialization
+ */
+enum i40iw_status_code i40iw_vsi_stats_init(struct i40iw_sc_vsi *vsi, struct i40iw_vsi_stats_info *info)
 {
-	u64 stat_value;
-	u32 stat_index;
-
-	for (stat_index = 0; stat_index < I40IW_HW_STAT_INDEX_MAX_32;
-	     stat_index++)
-		i40iw_hw_stat_read_32(devstat, stat_index, &stat_value);
-	for (stat_index = 0; stat_index < I40IW_HW_STAT_INDEX_MAX_64;
-	     stat_index++)
-		i40iw_hw_stat_read_64(devstat, stat_index, &stat_value);
+	u8 fcn_id = info->fcn_id;
+
+	if (info->alloc_fcn_id)
+		fcn_id = i40iw_get_fcn_id(vsi->dev);
+
+	if (fcn_id == I40IW_INVALID_FCN_ID)
+		return I40IW_ERR_NOT_READY;
+
+	vsi->pestat = info->pestat;
+	vsi->pestat->hw = vsi->dev->hw;
+
+	if (info->stats_initialize) {
+		i40iw_hw_stats_init(vsi->pestat, fcn_id, true);
+		spin_lock_init(&vsi->pestat->lock);
+		i40iw_hw_stats_start_timer(vsi);
+	}
+	vsi->stats_fcn_id_alloc = info->alloc_fcn_id;
+	vsi->fcn_id = fcn_id;
+	return I40IW_SUCCESS;
+}
+
+/**
+ * i40iw_vsi_stats_free - Free the vsi stats
+ * @vsi: pointer to the vsi structure
+ */
+void i40iw_vsi_stats_free(struct i40iw_sc_vsi *vsi)
+{
+	u8 fcn_id = vsi->fcn_id;
+
+	if ((vsi->stats_fcn_id_alloc) && (fcn_id != I40IW_INVALID_FCN_ID))
+		vsi->dev->fcn_id_array[fcn_id] = false;
+	i40iw_hw_stats_stop_timer(vsi);
 }
 
 static struct i40iw_cqp_ops iw_cqp_ops = {
@@ -4711,24 +4943,6 @@ static struct i40iw_hmc_ops iw_hmc_ops = {
 	NULL
 };
 
-static const struct i40iw_device_pestat_ops iw_device_pestat_ops = {
-	i40iw_hw_stat_init,
-	i40iw_hw_stat_read_32,
-	i40iw_hw_stat_read_64,
-	i40iw_hw_stat_read_all,
-	i40iw_hw_stat_refresh_all
-};
-
-/**
- * i40iw_device_init_pestat - Initialize the pestat structure
- * @dev: pestat struct
- */
-enum i40iw_status_code i40iw_device_init_pestat(struct i40iw_dev_pestat *devstat)
-{
-	devstat->ops = iw_device_pestat_ops;
-	return 0;
-}
-
 /**
  * i40iw_device_init - Initialize IWARP device
  * @dev: IWARP device pointer
@@ -4750,14 +4964,7 @@ enum i40iw_status_code i40iw_device_init(struct i40iw_sc_dev *dev,
 
 	dev->debug_mask = info->debug_mask;
 
-	ret_code = i40iw_device_init_pestat(&dev->dev_pestat);
-	if (ret_code) {
-		i40iw_debug(dev, I40IW_DEBUG_DEV,
-			    "%s: i40iw_device_init_pestat failed\n", __func__);
-		return ret_code;
-	}
 	dev->hmc_fn_id = info->hmc_fn_id;
-	dev->qs_handle = info->qs_handle;
 	dev->exception_lan_queue = info->exception_lan_queue;
 	dev->is_pf = info->is_pf;
 
@@ -4770,15 +4977,10 @@ enum i40iw_status_code i40iw_device_init(struct i40iw_sc_dev *dev,
 	dev->hw = info->hw;
 	dev->hw->hw_addr = info->bar0;
 
-	val = i40iw_rd32(dev->hw, I40E_GLPCI_DREVID);
-	dev->hw_rev = (u8)RS_32(val, I40E_GLPCI_DREVID_DEFAULT_REVID);
-
 	if (dev->is_pf) {
-		dev->dev_pestat.ops.iw_hw_stat_init(&dev->dev_pestat,
-			dev->hmc_fn_id, dev->hw, true);
-		spin_lock_init(&dev->dev_pestat.stats_lock);
-		/*start the periodic stats_timer */
-		i40iw_hw_stats_start_timer(dev);
+		val = i40iw_rd32(dev->hw, I40E_GLPCI_DREVID);
+		dev->hw_rev = (u8)RS_32(val, I40E_GLPCI_DREVID_DEFAULT_REVID);
+
 		val = i40iw_rd32(dev->hw, I40E_GLPCI_LBARCTRL);
 		db_size = (u8)RS_32(val, I40E_GLPCI_LBARCTRL_PE_DB_SIZE);
 		if ((db_size != I40IW_PE_DB_SIZE_4M) &&

drivers/infiniband/hw/i40iw/i40iw_d.h

@@ -35,6 +35,8 @@
 #ifndef I40IW_D_H
 #define I40IW_D_H
 
+#define I40IW_FIRST_USER_QP_ID  2
+
 #define I40IW_DB_ADDR_OFFSET    (4 * 1024 * 1024 - 64 * 1024)
 #define I40IW_VF_DB_ADDR_OFFSET (64 * 1024)
 
@@ -67,6 +69,9 @@
 #define I40IW_STAG_TYPE_NONSHARED 1
 
 #define I40IW_MAX_USER_PRIORITY 8
+#define I40IW_MAX_STATS_COUNT 16
+#define I40IW_FIRST_NON_PF_STAT	4
+
 
 #define LS_64_1(val, bits)      ((u64)(uintptr_t)val << bits)
 #define RS_64_1(val, bits)      ((u64)(uintptr_t)val >> bits)
@@ -74,6 +79,8 @@
 #define RS_32_1(val, bits)      (u32)(val >> bits)
 #define I40E_HI_DWORD(x)        ((u32)((((x) >> 16) >> 16) & 0xFFFFFFFF))
 
+#define QS_HANDLE_UNKNOWN       0xffff
+
 #define LS_64(val, field) (((u64)val << field ## _SHIFT) & (field ## _MASK))
 
 #define RS_64(val, field) ((u64)(val & field ## _MASK) >> field ## _SHIFT)
@@ -1199,8 +1206,11 @@
 #define I40IWQPC_RXCQNUM_SHIFT 32
 #define I40IWQPC_RXCQNUM_MASK (0x1ffffULL << I40IWQPC_RXCQNUM_SHIFT)
 
-#define I40IWQPC_Q2ADDR_SHIFT I40IW_CQPHC_QPCTX_SHIFT
-#define I40IWQPC_Q2ADDR_MASK I40IW_CQPHC_QPCTX_MASK
+#define I40IWQPC_STAT_INDEX_SHIFT 0
+#define I40IWQPC_STAT_INDEX_MASK (0x1fULL << I40IWQPC_STAT_INDEX_SHIFT)
+
+#define I40IWQPC_Q2ADDR_SHIFT 0
+#define I40IWQPC_Q2ADDR_MASK (0xffffffffffffff00ULL << I40IWQPC_Q2ADDR_SHIFT)
 
 #define I40IWQPC_LASTBYTESENT_SHIFT 0
 #define I40IWQPC_LASTBYTESENT_MASK (0xffUL << I40IWQPC_LASTBYTESENT_SHIFT)
@@ -1232,11 +1242,8 @@
 #define I40IWQPC_PRIVEN_SHIFT 25
 #define I40IWQPC_PRIVEN_MASK (1UL << I40IWQPC_PRIVEN_SHIFT)
 
-#define I40IWQPC_LSMMPRESENT_SHIFT 26
-#define I40IWQPC_LSMMPRESENT_MASK (1UL << I40IWQPC_LSMMPRESENT_SHIFT)
-
-#define I40IWQPC_ADJUSTFORLSMM_SHIFT 27
-#define I40IWQPC_ADJUSTFORLSMM_MASK (1UL << I40IWQPC_ADJUSTFORLSMM_SHIFT)
+#define I40IWQPC_USESTATSINSTANCE_SHIFT 26
+#define I40IWQPC_USESTATSINSTANCE_MASK (1UL << I40IWQPC_USESTATSINSTANCE_SHIFT)
 
 #define I40IWQPC_IWARPMODE_SHIFT 28
 #define I40IWQPC_IWARPMODE_MASK (1UL << I40IWQPC_IWARPMODE_SHIFT)
@@ -1713,6 +1720,8 @@ enum i40iw_alignment {
 #define OP_MANAGE_VF_PBLE_BP                    28
 #define OP_QUERY_FPM_VALUES                     29
 #define OP_COMMIT_FPM_VALUES                    30
-#define OP_SIZE_CQP_STAT_ARRAY                  31
+#define OP_REQUESTED_COMMANDS                   31
+#define OP_COMPLETED_COMMANDS                   32
+#define OP_SIZE_CQP_STAT_ARRAY                  33
 
 #endif

drivers/infiniband/hw/i40iw/i40iw_hw.c

@@ -62,7 +62,7 @@ u32 i40iw_initialize_hw_resources(struct i40iw_device *iwdev)
 	max_mr = iwdev->sc_dev.hmc_info->hmc_obj[I40IW_HMC_IW_MR].cnt;
 	arp_table_size = iwdev->sc_dev.hmc_info->hmc_obj[I40IW_HMC_IW_ARP].cnt;
 	iwdev->max_cqe = 0xFFFFF;
-	num_pds = max_qp * 4;
+	num_pds = I40IW_MAX_PDS;
 	resources_size = sizeof(struct i40iw_arp_entry) * arp_table_size;
 	resources_size += sizeof(unsigned long) * BITS_TO_LONGS(max_qp);
 	resources_size += sizeof(unsigned long) * BITS_TO_LONGS(max_mr);
@@ -308,7 +308,9 @@ void i40iw_process_aeq(struct i40iw_device *iwdev)
 			iwqp = iwdev->qp_table[info->qp_cq_id];
 			if (!iwqp) {
 				spin_unlock_irqrestore(&iwdev->qptable_lock, flags);
-				i40iw_pr_err("qp_id %d is already freed\n", info->qp_cq_id);
+				i40iw_debug(dev, I40IW_DEBUG_AEQ,
+					    "%s qp_id %d is already freed\n",
+					    __func__, info->qp_cq_id);
 				continue;
 			}
 			i40iw_add_ref(&iwqp->ibqp);
@@ -359,6 +361,9 @@ void i40iw_process_aeq(struct i40iw_device *iwdev)
 				continue;
 			i40iw_cm_disconn(iwqp);
 			break;
+		case I40IW_AE_QP_SUSPEND_COMPLETE:
+			i40iw_qp_suspend_resume(dev, &iwqp->sc_qp, false);
+			break;
 		case I40IW_AE_TERMINATE_SENT:
 			i40iw_terminate_send_fin(qp);
 			break;
@@ -404,19 +409,18 @@ void i40iw_process_aeq(struct i40iw_device *iwdev)
 		case I40IW_AE_LCE_CQ_CATASTROPHIC:
 		case I40IW_AE_UDA_XMIT_DGRAM_TOO_LONG:
 		case I40IW_AE_UDA_XMIT_IPADDR_MISMATCH:
-		case I40IW_AE_QP_SUSPEND_COMPLETE:
 			ctx_info->err_rq_idx_valid = false;
 		default:
-				if (!info->sq && ctx_info->err_rq_idx_valid) {
-					ctx_info->err_rq_idx = info->wqe_idx;
-					ctx_info->tcp_info_valid = false;
-					ctx_info->iwarp_info_valid = false;
-					ret = dev->iw_priv_qp_ops->qp_setctx(&iwqp->sc_qp,
-									     iwqp->host_ctx.va,
-									     ctx_info);
-				}
-				i40iw_terminate_connection(qp, info);
-				break;
+			if (!info->sq && ctx_info->err_rq_idx_valid) {
+				ctx_info->err_rq_idx = info->wqe_idx;
+				ctx_info->tcp_info_valid = false;
+				ctx_info->iwarp_info_valid = false;
+				ret = dev->iw_priv_qp_ops->qp_setctx(&iwqp->sc_qp,
+								     iwqp->host_ctx.va,
+								     ctx_info);
+			}
+			i40iw_terminate_connection(qp, info);
+			break;
 		}
 		if (info->qp)
 			i40iw_rem_ref(&iwqp->ibqp);
@@ -538,6 +542,7 @@ enum i40iw_status_code i40iw_manage_qhash(struct i40iw_device *iwdev,
 {
 	struct i40iw_qhash_table_info *info;
 	struct i40iw_sc_dev *dev = &iwdev->sc_dev;
+	struct i40iw_sc_vsi *vsi = &iwdev->vsi;
 	enum i40iw_status_code status;
 	struct i40iw_cqp *iwcqp = &iwdev->cqp;
 	struct i40iw_cqp_request *cqp_request;
@@ -550,6 +555,7 @@ enum i40iw_status_code i40iw_manage_qhash(struct i40iw_device *iwdev,
 	info = &cqp_info->in.u.manage_qhash_table_entry.info;
 	memset(info, 0, sizeof(*info));
 
+	info->vsi = &iwdev->vsi;
 	info->manage = mtype;
 	info->entry_type = etype;
 	if (cminfo->vlan_id != 0xFFFF) {
@@ -560,8 +566,9 @@ enum i40iw_status_code i40iw_manage_qhash(struct i40iw_device *iwdev,
 	}
 
 	info->ipv4_valid = cminfo->ipv4;
+	info->user_pri = cminfo->user_pri;
 	ether_addr_copy(info->mac_addr, iwdev->netdev->dev_addr);
-	info->qp_num = cpu_to_le32(dev->ilq->qp_id);
+	info->qp_num = cpu_to_le32(vsi->ilq->qp_id);
 	info->dest_port = cpu_to_le16(cminfo->loc_port);
 	info->dest_ip[0] = cpu_to_le32(cminfo->loc_addr[0]);
 	info->dest_ip[1] = cpu_to_le32(cminfo->loc_addr[1]);
@@ -617,6 +624,7 @@ enum i40iw_status_code i40iw_hw_flush_wqes(struct i40iw_device *iwdev,
 	struct i40iw_qp_flush_info *hw_info;
 	struct i40iw_cqp_request *cqp_request;
 	struct cqp_commands_info *cqp_info;
+	struct i40iw_qp *iwqp = (struct i40iw_qp *)qp->back_qp;
 
 	cqp_request = i40iw_get_cqp_request(&iwdev->cqp, wait);
 	if (!cqp_request)
@@ -631,9 +639,30 @@ enum i40iw_status_code i40iw_hw_flush_wqes(struct i40iw_device *iwdev,
 	cqp_info->in.u.qp_flush_wqes.qp = qp;
 	cqp_info->in.u.qp_flush_wqes.scratch = (uintptr_t)cqp_request;
 	status = i40iw_handle_cqp_op(iwdev, cqp_request);
-	if (status)
+	if (status) {
 		i40iw_pr_err("CQP-OP Flush WQE's fail");
-	return status;
+		complete(&iwqp->sq_drained);
+		complete(&iwqp->rq_drained);
+		return status;
+	}
+	if (!cqp_request->compl_info.maj_err_code) {
+		switch (cqp_request->compl_info.min_err_code) {
+		case I40IW_CQP_COMPL_RQ_WQE_FLUSHED:
+			complete(&iwqp->sq_drained);
+			break;
+		case I40IW_CQP_COMPL_SQ_WQE_FLUSHED:
+			complete(&iwqp->rq_drained);
+			break;
+		case I40IW_CQP_COMPL_RQ_SQ_WQE_FLUSHED:
+			break;
+		default:
+			complete(&iwqp->sq_drained);
+			complete(&iwqp->rq_drained);
+			break;
+		}
+	}
+
+	return 0;
 }
 
 /**

drivers/infiniband/hw/i40iw/i40iw_main.c

@@ -237,14 +237,11 @@ static irqreturn_t i40iw_irq_handler(int irq, void *data)
  */
 static void i40iw_destroy_cqp(struct i40iw_device *iwdev, bool free_hwcqp)
 {
-	enum i40iw_status_code status = 0;
 	struct i40iw_sc_dev *dev = &iwdev->sc_dev;
 	struct i40iw_cqp *cqp = &iwdev->cqp;
 
-	if (free_hwcqp && dev->cqp_ops->cqp_destroy)
-		status = dev->cqp_ops->cqp_destroy(dev->cqp);
-	if (status)
-		i40iw_pr_err("destroy cqp failed");
+	if (free_hwcqp)
+		dev->cqp_ops->cqp_destroy(dev->cqp);
 
 	i40iw_free_dma_mem(dev->hw, &cqp->sq);
 	kfree(cqp->scratch_array);
@@ -270,6 +267,7 @@ static void i40iw_disable_irq(struct i40iw_sc_dev *dev,
 		i40iw_wr32(dev->hw, I40E_PFINT_DYN_CTLN(msix_vec->idx - 1), 0);
 	else
 		i40iw_wr32(dev->hw, I40E_VFINT_DYN_CTLN1(msix_vec->idx - 1), 0);
+	irq_set_affinity_hint(msix_vec->irq, NULL);
 	free_irq(msix_vec->irq, dev_id);
 }
 
@@ -603,7 +601,7 @@ static enum i40iw_status_code i40iw_create_cqp(struct i40iw_device *iwdev)
 		i40iw_pr_err("cqp init status %d\n", status);
 		goto exit;
 	}
-	status = dev->cqp_ops->cqp_create(dev->cqp, true, &maj_err, &min_err);
+	status = dev->cqp_ops->cqp_create(dev->cqp, &maj_err, &min_err);
 	if (status) {
 		i40iw_pr_err("cqp create status %d maj_err %d min_err %d\n",
 			     status, maj_err, min_err);
@@ -688,6 +686,7 @@ static enum i40iw_status_code i40iw_configure_ceq_vector(struct i40iw_device *iw
 							 struct i40iw_msix_vector *msix_vec)
 {
 	enum i40iw_status_code status;
+	cpumask_t mask;
 
 	if (iwdev->msix_shared && !ceq_id) {
 		tasklet_init(&iwdev->dpc_tasklet, i40iw_dpc, (unsigned long)iwdev);
@@ -697,12 +696,15 @@ static enum i40iw_status_code i40iw_configure_ceq_vector(struct i40iw_device *iw
 		status = request_irq(msix_vec->irq, i40iw_ceq_handler, 0, "CEQ", iwceq);
 	}
 
+	cpumask_clear(&mask);
+	cpumask_set_cpu(msix_vec->cpu_affinity, &mask);
+	irq_set_affinity_hint(msix_vec->irq, &mask);
+
 	if (status) {
 		i40iw_pr_err("ceq irq config fail\n");
 		return I40IW_ERR_CONFIG;
 	}
 	msix_vec->ceq_id = ceq_id;
-	msix_vec->cpu_affinity = 0;
 
 	return 0;
 }
@@ -930,6 +932,7 @@ static enum i40iw_status_code i40iw_initialize_ilq(struct i40iw_device *iwdev)
 	struct i40iw_puda_rsrc_info info;
 	enum i40iw_status_code status;
 
+	memset(&info, 0, sizeof(info));
 	info.type = I40IW_PUDA_RSRC_TYPE_ILQ;
 	info.cq_id = 1;
 	info.qp_id = 0;
@@ -939,10 +942,9 @@ static enum i40iw_status_code i40iw_initialize_ilq(struct i40iw_device *iwdev)
 	info.rq_size = 8192;
 	info.buf_size = 1024;
 	info.tx_buf_cnt = 16384;
-	info.mss = iwdev->mss;
 	info.receive = i40iw_receive_ilq;
 	info.xmit_complete = i40iw_free_sqbuf;
-	status = i40iw_puda_create_rsrc(&iwdev->sc_dev, &info);
+	status = i40iw_puda_create_rsrc(&iwdev->vsi, &info);
 	if (status)
 		i40iw_pr_err("ilq create fail\n");
 	return status;
@@ -959,6 +961,7 @@ static enum i40iw_status_code i40iw_initialize_ieq(struct i40iw_device *iwdev)
 	struct i40iw_puda_rsrc_info info;
 	enum i40iw_status_code status;
 
