Merge branch 'for-4.3-rc/ti-clk-fixes' of https://github.com/t-kristo/linux-pm into clk-fixes

Pull fixes from Tero Kristo:

"A few TI clock driver fixes to pull against 4.3-rc"

* 'for-4.3-rc/ti-clk-fixes' of https://github.com/t-kristo/linux-pm: (3 commits)
  clk: ti: dflt: fix enable_reg validity check
  clk: ti: fix dual-registration of uart4_ick
  clk: ti: clk-7xx: Remove hardwired ABE clock configuration

9 files changed, 514 insertions, 560 deletions

diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c
index f50a546224ad..1688a17de4fe 100644
--- a/drivers/infiniband/hw/mlx4/ah.c
+++ b/drivers/infiniband/hw/mlx4/ah.c
@@ -89,7 +89,7 @@ static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr
 	if (vlan_tag < 0x1000)
 		vlan_tag |= (ah_attr->sl & 7) << 13;
 	ah->av.eth.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24));
-	ah->av.eth.gid_index = ah_attr->grh.sgid_index;
+	ah->av.eth.gid_index = mlx4_ib_gid_index_to_real_index(ibdev, ah_attr->port_num, ah_attr->grh.sgid_index);
 	ah->av.eth.vlan = cpu_to_be16(vlan_tag);
 	if (ah_attr->static_rate) {
 		ah->av.eth.stat_rate = ah_attr->static_rate + MLX4_STAT_RATE_OFFSET;
@@ -148,9 +148,13 @@ int mlx4_ib_query_ah(struct ib_ah *ibah, struct ib_ah_attr *ah_attr)
 	enum rdma_link_layer ll;
 
 	memset(ah_attr, 0, sizeof *ah_attr);
-	ah_attr->sl = be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 28;
 	ah_attr->port_num = be32_to_cpu(ah->av.ib.port_pd) >> 24;
 	ll = rdma_port_get_link_layer(ibah->device, ah_attr->port_num);
+	if (ll == IB_LINK_LAYER_ETHERNET)
+		ah_attr->sl = be32_to_cpu(ah->av.eth.sl_tclass_flowlabel) >> 29;
+	else
+		ah_attr->sl = be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 28;
+
 	ah_attr->dlid = ll == IB_LINK_LAYER_INFINIBAND ? be16_to_cpu(ah->av.ib.dlid) : 0;
 	if (ah->av.ib.stat_rate)
 		ah_attr->static_rate = ah->av.ib.stat_rate - MLX4_STAT_RATE_OFFSET;
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index 36eb3d012b6d..5fd49f9435f9 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -638,7 +638,7 @@ static void mlx4_ib_poll_sw_comp(struct mlx4_ib_cq *cq, int num_entries,
 	 * simulated FLUSH_ERR completions
 	 */
 	list_for_each_entry(qp, &cq->send_qp_list, cq_send_list) {
-		mlx4_ib_qp_sw_comp(qp, num_entries, wc, npolled, 1);
+		mlx4_ib_qp_sw_comp(qp, num_entries, wc + *npolled, npolled, 1);
 		if (*npolled >= num_entries)
 			goto out;
 	}
@@ -871,7 +871,7 @@ repoll:
 		if (is_eth) {
 			wc->sl  = be16_to_cpu(cqe->sl_vid) >> 13;
 			if (be32_to_cpu(cqe->vlan_my_qpn) &
-					MLX4_CQE_VLAN_PRESENT_MASK) {
+					MLX4_CQE_CVLAN_PRESENT_MASK) {
 				wc->vlan_id = be16_to_cpu(cqe->sl_vid) &
 					MLX4_CQE_VID_MASK;
 			} else {
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 85a50df2f203..1cd75ff02251 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -580,7 +580,7 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
 
 	list.addr = tun_qp->tx_ring[tun_tx_ix].buf.map;
 	list.length = sizeof (struct mlx4_rcv_tunnel_mad);
-	list.lkey = tun_ctx->mr->lkey;
+	list.lkey = tun_ctx->pd->local_dma_lkey;
 
 	wr.wr.ud.ah = ah;
 	wr.wr.ud.port_num = port;
@@ -860,21 +860,31 @@ int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	struct mlx4_ib_dev *dev = to_mdev(ibdev);
 	const struct ib_mad *in_mad = (const struct ib_mad *)in;
 	struct ib_mad *out_mad = (struct ib_mad *)out;
+	enum rdma_link_layer link = rdma_port_get_link_layer(ibdev, port_num);
 
-	BUG_ON(in_mad_size != sizeof(*in_mad) ||
-	       *out_mad_size != sizeof(*out_mad));
+	if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) ||
+			 *out_mad_size != sizeof(*out_mad)))
+		return IB_MAD_RESULT_FAILURE;
 
-	switch (rdma_port_get_link_layer(ibdev, port_num)) {
-	case IB_LINK_LAYER_INFINIBAND:
-		if (!mlx4_is_slave(dev->dev))
-			return ib_process_mad(ibdev, mad_flags, port_num, in_wc,
-					      in_grh, in_mad, out_mad);
-	case IB_LINK_LAYER_ETHERNET:
-		return iboe_process_mad(ibdev, mad_flags, port_num, in_wc,
-					  in_grh, in_mad, out_mad);
-	default:
-		return -EINVAL;
+	/* iboe_process_mad() which uses the HCA flow-counters to implement IB PMA
+	 * queries, should be called only by VFs and for that specific purpose
+	 */
+	if (link == IB_LINK_LAYER_INFINIBAND) {
+		if (mlx4_is_slave(dev->dev) &&
+		    in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT &&
+		    in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS)
+			return iboe_process_mad(ibdev, mad_flags, port_num, in_wc,
+						in_grh, in_mad, out_mad);
+
+		return ib_process_mad(ibdev, mad_flags, port_num, in_wc,
+				      in_grh, in_mad, out_mad);
 	}
+
+	if (link == IB_LINK_LAYER_ETHERNET)
+		return iboe_process_mad(ibdev, mad_flags, port_num, in_wc,
+					in_grh, in_mad, out_mad);
+
+	return -EINVAL;
 }
 
 static void send_handler(struct ib_mad_agent *agent,
@@ -1123,7 +1133,7 @@ static int mlx4_ib_post_pv_qp_buf(struct mlx4_ib_demux_pv_ctx *ctx,
 
 	sg_list.addr = tun_qp->ring[index].map;
 	sg_list.length = size;
-	sg_list.lkey = ctx->mr->lkey;
+	sg_list.lkey = ctx->pd->local_dma_lkey;
 
 	recv_wr.next = NULL;
 	recv_wr.sg_list = &sg_list;
@@ -1234,7 +1244,7 @@ int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port,
 
 	list.addr = sqp->tx_ring[wire_tx_ix].buf.map;
 	list.length = sizeof (struct mlx4_mad_snd_buf);
-	list.lkey = sqp_ctx->mr->lkey;
+	list.lkey = sqp_ctx->pd->local_dma_lkey;
 
 	wr.wr.ud.ah = ah;
 	wr.wr.ud.port_num = port;
@@ -1817,19 +1827,12 @@ static int create_pv_resources(struct ib_device *ibdev, int slave, int port,
 		goto err_cq;
 	}
 
-	ctx->mr = ib_get_dma_mr(ctx->pd, IB_ACCESS_LOCAL_WRITE);
-	if (IS_ERR(ctx->mr)) {
-		ret = PTR_ERR(ctx->mr);
-		pr_err("Couldn't get tunnel DMA MR (%d)\n", ret);
-		goto err_pd;
-	}
-
 	if (ctx->has_smi) {
 		ret = create_pv_sqp(ctx, IB_QPT_SMI, create_tun);
 		if (ret) {
 			pr_err("Couldn't create %s QP0 (%d)\n",
 			       create_tun ? "tunnel for" : "",  ret);
-			goto err_mr;
+			goto err_pd;
 		}
 	}
 
