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

Pull rdma updates from Jason Gunthorpe:
 "Usual size of updates, a new driver, and most of the bulk focusing on
  rxe:

   - Usual typos, style, and language updates

   - Driver updates for mlx5, irdma, siw, rts, srp, hfi1, hns, erdma,
     mlx4, srp

   - Lots of RXE updates:
      * Improve reply error handling for bad MR operations
      * Code tidying
      * Debug printing uses common loggers
      * Remove half implemented RD related stuff
      * Support IBA's recently defined Atomic Write and Flush operations

   - erdma support for atomic operations

   - New driver 'mana' for Ethernet HW available in Azure VMs. This
     driver only supports DPDK"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (122 commits)
  IB/IPoIB: Fix queue count inconsistency for PKEY child interfaces
  RDMA: Add missed netdev_put() for the netdevice_tracker
  RDMA/rxe: Enable RDMA FLUSH capability for rxe device
  RDMA/cm: Make QP FLUSHABLE for supported device
  RDMA/rxe: Implement flush completion
  RDMA/rxe: Implement flush execution in responder side
  RDMA/rxe: Implement RC RDMA FLUSH service in requester side
  RDMA/rxe: Extend rxe packet format to support flush
  RDMA/rxe: Allow registering persistent flag for pmem MR only
  RDMA/rxe: Extend rxe user ABI to support flush
  RDMA: Extend RDMA kernel verbs ABI to support flush
  RDMA: Extend RDMA user ABI to support flush
  RDMA/rxe: Fix incorrect responder length checking
  RDMA/rxe: Fix oops with zero length reads
  RDMA/mlx5: Remove not-used IB_FLOW_SPEC_IB define
  RDMA/hns: Fix XRC caps on HIP08
  RDMA/hns: Fix error code of CMD
  RDMA/hns: Fix page size cap from firmware
  RDMA/hns: Fix PBL page MTR find
  RDMA/hns: Fix AH attr queried by query_qp
  ...

Author: torvalds

MAINTAINERS

@@ -13806,6 +13806,15 @@ F:	drivers/scsi/smartpqi/smartpqi*.[ch]
 F:	include/linux/cciss*.h
 F:	include/uapi/linux/cciss*.h
 
+MICROSOFT MANA RDMA DRIVER
+M:	Long Li <[email protected]>
+M:	Ajay Sharma <[email protected]>
+L:	[email protected]
+S:	Supported
+F:	drivers/infiniband/hw/mana/
+F:	include/net/mana
+F:	include/uapi/rdma/mana-abi.h
+
 MICROSOFT SURFACE AGGREGATOR TABLET-MODE SWITCH
 M:	Maximilian Luz <[email protected]>
 L:	[email protected]

drivers/infiniband/Kconfig

@@ -78,13 +78,15 @@ config INFINIBAND_VIRT_DMA
 	def_bool !HIGHMEM
 
 if INFINIBAND_USER_ACCESS || !INFINIBAND_USER_ACCESS
+if !UML
 source "drivers/infiniband/hw/bnxt_re/Kconfig"
 source "drivers/infiniband/hw/cxgb4/Kconfig"
 source "drivers/infiniband/hw/efa/Kconfig"
 source "drivers/infiniband/hw/erdma/Kconfig"
 source "drivers/infiniband/hw/hfi1/Kconfig"
 source "drivers/infiniband/hw/hns/Kconfig"
 source "drivers/infiniband/hw/irdma/Kconfig"
+source "drivers/infiniband/hw/mana/Kconfig"
 source "drivers/infiniband/hw/mlx4/Kconfig"
 source "drivers/infiniband/hw/mlx5/Kconfig"
 source "drivers/infiniband/hw/mthca/Kconfig"
@@ -94,6 +96,7 @@ source "drivers/infiniband/hw/qib/Kconfig"
 source "drivers/infiniband/hw/usnic/Kconfig"
 source "drivers/infiniband/hw/vmw_pvrdma/Kconfig"
 source "drivers/infiniband/sw/rdmavt/Kconfig"
+endif # !UML
 source "drivers/infiniband/sw/rxe/Kconfig"
 source "drivers/infiniband/sw/siw/Kconfig"
 endif

drivers/infiniband/core/cache.c

@@ -1422,7 +1422,7 @@ int rdma_read_gid_l2_fields(const struct ib_gid_attr *attr,
 			*vlan_id = vlan_dev_vlan_id(ndev);
 		} else {
 			/* If the netdev is upper device and if it's lower
-			 * device is vlan device, consider vlan id of the
+			 * device is vlan device, consider vlan id of
 			 * the lower vlan device for this gid entry.
 			 */
 			netdev_walk_all_lower_dev_rcu(attr->ndev,