+	memset(&info, 0, sizeof(info));
 	info.type = I40IW_PUDA_RSRC_TYPE_IEQ;
 	info.cq_id = 2;
 	info.qp_id = iwdev->sc_dev.exception_lan_queue;
@@ -967,9 +970,8 @@ static enum i40iw_status_code i40iw_initialize_ieq(struct i40iw_device *iwdev)
 	info.sq_size = 8192;
 	info.rq_size = 8192;
 	info.buf_size = 2048;
-	info.mss = iwdev->mss;
 	info.tx_buf_cnt = 16384;
-	status = i40iw_puda_create_rsrc(&iwdev->sc_dev, &info);
+	status = i40iw_puda_create_rsrc(&iwdev->vsi, &info);
 	if (status)
 		i40iw_pr_err("ieq create fail\n");
 	return status;
@@ -1159,7 +1161,7 @@ static void i40iw_add_ipv6_addr(struct i40iw_device *iwdev)
 {
 	struct net_device *ip_dev;
 	struct inet6_dev *idev;
-	struct inet6_ifaddr *ifp;
+	struct inet6_ifaddr *ifp, *tmp;
 	u32 local_ipaddr6[4];
 
 	rcu_read_lock();
@@ -1172,7 +1174,7 @@ static void i40iw_add_ipv6_addr(struct i40iw_device *iwdev)
 				i40iw_pr_err("ipv6 inet device not found\n");
 				break;
 			}
-			list_for_each_entry(ifp, &idev->addr_list, if_list) {
+			list_for_each_entry_safe(ifp, tmp, &idev->addr_list, if_list) {
 				i40iw_pr_info("IP=%pI6, vlan_id=%d, MAC=%pM\n", &ifp->addr,
 					      rdma_vlan_dev_vlan_id(ip_dev), ip_dev->dev_addr);
 				i40iw_copy_ip_ntohl(local_ipaddr6,
@@ -1294,17 +1296,23 @@ static enum i40iw_status_code i40iw_initialize_dev(struct i40iw_device *iwdev,
 	enum i40iw_status_code status;
 	struct i40iw_sc_dev *dev = &iwdev->sc_dev;
 	struct i40iw_device_init_info info;
+	struct i40iw_vsi_init_info vsi_info;
 	struct i40iw_dma_mem mem;
+	struct i40iw_l2params l2params;
 	u32 size;
+	struct i40iw_vsi_stats_info stats_info;
+	u16 last_qset = I40IW_NO_QSET;
+	u16 qset;
+	u32 i;
 
+	memset(&l2params, 0, sizeof(l2params));
 	memset(&info, 0, sizeof(info));
 	size = sizeof(struct i40iw_hmc_pble_rsrc) + sizeof(struct i40iw_hmc_info) +
 				(sizeof(struct i40iw_hmc_obj_info) * I40IW_HMC_IW_MAX);
 	iwdev->hmc_info_mem = kzalloc(size, GFP_KERNEL);
-	if (!iwdev->hmc_info_mem) {
-		i40iw_pr_err("memory alloc fail\n");
+	if (!iwdev->hmc_info_mem)
 		return I40IW_ERR_NO_MEMORY;
-	}
+
 	iwdev->pble_rsrc = (struct i40iw_hmc_pble_rsrc *)iwdev->hmc_info_mem;
 	dev->hmc_info = &iwdev->hw.hmc;
 	dev->hmc_info->hmc_obj = (struct i40iw_hmc_obj_info *)(iwdev->pble_rsrc + 1);
@@ -1325,7 +1333,17 @@ static enum i40iw_status_code i40iw_initialize_dev(struct i40iw_device *iwdev,
 	info.bar0 = ldev->hw_addr;
 	info.hw = &iwdev->hw;
 	info.debug_mask = debug;
-	info.qs_handle = ldev->params.qos.prio_qos[0].qs_handle;
+	l2params.mss =
+		(ldev->params.mtu) ? ldev->params.mtu - I40IW_MTU_TO_MSS : I40IW_DEFAULT_MSS;
+	for (i = 0; i < I40E_CLIENT_MAX_USER_PRIORITY; i++) {
+		qset = ldev->params.qos.prio_qos[i].qs_handle;
+		l2params.qs_handle_list[i] = qset;
+		if (last_qset == I40IW_NO_QSET)
+			last_qset = qset;
+		else if ((qset != last_qset) && (qset != I40IW_NO_QSET))
+			iwdev->dcb = true;
+	}
+	i40iw_pr_info("DCB is set/clear = %d\n", iwdev->dcb);
 	info.exception_lan_queue = 1;
 	info.vchnl_send = i40iw_virtchnl_send;
 	status = i40iw_device_init(&iwdev->sc_dev, &info);
@@ -1334,6 +1352,20 @@ exit:
 		kfree(iwdev->hmc_info_mem);
 		iwdev->hmc_info_mem = NULL;
 	}
+	memset(&vsi_info, 0, sizeof(vsi_info));
+	vsi_info.dev = &iwdev->sc_dev;
+	vsi_info.back_vsi = (void *)iwdev;
+	vsi_info.params = &l2params;
+	i40iw_sc_vsi_init(&iwdev->vsi, &vsi_info);
+
+	if (dev->is_pf) {
+		memset(&stats_info, 0, sizeof(stats_info));
+		stats_info.fcn_id = ldev->fid;
+		stats_info.pestat = kzalloc(sizeof(*stats_info.pestat), GFP_KERNEL);
+		stats_info.stats_initialize = true;
+		if (stats_info.pestat)
+			i40iw_vsi_stats_init(&iwdev->vsi, &stats_info);
+	}
 	return status;
 }
 
@@ -1384,6 +1416,7 @@ static enum i40iw_status_code i40iw_save_msix_info(struct i40iw_device *iwdev,
 	for (i = 0, ceq_idx = 0; i < iwdev->msix_count; i++, iw_qvinfo++) {
 		iwdev->iw_msixtbl[i].idx = ldev->msix_entries[i].entry;
 		iwdev->iw_msixtbl[i].irq = ldev->msix_entries[i].vector;
+		iwdev->iw_msixtbl[i].cpu_affinity = ceq_idx;
 		if (i == 0) {
 			iw_qvinfo->aeq_idx = 0;
 			if (iwdev->msix_shared)
@@ -1404,18 +1437,19 @@ static enum i40iw_status_code i40iw_save_msix_info(struct i40iw_device *iwdev,
  * i40iw_deinit_device - clean up the device resources
  * @iwdev: iwarp device
  * @reset: true if called before reset
- * @del_hdl: true if delete hdl entry
  *
  * Destroy the ib device interface, remove the mac ip entry and ipv4/ipv6 addresses,
  * destroy the device queues and free the pble and the hmc objects
  */
-static void i40iw_deinit_device(struct i40iw_device *iwdev, bool reset, bool del_hdl)
+static void i40iw_deinit_device(struct i40iw_device *iwdev, bool reset)
 {
 	struct i40e_info *ldev = iwdev->ldev;
 
 	struct i40iw_sc_dev *dev = &iwdev->sc_dev;
 
 	i40iw_pr_info("state = %d\n", iwdev->init_state);
+	if (iwdev->param_wq)
+		destroy_workqueue(iwdev->param_wq);
 
 	switch (iwdev->init_state) {
 	case RDMA_DEV_REGISTERED:
@@ -1441,10 +1475,10 @@ static void i40iw_deinit_device(struct i40iw_device *iwdev, bool reset, bool del
 		i40iw_destroy_aeq(iwdev, reset);
 		/* fallthrough */
 	case IEQ_CREATED:
-		i40iw_puda_dele_resources(dev, I40IW_PUDA_RSRC_TYPE_IEQ, reset);
+		i40iw_puda_dele_resources(&iwdev->vsi, I40IW_PUDA_RSRC_TYPE_IEQ, reset);
 		/* fallthrough */
 	case ILQ_CREATED:
-		i40iw_puda_dele_resources(dev, I40IW_PUDA_RSRC_TYPE_ILQ, reset);
+		i40iw_puda_dele_resources(&iwdev->vsi, I40IW_PUDA_RSRC_TYPE_ILQ, reset);
 		/* fallthrough */
 	case CCQ_CREATED:
 		i40iw_destroy_ccq(iwdev, reset);
@@ -1456,13 +1490,14 @@ static void i40iw_deinit_device(struct i40iw_device *iwdev, bool reset, bool del
 		i40iw_del_hmc_objects(dev, dev->hmc_info, true, reset);
 		/* fallthrough */
 	case CQP_CREATED:
-		i40iw_destroy_cqp(iwdev, !reset);
+		i40iw_destroy_cqp(iwdev, true);
 		/* fallthrough */
 	case INITIAL_STATE:
 		i40iw_cleanup_cm_core(&iwdev->cm_core);
-		if (dev->is_pf)
-			i40iw_hw_stats_del_timer(dev);
-
+		if (iwdev->vsi.pestat) {
+			i40iw_vsi_stats_free(&iwdev->vsi);
+			kfree(iwdev->vsi.pestat);
+		}
 		i40iw_del_init_mem(iwdev);
 		break;
 	case INVALID_STATE:
@@ -1472,8 +1507,7 @@ static void i40iw_deinit_device(struct i40iw_device *iwdev, bool reset, bool del
 		break;
 	}
 
-	if (del_hdl)
-		i40iw_del_handler(i40iw_find_i40e_handler(ldev));
+	i40iw_del_handler(i40iw_find_i40e_handler(ldev));
 	kfree(iwdev->hdl);
 }
 
@@ -1508,7 +1542,6 @@ static enum i40iw_status_code i40iw_setup_init_state(struct i40iw_handler *hdl,
 	iwdev->max_enabled_vfs = iwdev->max_rdma_vfs;
 	iwdev->netdev = ldev->netdev;
 	hdl->client = client;
-	iwdev->mss = (!ldev->params.mtu) ? I40IW_DEFAULT_MSS : ldev->params.mtu - I40IW_MTU_TO_MSS;
 	if (!ldev->ftype)
 		iwdev->db_start = pci_resource_start(ldev->pcidev, 0) + I40IW_DB_ADDR_OFFSET;
 	else
@@ -1528,6 +1561,7 @@ static enum i40iw_status_code i40iw_setup_init_state(struct i40iw_handler *hdl,
 
 	init_waitqueue_head(&iwdev->vchnl_waitq);
 	init_waitqueue_head(&dev->vf_reqs);
+	init_waitqueue_head(&iwdev->close_wq);
 
 	status = i40iw_initialize_dev(iwdev, ldev);
 exit:
@@ -1539,6 +1573,20 @@ exit:
 	return status;
 }
 
+/**
+ * i40iw_get_used_rsrc - determine resources used internally
+ * @iwdev: iwarp device
+ *
+ * Called after internal allocations
+ */
+static void i40iw_get_used_rsrc(struct i40iw_device *iwdev)
+{
+	iwdev->used_pds = find_next_zero_bit(iwdev->allocated_pds, iwdev->max_pd, 0);
+	iwdev->used_qps = find_next_zero_bit(iwdev->allocated_qps, iwdev->max_qp, 0);
+	iwdev->used_cqs = find_next_zero_bit(iwdev->allocated_cqs, iwdev->max_cq, 0);
+	iwdev->used_mrs = find_next_zero_bit(iwdev->allocated_mrs, iwdev->max_mr, 0);
+}
+
 /**
  * i40iw_open - client interface operation open for iwarp/uda device
  * @ldev: lan device information
@@ -1611,6 +1659,7 @@ static int i40iw_open(struct i40e_info *ldev, struct i40e_client *client)
 		status = i40iw_initialize_hw_resources(iwdev);
 		if (status)
 			break;
+		i40iw_get_used_rsrc(iwdev);
 		dev->ccq_ops->ccq_arm(dev->ccq);
 		status = i40iw_hmc_init_pble(&iwdev->sc_dev, iwdev->pble_rsrc);
 		if (status)
@@ -1630,35 +1679,73 @@ static int i40iw_open(struct i40e_info *ldev, struct i40e_client *client)
 		iwdev->init_state = RDMA_DEV_REGISTERED;
 		iwdev->iw_status = 1;
 		i40iw_port_ibevent(iwdev);
+		iwdev->param_wq = alloc_ordered_workqueue("l2params", WQ_MEM_RECLAIM);
+		if(iwdev->param_wq == NULL)
+			break;
 		i40iw_pr_info("i40iw_open completed\n");
 		return 0;
 	} while (0);
 
 	i40iw_pr_err("status = %d last completion = %d\n", status, iwdev->init_state);
-	i40iw_deinit_device(iwdev, false, false);
+	i40iw_deinit_device(iwdev, false);
 	return -ERESTART;
 }
 
 /**
- * i40iw_l2param_change : handle qs handles for qos and mss change
+ * i40iw_l2params_worker - worker for l2 params change
+ * @work: work pointer for l2 params
+ */
+static void i40iw_l2params_worker(struct work_struct *work)
+{
+	struct l2params_work *dwork =
+	    container_of(work, struct l2params_work, work);
+	struct i40iw_device *iwdev = dwork->iwdev;
+
+	i40iw_change_l2params(&iwdev->vsi, &dwork->l2params);
+	atomic_dec(&iwdev->params_busy);
+	kfree(work);
+}
+
+/**
+ * i40iw_l2param_change - handle qs handles for qos and mss change
  * @ldev: lan device information
  * @client: client for paramater change
  * @params: new parameters from L2
  */
-static void i40iw_l2param_change(struct i40e_info *ldev,
-				 struct i40e_client *client,
+static void i40iw_l2param_change(struct i40e_info *ldev, struct i40e_client *client,
 				 struct i40e_params *params)
 {
 	struct i40iw_handler *hdl;
+	struct i40iw_l2params *l2params;
+	struct l2params_work *work;
 	struct i40iw_device *iwdev;
+	int i;
 
 	hdl = i40iw_find_i40e_handler(ldev);
 	if (!hdl)
 		return;
 
 	iwdev = &hdl->device;
-	if (params->mtu)
-		iwdev->mss = params->mtu - I40IW_MTU_TO_MSS;
+
+	if (atomic_read(&iwdev->params_busy))
+		return;
+
+
+	work = kzalloc(sizeof(*work), GFP_ATOMIC);
+	if (!work)
+		return;
+
+	atomic_inc(&iwdev->params_busy);
+
+	work->iwdev = iwdev;
+	l2params = &work->l2params;
+	for (i = 0; i < I40E_CLIENT_MAX_USER_PRIORITY; i++)
+		l2params->qs_handle_list[i] = params->qos.prio_qos[i].qs_handle;
+
+	l2params->mss = (params->mtu) ? params->mtu - I40IW_MTU_TO_MSS : iwdev->vsi.mss;
+
+	INIT_WORK(&work->work, i40iw_l2params_worker);
+	queue_work(iwdev->param_wq, &work->work);
 }
 
 /**
@@ -1679,8 +1766,11 @@ static void i40iw_close(struct i40e_info *ldev, struct i40e_client *client, bool
 		return;
 
 	iwdev = &hdl->device;
+	iwdev->closing = true;
+
+	i40iw_cm_disconnect_all(iwdev);
 	destroy_workqueue(iwdev->virtchnl_wq);
-	i40iw_deinit_device(iwdev, reset, true);
+	i40iw_deinit_device(iwdev, reset);
 }
 
 /**
@@ -1701,21 +1791,23 @@ static void i40iw_vf_reset(struct i40e_info *ldev, struct i40e_client *client, u
 	struct i40iw_vfdev *tmp_vfdev;
 	unsigned int i;
 	unsigned long flags;
+	struct i40iw_device *iwdev;
 
 	hdl = i40iw_find_i40e_handler(ldev);
 	if (!hdl)
 		return;
 
 	dev = &hdl->device.sc_dev;
+	iwdev = (struct i40iw_device *)dev->back_dev;
 
 	for (i = 0; i < I40IW_MAX_PE_ENABLED_VF_COUNT; i++) {
 		if (!dev->vf_dev[i] || (dev->vf_dev[i]->vf_id != vf_id))
 			continue;
 		/* free all resources allocated on behalf of vf */
 		tmp_vfdev = dev->vf_dev[i];
-		spin_lock_irqsave(&dev->dev_pestat.stats_lock, flags);
+		spin_lock_irqsave(&iwdev->vsi.pestat->lock, flags);
 		dev->vf_dev[i] = NULL;
-		spin_unlock_irqrestore(&dev->dev_pestat.stats_lock, flags);
+		spin_unlock_irqrestore(&iwdev->vsi.pestat->lock, flags);
 		i40iw_del_hmc_objects(dev, &tmp_vfdev->hmc_info, false, false);
 		/* remove vf hmc function */
 		memset(&hmc_fcn_info, 0, sizeof(hmc_fcn_info));

drivers/infiniband/hw/i40iw/i40iw_osdep.h

@@ -198,6 +198,8 @@ enum i40iw_status_code i40iw_cqp_manage_vf_pble_bp(struct i40iw_sc_dev *dev,
 void i40iw_cqp_spawn_worker(struct i40iw_sc_dev *dev,
 			    struct i40iw_virtchnl_work_info *work_info, u32 iw_vf_idx);
 void *i40iw_remove_head(struct list_head *list);
+void i40iw_qp_suspend_resume(struct i40iw_sc_dev *dev, struct i40iw_sc_qp *qp, bool suspend);
+void i40iw_qp_mss_modify(struct i40iw_sc_dev *dev, struct i40iw_sc_qp *qp);
 
 void i40iw_term_modify_qp(struct i40iw_sc_qp *qp, u8 next_state, u8 term, u8 term_len);
 void i40iw_terminate_done(struct i40iw_sc_qp *qp, int timeout_occurred);
@@ -207,9 +209,9 @@ void i40iw_terminate_del_timer(struct i40iw_sc_qp *qp);
 enum i40iw_status_code i40iw_hw_manage_vf_pble_bp(struct i40iw_device *iwdev,
 						  struct i40iw_manage_vf_pble_info *info,
 						  bool wait);
-struct i40iw_dev_pestat;
-void i40iw_hw_stats_start_timer(struct i40iw_sc_dev *);
-void i40iw_hw_stats_del_timer(struct i40iw_sc_dev *);
+struct i40iw_sc_vsi;
+void i40iw_hw_stats_start_timer(struct i40iw_sc_vsi *vsi);
+void i40iw_hw_stats_stop_timer(struct i40iw_sc_vsi *vsi);
 #define i40iw_mmiowb() mmiowb()
 void i40iw_wr32(struct i40iw_hw *hw, u32 reg, u32 value);
 u32  i40iw_rd32(struct i40iw_hw *hw, u32 reg);

drivers/infiniband/hw/i40iw/i40iw_p.h

@@ -47,8 +47,6 @@ void i40iw_debug_buf(struct i40iw_sc_dev *dev, enum i40iw_debug_flag mask,
 enum i40iw_status_code i40iw_device_init(struct i40iw_sc_dev *dev,
 					 struct i40iw_device_init_info *info);
 
-enum i40iw_status_code i40iw_device_init_pestat(struct i40iw_dev_pestat *);
-
 void i40iw_sc_cqp_post_sq(struct i40iw_sc_cqp *cqp);
 
 u64 *i40iw_sc_cqp_get_next_send_wqe(struct i40iw_sc_cqp *cqp, u64 scratch);
@@ -64,7 +62,24 @@ enum i40iw_status_code i40iw_sc_init_iw_hmc(struct i40iw_sc_dev *dev,
 enum i40iw_status_code i40iw_pf_init_vfhmc(struct i40iw_sc_dev *dev, u8 vf_hmc_fn_id,
 					   u32 *vf_cnt_array);
 