@@ -1866,10 +1869,6 @@ err_qp0:
 		ib_destroy_qp(ctx->qp[0].qp);
 	ctx->qp[0].qp = NULL;
 
-err_mr:
-	ib_dereg_mr(ctx->mr);
-	ctx->mr = NULL;
-
 err_pd:
 	ib_dealloc_pd(ctx->pd);
 	ctx->pd = NULL;
@@ -1906,8 +1905,6 @@ static void destroy_pv_resources(struct mlx4_ib_dev *dev, int slave, int port,
 		ib_destroy_qp(ctx->qp[1].qp);
 		ctx->qp[1].qp = NULL;
 		mlx4_ib_free_pv_qp_bufs(ctx, IB_QPT_GSI, 1);
-		ib_dereg_mr(ctx->mr);
-		ctx->mr = NULL;
 		ib_dealloc_pd(ctx->pd);
 		ctx->pd = NULL;
 		ib_destroy_cq(ctx->cq);
@@ -2040,8 +2037,6 @@ static void mlx4_ib_free_sqp_ctx(struct mlx4_ib_demux_pv_ctx *sqp_ctx)
 		ib_destroy_qp(sqp_ctx->qp[1].qp);
 		sqp_ctx->qp[1].qp = NULL;
 		mlx4_ib_free_pv_qp_bufs(sqp_ctx, IB_QPT_GSI, 0);
-		ib_dereg_mr(sqp_ctx->mr);
-		sqp_ctx->mr = NULL;
 		ib_dealloc_pd(sqp_ctx->pd);
 		sqp_ctx->pd = NULL;
 		ib_destroy_cq(sqp_ctx->cq);
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 067a691ecbed..efecdf0216d8 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -45,6 +45,9 @@
 #include <rdma/ib_smi.h>
 #include <rdma/ib_user_verbs.h>
 #include <rdma/ib_addr.h>
+#include <rdma/ib_cache.h>
+
+#include <net/bonding.h>
 
 #include <linux/mlx4/driver.h>
 #include <linux/mlx4/cmd.h>
@@ -74,13 +77,6 @@ static const char mlx4_ib_version[] =
 	DRV_NAME ": Mellanox ConnectX InfiniBand driver v"
 	DRV_VERSION " (" DRV_RELDATE ")\n";
 
-struct update_gid_work {
-	struct work_struct	work;
-	union ib_gid		gids[128];
-	struct mlx4_ib_dev     *dev;
-	int			port;
-};
-
 static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init);
 
 static struct workqueue_struct *wq;
@@ -93,8 +89,6 @@ static void init_query_mad(struct ib_smp *mad)
 	mad->method	   = IB_MGMT_METHOD_GET;
 }
 
-static union ib_gid zgid;
-
 static int check_flow_steering_support(struct mlx4_dev *dev)
 {
 	int eth_num_ports = 0;
@@ -131,6 +125,237 @@ static int num_ib_ports(struct mlx4_dev *dev)
 	return ib_ports;
 }
 
+static struct net_device *mlx4_ib_get_netdev(struct ib_device *device, u8 port_num)
+{
+	struct mlx4_ib_dev *ibdev = to_mdev(device);
+	struct net_device *dev;
+
+	rcu_read_lock();
+	dev = mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port_num);
+
+	if (dev) {
+		if (mlx4_is_bonded(ibdev->dev)) {
+			struct net_device *upper = NULL;
+
+			upper = netdev_master_upper_dev_get_rcu(dev);
+			if (upper) {
+				struct net_device *active;
+
+				active = bond_option_active_slave_get_rcu(netdev_priv(upper));
+				if (active)
+					dev = active;
+			}
+		}
+	}
+	if (dev)
+		dev_hold(dev);
+
+	rcu_read_unlock();
+	return dev;
+}
+
+static int mlx4_ib_update_gids(struct gid_entry *gids,
+			       struct mlx4_ib_dev *ibdev,
+			       u8 port_num)
+{
+	struct mlx4_cmd_mailbox *mailbox;
+	int err;
+	struct mlx4_dev *dev = ibdev->dev;
+	int i;
+	union ib_gid *gid_tbl;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return -ENOMEM;
+
+	gid_tbl = mailbox->buf;
+
+	for (i = 0; i < MLX4_MAX_PORT_GIDS; ++i)
+		memcpy(&gid_tbl[i], &gids[i].gid, sizeof(union ib_gid));
+
+	err = mlx4_cmd(dev, mailbox->dma,
+		       MLX4_SET_PORT_GID_TABLE << 8 | port_num,
+		       1, MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B,
+		       MLX4_CMD_WRAPPED);
+	if (mlx4_is_bonded(dev))
+		err += mlx4_cmd(dev, mailbox->dma,
+				MLX4_SET_PORT_GID_TABLE << 8 | 2,
+				1, MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B,
+				MLX4_CMD_WRAPPED);
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return err;
+}
+
+static int mlx4_ib_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)
+{
+	struct mlx4_ib_dev *ibdev = to_mdev(device);
+	struct mlx4_ib_iboe *iboe = &ibdev->iboe;
+	struct mlx4_port_gid_table   *port_gid_table;
+	int free = -1, found = -1;
+	int ret = 0;
+	int hw_update = 0;
+	int i;
+	struct gid_entry *gids = NULL;
+
+	if (!rdma_cap_roce_gid_table(device, port_num))
+		return -EINVAL;
+
+	if (port_num > MLX4_MAX_PORTS)
+		return -EINVAL;
+
+	if (!context)
+		return -EINVAL;
+
+	port_gid_table = &iboe->gids[port_num - 1];
+	spin_lock_bh(&iboe->lock);
+	for (i = 0; i < MLX4_MAX_PORT_GIDS; ++i) {
+		if (!memcmp(&port_gid_table->gids[i].gid, gid, sizeof(*gid))) {
+			found = i;
+			break;
+		}
+		if (free < 0 && !memcmp(&port_gid_table->gids[i].gid, &zgid, sizeof(*gid)))
+			free = i; /* HW has space */
+	}
+
+	if (found < 0) {
+		if (free < 0) {
+			ret = -ENOSPC;
+		} else {
+			port_gid_table->gids[free].ctx = kmalloc(sizeof(*port_gid_table->gids[free].ctx), GFP_ATOMIC);
+			if (!port_gid_table->gids[free].ctx) {
+				ret = -ENOMEM;
+			} else {
+				*context = port_gid_table->gids[free].ctx;
+				memcpy(&port_gid_table->gids[free].gid, gid, sizeof(*gid));
+				port_gid_table->gids[free].ctx->real_index = free;
+				port_gid_table->gids[free].ctx->refcount = 1;
+				hw_update = 1;
+			}
+		}
+	} else {
+		struct gid_cache_context *ctx = port_gid_table->gids[found].ctx;
+		*context = ctx;
+		ctx->refcount++;
+	}
+	if (!ret && hw_update) {
+		gids = kmalloc(sizeof(*gids) * MLX4_MAX_PORT_GIDS, GFP_ATOMIC);
+		if (!gids) {
+			ret = -ENOMEM;
+		} else {
+			for (i = 0; i < MLX4_MAX_PORT_GIDS; i++)
+				memcpy(&gids[i].gid, &port_gid_table->gids[i].gid, sizeof(union ib_gid));
+		}
+	}
+	spin_unlock_bh(&iboe->lock);
+
+	if (!ret && hw_update) {
+		ret = mlx4_ib_update_gids(gids, ibdev, port_num);
+		kfree(gids);
+	}
+
+	return ret;
+}
+
+static int mlx4_ib_del_gid(struct ib_device *device,
+			   u8 port_num,
+			   unsigned int index,
+			   void **context)
+{
+	struct gid_cache_context *ctx = *context;
+	struct mlx4_ib_dev *ibdev = to_mdev(device);
+	struct mlx4_ib_iboe *iboe = &ibdev->iboe;
+	struct mlx4_port_gid_table   *port_gid_table;
+	int ret = 0;
+	int hw_update = 0;
+	struct gid_entry *gids = NULL;
+
+	if (!rdma_cap_roce_gid_table(device, port_num))
+		return -EINVAL;
+
+	if (port_num > MLX4_MAX_PORTS)
+		return -EINVAL;
+
+	port_gid_table = &iboe->gids[port_num - 1];
+	spin_lock_bh(&iboe->lock);
+	if (ctx) {
+		ctx->refcount--;
+		if (!ctx->refcount) {
+			unsigned int real_index = ctx->real_index;
+
+			memcpy(&port_gid_table->gids[real_index].gid, &zgid, sizeof(zgid));
+			kfree(port_gid_table->gids[real_index].ctx);
+			port_gid_table->gids[real_index].ctx = NULL;
+			hw_update = 1;
+		}
+	}
+	if (!ret && hw_update) {
+		int i;
+
+		gids = kmalloc(sizeof(*gids) * MLX4_MAX_PORT_GIDS, GFP_ATOMIC);
+		if (!gids) {
+			ret = -ENOMEM;
+		} else {
+			for (i = 0; i < MLX4_MAX_PORT_GIDS; i++)
+				memcpy(&gids[i].gid, &port_gid_table->gids[i].gid, sizeof(union ib_gid));
+		}
+	}
+	spin_unlock_bh(&iboe->lock);
+
+	if (!ret && hw_update) {
+		ret = mlx4_ib_update_gids(gids, ibdev, port_num);
+		kfree(gids);
+	}
+	return ret;
+}
+
+int mlx4_ib_gid_index_to_real_index(struct mlx4_ib_dev *ibdev,
+				    u8 port_num, int index)
+{
+	struct mlx4_ib_iboe *iboe = &ibdev->iboe;
+	struct gid_cache_context *ctx = NULL;
+	union ib_gid gid;
+	struct mlx4_port_gid_table   *port_gid_table;
+	int real_index = -EINVAL;
+	int i;
+	int ret;
+	unsigned long flags;
+
+	if (port_num > MLX4_MAX_PORTS)
+		return -EINVAL;
+
+	if (mlx4_is_bonded(ibdev->dev))
+		port_num = 1;
+
+	if (!rdma_cap_roce_gid_table(&ibdev->ib_dev, port_num))
+		return index;
+
+	ret = ib_get_cached_gid(&ibdev->ib_dev, port_num, index, &gid);
+	if (ret)
+		return ret;
+
+	if (!memcmp(&gid, &zgid, sizeof(gid)))
+		return -EINVAL;
+
+	spin_lock_irqsave(&iboe->lock, flags);
+	port_gid_table = &iboe->gids[port_num - 1];
+
+	for (i = 0; i < MLX4_MAX_PORT_GIDS; ++i)
+		if (!memcmp(&port_gid_table->gids[i].gid, &gid, sizeof(gid))) {
+			ctx = port_gid_table->gids[i].ctx;
+			break;
+		}
+	if (ctx)
+		real_index = ctx->real_index;
+	spin_unlock_irqrestore(&iboe->lock, flags);
+	return real_index;
+}
+
 static int mlx4_ib_query_device(struct ib_device *ibdev,
 				struct ib_device_attr *props,
 				struct ib_udata *uhw)
@@ -229,6 +454,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 	props->max_qp_wr	   = dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE;
 	props->max_sge		   = min(dev->dev->caps.max_sq_sg,
 					 dev->dev->caps.max_rq_sg);
+	props->max_sge_rd = props->max_sge;
 	props->max_cq		   = dev->dev->quotas.cq;
 	props->max_cqe		   = dev->dev->caps.max_cqes;
 	props->max_mr		   = dev->dev->quotas.mpt;
@@ -253,14 +479,15 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 	props->hca_core_clock = dev->dev->caps.hca_core_clock * 1000UL;
 	props->timestamp_mask = 0xFFFFFFFFFFFFULL;
 
