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

Pull rdma updates from Jason Gunthorpe:
 "This contains a replacement driver for Intel iWarp hardware. This new
  driver supports the old ethernet hardware and also newer chips that
  can do ROCE.

  Other than that, this contains the typical mix of patches:

   - Driver updates and cleanups for bnxt_re, cxgb4, mlx4, and mlx5

   - Many static checker driven code clean ups, including a wide
     refcount_t conversion

   - Several series for the hns driver, more HIP09 HW capabilities,
     migration to new HW register manipulators, and code cleanups

   - Minor fixes and improvements in srp, rts, and cm

   - Improvements throughout for sysfs related code to use
     DEVICE_ATTR_*, make the ib_port sysfs first-class, and overall use
     sysfs APIs properly

   - Intel's new irdma driver replacing i40iw

   - rxe general clean ups and Memory Window support"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (211 commits)
  RDMA/core: Always release restrack object
  RDMA/mlx5: Don't access NULL-cleared mpi pointer
  RDMA/irdma: Fix potential overflow expression in irdma_prm_get_pbles
  RDMA/irdma: Check contents of user-space irdma_mem_reg_req object
  RDMA/rxe: Missing unlock on error in get_srq_wqe()
  RDMA/cma: Fix rdma_resolve_route() memory leak
  RDMA/core/sa_query: Remove unused argument
  RDMA/cma: Fix incorrect Packet Lifetime calculation
  RDMA/cma: Protect RMW with qp_mutex
  RDMA/cma: Remove unnecessary INIT->INIT transition
  RDMA/hns: Add window selection field of congestion control
  RDMA/hfi1: Remove use of kmap()
  RDMA/irdma: Remove use of kmap()
  RDMA/bnxt_re: Fix uninitialized struct bit field rsvd1
  IB/isert: Align target max I/O size to initiator size
  RDMA/hns: Fix incorrect vlan enable bit in QPC
  MAINTAINERS: Update Broadcom RDMA maintainers
  RDMA/irdma: Use the queried port attributes
  RDMA/rxe: Fix redundant skb_put_zero
  RDMA/rxe: Fix extra copy in prepare_ack_packet
  ...

1 files changed, 550 insertions, 560 deletions

diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index 05b702de00e8..6146c3c1cbe5 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -44,110 +44,174 @@
 #include <rdma/ib_pma.h>
 #include <rdma/ib_cache.h>
 #include <rdma/rdma_counter.h>
+#include <rdma/ib_sysfs.h>
 
-struct ib_port;
+struct port_table_attribute {
+	struct ib_port_attribute attr;
+	char			name[8];
+	int			index;
+	__be16			attr_id;
+};
 
 struct gid_attr_group {
-	struct ib_port		*port;
-	struct kobject		kobj;
-	struct attribute_group	ndev;
-	struct attribute_group	type;
+	struct ib_port *port;
+	struct kobject kobj;
+	struct attribute_group groups[2];
+	const struct attribute_group *groups_list[3];
+	struct port_table_attribute attrs_list[];
 };
+
 struct ib_port {
-	struct kobject         kobj;
-	struct ib_device      *ibdev;
+	struct kobject kobj;
+	struct ib_device *ibdev;
 	struct gid_attr_group *gid_attr_group;
-	struct attribute_group gid_group;
-	struct attribute_group *pkey_group;
-	const struct attribute_group *pma_table;
-	struct attribute_group *hw_stats_ag;
-	struct rdma_hw_stats   *hw_stats;
-	u32                     port_num;
+	struct hw_stats_port_data *hw_stats_data;
+
+	struct attribute_group groups[3];
+	const struct attribute_group *groups_list[5];
+	u32 port_num;
+	struct port_table_attribute attrs_list[];
 };
 
-struct port_attribute {
-	struct attribute attr;
-	ssize_t (*show)(struct ib_port *, struct port_attribute *, char *buf);
-	ssize_t (*store)(struct ib_port *, struct port_attribute *,
+struct hw_stats_device_attribute {
+	struct device_attribute attr;
+	ssize_t (*show)(struct ib_device *ibdev, struct rdma_hw_stats *stats,
+			unsigned int index, unsigned int port_num, char *buf);
+	ssize_t (*store)(struct ib_device *ibdev, struct rdma_hw_stats *stats,
+			 unsigned int index, unsigned int port_num,
 			 const char *buf, size_t count);
 };
 
-#define PORT_ATTR(_name, _mode, _show, _store) \
-struct port_attribute port_attr_##_name = __ATTR(_name, _mode, _show, _store)
-
-#define PORT_ATTR_RO(_name) \
-struct port_attribute port_attr_##_name = __ATTR_RO(_name)
+struct hw_stats_port_attribute {
+	struct ib_port_attribute attr;
+	ssize_t (*show)(struct ib_device *ibdev, struct rdma_hw_stats *stats,
+			unsigned int index, unsigned int port_num, char *buf);
+	ssize_t (*store)(struct ib_device *ibdev, struct rdma_hw_stats *stats,
+			 unsigned int index, unsigned int port_num,
+			 const char *buf, size_t count);
+};
 
-struct port_table_attribute {
-	struct port_attribute	attr;
-	char			name[8];
-	int			index;
-	__be16			attr_id;
+struct hw_stats_device_data {
+	struct attribute_group group;
+	struct rdma_hw_stats *stats;
+	struct hw_stats_device_attribute attrs[];
 };
 
-struct hw_stats_attribute {
-	struct attribute	attr;
-	ssize_t			(*show)(struct kobject *kobj,
-					struct attribute *attr, char *buf);
-	ssize_t			(*store)(struct kobject *kobj,
-					 struct attribute *attr,
-					 const char *buf,
-					 size_t count);
-	int			index;
-	u32			port_num;
+struct hw_stats_port_data {
+	struct rdma_hw_stats *stats;
+	struct hw_stats_port_attribute attrs[];
 };
 
 static ssize_t port_attr_show(struct kobject *kobj,
 			      struct attribute *attr, char *buf)
 {
-	struct port_attribute *port_attr =
-		container_of(attr, struct port_attribute, attr);
+	struct ib_port_attribute *port_attr =
+		container_of(attr, struct ib_port_attribute, attr);
 	struct ib_port *p = container_of(kobj, struct ib_port, kobj);
 
 	if (!port_attr->show)
 		return -EIO;
 
-	return port_attr->show(p, port_attr, buf);
+	return port_attr->show(p->ibdev, p->port_num, port_attr, buf);
 }
 
 static ssize_t port_attr_store(struct kobject *kobj,
 			       struct attribute *attr,
 			       const char *buf, size_t count)
 {
-	struct port_attribute *port_attr =
-		container_of(attr, struct port_attribute, attr);
+	struct ib_port_attribute *port_attr =
+		container_of(attr, struct ib_port_attribute, attr);
 	struct ib_port *p = container_of(kobj, struct ib_port, kobj);
 
 	if (!port_attr->store)
 		return -EIO;
-	return port_attr->store(p, port_attr, buf, count);
+	return port_attr->store(p->ibdev, p->port_num, port_attr, buf, count);
+}
+
+struct ib_device *ib_port_sysfs_get_ibdev_kobj(struct kobject *kobj,
+					       u32 *port_num)
+{
+	struct ib_port *port = container_of(kobj, struct ib_port, kobj);
+
+	*port_num = port->port_num;
+	return port->ibdev;
 }
+EXPORT_SYMBOL(ib_port_sysfs_get_ibdev_kobj);
 
 static const struct sysfs_ops port_sysfs_ops = {
 	.show	= port_attr_show,
 	.store	= port_attr_store
 };
 