-/* cqp misc functions */
+/* stats functions */
+void i40iw_hw_stats_refresh_all(struct i40iw_vsi_pestat *stats);
+void i40iw_hw_stats_read_all(struct i40iw_vsi_pestat *stats, struct i40iw_dev_hw_stats *stats_values);
+void i40iw_hw_stats_read_32(struct i40iw_vsi_pestat *stats,
+			    enum i40iw_hw_stats_index_32b index,
+			    u64 *value);
+void i40iw_hw_stats_read_64(struct i40iw_vsi_pestat *stats,
+			    enum i40iw_hw_stats_index_64b index,
+			    u64 *value);
+void i40iw_hw_stats_init(struct i40iw_vsi_pestat *stats, u8 index, bool is_pf);
+
+/* vsi misc functions */
+enum i40iw_status_code i40iw_vsi_stats_init(struct i40iw_sc_vsi *vsi, struct i40iw_vsi_stats_info *info);
+void i40iw_vsi_stats_free(struct i40iw_sc_vsi *vsi);
+void i40iw_sc_vsi_init(struct i40iw_sc_vsi *vsi, struct i40iw_vsi_init_info *info);
+
+void i40iw_change_l2params(struct i40iw_sc_vsi *vsi, struct i40iw_l2params *l2params);
+void i40iw_qp_add_qos(struct i40iw_sc_qp *qp);
 
 void i40iw_terminate_send_fin(struct i40iw_sc_qp *qp);
 

drivers/infiniband/hw/i40iw/i40iw_pble.c

@@ -353,10 +353,6 @@ static enum i40iw_status_code add_pble_pool(struct i40iw_sc_dev *dev,
 	pages = (idx->rel_pd_idx) ? (I40IW_HMC_PD_CNT_IN_SD -
 			idx->rel_pd_idx) : I40IW_HMC_PD_CNT_IN_SD;
 	pages = min(pages, pble_rsrc->unallocated_pble >> PBLE_512_SHIFT);
-	if (!pages) {
-		ret_code = I40IW_ERR_NO_PBLCHUNKS_AVAILABLE;
-		goto error;
-	}
 	info.chunk = chunk;
 	info.hmc_info = hmc_info;
 	info.pages = pages;

drivers/infiniband/hw/i40iw/i40iw_puda.c

@@ -42,12 +42,13 @@
 #include "i40iw_p.h"
 #include "i40iw_puda.h"
 
-static void i40iw_ieq_receive(struct i40iw_sc_dev *dev,
+static void i40iw_ieq_receive(struct i40iw_sc_vsi *vsi,
 			      struct i40iw_puda_buf *buf);
-static void i40iw_ieq_tx_compl(struct i40iw_sc_dev *dev, void *sqwrid);
+static void i40iw_ieq_tx_compl(struct i40iw_sc_vsi *vsi, void *sqwrid);
 static void i40iw_ilq_putback_rcvbuf(struct i40iw_sc_qp *qp, u32 wqe_idx);
 static enum i40iw_status_code i40iw_puda_replenish_rq(struct i40iw_puda_rsrc
 						      *rsrc, bool initial);
+static void i40iw_ieq_cleanup_qp(struct i40iw_puda_rsrc *ieq, struct i40iw_sc_qp *qp);
 /**
  * i40iw_puda_get_listbuf - get buffer from puda list
  * @list: list to use for buffers (ILQ or IEQ)
@@ -292,7 +293,7 @@ enum i40iw_status_code i40iw_puda_poll_completion(struct i40iw_sc_dev *dev,
 	unsigned long	flags;
 
 	if ((cq_type == I40IW_CQ_TYPE_ILQ) || (cq_type == I40IW_CQ_TYPE_IEQ)) {
-		rsrc = (cq_type == I40IW_CQ_TYPE_ILQ) ? dev->ilq : dev->ieq;
+		rsrc = (cq_type == I40IW_CQ_TYPE_ILQ) ? cq->vsi->ilq : cq->vsi->ieq;
 	} else {
 		i40iw_debug(dev, I40IW_DEBUG_PUDA, "%s qp_type error\n", __func__);
 		return I40IW_ERR_BAD_PTR;
@@ -335,7 +336,7 @@ enum i40iw_status_code i40iw_puda_poll_completion(struct i40iw_sc_dev *dev,
 		rsrc->stats_pkt_rcvd++;
 		rsrc->compl_rxwqe_idx = info.wqe_idx;
 		i40iw_debug(dev, I40IW_DEBUG_PUDA, "%s RQ completion\n", __func__);
-		rsrc->receive(rsrc->dev, buf);
+		rsrc->receive(rsrc->vsi, buf);
 		if (cq_type == I40IW_CQ_TYPE_ILQ)
 			i40iw_ilq_putback_rcvbuf(&rsrc->qp, info.wqe_idx);
 		else
@@ -345,12 +346,12 @@ enum i40iw_status_code i40iw_puda_poll_completion(struct i40iw_sc_dev *dev,
 		i40iw_debug(dev, I40IW_DEBUG_PUDA, "%s SQ completion\n", __func__);
 		sqwrid = (void *)(uintptr_t)qp->sq_wrtrk_array[info.wqe_idx].wrid;
 		I40IW_RING_SET_TAIL(qp->sq_ring, info.wqe_idx);
-		rsrc->xmit_complete(rsrc->dev, sqwrid);
+		rsrc->xmit_complete(rsrc->vsi, sqwrid);
 		spin_lock_irqsave(&rsrc->bufpool_lock, flags);
 		rsrc->tx_wqe_avail_cnt++;
 		spin_unlock_irqrestore(&rsrc->bufpool_lock, flags);
-		if (!list_empty(&dev->ilq->txpend))
-			i40iw_puda_send_buf(dev->ilq, NULL);
+		if (!list_empty(&rsrc->vsi->ilq->txpend))
+			i40iw_puda_send_buf(rsrc->vsi->ilq, NULL);
 	}
 
 done:
@@ -513,10 +514,8 @@ static void i40iw_puda_qp_setctx(struct i40iw_puda_rsrc *rsrc)
  * i40iw_puda_qp_wqe - setup wqe for qp create
  * @rsrc: resource for qp
  */
-static enum i40iw_status_code i40iw_puda_qp_wqe(struct i40iw_puda_rsrc *rsrc)
+static enum i40iw_status_code i40iw_puda_qp_wqe(struct i40iw_sc_dev *dev, struct i40iw_sc_qp *qp)
 {
-	struct i40iw_sc_qp *qp = &rsrc->qp;
-	struct i40iw_sc_dev *dev = rsrc->dev;
 	struct i40iw_sc_cqp *cqp;
 	u64 *wqe;
 	u64 header;
@@ -582,6 +581,7 @@ static enum i40iw_status_code i40iw_puda_qp_create(struct i40iw_puda_rsrc *rsrc)
 	qp->back_qp = (void *)rsrc;
 	qp->sq_pa = mem->pa;
 	qp->rq_pa = qp->sq_pa + sq_size;
+	qp->vsi = rsrc->vsi;
 	ukqp->sq_base = mem->va;
 	ukqp->rq_base = &ukqp->sq_base[rsrc->sq_size];
 	ukqp->shadow_area = ukqp->rq_base[rsrc->rq_size].elem;
@@ -608,14 +608,62 @@ static enum i40iw_status_code i40iw_puda_qp_create(struct i40iw_puda_rsrc *rsrc)
 		ukqp->wqe_alloc_reg = (u32 __iomem *)(i40iw_get_hw_addr(qp->pd->dev) +
 						    I40E_VFPE_WQEALLOC1);
 
-	qp->qs_handle = qp->dev->qs_handle;
+	qp->user_pri = 0;
+	i40iw_qp_add_qos(qp);
 	i40iw_puda_qp_setctx(rsrc);
-	ret = i40iw_puda_qp_wqe(rsrc);
+	if (rsrc->ceq_valid)
+		ret = i40iw_cqp_qp_create_cmd(rsrc->dev, qp);
+	else
+		ret = i40iw_puda_qp_wqe(rsrc->dev, qp);
 	if (ret)
 		i40iw_free_dma_mem(rsrc->dev->hw, &rsrc->qpmem);
 	return ret;
 }
 
+/**
+ * i40iw_puda_cq_wqe - setup wqe for cq create
+ * @rsrc: resource for cq
+ */
+static enum i40iw_status_code i40iw_puda_cq_wqe(struct i40iw_sc_dev *dev, struct i40iw_sc_cq *cq)
+{
+	u64 *wqe;
+	struct i40iw_sc_cqp *cqp;
+	u64 header;
+	struct i40iw_ccq_cqe_info compl_info;
+	enum i40iw_status_code status = 0;
+
+	cqp = dev->cqp;
+	wqe = i40iw_sc_cqp_get_next_send_wqe(cqp, 0);
+	if (!wqe)
+		return I40IW_ERR_RING_FULL;
+
+	set_64bit_val(wqe, 0, cq->cq_uk.cq_size);
+	set_64bit_val(wqe, 8, RS_64_1(cq, 1));
+	set_64bit_val(wqe, 16,
+		      LS_64(cq->shadow_read_threshold,
+			    I40IW_CQPSQ_CQ_SHADOW_READ_THRESHOLD));
+	set_64bit_val(wqe, 32, cq->cq_pa);
+
+	set_64bit_val(wqe, 40, cq->shadow_area_pa);
+
+	header = cq->cq_uk.cq_id |
+	    LS_64(I40IW_CQP_OP_CREATE_CQ, I40IW_CQPSQ_OPCODE) |
+	    LS_64(1, I40IW_CQPSQ_CQ_CHKOVERFLOW) |
+	    LS_64(1, I40IW_CQPSQ_CQ_ENCEQEMASK) |
+	    LS_64(1, I40IW_CQPSQ_CQ_CEQIDVALID) |
+	    LS_64(cqp->polarity, I40IW_CQPSQ_WQEVALID);
+	set_64bit_val(wqe, 24, header);
+
+	i40iw_debug_buf(dev, I40IW_DEBUG_PUDA, "PUDA CQE",
+			wqe, I40IW_CQP_WQE_SIZE * 8);
+
+	i40iw_sc_cqp_post_sq(dev->cqp);
+	status = dev->cqp_ops->poll_for_cqp_op_done(dev->cqp,
+						 I40IW_CQP_OP_CREATE_CQ,
+						 &compl_info);
+	return status;
+}
+
 /**
  * i40iw_puda_cq_create - create cq for resource
  * @rsrc: resource for which cq to create
@@ -624,18 +672,13 @@ static enum i40iw_status_code i40iw_puda_cq_create(struct i40iw_puda_rsrc *rsrc)
 {
 	struct i40iw_sc_dev *dev = rsrc->dev;
 	struct i40iw_sc_cq *cq = &rsrc->cq;
-	u64 *wqe;
-	struct i40iw_sc_cqp *cqp;
-	u64 header;
 	enum i40iw_status_code ret = 0;
 	u32 tsize, cqsize;
-	u32 shadow_read_threshold = 128;
 	struct i40iw_dma_mem *mem;
-	struct i40iw_ccq_cqe_info compl_info;
 	struct i40iw_cq_init_info info;
 	struct i40iw_cq_uk_init_info *init_info = &info.cq_uk_init_info;
 
-	cq->back_cq = (void *)rsrc;
+	cq->vsi = rsrc->vsi;
 	cqsize = rsrc->cq_size * (sizeof(struct i40iw_cqe));
 	tsize = cqsize + sizeof(struct i40iw_cq_shadow_area);
 	ret = i40iw_allocate_dma_mem(dev->hw, &rsrc->cqmem, tsize,
@@ -656,43 +699,84 @@ static enum i40iw_status_code i40iw_puda_cq_create(struct i40iw_puda_rsrc *rsrc)
 	init_info->shadow_area = (u64 *)((u8 *)mem->va + cqsize);
 	init_info->cq_size = rsrc->cq_size;
 	init_info->cq_id = rsrc->cq_id;
+	info.ceqe_mask = true;
+	info.ceq_id_valid = true;
 	ret = dev->iw_priv_cq_ops->cq_init(cq, &info);
 	if (ret)
 		goto error;
-	cqp = dev->cqp;
-	wqe = i40iw_sc_cqp_get_next_send_wqe(cqp, 0);
-	if (!wqe) {
-		ret = I40IW_ERR_RING_FULL;
-		goto error;
-	}
+	if (rsrc->ceq_valid)
+		ret = i40iw_cqp_cq_create_cmd(dev, cq);
+	else
+		ret = i40iw_puda_cq_wqe(dev, cq);
+error:
+	if (ret)
+		i40iw_free_dma_mem(dev->hw, &rsrc->cqmem);
+	return ret;
+}
 
-	set_64bit_val(wqe, 0, rsrc->cq_size);
-	set_64bit_val(wqe, 8, RS_64_1(cq, 1));
-	set_64bit_val(wqe, 16, LS_64(shadow_read_threshold, I40IW_CQPSQ_CQ_SHADOW_READ_THRESHOLD));
-	set_64bit_val(wqe, 32, cq->cq_pa);
+/**
+ * i40iw_puda_free_qp - free qp for resource
+ * @rsrc: resource for which qp to free
+ */
+static void i40iw_puda_free_qp(struct i40iw_puda_rsrc *rsrc)
+{
+	enum i40iw_status_code ret;
+	struct i40iw_ccq_cqe_info compl_info;
+	struct i40iw_sc_dev *dev = rsrc->dev;
 
-	set_64bit_val(wqe, 40, cq->shadow_area_pa);
+	if (rsrc->ceq_valid) {
+		i40iw_cqp_qp_destroy_cmd(dev, &rsrc->qp);
+		return;
+	}
 
-	header = rsrc->cq_id |
-	    LS_64(I40IW_CQP_OP_CREATE_CQ, I40IW_CQPSQ_OPCODE) |
-	    LS_64(1, I40IW_CQPSQ_CQ_CHKOVERFLOW) |
-	    LS_64(1, I40IW_CQPSQ_CQ_ENCEQEMASK) |
-	    LS_64(1, I40IW_CQPSQ_CQ_CEQIDVALID) |
-	    LS_64(cqp->polarity, I40IW_CQPSQ_WQEVALID);
-	set_64bit_val(wqe, 24, header);
+	ret = dev->iw_priv_qp_ops->qp_destroy(&rsrc->qp,
+			0, false, true, true);
+	if (ret)
+		i40iw_debug(dev, I40IW_DEBUG_PUDA,
+			    "%s error puda qp destroy wqe\n",
+			    __func__);
 
-	i40iw_debug_buf(dev, I40IW_DEBUG_PUDA, "PUDA CQE",
-			wqe, I40IW_CQP_WQE_SIZE * 8);
+	if (!ret) {
+		ret = dev->cqp_ops->poll_for_cqp_op_done(dev->cqp,
+				I40IW_CQP_OP_DESTROY_QP,
+				&compl_info);
+		if (ret)
+			i40iw_debug(dev, I40IW_DEBUG_PUDA,
+				    "%s error puda qp destroy failed\n",
+				    __func__);
+	}
+}
 
-	i40iw_sc_cqp_post_sq(dev->cqp);
-	ret = dev->cqp_ops->poll_for_cqp_op_done(dev->cqp,
-						 I40IW_CQP_OP_CREATE_CQ,
-						 &compl_info);
+/**
+ * i40iw_puda_free_cq - free cq for resource
+ * @rsrc: resource for which cq to free
+ */
+static void i40iw_puda_free_cq(struct i40iw_puda_rsrc *rsrc)
+{
+	enum i40iw_status_code ret;
+	struct i40iw_ccq_cqe_info compl_info;
+	struct i40iw_sc_dev *dev = rsrc->dev;
+
+	if (rsrc->ceq_valid) {
+		i40iw_cqp_cq_destroy_cmd(dev, &rsrc->cq);
+		return;
+	}
+	ret = dev->iw_priv_cq_ops->cq_destroy(&rsrc->cq, 0, true);
 
-error:
 	if (ret)
-		i40iw_free_dma_mem(dev->hw, &rsrc->cqmem);
-	return ret;
+		i40iw_debug(dev, I40IW_DEBUG_PUDA,
+			    "%s error ieq cq destroy\n",
+			    __func__);
+
+	if (!ret) {
+		ret = dev->cqp_ops->poll_for_cqp_op_done(dev->cqp,
+				I40IW_CQP_OP_DESTROY_CQ,
+				&compl_info);
+		if (ret)
+			i40iw_debug(dev, I40IW_DEBUG_PUDA,
+				    "%s error ieq qp destroy done\n",
+				    __func__);
+	}
 }
 
 /**
@@ -701,25 +785,24 @@ error:
  * @type: type of resource to dele
  * @reset: true if reset chip
  */
-void i40iw_puda_dele_resources(struct i40iw_sc_dev *dev,
+void i40iw_puda_dele_resources(struct i40iw_sc_vsi *vsi,
 			       enum puda_resource_type type,
 			       bool reset)
 {
-	struct i40iw_ccq_cqe_info compl_info;
+	struct i40iw_sc_dev *dev = vsi->dev;
 	struct i40iw_puda_rsrc *rsrc;
 	struct i40iw_puda_buf *buf = NULL;
 	struct i40iw_puda_buf *nextbuf = NULL;
 	struct i40iw_virt_mem *vmem;
-	enum i40iw_status_code ret;
 
 	switch (type) {
 	case I40IW_PUDA_RSRC_TYPE_ILQ:
-		rsrc = dev->ilq;
-		vmem = &dev->ilq_mem;
+		rsrc = vsi->ilq;
+		vmem = &vsi->ilq_mem;
 		break;
 	case I40IW_PUDA_RSRC_TYPE_IEQ:
-		rsrc = dev->ieq;
-		vmem = &dev->ieq_mem;
+		rsrc = vsi->ieq;
+		vmem = &vsi->ieq_mem;
 		break;
 	default:
 		i40iw_debug(dev, I40IW_DEBUG_PUDA, "%s: error resource type = 0x%x\n",
@@ -731,45 +814,14 @@ void i40iw_puda_dele_resources(struct i40iw_sc_dev *dev,
 	case PUDA_HASH_CRC_COMPLETE:
 		i40iw_free_hash_desc(rsrc->hash_desc);
 	case PUDA_QP_CREATED:
-		do {
-			if (reset)
-				break;
-			ret = dev->iw_priv_qp_ops->qp_destroy(&rsrc->qp,
-							      0, false, true, true);
-			if (ret)
-				i40iw_debug(rsrc->dev, I40IW_DEBUG_PUDA,
-					    "%s error ieq qp destroy\n",
-					    __func__);
-
-			ret = dev->cqp_ops->poll_for_cqp_op_done(dev->cqp,
-								 I40IW_CQP_OP_DESTROY_QP,
-								 &compl_info);
-			if (ret)
-				i40iw_debug(rsrc->dev, I40IW_DEBUG_PUDA,
-					    "%s error ieq qp destroy done\n",
-					    __func__);
-		} while (0);
+		if (!reset)
+			i40iw_puda_free_qp(rsrc);
 
 		i40iw_free_dma_mem(dev->hw, &rsrc->qpmem);
 		/* fallthrough */
 	case PUDA_CQ_CREATED:
-		do {
-			if (reset)
-				break;
-			ret = dev->iw_priv_cq_ops->cq_destroy(&rsrc->cq, 0, true);
-			if (ret)
-				i40iw_debug(rsrc->dev, I40IW_DEBUG_PUDA,
-					    "%s error ieq cq destroy\n",
-					    __func__);
-
-			ret = dev->cqp_ops->poll_for_cqp_op_done(dev->cqp,
-								 I40IW_CQP_OP_DESTROY_CQ,
-								 &compl_info);
-			if (ret)
-				i40iw_debug(rsrc->dev, I40IW_DEBUG_PUDA,
-					    "%s error ieq qp destroy done\n",
-					    __func__);
-		} while (0);
+		if (!reset)
+			i40iw_puda_free_cq(rsrc);
 
 		i40iw_free_dma_mem(dev->hw, &rsrc->cqmem);
 		break;
@@ -825,9 +877,10 @@ static enum i40iw_status_code i40iw_puda_allocbufs(struct i40iw_puda_rsrc *rsrc,
  * @dev: iwarp device
  * @info: resource information
  */
-enum i40iw_status_code i40iw_puda_create_rsrc(struct i40iw_sc_dev *dev,
+enum i40iw_status_code i40iw_puda_create_rsrc(struct i40iw_sc_vsi *vsi,
 					      struct i40iw_puda_rsrc_info *info)
 {
+	struct i40iw_sc_dev *dev = vsi->dev;
 	enum i40iw_status_code ret = 0;
 	struct i40iw_puda_rsrc *rsrc;
 	u32 pudasize;
@@ -840,10 +893,10 @@ enum i40iw_status_code i40iw_puda_create_rsrc(struct i40iw_sc_dev *dev,
 	rqwridsize = info->rq_size * 8;
 	switch (info->type) {
 	case I40IW_PUDA_RSRC_TYPE_ILQ:
-		vmem = &dev->ilq_mem;
+		vmem = &vsi->ilq_mem;
 		break;
 	case I40IW_PUDA_RSRC_TYPE_IEQ:
-		vmem = &dev->ieq_mem;
+		vmem = &vsi->ieq_mem;
 		break;
 	default:
 		return I40IW_NOT_SUPPORTED;
@@ -856,22 +909,22 @@ enum i40iw_status_code i40iw_puda_create_rsrc(struct i40iw_sc_dev *dev,
 	rsrc = (struct i40iw_puda_rsrc *)vmem->va;
 	spin_lock_init(&rsrc->bufpool_lock);
 	if (info->type == I40IW_PUDA_RSRC_TYPE_ILQ) {
-		dev->ilq = (struct i40iw_puda_rsrc *)vmem->va;
-		dev->ilq_count = info->count;
+		vsi->ilq = (struct i40iw_puda_rsrc *)vmem->va;
+		vsi->ilq_count = info->count;
 		rsrc->receive = info->receive;
 		rsrc->xmit_complete = info->xmit_complete;
 	} else {
-		vmem = &dev->ieq_mem;
-		dev->ieq_count = info->count;
-		dev->ieq = (struct i40iw_puda_rsrc *)vmem->va;
+		vmem = &vsi->ieq_mem;
+		vsi->ieq_count = info->count;
+		vsi->ieq = (struct i40iw_puda_rsrc *)vmem->va;
 		rsrc->receive = i40iw_ieq_receive;
 		rsrc->xmit_complete = i40iw_ieq_tx_compl;
 	}
 