-	err = mlx4_get_internal_clock_params(dev->dev, &clock_params);
-	if (err)
-		goto out;
+	if (!mlx4_is_slave(dev->dev))
+		err = mlx4_get_internal_clock_params(dev->dev, &clock_params);
 
 	if (uhw->outlen >= resp.response_length + sizeof(resp.hca_core_clock_offset)) {
-		resp.hca_core_clock_offset = clock_params.offset % PAGE_SIZE;
 		resp.response_length += sizeof(resp.hca_core_clock_offset);
-		resp.comp_mask |= QUERY_DEVICE_RESP_MASK_TIMESTAMP;
+		if (!err && !mlx4_is_slave(dev->dev)) {
+			resp.comp_mask |= QUERY_DEVICE_RESP_MASK_TIMESTAMP;
+			resp.hca_core_clock_offset = clock_params.offset % PAGE_SIZE;
+		}
 	}
 
 	if (uhw->outlen) {
@@ -413,12 +640,13 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port,
 	props->state		= IB_PORT_DOWN;
 	props->phys_state	= state_to_phys_state(props->state);
 	props->active_mtu	= IB_MTU_256;
-	if (is_bonded)
-		rtnl_lock(); /* required to get upper dev */
 	spin_lock_bh(&iboe->lock);
 	ndev = iboe->netdevs[port - 1];
-	if (ndev && is_bonded)
-		ndev = netdev_master_upper_dev_get(ndev);
+	if (ndev && is_bonded) {
+		rcu_read_lock(); /* required to get upper dev */
+		ndev = netdev_master_upper_dev_get_rcu(ndev);
+		rcu_read_unlock();
+	}
 	if (!ndev)
 		goto out_unlock;
 
@@ -430,8 +658,6 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port,
 	props->phys_state	= state_to_phys_state(props->state);
 out_unlock:
 	spin_unlock_bh(&iboe->lock);
-	if (is_bonded)
-		rtnl_unlock();
 out:
 	mlx4_free_cmd_mailbox(mdev->dev, mailbox);
 	return err;
@@ -514,23 +740,27 @@ out:
 	return err;
 }
 
-static int iboe_query_gid(struct ib_device *ibdev, u8 port, int index,
-			  union ib_gid *gid)
-{
-	struct mlx4_ib_dev *dev = to_mdev(ibdev);
-
-	*gid = dev->iboe.gid_table[port - 1][index];
-
-	return 0;
-}
-
 static int mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
 			     union ib_gid *gid)
 {
-	if (rdma_port_get_link_layer(ibdev, port) == IB_LINK_LAYER_INFINIBAND)
+	int ret;
+
+	if (rdma_protocol_ib(ibdev, port))
 		return __mlx4_ib_query_gid(ibdev, port, index, gid, 0);
-	else
-		return iboe_query_gid(ibdev, port, index, gid);
+
+	if (!rdma_protocol_roce(ibdev, port))
+		return -ENODEV;
+
+	if (!rdma_cap_roce_gid_table(ibdev, port))
+		return -ENODEV;
+
+	ret = ib_get_cached_gid(ibdev, port, index, gid);
+	if (ret == -EAGAIN) {
+		memcpy(gid, &zgid, sizeof(*gid));
+		return 0;
+	}
+
+	return ret;
 }
 
 int __mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index,
@@ -691,7 +921,7 @@ static struct ib_ucontext *mlx4_ib_alloc_ucontext(struct ib_device *ibdev,
 		resp.cqe_size	      = dev->dev->caps.cqe_size;
 	}
 
-	context = kmalloc(sizeof *context, GFP_KERNEL);
+	context = kzalloc(sizeof(*context), GFP_KERNEL);
 	if (!context)
 		return ERR_PTR(-ENOMEM);
 
@@ -728,21 +958,143 @@ static int mlx4_ib_dealloc_ucontext(struct ib_ucontext *ibcontext)
 	return 0;
 }
 