+static ssize_t hw_stat_device_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct hw_stats_device_attribute *stat_attr =
+		container_of(attr, struct hw_stats_device_attribute, attr);
+	struct ib_device *ibdev = container_of(dev, struct ib_device, dev);
+
+	return stat_attr->show(ibdev, ibdev->hw_stats_data->stats,
+			       stat_attr - ibdev->hw_stats_data->attrs, 0, buf);
+}
+
+static ssize_t hw_stat_device_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t count)
+{
+	struct hw_stats_device_attribute *stat_attr =
+		container_of(attr, struct hw_stats_device_attribute, attr);
+	struct ib_device *ibdev = container_of(dev, struct ib_device, dev);
+
+	return stat_attr->store(ibdev, ibdev->hw_stats_data->stats,
+				stat_attr - ibdev->hw_stats_data->attrs, 0, buf,
+				count);
+}
+
+static ssize_t hw_stat_port_show(struct ib_device *ibdev, u32 port_num,
+				 struct ib_port_attribute *attr, char *buf)
+{
+	struct hw_stats_port_attribute *stat_attr =
+		container_of(attr, struct hw_stats_port_attribute, attr);
+	struct ib_port *port = ibdev->port_data[port_num].sysfs;
+
+	return stat_attr->show(ibdev, port->hw_stats_data->stats,
+			       stat_attr - port->hw_stats_data->attrs,
+			       port->port_num, buf);
+}
+
+static ssize_t hw_stat_port_store(struct ib_device *ibdev, u32 port_num,
+				  struct ib_port_attribute *attr,
+				  const char *buf, size_t count)
+{
+	struct hw_stats_port_attribute *stat_attr =
+		container_of(attr, struct hw_stats_port_attribute, attr);
+	struct ib_port *port = ibdev->port_data[port_num].sysfs;
+
+	return stat_attr->store(ibdev, port->hw_stats_data->stats,
+				stat_attr - port->hw_stats_data->attrs,
+				port->port_num, buf, count);
+}
+
 static ssize_t gid_attr_show(struct kobject *kobj,
 			     struct attribute *attr, char *buf)
 {
-	struct port_attribute *port_attr =
-		container_of(attr, struct port_attribute, attr);
+	struct ib_port_attribute *port_attr =
+		container_of(attr, struct ib_port_attribute, attr);
 	struct ib_port *p = container_of(kobj, struct gid_attr_group,
 					 kobj)->port;
 
 	if (!port_attr->show)
 		return -EIO;
 
-	return port_attr->show(p, port_attr, buf);
+	return port_attr->show(p->ibdev, p->port_num, port_attr, buf);
 }
 
 static const struct sysfs_ops gid_attr_sysfs_ops = {
 	.show = gid_attr_show
 };
 
-static ssize_t state_show(struct ib_port *p, struct port_attribute *unused,
-			  char *buf)
+static ssize_t state_show(struct ib_device *ibdev, u32 port_num,
+			  struct ib_port_attribute *unused, char *buf)
 {
 	struct ib_port_attr attr;
 	ssize_t ret;
@@ -161,7 +225,7 @@ static ssize_t state_show(struct ib_port *p, struct port_attribute *unused,
 		[IB_PORT_ACTIVE_DEFER]	= "ACTIVE_DEFER"
 	};
 
-	ret = ib_query_port(p->ibdev, p->port_num, &attr);
+	ret = ib_query_port(ibdev, port_num, &attr);
 	if (ret)
 		return ret;
 
@@ -172,81 +236,80 @@ static ssize_t state_show(struct ib_port *p, struct port_attribute *unused,
 				  "UNKNOWN");
 }
 
-static ssize_t lid_show(struct ib_port *p, struct port_attribute *unused,
-			char *buf)
+static ssize_t lid_show(struct ib_device *ibdev, u32 port_num,
+			struct ib_port_attribute *unused, char *buf)
 {
 	struct ib_port_attr attr;
 	ssize_t ret;
 
-	ret = ib_query_port(p->ibdev, p->port_num, &attr);
+	ret = ib_query_port(ibdev, port_num, &attr);
 	if (ret)
 		return ret;
 
 	return sysfs_emit(buf, "0x%x\n", attr.lid);
 }
 
-static ssize_t lid_mask_count_show(struct ib_port *p,
-				   struct port_attribute *unused,
-				   char *buf)
+static ssize_t lid_mask_count_show(struct ib_device *ibdev, u32 port_num,
+				   struct ib_port_attribute *unused, char *buf)
 {
 	struct ib_port_attr attr;
 	ssize_t ret;
 
-	ret = ib_query_port(p->ibdev, p->port_num, &attr);
+	ret = ib_query_port(ibdev, port_num, &attr);
 	if (ret)
 		return ret;
 
-	return sysfs_emit(buf, "%d\n", attr.lmc);
+	return sysfs_emit(buf, "%u\n", attr.lmc);
 }
 
-static ssize_t sm_lid_show(struct ib_port *p, struct port_attribute *unused,
-			   char *buf)
+static ssize_t sm_lid_show(struct ib_device *ibdev, u32 port_num,
+			   struct ib_port_attribute *unused, char *buf)
 {
 	struct ib_port_attr attr;
 	ssize_t ret;
 
-	ret = ib_query_port(p->ibdev, p->port_num, &attr);
+	ret = ib_query_port(ibdev, port_num, &attr);
 	if (ret)
 		return ret;
 
 	return sysfs_emit(buf, "0x%x\n", attr.sm_lid);
 }
 
-static ssize_t sm_sl_show(struct ib_port *p, struct port_attribute *unused,
-			  char *buf)
+static ssize_t sm_sl_show(struct ib_device *ibdev, u32 port_num,
+			  struct ib_port_attribute *unused, char *buf)
 {
 	struct ib_port_attr attr;
 	ssize_t ret;
 
-	ret = ib_query_port(p->ibdev, p->port_num, &attr);
+	ret = ib_query_port(ibdev, port_num, &attr);
 	if (ret)
 		return ret;
 
-	return sysfs_emit(buf, "%d\n", attr.sm_sl);
+	return sysfs_emit(buf, "%u\n", attr.sm_sl);
 }
 
-static ssize_t cap_mask_show(struct ib_port *p, struct port_attribute *unused,
-			     char *buf)
+static ssize_t cap_mask_show(struct ib_device *ibdev, u32 port_num,
+			     struct ib_port_attribute *unused, char *buf)
 {
 	struct ib_port_attr attr;
 	ssize_t ret;
 
-	ret = ib_query_port(p->ibdev, p->port_num, &attr);
+	ret = ib_query_port(ibdev, port_num, &attr);
 	if (ret)
 		return ret;
 
 	return sysfs_emit(buf, "0x%08x\n", attr.port_cap_flags);
 }
 
-static ssize_t rate_show(struct ib_port *p, struct port_attribute *unused,
-			 char *buf)
+static ssize_t rate_show(struct ib_device *ibdev, u32 port_num,
+			 struct ib_port_attribute *unused, char *buf)
 {
 	struct ib_port_attr attr;
 	char *speed = "";
 	int rate;		/* in deci-Gb/sec */
 	ssize_t ret;
 
-	ret = ib_query_port(p->ibdev, p->port_num, &attr);
+	ret = ib_query_port(ibdev, port_num, &attr);
 	if (ret)
 		return ret;
 