+	rsrc->ceq_valid = info->ceq_valid;
 	rsrc->type = info->type;
 	rsrc->sq_wrtrk_array = (struct i40iw_sq_uk_wr_trk_info *)((u8 *)vmem->va + pudasize);
 	rsrc->rq_wrid_array = (u64 *)((u8 *)vmem->va + pudasize + sqwridsize);
-	rsrc->mss = info->mss;
 	/* Initialize all ieq lists */
 	INIT_LIST_HEAD(&rsrc->bufpool);
 	INIT_LIST_HEAD(&rsrc->txpend);
@@ -885,6 +938,7 @@ enum i40iw_status_code i40iw_puda_create_rsrc(struct i40iw_sc_dev *dev,
 	rsrc->cq_size = info->rq_size + info->sq_size;
 	rsrc->buf_size = info->buf_size;
 	rsrc->dev = dev;
+	rsrc->vsi = vsi;
 
 	ret = i40iw_puda_cq_create(rsrc);
 	if (!ret) {
@@ -919,7 +973,7 @@ enum i40iw_status_code i40iw_puda_create_rsrc(struct i40iw_sc_dev *dev,
 	dev->ccq_ops->ccq_arm(&rsrc->cq);
 	return ret;
  error:
-	i40iw_puda_dele_resources(dev, info->type, false);
+	i40iw_puda_dele_resources(vsi, info->type, false);
 
 	return ret;
 }
@@ -1131,7 +1185,7 @@ static enum i40iw_status_code i40iw_ieq_handle_partial(struct i40iw_puda_rsrc *i
 	list_add(&buf->list, &pbufl);
 
 	status = i40iw_ieq_create_pbufl(pfpdu, rxlist, &pbufl, buf, fpdu_len);
-	if (!status)
+	if (status)
 		goto error;
 
 	txbuf = i40iw_puda_get_bufpool(ieq);
@@ -1332,7 +1386,7 @@ static void i40iw_ieq_handle_exception(struct i40iw_puda_rsrc *ieq,
 	}
 	if (pfpdu->mode && (fps != pfpdu->fps)) {
 		/* clean up qp as it is new partial sequence */
-		i40iw_ieq_cleanup_qp(ieq->dev, qp);
+		i40iw_ieq_cleanup_qp(ieq, qp);
 		i40iw_debug(ieq->dev, I40IW_DEBUG_IEQ,
 			    "%s: restarting new partial\n", __func__);
 		pfpdu->mode = false;
@@ -1344,7 +1398,7 @@ static void i40iw_ieq_handle_exception(struct i40iw_puda_rsrc *ieq,
 		pfpdu->rcv_nxt = fps;
 		pfpdu->fps = fps;
 		pfpdu->mode = true;
-		pfpdu->max_fpdu_data = ieq->mss;
+		pfpdu->max_fpdu_data = ieq->vsi->mss;
 		pfpdu->pmode_count++;
 		INIT_LIST_HEAD(rxlist);
 		i40iw_ieq_check_first_buf(buf, fps);
@@ -1379,14 +1433,14 @@ static void i40iw_ieq_handle_exception(struct i40iw_puda_rsrc *ieq,
  * @dev: iwarp device
  * @buf: exception buffer received
  */
-static void i40iw_ieq_receive(struct i40iw_sc_dev *dev,
+static void i40iw_ieq_receive(struct i40iw_sc_vsi *vsi,
 			      struct i40iw_puda_buf *buf)
 {
-	struct i40iw_puda_rsrc *ieq = dev->ieq;
+	struct i40iw_puda_rsrc *ieq = vsi->ieq;
 	struct i40iw_sc_qp *qp = NULL;
 	u32 wqe_idx = ieq->compl_rxwqe_idx;
 
-	qp = i40iw_ieq_get_qp(dev, buf);
+	qp = i40iw_ieq_get_qp(vsi->dev, buf);
 	if (!qp) {
 		ieq->stats_bad_qp_id++;
 		i40iw_puda_ret_bufpool(ieq, buf);
@@ -1404,12 +1458,12 @@ static void i40iw_ieq_receive(struct i40iw_sc_dev *dev,
 
 /**
  * i40iw_ieq_tx_compl - put back after sending completed exception buffer
- * @dev: iwarp device
+ * @vsi: pointer to the vsi structure
  * @sqwrid: pointer to puda buffer
  */
-static void i40iw_ieq_tx_compl(struct i40iw_sc_dev *dev, void *sqwrid)
+static void i40iw_ieq_tx_compl(struct i40iw_sc_vsi *vsi, void *sqwrid)
 {
-	struct i40iw_puda_rsrc *ieq = dev->ieq;
+	struct i40iw_puda_rsrc *ieq = vsi->ieq;
 	struct i40iw_puda_buf *buf = (struct i40iw_puda_buf *)sqwrid;
 
 	i40iw_puda_ret_bufpool(ieq, buf);
@@ -1421,15 +1475,14 @@ static void i40iw_ieq_tx_compl(struct i40iw_sc_dev *dev, void *sqwrid)
 
 /**
  * i40iw_ieq_cleanup_qp - qp is being destroyed
- * @dev: iwarp device
+ * @ieq: ieq resource
  * @qp: all pending fpdu buffers
  */
-void i40iw_ieq_cleanup_qp(struct i40iw_sc_dev *dev, struct i40iw_sc_qp *qp)
+static void i40iw_ieq_cleanup_qp(struct i40iw_puda_rsrc *ieq, struct i40iw_sc_qp *qp)
 {
 	struct i40iw_puda_buf *buf;
 	struct i40iw_pfpdu *pfpdu = &qp->pfpdu;
 	struct list_head *rxlist = &pfpdu->rxlist;
-	struct i40iw_puda_rsrc *ieq = dev->ieq;
 
 	if (!pfpdu->mode)
 		return;

drivers/infiniband/hw/i40iw/i40iw_puda.h

@@ -100,6 +100,7 @@ struct i40iw_puda_rsrc_info {
 	enum puda_resource_type type;	/* ILQ or IEQ */
 	u32 count;
 	u16 pd_id;
+	bool ceq_valid;
 	u32 cq_id;
 	u32 qp_id;
 	u32 sq_size;
@@ -107,8 +108,8 @@ struct i40iw_puda_rsrc_info {
 	u16 buf_size;
 	u16 mss;
 	u32 tx_buf_cnt;		/* total bufs allocated will be rq_size + tx_buf_cnt */
-	void (*receive)(struct i40iw_sc_dev *, struct i40iw_puda_buf *);
-	void (*xmit_complete)(struct i40iw_sc_dev *, void *);
+	void (*receive)(struct i40iw_sc_vsi *, struct i40iw_puda_buf *);
+	void (*xmit_complete)(struct i40iw_sc_vsi *, void *);
 };
 
 struct i40iw_puda_rsrc {
@@ -116,6 +117,7 @@ struct i40iw_puda_rsrc {
 	struct i40iw_sc_qp qp;
 	struct i40iw_sc_pd sc_pd;
 	struct i40iw_sc_dev *dev;
+	struct i40iw_sc_vsi *vsi;
 	struct i40iw_dma_mem cqmem;
 	struct i40iw_dma_mem qpmem;
 	struct i40iw_virt_mem ilq_mem;
@@ -123,6 +125,7 @@ struct i40iw_puda_rsrc {
 	enum puda_resource_type type;
 	u16 buf_size;		/*buffer must be max datalen + tcpip hdr + mac */
 	u16 mss;
+	bool ceq_valid;
 	u32 cq_id;
 	u32 qp_id;
 	u32 sq_size;
@@ -142,8 +145,8 @@ struct i40iw_puda_rsrc {
 	u32 avail_buf_count;		/* snapshot of currently available buffers */
 	spinlock_t bufpool_lock;
 	struct i40iw_puda_buf *alloclist;
-	void (*receive)(struct i40iw_sc_dev *, struct i40iw_puda_buf *);
-	void (*xmit_complete)(struct i40iw_sc_dev *, void *);
+	void (*receive)(struct i40iw_sc_vsi *, struct i40iw_puda_buf *);
+	void (*xmit_complete)(struct i40iw_sc_vsi *, void *);
 	/* puda stats */
 	u64 stats_buf_alloc_fail;
 	u64 stats_pkt_rcvd;
@@ -160,14 +163,13 @@ void i40iw_puda_send_buf(struct i40iw_puda_rsrc *rsrc,
 			 struct i40iw_puda_buf *buf);
 enum i40iw_status_code i40iw_puda_send(struct i40iw_sc_qp *qp,
 				       struct i40iw_puda_send_info *info);
-enum i40iw_status_code i40iw_puda_create_rsrc(struct i40iw_sc_dev *dev,
+enum i40iw_status_code i40iw_puda_create_rsrc(struct i40iw_sc_vsi *vsi,
 					      struct i40iw_puda_rsrc_info *info);
-void i40iw_puda_dele_resources(struct i40iw_sc_dev *dev,
+void i40iw_puda_dele_resources(struct i40iw_sc_vsi *vsi,
 			       enum puda_resource_type type,
 			       bool reset);
 enum i40iw_status_code i40iw_puda_poll_completion(struct i40iw_sc_dev *dev,
 						  struct i40iw_sc_cq *cq, u32 *compl_err);
-void i40iw_ieq_cleanup_qp(struct i40iw_sc_dev *dev, struct i40iw_sc_qp *qp);
 
 struct i40iw_sc_qp *i40iw_ieq_get_qp(struct i40iw_sc_dev *dev,
 				     struct i40iw_puda_buf *buf);
@@ -180,4 +182,8 @@ void i40iw_ieq_mpa_crc_ae(struct i40iw_sc_dev *dev, struct i40iw_sc_qp *qp);
 void i40iw_free_hash_desc(struct shash_desc *desc);
 void i40iw_ieq_update_tcpip_info(struct i40iw_puda_buf *buf, u16 length,
 				 u32 seqnum);
+enum i40iw_status_code i40iw_cqp_qp_create_cmd(struct i40iw_sc_dev *dev, struct i40iw_sc_qp *qp);
+enum i40iw_status_code i40iw_cqp_cq_create_cmd(struct i40iw_sc_dev *dev, struct i40iw_sc_cq *cq);
+void i40iw_cqp_qp_destroy_cmd(struct i40iw_sc_dev *dev, struct i40iw_sc_qp *qp);
+void i40iw_cqp_cq_destroy_cmd(struct i40iw_sc_dev *dev, struct i40iw_sc_cq *cq);
 #endif

drivers/infiniband/hw/i40iw/i40iw_type.h

@@ -61,7 +61,7 @@ struct i40iw_cq_shadow_area {
 
 struct i40iw_sc_dev;
 struct i40iw_hmc_info;
-struct i40iw_dev_pestat;
+struct i40iw_vsi_pestat;
 
 struct i40iw_cqp_ops;
 struct i40iw_ccq_ops;
@@ -74,6 +74,11 @@ struct i40iw_priv_qp_ops;
 struct i40iw_priv_cq_ops;
 struct i40iw_hmc_ops;
 
+enum i40iw_page_size {
+	I40IW_PAGE_SIZE_4K,
+	I40IW_PAGE_SIZE_2M
+};
+
 enum i40iw_resource_indicator_type {
 	I40IW_RSRC_INDICATOR_TYPE_ADAPTER = 0,
 	I40IW_RSRC_INDICATOR_TYPE_CQ,
@@ -186,7 +191,7 @@ enum i40iw_debug_flag {
 	I40IW_DEBUG_ALL		= 0xFFFFFFFF
 };
 
-enum i40iw_hw_stat_index_32b {
+enum i40iw_hw_stats_index_32b {
 	I40IW_HW_STAT_INDEX_IP4RXDISCARD = 0,
 	I40IW_HW_STAT_INDEX_IP4RXTRUNC,
 	I40IW_HW_STAT_INDEX_IP4TXNOROUTE,
@@ -199,7 +204,7 @@ enum i40iw_hw_stat_index_32b {
 	I40IW_HW_STAT_INDEX_MAX_32
 };
 
-enum i40iw_hw_stat_index_64b {
+enum i40iw_hw_stats_index_64b {
 	I40IW_HW_STAT_INDEX_IP4RXOCTS = 0,
 	I40IW_HW_STAT_INDEX_IP4RXPKTS,
 	I40IW_HW_STAT_INDEX_IP4RXFRAGS,
@@ -229,32 +234,23 @@ enum i40iw_hw_stat_index_64b {
 	I40IW_HW_STAT_INDEX_MAX_64
 };
 
-struct i40iw_dev_hw_stat_offsets {
-	u32 stat_offset_32[I40IW_HW_STAT_INDEX_MAX_32];
-	u32 stat_offset_64[I40IW_HW_STAT_INDEX_MAX_64];
+struct i40iw_dev_hw_stats_offsets {
+	u32 stats_offset_32[I40IW_HW_STAT_INDEX_MAX_32];
+	u32 stats_offset_64[I40IW_HW_STAT_INDEX_MAX_64];
 };
 
 struct i40iw_dev_hw_stats {
-	u64 stat_value_32[I40IW_HW_STAT_INDEX_MAX_32];
-	u64 stat_value_64[I40IW_HW_STAT_INDEX_MAX_64];
-};
-
-struct i40iw_device_pestat_ops {
-	void (*iw_hw_stat_init)(struct i40iw_dev_pestat *, u8, struct i40iw_hw *, bool);
-	void (*iw_hw_stat_read_32)(struct i40iw_dev_pestat *, enum i40iw_hw_stat_index_32b, u64 *);
-	void (*iw_hw_stat_read_64)(struct i40iw_dev_pestat *, enum i40iw_hw_stat_index_64b, u64 *);
-	void (*iw_hw_stat_read_all)(struct i40iw_dev_pestat *, struct i40iw_dev_hw_stats *);
-	void (*iw_hw_stat_refresh_all)(struct i40iw_dev_pestat *);
+	u64 stats_value_32[I40IW_HW_STAT_INDEX_MAX_32];
+	u64 stats_value_64[I40IW_HW_STAT_INDEX_MAX_64];
 };
 
-struct i40iw_dev_pestat {
+struct i40iw_vsi_pestat {
 	struct i40iw_hw *hw;
-	struct i40iw_device_pestat_ops ops;
 	struct i40iw_dev_hw_stats hw_stats;
 	struct i40iw_dev_hw_stats last_read_hw_stats;
-	struct i40iw_dev_hw_stat_offsets hw_stat_offsets;
+	struct i40iw_dev_hw_stats_offsets hw_stats_offsets;
 	struct timer_list stats_timer;
-	spinlock_t stats_lock; /* rdma stats lock */
+	spinlock_t lock; /* rdma stats lock */
 };
 
 struct i40iw_hw {
@@ -350,6 +346,7 @@ struct i40iw_sc_cq {
 	u64 cq_pa;
 	u64 shadow_area_pa;
 	struct i40iw_sc_dev *dev;
+	struct i40iw_sc_vsi *vsi;
 	void *pbl_list;
 	void *back_cq;
 	u32 ceq_id;
@@ -373,6 +370,7 @@ struct i40iw_sc_qp {
 	u64 shadow_area_pa;
 	u64 q2_pa;
 	struct i40iw_sc_dev *dev;
+	struct i40iw_sc_vsi *vsi;
 	struct i40iw_sc_pd *pd;
 	u64 *hw_host_ctx;
 	void *llp_stream_handle;
@@ -397,6 +395,9 @@ struct i40iw_sc_qp {
 	bool virtual_map;
 	bool flush_sq;
 	bool flush_rq;
+	u8 user_pri;
+	struct list_head list;
+	bool on_qoslist;
 	bool sq_flush;
 	enum i40iw_flush_opcode flush_code;
 	enum i40iw_term_eventtypes eventtype;
@@ -424,10 +425,16 @@ struct i40iw_vchnl_vf_msg_buffer {
 	char parm_buffer[I40IW_VCHNL_MAX_VF_MSG_SIZE - 1];
 };
 
+struct i40iw_qos {
+	struct list_head qplist;
+	spinlock_t lock;	/* qos list */
+	u16 qs_handle;
+};
+
 struct i40iw_vfdev {
 	struct i40iw_sc_dev *pf_dev;
 	u8 *hmc_info_mem;
-	struct i40iw_dev_pestat dev_pestat;
+	struct i40iw_vsi_pestat pestat;
 	struct i40iw_hmc_pble_info *pble_info;
 	struct i40iw_hmc_info hmc_info;
 	struct i40iw_vchnl_vf_msg_buffer vf_msg_buffer;
@@ -441,11 +448,28 @@ struct i40iw_vfdev {
 	bool stats_initialized;
 };
 
+#define I40IW_INVALID_FCN_ID 0xff
+struct i40iw_sc_vsi {
+	struct i40iw_sc_dev *dev;
+	void *back_vsi; /* Owned by OS */
+	u32 ilq_count;
+	struct i40iw_virt_mem ilq_mem;
+	struct i40iw_puda_rsrc *ilq;
+	u32 ieq_count;
+	struct i40iw_virt_mem ieq_mem;
+	struct i40iw_puda_rsrc *ieq;
+	u16 mss;
+	u8 fcn_id;
+	bool stats_fcn_id_alloc;
+	struct i40iw_qos qos[I40IW_MAX_USER_PRIORITY];
+	struct i40iw_vsi_pestat *pestat;
+};
+
 struct i40iw_sc_dev {
 	struct list_head cqp_cmd_head;	/* head of the CQP command list */
 	spinlock_t cqp_lock; /* cqp list sync */
 	struct i40iw_dev_uk dev_uk;
-	struct i40iw_dev_pestat dev_pestat;
+	bool fcn_id_array[I40IW_MAX_STATS_COUNT];
 	struct i40iw_dma_mem vf_fpm_query_buf[I40IW_MAX_PE_ENABLED_VF_COUNT];
 	u64 fpm_query_buf_pa;
 	u64 fpm_commit_buf_pa;
@@ -472,17 +496,9 @@ struct i40iw_sc_dev {
 	struct i40iw_cqp_misc_ops *cqp_misc_ops;
 	struct i40iw_hmc_ops *hmc_ops;
 	struct i40iw_vchnl_if vchnl_if;
-	u32 ilq_count;
-	struct i40iw_virt_mem ilq_mem;
-	struct i40iw_puda_rsrc *ilq;
-	u32 ieq_count;
-	struct i40iw_virt_mem ieq_mem;
-	struct i40iw_puda_rsrc *ieq;
-
 	const struct i40iw_vf_cqp_ops *iw_vf_cqp_ops;
 
 	struct i40iw_hmc_fpm_misc hmc_fpm_misc;
-	u16 qs_handle;
 	u32 debug_mask;
 	u16 exception_lan_queue;
 	u8 hmc_fn_id;
@@ -556,6 +572,19 @@ struct i40iw_l2params {
 	u16 mss;
 };
 