+static void  mlx4_ib_vma_open(struct vm_area_struct *area)
+{
+	/* vma_open is called when a new VMA is created on top of our VMA.
+	 * This is done through either mremap flow or split_vma (usually due
+	 * to mlock, madvise, munmap, etc.). We do not support a clone of the
+	 * vma, as this VMA is strongly hardware related. Therefore we set the
+	 * vm_ops of the newly created/cloned VMA to NULL, to prevent it from
+	 * calling us again and trying to do incorrect actions. We assume that
+	 * the original vma size is exactly a single page that there will be no
+	 * "splitting" operations on.
+	 */
+	area->vm_ops = NULL;
+}
+
+static void  mlx4_ib_vma_close(struct vm_area_struct *area)
+{
+	struct mlx4_ib_vma_private_data *mlx4_ib_vma_priv_data;
+
+	/* It's guaranteed that all VMAs opened on a FD are closed before the
+	 * file itself is closed, therefore no sync is needed with the regular
+	 * closing flow. (e.g. mlx4_ib_dealloc_ucontext) However need a sync
+	 * with accessing the vma as part of mlx4_ib_disassociate_ucontext.
+	 * The close operation is usually called under mm->mmap_sem except when
+	 * process is exiting.  The exiting case is handled explicitly as part
+	 * of mlx4_ib_disassociate_ucontext.
+	 */
+	mlx4_ib_vma_priv_data = (struct mlx4_ib_vma_private_data *)
+				area->vm_private_data;
+
+	/* set the vma context pointer to null in the mlx4_ib driver's private
+	 * data to protect against a race condition in mlx4_ib_dissassociate_ucontext().
+	 */
+	mlx4_ib_vma_priv_data->vma = NULL;
+}
+
+static const struct vm_operations_struct mlx4_ib_vm_ops = {
+	.open = mlx4_ib_vma_open,
+	.close = mlx4_ib_vma_close
+};
+
+static void mlx4_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
+{
+	int i;
+	int ret = 0;
+	struct vm_area_struct *vma;
+	struct mlx4_ib_ucontext *context = to_mucontext(ibcontext);
+	struct task_struct *owning_process  = NULL;
+	struct mm_struct   *owning_mm       = NULL;
+
+	owning_process = get_pid_task(ibcontext->tgid, PIDTYPE_PID);
+	if (!owning_process)
+		return;
+
+	owning_mm = get_task_mm(owning_process);
+	if (!owning_mm) {
+		pr_info("no mm, disassociate ucontext is pending task termination\n");
+		while (1) {
+			/* make sure that task is dead before returning, it may
+			 * prevent a rare case of module down in parallel to a
+			 * call to mlx4_ib_vma_close.
+			 */
+			put_task_struct(owning_process);
+			msleep(1);
+			owning_process = get_pid_task(ibcontext->tgid,
+						      PIDTYPE_PID);
+			if (!owning_process ||
+			    owning_process->state == TASK_DEAD) {
+				pr_info("disassociate ucontext done, task was terminated\n");
+				/* in case task was dead need to release the task struct */
+				if (owning_process)
+					put_task_struct(owning_process);
+				return;
+			}
+		}
+	}
+
+	/* need to protect from a race on closing the vma as part of
+	 * mlx4_ib_vma_close().
+	 */
+	down_read(&owning_mm->mmap_sem);
+	for (i = 0; i < HW_BAR_COUNT; i++) {
+		vma = context->hw_bar_info[i].vma;
+		if (!vma)
+			continue;
+
+		ret = zap_vma_ptes(context->hw_bar_info[i].vma,
+				   context->hw_bar_info[i].vma->vm_start,
+				   PAGE_SIZE);
+		if (ret) {
+			pr_err("Error: zap_vma_ptes failed for index=%d, ret=%d\n", i, ret);
+			BUG_ON(1);
+		}
+
+		/* context going to be destroyed, should not access ops any more */
+		context->hw_bar_info[i].vma->vm_ops = NULL;
+	}
+
+	up_read(&owning_mm->mmap_sem);
+	mmput(owning_mm);
+	put_task_struct(owning_process);
+}
+
+static void mlx4_ib_set_vma_data(struct vm_area_struct *vma,
+				 struct mlx4_ib_vma_private_data *vma_private_data)
+{
+	vma_private_data->vma = vma;
+	vma->vm_private_data = vma_private_data;
+	vma->vm_ops =  &mlx4_ib_vm_ops;
+}
+
 static int mlx4_ib_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
 {
 	struct mlx4_ib_dev *dev = to_mdev(context->device);
+	struct mlx4_ib_ucontext *mucontext = to_mucontext(context);
 
 	if (vma->vm_end - vma->vm_start != PAGE_SIZE)
 		return -EINVAL;
 
 	if (vma->vm_pgoff == 0) {
+		/* We prevent double mmaping on same context */
+		if (mucontext->hw_bar_info[HW_BAR_DB].vma)
+			return -EINVAL;
+
 		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 
 		if (io_remap_pfn_range(vma, vma->vm_start,
 				       to_mucontext(context)->uar.pfn,
 				       PAGE_SIZE, vma->vm_page_prot))
 			return -EAGAIN;
+
+		mlx4_ib_set_vma_data(vma, &mucontext->hw_bar_info[HW_BAR_DB]);
+
 	} else if (vma->vm_pgoff == 1 && dev->dev->caps.bf_reg_size != 0) {
+		/* We prevent double mmaping on same context */
+		if (mucontext->hw_bar_info[HW_BAR_BF].vma)
+			return -EINVAL;
+
 		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
 
 		if (io_remap_pfn_range(vma, vma->vm_start,
@@ -750,9 +1102,18 @@ static int mlx4_ib_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
 				       dev->dev->caps.num_uars,
 				       PAGE_SIZE, vma->vm_page_prot))
 			return -EAGAIN;
+
+		mlx4_ib_set_vma_data(vma, &mucontext->hw_bar_info[HW_BAR_BF]);
+
 	} else if (vma->vm_pgoff == 3) {
 		struct mlx4_clock_params params;
-		int ret = mlx4_get_internal_clock_params(dev->dev, &params);
+		int ret;
+
+		/* We prevent double mmaping on same context */
+		if (mucontext->hw_bar_info[HW_BAR_CLOCK].vma)
+			return -EINVAL;
+
+		ret = mlx4_get_internal_clock_params(dev->dev, &params);
 
 		if (ret)
 			return ret;
@@ -765,6 +1126,9 @@ static int mlx4_ib_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
 				       >> PAGE_SHIFT,
 				       PAGE_SIZE, vma->vm_page_prot))
 			return -EAGAIN;
+
+		mlx4_ib_set_vma_data(vma,
+				     &mucontext->hw_bar_info[HW_BAR_CLOCK]);
 	} else {
 		return -EINVAL;
 	}
@@ -1546,272 +1910,6 @@ static struct device_attribute *mlx4_class_attributes[] = {
 	&dev_attr_board_id
 };
 