drivers/infiniband/core/cm.c

@@ -4094,9 +4094,18 @@ static int cm_init_qp_init_attr(struct cm_id_private *cm_id_priv,
 		*qp_attr_mask = IB_QP_STATE | IB_QP_ACCESS_FLAGS |
 				IB_QP_PKEY_INDEX | IB_QP_PORT;
 		qp_attr->qp_access_flags = IB_ACCESS_REMOTE_WRITE;
-		if (cm_id_priv->responder_resources)
+		if (cm_id_priv->responder_resources) {
+			struct ib_device *ib_dev = cm_id_priv->id.device;
+			u64 support_flush = ib_dev->attrs.device_cap_flags &
+			  (IB_DEVICE_FLUSH_GLOBAL | IB_DEVICE_FLUSH_PERSISTENT);
+			u32 flushable = support_flush ?
+					(IB_ACCESS_FLUSH_GLOBAL |
+					 IB_ACCESS_FLUSH_PERSISTENT) : 0;
+
 			qp_attr->qp_access_flags |= IB_ACCESS_REMOTE_READ |
-						    IB_ACCESS_REMOTE_ATOMIC;
+						    IB_ACCESS_REMOTE_ATOMIC |
+						    flushable;
+		}
 		qp_attr->pkey_index = cm_id_priv->av.pkey_index;
 		if (cm_id_priv->av.port)
 			qp_attr->port_num = cm_id_priv->av.port->port_num;

drivers/infiniband/core/cma.c

@@ -47,7 +47,7 @@ MODULE_LICENSE("Dual BSD/GPL");
 #define CMA_CM_RESPONSE_TIMEOUT 20
 #define CMA_MAX_CM_RETRIES 15
 #define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24)
-#define CMA_IBOE_PACKET_LIFETIME 18
+#define CMA_IBOE_PACKET_LIFETIME 16
 #define CMA_PREFERRED_ROCE_GID_TYPE IB_GID_TYPE_ROCE_UDP_ENCAP
 
 static const char * const cma_events[] = {

drivers/infiniband/core/device.c

@@ -2159,14 +2159,16 @@ int ib_device_set_netdev(struct ib_device *ib_dev, struct net_device *ndev,
 		return 0;
 	}
 
+	if (old_ndev)
+		netdev_tracker_free(ndev, &pdata->netdev_tracker);
 	if (ndev)
-		dev_hold(ndev);
+		netdev_hold(ndev, &pdata->netdev_tracker, GFP_ATOMIC);
 	rcu_assign_pointer(pdata->netdev, ndev);
 	spin_unlock_irqrestore(&pdata->netdev_lock, flags);
 
 	add_ndev_hash(pdata);
 	if (old_ndev)
-		dev_put(old_ndev);
+		__dev_put(old_ndev);
 
 	return 0;
 }
@@ -2199,7 +2201,7 @@ static void free_netdevs(struct ib_device *ib_dev)
 			 * comparisons after the put
 			 */
 			rcu_assign_pointer(pdata->netdev, NULL);
-			dev_put(ndev);
+			netdev_put(ndev, &pdata->netdev_tracker);
 		}
 		spin_unlock_irqrestore(&pdata->netdev_lock, flags);
 	}
@@ -2851,8 +2853,8 @@ static int __init ib_core_init(void)
 static void __exit ib_core_cleanup(void)
 {
 	roce_gid_mgmt_cleanup();
-	nldev_exit();
 	rdma_nl_unregister(RDMA_NL_LS);
+	nldev_exit();
 	unregister_pernet_device(&rdma_dev_net_ops);
 	unregister_blocking_lsm_notifier(&ibdev_lsm_nb);
 	ib_sa_cleanup();

drivers/infiniband/core/mad.c

@@ -59,18 +59,13 @@ static void create_mad_addr_info(struct ib_mad_send_wr_private *mad_send_wr,
 			  struct ib_mad_qp_info *qp_info,
 			  struct trace_event_raw_ib_mad_send_template *entry)
 {
-	u16 pkey;
-	struct ib_device *dev = qp_info->port_priv->device;
-	u32 pnum = qp_info->port_priv->port_num;
 	struct ib_ud_wr *wr = &mad_send_wr->send_wr;
 	struct rdma_ah_attr attr = {};
 
 	rdma_query_ah(wr->ah, &attr);
 
 	/* These are common */
 	entry->sl = attr.sl;
-	ib_query_pkey(dev, pnum, wr->pkey_index, &pkey);
-	entry->pkey = pkey;
 	entry->rqpn = wr->remote_qpn;
 	entry->rqkey = wr->remote_qkey;
 	entry->dlid = rdma_ah_get_dlid(&attr);

drivers/infiniband/core/nldev.c

@@ -513,7 +513,7 @@ static int fill_res_qp_entry(struct sk_buff *msg, bool has_cap_net_admin,
 