+struct i40iw_vsi_init_info {
+	struct i40iw_sc_dev *dev;
+	void  *back_vsi;
+	struct i40iw_l2params *params;
+};
+
+struct i40iw_vsi_stats_info {
+	struct i40iw_vsi_pestat *pestat;
+	u8 fcn_id;
+	bool alloc_fcn_id;
+	bool stats_initialize;
+};
+
 struct i40iw_device_init_info {
 	u64 fpm_query_buf_pa;
 	u64 fpm_commit_buf_pa;
@@ -564,7 +593,6 @@ struct i40iw_device_init_info {
 	struct i40iw_hw *hw;
 	void __iomem *bar0;
 	enum i40iw_status_code (*vchnl_send)(struct i40iw_sc_dev *, u32, u8 *, u16);
-	u16 qs_handle;
 	u16 exception_lan_queue;
 	u8 hmc_fn_id;
 	bool is_pf;
@@ -722,6 +750,8 @@ struct i40iw_qp_host_ctx_info {
 	bool iwarp_info_valid;
 	bool err_rq_idx_valid;
 	u16 err_rq_idx;
+	bool add_to_qoslist;
+	u8 user_pri;
 };
 
 struct i40iw_aeqe_info {
@@ -814,6 +844,7 @@ struct i40iw_register_shared_stag {
 struct i40iw_qp_init_info {
 	struct i40iw_qp_uk_init_info qp_uk_init_info;
 	struct i40iw_sc_pd *pd;
+	struct i40iw_sc_vsi *vsi;
 	u64 *host_ctx;
 	u8 *q2;
 	u64 sq_pa;
@@ -880,13 +911,14 @@ enum i40iw_quad_hash_manage_type {
 };
 
 struct i40iw_qhash_table_info {
+	struct i40iw_sc_vsi *vsi;
 	enum i40iw_quad_hash_manage_type manage;
 	enum i40iw_quad_entry_type entry_type;
 	bool vlan_valid;
 	bool ipv4_valid;
 	u8 mac_addr[6];
 	u16 vlan_id;
-	u16 qs_handle;
+	u8 user_pri;
 	u32 qp_num;
 	u32 dest_ip[4];
 	u32 src_ip[4];
@@ -976,7 +1008,7 @@ struct i40iw_cqp_query_fpm_values {
 struct i40iw_cqp_ops {
 	enum i40iw_status_code (*cqp_init)(struct i40iw_sc_cqp *,
 					   struct i40iw_cqp_init_info *);
-	enum i40iw_status_code (*cqp_create)(struct i40iw_sc_cqp *, bool, u16 *, u16 *);
+	enum i40iw_status_code (*cqp_create)(struct i40iw_sc_cqp *, u16 *, u16 *);
 	void (*cqp_post_sq)(struct i40iw_sc_cqp *);
 	u64 *(*cqp_get_next_send_wqe)(struct i40iw_sc_cqp *, u64 scratch);
 	enum i40iw_status_code (*cqp_destroy)(struct i40iw_sc_cqp *);

drivers/infiniband/hw/i40iw/i40iw_uk.c

@@ -175,12 +175,10 @@ u64 *i40iw_qp_get_next_send_wqe(struct i40iw_qp_uk *qp,
 		if (!*wqe_idx)
 			qp->swqe_polarity = !qp->swqe_polarity;
 	}
-
-	for (i = 0; i < wqe_size / I40IW_QP_WQE_MIN_SIZE; i++) {
-		I40IW_RING_MOVE_HEAD(qp->sq_ring, ret_code);
-		if (ret_code)
-			return NULL;
-	}
+	I40IW_RING_MOVE_HEAD_BY_COUNT(qp->sq_ring,
+				      wqe_size / I40IW_QP_WQE_MIN_SIZE, ret_code);
+	if (ret_code)
+		return NULL;
 
 	wqe = qp->sq_base[*wqe_idx].elem;
 
@@ -430,7 +428,7 @@ static enum i40iw_status_code i40iw_inline_rdma_write(struct i40iw_qp_uk *qp,
 	struct i40iw_inline_rdma_write *op_info;
 	u64 *push;
 	u64 header = 0;
-	u32 i, wqe_idx;
+	u32 wqe_idx;
 	enum i40iw_status_code ret_code;
 	bool read_fence = false;
 	u8 wqe_size;
@@ -465,14 +463,12 @@ static enum i40iw_status_code i40iw_inline_rdma_write(struct i40iw_qp_uk *qp,
 	src = (u8 *)(op_info->data);
 
 	if (op_info->len <= 16) {
-		for (i = 0; i < op_info->len; i++, src++, dest++)
-			*dest = *src;
+		memcpy(dest, src, op_info->len);
 	} else {
-		for (i = 0; i < 16; i++, src++, dest++)
-			*dest = *src;
+		memcpy(dest, src, 16);
+		src += 16;
 		dest = (u8 *)wqe + 32;
-		for (; i < op_info->len; i++, src++, dest++)
-			*dest = *src;
+		memcpy(dest, src, op_info->len - 16);
 	}
 
 	wmb(); /* make sure WQE is populated before valid bit is set */
@@ -507,7 +503,7 @@ static enum i40iw_status_code i40iw_inline_send(struct i40iw_qp_uk *qp,
 	u8 *dest, *src;
 	struct i40iw_post_inline_send *op_info;
 	u64 header;
-	u32 wqe_idx, i;
+	u32 wqe_idx;
 	enum i40iw_status_code ret_code;
 	bool read_fence = false;
 	u8 wqe_size;
@@ -540,14 +536,12 @@ static enum i40iw_status_code i40iw_inline_send(struct i40iw_qp_uk *qp,
 	src = (u8 *)(op_info->data);
 
 	if (op_info->len <= 16) {
-		for (i = 0; i < op_info->len; i++, src++, dest++)
-			*dest = *src;
+		memcpy(dest, src, op_info->len);
 	} else {
-		for (i = 0; i < 16; i++, src++, dest++)
-			*dest = *src;
+		memcpy(dest, src, 16);
+		src += 16;
 		dest = (u8 *)wqe + 32;
-		for (; i < op_info->len; i++, src++, dest++)
-			*dest = *src;
+		memcpy(dest, src, op_info->len - 16);
 	}
 
 	wmb(); /* make sure WQE is populated before valid bit is set */
@@ -1190,12 +1184,8 @@ enum i40iw_status_code i40iw_inline_data_size_to_wqesize(u32 data_size,
 
 	if (data_size <= 16)
 		*wqe_size = I40IW_QP_WQE_MIN_SIZE;
-	else if (data_size <= 48)
-		*wqe_size = 64;
-	else if (data_size <= 80)
-		*wqe_size = 96;
 	else
-		*wqe_size = 128;
+		*wqe_size = 64;
 
 	return 0;
 }

drivers/infiniband/hw/i40iw/i40iw_user.h

@@ -72,12 +72,12 @@ enum i40iw_device_capabilities_const {
 	I40IW_MAX_SQ_PAYLOAD_SIZE =		2145386496,
 	I40IW_MAX_INLINE_DATA_SIZE =		48,
 	I40IW_MAX_PUSHMODE_INLINE_DATA_SIZE =	48,
-	I40IW_MAX_IRD_SIZE =			32,
-	I40IW_QPCTX_ENCD_MAXIRD =		3,
+	I40IW_MAX_IRD_SIZE =			63,
+	I40IW_MAX_ORD_SIZE =			127,
 	I40IW_MAX_WQ_ENTRIES =			2048,
-	I40IW_MAX_ORD_SIZE =			32,
 	I40IW_Q2_BUFFER_SIZE =			(248 + 100),
-	I40IW_QP_CTX_SIZE =			248
+	I40IW_QP_CTX_SIZE =			248,
+	I40IW_MAX_PDS = 			32768
 };
 
 #define i40iw_handle void *
@@ -96,12 +96,6 @@ enum i40iw_device_capabilities_const {
 #define i40iw_physical_fragment u64
 #define i40iw_address_list u64 *
 
-#define I40IW_CREATE_STAG(index, key)       (((index) << 8) + (key))
-
-#define I40IW_STAG_KEY_FROM_STAG(stag)      ((stag) && 0x000000FF)
-
-#define I40IW_STAG_INDEX_FROM_STAG(stag)    (((stag) && 0xFFFFFF00) >> 8)
-
 #define	I40IW_MAX_MR_SIZE	0x10000000000L
 
 struct i40iw_qp_uk;

drivers/infiniband/hw/i40iw/i40iw_utils.c

@@ -153,6 +153,7 @@ int i40iw_inetaddr_event(struct notifier_block *notifier,
 	struct i40iw_device *iwdev;
 	struct i40iw_handler *hdl;
 	u32 local_ipaddr;
+	u32 action = I40IW_ARP_ADD;
 
 	hdl = i40iw_find_netdev(event_netdev);
 	if (!hdl)
@@ -164,44 +165,25 @@ int i40iw_inetaddr_event(struct notifier_block *notifier,
 	if (netdev != event_netdev)
 		return NOTIFY_DONE;
 
+	if (upper_dev)
+		local_ipaddr = ntohl(
+			((struct in_device *)upper_dev->ip_ptr)->ifa_list->ifa_address);
+	else
+		local_ipaddr = ntohl(ifa->ifa_address);
 	switch (event) {
 	case NETDEV_DOWN:
-		if (upper_dev)
-			local_ipaddr = ntohl(
-				((struct in_device *)upper_dev->ip_ptr)->ifa_list->ifa_address);
-		else
-			local_ipaddr = ntohl(ifa->ifa_address);
-		i40iw_manage_arp_cache(iwdev,
-				       netdev->dev_addr,
-				       &local_ipaddr,
-				       true,
-				       I40IW_ARP_DELETE);
-		return NOTIFY_OK;
+		action = I40IW_ARP_DELETE;
+		/* Fall through */
 	case NETDEV_UP:
-		if (upper_dev)
-			local_ipaddr = ntohl(
-				((struct in_device *)upper_dev->ip_ptr)->ifa_list->ifa_address);
-		else
-			local_ipaddr = ntohl(ifa->ifa_address);
-		i40iw_manage_arp_cache(iwdev,
-				       netdev->dev_addr,
-				       &local_ipaddr,
-				       true,
-				       I40IW_ARP_ADD);
-		break;
+		/* Fall through */
 	case NETDEV_CHANGEADDR:
-		/* Add the address to the IP table */
-		if (upper_dev)
-			local_ipaddr = ntohl(
-				((struct in_device *)upper_dev->ip_ptr)->ifa_list->ifa_address);
-		else
-			local_ipaddr = ntohl(ifa->ifa_address);
-
 		i40iw_manage_arp_cache(iwdev,
 				       netdev->dev_addr,
 				       &local_ipaddr,
 				       true,
-				       I40IW_ARP_ADD);
+				       action);
+		i40iw_if_notify(iwdev, netdev, &local_ipaddr, true,
+				(action == I40IW_ARP_ADD) ? true : false);
 		break;
 	default:
 		break;
@@ -225,6 +207,7 @@ int i40iw_inet6addr_event(struct notifier_block *notifier,
 	struct i40iw_device *iwdev;
 	struct i40iw_handler *hdl;
 	u32 local_ipaddr6[4];
+	u32 action = I40IW_ARP_ADD;
 
 	hdl = i40iw_find_netdev(event_netdev);
 	if (!hdl)
@@ -235,24 +218,21 @@ int i40iw_inet6addr_event(struct notifier_block *notifier,
 	if (netdev != event_netdev)
 		return NOTIFY_DONE;
 
+	i40iw_copy_ip_ntohl(local_ipaddr6, ifa->addr.in6_u.u6_addr32);
 	switch (event) {
 	case NETDEV_DOWN:
-		i40iw_copy_ip_ntohl(local_ipaddr6, ifa->addr.in6_u.u6_addr32);
-		i40iw_manage_arp_cache(iwdev,
-				       netdev->dev_addr,
-				       local_ipaddr6,
-				       false,
-				       I40IW_ARP_DELETE);
-		return NOTIFY_OK;
+		action = I40IW_ARP_DELETE;
+		/* Fall through */
 	case NETDEV_UP:
 		/* Fall through */
 	case NETDEV_CHANGEADDR:
-		i40iw_copy_ip_ntohl(local_ipaddr6, ifa->addr.in6_u.u6_addr32);
 		i40iw_manage_arp_cache(iwdev,
 				       netdev->dev_addr,
 				       local_ipaddr6,
 				       false,
-				       I40IW_ARP_ADD);
+				       action);
+		i40iw_if_notify(iwdev, netdev, local_ipaddr6, false,
+				(action == I40IW_ARP_ADD) ? true : false);
 		break;
 	default:
 		break;
@@ -392,6 +372,7 @@ static void i40iw_free_qp(struct i40iw_cqp_request *cqp_request, u32 num)
 
 	i40iw_rem_pdusecount(iwqp->iwpd, iwdev);
 	i40iw_free_qp_resources(iwdev, iwqp, qp_num);
+	i40iw_rem_devusecount(iwdev);
 }
 
 /**
@@ -415,7 +396,10 @@ static int i40iw_wait_event(struct i40iw_device *iwdev,
 		i40iw_pr_err("error cqp command 0x%x timed out ret = %d\n",
 			     info->cqp_cmd, timeout_ret);
 		err_code = -ETIME;
-		i40iw_request_reset(iwdev);
+		if (!iwdev->reset) {
+			iwdev->reset = true;
+			i40iw_request_reset(iwdev);
+		}
 		goto done;
 	}
 	cqp_error = cqp_request->compl_info.error;
@@ -445,6 +429,11 @@ enum i40iw_status_code i40iw_handle_cqp_op(struct i40iw_device *iwdev,
 	struct cqp_commands_info *info = &cqp_request->info;
 	int err_code = 0;
 
+	if (iwdev->reset) {
+		i40iw_free_cqp_request(&iwdev->cqp, cqp_request);
+		return I40IW_ERR_CQP_COMPL_ERROR;
+	}
+
 	status = i40iw_process_cqp_cmd(dev, info);
 	if (status) {
 		i40iw_pr_err("error cqp command 0x%x failed\n", info->cqp_cmd);
@@ -458,6 +447,26 @@ enum i40iw_status_code i40iw_handle_cqp_op(struct i40iw_device *iwdev,
 	return status;
 }
 
+/**
+ * i40iw_add_devusecount - add dev refcount
+ * @iwdev: dev for refcount
+ */
+void i40iw_add_devusecount(struct i40iw_device *iwdev)
+{
+	atomic64_inc(&iwdev->use_count);
+}
+
+/**
+ * i40iw_rem_devusecount - decrement refcount for dev
+ * @iwdev: device
+ */
+void i40iw_rem_devusecount(struct i40iw_device *iwdev)
+{
+	if (!atomic64_dec_and_test(&iwdev->use_count))
+		return;
+	wake_up(&iwdev->close_wq);
+}
+
 /**
  * i40iw_add_pdusecount - add pd refcount
  * @iwpd: pd for refcount
@@ -711,6 +720,51 @@ enum i40iw_status_code i40iw_cqp_sds_cmd(struct i40iw_sc_dev *dev,
 	return status;
 }
 
+/**
+ * i40iw_qp_suspend_resume - cqp command for suspend/resume
+ * @dev: hardware control device structure
+ * @qp: hardware control qp
+ * @suspend: flag if suspend or resume
+ */
+void i40iw_qp_suspend_resume(struct i40iw_sc_dev *dev, struct i40iw_sc_qp *qp, bool suspend)
+{
+	struct i40iw_device *iwdev = (struct i40iw_device *)dev->back_dev;
+	struct i40iw_cqp_request *cqp_request;
+	struct i40iw_sc_cqp *cqp = dev->cqp;
+	struct cqp_commands_info *cqp_info;
+	enum i40iw_status_code status;
+
+	cqp_request = i40iw_get_cqp_request(&iwdev->cqp, false);
+	if (!cqp_request)
+		return;
+
+	cqp_info = &cqp_request->info;
+	cqp_info->cqp_cmd = (suspend) ? OP_SUSPEND : OP_RESUME;
+	cqp_info->in.u.suspend_resume.cqp = cqp;
+	cqp_info->in.u.suspend_resume.qp = qp;
+	cqp_info->in.u.suspend_resume.scratch = (uintptr_t)cqp_request;
+	status = i40iw_handle_cqp_op(iwdev, cqp_request);
+	if (status)
+		i40iw_pr_err("CQP-OP QP Suspend/Resume fail");
+}
+
+/**
+ * i40iw_qp_mss_modify - modify mss for qp
+ * @dev: hardware control device structure
+ * @qp: hardware control qp
+ */
+void i40iw_qp_mss_modify(struct i40iw_sc_dev *dev, struct i40iw_sc_qp *qp)
+{
+	struct i40iw_device *iwdev = (struct i40iw_device *)dev->back_dev;
+	struct i40iw_qp *iwqp = (struct i40iw_qp *)qp->back_qp;
+	struct i40iw_modify_qp_info info;
+
+	memset(&info, 0, sizeof(info));
+	info.mss_change = true;
+	info.new_mss = qp->vsi->mss;
+	i40iw_hw_modify_qp(iwdev, iwqp, &info, false);
+}
+
 /**
  * i40iw_term_modify_qp - modify qp for term message
  * @qp: hardware control qp
@@ -769,6 +823,7 @@ static void i40iw_terminate_timeout(unsigned long context)
 	struct i40iw_sc_qp *qp = (struct i40iw_sc_qp *)&iwqp->sc_qp;
 
 	i40iw_terminate_done(qp, 1);
+	i40iw_rem_ref(&iwqp->ibqp);
 }
 
 /**
@@ -780,6 +835,7 @@ void i40iw_terminate_start_timer(struct i40iw_sc_qp *qp)
 	struct i40iw_qp *iwqp;
 
 	iwqp = (struct i40iw_qp *)qp->back_qp;
+	i40iw_add_ref(&iwqp->ibqp);
 	init_timer(&iwqp->terminate_timer);
 	iwqp->terminate_timer.function = i40iw_terminate_timeout;
 	iwqp->terminate_timer.expires = jiffies + HZ;
@@ -796,7 +852,8 @@ void i40iw_terminate_del_timer(struct i40iw_sc_qp *qp)
 	struct i40iw_qp *iwqp;
 
 	iwqp = (struct i40iw_qp *)qp->back_qp;
-	del_timer(&iwqp->terminate_timer);
+	if (del_timer(&iwqp->terminate_timer))
+		i40iw_rem_ref(&iwqp->ibqp);
 }
 
 /**
@@ -1010,6 +1067,116 @@ enum i40iw_status_code i40iw_vf_wait_vchnl_resp(struct i40iw_sc_dev *dev)
 	return 0;
 }
 