-static void mlx4_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 update_gids_task(struct work_struct *work)
-{
-	struct update_gid_work *gw = container_of(work, struct update_gid_work, work);
-	struct mlx4_cmd_mailbox *mailbox;
-	union ib_gid *gids;
-	int err;
-	struct mlx4_dev	*dev = gw->dev->dev;
-	int is_bonded = mlx4_is_bonded(dev);
-
-	if (!gw->dev->ib_active)
-		return;
-
-	mailbox = mlx4_alloc_cmd_mailbox(dev);
-	if (IS_ERR(mailbox)) {
-		pr_warn("update gid table failed %ld\n", PTR_ERR(mailbox));
-		return;
-	}
-
-	gids = mailbox->buf;
-	memcpy(gids, gw->gids, sizeof gw->gids);
-
-	err = mlx4_cmd(dev, mailbox->dma, MLX4_SET_PORT_GID_TABLE << 8 | gw->port,
-		       MLX4_SET_PORT_ETH_OPCODE, MLX4_CMD_SET_PORT,
-		       MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED);
-	if (err)
-		pr_warn("set port command failed\n");
-	else
-		if ((gw->port == 1) || !is_bonded)
-			mlx4_ib_dispatch_event(gw->dev,
-					       is_bonded ? 1 : gw->port,
-					       IB_EVENT_GID_CHANGE);
-
-	mlx4_free_cmd_mailbox(dev, mailbox);
-	kfree(gw);
-}
-
-static void reset_gids_task(struct work_struct *work)
-{
-	struct update_gid_work *gw =
-			container_of(work, struct update_gid_work, work);
-	struct mlx4_cmd_mailbox *mailbox;
-	union ib_gid *gids;
-	int err;
-	struct mlx4_dev	*dev = gw->dev->dev;
-
-	if (!gw->dev->ib_active)
-		return;
-
-	mailbox = mlx4_alloc_cmd_mailbox(dev);
-	if (IS_ERR(mailbox)) {
-		pr_warn("reset gid table failed\n");
-		goto free;
-	}
-
-	gids = mailbox->buf;
-	memcpy(gids, gw->gids, sizeof(gw->gids));
-
-	if (mlx4_ib_port_link_layer(&gw->dev->ib_dev, gw->port) ==
-				    IB_LINK_LAYER_ETHERNET) {
-		err = mlx4_cmd(dev, mailbox->dma,
-			       MLX4_SET_PORT_GID_TABLE << 8 | gw->port,
-			       MLX4_SET_PORT_ETH_OPCODE, MLX4_CMD_SET_PORT,
-			       MLX4_CMD_TIME_CLASS_B,
-			       MLX4_CMD_WRAPPED);
-		if (err)
-			pr_warn("set port %d command failed\n", gw->port);
-	}
-
-	mlx4_free_cmd_mailbox(dev, mailbox);
-free:
-	kfree(gw);
-}
-
-static int update_gid_table(struct mlx4_ib_dev *dev, int port,
-			    union ib_gid *gid, int clear,
-			    int default_gid)
-{
-	struct update_gid_work *work;
-	int i;
-	int need_update = 0;
-	int free = -1;
-	int found = -1;
-	int max_gids;
-
-	if (default_gid) {
-		free = 0;
-	} else {
-		max_gids = dev->dev->caps.gid_table_len[port];
-		for (i = 1; i < max_gids; ++i) {
-			if (!memcmp(&dev->iboe.gid_table[port - 1][i], gid,
-				    sizeof(*gid)))
-				found = i;
-
-			if (clear) {
-				if (found >= 0) {
-					need_update = 1;
-					dev->iboe.gid_table[port - 1][found] =
-						zgid;
-					break;
-				}
-			} else {
-				if (found >= 0)
-					break;
-
-				if (free < 0 &&
-				    !memcmp(&dev->iboe.gid_table[port - 1][i],
-					    &zgid, sizeof(*gid)))
-					free = i;
-			}
-		}
-	}
-
-	if (found == -1 && !clear && free >= 0) {
-		dev->iboe.gid_table[port - 1][free] = *gid;
-		need_update = 1;
-	}
-
-	if (!need_update)
-		return 0;
-
-	work = kzalloc(sizeof(*work), GFP_ATOMIC);
-	if (!work)
-		return -ENOMEM;
-
-	memcpy(work->gids, dev->iboe.gid_table[port - 1], sizeof(work->gids));
-	INIT_WORK(&work->work, update_gids_task);
-	work->port = port;
-	work->dev = dev;
-	queue_work(wq, &work->work);
-
-	return 0;
-}
-
-static void mlx4_make_default_gid(struct  net_device *dev, union ib_gid *gid)
-{
-	gid->global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
-	mlx4_addrconf_ifid_eui48(&gid->raw[8], 0xffff, dev);
-}
-
-
-static int reset_gid_table(struct mlx4_ib_dev *dev, u8 port)
-{
-	struct update_gid_work *work;
-
-	work = kzalloc(sizeof(*work), GFP_ATOMIC);
-	if (!work)
-		return -ENOMEM;
-
-	memset(dev->iboe.gid_table[port - 1], 0, sizeof(work->gids));
-	memset(work->gids, 0, sizeof(work->gids));
-	INIT_WORK(&work->work, reset_gids_task);
-	work->dev = dev;
-	work->port = port;
-	queue_work(wq, &work->work);
-	return 0;
-}
-
-static int mlx4_ib_addr_event(int event, struct net_device *event_netdev,
-			      struct mlx4_ib_dev *ibdev, union ib_gid *gid)
-{
-	struct mlx4_ib_iboe *iboe;
-	int port = 0;
-	struct net_device *real_dev = rdma_vlan_dev_real_dev(event_netdev) ?
-				rdma_vlan_dev_real_dev(event_netdev) :
-				event_netdev;
-	union ib_gid default_gid;
-
-	mlx4_make_default_gid(real_dev, &default_gid);
-
-	if (!memcmp(gid, &default_gid, sizeof(*gid)))
-		return 0;
-
-	if (event != NETDEV_DOWN && event != NETDEV_UP)
-		return 0;
-
-	if ((real_dev != event_netdev) &&
-	    (event == NETDEV_DOWN) &&
-	    rdma_link_local_addr((struct in6_addr *)gid))
-		return 0;
-
-	iboe = &ibdev->iboe;
-	spin_lock_bh(&iboe->lock);
-
-	for (port = 1; port <= ibdev->dev->caps.num_ports; ++port)
-		if ((netif_is_bond_master(real_dev) &&
-		     (real_dev == iboe->masters[port - 1])) ||
-		     (!netif_is_bond_master(real_dev) &&
-		     (real_dev == iboe->netdevs[port - 1])))
-			update_gid_table(ibdev, port, gid,
-					 event == NETDEV_DOWN, 0);
-
-	spin_unlock_bh(&iboe->lock);
-	return 0;
-
-}
-
-static u8 mlx4_ib_get_dev_port(struct net_device *dev,
-			       struct mlx4_ib_dev *ibdev)
-{
-	u8 port = 0;
-	struct mlx4_ib_iboe *iboe;
-	struct net_device *real_dev = rdma_vlan_dev_real_dev(dev) ?
-				rdma_vlan_dev_real_dev(dev) : dev;
-
-	iboe = &ibdev->iboe;
-
-	for (port = 1; port <= ibdev->dev->caps.num_ports; ++port)
-		if ((netif_is_bond_master(real_dev) &&
-		     (real_dev == iboe->masters[port - 1])) ||
-		     (!netif_is_bond_master(real_dev) &&
-		     (real_dev == iboe->netdevs[port - 1])))
-			break;
-
-	if ((port == 0) || (port > ibdev->dev->caps.num_ports))
-		return 0;
-	else
-		return port;
-}
-
-static int mlx4_ib_inet_event(struct notifier_block *this, unsigned long event,
-				void *ptr)
-{
-	struct mlx4_ib_dev *ibdev;
-	struct in_ifaddr *ifa = ptr;
-	union ib_gid gid;
-	struct net_device *event_netdev = ifa->ifa_dev->dev;
-
-	ipv6_addr_set_v4mapped(ifa->ifa_address, (struct in6_addr *)&gid);
-
-	ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb_inet);
-
-	mlx4_ib_addr_event(event, event_netdev, ibdev, &gid);
-	return NOTIFY_DONE;
-}
-
-#if IS_ENABLED(CONFIG_IPV6)
-static int mlx4_ib_inet6_event(struct notifier_block *this, unsigned long event,
-				void *ptr)
-{
-	struct mlx4_ib_dev *ibdev;
-	struct inet6_ifaddr *ifa = ptr;
-	union  ib_gid *gid = (union ib_gid *)&ifa->addr;
-	struct net_device *event_netdev = ifa->idev->dev;
-
-	ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb_inet6);
-
-	mlx4_ib_addr_event(event, event_netdev, ibdev, gid);
-	return NOTIFY_DONE;
-}
-#endif
-
 #define MLX4_IB_INVALID_MAC	((u64)-1)
 static void mlx4_ib_update_qps(struct mlx4_ib_dev *ibdev,
 			       struct net_device *dev,
@@ -1870,94 +1968,6 @@ unlock:
 	mutex_unlock(&ibdev->qp1_proxy_lock[port - 1]);
 }
 