 	/* In create_qp() port is not set yet */
 	if (qp->port && nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, qp->port))
-		return -EINVAL;
+		return -EMSGSIZE;
 
 	ret = nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LQPN, qp->qp_num);
 	if (ret)
@@ -552,7 +552,7 @@ static int fill_res_cm_id_entry(struct sk_buff *msg, bool has_cap_net_admin,
 	struct rdma_cm_id *cm_id = &id_priv->id;
 
 	if (port && port != cm_id->port_num)
-		return 0;
+		return -EAGAIN;
 
 	if (cm_id->port_num &&
 	    nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, cm_id->port_num))
@@ -894,6 +894,8 @@ static int fill_stat_counter_qps(struct sk_buff *msg,
 	int ret = 0;
 
 	table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_QP);
+	if (!table_attr)
+		return -EMSGSIZE;
 
 	rt = &counter->device->res[RDMA_RESTRACK_QP];
 	xa_lock(&rt->xa);
@@ -1041,6 +1043,10 @@ static int nldev_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
 			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET),
 			0, 0);
+	if (!nlh) {
+		err = -EMSGSIZE;
+		goto err_free;
+	}
 
 	err = fill_dev_info(msg, device);
 	if (err)
@@ -1126,7 +1132,7 @@ static int _nldev_get_dumpit(struct ib_device *device,
 			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET),
 			0, NLM_F_MULTI);
 
-	if (fill_dev_info(skb, device)) {
+	if (!nlh || fill_dev_info(skb, device)) {
 		nlmsg_cancel(skb, nlh);
 		goto out;
 	}
@@ -1185,6 +1191,10 @@ static int nldev_port_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
 			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET),
 			0, 0);
+	if (!nlh) {
+		err = -EMSGSIZE;
+		goto err_free;
+	}
 
 	err = fill_port_info(msg, device, port, sock_net(skb->sk));
 	if (err)
@@ -1246,7 +1256,7 @@ static int nldev_port_get_dumpit(struct sk_buff *skb,
 						 RDMA_NLDEV_CMD_PORT_GET),
 				0, NLM_F_MULTI);
 
-		if (fill_port_info(skb, device, p, sock_net(skb->sk))) {
+		if (!nlh || fill_port_info(skb, device, p, sock_net(skb->sk))) {
 			nlmsg_cancel(skb, nlh);
 			goto out;
 		}
@@ -1288,6 +1298,10 @@ static int nldev_res_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
 			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_RES_GET),
 			0, 0);
+	if (!nlh) {
+		ret = -EMSGSIZE;
+		goto err_free;
+	}
 
 	ret = fill_res_info(msg, device);
 	if (ret)
@@ -1319,7 +1333,7 @@ static int _nldev_res_get_dumpit(struct ib_device *device,
 			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_RES_GET),
 			0, NLM_F_MULTI);
 
-	if (fill_res_info(skb, device)) {
+	if (!nlh || fill_res_info(skb, device)) {
 		nlmsg_cancel(skb, nlh);
 		goto out;
 	}
@@ -1454,7 +1468,7 @@ static int res_get_common_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 					 RDMA_NL_GET_OP(nlh->nlmsg_type)),
 			0, 0);
 
-	if (fill_nldev_handle(msg, device)) {
+	if (!nlh || fill_nldev_handle(msg, device)) {
 		ret = -EMSGSIZE;
 		goto err_free;
 	}
@@ -1533,7 +1547,7 @@ static int res_get_common_dumpit(struct sk_buff *skb,
 					 RDMA_NL_GET_OP(cb->nlh->nlmsg_type)),
 			0, NLM_F_MULTI);
 
-	if (fill_nldev_handle(skb, device)) {
+	if (!nlh || fill_nldev_handle(skb, device)) {
 		ret = -EMSGSIZE;
 		goto err;
 	}
@@ -1795,6 +1809,10 @@ static int nldev_get_chardev(struct sk_buff *skb, struct nlmsghdr *nlh,
 			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
 					 RDMA_NLDEV_CMD_GET_CHARDEV),
 			0, 0);
+	if (!nlh) {
+		err = -EMSGSIZE;
+		goto out_nlmsg;
+	}
 
 	data.nl_msg = msg;
 	err = ib_get_client_nl_info(ibdev, client_name, &data);
@@ -1852,6 +1870,10 @@ static int nldev_sys_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
 					 RDMA_NLDEV_CMD_SYS_GET),
 			0, 0);
+	if (!nlh) {
+		nlmsg_free(msg);
+		return -EMSGSIZE;
+	}
 
