Linux-libre 4.8.2-gnupck-4.8.2-gnu

6 files changed, 289 insertions, 76 deletions

diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index 9f8b516eb..5df63daca 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -288,7 +288,7 @@ static int mlx4_alloc_resize_buf(struct mlx4_ib_dev *dev, struct mlx4_ib_cq *cq,
 	if (cq->resize_buf)
 		return -EBUSY;
 
-	cq->resize_buf = kmalloc(sizeof *cq->resize_buf, GFP_ATOMIC);
+	cq->resize_buf = kmalloc(sizeof *cq->resize_buf, GFP_KERNEL);
 	if (!cq->resize_buf)
 		return -ENOMEM;
 
@@ -316,7 +316,7 @@ static int mlx4_alloc_resize_umem(struct mlx4_ib_dev *dev, struct mlx4_ib_cq *cq
 	if (ib_copy_from_udata(&ucmd, udata, sizeof ucmd))
 		return -EFAULT;
 
-	cq->resize_buf = kmalloc(sizeof *cq->resize_buf, GFP_ATOMIC);
+	cq->resize_buf = kmalloc(sizeof *cq->resize_buf, GFP_KERNEL);
 	if (!cq->resize_buf)
 		return -ENOMEM;
 
@@ -576,8 +576,8 @@ static int mlx4_ib_ipoib_csum_ok(__be16 status, __be16 checksum)
 		checksum == cpu_to_be16(0xffff);
 }
 
-static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct ib_wc *wc,
-			   unsigned tail, struct mlx4_cqe *cqe, int is_eth)
+static void use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct ib_wc *wc,
+			    unsigned tail, struct mlx4_cqe *cqe, int is_eth)
 {
 	struct mlx4_ib_proxy_sqp_hdr *hdr;
 
@@ -600,8 +600,6 @@ static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct
 		wc->slid        = be16_to_cpu(hdr->tun.slid_mac_47_32);
 		wc->sl          = (u8) (be16_to_cpu(hdr->tun.sl_vid) >> 12);
 	}
-
-	return 0;
 }
 
 static void mlx4_ib_qp_sw_comp(struct mlx4_ib_qp *qp, int num_entries,
@@ -689,12 +687,6 @@ repoll:
 	is_error = (cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) ==
 		MLX4_CQE_OPCODE_ERROR;
 
-	if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == MLX4_OPCODE_NOP &&
-		     is_send)) {
-		pr_warn("Completion for NOP opcode detected!\n");
-		return -EINVAL;
-	}
-
 	/* Resize CQ in progress */
 	if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == MLX4_CQE_OPCODE_RESIZE)) {
 		if (cq->resize_buf) {
@@ -720,12 +712,6 @@ repoll:
 		 */
 		mqp = __mlx4_qp_lookup(to_mdev(cq->ibcq.device)->dev,
 				       be32_to_cpu(cqe->vlan_my_qpn));
-		if (unlikely(!mqp)) {
-			pr_warn("CQ %06x with entry for unknown QPN %06x\n",
-			       cq->mcq.cqn, be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_QPN_MASK);
-			return -EINVAL;
-		}
-
 		*cur_qp = to_mibqp(mqp);
 	}
 
@@ -738,11 +724,6 @@ repoll:
 		/* SRQ is also in the radix tree */
 		msrq = mlx4_srq_lookup(to_mdev(cq->ibcq.device)->dev,
 				       srq_num);
-		if (unlikely(!msrq)) {
-			pr_warn("CQ %06x with entry for unknown SRQN %06x\n",
-				cq->mcq.cqn, srq_num);
-			return -EINVAL;
-		}
 	}
 
 	if (is_send) {
@@ -852,9 +833,11 @@ repoll:
 		if (mlx4_is_mfunc(to_mdev(cq->ibcq.device)->dev)) {
 			if ((*cur_qp)->mlx4_ib_qp_type &
 			    (MLX4_IB_QPT_PROXY_SMI_OWNER |
-			     MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI))
-				return use_tunnel_data(*cur_qp, cq, wc, tail,
-						       cqe, is_eth);
+			     MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI)) {
+				use_tunnel_data(*cur_qp, cq, wc, tail, cqe,
+						is_eth);
+				return 0;
+			}
 		}
 
 		wc->slid	   = be16_to_cpu(cqe->rlid);
@@ -891,7 +874,6 @@ int mlx4_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
 	struct mlx4_ib_qp *cur_qp = NULL;
 	unsigned long flags;
 	int npolled;
-	int err = 0;
 	struct mlx4_ib_dev *mdev = to_mdev(cq->ibcq.device);
 
 	spin_lock_irqsave(&cq->lock, flags);
@@ -901,8 +883,7 @@ int mlx4_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
 	}
 
 	for (npolled = 0; npolled < num_entries; ++npolled) {
-		err = mlx4_ib_poll_one(cq, &cur_qp, wc + npolled);
-		if (err)
+		if (mlx4_ib_poll_one(cq, &cur_qp, wc + npolled))
 			break;
 	}
 
