1 files changed, 232 insertions, 172 deletions

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index ae4c91b612ce..dd35e03402ab 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -82,17 +82,11 @@ static const char mlx4_ib_version[] =
 static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init);
 static enum rdma_link_layer mlx4_ib_port_link_layer(struct ib_device *device,
 						    u32 port_num);
+static int mlx4_ib_event(struct notifier_block *this, unsigned long event,
+			 void *param);
 
 static struct workqueue_struct *wq;
 
-static void init_query_mad(struct ib_smp *mad)
-{
-	mad->base_version  = 1;
-	mad->mgmt_class    = IB_MGMT_CLASS_SUBN_LID_ROUTED;
-	mad->class_version = 1;
-	mad->method	   = IB_MGMT_METHOD_GET;
-}
-
 static int check_flow_steering_support(struct mlx4_dev *dev)
 {
 	int eth_num_ports = 0;
@@ -133,14 +127,16 @@ static struct net_device *mlx4_ib_get_netdev(struct ib_device *device,
 					     u32 port_num)
 {
 	struct mlx4_ib_dev *ibdev = to_mdev(device);
-	struct net_device *dev;
+	struct net_device *dev, *ret = NULL;
 
 	rcu_read_lock();
-	dev = mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port_num);
+	for_each_netdev_rcu(&init_net, dev) {
+		if (dev->dev.parent != ibdev->ib_dev.dev.parent ||
+		    dev->dev_port + 1 != port_num)
+			continue;
 
-	if (dev) {
 		if (mlx4_is_bonded(ibdev->dev)) {
-			struct net_device *upper = NULL;
+			struct net_device *upper;
 
 			upper = netdev_master_upper_dev_get_rcu(dev);
 			if (upper) {
@@ -151,12 +147,14 @@ static struct net_device *mlx4_ib_get_netdev(struct ib_device *device,
 					dev = active;
 			}
 		}
-	}
-	if (dev)
+
 		dev_hold(dev);
+		ret = dev;
+		break;
+	}
 
 	rcu_read_unlock();
-	return dev;
+	return ret;
 }
 
 static int mlx4_ib_update_gids_v1(struct gid_entry *gids,
@@ -263,7 +261,7 @@ static int mlx4_ib_add_gid(const struct ib_gid_attr *attr, void **context)
 	int ret = 0;
 	int hw_update = 0;
 	int i;
-	struct gid_entry *gids = NULL;
+	struct gid_entry *gids;
 	u16 vlan_id = 0xffff;
 	u8 mac[ETH_ALEN];
 
@@ -302,8 +300,7 @@ static int mlx4_ib_add_gid(const struct ib_gid_attr *attr, void **context)
 				ret = -ENOMEM;
 			} else {
 				*context = port_gid_table->gids[free].ctx;
-				memcpy(&port_gid_table->gids[free].gid,
-				       &attr->gid, sizeof(attr->gid));
+				port_gid_table->gids[free].gid = attr->gid;
 				port_gid_table->gids[free].gid_type = attr->gid_type;
 				port_gid_table->gids[free].vlan_id = vlan_id;
 				port_gid_table->gids[free].ctx->real_index = free;
@@ -392,10 +389,10 @@ static int mlx4_ib_del_gid(const struct ib_gid_attr *attr, void **context)
 	}
 	spin_unlock_bh(&iboe->lock);
 
-	if (!ret && hw_update) {
+	if (gids)
 		ret = mlx4_ib_update_gids(gids, ibdev, attr->port_num);
-		kfree(gids);
-	}
+
+	kfree(gids);
 	return ret;
 }
 
@@ -440,8 +437,8 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 				struct ib_udata *uhw)
 {
 	struct mlx4_ib_dev *dev = to_mdev(ibdev);
-	struct ib_smp *in_mad  = NULL;
-	struct ib_smp *out_mad = NULL;
+	struct ib_smp *in_mad;
+	struct ib_smp *out_mad;
 	int err;
 	int have_ib_ports;
 	struct mlx4_uverbs_ex_query_device cmd;
@@ -471,7 +468,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 	if (!in_mad || !out_mad)
 		goto out;
 
-	init_query_mad(in_mad);
+	ib_init_query_mad(in_mad);
 	in_mad->attr_id = IB_SMP_ATTR_NODE_INFO;
 