 	err = nla_put_u8(msg, RDMA_NLDEV_SYS_ATTR_NETNS_MODE,
 			 (u8)ib_devices_shared_netns);
@@ -2032,7 +2054,7 @@ static int nldev_stat_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
 					 RDMA_NLDEV_CMD_STAT_SET),
 			0, 0);
-	if (fill_nldev_handle(msg, device) ||
+	if (!nlh || fill_nldev_handle(msg, device) ||
 	    nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port)) {
 		ret = -EMSGSIZE;
 		goto err_free_msg;
@@ -2101,6 +2123,10 @@ static int nldev_stat_del_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
 					 RDMA_NLDEV_CMD_STAT_SET),
 			0, 0);
+	if (!nlh) {
+		ret = -EMSGSIZE;
+		goto err_fill;
+	}
 
 	cntn = nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]);
 	qpn = nla_get_u32(tb[RDMA_NLDEV_ATTR_RES_LQPN]);
@@ -2171,7 +2197,7 @@ static int stat_get_doit_default_counter(struct sk_buff *skb,
 					 RDMA_NLDEV_CMD_STAT_GET),
 			0, 0);
 
-	if (fill_nldev_handle(msg, device) ||
+	if (!nlh || fill_nldev_handle(msg, device) ||
 	    nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port)) {
 		ret = -EMSGSIZE;
 		goto err_msg;
@@ -2259,6 +2285,10 @@ static int stat_get_doit_qp(struct sk_buff *skb, struct nlmsghdr *nlh,
 			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
 					 RDMA_NLDEV_CMD_STAT_GET),
 			0, 0);
+	if (!nlh) {
+		ret = -EMSGSIZE;
+		goto err_msg;
+	}
 
 	ret = rdma_counter_get_mode(device, port, &mode, &mask);
 	if (ret)
@@ -2391,7 +2421,7 @@ static int nldev_stat_get_counter_status_doit(struct sk_buff *skb,
 		0, 0);
 
 	ret = -EMSGSIZE;
-	if (fill_nldev_handle(msg, device) ||
+	if (!nlh || fill_nldev_handle(msg, device) ||
 	    nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port))
 		goto err_msg;
 

drivers/infiniband/core/restrack.c

@@ -343,8 +343,6 @@ void rdma_restrack_del(struct rdma_restrack_entry *res)
 	rt = &dev->res[res->type];
 
 	old = xa_erase(&rt->xa, res->id);
-	if (res->type == RDMA_RESTRACK_MR)
-		return;
 	WARN_ON(old != res);
 
 out:

drivers/infiniband/core/sysfs.c

@@ -1213,6 +1213,9 @@ static struct ib_port *setup_port(struct ib_core_device *coredev, int port_num,
 	p->port_num = port_num;
 	kobject_init(&p->kobj, &port_type);
 
+	if (device->port_data && is_full_dev)
+		device->port_data[port_num].sysfs = p;
+
 	cur_group = p->groups_list;
 	ret = alloc_port_table_group("gids", &p->groups[0], p->attrs_list,
 				     attr->gid_tbl_len, show_port_gid);
@@ -1258,16 +1261,15 @@ static struct ib_port *setup_port(struct ib_core_device *coredev, int port_num,
 	}
 
 	list_add_tail(&p->kobj.entry, &coredev->port_list);
-	if (device->port_data && is_full_dev)
-		device->port_data[port_num].sysfs = p;
-
 	return p;
 
 err_groups:
 	sysfs_remove_groups(&p->kobj, p->groups_list);
 err_del:
 	kobject_del(&p->kobj);
 err_put:
+	if (device->port_data && is_full_dev)
+		device->port_data[port_num].sysfs = NULL;
 	kobject_put(&p->kobj);
 	return ERR_PTR(ret);
 }
@@ -1276,14 +1278,17 @@ static void destroy_port(struct ib_core_device *coredev, struct ib_port *port)
 {
 	bool is_full_dev = &port->ibdev->coredev == coredev;
 
-	if (port->ibdev->port_data &&
-	    port->ibdev->port_data[port->port_num].sysfs == port)
-		port->ibdev->port_data[port->port_num].sysfs = NULL;
 	list_del(&port->kobj.entry);
 	if (is_full_dev)
 		sysfs_remove_groups(&port->kobj, port->ibdev->ops.port_groups);
+
 	sysfs_remove_groups(&port->kobj, port->groups_list);
 	kobject_del(&port->kobj);
+
+	if (port->ibdev->port_data &&
+	    port->ibdev->port_data[port->port_num].sysfs == port)
+		port->ibdev->port_data[port->port_num].sysfs = NULL;
+
 	kobject_put(&port->kobj);
 }