@@ -911,10 +892,7 @@ int mlx4_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
 out:
 	spin_unlock_irqrestore(&cq->lock, flags);
 
-	if (err == 0 || err == -EAGAIN)
-		return npolled;
-	else
-		return err;
+	return npolled;
 }
 
 int mlx4_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 9c2e53d28..0f21c3a25 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -1128,6 +1128,27 @@ void handle_port_mgmt_change_event(struct work_struct *work)
 
 		/* Generate GUID changed event */
 		if (changed_attr & MLX4_EQ_PORT_INFO_GID_PFX_CHANGE_MASK) {
+			if (mlx4_is_master(dev->dev)) {
+				union ib_gid gid;
+				int err = 0;
+
+				if (!eqe->event.port_mgmt_change.params.port_info.gid_prefix)
+					err = __mlx4_ib_query_gid(&dev->ib_dev, port, 0, &gid, 1);
+				else
+					gid.global.subnet_prefix =
+						eqe->event.port_mgmt_change.params.port_info.gid_prefix;
+				if (err) {
+					pr_warn("Could not change QP1 subnet prefix for port %d: query_gid error (%d)\n",
+						port, err);
+				} else {
+					pr_debug("Changing QP1 subnet prefix for port %d. old=0x%llx. new=0x%llx\n",
+						 port,
+						 (u64)atomic64_read(&dev->sriov.demux[port - 1].subnet_prefix),
+						 be64_to_cpu(gid.global.subnet_prefix));
+					atomic64_set(&dev->sriov.demux[port - 1].subnet_prefix,
+						     be64_to_cpu(gid.global.subnet_prefix));
+				}
+			}
 			mlx4_ib_dispatch_event(dev, port, IB_EVENT_GID_CHANGE);
 			/*if master, notify all slaves*/
 			if (mlx4_is_master(dev->dev))
@@ -2202,6 +2223,8 @@ int mlx4_ib_init_sriov(struct mlx4_ib_dev *dev)
 		if (err)
 			goto demux_err;
 		dev->sriov.demux[i].guid_cache[0] = gid.global.interface_id;
+		atomic64_set(&dev->sriov.demux[i].subnet_prefix,
+			     be64_to_cpu(gid.global.subnet_prefix));
 		err = alloc_pv_object(dev, mlx4_master_func_num(dev->dev), i + 1,
 				      &dev->sriov.sqps[i]);
 		if (err)
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 42a46078d..87ba9bca4 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -2025,16 +2025,6 @@ static ssize_t show_hca(struct device *device, struct device_attribute *attr,
 	return sprintf(buf, "MT%d\n", dev->dev->persist->pdev->device);
 }
 
-static ssize_t show_fw_ver(struct device *device, struct device_attribute *attr,
-			   char *buf)
-{
-	struct mlx4_ib_dev *dev =
-		container_of(device, struct mlx4_ib_dev, ib_dev.dev);
-	return sprintf(buf, "%d.%d.%d\n", (int) (dev->dev->caps.fw_ver >> 32),
-		       (int) (dev->dev->caps.fw_ver >> 16) & 0xffff,
-		       (int) dev->dev->caps.fw_ver & 0xffff);
-}
-
 static ssize_t show_rev(struct device *device, struct device_attribute *attr,
 			char *buf)
 {
@@ -2053,17 +2043,207 @@ static ssize_t show_board(struct device *device, struct device_attribute *attr,
 }
 
 static DEVICE_ATTR(hw_rev,   S_IRUGO, show_rev,    NULL);
-static DEVICE_ATTR(fw_ver,   S_IRUGO, show_fw_ver, NULL);
 static DEVICE_ATTR(hca_type, S_IRUGO, show_hca,    NULL);
 static DEVICE_ATTR(board_id, S_IRUGO, show_board,  NULL);
 
 static struct device_attribute *mlx4_class_attributes[] = {
 	&dev_attr_hw_rev,
-	&dev_attr_fw_ver,
 	&dev_attr_hca_type,
 	&dev_attr_board_id
 };
 