 	err = mlx4_MAD_IFC(to_mdev(ibdev), MLX4_MAD_IFC_IGNORE_KEYS,
@@ -487,8 +484,8 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 	props->device_cap_flags    = IB_DEVICE_CHANGE_PHY_PORT |
 		IB_DEVICE_PORT_ACTIVE_EVENT		|
 		IB_DEVICE_SYS_IMAGE_GUID		|
-		IB_DEVICE_RC_RNR_NAK_GEN		|
-		IB_DEVICE_BLOCK_MULTICAST_LOOPBACK;
+		IB_DEVICE_RC_RNR_NAK_GEN;
+	props->kernel_cap_flags = IBK_BLOCK_MULTICAST_LOOPBACK;
 	if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_BAD_PKEY_CNTR)
 		props->device_cap_flags |= IB_DEVICE_BAD_PKEY_CNTR;
 	if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_BAD_QKEY_CNTR)
@@ -502,9 +499,9 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 	if (dev->dev->caps.max_gso_sz &&
 	    (dev->dev->rev_id != MLX4_IB_CARD_REV_A0) &&
 	    (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_BLH))
-		props->device_cap_flags |= IB_DEVICE_UD_TSO;
+		props->kernel_cap_flags |= IBK_UD_TSO;
 	if (dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_RESERVED_LKEY)
-		props->device_cap_flags |= IB_DEVICE_LOCAL_DMA_LKEY;
+		props->kernel_cap_flags |= IBK_LOCAL_DMA_LKEY;
 	if ((dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_LOCAL_INV) &&
 	    (dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_REMOTE_INV) &&
 	    (dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_FAST_REG_WR))
@@ -658,8 +655,8 @@ mlx4_ib_port_link_layer(struct ib_device *device, u32 port_num)
 static int ib_link_query_port(struct ib_device *ibdev, u32 port,
 			      struct ib_port_attr *props, int netw_view)
 {
-	struct ib_smp *in_mad  = NULL;
-	struct ib_smp *out_mad = NULL;
+	struct ib_smp *in_mad;
+	struct ib_smp *out_mad;
 	int ext_active_speed;
 	int mad_ifc_flags = MLX4_MAD_IFC_IGNORE_KEYS;
 	int err = -ENOMEM;
@@ -669,7 +666,7 @@ static int ib_link_query_port(struct ib_device *ibdev, u32 port,
 	if (!in_mad || !out_mad)
 		goto out;
 
-	init_query_mad(in_mad);
+	ib_init_query_mad(in_mad);
 	in_mad->attr_id  = IB_SMP_ATTR_PORT_INFO;
 	in_mad->attr_mod = cpu_to_be32(port);
 
@@ -721,7 +718,7 @@ static int ib_link_query_port(struct ib_device *ibdev, u32 port,
 
 	/* If reported active speed is QDR, check if is FDR-10 */
 	if (props->active_speed == IB_SPEED_QDR) {
-		init_query_mad(in_mad);
+		ib_init_query_mad(in_mad);
 		in_mad->attr_id = MLX4_ATTR_EXTENDED_PORT_INFO;
 		in_mad->attr_mod = cpu_to_be32(port);
 
@@ -836,8 +833,8 @@ static int mlx4_ib_query_port(struct ib_device *ibdev, u32 port,
 int __mlx4_ib_query_gid(struct ib_device *ibdev, u32 port, int index,
 			union ib_gid *gid, int netw_view)
 {
-	struct ib_smp *in_mad  = NULL;
-	struct ib_smp *out_mad = NULL;
+	struct ib_smp *in_mad;
+	struct ib_smp *out_mad;
 	int err = -ENOMEM;
 	struct mlx4_ib_dev *dev = to_mdev(ibdev);
 	int clear = 0;
@@ -848,7 +845,7 @@ int __mlx4_ib_query_gid(struct ib_device *ibdev, u32 port, int index,
 	if (!in_mad || !out_mad)
 		goto out;
 
-	init_query_mad(in_mad);
+	ib_init_query_mad(in_mad);
 	in_mad->attr_id  = IB_SMP_ATTR_PORT_INFO;
 	in_mad->attr_mod = cpu_to_be32(port);
 
@@ -870,7 +867,7 @@ int __mlx4_ib_query_gid(struct ib_device *ibdev, u32 port, int index,
 		}
 	}
 
-	init_query_mad(in_mad);
+	ib_init_query_mad(in_mad);
 	in_mad->attr_id  = IB_SMP_ATTR_GUID_INFO;
 	in_mad->attr_mod = cpu_to_be32(index / 8);
 
@@ -901,8 +898,8 @@ static int mlx4_ib_query_sl2vl(struct ib_device *ibdev, u32 port,
 			       u64 *sl2vl_tbl)
 {
 	union sl2vl_tbl_to_u64 sl2vl64;
-	struct ib_smp *in_mad  = NULL;
-	struct ib_smp *out_mad = NULL;
+	struct ib_smp *in_mad;
+	struct ib_smp *out_mad;
 	int mad_ifc_flags = MLX4_MAD_IFC_IGNORE_KEYS;
 	int err = -ENOMEM;
 	int jj;
@@ -917,7 +914,7 @@ static int mlx4_ib_query_sl2vl(struct ib_device *ibdev, u32 port,
 	if (!in_mad || !out_mad)
 		goto out;
 
-	init_query_mad(in_mad);
+	ib_init_query_mad(in_mad);
 	in_mad->attr_id  = IB_SMP_ATTR_SL_TO_VL_TABLE;
 	in_mad->attr_mod = 0;
 