@@ -313,27 +376,27 @@ static const char *phys_state_to_str(enum ib_port_phys_state phys_state)
 	return "<unknown>";
 }
 
-static ssize_t phys_state_show(struct ib_port *p, struct port_attribute *unused,
-			       char *buf)
+static ssize_t phys_state_show(struct ib_device *ibdev, u32 port_num,
+			       struct ib_port_attribute *unused, char *buf)
 {
 	struct ib_port_attr attr;
 
 	ssize_t ret;
 
-	ret = ib_query_port(p->ibdev, p->port_num, &attr);
+	ret = ib_query_port(ibdev, port_num, &attr);
 	if (ret)
 		return ret;
 
-	return sysfs_emit(buf, "%d: %s\n", attr.phys_state,
+	return sysfs_emit(buf, "%u: %s\n", attr.phys_state,
 			  phys_state_to_str(attr.phys_state));
 }
 
-static ssize_t link_layer_show(struct ib_port *p, struct port_attribute *unused,
-			       char *buf)
+static ssize_t link_layer_show(struct ib_device *ibdev, u32 port_num,
+			       struct ib_port_attribute *unused, char *buf)
 {
 	const char *output;
 
-	switch (rdma_port_get_link_layer(p->ibdev, p->port_num)) {
+	switch (rdma_port_get_link_layer(ibdev, port_num)) {
 	case IB_LINK_LAYER_INFINIBAND:
 		output = "InfiniBand";
 		break;
@@ -348,26 +411,26 @@ static ssize_t link_layer_show(struct ib_port *p, struct port_attribute *unused,
 	return sysfs_emit(buf, "%s\n", output);
 }
 
-static PORT_ATTR_RO(state);
-static PORT_ATTR_RO(lid);
-static PORT_ATTR_RO(lid_mask_count);
-static PORT_ATTR_RO(sm_lid);
-static PORT_ATTR_RO(sm_sl);
-static PORT_ATTR_RO(cap_mask);
-static PORT_ATTR_RO(rate);
-static PORT_ATTR_RO(phys_state);
-static PORT_ATTR_RO(link_layer);
+static IB_PORT_ATTR_RO(state);
+static IB_PORT_ATTR_RO(lid);
+static IB_PORT_ATTR_RO(lid_mask_count);
+static IB_PORT_ATTR_RO(sm_lid);
+static IB_PORT_ATTR_RO(sm_sl);
+static IB_PORT_ATTR_RO(cap_mask);
+static IB_PORT_ATTR_RO(rate);
+static IB_PORT_ATTR_RO(phys_state);
+static IB_PORT_ATTR_RO(link_layer);
 
 static struct attribute *port_default_attrs[] = {
-	&port_attr_state.attr,
-	&port_attr_lid.attr,
-	&port_attr_lid_mask_count.attr,
-	&port_attr_sm_lid.attr,
-	&port_attr_sm_sl.attr,
-	&port_attr_cap_mask.attr,
-	&port_attr_rate.attr,
-	&port_attr_phys_state.attr,
-	&port_attr_link_layer.attr,
+	&ib_port_attr_state.attr,
+	&ib_port_attr_lid.attr,
+	&ib_port_attr_lid_mask_count.attr,
+	&ib_port_attr_sm_lid.attr,
+	&ib_port_attr_sm_sl.attr,
+	&ib_port_attr_cap_mask.attr,
+	&ib_port_attr_rate.attr,
+	&ib_port_attr_phys_state.attr,
+	&ib_port_attr_link_layer.attr,
 	NULL
 };
 
@@ -391,7 +454,8 @@ static ssize_t print_gid_type(const struct ib_gid_attr *gid_attr, char *buf)
 }
 
 static ssize_t _show_port_gid_attr(
-	struct ib_port *p, struct port_attribute *attr, char *buf,
+	struct ib_device *ibdev, u32 port_num, struct ib_port_attribute *attr,
+	char *buf,
 	ssize_t (*print)(const struct ib_gid_attr *gid_attr, char *buf))
 {
 	struct port_table_attribute *tab_attr =
@@ -399,7 +463,7 @@ static ssize_t _show_port_gid_attr(
 	const struct ib_gid_attr *gid_attr;
 	ssize_t ret;
 
-	gid_attr = rdma_get_gid_attr(p->ibdev, p->port_num, tab_attr->index);
+	gid_attr = rdma_get_gid_attr(ibdev, port_num, tab_attr->index);
 	if (IS_ERR(gid_attr))
 		/* -EINVAL is returned for user space compatibility reasons. */
 		return -EINVAL;
@@ -409,15 +473,15 @@ static ssize_t _show_port_gid_attr(
 	return ret;
 }
 
-static ssize_t show_port_gid(struct ib_port *p, struct port_attribute *attr,
-			     char *buf)
+static ssize_t show_port_gid(struct ib_device *ibdev, u32 port_num,
+			     struct ib_port_attribute *attr, char *buf)
 {
 	struct port_table_attribute *tab_attr =
 		container_of(attr, struct port_table_attribute, attr);
 	const struct ib_gid_attr *gid_attr;
 	int len;
 
-	gid_attr = rdma_get_gid_attr(p->ibdev, p->port_num, tab_attr->index);
+	gid_attr = rdma_get_gid_attr(ibdev, port_num, tab_attr->index);
 	if (IS_ERR(gid_attr)) {
 		const union ib_gid zgid = {};
 
@@ -438,28 +502,30 @@ static ssize_t show_port_gid(struct ib_port *p, struct port_attribute *attr,
 	return len;
 }
 
-static ssize_t show_port_gid_attr_ndev(struct ib_port *p,
-				       struct port_attribute *attr, char *buf)
+static ssize_t show_port_gid_attr_ndev(struct ib_device *ibdev, u32 port_num,
+				       struct ib_port_attribute *attr,
+				       char *buf)
 {
-	return _show_port_gid_attr(p, attr, buf, print_ndev);
+	return _show_port_gid_attr(ibdev, port_num, attr, buf, print_ndev);
 }
 
-static ssize_t show_port_gid_attr_gid_type(struct ib_port *p,
-					   struct port_attribute *attr,
+static ssize_t show_port_gid_attr_gid_type(struct ib_device *ibdev,
+					   u32 port_num,
+					   struct ib_port_attribute *attr,
 					   char *buf)
 {
-	return _show_port_gid_attr(p, attr, buf, print_gid_type);
+	return _show_port_gid_attr(ibdev, port_num, attr, buf, print_gid_type);
 }
 
-static ssize_t show_port_pkey(struct ib_port *p, struct port_attribute *attr,
-			      char *buf)
+static ssize_t show_port_pkey(struct ib_device *ibdev, u32 port_num,
+			      struct ib_port_attribute *attr, char *buf)
 {
 	struct port_table_attribute *tab_attr =
 		container_of(attr, struct port_table_attribute, attr);
 	u16 pkey;
 	int ret;
 
-	ret = ib_query_pkey(p->ibdev, p->port_num, tab_attr->index, &pkey);
+	ret = ib_query_pkey(ibdev, port_num, tab_attr->index, &pkey);
 	if (ret)
 		return ret;
 
@@ -528,8 +594,8 @@ out:
 	return ret;
 }
 
-static ssize_t show_pma_counter(struct ib_port *p, struct port_attribute *attr,
-				char *buf)
+static ssize_t show_pma_counter(struct ib_device *ibdev, u32 port_num,
+				struct ib_port_attribute *attr, char *buf)
 {
 	struct port_table_attribute *tab_attr =
 		container_of(attr, struct port_table_attribute, attr);
@@ -539,14 +605,14 @@ static ssize_t show_pma_counter(struct ib_port *p, struct port_attribute *attr,
 	u8 data[8];
 	int len;
 