+struct diag_counter {
+	const char *name;
+	u32 offset;
+};
+
+#define DIAG_COUNTER(_name, _offset)			\
+	{ .name = #_name, .offset = _offset }
+
+static const struct diag_counter diag_basic[] = {
+	DIAG_COUNTER(rq_num_lle, 0x00),
+	DIAG_COUNTER(sq_num_lle, 0x04),
+	DIAG_COUNTER(rq_num_lqpoe, 0x08),
+	DIAG_COUNTER(sq_num_lqpoe, 0x0C),
+	DIAG_COUNTER(rq_num_lpe, 0x18),
+	DIAG_COUNTER(sq_num_lpe, 0x1C),
+	DIAG_COUNTER(rq_num_wrfe, 0x20),
+	DIAG_COUNTER(sq_num_wrfe, 0x24),
+	DIAG_COUNTER(sq_num_mwbe, 0x2C),
+	DIAG_COUNTER(sq_num_bre, 0x34),
+	DIAG_COUNTER(sq_num_rire, 0x44),
+	DIAG_COUNTER(rq_num_rire, 0x48),
+	DIAG_COUNTER(sq_num_rae, 0x4C),
+	DIAG_COUNTER(rq_num_rae, 0x50),
+	DIAG_COUNTER(sq_num_roe, 0x54),
+	DIAG_COUNTER(sq_num_tree, 0x5C),
+	DIAG_COUNTER(sq_num_rree, 0x64),
+	DIAG_COUNTER(rq_num_rnr, 0x68),
+	DIAG_COUNTER(sq_num_rnr, 0x6C),
+	DIAG_COUNTER(rq_num_oos, 0x100),
+	DIAG_COUNTER(sq_num_oos, 0x104),
+};
+
+static const struct diag_counter diag_ext[] = {
+	DIAG_COUNTER(rq_num_dup, 0x130),
+	DIAG_COUNTER(sq_num_to, 0x134),
+};
+
+static const struct diag_counter diag_device_only[] = {
+	DIAG_COUNTER(num_cqovf, 0x1A0),
+	DIAG_COUNTER(rq_num_udsdprd, 0x118),
+};
+
+static struct rdma_hw_stats *mlx4_ib_alloc_hw_stats(struct ib_device *ibdev,
+						    u8 port_num)
+{
+	struct mlx4_ib_dev *dev = to_mdev(ibdev);
+	struct mlx4_ib_diag_counters *diag = dev->diag_counters;
+
+	if (!diag[!!port_num].name)
+		return NULL;
+
+	return rdma_alloc_hw_stats_struct(diag[!!port_num].name,
+					  diag[!!port_num].num_counters,
+					  RDMA_HW_STATS_DEFAULT_LIFESPAN);
+}
+
+static int mlx4_ib_get_hw_stats(struct ib_device *ibdev,
+				struct rdma_hw_stats *stats,
+				u8 port, int index)
+{
+	struct mlx4_ib_dev *dev = to_mdev(ibdev);
+	struct mlx4_ib_diag_counters *diag = dev->diag_counters;
+	u32 hw_value[ARRAY_SIZE(diag_device_only) +
+		ARRAY_SIZE(diag_ext) + ARRAY_SIZE(diag_basic)] = {};
+	int ret;
+	int i;
+
+	ret = mlx4_query_diag_counters(dev->dev,
+				       MLX4_OP_MOD_QUERY_TRANSPORT_CI_ERRORS,
+				       diag[!!port].offset, hw_value,
+				       diag[!!port].num_counters, port);
+
+	if (ret)
+		return ret;
+
+	for (i = 0; i < diag[!!port].num_counters; i++)
+		stats->value[i] = hw_value[i];
+
+	return diag[!!port].num_counters;
+}
+
+static int __mlx4_ib_alloc_diag_counters(struct mlx4_ib_dev *ibdev,
+					 const char ***name,
+					 u32 **offset,
+					 u32 *num,
+					 bool port)
+{
+	u32 num_counters;
+
+	num_counters = ARRAY_SIZE(diag_basic);
+
+	if (ibdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DIAG_PER_PORT)
+		num_counters += ARRAY_SIZE(diag_ext);
+
+	if (!port)
+		num_counters += ARRAY_SIZE(diag_device_only);