@@ -961,8 +958,8 @@ static void mlx4_init_sl2vl_tbl(struct mlx4_ib_dev *mdev)
 int __mlx4_ib_query_pkey(struct ib_device *ibdev, u32 port, u16 index,
 			 u16 *pkey, int netw_view)
 {
-	struct ib_smp *in_mad  = NULL;
-	struct ib_smp *out_mad = NULL;
+	struct ib_smp *in_mad;
+	struct ib_smp *out_mad;
 	int mad_ifc_flags = MLX4_MAD_IFC_IGNORE_KEYS;
 	int err = -ENOMEM;
 
@@ -971,7 +968,7 @@ int __mlx4_ib_query_pkey(struct ib_device *ibdev, u32 port, u16 index,
 	if (!in_mad || !out_mad)
 		goto out;
 
-	init_query_mad(in_mad);
+	ib_init_query_mad(in_mad);
 	in_mad->attr_id  = IB_SMP_ATTR_PKEY_TABLE;
 	in_mad->attr_mod = cpu_to_be32(index / 32);
 
@@ -1315,8 +1312,7 @@ int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
 
 	spin_lock_bh(&mdev->iboe.lock);
 	ndev = mdev->iboe.netdevs[mqp->port - 1];
-	if (ndev)
-		dev_hold(ndev);
+	dev_hold(ndev);
 	spin_unlock_bh(&mdev->iboe.lock);
 
 	if (ndev) {
@@ -1963,11 +1959,9 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 	if (ge) {
 		spin_lock_bh(&mdev->iboe.lock);
 		ndev = ge->added ? mdev->iboe.netdevs[ge->port - 1] : NULL;
-		if (ndev)
-			dev_hold(ndev);
+		dev_hold(ndev);
 		spin_unlock_bh(&mdev->iboe.lock);
-		if (ndev)
-			dev_put(ndev);
+		dev_put(ndev);
 		list_del(&ge->list);
 		kfree(ge);
 	} else
@@ -1980,8 +1974,8 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 
 static int init_node_data(struct mlx4_ib_dev *dev)
 {
-	struct ib_smp *in_mad  = NULL;
-	struct ib_smp *out_mad = NULL;
+	struct ib_smp *in_mad;
+	struct ib_smp *out_mad;
 	int mad_ifc_flags = MLX4_MAD_IFC_IGNORE_KEYS;
 	int err = -ENOMEM;
 
@@ -1990,7 +1984,7 @@ static int init_node_data(struct mlx4_ib_dev *dev)
 	if (!in_mad || !out_mad)
 		goto out;
 
-	init_query_mad(in_mad);
+	ib_init_query_mad(in_mad);
 	in_mad->attr_id = IB_SMP_ATTR_NODE_DESC;
 	if (mlx4_is_master(dev->dev))
 		mad_ifc_flags |= MLX4_MAD_IFC_NET_VIEW;
@@ -2105,10 +2099,10 @@ mlx4_ib_alloc_hw_device_stats(struct ib_device *ibdev)
 	struct mlx4_ib_dev *dev = to_mdev(ibdev);
 	struct mlx4_ib_diag_counters *diag = dev->diag_counters;
 
-	if (!diag[0].name)
+	if (!diag[0].descs)
 		return NULL;
 
-	return rdma_alloc_hw_stats_struct(diag[0].name, diag[0].num_counters,
+	return rdma_alloc_hw_stats_struct(diag[0].descs, diag[0].num_counters,
 					  RDMA_HW_STATS_DEFAULT_LIFESPAN);
 }
 
@@ -2118,10 +2112,10 @@ mlx4_ib_alloc_hw_port_stats(struct ib_device *ibdev, u32 port_num)
 	struct mlx4_ib_dev *dev = to_mdev(ibdev);
 	struct mlx4_ib_diag_counters *diag = dev->diag_counters;
 
-	if (!diag[1].name)
+	if (!diag[1].descs)
 		return NULL;
 
-	return rdma_alloc_hw_stats_struct(diag[1].name, diag[1].num_counters,
+	return rdma_alloc_hw_stats_struct(diag[1].descs, diag[1].num_counters,
 					  RDMA_HW_STATS_DEFAULT_LIFESPAN);
 }
 
@@ -2151,10 +2145,8 @@ static int mlx4_ib_get_hw_stats(struct ib_device *ibdev,
 }
 
 static int __mlx4_ib_alloc_diag_counters(struct mlx4_ib_dev *ibdev,
-					 const char ***name,
-					 u32 **offset,
-					 u32 *num,
-					 bool port)
+					 struct rdma_stat_desc **pdescs,
+					 u32 **offset, u32 *num, bool port)
 {
 	u32 num_counters;
 
@@ -2166,46 +2158,46 @@ static int __mlx4_ib_alloc_diag_counters(struct mlx4_ib_dev *ibdev,
 	if (!port)
 		num_counters += ARRAY_SIZE(diag_device_only);
 
-	*name = kcalloc(num_counters, sizeof(**name), GFP_KERNEL);
-	if (!*name)
+	*pdescs = kcalloc(num_counters, sizeof(struct rdma_stat_desc),
+			  GFP_KERNEL);
+	if (!*pdescs)
 		return -ENOMEM;
 