-	ret = get_perf_mad(p->ibdev, p->port_num, tab_attr->attr_id, &data,
+	ret = get_perf_mad(ibdev, port_num, tab_attr->attr_id, &data,
 			40 + offset / 8, sizeof(data));
 	if (ret < 0)
 		return ret;
 
 	switch (width) {
 	case 4:
-		len = sysfs_emit(buf, "%u\n",
+		len = sysfs_emit(buf, "%d\n",
 				 (*data >> (4 - (offset % 8))) & 0xf);
 		break;
 	case 8:
@@ -683,54 +749,26 @@ static const struct attribute_group pma_group_noietf = {
 
 static void ib_port_release(struct kobject *kobj)
 {
-	struct ib_port *p = container_of(kobj, struct ib_port, kobj);
-	struct attribute *a;
+	struct ib_port *port = container_of(kobj, struct ib_port, kobj);
 	int i;
 
-	if (p->gid_group.attrs) {
-		for (i = 0; (a = p->gid_group.attrs[i]); ++i)
-			kfree(a);
-
-		kfree(p->gid_group.attrs);
-	}
-
-	if (p->pkey_group) {
-		if (p->pkey_group->attrs) {
-			for (i = 0; (a = p->pkey_group->attrs[i]); ++i)
-				kfree(a);
-
-			kfree(p->pkey_group->attrs);
-		}
-
-		kfree(p->pkey_group);
-		p->pkey_group = NULL;
-	}
-
-	kfree(p);
+	for (i = 0; i != ARRAY_SIZE(port->groups); i++)
+		kfree(port->groups[i].attrs);
+	if (port->hw_stats_data)
+		kfree(port->hw_stats_data->stats);
+	kfree(port->hw_stats_data);
+	kfree(port);
 }
 
 static void ib_port_gid_attr_release(struct kobject *kobj)
 {
-	struct gid_attr_group *g = container_of(kobj, struct gid_attr_group,
-						kobj);
-	struct attribute *a;
+	struct gid_attr_group *gid_attr_group =
+		container_of(kobj, struct gid_attr_group, kobj);
 	int i;
 
-	if (g->ndev.attrs) {
-		for (i = 0; (a = g->ndev.attrs[i]); ++i)
-			kfree(a);
-
-		kfree(g->ndev.attrs);
-	}
-
-	if (g->type.attrs) {
-		for (i = 0; (a = g->type.attrs[i]); ++i)
-			kfree(a);
-
-		kfree(g->type.attrs);
-	}
-
-	kfree(g);
+	for (i = 0; i != ARRAY_SIZE(gid_attr_group->groups); i++)
+		kfree(gid_attr_group->groups[i].attrs);
+	kfree(gid_attr_group);
 }
 
 static struct kobj_type port_type = {
@@ -744,49 +782,6 @@ static struct kobj_type gid_attr_type = {
 	.release        = ib_port_gid_attr_release
 };
 
-static struct attribute **
-alloc_group_attrs(ssize_t (*show)(struct ib_port *,
-				  struct port_attribute *, char *buf),
-		  int len)
-{
-	struct attribute **tab_attr;
-	struct port_table_attribute *element;
-	int i;
-
-	tab_attr = kcalloc(1 + len, sizeof(struct attribute *), GFP_KERNEL);
-	if (!tab_attr)
-		return NULL;
-
-	for (i = 0; i < len; i++) {
-		element = kzalloc(sizeof(struct port_table_attribute),
-				  GFP_KERNEL);
-		if (!element)
-			goto err;
-
-		if (snprintf(element->name, sizeof(element->name),
-			     "%d", i) >= sizeof(element->name)) {
-			kfree(element);
-			goto err;
-		}
-
-		element->attr.attr.name  = element->name;
-		element->attr.attr.mode  = S_IRUGO;
-		element->attr.show       = show;
-		element->index		 = i;
-		sysfs_attr_init(&element->attr.attr);
-
-		tab_attr[i] = &element->attr.attr;
-	}
-
-	return tab_attr;
-
-err:
-	while (--i >= 0)
-		kfree(tab_attr[i]);
-	kfree(tab_attr);
-	return NULL;
-}
-
 /*
  * Figure out which counter table to use depending on
  * the device capabilities.
@@ -835,56 +830,30 @@ static int print_hw_stat(struct ib_device *dev, int port_num,
 	return sysfs_emit(buf, "%llu\n", stats->value[index] + v);
 }
 
-static ssize_t show_hw_stats(struct kobject *kobj, struct attribute *attr,
-			     char *buf)
+static ssize_t show_hw_stats(struct ib_device *ibdev,
+			     struct rdma_hw_stats *stats, unsigned int index,
+			     unsigned int port_num, char *buf)
 {
-	struct ib_device *dev;
-	struct ib_port *port;
-	struct hw_stats_attribute *hsa;
-	struct rdma_hw_stats *stats;
 	int ret;
 
-	hsa = container_of(attr, struct hw_stats_attribute, attr);
-	if (!hsa->port_num) {
-		dev = container_of((struct device *)kobj,
-				   struct ib_device, dev);
-		stats = dev->hw_stats;
-	} else {
-		port = container_of(kobj, struct ib_port, kobj);
-		dev = port->ibdev;
-		stats = port->hw_stats;
-	}
 	mutex_lock(&stats->lock);
-	ret = update_hw_stats(dev, stats, hsa->port_num, hsa->index);
+	ret = update_hw_stats(ibdev, stats, port_num, index);
 	if (ret)
 		goto unlock;
-	ret = print_hw_stat(dev, hsa->port_num, stats, hsa->index, buf);
+	ret = print_hw_stat(ibdev, port_num, stats, index, buf);
 unlock:
 	mutex_unlock(&stats->lock);
 
 	return ret;
 }
 
-static ssize_t show_stats_lifespan(struct kobject *kobj,
-				   struct attribute *attr,
+static ssize_t show_stats_lifespan(struct ib_device *ibdev,
+				   struct rdma_hw_stats *stats,
+				   unsigned int index, unsigned int port_num,
 				   char *buf)
 {
-	struct hw_stats_attribute *hsa;
-	struct rdma_hw_stats *stats;
 	int msecs;
 
-	hsa = container_of(attr, struct hw_stats_attribute, attr);
-	if (!hsa->port_num) {
-		struct ib_device *dev = container_of((struct device *)kobj,
-						     struct ib_device, dev);
-
-		stats = dev->hw_stats;
-	} else {
-		struct ib_port *p = container_of(kobj, struct ib_port, kobj);
-
-		stats = p->hw_stats;
-	}
-
 	mutex_lock(&stats->lock);
 	msecs = jiffies_to_msecs(stats->lifespan);
 	mutex_unlock(&stats->lock);
@@ -892,12 +861,11 @@ static ssize_t show_stats_lifespan(struct kobject *kobj,
 	return sysfs_emit(buf, "%d\n", msecs);
 }
 