+
+	*name = kcalloc(num_counters, sizeof(**name), GFP_KERNEL);
+	if (!*name)
+		return -ENOMEM;
+
+	*offset = kcalloc(num_counters, sizeof(**offset), GFP_KERNEL);
+	if (!*offset)
+		goto err_name;
+
+	*num = num_counters;
+
+	return 0;
+
+err_name:
+	kfree(*name);
+	return -ENOMEM;
+}
+
+static void mlx4_ib_fill_diag_counters(struct mlx4_ib_dev *ibdev,
+				       const char **name,
+				       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;
+		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;
+			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;
+			offset[j] = diag_device_only[i].offset;
+		}
+	}
+}
+
+static int mlx4_ib_alloc_diag_counters(struct mlx4_ib_dev *ibdev)
+{
+	struct mlx4_ib_diag_counters *diag = ibdev->diag_counters;
+	int i;
+	int ret;
+	bool per_port = !!(ibdev->dev->caps.flags2 &
+		MLX4_DEV_CAP_FLAG2_DIAG_PER_PORT);
+
+	if (mlx4_is_slave(ibdev->dev))
+		return 0;
+
+	for (i = 0; i < MLX4_DIAG_COUNTERS_TYPES; i++) {
+		/* i == 1 means we are building port counters */
+		if (i && !per_port)
+			continue;
+
+		ret = __mlx4_ib_alloc_diag_counters(ibdev, &diag[i].name,
+						    &diag[i].offset,
+						    &diag[i].num_counters, i);
+		if (ret)
+			goto err_alloc;
+
+		mlx4_ib_fill_diag_counters(ibdev, diag[i].name,
+					   diag[i].offset, i);
+	}
+
+	ibdev->ib_dev.get_hw_stats	= mlx4_ib_get_hw_stats;
+	ibdev->ib_dev.alloc_hw_stats	= mlx4_ib_alloc_hw_stats;
+
+	return 0;
+
+err_alloc:
+	if (i) {
+		kfree(diag[i - 1].name);
+		kfree(diag[i - 1].offset);
+	}
+
+	return ret;
+}
+
+static void mlx4_ib_diag_cleanup(struct mlx4_ib_dev *ibdev)
+{
+	int i;
+
+	for (i = 0; i < MLX4_DIAG_COUNTERS_TYPES; i++) {
+		kfree(ibdev->diag_counters[i].offset);
+		kfree(ibdev->diag_counters[i].name);
+	}
+}
+
 #define MLX4_IB_INVALID_MAC	((u64)-1)
 static void mlx4_ib_update_qps(struct mlx4_ib_dev *ibdev,
 			       struct net_device *dev,
@@ -2280,6 +2460,17 @@ static int mlx4_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
+static void get_fw_ver_str(struct ib_device *device, char *str,
+			   size_t str_len)
+{
+	struct mlx4_ib_dev *dev =
+		container_of(device, struct mlx4_ib_dev, ib_dev);
+	snprintf(str, str_len, "%d.%d.%d",
+		 (int) (dev->dev->caps.fw_ver >> 32),
+		 (int) (dev->dev->caps.fw_ver >> 16) & 0xffff,
+		 (int) dev->dev->caps.fw_ver & 0xffff);
+}
+
 static void *mlx4_ib_add(struct mlx4_dev *dev)
 {
 	struct mlx4_ib_dev *ibdev;
@@ -2413,6 +2604,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	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.get_dev_fw_str    = get_fw_ver_str;
 	ibdev->ib_dev.disassociate_ucontext = mlx4_ib_disassociate_ucontext;
 