 	*offset = kcalloc(num_counters, sizeof(**offset), GFP_KERNEL);
 	if (!*offset)
-		goto err_name;
+		goto err;
 
 	*num = num_counters;
 
 	return 0;
 
-err_name:
-	kfree(*name);
+err:
+	kfree(*pdescs);
 	return -ENOMEM;
 }
 
 static void mlx4_ib_fill_diag_counters(struct mlx4_ib_dev *ibdev,
-				       const char **name,
-				       u32 *offset,
-				       bool port)
+				       struct rdma_stat_desc *descs,
+				       u32 *offset, bool port)
 {
 	int i;
 	int j;
 
 	for (i = 0, j = 0; i < ARRAY_SIZE(diag_basic); i++, j++) {
-		name[i] = diag_basic[i].name;
+		descs[i].name = diag_basic[i].name;
 		offset[i] = diag_basic[i].offset;
 	}
 
 	if (ibdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DIAG_PER_PORT) {
 		for (i = 0; i < ARRAY_SIZE(diag_ext); i++, j++) {
-			name[j] = diag_ext[i].name;
+			descs[j].name = diag_ext[i].name;
 			offset[j] = diag_ext[i].offset;
 		}
 	}
 
 	if (!port) {
 		for (i = 0; i < ARRAY_SIZE(diag_device_only); i++, j++) {
-			name[j] = diag_device_only[i].name;
+			descs[j].name = diag_device_only[i].name;
 			offset[j] = diag_device_only[i].offset;
 		}
 	}
@@ -2217,6 +2209,11 @@ static const struct ib_device_ops mlx4_ib_hw_stats_ops = {
 	.get_hw_stats = mlx4_ib_get_hw_stats,
 };
 
+static const struct ib_device_ops mlx4_ib_hw_stats_ops1 = {
+	.alloc_hw_device_stats = mlx4_ib_alloc_hw_device_stats,
+	.get_hw_stats = mlx4_ib_get_hw_stats,
+};
+
 static int mlx4_ib_alloc_diag_counters(struct mlx4_ib_dev *ibdev)
 {
 	struct mlx4_ib_diag_counters *diag = ibdev->diag_counters;
@@ -2229,17 +2226,24 @@ static int mlx4_ib_alloc_diag_counters(struct mlx4_ib_dev *ibdev)
 		return 0;
 
 	for (i = 0; i < MLX4_DIAG_COUNTERS_TYPES; i++) {
-		/* i == 1 means we are building port counters */
-		if (i && !per_port)
-			continue;
+		/*
+		 * i == 1 means we are building port counters, set a different
+		 * stats ops without port stats callback.
+		 */
+		if (i && !per_port) {
+			ib_set_device_ops(&ibdev->ib_dev,
+					  &mlx4_ib_hw_stats_ops1);
 
-		ret = __mlx4_ib_alloc_diag_counters(ibdev, &diag[i].name,
+			return 0;
+		}
+
+		ret = __mlx4_ib_alloc_diag_counters(ibdev, &diag[i].descs,
 						    &diag[i].offset,
 						    &diag[i].num_counters, i);
 		if (ret)
 			goto err_alloc;
 
-		mlx4_ib_fill_diag_counters(ibdev, diag[i].name,
+		mlx4_ib_fill_diag_counters(ibdev, diag[i].descs,
 					   diag[i].offset, i);
 	}
 
@@ -2249,7 +2253,7 @@ static int mlx4_ib_alloc_diag_counters(struct mlx4_ib_dev *ibdev)
 
 err_alloc:
 	if (i) {
-		kfree(diag[i - 1].name);
+		kfree(diag[i - 1].descs);
 		kfree(diag[i - 1].offset);
 	}
 
@@ -2262,7 +2266,7 @@ static void mlx4_ib_diag_cleanup(struct mlx4_ib_dev *ibdev)
 
 	for (i = 0; i < MLX4_DIAG_COUNTERS_TYPES; i++) {
 		kfree(ibdev->diag_counters[i].offset);
-		kfree(ibdev->diag_counters[i].name);
+		kfree(ibdev->diag_counters[i].descs);
 	}
 }
 
@@ -2275,7 +2279,7 @@ static void mlx4_ib_update_qps(struct mlx4_ib_dev *ibdev,
 	u64 release_mac = MLX4_IB_INVALID_MAC;
 	struct mlx4_ib_qp *qp;
 
-	new_smac = mlx4_mac_to_u64(dev->dev_addr);
+	new_smac = ether_addr_to_u64(dev->dev_addr);
 	atomic64_set(&ibdev->iboe.mac[port - 1], new_smac);
 
 	/* no need for update QP1 and mac registration in non-SRIOV */
@@ -2321,61 +2325,54 @@ unlock:
 	mutex_unlock(&ibdev->qp1_proxy_lock[port - 1]);
 }
 
-static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev,
-				 struct net_device *dev,
-				 unsigned long event)
+static void mlx4_ib_scan_netdev(struct mlx4_ib_dev *ibdev,
+				struct net_device *dev,
+				unsigned long event)
 