-static void mlx4_ib_get_dev_addr(struct net_device *dev,
-				 struct mlx4_ib_dev *ibdev, u8 port)
-{
-	struct in_device *in_dev;
-#if IS_ENABLED(CONFIG_IPV6)
-	struct inet6_dev *in6_dev;
-	union ib_gid  *pgid;
-	struct inet6_ifaddr *ifp;
-	union ib_gid default_gid;
-#endif
-	union ib_gid gid;
-
-
-	if ((port == 0) || (port > ibdev->dev->caps.num_ports))
-		return;
-
-	/* IPv4 gids */
-	in_dev = in_dev_get(dev);
-	if (in_dev) {
-		for_ifa(in_dev) {
-			/*ifa->ifa_address;*/
-			ipv6_addr_set_v4mapped(ifa->ifa_address,
-					       (struct in6_addr *)&gid);
-			update_gid_table(ibdev, port, &gid, 0, 0);
-		}
-		endfor_ifa(in_dev);
-		in_dev_put(in_dev);
-	}
-#if IS_ENABLED(CONFIG_IPV6)
-	mlx4_make_default_gid(dev, &default_gid);
-	/* IPv6 gids */
-	in6_dev = in6_dev_get(dev);
-	if (in6_dev) {
-		read_lock_bh(&in6_dev->lock);
-		list_for_each_entry(ifp, &in6_dev->addr_list, if_list) {
-			pgid = (union ib_gid *)&ifp->addr;
-			if (!memcmp(pgid, &default_gid, sizeof(*pgid)))
-				continue;
-			update_gid_table(ibdev, port, pgid, 0, 0);
-		}
-		read_unlock_bh(&in6_dev->lock);
-		in6_dev_put(in6_dev);
-	}
-#endif
-}
-
-static void mlx4_ib_set_default_gid(struct mlx4_ib_dev *ibdev,
-				 struct  net_device *dev, u8 port)
-{
-	union ib_gid gid;
-	mlx4_make_default_gid(dev, &gid);
-	update_gid_table(ibdev, port, &gid, 0, 1);
-}
-
-static int mlx4_ib_init_gid_table(struct mlx4_ib_dev *ibdev)
-{
-	struct	net_device *dev;
-	struct mlx4_ib_iboe *iboe = &ibdev->iboe;
-	int i;
-	int err = 0;
-
-	for (i = 1; i <= ibdev->num_ports; ++i) {
-		if (rdma_port_get_link_layer(&ibdev->ib_dev, i) ==
-		    IB_LINK_LAYER_ETHERNET) {
-			err = reset_gid_table(ibdev, i);
-			if (err)
-				goto out;
-		}
-	}
-
-	read_lock(&dev_base_lock);
-	spin_lock_bh(&iboe->lock);
-
-	for_each_netdev(&init_net, dev) {
-		u8 port = mlx4_ib_get_dev_port(dev, ibdev);
-		/* port will be non-zero only for ETH ports */
-		if (port) {
-			mlx4_ib_set_default_gid(ibdev, dev, port);
-			mlx4_ib_get_dev_addr(dev, ibdev, port);
-		}
-	}
-
-	spin_unlock_bh(&iboe->lock);
-	read_unlock(&dev_base_lock);
-out:
-	return err;
-}
-
 static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev,
 				 struct net_device *dev,
 				 unsigned long event)
@@ -1967,81 +1977,22 @@ static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev,
 	int update_qps_port = -1;
 	int port;
 
+	ASSERT_RTNL();
+
 	iboe = &ibdev->iboe;
 
 	spin_lock_bh(&iboe->lock);
 	mlx4_foreach_ib_transport_port(port, ibdev->dev) {
-		enum ib_port_state	port_state = IB_PORT_NOP;
-		struct net_device *old_master = iboe->masters[port - 1];
-		struct net_device *curr_netdev;
-		struct net_device *curr_master;
 
 		iboe->netdevs[port - 1] =
 			mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port);
-		if (iboe->netdevs[port - 1])
-			mlx4_ib_set_default_gid(ibdev,
-						iboe->netdevs[port - 1], port);
-		curr_netdev = iboe->netdevs[port - 1];
-
-		if (iboe->netdevs[port - 1] &&
-		    netif_is_bond_slave(iboe->netdevs[port - 1])) {
-			iboe->masters[port - 1] = netdev_master_upper_dev_get(
-				iboe->netdevs[port - 1]);
-		} else {
-			iboe->masters[port - 1] = NULL;
-		}
-		curr_master = iboe->masters[port - 1];
 
 		if (dev == iboe->netdevs[port - 1] &&
 		    (event == NETDEV_CHANGEADDR || event == NETDEV_REGISTER ||
 		     event == NETDEV_UP || event == NETDEV_CHANGE))
 			update_qps_port = port;
 
-		if (curr_netdev) {
-			port_state = (netif_running(curr_netdev) && netif_carrier_ok(curr_netdev)) ?
-						IB_PORT_ACTIVE : IB_PORT_DOWN;
-			mlx4_ib_set_default_gid(ibdev, curr_netdev, port);
-			if (curr_master) {
-				/* if using bonding/team and a slave port is down, we
-				 * don't want the bond IP based gids in the table since
-				 * flows that select port by gid may get the down port.
-				*/
-				if (port_state == IB_PORT_DOWN &&
-				    !mlx4_is_bonded(ibdev->dev)) {
-					reset_gid_table(ibdev, port);
-					mlx4_ib_set_default_gid(ibdev,
-								curr_netdev,
-								port);
-				} else {
-					/* gids from the upper dev (bond/team)
-					 * should appear in port's gid table
-					*/
-					mlx4_ib_get_dev_addr(curr_master,
-							     ibdev, port);
-				}
-			}
-			/* if bonding is used it is possible that we add it to
-			 * masters only after IP address is assigned to the
-			 * net bonding interface.
-			*/
-			if (curr_master && (old_master != curr_master)) {
-				reset_gid_table(ibdev, port);
-				mlx4_ib_set_default_gid(ibdev,
-							curr_netdev, port);
-				mlx4_ib_get_dev_addr(curr_master, ibdev, port);
-			}
-
-			if (!curr_master && (old_master != curr_master)) {
-				reset_gid_table(ibdev, port);
-				mlx4_ib_set_default_gid(ibdev,
-							curr_netdev, port);
-				mlx4_ib_get_dev_addr(curr_netdev, ibdev, port);
-			}
-		} else {
-			reset_gid_table(ibdev, port);
-		}
 	}
-
 	spin_unlock_bh(&iboe->lock);
 
 	if (update_qps_port > 0)
@@ -2224,6 +2175,9 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 						1 : ibdev->num_ports;
 	ibdev->ib_dev.num_comp_vectors	= dev->caps.num_comp_vectors;
 	ibdev->ib_dev.dma_device	= &dev->persist->pdev->dev;
+	ibdev->ib_dev.get_netdev	= mlx4_ib_get_netdev;
+	ibdev->ib_dev.add_gid		= mlx4_ib_add_gid;
+	ibdev->ib_dev.del_gid		= mlx4_ib_del_gid;
 