 	if (!mlx4_is_slave(ibdev->dev)) {
@@ -2555,9 +2747,12 @@ 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 (ib_register_device(&ibdev->ib_dev, NULL))
+	if (mlx4_ib_alloc_diag_counters(ibdev))
 		goto err_steer_free_bitmap;
 
+	if (ib_register_device(&ibdev->ib_dev, NULL))
+		goto err_diag_counters;
+
 	if (mlx4_ib_mad_init(ibdev))
 		goto err_reg;
 
@@ -2623,6 +2818,9 @@ err_mad:
 err_reg:
 	ib_unregister_device(&ibdev->ib_dev);
 
+err_diag_counters:
+	mlx4_ib_diag_cleanup(ibdev);
+
 err_steer_free_bitmap:
 	kfree(ibdev->ib_uc_qpns_bitmap);
 
@@ -2726,6 +2924,7 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
 	mlx4_ib_close_sriov(ibdev);
 	mlx4_ib_mad_cleanup(ibdev);
 	ib_unregister_device(&ibdev->ib_dev);
+	mlx4_ib_diag_cleanup(ibdev);
 	if (ibdev->iboe.nb.notifier_call) {
 		if (unregister_netdevice_notifier(&ibdev->iboe.nb))
 			pr_warn("failure unregistering notifier\n");
diff --git a/drivers/infiniband/hw/mlx4/mcg.c b/drivers/infiniband/hw/mlx4/mcg.c
index 8f7ad0791..097bfcc4e 100644
--- a/drivers/infiniband/hw/mlx4/mcg.c
+++ b/drivers/infiniband/hw/mlx4/mcg.c
@@ -489,7 +489,7 @@ static u8 get_leave_state(struct mcast_group *group)
 		if (!group->members[i])
 			leave_state |= (1 << i);
 
-	return leave_state & (group->rec.scope_join_state & 7);
+	return leave_state & (group->rec.scope_join_state & 0xf);
 }
 
 static int join_group(struct mcast_group *group, int slave, u8 join_mask)
@@ -564,8 +564,8 @@ static void mlx4_ib_mcg_timeout_handler(struct work_struct *work)
 		} else
 			mcg_warn_group(group, "DRIVER BUG\n");
 	} else if (group->state == MCAST_LEAVE_SENT) {
-		if (group->rec.scope_join_state & 7)
-			group->rec.scope_join_state &= 0xf8;
+		if (group->rec.scope_join_state & 0xf)
+			group->rec.scope_join_state &= 0xf0;
 		group->state = MCAST_IDLE;
 		mutex_unlock(&group->lock);
 		if (release_group(group, 1))
@@ -605,7 +605,7 @@ static int handle_leave_req(struct mcast_group *group, u8 leave_mask,
 static int handle_join_req(struct mcast_group *group, u8 join_mask,
 			   struct mcast_req *req)
 {
-	u8 group_join_state = group->rec.scope_join_state & 7;
+	u8 group_join_state = group->rec.scope_join_state & 0xf;
 	int ref = 0;
 	u16 status;
 	struct ib_sa_mcmember_data *sa_data = (struct ib_sa_mcmember_data *)req->sa_mad.data;
@@ -690,8 +690,8 @@ static void mlx4_ib_mcg_work_handler(struct work_struct *work)
 			u8 cur_join_state;
 
 			resp_join_state = ((struct ib_sa_mcmember_data *)
-						group->response_sa_mad.data)->scope_join_state & 7;
-			cur_join_state = group->rec.scope_join_state & 7;
+						group->response_sa_mad.data)->scope_join_state & 0xf;
+			cur_join_state = group->rec.scope_join_state & 0xf;
 
 			if (method == IB_MGMT_METHOD_GET_RESP) {
 				/* successfull join */
@@ -710,7 +710,7 @@ process_requests:
 		req = list_first_entry(&group->pending_list, struct mcast_req,
 				       group_list);
 		sa_data = (struct ib_sa_mcmember_data *)req->sa_mad.data;
-		req_join_state = sa_data->scope_join_state & 0x7;
+		req_join_state = sa_data->scope_join_state & 0xf;
 
 		/* For a leave request, we will immediately answer the VF, and
 		 * update our internal counters. The actual leave will be sent
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 29acda249..686ab48ff 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -448,7 +448,7 @@ struct mlx4_ib_demux_ctx {
 	struct workqueue_struct *wq;
 	struct workqueue_struct *ud_wq;
 	spinlock_t ud_lock;
-	__be64 subnet_prefix;
+	atomic64_t subnet_prefix;
 	__be64 guid_cache[128];
 	struct mlx4_ib_dev *dev;
 	/* the following lock protects both mcg_table and mcg_mgid0_list */
@@ -549,6 +549,14 @@ struct mlx4_ib_counters {
 	u32			default_counter;
 };
 