-static ssize_t set_stats_lifespan(struct kobject *kobj,
-				  struct attribute *attr,
-				  const char *buf, size_t count)
+static ssize_t set_stats_lifespan(struct ib_device *ibdev,
+				   struct rdma_hw_stats *stats,
+				   unsigned int index, unsigned int port_num,
+				   const char *buf, size_t count)
 {
-	struct hw_stats_attribute *hsa;
-	struct rdma_hw_stats *stats;
 	int msecs;
 	int jiffies;
 	int ret;
@@ -908,17 +876,6 @@ static ssize_t set_stats_lifespan(struct kobject *kobj,
 	if (msecs < 0 || msecs > 10000)
 		return -EINVAL;
 	jiffies = msecs_to_jiffies(msecs);
-	hsa = container_of(attr, struct hw_stats_attribute, attr);
-	if (!hsa->port_num) {
-		struct ib_device *dev = container_of((struct device *)kobj,
-						     struct ib_device, dev);
-
-		stats = dev->hw_stats;
-	} else {
-		struct ib_port *p = container_of(kobj, struct ib_port, kobj);
-
-		stats = p->hw_stats;
-	}
 
 	mutex_lock(&stats->lock);
 	stats->lifespan = jiffies;
@@ -927,65 +884,116 @@ static ssize_t set_stats_lifespan(struct kobject *kobj,
 	return count;
 }
 
-static void free_hsag(struct kobject *kobj, struct attribute_group *attr_group)
+static struct hw_stats_device_data *
+alloc_hw_stats_device(struct ib_device *ibdev)
 {
-	struct attribute **attr;
-
-	sysfs_remove_group(kobj, attr_group);
+	struct hw_stats_device_data *data;
+	struct rdma_hw_stats *stats;
 
-	for (attr = attr_group->attrs; *attr; attr++)
-		kfree(*attr);
-	kfree(attr_group);
-}
+	if (!ibdev->ops.alloc_hw_device_stats)
+		return ERR_PTR(-EOPNOTSUPP);
+	stats = ibdev->ops.alloc_hw_device_stats(ibdev);
+	if (!stats)
+		return ERR_PTR(-ENOMEM);
+	if (!stats->names || stats->num_counters <= 0)
+		goto err_free_stats;
 
-static struct attribute *alloc_hsa(int index, u32 port_num, const char *name)
-{
-	struct hw_stats_attribute *hsa;
+	/*
+	 * Two extra attribue elements here, one for the lifespan entry and
+	 * one to NULL terminate the list for the sysfs core code
+	 */
+	data = kzalloc(struct_size(data, attrs, stats->num_counters + 1),
+		       GFP_KERNEL);
+	if (!data)
+		goto err_free_stats;
+	data->group.attrs = kcalloc(stats->num_counters + 2,
+				    sizeof(*data->group.attrs), GFP_KERNEL);
+	if (!data->group.attrs)
+		goto err_free_data;
 
-	hsa = kmalloc(sizeof(*hsa), GFP_KERNEL);
-	if (!hsa)
-		return NULL;
+	mutex_init(&stats->lock);
+	data->group.name = "hw_counters";
+	data->stats = stats;
+	return data;
 
-	hsa->attr.name = (char *)name;
-	hsa->attr.mode = S_IRUGO;
-	hsa->show = show_hw_stats;
-	hsa->store = NULL;
-	hsa->index = index;
-	hsa->port_num = port_num;
+err_free_data:
+	kfree(data);
+err_free_stats:
+	kfree(stats);
+	return ERR_PTR(-ENOMEM);
+}
 
-	return &hsa->attr;
+void ib_device_release_hw_stats(struct hw_stats_device_data *data)
+{
+	kfree(data->group.attrs);
+	kfree(data->stats);
+	kfree(data);
 }
 
-static struct attribute *alloc_hsa_lifespan(char *name, u32 port_num)
+int ib_setup_device_attrs(struct ib_device *ibdev)
 {
-	struct hw_stats_attribute *hsa;
+	struct hw_stats_device_attribute *attr;
+	struct hw_stats_device_data *data;
+	int i, ret;
 
-	hsa = kmalloc(sizeof(*hsa), GFP_KERNEL);
-	if (!hsa)
-		return NULL;
+	data = alloc_hw_stats_device(ibdev);
+	if (IS_ERR(data)) {
+		if (PTR_ERR(data) == -EOPNOTSUPP)
+			return 0;
+		return PTR_ERR(data);
+	}
+	ibdev->hw_stats_data = data;
 
-	hsa->attr.name = name;
-	hsa->attr.mode = S_IWUSR | S_IRUGO;
-	hsa->show = show_stats_lifespan;
-	hsa->store = set_stats_lifespan;
-	hsa->index = 0;
-	hsa->port_num = port_num;
+	ret = ibdev->ops.get_hw_stats(ibdev, data->stats, 0,
+				      data->stats->num_counters);
+	if (ret != data->stats->num_counters) {
+		if (WARN_ON(ret >= 0))
+			return -EINVAL;
+		return ret;
+	}
+
+	data->stats->timestamp = jiffies;
+
+	for (i = 0; i < data->stats->num_counters; i++) {
+		attr = &data->attrs[i];
+		sysfs_attr_init(&attr->attr.attr);
+		attr->attr.attr.name = data->stats->names[i];
+		attr->attr.attr.mode = 0444;
+		attr->attr.show = hw_stat_device_show;
+		attr->show = show_hw_stats;
+		data->group.attrs[i] = &attr->attr.attr;
+	}
 
-	return &hsa->attr;
+	attr = &data->attrs[i];
+	sysfs_attr_init(&attr->attr.attr);
+	attr->attr.attr.name = "lifespan";
+	attr->attr.attr.mode = 0644;
+	attr->attr.show = hw_stat_device_show;
+	attr->show = show_stats_lifespan;
+	attr->attr.store = hw_stat_device_store;
+	attr->store = set_stats_lifespan;
+	data->group.attrs[i] = &attr->attr.attr;
+	for (i = 0; i != ARRAY_SIZE(ibdev->groups); i++)
+		if (!ibdev->groups[i]) {
+			ibdev->groups[i] = &data->group;
+			return 0;
+		}
+	WARN(true, "struct ib_device->groups is too small");
+	return -EINVAL;
 }
 
-static void setup_hw_stats(struct ib_device *device, struct ib_port *port,
-			   u32 port_num)
+static struct hw_stats_port_data *
+alloc_hw_stats_port(struct ib_port *port, struct attribute_group *group)
 {
-	struct attribute_group *hsag;
+	struct ib_device *ibdev = port->ibdev;
+	struct hw_stats_port_data *data;
 	struct rdma_hw_stats *stats;
-	int i, ret;
-
-	stats = device->ops.alloc_hw_stats(device, port_num);
 
+	if (!ibdev->ops.alloc_hw_port_stats)
+		return ERR_PTR(-EOPNOTSUPP);
+	stats = ibdev->ops.alloc_hw_port_stats(port->ibdev, port->port_num);
 	if (!stats)
-		return;
-
+		return ERR_PTR(-ENOMEM);
 	if (!stats->names || stats->num_counters <= 0)
 		goto err_free_stats;
 
@@ -993,244 +1001,275 @@ static void setup_hw_stats(struct ib_device *device, struct ib_port *port,
 	 * Two extra attribue elements here, one for the lifespan entry and
 	 * one to NULL terminate the list for the sysfs core code
 	 */
-	hsag = kzalloc(sizeof(*hsag) +
-		       sizeof(void *) * (stats->num_counters + 2),
+	data = kzalloc(struct_size(data, attrs, stats->num_counters + 1),
 		       GFP_KERNEL);
-	if (!hsag)
+	if (!data)
 		goto err_free_stats;
+	group->attrs = kcalloc(stats->num_counters + 2,
+				    sizeof(*group->attrs), GFP_KERNEL);
+	if (!group->attrs)
+		goto err_free_data;
 