 	if (dev->caps.userspace_caps)
 		ibdev->ib_dev.uverbs_abi_ver = MLX4_IB_UVERBS_ABI_VERSION;
@@ -2292,13 +2246,14 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	ibdev->ib_dev.reg_user_mr	= mlx4_ib_reg_user_mr;
 	ibdev->ib_dev.rereg_user_mr	= mlx4_ib_rereg_user_mr;
 	ibdev->ib_dev.dereg_mr		= mlx4_ib_dereg_mr;
-	ibdev->ib_dev.alloc_fast_reg_mr = mlx4_ib_alloc_fast_reg_mr;
+	ibdev->ib_dev.alloc_mr		= mlx4_ib_alloc_mr;
 	ibdev->ib_dev.alloc_fast_reg_page_list = mlx4_ib_alloc_fast_reg_page_list;
 	ibdev->ib_dev.free_fast_reg_page_list  = mlx4_ib_free_fast_reg_page_list;
 	ibdev->ib_dev.attach_mcast	= mlx4_ib_mcg_attach;
 	ibdev->ib_dev.detach_mcast	= mlx4_ib_mcg_detach;
 	ibdev->ib_dev.process_mad	= mlx4_ib_process_mad;
 	ibdev->ib_dev.get_port_immutable = mlx4_port_immutable;
+	ibdev->ib_dev.disassociate_ucontext = mlx4_ib_disassociate_ucontext;
 
 	if (!mlx4_is_slave(ibdev->dev)) {
 		ibdev->ib_dev.alloc_fmr		= mlx4_ib_fmr_alloc;
@@ -2434,26 +2389,6 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 				goto err_notif;
 			}
 		}
-		if (!iboe->nb_inet.notifier_call) {
-			iboe->nb_inet.notifier_call = mlx4_ib_inet_event;
-			err = register_inetaddr_notifier(&iboe->nb_inet);
-			if (err) {
-				iboe->nb_inet.notifier_call = NULL;
-				goto err_notif;
-			}
-		}
-#if IS_ENABLED(CONFIG_IPV6)
-		if (!iboe->nb_inet6.notifier_call) {
-			iboe->nb_inet6.notifier_call = mlx4_ib_inet6_event;
-			err = register_inet6addr_notifier(&iboe->nb_inet6);
-			if (err) {
-				iboe->nb_inet6.notifier_call = NULL;
-				goto err_notif;
-			}
-		}
-#endif
-		if (mlx4_ib_init_gid_table(ibdev))
-			goto err_notif;
 	}
 
 	for (j = 0; j < ARRAY_SIZE(mlx4_class_attributes); ++j) {
@@ -2484,18 +2419,6 @@ err_notif:
 			pr_warn("failure unregistering notifier\n");
 		ibdev->iboe.nb.notifier_call = NULL;
 	}
-	if (ibdev->iboe.nb_inet.notifier_call) {
-		if (unregister_inetaddr_notifier(&ibdev->iboe.nb_inet))
-			pr_warn("failure unregistering notifier\n");
-		ibdev->iboe.nb_inet.notifier_call = NULL;
-	}
-#if IS_ENABLED(CONFIG_IPV6)
-	if (ibdev->iboe.nb_inet6.notifier_call) {
-		if (unregister_inet6addr_notifier(&ibdev->iboe.nb_inet6))
-			pr_warn("failure unregistering notifier\n");
-		ibdev->iboe.nb_inet6.notifier_call = NULL;
-	}
-#endif
 	flush_workqueue(wq);
 
 	mlx4_ib_close_sriov(ibdev);
@@ -2621,19 +2544,6 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
 		kfree(ibdev->ib_uc_qpns_bitmap);
 	}
 
-	if (ibdev->iboe.nb_inet.notifier_call) {
-		if (unregister_inetaddr_notifier(&ibdev->iboe.nb_inet))
-			pr_warn("failure unregistering notifier\n");
-		ibdev->iboe.nb_inet.notifier_call = NULL;
-	}
-#if IS_ENABLED(CONFIG_IPV6)
-	if (ibdev->iboe.nb_inet6.notifier_call) {
-		if (unregister_inet6addr_notifier(&ibdev->iboe.nb_inet6))
-			pr_warn("failure unregistering notifier\n");
-		ibdev->iboe.nb_inet6.notifier_call = NULL;
-	}
-#endif
-
 	iounmap(ibdev->uar_map);
 	for (p = 0; p < ibdev->num_ports; ++p)
 		if (ibdev->counters[p].index != -1 &&
@@ -2669,31 +2579,33 @@ static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init)
 	dm = kcalloc(ports, sizeof(*dm), GFP_ATOMIC);
 	if (!dm) {
 		pr_err("failed to allocate memory for tunneling qp update\n");
-		goto out;
+		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");
-			for (i = 0; i < dev->caps.num_ports; i++) {
-				if (dm[i])
-					kfree(dm[i]);
-			}
+			while (--i >= 0)
+				kfree(dm[i]);
 			goto out;
 		}
-	}
-	/* initialize or tear down tunnel QPs for the slave */
-	for (i = 0; i < ports; i++) {
 		INIT_WORK(&dm[i]->work, mlx4_ib_tunnels_update_work);
 		dm[i]->port = first_port + i + 1;
 		dm[i]->slave = slave;
 		dm[i]->do_init = do_init;
 		dm[i]->dev = ibdev;
-		spin_lock_irqsave(&ibdev->sriov.going_down_lock, flags);
-		if (!ibdev->sriov.is_going_down)
+	}
+	/* initialize or tear down tunnel QPs for the slave */
+	spin_lock_irqsave(&ibdev->sriov.going_down_lock, flags);
+	if (!ibdev->sriov.is_going_down) {
+		for (i = 0; i < ports; i++)
 			queue_work(ibdev->sriov.demux[i].ud_wq, &dm[i]->work);
 		spin_unlock_irqrestore(&ibdev->sriov.going_down_lock, flags);
+	} else {
+		spin_unlock_irqrestore(&ibdev->sriov.going_down_lock, flags);
+		for (i = 0; i < ports; i++)
+			kfree(dm[i]);
 	}
 out:
 	kfree(dm);
diff --git a/drivers/infiniband/hw/mlx4/mcg.c b/drivers/infiniband/hw/mlx4/mcg.c
index ed327e6c8fdc..2d5bccd71fc6 100644
--- a/drivers/infiniband/hw/mlx4/mcg.c
+++ b/drivers/infiniband/hw/mlx4/mcg.c
@@ -51,6 +51,10 @@
 	pr_warn("%s-%d: %16s (port %d): WARNING: " format, __func__, __LINE__,\
 	(group)->name, group->demux->port, ## arg)
 
+#define mcg_debug_group(group, format, arg...) \
+	pr_debug("%s-%d: %16s (port %d): WARNING: " format, __func__, __LINE__,\
+		 (group)->name, (group)->demux->port, ## arg)
+
 #define mcg_error_group(group, format, arg...) \
 	pr_err("  %16s: " format, (group)->name, ## arg)
 
@@ -206,15 +210,16 @@ static int send_mad_to_wire(struct mlx4_ib_demux_ctx *ctx, struct ib_mad *mad)
 {
 	struct mlx4_ib_dev *dev = ctx->dev;
 	struct ib_ah_attr	ah_attr;
+	unsigned long flags;
 
-	spin_lock(&dev->sm_lock);
+	spin_lock_irqsave(&dev->sm_lock, flags);
 	if (!dev->sm_ah[ctx->port - 1]) {
 		/* port is not yet Active, sm_ah not ready */
-		spin_unlock(&dev->sm_lock);
+		spin_unlock_irqrestore(&dev->sm_lock, flags);
 		return -EAGAIN;
 	}
 	mlx4_ib_query_ah(dev->sm_ah[ctx->port - 1], &ah_attr);
-	spin_unlock(&dev->sm_lock);
+	spin_unlock_irqrestore(&dev->sm_lock, flags);
 	return mlx4_ib_send_to_wire(dev, mlx4_master_func_num(dev->dev),
 				    ctx->port, IB_QPT_GSI, 0, 1, IB_QP1_QKEY,
 				    &ah_attr, NULL, mad);
@@ -961,8 +966,8 @@ int mlx4_ib_mcg_multiplex_handler(struct ib_device *ibdev, int port,
 		mutex_lock(&group->lock);
 		if (group->func[slave].num_pend_reqs > MAX_PEND_REQS_PER_FUNC) {
 			mutex_unlock(&group->lock);
-			mcg_warn_group(group, "Port %d, Func %d has too many pending requests (%d), dropping\n",
-				       port, slave, MAX_PEND_REQS_PER_FUNC);
+			mcg_debug_group(group, "Port %d, Func %d has too many pending requests (%d), dropping\n",
+					port, slave, MAX_PEND_REQS_PER_FUNC);
 			release_group(group, 0);
 			kfree(req);
 			return -ENOMEM;
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 334387f63358..1e7b23bb2eb0 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -70,11 +70,24 @@ extern int mlx4_ib_sm_guid_assign;
 