+/**
+ * i40iw_cqp_cq_create_cmd - create a cq for the cqp
+ * @dev: device pointer
+ * @cq: pointer to created cq
+ */
+enum i40iw_status_code i40iw_cqp_cq_create_cmd(struct i40iw_sc_dev *dev,
+					       struct i40iw_sc_cq *cq)
+{
+	struct i40iw_device *iwdev = (struct i40iw_device *)dev->back_dev;
+	struct i40iw_cqp *iwcqp = &iwdev->cqp;
+	struct i40iw_cqp_request *cqp_request;
+	struct cqp_commands_info *cqp_info;
+	enum i40iw_status_code status;
+
+	cqp_request = i40iw_get_cqp_request(iwcqp, true);
+	if (!cqp_request)
+		return I40IW_ERR_NO_MEMORY;
+
+	cqp_info = &cqp_request->info;
+	cqp_info->cqp_cmd = OP_CQ_CREATE;
+	cqp_info->post_sq = 1;
+	cqp_info->in.u.cq_create.cq = cq;
+	cqp_info->in.u.cq_create.scratch = (uintptr_t)cqp_request;
+	status = i40iw_handle_cqp_op(iwdev, cqp_request);
+	if (status)
+		i40iw_pr_err("CQP-OP Create QP fail");
+
+	return status;
+}
+
+/**
+ * i40iw_cqp_qp_create_cmd - create a qp for the cqp
+ * @dev: device pointer
+ * @qp: pointer to created qp
+ */
+enum i40iw_status_code i40iw_cqp_qp_create_cmd(struct i40iw_sc_dev *dev,
+					       struct i40iw_sc_qp *qp)
+{
+	struct i40iw_device *iwdev = (struct i40iw_device *)dev->back_dev;
+	struct i40iw_cqp *iwcqp = &iwdev->cqp;
+	struct i40iw_cqp_request *cqp_request;
+	struct cqp_commands_info *cqp_info;
+	struct i40iw_create_qp_info *qp_info;
+	enum i40iw_status_code status;
+
+	cqp_request = i40iw_get_cqp_request(iwcqp, true);
+	if (!cqp_request)
+		return I40IW_ERR_NO_MEMORY;
+
+	cqp_info = &cqp_request->info;
+	qp_info = &cqp_request->info.in.u.qp_create.info;
+
+	memset(qp_info, 0, sizeof(*qp_info));
+
+	qp_info->cq_num_valid = true;
+	qp_info->next_iwarp_state = I40IW_QP_STATE_RTS;
+
+	cqp_info->cqp_cmd = OP_QP_CREATE;
+	cqp_info->post_sq = 1;
+	cqp_info->in.u.qp_create.qp = qp;
+	cqp_info->in.u.qp_create.scratch = (uintptr_t)cqp_request;
+	status = i40iw_handle_cqp_op(iwdev, cqp_request);
+	if (status)
+		i40iw_pr_err("CQP-OP QP create fail");
+	return status;
+}
+
+/**
+ * i40iw_cqp_cq_destroy_cmd - destroy the cqp cq
+ * @dev: device pointer
+ * @cq: pointer to cq
+ */
+void i40iw_cqp_cq_destroy_cmd(struct i40iw_sc_dev *dev, struct i40iw_sc_cq *cq)
+{
+	struct i40iw_device *iwdev = (struct i40iw_device *)dev->back_dev;
+
+	i40iw_cq_wq_destroy(iwdev, cq);
+}
+
+/**
+ * i40iw_cqp_qp_destroy_cmd - destroy the cqp
+ * @dev: device pointer
+ * @qp: pointer to qp
+ */
+void i40iw_cqp_qp_destroy_cmd(struct i40iw_sc_dev *dev, struct i40iw_sc_qp *qp)
+{
+	struct i40iw_device *iwdev = (struct i40iw_device *)dev->back_dev;
+	struct i40iw_cqp *iwcqp = &iwdev->cqp;
+	struct i40iw_cqp_request *cqp_request;
+	struct cqp_commands_info *cqp_info;
+	enum i40iw_status_code status;
+
+	cqp_request = i40iw_get_cqp_request(iwcqp, true);
+	if (!cqp_request)
+		return;
+
+	cqp_info = &cqp_request->info;
+	memset(cqp_info, 0, sizeof(*cqp_info));
+
+	cqp_info->cqp_cmd = OP_QP_DESTROY;
+	cqp_info->post_sq = 1;
+	cqp_info->in.u.qp_destroy.qp = qp;
+	cqp_info->in.u.qp_destroy.scratch = (uintptr_t)cqp_request;
+	cqp_info->in.u.qp_destroy.remove_hash_idx = true;
+	status = i40iw_handle_cqp_op(iwdev, cqp_request);
+	if (status)
+		i40iw_pr_err("CQP QP_DESTROY fail");
+}
+
+
 /**
  * i40iw_ieq_mpa_crc_ae - generate AE for crc error
  * @dev: hardware control device structure
@@ -1208,7 +1375,7 @@ enum i40iw_status_code i40iw_puda_get_tcpip_info(struct i40iw_puda_completion_in
 
 	buf->totallen = pkt_len + buf->maclen;
 
-	if (info->payload_len < buf->totallen - 4) {
+	if (info->payload_len < buf->totallen) {
 		i40iw_pr_err("payload_len = 0x%x totallen expected0x%x\n",
 			     info->payload_len, buf->totallen);
 		return I40IW_ERR_INVALID_SIZE;
@@ -1224,27 +1391,29 @@ enum i40iw_status_code i40iw_puda_get_tcpip_info(struct i40iw_puda_completion_in
 
 /**
  * i40iw_hw_stats_timeout - Stats timer-handler which updates all HW stats
- * @dev: hardware control device structure
+ * @vsi: pointer to the vsi structure
  */
-static void i40iw_hw_stats_timeout(unsigned long dev)
+static void i40iw_hw_stats_timeout(unsigned long vsi)
 {
-	struct i40iw_sc_dev *pf_dev = (struct i40iw_sc_dev *)dev;
-	struct i40iw_dev_pestat *pf_devstat = &pf_dev->dev_pestat;
-	struct i40iw_dev_pestat *vf_devstat = NULL;
+	struct i40iw_sc_vsi *sc_vsi =  (struct i40iw_sc_vsi *)vsi;
+	struct i40iw_sc_dev *pf_dev = sc_vsi->dev;
+	struct i40iw_vsi_pestat *pf_devstat = sc_vsi->pestat;
+	struct i40iw_vsi_pestat *vf_devstat = NULL;
 	u16 iw_vf_idx;
 	unsigned long flags;
 
 	/*PF*/
-	pf_devstat->ops.iw_hw_stat_read_all(pf_devstat, &pf_devstat->hw_stats);
+	i40iw_hw_stats_read_all(pf_devstat, &pf_devstat->hw_stats);
+
 	for (iw_vf_idx = 0; iw_vf_idx < I40IW_MAX_PE_ENABLED_VF_COUNT; iw_vf_idx++) {
-		spin_lock_irqsave(&pf_devstat->stats_lock, flags);
+		spin_lock_irqsave(&pf_devstat->lock, flags);
 		if (pf_dev->vf_dev[iw_vf_idx]) {
 			if (pf_dev->vf_dev[iw_vf_idx]->stats_initialized) {
-				vf_devstat = &pf_dev->vf_dev[iw_vf_idx]->dev_pestat;
-				vf_devstat->ops.iw_hw_stat_read_all(vf_devstat, &vf_devstat->hw_stats);
+				vf_devstat = &pf_dev->vf_dev[iw_vf_idx]->pestat;
+				i40iw_hw_stats_read_all(vf_devstat, &vf_devstat->hw_stats);
 			}
 		}
-		spin_unlock_irqrestore(&pf_devstat->stats_lock, flags);
+		spin_unlock_irqrestore(&pf_devstat->lock, flags);
 	}
 
 	mod_timer(&pf_devstat->stats_timer,
@@ -1253,26 +1422,26 @@ static void i40iw_hw_stats_timeout(unsigned long dev)
 
 /**
  * i40iw_hw_stats_start_timer - Start periodic stats timer
- * @dev: hardware control device structure
+ * @vsi: pointer to the vsi structure
  */
-void i40iw_hw_stats_start_timer(struct i40iw_sc_dev *dev)
+void i40iw_hw_stats_start_timer(struct i40iw_sc_vsi *vsi)
 {
-	struct i40iw_dev_pestat *devstat = &dev->dev_pestat;
+	struct i40iw_vsi_pestat *devstat = vsi->pestat;
 
 	init_timer(&devstat->stats_timer);
 	devstat->stats_timer.function = i40iw_hw_stats_timeout;
-	devstat->stats_timer.data = (unsigned long)dev;
+	devstat->stats_timer.data = (unsigned long)vsi;
 	mod_timer(&devstat->stats_timer,
 		  jiffies + msecs_to_jiffies(STATS_TIMER_DELAY));
 }
 
 /**
- * i40iw_hw_stats_del_timer - Delete periodic stats timer
- * @dev: hardware control device structure
+ * i40iw_hw_stats_stop_timer - Delete periodic stats timer
+ * @vsi: pointer to the vsi structure
  */
-void i40iw_hw_stats_del_timer(struct i40iw_sc_dev *dev)
+void i40iw_hw_stats_stop_timer(struct i40iw_sc_vsi *vsi)
 {
-	struct i40iw_dev_pestat *devstat = &dev->dev_pestat;
+	struct i40iw_vsi_pestat *devstat = vsi->pestat;
 
 	del_timer_sync(&devstat->stats_timer);
 }

drivers/infiniband/hw/i40iw/i40iw_verbs.c

@@ -37,6 +37,7 @@
 #include <linux/random.h>
 #include <linux/highmem.h>
 #include <linux/time.h>
+#include <linux/hugetlb.h>
 #include <asm/byteorder.h>
 #include <net/ip.h>
 #include <rdma/ib_verbs.h>
@@ -67,13 +68,13 @@ static int i40iw_query_device(struct ib_device *ibdev,
 	props->vendor_part_id = iwdev->ldev->pcidev->device;
 	props->hw_ver = (u32)iwdev->sc_dev.hw_rev;
 	props->max_mr_size = I40IW_MAX_OUTBOUND_MESSAGE_SIZE;
-	props->max_qp = iwdev->max_qp;
+	props->max_qp = iwdev->max_qp - iwdev->used_qps;
 	props->max_qp_wr = (I40IW_MAX_WQ_ENTRIES >> 2) - 1;
 	props->max_sge = I40IW_MAX_WQ_FRAGMENT_COUNT;
-	props->max_cq = iwdev->max_cq;
+	props->max_cq = iwdev->max_cq - iwdev->used_cqs;
 	props->max_cqe = iwdev->max_cqe;
-	props->max_mr = iwdev->max_mr;
-	props->max_pd = iwdev->max_pd;
+	props->max_mr = iwdev->max_mr - iwdev->used_mrs;
+	props->max_pd = iwdev->max_pd - iwdev->used_pds;
 	props->max_sge_rd = I40IW_MAX_SGE_RD;
 	props->max_qp_rd_atom = I40IW_MAX_IRD_SIZE;
 	props->max_qp_init_rd_atom = props->max_qp_rd_atom;
@@ -254,7 +255,6 @@ static void i40iw_alloc_push_page(struct i40iw_device *iwdev, struct i40iw_sc_qp
 {
 	struct i40iw_cqp_request *cqp_request;
 	struct cqp_commands_info *cqp_info;
-	struct i40iw_sc_dev *dev = &iwdev->sc_dev;
 	enum i40iw_status_code status;
 
 	if (qp->push_idx != I40IW_INVALID_PUSH_PAGE_INDEX)
@@ -270,7 +270,7 @@ static void i40iw_alloc_push_page(struct i40iw_device *iwdev, struct i40iw_sc_qp
 	cqp_info->cqp_cmd = OP_MANAGE_PUSH_PAGE;
 	cqp_info->post_sq = 1;
 
-	cqp_info->in.u.manage_push_page.info.qs_handle = dev->qs_handle;
+	cqp_info->in.u.manage_push_page.info.qs_handle = qp->qs_handle;
 	cqp_info->in.u.manage_push_page.info.free_page = 0;
 	cqp_info->in.u.manage_push_page.cqp = &iwdev->cqp.sc_cqp;
 	cqp_info->in.u.manage_push_page.scratch = (uintptr_t)cqp_request;
@@ -292,7 +292,6 @@ static void i40iw_dealloc_push_page(struct i40iw_device *iwdev, struct i40iw_sc_
 {
 	struct i40iw_cqp_request *cqp_request;
 	struct cqp_commands_info *cqp_info;
-	struct i40iw_sc_dev *dev = &iwdev->sc_dev;
 	enum i40iw_status_code status;
 
 	if (qp->push_idx == I40IW_INVALID_PUSH_PAGE_INDEX)
@@ -307,7 +306,7 @@ static void i40iw_dealloc_push_page(struct i40iw_device *iwdev, struct i40iw_sc_
 	cqp_info->post_sq = 1;
 
 	cqp_info->in.u.manage_push_page.info.push_idx = qp->push_idx;
-	cqp_info->in.u.manage_push_page.info.qs_handle = dev->qs_handle;
+	cqp_info->in.u.manage_push_page.info.qs_handle = qp->qs_handle;
 	cqp_info->in.u.manage_push_page.info.free_page = 1;
 	cqp_info->in.u.manage_push_page.cqp = &iwdev->cqp.sc_cqp;
 	cqp_info->in.u.manage_push_page.scratch = (uintptr_t)cqp_request;
@@ -337,6 +336,9 @@ static struct ib_pd *i40iw_alloc_pd(struct ib_device *ibdev,
 	u32 pd_id = 0;
 	int err;
 
+	if (iwdev->closing)
+		return ERR_PTR(-ENODEV);
+
 	err = i40iw_alloc_resource(iwdev, iwdev->allocated_pds,
 				   iwdev->max_pd, &pd_id, &iwdev->next_pd);
 	if (err) {
@@ -602,6 +604,9 @@ static struct ib_qp *i40iw_create_qp(struct ib_pd *ibpd,
 	struct i40iwarp_offload_info *iwarp_info;
 	unsigned long flags;
 
+	if (iwdev->closing)
+		return ERR_PTR(-ENODEV);
+
 	if (init_attr->create_flags)
 		return ERR_PTR(-EINVAL);
 	if (init_attr->cap.max_inline_data > I40IW_MAX_INLINE_DATA_SIZE)
@@ -610,11 +615,15 @@ static struct ib_qp *i40iw_create_qp(struct ib_pd *ibpd,
 	if (init_attr->cap.max_send_sge > I40IW_MAX_WQ_FRAGMENT_COUNT)
 		init_attr->cap.max_send_sge = I40IW_MAX_WQ_FRAGMENT_COUNT;
 
+	if (init_attr->cap.max_recv_sge > I40IW_MAX_WQ_FRAGMENT_COUNT)
+		init_attr->cap.max_recv_sge = I40IW_MAX_WQ_FRAGMENT_COUNT;
+
 	memset(&init_info, 0, sizeof(init_info));
 
 	sq_size = init_attr->cap.max_send_wr;
 	rq_size = init_attr->cap.max_recv_wr;
 
+	init_info.vsi = &iwdev->vsi;
 	init_info.qp_uk_init_info.sq_size = sq_size;
 	init_info.qp_uk_init_info.rq_size = rq_size;
 	init_info.qp_uk_init_info.max_sq_frag_cnt = init_attr->cap.max_send_sge;
@@ -774,6 +783,7 @@ static struct ib_qp *i40iw_create_qp(struct ib_pd *ibpd,
 	iwqp->sig_all = (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR) ? 1 : 0;
 	iwdev->qp_table[qp_num] = iwqp;
 	i40iw_add_pdusecount(iwqp->iwpd);
+	i40iw_add_devusecount(iwdev);
 	if (ibpd->uobject && udata) {
 		memset(&uresp, 0, sizeof(uresp));
 		uresp.actual_sq_size = sq_size;
@@ -815,8 +825,9 @@ static int i40iw_query_qp(struct ib_qp *ibqp,
 	attr->qp_access_flags = 0;
 	attr->cap.max_send_wr = qp->qp_uk.sq_size;
 	attr->cap.max_recv_wr = qp->qp_uk.rq_size;
-	attr->cap.max_recv_sge = 1;
 	attr->cap.max_inline_data = I40IW_MAX_INLINE_DATA_SIZE;
+	attr->cap.max_send_sge = I40IW_MAX_WQ_FRAGMENT_COUNT;
+	attr->cap.max_recv_sge = I40IW_MAX_WQ_FRAGMENT_COUNT;
 	init_attr->event_handler = iwqp->ibqp.event_handler;
 	init_attr->qp_context = iwqp->ibqp.qp_context;
 	init_attr->send_cq = iwqp->ibqp.send_cq;
@@ -884,6 +895,11 @@ int i40iw_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	spin_lock_irqsave(&iwqp->lock, flags);
 
 	if (attr_mask & IB_QP_STATE) {
+		if (iwdev->closing && attr->qp_state != IB_QPS_ERR) {
+			err = -EINVAL;
+			goto exit;
+		}
+
 		switch (attr->qp_state) {
 		case IB_QPS_INIT:
 		case IB_QPS_RTR:
@@ -944,7 +960,7 @@ int i40iw_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 				goto exit;
 			}
 			if (iwqp->sc_qp.term_flags)
-				del_timer(&iwqp->terminate_timer);
+				i40iw_terminate_del_timer(&iwqp->sc_qp);
 			info.next_iwarp_state = I40IW_QP_STATE_ERROR;
 			if ((iwqp->hw_tcp_state > I40IW_TCP_STATE_CLOSED) &&
 			    iwdev->iw_status &&
@@ -1037,11 +1053,11 @@ static void cq_free_resources(struct i40iw_device *iwdev, struct i40iw_cq *iwcq)
 }
 
 /**
- * cq_wq_destroy - send cq destroy cqp
+ * i40iw_cq_wq_destroy - send cq destroy cqp
  * @iwdev: iwarp device
  * @cq: hardware control cq
  */
-static void cq_wq_destroy(struct i40iw_device *iwdev, struct i40iw_sc_cq *cq)
+void i40iw_cq_wq_destroy(struct i40iw_device *iwdev, struct i40iw_sc_cq *cq)
 {
 	enum i40iw_status_code status;
 	struct i40iw_cqp_request *cqp_request;
@@ -1080,9 +1096,10 @@ static int i40iw_destroy_cq(struct ib_cq *ib_cq)
 	iwcq = to_iwcq(ib_cq);
 	iwdev = to_iwdev(ib_cq->device);
 	cq = &iwcq->sc_cq;
-	cq_wq_destroy(iwdev, cq);
+	i40iw_cq_wq_destroy(iwdev, cq);
 	cq_free_resources(iwdev, iwcq);
 	kfree(iwcq);
+	i40iw_rem_devusecount(iwdev);
 	return 0;
 }
 
@@ -1113,6 +1130,9 @@ static struct ib_cq *i40iw_create_cq(struct ib_device *ibdev,
 	int err_code;
 	int entries = attr->cqe;
 
+	if (iwdev->closing)
+		return ERR_PTR(-ENODEV);
+
 	if (entries > iwdev->max_cqe)
 		return ERR_PTR(-EINVAL);
 
@@ -1137,7 +1157,8 @@ static struct ib_cq *i40iw_create_cq(struct ib_device *ibdev,
 	ukinfo->cq_id = cq_num;
 	iwcq->ibcq.cqe = info.cq_uk_init_info.cq_size;
 	info.ceqe_mask = 0;
-	info.ceq_id = 0;
+	if (attr->comp_vector < iwdev->ceqs_count)
+		info.ceq_id = attr->comp_vector;
 	info.ceq_id_valid = true;
 	info.ceqe_mask = 1;
 	info.type = I40IW_CQ_TYPE_IWARP;
@@ -1229,10 +1250,11 @@ static struct ib_cq *i40iw_create_cq(struct ib_device *ibdev,
 		}
 	}
 
+	i40iw_add_devusecount(iwdev);
 	return (struct ib_cq *)iwcq;
 
 cq_destroy:
-	cq_wq_destroy(iwdev, cq);
+	i40iw_cq_wq_destroy(iwdev, cq);
 cq_free_resources:
 	cq_free_resources(iwdev, iwcq);
 error:
@@ -1266,6 +1288,7 @@ static void i40iw_free_stag(struct i40iw_device *iwdev, u32 stag)
 
 	stag_idx = (stag & iwdev->mr_stagmask) >> I40IW_CQPSQ_STAG_IDX_SHIFT;
 	i40iw_free_resource(iwdev, iwdev->allocated_mrs, stag_idx);
+	i40iw_rem_devusecount(iwdev);
 }
 
 /**
@@ -1296,19 +1319,18 @@ static u32 i40iw_create_stag(struct i40iw_device *iwdev)
 		stag = stag_index << I40IW_CQPSQ_STAG_IDX_SHIFT;
 		stag |= driver_key;
 		stag += (u32)consumer_key;
+		i40iw_add_devusecount(iwdev);
 	}
 	return stag;
 }
 
 /**
  * i40iw_next_pbl_addr - Get next pbl address
- * @palloc: Poiner to allocated pbles
  * @pbl: pointer to a pble
  * @pinfo: info pointer
  * @idx: index
  */
-static inline u64 *i40iw_next_pbl_addr(struct i40iw_pble_alloc *palloc,
-				       u64 *pbl,
+static inline u64 *i40iw_next_pbl_addr(u64 *pbl,
 				       struct i40iw_pble_info **pinfo,
 				       u32 *idx)
 {
@@ -1336,9 +1358,11 @@ static void i40iw_copy_user_pgaddrs(struct i40iw_mr *iwmr,
 	struct i40iw_pble_alloc *palloc = &iwpbl->pble_alloc;
 	struct i40iw_pble_info *pinfo;
 	struct scatterlist *sg;
+	u64 pg_addr = 0;
 	u32 idx = 0;
 
 	pinfo = (level == I40IW_LEVEL_1) ? NULL : palloc->level2.leaf;
+
 	pg_shift = ffs(region->page_size) - 1;
 	for_each_sg(region->sg_head.sgl, sg, region->nmap, entry) {
 		chunk_pages = sg_dma_len(sg) >> pg_shift;
@@ -1346,17 +1370,96 @@ static void i40iw_copy_user_pgaddrs(struct i40iw_mr *iwmr,
 		    !iwpbl->qp_mr.sq_page)
 			iwpbl->qp_mr.sq_page = sg_page(sg);
 		for (i = 0; i < chunk_pages; i++) {
-			*pbl = cpu_to_le64(sg_dma_address(sg) + region->page_size * i);
-			pbl = i40iw_next_pbl_addr(palloc, pbl, &pinfo, &idx);
+			pg_addr = sg_dma_address(sg) + region->page_size * i;
+
+			if ((entry + i) == 0)
+				*pbl = cpu_to_le64(pg_addr & iwmr->page_msk);
+			else if (!(pg_addr & ~iwmr->page_msk))
+				*pbl = cpu_to_le64(pg_addr);
+			else
+				continue;
+			pbl = i40iw_next_pbl_addr(pbl, &pinfo, &idx);
+		}
+	}
+}
+
+/**
+ * i40iw_set_hugetlb_params - set MR pg size and mask to huge pg values.
+ * @addr: virtual address
+ * @iwmr: mr pointer for this memory registration
+ */
+static void i40iw_set_hugetlb_values(u64 addr, struct i40iw_mr *iwmr)
+{
+	struct vm_area_struct *vma;
+	struct hstate *h;
+
+	vma = find_vma(current->mm, addr);
+	if (vma && is_vm_hugetlb_page(vma)) {
+		h = hstate_vma(vma);
+		if (huge_page_size(h) == 0x200000) {
+			iwmr->page_size = huge_page_size(h);
+			iwmr->page_msk = huge_page_mask(h);
 		}
 	}
 }
 