 {
-	struct mlx4_ib_iboe *iboe;
-	int update_qps_port = -1;
-	int port;
+	struct mlx4_ib_iboe *iboe = &ibdev->iboe;
 
 	ASSERT_RTNL();
 
-	iboe = &ibdev->iboe;
+	if (dev->dev.parent != ibdev->ib_dev.dev.parent)
+		return;
 
 	spin_lock_bh(&iboe->lock);
-	mlx4_foreach_ib_transport_port(port, ibdev->dev) {
 
-		iboe->netdevs[port - 1] =
-			mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port);
+	iboe->netdevs[dev->dev_port] = event != NETDEV_UNREGISTER ? dev : NULL;
 
-		if (dev == iboe->netdevs[port - 1] &&
-		    (event == NETDEV_CHANGEADDR || event == NETDEV_REGISTER ||
-		     event == NETDEV_UP || event == NETDEV_CHANGE))
-			update_qps_port = port;
+	spin_unlock_bh(&iboe->lock);
 
-		if (dev == iboe->netdevs[port - 1] &&
-		    (event == NETDEV_UP || event == NETDEV_DOWN)) {
-			enum ib_port_state port_state;
-			struct ib_event ibev = { };
+	if (event == NETDEV_CHANGEADDR || event == NETDEV_REGISTER)
+		mlx4_ib_update_qps(ibdev, dev, dev->dev_port + 1);
+}
 
-			if (ib_get_cached_port_state(&ibdev->ib_dev, port,
-						     &port_state))
-				continue;
+static void mlx4_ib_port_event(struct ib_device *ibdev, struct net_device *ndev,
+			       unsigned long event)
+{
+	struct mlx4_ib_dev *mlx4_ibdev =
+		container_of(ibdev, struct mlx4_ib_dev, ib_dev);
+	struct mlx4_ib_iboe *iboe = &mlx4_ibdev->iboe;
 
-			if (event == NETDEV_UP &&
-			    (port_state != IB_PORT_ACTIVE ||
-			     iboe->last_port_state[port - 1] != IB_PORT_DOWN))
-				continue;
-			if (event == NETDEV_DOWN &&
-			    (port_state != IB_PORT_DOWN ||
-			     iboe->last_port_state[port - 1] != IB_PORT_ACTIVE))
-				continue;
-			iboe->last_port_state[port - 1] = port_state;
+	if (!net_eq(dev_net(ndev), &init_net))
+		return;
 
-			ibev.device = &ibdev->ib_dev;
-			ibev.element.port_num = port;
-			ibev.event = event == NETDEV_UP ? IB_EVENT_PORT_ACTIVE :
-							  IB_EVENT_PORT_ERR;
-			ib_dispatch_event(&ibev);
-		}
+	ASSERT_RTNL();
+
+	if (ndev->dev.parent != mlx4_ibdev->ib_dev.dev.parent)
+		return;
+
+	spin_lock_bh(&iboe->lock);
+
+	iboe->netdevs[ndev->dev_port] = event != NETDEV_UNREGISTER ? ndev : NULL;
+
+	if (event == NETDEV_UP || event == NETDEV_DOWN)
+		ib_dispatch_port_state_event(&mlx4_ibdev->ib_dev, ndev);
 
-	}
 	spin_unlock_bh(&iboe->lock);
 
-	if (update_qps_port > 0)
-		mlx4_ib_update_qps(ibdev, dev, update_qps_port);
+	if (event == NETDEV_UP || event == NETDEV_CHANGE)
+		mlx4_ib_update_qps(mlx4_ibdev, ndev, ndev->dev_port + 1);
 }
 
 static int mlx4_ib_netdev_event(struct notifier_block *this,
@@ -2388,7 +2385,7 @@ static int mlx4_ib_netdev_event(struct notifier_block *this,
 		return NOTIFY_DONE;
 
 	ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb);
-	mlx4_ib_scan_netdevs(ibdev, dev, event);
+	mlx4_ib_scan_netdev(ibdev, dev, event);
 
 	return NOTIFY_DONE;
 }
@@ -2573,10 +2570,12 @@ static const struct ib_device_ops mlx4_ib_dev_ops = {
 	.req_notify_cq = mlx4_ib_arm_cq,
 	.rereg_user_mr = mlx4_ib_rereg_user_mr,
 	.resize_cq = mlx4_ib_resize_cq,
+	.report_port_event = mlx4_ib_port_event,
 
 	INIT_RDMA_OBJ_SIZE(ib_ah, mlx4_ib_ah, ibah),
 	INIT_RDMA_OBJ_SIZE(ib_cq, mlx4_ib_cq, ibcq),
 	INIT_RDMA_OBJ_SIZE(ib_pd, mlx4_ib_pd, ibpd),
+	INIT_RDMA_OBJ_SIZE(ib_qp, mlx4_ib_qp, ibqp),
 	INIT_RDMA_OBJ_SIZE(ib_srq, mlx4_ib_srq, ibsrq),
 	INIT_RDMA_OBJ_SIZE(ib_ucontext, mlx4_ib_ucontext, ibucontext),
 };
@@ -2611,8 +2610,11 @@ static const struct ib_device_ops mlx4_ib_dev_fs_ops = {
 	.destroy_flow = mlx4_ib_destroy_flow,
 };
 