 #define MLX4_IB_UC_STEER_QPN_ALIGN 1
 #define MLX4_IB_UC_MAX_NUM_QPS     256
+
+enum hw_bar_type {
+	HW_BAR_BF,
+	HW_BAR_DB,
+	HW_BAR_CLOCK,
+	HW_BAR_COUNT
+};
+
+struct mlx4_ib_vma_private_data {
+	struct vm_area_struct *vma;
+};
+
 struct mlx4_ib_ucontext {
 	struct ib_ucontext	ibucontext;
 	struct mlx4_uar		uar;
 	struct list_head	db_page_list;
 	struct mutex		db_page_mutex;
+	struct mlx4_ib_vma_private_data hw_bar_info[HW_BAR_COUNT];
 };
 
 struct mlx4_ib_pd {
@@ -415,7 +428,6 @@ struct mlx4_ib_demux_pv_ctx {
 	struct ib_device *ib_dev;
 	struct ib_cq *cq;
 	struct ib_pd *pd;
-	struct ib_mr *mr;
 	struct work_struct work;
 	struct workqueue_struct *wq;
 	struct mlx4_ib_demux_pv_qp qp[2];
@@ -457,15 +469,26 @@ struct mlx4_ib_sriov {
 	struct idr pv_id_table;
 };
 
+struct gid_cache_context {
+	int real_index;
+	int refcount;
+};
+
+struct gid_entry {
+	union ib_gid	gid;
+	struct gid_cache_context *ctx;
+};
+
+struct mlx4_port_gid_table {
+	struct gid_entry gids[MLX4_MAX_PORT_GIDS];
+};
+
 struct mlx4_ib_iboe {
 	spinlock_t		lock;
 	struct net_device      *netdevs[MLX4_MAX_PORTS];
-	struct net_device      *masters[MLX4_MAX_PORTS];
 	atomic64_t		mac[MLX4_MAX_PORTS];
 	struct notifier_block 	nb;
-	struct notifier_block	nb_inet;
-	struct notifier_block	nb_inet6;
-	union ib_gid		gid_table[MLX4_MAX_PORTS][128];
+	struct mlx4_port_gid_table gids[MLX4_MAX_PORTS];
 };
 
 struct pkey_mgt {
@@ -680,8 +703,9 @@ struct ib_mw *mlx4_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type);
 int mlx4_ib_bind_mw(struct ib_qp *qp, struct ib_mw *mw,
 		    struct ib_mw_bind *mw_bind);
 int mlx4_ib_dealloc_mw(struct ib_mw *mw);
-struct ib_mr *mlx4_ib_alloc_fast_reg_mr(struct ib_pd *pd,
-					int max_page_list_len);
+struct ib_mr *mlx4_ib_alloc_mr(struct ib_pd *pd,
+			       enum ib_mr_type mr_type,
+			       u32 max_num_sg);
 struct ib_fast_reg_page_list *mlx4_ib_alloc_fast_reg_page_list(struct ib_device *ibdev,
 							       int page_list_len);
 void mlx4_ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list);
@@ -838,5 +862,7 @@ int mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags,
 			  u64 start, u64 length, u64 virt_addr,
 			  int mr_access_flags, struct ib_pd *pd,
 			  struct ib_udata *udata);
+int mlx4_ib_gid_index_to_real_index(struct mlx4_ib_dev *ibdev,
+				    u8 port_num, int index);
 
 #endif /* MLX4_IB_H */
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index e0d271782d0a..2542fd3c1a49 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -350,19 +350,24 @@ int mlx4_ib_dealloc_mw(struct ib_mw *ibmw)
 	return 0;
 }
 
-struct ib_mr *mlx4_ib_alloc_fast_reg_mr(struct ib_pd *pd,
-					int max_page_list_len)
+struct ib_mr *mlx4_ib_alloc_mr(struct ib_pd *pd,
+			       enum ib_mr_type mr_type,
+			       u32 max_num_sg)
 {
 	struct mlx4_ib_dev *dev = to_mdev(pd->device);
 	struct mlx4_ib_mr *mr;
 	int err;
 
+	if (mr_type != IB_MR_TYPE_MEM_REG ||
+	    max_num_sg > MLX4_MAX_FAST_REG_PAGES)
+		return ERR_PTR(-EINVAL);
+
 	mr = kmalloc(sizeof *mr, GFP_KERNEL);
 	if (!mr)
 		return ERR_PTR(-ENOMEM);
 
 	err = mlx4_mr_alloc(dev->dev, to_mpd(pd)->pdn, 0, 0, 0,
-			    max_page_list_len, 0, &mr->mmr);
+			    max_num_sg, 0, &mr->mmr);
 	if (err)
 		goto err_free;
 
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index c5a3a5f0de41..4ad9be3ad61c 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -1292,14 +1292,18 @@ static int _mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
 		path->static_rate = 0;
 
 	if (ah->ah_flags & IB_AH_GRH) {
-		if (ah->grh.sgid_index >= dev->dev->caps.gid_table_len[port]) {
+		int real_sgid_index = mlx4_ib_gid_index_to_real_index(dev,
+								      port,
+								      ah->grh.sgid_index);
+
+		if (real_sgid_index >= dev->dev->caps.gid_table_len[port]) {
 			pr_err("sgid_index (%u) too large. max is %d\n",
-			       ah->grh.sgid_index, dev->dev->caps.gid_table_len[port] - 1);
+			       real_sgid_index, dev->dev->caps.gid_table_len[port] - 1);
 			return -1;
 		}
 
 		path->grh_mylmc |= 1 << 7;
-		path->mgid_index = ah->grh.sgid_index;
+		path->mgid_index = real_sgid_index;
 		path->hop_limit  = ah->grh.hop_limit;
 		path->tclass_flowlabel =
 			cpu_to_be32((ah->grh.traffic_class << 20) |
diff --git a/drivers/infiniband/hw/mlx4/sysfs.c b/drivers/infiniband/hw/mlx4/sysfs.c
index 6797108ce873..69fb5ba94d0f 100644
--- a/drivers/infiniband/hw/mlx4/sysfs.c
+++ b/drivers/infiniband/hw/mlx4/sysfs.c
@@ -640,6 +640,8 @@ static int add_port(struct mlx4_ib_dev *dev, int port_num, int slave)
 	struct mlx4_port *p;
 	int i;
 	int ret;
+	int is_eth = rdma_port_get_link_layer(&dev->ib_dev, port_num) ==
+			IB_LINK_LAYER_ETHERNET;
 
 	p = kzalloc(sizeof *p, GFP_KERNEL);
 	if (!p)
@@ -657,7 +659,8 @@ static int add_port(struct mlx4_ib_dev *dev, int port_num, int slave)
 
 	p->pkey_group.name  = "pkey_idx";
 	p->pkey_group.attrs =
-		alloc_group_attrs(show_port_pkey, store_port_pkey,
+		alloc_group_attrs(show_port_pkey,
+				  is_eth ? NULL : store_port_pkey,
 				  dev->dev->caps.pkey_table_len[port_num]);
 	if (!p->pkey_group.attrs) {
 		ret = -ENOMEM;