+#define MLX4_DIAG_COUNTERS_TYPES 2
+
+struct mlx4_ib_diag_counters {
+	const char **name;
+	u32 *offset;
+	u32 num_counters;
+};
+
 struct mlx4_ib_dev {
 	struct ib_device	ib_dev;
 	struct mlx4_dev	       *dev;
@@ -585,6 +593,7 @@ struct mlx4_ib_dev {
 	/* protect resources needed as part of reset flow */
 	spinlock_t		reset_flow_resource_lock;
 	struct list_head		qp_list;
+	struct mlx4_ib_diag_counters diag_counters[MLX4_DIAG_COUNTERS_TYPES];
 };
 
 struct ib_event_work {
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 8db8405c1..7fb9629bd 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -232,7 +232,7 @@ static void stamp_send_wqe(struct mlx4_ib_qp *qp, int n, int size)
 		}
 	} else {
 		ctrl = buf = get_send_wqe(qp, n & (qp->sq.wqe_cnt - 1));
-		s = (ctrl->fence_size & 0x3f) << 4;
+		s = (ctrl->qpn_vlan.fence_size & 0x3f) << 4;
 		for (i = 64; i < s; i += 64) {
 			wqe = buf + i;
 			*wqe = cpu_to_be32(0xffffffff);
@@ -264,7 +264,7 @@ static void post_nop_wqe(struct mlx4_ib_qp *qp, int n, int size)
 		inl->byte_count = cpu_to_be32(1 << 31 | (size - s - sizeof *inl));
 	}
 	ctrl->srcrb_flags = 0;
-	ctrl->fence_size = size / 16;
+	ctrl->qpn_vlan.fence_size = size / 16;
 	/*
 	 * Make sure descriptor is fully written before setting ownership bit
 	 * (because HW can start executing as soon as we do).
@@ -1992,7 +1992,8 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 			ctrl = get_send_wqe(qp, i);
 			ctrl->owner_opcode = cpu_to_be32(1 << 31);
 			if (qp->sq_max_wqes_per_wr == 1)
-				ctrl->fence_size = 1 << (qp->sq.wqe_shift - 4);
+				ctrl->qpn_vlan.fence_size =
+						1 << (qp->sq.wqe_shift - 4);
 
 			stamp_send_wqe(qp, i, 1 << qp->sq.wqe_shift);
 		}
@@ -2492,24 +2493,27 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_ud_wr *wr,
 		sqp->ud_header.grh.flow_label    =
 			ah->av.ib.sl_tclass_flowlabel & cpu_to_be32(0xfffff);
 		sqp->ud_header.grh.hop_limit     = ah->av.ib.hop_limit;
-		if (is_eth)
+		if (is_eth) {
 			memcpy(sqp->ud_header.grh.source_gid.raw, sgid.raw, 16);
-		else {
-		if (mlx4_is_mfunc(to_mdev(ib_dev)->dev)) {
-			/* When multi-function is enabled, the ib_core gid
-			 * indexes don't necessarily match the hw ones, so
-			 * we must use our own cache */
-			sqp->ud_header.grh.source_gid.global.subnet_prefix =
-				to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1].
-						       subnet_prefix;
-			sqp->ud_header.grh.source_gid.global.interface_id =
-				to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1].
-					       guid_cache[ah->av.ib.gid_index];
-		} else
-			ib_get_cached_gid(ib_dev,
-					  be32_to_cpu(ah->av.ib.port_pd) >> 24,
-					  ah->av.ib.gid_index,
-					  &sqp->ud_header.grh.source_gid, NULL);
+		} else {
+			if (mlx4_is_mfunc(to_mdev(ib_dev)->dev)) {
+				/* When multi-function is enabled, the ib_core gid
+				 * indexes don't necessarily match the hw ones, so
+				 * we must use our own cache
+				 */
+				sqp->ud_header.grh.source_gid.global.subnet_prefix =
+					cpu_to_be64(atomic64_read(&(to_mdev(ib_dev)->sriov.
+								    demux[sqp->qp.port - 1].
+								    subnet_prefix)));
+				sqp->ud_header.grh.source_gid.global.interface_id =
+					to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1].
+						       guid_cache[ah->av.ib.gid_index];
+			} else {
+				ib_get_cached_gid(ib_dev,
+						  be32_to_cpu(ah->av.ib.port_pd) >> 24,
+						  ah->av.ib.gid_index,
+						  &sqp->ud_header.grh.source_gid, NULL);
+			}
 		}
 		memcpy(sqp->ud_header.grh.destination_gid.raw,
 		       ah->av.ib.dgid, 16);
@@ -3169,8 +3173,8 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		wmb();
 		*lso_wqe = lso_hdr_sz;
 
-		ctrl->fence_size = (wr->send_flags & IB_SEND_FENCE ?
-				    MLX4_WQE_CTRL_FENCE : 0) | size;
+		ctrl->qpn_vlan.fence_size = (wr->send_flags & IB_SEND_FENCE ?
+					     MLX4_WQE_CTRL_FENCE : 0) | size;
 
 		/*
 		 * Make sure descriptor is fully written before