-static void *mlx4_ib_add(struct mlx4_dev *dev)
+static int mlx4_ib_probe(struct auxiliary_device *adev,
+			 const struct auxiliary_device_id *id)
 {
+	struct mlx4_adev *madev = container_of(adev, struct mlx4_adev, adev);
+	struct mlx4_dev *dev = madev->mdev;
 	struct mlx4_ib_dev *ibdev;
 	int num_ports = 0;
 	int i, j;
@@ -2622,7 +2624,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	int num_req_counters;
 	int allocated;
 	u32 counter_index;
-	struct counter_index *new_counter_index = NULL;
+	struct counter_index *new_counter_index;
 
 	pr_info_once("%s", mlx4_ib_version);
 
@@ -2632,27 +2634,31 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 
 	/* No point in registering a device with no ports... */
 	if (num_ports == 0)
-		return NULL;
+		return -ENODEV;
 
 	ibdev = ib_alloc_device(mlx4_ib_dev, ib_dev);
 	if (!ibdev) {
 		dev_err(&dev->persist->pdev->dev,
 			"Device struct alloc failed\n");
-		return NULL;
+		return -ENOMEM;
 	}
 
 	iboe = &ibdev->iboe;
 
-	if (mlx4_pd_alloc(dev, &ibdev->priv_pdn))
+	err = mlx4_pd_alloc(dev, &ibdev->priv_pdn);
+	if (err)
 		goto err_dealloc;
 
-	if (mlx4_uar_alloc(dev, &ibdev->priv_uar))
+	err = mlx4_uar_alloc(dev, &ibdev->priv_uar);
+	if (err)
 		goto err_pd;
 
 	ibdev->uar_map = ioremap((phys_addr_t) ibdev->priv_uar.pfn << PAGE_SHIFT,
 				 PAGE_SIZE);
-	if (!ibdev->uar_map)
+	if (!ibdev->uar_map) {
+		err = -ENOMEM;
 		goto err_uar;
+	}
 	MLX4_INIT_DOORBELL_LOCK(&ibdev->uar_lock);
 
 	ibdev->dev = dev;
@@ -2696,7 +2702,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 
 	spin_lock_init(&iboe->lock);
 
-	if (init_node_data(ibdev))
+	err = init_node_data(ibdev);
+	if (err)
 		goto err_map;
 	mlx4_init_sl2vl_tbl(ibdev);
 
@@ -2728,6 +2735,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 		new_counter_index = kmalloc(sizeof(*new_counter_index),
 					    GFP_KERNEL);
 		if (!new_counter_index) {
+			err = -ENOMEM;
 			if (allocated)
 				mlx4_counter_free(ibdev->dev, counter_index);
 			goto err_counter;
@@ -2745,8 +2753,10 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 			new_counter_index =
 					kmalloc(sizeof(struct counter_index),
 						GFP_KERNEL);
-			if (!new_counter_index)
+			if (!new_counter_index) {
+				err = -ENOMEM;
 				goto err_counter;
+			}
 			new_counter_index->index = counter_index;
 			new_counter_index->allocated = 0;
 			list_add_tail(&new_counter_index->list,
@@ -2773,12 +2783,12 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 		if (err)
 			goto err_counter;
 
-		ibdev->ib_uc_qpns_bitmap =
-			kmalloc_array(BITS_TO_LONGS(ibdev->steer_qpn_count),
-				      sizeof(long),
-				      GFP_KERNEL);
-		if (!ibdev->ib_uc_qpns_bitmap)
+		ibdev->ib_uc_qpns_bitmap = bitmap_alloc(ibdev->steer_qpn_count,
+							GFP_KERNEL);
+		if (!ibdev->ib_uc_qpns_bitmap) {
+			err = -ENOMEM;
 			goto err_steer_qp_release;
+		}
 
 		if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DMFS_IPOIB) {
 			bitmap_zero(ibdev->ib_uc_qpns_bitmap,
@@ -2798,17 +2808,21 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	for (j = 1; j <= ibdev->dev->caps.num_ports; j++)
 		atomic64_set(&iboe->mac[j - 1], ibdev->dev->caps.def_mac[j]);
 
-	if (mlx4_ib_alloc_diag_counters(ibdev))
+	err = mlx4_ib_alloc_diag_counters(ibdev);
+	if (err)
 		goto err_steer_free_bitmap;
 
-	if (ib_register_device(&ibdev->ib_dev, "mlx4_%d",
-			       &dev->persist->pdev->dev))
+	err = ib_register_device(&ibdev->ib_dev, "mlx4_%d",
+				 &dev->persist->pdev->dev);
+	if (err)
 		goto err_diag_counters;
 
-	if (mlx4_ib_mad_init(ibdev))
+	err = mlx4_ib_mad_init(ibdev);
+	if (err)
 		goto err_reg;
 