+/**
+ * i40iw_check_mem_contiguous - check if pbls stored in arr are contiguous
+ * @arr: lvl1 pbl array
+ * @npages: page count
+ * pg_size: page size
+ *
+ */
+static bool i40iw_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])
+			return false;
+	}
+	return true;
+}
+
+/**
+ * i40iw_check_mr_contiguous - check if MR is physically contiguous
+ * @palloc: pbl allocation struct
+ * pg_size: page size
+ */
+static bool i40iw_check_mr_contiguous(struct i40iw_pble_alloc *palloc, u32 pg_size)
+{
+	struct i40iw_pble_level2 *lvl2 = &palloc->level2;
+	struct i40iw_pble_info *leaf = lvl2->leaf;
+	u64 *arr = NULL;
+	u64 *start_addr = NULL;
+	int i;
+	bool ret;
+
+	if (palloc->level == I40IW_LEVEL_1) {
+		arr = (u64 *)palloc->level1.addr;
+		ret = i40iw_check_mem_contiguous(arr, palloc->total_cnt, pg_size);
+		return ret;
+	}
+
+	start_addr = (u64 *)leaf->addr;
+
+	for (i = 0; i < lvl2->leaf_cnt; i++, leaf++) {
+		arr = (u64 *)leaf->addr;
+		if ((*start_addr + (i * pg_size * PBLE_PER_PAGE)) != *arr)
+			return false;
+		ret = i40iw_check_mem_contiguous(arr, leaf->cnt, pg_size);
+		if (!ret)
+			return false;
+	}
+
+	return true;
+}
+
 /**
  * i40iw_setup_pbles - copy user pg address to pble's
  * @iwdev: iwarp device
  * @iwmr: mr pointer for this memory registration
- * @use_pbles: flag if to use pble's or memory (level 0)
+ * @use_pbles: flag if to use pble's
  */
 static int i40iw_setup_pbles(struct i40iw_device *iwdev,
 			     struct i40iw_mr *iwmr,
@@ -1369,9 +1472,6 @@ static int i40iw_setup_pbles(struct i40iw_device *iwdev,
 	enum i40iw_status_code status;
 	enum i40iw_pble_level level = I40IW_LEVEL_1;
 
-	if (!use_pbles && (iwmr->page_cnt > MAX_SAVE_PAGE_ADDRS))
-		return -ENOMEM;
-
 	if (use_pbles) {
 		mutex_lock(&iwdev->pbl_mutex);
 		status = i40iw_get_pble(&iwdev->sc_dev, iwdev->pble_rsrc, palloc, iwmr->page_cnt);
@@ -1388,6 +1488,10 @@ static int i40iw_setup_pbles(struct i40iw_device *iwdev,
 	}
 
 	i40iw_copy_user_pgaddrs(iwmr, pbl, level);
+
+	if (use_pbles)
+		iwmr->pgaddrmem[0] = *pbl;
+
 	return 0;
 }
 
@@ -1409,14 +1513,18 @@ static int i40iw_handle_q_mem(struct i40iw_device *iwdev,
 	struct i40iw_cq_mr *cqmr = &iwpbl->cq_mr;
 	struct i40iw_hmc_pble *hmc_p;
 	u64 *arr = iwmr->pgaddrmem;
+	u32 pg_size;
 	int err;
 	int total;
+	bool ret = true;
 
 	total = req->sq_pages + req->rq_pages + req->cq_pages;
+	pg_size = iwmr->page_size;
 
 	err = i40iw_setup_pbles(iwdev, iwmr, use_pbles);
 	if (err)
 		return err;
+
 	if (use_pbles && (palloc->level != I40IW_LEVEL_1)) {
 		i40iw_free_pble(iwdev->pble_rsrc, palloc);
 		iwpbl->pbl_allocated = false;
@@ -1425,26 +1533,44 @@ static int i40iw_handle_q_mem(struct i40iw_device *iwdev,
 
 	if (use_pbles)
 		arr = (u64 *)palloc->level1.addr;
-	if (req->reg_type == IW_MEMREG_TYPE_QP) {
+
+	if (iwmr->type == IW_MEMREG_TYPE_QP) {
 		hmc_p = &qpmr->sq_pbl;
 		qpmr->shadow = (dma_addr_t)arr[total];
+
 		if (use_pbles) {
+			ret = i40iw_check_mem_contiguous(arr, req->sq_pages, pg_size);
+			if (ret)
+				ret = i40iw_check_mem_contiguous(&arr[req->sq_pages], req->rq_pages, pg_size);
+		}
+
+		if (!ret) {
 			hmc_p->idx = palloc->level1.idx;
 			hmc_p = &qpmr->rq_pbl;
 			hmc_p->idx = palloc->level1.idx + req->sq_pages;
 		} else {
 			hmc_p->addr = arr[0];
 			hmc_p = &qpmr->rq_pbl;
-			hmc_p->addr = arr[1];
+			hmc_p->addr = arr[req->sq_pages];
 		}
 	} else {		/* CQ */
 		hmc_p = &cqmr->cq_pbl;
 		cqmr->shadow = (dma_addr_t)arr[total];
+
 		if (use_pbles)
+			ret = i40iw_check_mem_contiguous(arr, req->cq_pages, pg_size);
+
+		if (!ret)
 			hmc_p->idx = palloc->level1.idx;
 		else
 			hmc_p->addr = arr[0];
 	}
+
+	if (use_pbles && ret) {
+		i40iw_free_pble(iwdev->pble_rsrc, palloc);
+		iwpbl->pbl_allocated = false;
+	}
+
 	return err;
 }
 
@@ -1642,8 +1768,9 @@ static int i40iw_hwreg_mr(struct i40iw_device *iwdev,
 	stag_info->access_rights = access;
 	stag_info->pd_id = iwpd->sc_pd.pd_id;
 	stag_info->addr_type = I40IW_ADDR_TYPE_VA_BASED;
+	stag_info->page_size = iwmr->page_size;
 
-	if (iwmr->page_cnt > 1) {
+	if (iwpbl->pbl_allocated) {
 		if (palloc->level == I40IW_LEVEL_1) {
 			stag_info->first_pm_pbl_index = palloc->level1.idx;
 			stag_info->chunk_size = 1;
@@ -1699,6 +1826,11 @@ static struct ib_mr *i40iw_reg_user_mr(struct ib_pd *pd,
 	bool use_pbles = false;
 	unsigned long flags;
 	int err = -ENOSYS;
+	int ret;
+	int pg_shift;
+
+	if (iwdev->closing)
+		return ERR_PTR(-ENODEV);
 
 	if (length > I40IW_MAX_MR_SIZE)
 		return ERR_PTR(-EINVAL);
@@ -1723,9 +1855,17 @@ static struct ib_mr *i40iw_reg_user_mr(struct ib_pd *pd,
 	iwmr->ibmr.pd = pd;
 	iwmr->ibmr.device = pd->device;
 	ucontext = to_ucontext(pd->uobject->context);
-	region_length = region->length + (start & 0xfff);
-	pbl_depth = region_length >> 12;
-	pbl_depth += (region_length & (4096 - 1)) ? 1 : 0;
+
+	iwmr->page_size = region->page_size;
+	iwmr->page_msk = PAGE_MASK;
+
+	if (region->hugetlb && (req.reg_type == IW_MEMREG_TYPE_MEM))
+		i40iw_set_hugetlb_values(start, iwmr);
+
+	region_length = region->length + (start & (iwmr->page_size - 1));
+	pg_shift = ffs(iwmr->page_size) - 1;
+	pbl_depth = region_length >> pg_shift;
+	pbl_depth += (region_length & (iwmr->page_size - 1)) ? 1 : 0;
 	iwmr->length = region->length;
 
 	iwpbl->user_base = virt;
@@ -1755,13 +1895,21 @@ static struct ib_mr *i40iw_reg_user_mr(struct ib_pd *pd,
 		spin_unlock_irqrestore(&ucontext->cq_reg_mem_list_lock, flags);
 		break;
 	case IW_MEMREG_TYPE_MEM:
+		use_pbles = (iwmr->page_cnt != 1);
 		access = I40IW_ACCESS_FLAGS_LOCALREAD;
 
-		use_pbles = (iwmr->page_cnt != 1);
 		err = i40iw_setup_pbles(iwdev, iwmr, use_pbles);
 		if (err)
 			goto error;
 
+		if (use_pbles) {
+			ret = i40iw_check_mr_contiguous(palloc, iwmr->page_size);
+			if (ret) {
+				i40iw_free_pble(iwdev->pble_rsrc, palloc);
+				iwpbl->pbl_allocated = false;
+			}
+		}
+
 		access |= i40iw_get_user_access(acc);
 		stag = i40iw_create_stag(iwdev);
 		if (!stag) {
@@ -1778,6 +1926,7 @@ static struct ib_mr *i40iw_reg_user_mr(struct ib_pd *pd,
 			i40iw_free_stag(iwdev, stag);
 			goto error;
 		}
+
 		break;
 	default:
 		goto error;
@@ -1789,7 +1938,7 @@ static struct ib_mr *i40iw_reg_user_mr(struct ib_pd *pd,
 	return &iwmr->ibmr;
 
 error:
-	if (palloc->level != I40IW_LEVEL_0)
+	if (palloc->level != I40IW_LEVEL_0 && iwpbl->pbl_allocated)
 		i40iw_free_pble(iwdev->pble_rsrc, palloc);
 	ib_umem_release(region);
 	kfree(iwmr);
@@ -2142,7 +2291,6 @@ static int i40iw_post_send(struct ib_qp *ibqp,
 		case IB_WR_REG_MR:
 		{
 			struct i40iw_mr *iwmr = to_iwmr(reg_wr(ib_wr)->mr);
-			int page_shift = ilog2(reg_wr(ib_wr)->mr->page_size);
 			int flags = reg_wr(ib_wr)->access;
 			struct i40iw_pble_alloc *palloc = &iwmr->iwpbl.pble_alloc;
 			struct i40iw_sc_dev *dev = &iwqp->iwdev->sc_dev;
@@ -2153,6 +2301,7 @@ static int i40iw_post_send(struct ib_qp *ibqp,
 			info.access_rights |= i40iw_get_user_access(flags);
 			info.stag_key = reg_wr(ib_wr)->key & 0xff;
 			info.stag_idx = reg_wr(ib_wr)->key >> 8;
+			info.page_size = reg_wr(ib_wr)->mr->page_size;
 			info.wr_id = ib_wr->wr_id;
 
 			info.addr_type = I40IW_ADDR_TYPE_VA_BASED;
@@ -2166,9 +2315,6 @@ static int i40iw_post_send(struct ib_qp *ibqp,
 			if (iwmr->npages > I40IW_MIN_PAGES_PER_FMR)
 				info.chunk_size = 1;
 
-			if (page_shift == 21)
-				info.page_size = 1; /* 2M page */
-
 			ret = dev->iw_priv_qp_ops->iw_mr_fast_register(&iwqp->sc_qp, &info, true);
 			if (ret)
 				err = -ENOMEM;
@@ -2487,21 +2633,17 @@ static int i40iw_get_hw_stats(struct ib_device *ibdev,
 {
 	struct i40iw_device *iwdev = to_iwdev(ibdev);
 	struct i40iw_sc_dev *dev = &iwdev->sc_dev;
-	struct i40iw_dev_pestat *devstat = &dev->dev_pestat;
+	struct i40iw_vsi_pestat *devstat = iwdev->vsi.pestat;
 	struct i40iw_dev_hw_stats *hw_stats = &devstat->hw_stats;
-	unsigned long flags;
 
 	if (dev->is_pf) {
-		spin_lock_irqsave(&devstat->stats_lock, flags);
-		devstat->ops.iw_hw_stat_read_all(devstat,
-			&devstat->hw_stats);
-		spin_unlock_irqrestore(&devstat->stats_lock, flags);
+		i40iw_hw_stats_read_all(devstat, &devstat->hw_stats);
 	} else {
 		if (i40iw_vchnl_vf_get_pe_stats(dev, &devstat->hw_stats))
 			return -ENOSYS;
 	}
 
-	memcpy(&stats->value[0], &hw_stats, sizeof(*hw_stats));
+	memcpy(&stats->value[0], hw_stats, sizeof(*hw_stats));
 
 	return stats->num_counters;
 }
@@ -2562,7 +2704,9 @@ static int i40iw_query_pkey(struct ib_device *ibdev,
  * @ah_attr: address handle attributes
  */
 static struct ib_ah *i40iw_create_ah(struct ib_pd *ibpd,
-				     struct ib_ah_attr *attr)
+				     struct ib_ah_attr *attr,
+				     struct ib_udata *udata)
+
 {
 	return ERR_PTR(-ENOSYS);
 }
@@ -2621,7 +2765,7 @@ static struct i40iw_ib_device *i40iw_init_rdma_device(struct i40iw_device *iwdev
 	    (1ull << IB_USER_VERBS_CMD_POST_RECV) |
 	    (1ull << IB_USER_VERBS_CMD_POST_SEND);
 	iwibdev->ibdev.phys_port_cnt = 1;
-	iwibdev->ibdev.num_comp_vectors = 1;
+	iwibdev->ibdev.num_comp_vectors = iwdev->ceqs_count;
 	iwibdev->ibdev.dma_device = &pcidev->dev;
 	iwibdev->ibdev.dev.parent = &pcidev->dev;
 	iwibdev->ibdev.query_port = i40iw_query_port;
@@ -2654,7 +2798,6 @@ static struct i40iw_ib_device *i40iw_init_rdma_device(struct i40iw_device *iwdev
 	iwibdev->ibdev.iwcm = kzalloc(sizeof(*iwibdev->ibdev.iwcm), GFP_KERNEL);
 	if (!iwibdev->ibdev.iwcm) {
 		ib_dealloc_device(&iwibdev->ibdev);
-		i40iw_pr_err("iwcm == NULL\n");
 		return NULL;
 	}
 
@@ -2719,6 +2862,9 @@ void i40iw_destroy_rdma_device(struct i40iw_ib_device *iwibdev)
 	i40iw_unregister_rdma_device(iwibdev);
 	kfree(iwibdev->ibdev.iwcm);
 	iwibdev->ibdev.iwcm = NULL;
+	wait_event_timeout(iwibdev->iwdev->close_wq,
+			   !atomic64_read(&iwibdev->iwdev->use_count),
+			   I40IW_EVENT_TIMEOUT);
 	ib_dealloc_device(&iwibdev->ibdev);
 }
 

drivers/infiniband/hw/i40iw/i40iw_verbs.h

@@ -92,6 +92,8 @@ struct i40iw_mr {
 	struct ib_umem *region;
 	u16 type;
 	u32 page_cnt;
+	u32 page_size;
+	u64 page_msk;
 	u32 npages;
 	u32 stag;
 	u64 length;

drivers/infiniband/hw/i40iw/i40iw_virtchnl.c

@@ -402,6 +402,19 @@ del_out:
 	vchnl_pf_send_error_resp(vf_dev->pf_dev, vf_dev->vf_id, vchnl_msg, (u16)ret_code);
 }
 
+/**
+ * i40iw_vf_init_pestat - Initialize stats for VF
+ * @devL pointer to the VF Device
+ * @stats: Statistics structure pointer
+ * @index: Stats index
+ */
+static void i40iw_vf_init_pestat(struct i40iw_sc_dev *dev, struct i40iw_vsi_pestat *stats, u16 index)
+{
+	stats->hw = dev->hw;
+	i40iw_hw_stats_init(stats, (u8)index, false);
+	spin_lock_init(&stats->lock);
+}
+
 /**
  * i40iw_vchnl_recv_pf - Receive PF virtual channel messages
  * @dev: IWARP device pointer
@@ -421,9 +434,8 @@ enum i40iw_status_code i40iw_vchnl_recv_pf(struct i40iw_sc_dev *dev,
 	u16 first_avail_iw_vf = I40IW_MAX_PE_ENABLED_VF_COUNT;
 	struct i40iw_virt_mem vf_dev_mem;
 	struct i40iw_virtchnl_work_info work_info;
-	struct i40iw_dev_pestat *devstat;
+	struct i40iw_vsi_pestat *stats;
 	enum i40iw_status_code ret_code;
-	unsigned long flags;
 
 	if (!dev || !msg || !len)
 		return I40IW_ERR_PARAM;
@@ -496,14 +508,7 @@ enum i40iw_status_code i40iw_vchnl_recv_pf(struct i40iw_sc_dev *dev,
 				i40iw_debug(dev, I40IW_DEBUG_VIRT,
 					    "VF%u error CQP HMC Function operation.\n",
 					    vf_id);
-			ret_code = i40iw_device_init_pestat(&vf_dev->dev_pestat);
-			if (ret_code)
-				i40iw_debug(dev, I40IW_DEBUG_VIRT,
-					    "VF%u - i40iw_device_init_pestat failed\n",
-					    vf_id);
-			vf_dev->dev_pestat.ops.iw_hw_stat_init(&vf_dev->dev_pestat,
-							      (u8)vf_dev->pmf_index,
-							      dev->hw, false);
+			i40iw_vf_init_pestat(dev, &vf_dev->pestat, vf_dev->pmf_index);
 			vf_dev->stats_initialized = true;
 		} else {
 			if (vf_dev) {
@@ -534,12 +539,10 @@ enum i40iw_status_code i40iw_vchnl_recv_pf(struct i40iw_sc_dev *dev,
 	case I40IW_VCHNL_OP_GET_STATS:
 		if (!vf_dev)
 			return I40IW_ERR_BAD_PTR;
-		devstat = &vf_dev->dev_pestat;
-		spin_lock_irqsave(&dev->dev_pestat.stats_lock, flags);
-		devstat->ops.iw_hw_stat_read_all(devstat, &devstat->hw_stats);
-		spin_unlock_irqrestore(&dev->dev_pestat.stats_lock, flags);
+		stats = &vf_dev->pestat;
+		i40iw_hw_stats_read_all(stats, &stats->hw_stats);
 		vf_dev->msg_count--;
-		vchnl_pf_send_get_pe_stats_resp(dev, vf_id, vchnl_msg, &devstat->hw_stats);
+		vchnl_pf_send_get_pe_stats_resp(dev, vf_id, vchnl_msg, &stats->hw_stats);
 		break;
 	default:
 		i40iw_debug(dev, I40IW_DEBUG_VIRT,

drivers/infiniband/hw/mlx4/ah.c

@@ -114,7 +114,9 @@ static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr
 		       !(1 << ah->av.eth.stat_rate & dev->caps.stat_rate_support))
 			--ah->av.eth.stat_rate;
 	}
-
+	ah->av.eth.sl_tclass_flowlabel |=
+			cpu_to_be32((ah_attr->grh.traffic_class << 20) |
+				    ah_attr->grh.flow_label);
 	/*
 	 * HW requires multicast LID so we just choose one.
 	 */
@@ -122,12 +124,14 @@ static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr
 		ah->av.ib.dlid = cpu_to_be16(0xc000);
 
 	memcpy(ah->av.eth.dgid, ah_attr->grh.dgid.raw, 16);
-	ah->av.eth.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 29);
+	ah->av.eth.sl_tclass_flowlabel |= cpu_to_be32(ah_attr->sl << 29);
 
 	return &ah->ibah;
 }
 
-struct ib_ah *mlx4_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr)
+struct ib_ah *mlx4_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
+				struct ib_udata *udata)
+
 {
 	struct mlx4_ib_ah *ah;
 	struct ib_ah *ret;

drivers/infiniband/hw/mlx4/alias_GUID.c

@@ -755,10 +755,8 @@ static void alias_guid_work(struct work_struct *work)
 	struct mlx4_ib_dev *dev = container_of(ib_sriov, struct mlx4_ib_dev, sriov);
 
 	rec = kzalloc(sizeof *rec, GFP_KERNEL);
-	if (!rec) {
-		pr_err("alias_guid_work: No Memory\n");
+	if (!rec)
 		return;
-	}
 
 	pr_debug("starting [port: %d]...\n", sriov_alias_port->port + 1);
 	ret = get_next_record_to_update(dev, sriov_alias_port->port, rec);

drivers/infiniband/hw/mlx4/cm.c

@@ -247,10 +247,8 @@ id_map_alloc(struct ib_device *ibdev, int slave_id, u32 sl_cm_id)
 	struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov;
 
 	ent = kmalloc(sizeof (struct id_map_entry), GFP_KERNEL);
-	if (!ent) {
-		mlx4_ib_warn(ibdev, "Couldn't allocate id cache entry - out of memory\n");
+	if (!ent)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	ent->sl_cm_id = sl_cm_id;
 	ent->slave_id = slave_id;

drivers/infiniband/hw/mlx4/mad.c

@@ -39,6 +39,8 @@
 #include <linux/mlx4/cmd.h>
 #include <linux/gfp.h>
 #include <rdma/ib_pma.h>
+#include <linux/ip.h>
+#include <net/ipv6.h>
 