-	ret = device->ops.get_hw_stats(device, stats, port_num,
-				       stats->num_counters);
-	if (ret != stats->num_counters)
-		goto err_free_hsag;
+	mutex_init(&stats->lock);
+	group->name = "hw_counters";
+	data->stats = stats;
+	return data;
 
-	stats->timestamp = jiffies;
+err_free_data:
+	kfree(data);
+err_free_stats:
+	kfree(stats);
+	return ERR_PTR(-ENOMEM);
+}
 
-	hsag->name = "hw_counters";
-	hsag->attrs = (void *)hsag + sizeof(*hsag);
+static int setup_hw_port_stats(struct ib_port *port,
+			       struct attribute_group *group)
+{
+	struct hw_stats_port_attribute *attr;
+	struct hw_stats_port_data *data;
+	int i, ret;
 
-	for (i = 0; i < stats->num_counters; i++) {
-		hsag->attrs[i] = alloc_hsa(i, port_num, stats->names[i]);
-		if (!hsag->attrs[i])
-			goto err;
-		sysfs_attr_init(hsag->attrs[i]);
+	data = alloc_hw_stats_port(port, group);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	ret = port->ibdev->ops.get_hw_stats(port->ibdev, data->stats,
+					    port->port_num,
+					    data->stats->num_counters);
+	if (ret != data->stats->num_counters) {
+		if (WARN_ON(ret >= 0))
+			return -EINVAL;
+		return ret;
 	}
 
-	mutex_init(&stats->lock);
-	/* treat an error here as non-fatal */
-	hsag->attrs[i] = alloc_hsa_lifespan("lifespan", port_num);
-	if (hsag->attrs[i])
-		sysfs_attr_init(hsag->attrs[i]);
-
-	if (port) {
-		struct kobject *kobj = &port->kobj;
-		ret = sysfs_create_group(kobj, hsag);
-		if (ret)
-			goto err;
-		port->hw_stats_ag = hsag;
-		port->hw_stats = stats;
-		if (device->port_data)
-			device->port_data[port_num].hw_stats = stats;
-	} else {
-		struct kobject *kobj = &device->dev.kobj;
-		ret = sysfs_create_group(kobj, hsag);
-		if (ret)
-			goto err;
-		device->hw_stats_ag = hsag;
-		device->hw_stats = stats;
+	data->stats->timestamp = jiffies;
+
+	for (i = 0; i < data->stats->num_counters; i++) {
+		attr = &data->attrs[i];
+		sysfs_attr_init(&attr->attr.attr);
+		attr->attr.attr.name = data->stats->names[i];
+		attr->attr.attr.mode = 0444;
+		attr->attr.show = hw_stat_port_show;
+		attr->show = show_hw_stats;
+		group->attrs[i] = &attr->attr.attr;
 	}
 
-	return;
+	attr = &data->attrs[i];
+	sysfs_attr_init(&attr->attr.attr);
+	attr->attr.attr.name = "lifespan";
+	attr->attr.attr.mode = 0644;
+	attr->attr.show = hw_stat_port_show;
+	attr->show = show_stats_lifespan;
+	attr->attr.store = hw_stat_port_store;
+	attr->store = set_stats_lifespan;
+	group->attrs[i] = &attr->attr.attr;
+
+	port->hw_stats_data = data;
+	return 0;
+}
 
-err:
-	for (; i >= 0; i--)
-		kfree(hsag->attrs[i]);
-err_free_hsag:
-	kfree(hsag);
-err_free_stats:
-	kfree(stats);
+struct rdma_hw_stats *ib_get_hw_stats_port(struct ib_device *ibdev,
+					   u32 port_num)
+{
+	if (!ibdev->port_data || !rdma_is_port_valid(ibdev, port_num) ||
+	    !ibdev->port_data[port_num].sysfs->hw_stats_data)
+		return NULL;
+	return ibdev->port_data[port_num].sysfs->hw_stats_data->stats;
 }
 
-static int add_port(struct ib_core_device *coredev, int port_num)
+static int
+alloc_port_table_group(const char *name, struct attribute_group *group,
+		       struct port_table_attribute *attrs, size_t num,
+		       ssize_t (*show)(struct ib_device *ibdev, u32 port_num,
+				       struct ib_port_attribute *, char *buf))
 {
-	struct ib_device *device = rdma_device_to_ibdev(&coredev->dev);
-	bool is_full_dev = &device->coredev == coredev;
-	struct ib_port *p;
-	struct ib_port_attr attr;
+	struct attribute **attr_list;
 	int i;
-	int ret;
-
-	ret = ib_query_port(device, port_num, &attr);
-	if (ret)
-		return ret;
 
-	p = kzalloc(sizeof *p, GFP_KERNEL);
-	if (!p)
+	attr_list = kcalloc(num + 1, sizeof(*attr_list), GFP_KERNEL);
+	if (!attr_list)
 		return -ENOMEM;
 
-	p->ibdev      = device;
-	p->port_num   = port_num;
-
-	ret = kobject_init_and_add(&p->kobj, &port_type,
-				   coredev->ports_kobj,
-				   "%d", port_num);
-	if (ret)
-		goto err_put;
+	for (i = 0; i < num; i++) {
+		struct port_table_attribute *element = &attrs[i];
 
-	p->gid_attr_group = kzalloc(sizeof(*p->gid_attr_group), GFP_KERNEL);
-	if (!p->gid_attr_group) {
-		ret = -ENOMEM;
-		goto err_put;
-	}
-
-	p->gid_attr_group->port = p;
-	ret = kobject_init_and_add(&p->gid_attr_group->kobj, &gid_attr_type,
-				   &p->kobj, "gid_attrs");
-	if (ret)
-		goto err_put_gid_attrs;
+		if (snprintf(element->name, sizeof(element->name), "%d", i) >=
+		    sizeof(element->name))
+			goto err;
 
-	if (device->ops.process_mad && is_full_dev) {
-		p->pma_table = get_counter_table(device, port_num);
-		ret = sysfs_create_group(&p->kobj, p->pma_table);
-		if (ret)
-			goto err_put_gid_attrs;
-	}
+		sysfs_attr_init(&element->attr.attr);
+		element->attr.attr.name = element->name;
+		element->attr.attr.mode = 0444;
+		element->attr.show = show;
+		element->index = i;
 
-	p->gid_group.name  = "gids";
-	p->gid_group.attrs = alloc_group_attrs(show_port_gid, attr.gid_tbl_len);
-	if (!p->gid_group.attrs) {
-		ret = -ENOMEM;
-		goto err_remove_pma;
+		attr_list[i] = &element->attr.attr;
 	}
+	group->name = name;
+	group->attrs = attr_list;
+	return 0;
+err:
+	kfree(attr_list);
+	return -EINVAL;
+}
 
-	ret = sysfs_create_group(&p->kobj, &p->gid_group);
-	if (ret)
-		goto err_free_gid;
+/*
+ * Create the sysfs:
+ *  ibp0s9/ports/XX/gid_attrs/{ndevs,types}/YYY
+ * YYY is the gid table index in decimal
+ */
+static int setup_gid_attrs(struct ib_port *port,
+			   const struct ib_port_attr *attr)
+{
+	struct gid_attr_group *gid_attr_group;
+	int ret;
 