-	if (mlx4_ib_init_sriov(ibdev))
+	err = mlx4_ib_init_sriov(ibdev);
+	if (err)
 		goto err_mad;
 
 	if (!iboe->nb.notifier_call) {
@@ -2842,7 +2856,14 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 				do_slave_init(ibdev, j, 1);
 		}
 	}
-	return ibdev;
+
+	/* register mlx4 core notifier */
+	ibdev->mlx_nb.notifier_call = mlx4_ib_event;
+	err = mlx4_register_event_notifier(dev, &ibdev->mlx_nb);
+	WARN(err, "failed to register mlx4 event notifier (%d)", err);
+
+	auxiliary_set_drvdata(adev, ibdev);
+	return 0;
 
 err_notif:
 	if (ibdev->iboe.nb.notifier_call) {
@@ -2864,7 +2885,7 @@ err_diag_counters:
 	mlx4_ib_diag_cleanup(ibdev);
 
 err_steer_free_bitmap:
-	kfree(ibdev->ib_uc_qpns_bitmap);
+	bitmap_free(ibdev->ib_uc_qpns_bitmap);
 
 err_steer_qp_release:
 	mlx4_qp_release_range(dev, ibdev->steer_qpn_base,
@@ -2886,7 +2907,7 @@ err_pd:
 err_dealloc:
 	ib_dealloc_device(&ibdev->ib_dev);
 
-	return NULL;
+	return err;
 }
 
 int mlx4_ib_steer_qp_alloc(struct mlx4_ib_dev *dev, int count, int *qpn)
@@ -2926,7 +2947,7 @@ int mlx4_ib_steer_qp_reg(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
 {
 	int err;
 	size_t flow_size;
-	struct ib_flow_attr *flow = NULL;
+	struct ib_flow_attr *flow;
 	struct ib_flow_spec_ib *ib_spec;
 
 	if (is_attach) {
@@ -2946,19 +2967,23 @@ int mlx4_ib_steer_qp_reg(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
 
 		err = __mlx4_ib_create_flow(&mqp->ibqp, flow, MLX4_DOMAIN_NIC,
 					    MLX4_FS_REGULAR, &mqp->reg_id);
-	} else {
-		err = __mlx4_ib_destroy_flow(mdev->dev, mqp->reg_id);
+		kfree(flow);
+		return err;
 	}
-	kfree(flow);
-	return err;
+	
+	return __mlx4_ib_destroy_flow(mdev->dev, mqp->reg_id);
 }
 
-static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
+static void mlx4_ib_remove(struct auxiliary_device *adev)
 {
-	struct mlx4_ib_dev *ibdev = ibdev_ptr;
+	struct mlx4_adev *madev = container_of(adev, struct mlx4_adev, adev);
+	struct mlx4_dev *dev = madev->mdev;
+	struct mlx4_ib_dev *ibdev = auxiliary_get_drvdata(adev);
 	int p;
 	int i;
 
+	mlx4_unregister_event_notifier(dev, &ibdev->mlx_nb);
+
 	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
 		devlink_port_type_clear(mlx4_get_devlink_port(dev, i));
 	ibdev->ib_active = false;
@@ -2977,7 +3002,7 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
 
 	mlx4_qp_release_range(dev, ibdev->steer_qpn_base,
 			      ibdev->steer_qpn_count);
-	kfree(ibdev->ib_uc_qpns_bitmap);
+	bitmap_free(ibdev->ib_uc_qpns_bitmap);
 
 	iounmap(ibdev->uar_map);
 	for (p = 0; p < ibdev->num_ports; ++p)
@@ -2995,7 +3020,7 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
 
 static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init)
 {
-	struct mlx4_ib_demux_work **dm = NULL;
+	struct mlx4_ib_demux_work **dm;
 	struct mlx4_dev *dev = ibdev->dev;
 	int i;
 	unsigned long flags;
@@ -3179,11 +3204,13 @@ void mlx4_sched_ib_sl2vl_update_work(struct mlx4_ib_dev *ibdev,
 	}
 }
 
-static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
-			  enum mlx4_dev_event event, unsigned long param)
+static int mlx4_ib_event(struct notifier_block *this, unsigned long event,
+			 void *param)
 {
+	struct mlx4_ib_dev *ibdev =
+		container_of(this, struct mlx4_ib_dev, mlx_nb);
+	struct mlx4_dev *dev = ibdev->dev;
 	struct ib_event ibev;
-	struct mlx4_ib_dev *ibdev = to_mdev((struct ib_device *) ibdev_ptr);
 	struct mlx4_eqe *eqe = NULL;
 	struct ib_event_work *ew;
 	int p = 0;
@@ -3193,22 +3220,28 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 	    (event == MLX4_DEV_EVENT_PORT_DOWN))) {
 		ew = kmalloc(sizeof(*ew), GFP_ATOMIC);
 		if (!ew)
-			return;
+			return NOTIFY_DONE;
 		INIT_WORK(&ew->work, handle_bonded_port_state_event);
 		ew->ib_dev = ibdev;
 		queue_work(wq, &ew->work);
-		return;
+		return NOTIFY_DONE;
 	}
 