 #include <linux/mlx4/driver.h>
 #include "mlx4_ib.h"
@@ -480,6 +482,23 @@ static int find_slave_port_pkey_ix(struct mlx4_ib_dev *dev, int slave,
 	return -EINVAL;
 }
 
+static int get_gids_from_l3_hdr(struct ib_grh *grh, union ib_gid *sgid,
+				union ib_gid *dgid)
+{
+	int version = ib_get_rdma_header_version((const union rdma_network_hdr *)grh);
+	enum rdma_network_type net_type;
+
+	if (version == 4)
+		net_type = RDMA_NETWORK_IPV4;
+	else if (version == 6)
+		net_type = RDMA_NETWORK_IPV6;
+	else
+		return -EINVAL;
+
+	return ib_get_gids_from_rdma_hdr((union rdma_network_hdr *)grh, net_type,
+					 sgid, dgid);
+}
+
 int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
 			  enum ib_qp_type dest_qpt, struct ib_wc *wc,
 			  struct ib_grh *grh, struct ib_mad *mad)
@@ -538,7 +557,10 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
 	memset(&attr, 0, sizeof attr);
 	attr.port_num = port;
 	if (is_eth) {
-		memcpy(&attr.grh.dgid.raw[0], &grh->dgid.raw[0], 16);
+		union ib_gid sgid;
+
+		if (get_gids_from_l3_hdr(grh, &sgid, &attr.grh.dgid))
+			return -EINVAL;
 		attr.ah_flags = IB_AH_GRH;
 	}
 	ah = ib_create_ah(tun_ctx->pd, &attr);
@@ -651,6 +673,11 @@ static int mlx4_ib_demux_mad(struct ib_device *ibdev, u8 port,
 		is_eth = 1;
 
 	if (is_eth) {
+		union ib_gid dgid;
+		union ib_gid sgid;
+
+		if (get_gids_from_l3_hdr(grh, &sgid, &dgid))
+			return -EINVAL;
 		if (!(wc->wc_flags & IB_WC_GRH)) {
 			mlx4_ib_warn(ibdev, "RoCE grh not present.\n");
 			return -EINVAL;
@@ -659,10 +686,10 @@ static int mlx4_ib_demux_mad(struct ib_device *ibdev, u8 port,
 			mlx4_ib_warn(ibdev, "RoCE mgmt class is not CM\n");
 			return -EINVAL;
 		}
-		err = mlx4_get_slave_from_roce_gid(dev->dev, port, grh->dgid.raw, &slave);
+		err = mlx4_get_slave_from_roce_gid(dev->dev, port, dgid.raw, &slave);
 		if (err && mlx4_is_mf_bonded(dev->dev)) {
 			other_port = (port == 1) ? 2 : 1;
-			err = mlx4_get_slave_from_roce_gid(dev->dev, other_port, grh->dgid.raw, &slave);
+			err = mlx4_get_slave_from_roce_gid(dev->dev, other_port, dgid.raw, &slave);
 			if (!err) {
 				port = other_port;
 				pr_debug("resolved slave %d from gid %pI6 wire port %d other %d\n",
@@ -702,10 +729,18 @@ static int mlx4_ib_demux_mad(struct ib_device *ibdev, u8 port,
 
 	/* If a grh is present, we demux according to it */
 	if (wc->wc_flags & IB_WC_GRH) {
-		slave = mlx4_ib_find_real_gid(ibdev, port, grh->dgid.global.interface_id);
-		if (slave < 0) {
-			mlx4_ib_warn(ibdev, "failed matching grh\n");
-			return -ENOENT;
+		if (grh->dgid.global.interface_id ==
+			cpu_to_be64(IB_SA_WELL_KNOWN_GUID) &&
+		    grh->dgid.global.subnet_prefix == cpu_to_be64(
+			atomic64_read(&dev->sriov.demux[port - 1].subnet_prefix))) {
+			slave = 0;
+		} else {
+			slave = mlx4_ib_find_real_gid(ibdev, port,
+						      grh->dgid.global.interface_id);
+			if (slave < 0) {
+				mlx4_ib_warn(ibdev, "failed matching grh\n");
+				return -ENOENT;
+			}
 		}
 	}
 	/* Class-specific handling */
@@ -1102,10 +1137,8 @@ static void handle_slaves_guid_change(struct mlx4_ib_dev *dev, u8 port_num,
 
 	in_mad  = kmalloc(sizeof *in_mad, GFP_KERNEL);
 	out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL);
-	if (!in_mad || !out_mad) {
-		mlx4_ib_warn(&dev->ib_dev, "failed to allocate memory for guid info mads\n");
+	if (!in_mad || !out_mad)
 		goto out;
-	}
 
 	guid_tbl_blk_num  *= 4;
 
@@ -1916,11 +1949,8 @@ static int alloc_pv_object(struct mlx4_ib_dev *dev, int slave, int port,
 
 	*ret_ctx = NULL;
 	ctx = kzalloc(sizeof (struct mlx4_ib_demux_pv_ctx), GFP_KERNEL);
-	if (!ctx) {
-		pr_err("failed allocating pv resource context "
-		       "for port %d, slave %d\n", port, slave);
+	if (!ctx)
 		return -ENOMEM;
-	}
 
 	ctx->ib_dev = &dev->ib_dev;
 	ctx->port = port;

drivers/infiniband/hw/mlx4/main.c

@@ -430,7 +430,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 	struct mlx4_ib_dev *dev = to_mdev(ibdev);
 	struct ib_smp *in_mad  = NULL;
 	struct ib_smp *out_mad = NULL;
-	int err = -ENOMEM;
+	int err;
 	int have_ib_ports;
 	struct mlx4_uverbs_ex_query_device cmd;
 	struct mlx4_uverbs_ex_query_device_resp resp = {.comp_mask = 0};
@@ -455,6 +455,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 		sizeof(resp.response_length);
 	in_mad  = kzalloc(sizeof *in_mad, GFP_KERNEL);
 	out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL);
+	err = -ENOMEM;
 	if (!in_mad || !out_mad)
 		goto out;
 
@@ -547,6 +548,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 	props->max_map_per_fmr = dev->dev->caps.max_fmr_maps;
 	props->hca_core_clock = dev->dev->caps.hca_core_clock * 1000UL;
 	props->timestamp_mask = 0xFFFFFFFFFFFFULL;
+	props->max_ah = INT_MAX;
 
 	if (!mlx4_is_slave(dev->dev))
 		err = mlx4_get_internal_clock_params(dev->dev, &clock_params);
@@ -697,9 +699,11 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port,
 	if (err)
 		goto out;
 
-	props->active_width	=  (((u8 *)mailbox->buf)[5] == 0x40) ?
-						IB_WIDTH_4X : IB_WIDTH_1X;
-	props->active_speed	= IB_SPEED_QDR;
+	props->active_width	=  (((u8 *)mailbox->buf)[5] == 0x40) ||
+				   (((u8 *)mailbox->buf)[5] == 0x20 /*56Gb*/) ?
+					   IB_WIDTH_4X : IB_WIDTH_1X;
+	props->active_speed	=  (((u8 *)mailbox->buf)[5] == 0x20 /*56Gb*/) ?
+					   IB_SPEED_FDR : IB_SPEED_QDR;
 	props->port_cap_flags	= IB_PORT_CM_SUP | IB_PORT_IP_BASED_GIDS;
 	props->gid_tbl_len	= mdev->dev->caps.gid_table_len[port];
 	props->max_msg_sz	= mdev->dev->caps.max_msg_sz;
@@ -2814,20 +2818,22 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 			kmalloc(BITS_TO_LONGS(ibdev->steer_qpn_count) *
 				sizeof(long),
 				GFP_KERNEL);
-		if (!ibdev->ib_uc_qpns_bitmap) {
-			dev_err(&dev->persist->pdev->dev,
-				"bit map alloc failed\n");
+		if (!ibdev->ib_uc_qpns_bitmap)
 			goto err_steer_qp_release;
-		}
 
-		bitmap_zero(ibdev->ib_uc_qpns_bitmap, ibdev->steer_qpn_count);
-
-		err = mlx4_FLOW_STEERING_IB_UC_QP_RANGE(
-				dev, ibdev->steer_qpn_base,
-				ibdev->steer_qpn_base +
-				ibdev->steer_qpn_count - 1);
-		if (err)
-			goto err_steer_free_bitmap;
+		if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DMFS_IPOIB) {
+			bitmap_zero(ibdev->ib_uc_qpns_bitmap,
+				    ibdev->steer_qpn_count);
+			err = mlx4_FLOW_STEERING_IB_UC_QP_RANGE(
+					dev, ibdev->steer_qpn_base,
+					ibdev->steer_qpn_base +
+					ibdev->steer_qpn_count - 1);
+			if (err)
+				goto err_steer_free_bitmap;
+		} else {
+			bitmap_fill(ibdev->ib_uc_qpns_bitmap,
+				    ibdev->steer_qpn_count);
+		}
 	}
 
 	for (j = 1; j <= ibdev->dev->caps.num_ports; j++)
@@ -3055,15 +3061,12 @@ static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init)
 	first_port = find_first_bit(actv_ports.ports, dev->caps.num_ports);
 
 	dm = kcalloc(ports, sizeof(*dm), GFP_ATOMIC);
-	if (!dm) {
-		pr_err("failed to allocate memory for tunneling qp update\n");
+	if (!dm)
 		return;
-	}
 
 	for (i = 0; i < ports; i++) {
 		dm[i] = kmalloc(sizeof (struct mlx4_ib_demux_work), GFP_ATOMIC);
 		if (!dm[i]) {
-			pr_err("failed to allocate memory for tunneling qp update work struct\n");
 			while (--i >= 0)
 				kfree(dm[i]);
 			goto out;
@@ -3223,8 +3226,6 @@ void mlx4_sched_ib_sl2vl_update_work(struct mlx4_ib_dev *ibdev,
 		ew->port = port;
 		ew->ib_dev = ibdev;
 		queue_work(wq, &ew->work);
-	} else {
-		pr_err("failed to allocate memory for sl2vl update work\n");
 	}
 }
 
@@ -3284,10 +3285,8 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 
 	case MLX4_DEV_EVENT_PORT_MGMT_CHANGE:
 		ew = kmalloc(sizeof *ew, GFP_ATOMIC);
-		if (!ew) {
-			pr_err("failed to allocate memory for events work\n");
+		if (!ew)
 			break;
-		}
 
 		INIT_WORK(&ew->work, handle_port_mgmt_change_event);
 		memcpy(&ew->ib_eqe, eqe, sizeof *eqe);

drivers/infiniband/hw/mlx4/mcg.c

@@ -1142,7 +1142,6 @@ void mlx4_ib_mcg_port_cleanup(struct mlx4_ib_demux_ctx *ctx, int destroy_wq)
 	work = kmalloc(sizeof *work, GFP_KERNEL);
 	if (!work) {
 		ctx->flushing = 0;
-		mcg_warn("failed allocating work for cleanup\n");
 		return;
 	}
 
@@ -1202,10 +1201,8 @@ static int push_deleteing_req(struct mcast_group *group, int slave)
 		return 0;
 
 	req = kzalloc(sizeof *req, GFP_KERNEL);
-	if (!req) {
-		mcg_warn_group(group, "failed allocation - may leave stall groups\n");
+	if (!req)
 		return -ENOMEM;
-	}
 
 	if (!list_empty(&group->func[slave].pending)) {
 		pend_req = list_entry(group->func[slave].pending.prev, struct mcast_req, group_list);

drivers/infiniband/hw/mlx4/mlx4_ib.h

@@ -742,7 +742,8 @@ int mlx4_ib_arm_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags);
 void __mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq);
 void mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq);
 
-struct ib_ah *mlx4_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr);
+struct ib_ah *mlx4_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
+				struct ib_udata *udata);
 int mlx4_ib_query_ah(struct ib_ah *ibah, struct ib_ah_attr *ah_attr);
 int mlx4_ib_destroy_ah(struct ib_ah *ah);
 

drivers/infiniband/hw/mlx4/qp.c

@@ -644,7 +644,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 	int qpn;
 	int err;
 	struct ib_qp_cap backup_cap;
-	struct mlx4_ib_sqp *sqp;
+	struct mlx4_ib_sqp *sqp = NULL;
 	struct mlx4_ib_qp *qp;
 	enum mlx4_ib_qp_type qp_type = (enum mlx4_ib_qp_type) init_attr->qp_type;
 	struct mlx4_ib_cq *mcq;
@@ -933,7 +933,9 @@ err_db:
 		mlx4_db_free(dev->dev, &qp->db);
 
 err:
-	if (!*caller_qp)
+	if (sqp)
+		kfree(sqp);
+	else if (!*caller_qp)
 		kfree(qp);
 	return err;
 }
@@ -1280,7 +1282,8 @@ static int _mlx4_ib_destroy_qp(struct ib_qp *qp)
 	if (is_qp0(dev, mqp))
 		mlx4_CLOSE_PORT(dev->dev, mqp->port);
 
-	if (dev->qp1_proxy[mqp->port - 1] == mqp) {
+	if (mqp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_GSI &&
+	    dev->qp1_proxy[mqp->port - 1] == mqp) {
 		mutex_lock(&dev->qp1_proxy_lock[mqp->port - 1]);
 		dev->qp1_proxy[mqp->port - 1] = NULL;
 		mutex_unlock(&dev->qp1_proxy_lock[mqp->port - 1]);
@@ -1764,14 +1767,14 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 		u8 port_num = mlx4_is_bonded(to_mdev(ibqp->device)->dev) ? 1 :
 			attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
 		union ib_gid gid;
-		struct ib_gid_attr gid_attr;
+		struct ib_gid_attr gid_attr = {.gid_type = IB_GID_TYPE_IB};
 		u16 vlan = 0xffff;
 		u8 smac[ETH_ALEN];
 		int status = 0;
 		int is_eth = rdma_cap_eth_ah(&dev->ib_dev, port_num) &&
 			attr->ah_attr.ah_flags & IB_AH_GRH;
 
-		if (is_eth) {
+		if (is_eth && attr->ah_attr.ah_flags & IB_AH_GRH) {
 			int index = attr->ah_attr.grh.sgid_index;
 
 			status = ib_get_cached_gid(ibqp->device, port_num,

drivers/infiniband/hw/mlx5/ah.c

@@ -64,7 +64,9 @@ static struct ib_ah *create_ib_ah(struct mlx5_ib_dev *dev,
 	return &ah->ibah;
 }
 
-struct ib_ah *mlx5_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr)
+struct ib_ah *mlx5_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
+				struct ib_udata *udata)
+
 {
 	struct mlx5_ib_ah *ah;
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
@@ -75,6 +77,27 @@ struct ib_ah *mlx5_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr)
 	if (ll == IB_LINK_LAYER_ETHERNET && !(ah_attr->ah_flags & IB_AH_GRH))
 		return ERR_PTR(-EINVAL);
 
+	if (ll == IB_LINK_LAYER_ETHERNET && udata) {
+		int err;
+		struct mlx5_ib_create_ah_resp resp = {};
+		u32 min_resp_len = offsetof(typeof(resp), dmac) +
+				   sizeof(resp.dmac);
+
+		if (udata->outlen < min_resp_len)
+			return ERR_PTR(-EINVAL);
+
+		resp.response_length = min_resp_len;
+
+		err = ib_resolve_eth_dmac(pd->device, ah_attr);
+		if (err)
+			return ERR_PTR(err);
+
+		memcpy(resp.dmac, ah_attr->dmac, ETH_ALEN);
+		err = ib_copy_to_udata(udata, &resp, resp.response_length);
+		if (err)
+			return ERR_PTR(err);
+	}
+
 	ah = kzalloc(sizeof(*ah), GFP_ATOMIC);
 	if (!ah)
 		return ERR_PTR(-ENOMEM);

drivers/infiniband/hw/mlx5/cq.c

@@ -731,7 +731,7 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 			  int entries, u32 **cqb,
 			  int *cqe_size, int *index, int *inlen)
 {
-	struct mlx5_ib_create_cq ucmd;
+	struct mlx5_ib_create_cq ucmd = {};
 	size_t ucmdlen;
 	int page_shift;
 	__be64 *pas;
@@ -770,7 +770,7 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 	if (err)
 		goto err_umem;
 
-	mlx5_ib_cont_pages(cq->buf.umem, ucmd.buf_addr, &npages, &page_shift,
+	mlx5_ib_cont_pages(cq->buf.umem, ucmd.buf_addr, 0, &npages, &page_shift,
 			   &ncont, NULL);
 	mlx5_ib_dbg(dev, "addr 0x%llx, size %u, npages %d, page_shift %d, ncont %d\n",
 		    ucmd.buf_addr, entries * ucmd.cqe_size, npages, page_shift, ncont);
@@ -792,8 +792,36 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 
 	*index = to_mucontext(context)->uuari.uars[0].index;
 
+	if (ucmd.cqe_comp_en == 1) {
+		if (unlikely((*cqe_size != 64) ||
+			     !MLX5_CAP_GEN(dev->mdev, cqe_compression))) {
+			err = -EOPNOTSUPP;
+			mlx5_ib_warn(dev, "CQE compression is not supported for size %d!\n",
+				     *cqe_size);
+			goto err_cqb;
+		}
+
+		if (unlikely(!ucmd.cqe_comp_res_format ||
+			     !(ucmd.cqe_comp_res_format <
+			       MLX5_IB_CQE_RES_RESERVED) ||
+			     (ucmd.cqe_comp_res_format &
+			      (ucmd.cqe_comp_res_format - 1)))) {
+			err = -EOPNOTSUPP;
+			mlx5_ib_warn(dev, "CQE compression res format %d is not supported!\n",
+				     ucmd.cqe_comp_res_format);
+			goto err_cqb;
+		}
+
+		MLX5_SET(cqc, cqc, cqe_comp_en, 1);
+		MLX5_SET(cqc, cqc, mini_cqe_res_format,
+			 ilog2(ucmd.cqe_comp_res_format));
+	}
+
 	return 0;
 
+err_cqb:
+	kfree(cqb);
+
 err_db:
 	mlx5_ib_db_unmap_user(to_mucontext(context), &cq->db);
 
@@ -1124,7 +1152,7 @@ static int resize_user(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
 		return err;
 	}
 
-	mlx5_ib_cont_pages(umem, ucmd.buf_addr, &npages, page_shift,
+	mlx5_ib_cont_pages(umem, ucmd.buf_addr, 0, &npages, page_shift,
 			   npas, NULL);
 
 	cq->resize_umem = umem;