-	p->gid_attr_group->ndev.name = "ndevs";
-	p->gid_attr_group->ndev.attrs = alloc_group_attrs(show_port_gid_attr_ndev,
-							  attr.gid_tbl_len);
-	if (!p->gid_attr_group->ndev.attrs) {
-		ret = -ENOMEM;
-		goto err_remove_gid;
-	}
+	gid_attr_group = kzalloc(struct_size(gid_attr_group, attrs_list,
+					     attr->gid_tbl_len * 2),
+				 GFP_KERNEL);
+	if (!gid_attr_group)
+		return -ENOMEM;
+	gid_attr_group->port = port;
+	kobject_init(&gid_attr_group->kobj, &gid_attr_type);
 
-	ret = sysfs_create_group(&p->gid_attr_group->kobj,
-				 &p->gid_attr_group->ndev);
+	ret = alloc_port_table_group("ndevs", &gid_attr_group->groups[0],
+				     gid_attr_group->attrs_list,
+				     attr->gid_tbl_len,
+				     show_port_gid_attr_ndev);
 	if (ret)
-		goto err_free_gid_ndev;
+		goto err_put;
+	gid_attr_group->groups_list[0] = &gid_attr_group->groups[0];
 
-	p->gid_attr_group->type.name = "types";
-	p->gid_attr_group->type.attrs = alloc_group_attrs(show_port_gid_attr_gid_type,
-							  attr.gid_tbl_len);
-	if (!p->gid_attr_group->type.attrs) {
-		ret = -ENOMEM;
-		goto err_remove_gid_ndev;
-	}
+	ret = alloc_port_table_group(
+		"types", &gid_attr_group->groups[1],
+		gid_attr_group->attrs_list + attr->gid_tbl_len,
+		attr->gid_tbl_len, show_port_gid_attr_gid_type);
+	if (ret)
+		goto err_put;
+	gid_attr_group->groups_list[1] = &gid_attr_group->groups[1];
 
-	ret = sysfs_create_group(&p->gid_attr_group->kobj,
-				 &p->gid_attr_group->type);
+	ret = kobject_add(&gid_attr_group->kobj, &port->kobj, "gid_attrs");
+	if (ret)
+		goto err_put;
+	ret = sysfs_create_groups(&gid_attr_group->kobj,
+				  gid_attr_group->groups_list);
 	if (ret)
-		goto err_free_gid_type;
+		goto err_del;
+	port->gid_attr_group = gid_attr_group;
+	return 0;
 
-	if (attr.pkey_tbl_len) {
-		p->pkey_group = kzalloc(sizeof(*p->pkey_group), GFP_KERNEL);
-		if (!p->pkey_group) {
-			ret = -ENOMEM;
-			goto err_remove_gid_type;
-		}
+err_del:
+	kobject_del(&gid_attr_group->kobj);
+err_put:
+	kobject_put(&gid_attr_group->kobj);
+	return ret;
+}
 
-		p->pkey_group->name  = "pkeys";
-		p->pkey_group->attrs = alloc_group_attrs(show_port_pkey,
-							 attr.pkey_tbl_len);
-		if (!p->pkey_group->attrs) {
-			ret = -ENOMEM;
-			goto err_free_pkey_group;
-		}
+static void destroy_gid_attrs(struct ib_port *port)
+{
+	struct gid_attr_group *gid_attr_group = port->gid_attr_group;
 
-		ret = sysfs_create_group(&p->kobj, p->pkey_group);
-		if (ret)
-			goto err_free_pkey;
-	}
+	if (!gid_attr_group)
+		return;
+	sysfs_remove_groups(&gid_attr_group->kobj, gid_attr_group->groups_list);
+	kobject_del(&gid_attr_group->kobj);
+	kobject_put(&gid_attr_group->kobj);
+}
+
+/*
+ * Create the sysfs:
+ *  ibp0s9/ports/XX/{gids,pkeys,counters}/YYY
+ */
+static struct ib_port *setup_port(struct ib_core_device *coredev, int port_num,
+				  const struct ib_port_attr *attr)
+{
+	struct ib_device *device = rdma_device_to_ibdev(&coredev->dev);
+	bool is_full_dev = &device->coredev == coredev;
+	const struct attribute_group **cur_group;
+	struct ib_port *p;
+	int ret;
 
+	p = kzalloc(struct_size(p, attrs_list,
+				attr->gid_tbl_len + attr->pkey_tbl_len),
+		    GFP_KERNEL);
+	if (!p)
+		return ERR_PTR(-ENOMEM);
+	p->ibdev = device;
+	p->port_num = port_num;
+	kobject_init(&p->kobj, &port_type);
+
+	cur_group = p->groups_list;
+	ret = alloc_port_table_group("gids", &p->groups[0], p->attrs_list,
+				     attr->gid_tbl_len, show_port_gid);
+	if (ret)
+		goto err_put;
+	*cur_group++ = &p->groups[0];
 
-	if (device->ops.init_port && is_full_dev) {
-		ret = device->ops.init_port(device, port_num, &p->kobj);
+	if (attr->pkey_tbl_len) {
+		ret = alloc_port_table_group("pkeys", &p->groups[1],
+					     p->attrs_list + attr->gid_tbl_len,
+					     attr->pkey_tbl_len, show_port_pkey);
 		if (ret)
-			goto err_remove_pkey;
+			goto err_put;
+		*cur_group++ = &p->groups[1];
 	}
 
 	/*
 	 * If port == 0, it means hw_counters are per device and not per
-	 * port, so holder should be device. Therefore skip per port conunter
-	 * initialization.
+	 * port, so holder should be device. Therefore skip per port
+	 * counter initialization.
 	 */
-	if (device->ops.alloc_hw_stats && port_num && is_full_dev)
-		setup_hw_stats(device, p, port_num);
-
-	list_add_tail(&p->kobj.entry, &coredev->port_list);
-
-	kobject_uevent(&p->kobj, KOBJ_ADD);
-	return 0;
-
-err_remove_pkey:
-	if (p->pkey_group)
-		sysfs_remove_group(&p->kobj, p->pkey_group);
-
-err_free_pkey:
-	if (p->pkey_group) {
-		for (i = 0; i < attr.pkey_tbl_len; ++i)
-			kfree(p->pkey_group->attrs[i]);
-
-		kfree(p->pkey_group->attrs);
-		p->pkey_group->attrs = NULL;
+	if (port_num && is_full_dev) {
+		ret = setup_hw_port_stats(p, &p->groups[2]);
+		if (ret && ret != -EOPNOTSUPP)
+			goto err_put;
+		if (!ret)
+			*cur_group++ = &p->groups[2];
 	}
 
-err_free_pkey_group:
-	kfree(p->pkey_group);
-
-err_remove_gid_type:
-	sysfs_remove_group(&p->gid_attr_group->kobj,
-			   &p->gid_attr_group->type);
-
-err_free_gid_type:
-	for (i = 0; i < attr.gid_tbl_len; ++i)
-		kfree(p->gid_attr_group->type.attrs[i]);
-
-	kfree(p->gid_attr_group->type.attrs);
-	p->gid_attr_group->type.attrs = NULL;
-
-err_remove_gid_ndev:
-	sysfs_remove_group(&p->gid_attr_group->kobj,
-			   &p->gid_attr_group->ndev);
-
-err_free_gid_ndev:
-	for (i = 0; i < attr.gid_tbl_len; ++i)
-		kfree(p->gid_attr_group->ndev.attrs[i]);
+	if (device->ops.process_mad && is_full_dev)
+		*cur_group++ = get_counter_table(device, port_num);
 