-	if (event == MLX4_DEV_EVENT_PORT_MGMT_CHANGE)
+	switch (event) {
+	case MLX4_DEV_EVENT_CATASTROPHIC_ERROR:
+		break;
+	case MLX4_DEV_EVENT_PORT_MGMT_CHANGE:
 		eqe = (struct mlx4_eqe *)param;
-	else
-		p = (int) param;
+		break;
+	default:
+		p = *(int *)param;
+		break;
+	}
 
 	switch (event) {
 	case MLX4_DEV_EVENT_PORT_UP:
 		if (p > ibdev->num_ports)
-			return;
+			return NOTIFY_DONE;
 		if (!mlx4_is_slave(dev) &&
 		    rdma_port_get_link_layer(&ibdev->ib_dev, p) ==
 			IB_LINK_LAYER_INFINIBAND) {
@@ -3223,7 +3256,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 
 	case MLX4_DEV_EVENT_PORT_DOWN:
 		if (p > ibdev->num_ports)
-			return;
+			return NOTIFY_DONE;
 		ibev.event = IB_EVENT_PORT_ERR;
 		break;
 
@@ -3236,7 +3269,7 @@ 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)
-			break;
+			return NOTIFY_DONE;
 
 		INIT_WORK(&ew->work, handle_port_mgmt_change_event);
 		memcpy(&ew->ib_eqe, eqe, sizeof *eqe);
@@ -3246,7 +3279,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 			queue_work(wq, &ew->work);
 		else
 			handle_port_mgmt_change_event(&ew->work);
-		return;
+		return NOTIFY_DONE;
 
 	case MLX4_DEV_EVENT_SLAVE_INIT:
 		/* here, p is the slave id */
@@ -3262,7 +3295,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 								       1);
 			}
 		}
-		return;
+		return NOTIFY_DONE;
 
 	case MLX4_DEV_EVENT_SLAVE_SHUTDOWN:
 		if (mlx4_is_master(dev)) {
@@ -3278,22 +3311,33 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 		}
 		/* here, p is the slave id */
 		do_slave_init(ibdev, p, 0);
-		return;
+		return NOTIFY_DONE;
 
 	default:
-		return;
+		return NOTIFY_DONE;
 	}
 
-	ibev.device	      = ibdev_ptr;
+	ibev.device	      = &ibdev->ib_dev;
 	ibev.element.port_num = mlx4_is_bonded(ibdev->dev) ? 1 : (u8)p;
 
 	ib_dispatch_event(&ibev);
+	return NOTIFY_DONE;
 }
 
-static struct mlx4_interface mlx4_ib_interface = {
-	.add		= mlx4_ib_add,
-	.remove		= mlx4_ib_remove,
-	.event		= mlx4_ib_event,
+static const struct auxiliary_device_id mlx4_ib_id_table[] = {
+	{ .name = MLX4_ADEV_NAME ".ib" },
+	{},
+};
+
+MODULE_DEVICE_TABLE(auxiliary, mlx4_ib_id_table);
+
+static struct mlx4_adrv mlx4_ib_adrv = {
+	.adrv = {
+		.name	= "ib",
+		.probe	= mlx4_ib_probe,
+		.remove	= mlx4_ib_remove,
+		.id_table = mlx4_ib_id_table,
+	},
 	.protocol	= MLX4_PROT_IB_IPV6,
 	.flags		= MLX4_INTFF_BONDING
 };
@@ -3306,11 +3350,19 @@ static int __init mlx4_ib_init(void)
 	if (!wq)
 		return -ENOMEM;
 
-	err = mlx4_ib_mcg_init();
+	err = mlx4_ib_qp_event_init();
+	if (err)
+		goto clean_qp_event;
+
+	err = mlx4_ib_cm_init();
 	if (err)
 		goto clean_wq;
 
-	err = mlx4_register_interface(&mlx4_ib_interface);
+	err = mlx4_ib_mcg_init();
+	if (err)
+		goto clean_cm;
+
+	err = mlx4_register_auxiliary_driver(&mlx4_ib_adrv);
 	if (err)
 		goto clean_mcg;
 
@@ -3319,15 +3371,23 @@ static int __init mlx4_ib_init(void)
 clean_mcg:
 	mlx4_ib_mcg_destroy();
 
+clean_cm:
+	mlx4_ib_cm_destroy();
+
 clean_wq:
+	mlx4_ib_qp_event_cleanup();
+
+clean_qp_event:
 	destroy_workqueue(wq);
 	return err;
 }
 
 static void __exit mlx4_ib_cleanup(void)
 {
-	mlx4_unregister_interface(&mlx4_ib_interface);
+	mlx4_unregister_auxiliary_driver(&mlx4_ib_adrv);
 	mlx4_ib_mcg_destroy();
+	mlx4_ib_cm_destroy();
+	mlx4_ib_qp_event_cleanup();
 	destroy_workqueue(wq);
 }