-	kfree(p->gid_attr_group->ndev.attrs);
-	p->gid_attr_group->ndev.attrs = NULL;
-
-err_remove_gid:
-	sysfs_remove_group(&p->kobj, &p->gid_group);
-
-err_free_gid:
-	for (i = 0; i < attr.gid_tbl_len; ++i)
-		kfree(p->gid_group.attrs[i]);
-
-	kfree(p->gid_group.attrs);
-	p->gid_group.attrs = NULL;
+	ret = kobject_add(&p->kobj, coredev->ports_kobj, "%d", port_num);
+	if (ret)
+		goto err_put;
+	ret = sysfs_create_groups(&p->kobj, p->groups_list);
+	if (ret)
+		goto err_del;
+	if (is_full_dev) {
+		ret = sysfs_create_groups(&p->kobj, device->ops.port_groups);
+		if (ret)
+			goto err_groups;
+	}
 
-err_remove_pma:
-	if (p->pma_table)
-		sysfs_remove_group(&p->kobj, p->pma_table);
+	list_add_tail(&p->kobj.entry, &coredev->port_list);
+	if (device->port_data && is_full_dev)
+		device->port_data[port_num].sysfs = p;
 
-err_put_gid_attrs:
-	kobject_put(&p->gid_attr_group->kobj);
+	return p;
 
+err_groups:
+	sysfs_remove_groups(&p->kobj, p->groups_list);
+err_del:
+	kobject_del(&p->kobj);
 err_put:
 	kobject_put(&p->kobj);
-	return ret;
+	return ERR_PTR(ret);
+}
+
+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);
+	kobject_put(&port->kobj);
 }
 
 static const char *node_type_string(int node_type)
@@ -1259,7 +1298,7 @@ static ssize_t node_type_show(struct device *device,
 {
 	struct ib_device *dev = rdma_device_to_ibdev(device);
 
-	return sysfs_emit(buf, "%d: %s\n", dev->node_type,
+	return sysfs_emit(buf, "%u: %s\n", dev->node_type,
 			  node_type_string(dev->node_type));
 }
 static DEVICE_ATTR_RO(node_type);
@@ -1347,31 +1386,13 @@ const struct attribute_group ib_dev_attr_group = {
 
 void ib_free_port_attrs(struct ib_core_device *coredev)
 {
-	struct ib_device *device = rdma_device_to_ibdev(&coredev->dev);
-	bool is_full_dev = &device->coredev == coredev;
 	struct kobject *p, *t;
 
 	list_for_each_entry_safe(p, t, &coredev->port_list, entry) {
 		struct ib_port *port = container_of(p, struct ib_port, kobj);
 
-		list_del(&p->entry);
-		if (port->hw_stats_ag)
-			free_hsag(&port->kobj, port->hw_stats_ag);
-		kfree(port->hw_stats);
-		if (device->port_data && is_full_dev)
-			device->port_data[port->port_num].hw_stats = NULL;
-
-		if (port->pma_table)
-			sysfs_remove_group(p, port->pma_table);
-		if (port->pkey_group)
-			sysfs_remove_group(p, port->pkey_group);
-		sysfs_remove_group(p, &port->gid_group);
-		sysfs_remove_group(&port->gid_attr_group->kobj,
-				   &port->gid_attr_group->ndev);
-		sysfs_remove_group(&port->gid_attr_group->kobj,
-				   &port->gid_attr_group->type);
-		kobject_put(&port->gid_attr_group->kobj);
-		kobject_put(p);
+		destroy_gid_attrs(port);
+		destroy_port(coredev, port);
 	}
 
 	kobject_put(coredev->ports_kobj);
@@ -1380,7 +1401,7 @@ void ib_free_port_attrs(struct ib_core_device *coredev)
 int ib_setup_port_attrs(struct ib_core_device *coredev)
 {
 	struct ib_device *device = rdma_device_to_ibdev(&coredev->dev);
-	u32 port;
+	u32 port_num;
 	int ret;
 
 	coredev->ports_kobj = kobject_create_and_add("ports",
@@ -1388,12 +1409,24 @@ int ib_setup_port_attrs(struct ib_core_device *coredev)
 	if (!coredev->ports_kobj)
 		return -ENOMEM;
 
-	rdma_for_each_port (device, port) {
-		ret = add_port(coredev, port);
+	rdma_for_each_port (device, port_num) {
+		struct ib_port_attr attr;
+		struct ib_port *port;
+
+		ret = ib_query_port(device, port_num, &attr);
 		if (ret)
 			goto err_put;
-	}
 
+		port = setup_port(coredev, port_num, &attr);
+		if (IS_ERR(port)) {
+			ret = PTR_ERR(port);
+			goto err_put;
+		}
+
+		ret = setup_gid_attrs(port, &attr);
+		if (ret)
+			goto err_put;
+	}
 	return 0;
 
 err_put:
@@ -1401,70 +1434,27 @@ err_put:
 	return ret;
 }
 
-int ib_device_register_sysfs(struct ib_device *device)
-{
-	int ret;
-
-	ret = ib_setup_port_attrs(&device->coredev);
-	if (ret)
-		return ret;
-
-	if (device->ops.alloc_hw_stats)
-		setup_hw_stats(device, NULL, 0);
-
-	return 0;
-}
-
-void ib_device_unregister_sysfs(struct ib_device *device)
-{
-	if (device->hw_stats_ag)
-		free_hsag(&device->dev.kobj, device->hw_stats_ag);
-	kfree(device->hw_stats);
-
-	ib_free_port_attrs(&device->coredev);
-}
-
 /**
- * ib_port_register_module_stat - add module counters under relevant port
- *  of IB device.
+ * ib_port_register_client_groups - Add an ib_client's attributes to the port
  *
- * @device: IB device to add counters
+ * @ibdev: IB device to add counters
  * @port_num: valid port number
- * @kobj: pointer to the kobject to initialize
- * @ktype: pointer to the ktype for this kobject.
- * @name: the name of the kobject
+ * @groups: Group list of attributes
+ *
+ * Do not use. Only for legacy sysfs compatibility.
  */
-int ib_port_register_module_stat(struct ib_device *device, u32 port_num,
-				 struct kobject *kobj, struct kobj_type *ktype,
-				 const char *name)
+int ib_port_register_client_groups(struct ib_device *ibdev, u32 port_num,
+				   const struct attribute_group **groups)
 {
-	struct kobject *p, *t;
-	int ret;
-
-	list_for_each_entry_safe(p, t, &device->coredev.port_list, entry) {
-		struct ib_port *port = container_of(p, struct ib_port, kobj);
-
-		if (port->port_num != port_num)
-			continue;
-
-		ret = kobject_init_and_add(kobj, ktype, &port->kobj, "%s",
-					   name);
-		if (ret) {
-			kobject_put(kobj);
-			return ret;
-		}
-	}
-
-	return 0;
+	return sysfs_create_groups(&ibdev->port_data[port_num].sysfs->kobj,
+				   groups);
 }
-EXPORT_SYMBOL(ib_port_register_module_stat);
+EXPORT_SYMBOL(ib_port_register_client_groups);
 
-/**
- * ib_port_unregister_module_stat - release module counters
- * @kobj: pointer to the kobject to release
- */
-void ib_port_unregister_module_stat(struct kobject *kobj)
+void ib_port_unregister_client_groups(struct ib_device *ibdev, u32 port_num,
+				      const struct attribute_group **groups)
 {
-	kobject_put(kobj);
+	return sysfs_remove_groups(&ibdev->port_data[port_num].sysfs->kobj,
+				   groups);
 }
-EXPORT_SYMBOL(ib_port_unregister_module_stat);
+EXPORT_SYMBOL(ib_port_unregister_client_groups);