1 files changed, 431 insertions, 231 deletions

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 1aaa2056d188..abac70ad5c7c 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -156,6 +156,34 @@ static int get_port_state(struct ib_device *ibdev,
 	return ret;
 }
 
+static struct mlx5_roce *mlx5_get_rep_roce(struct mlx5_ib_dev *dev,
+					   struct net_device *ndev,
+					   u8 *port_num)
+{
+	struct mlx5_eswitch *esw = dev->mdev->priv.eswitch;
+	struct net_device *rep_ndev;
+	struct mlx5_ib_port *port;
+	int i;
+
+	for (i = 0; i < dev->num_ports; i++) {
+		port  = &dev->port[i];
+		if (!port->rep)
+			continue;
+
+		read_lock(&port->roce.netdev_lock);
+		rep_ndev = mlx5_ib_get_rep_netdev(esw,
+						  port->rep->vport);
+		if (rep_ndev == ndev) {
+			read_unlock(&port->roce.netdev_lock);
+			*port_num = i + 1;
+			return &port->roce;
+		}
+		read_unlock(&port->roce.netdev_lock);
+	}
+
+	return NULL;
+}
+
 static int mlx5_netdev_event(struct notifier_block *this,
 			     unsigned long event, void *ptr)
 {
@@ -172,22 +200,17 @@ static int mlx5_netdev_event(struct notifier_block *this,
 
 	switch (event) {
 	case NETDEV_REGISTER:
+		/* Should already be registered during the load */
+		if (ibdev->is_rep)
+			break;
 		write_lock(&roce->netdev_lock);
-		if (ibdev->rep) {
-			struct mlx5_eswitch *esw = ibdev->mdev->priv.eswitch;
-			struct net_device *rep_ndev;
-
-			rep_ndev = mlx5_ib_get_rep_netdev(esw,
-							  ibdev->rep->vport);
-			if (rep_ndev == ndev)
-				roce->netdev = ndev;
-		} else if (ndev->dev.parent == mdev->device) {
+		if (ndev->dev.parent == mdev->device)
 			roce->netdev = ndev;
-		}
 		write_unlock(&roce->netdev_lock);
 		break;
 
 	case NETDEV_UNREGISTER:
+		/* In case of reps, ib device goes away before the netdevs */
 		write_lock(&roce->netdev_lock);
 		if (roce->netdev == ndev)
 			roce->netdev = NULL;
@@ -205,6 +228,10 @@ static int mlx5_netdev_event(struct notifier_block *this,
 			dev_put(lag_ndev);
 		}
 
+		if (ibdev->is_rep)
+			roce = mlx5_get_rep_roce(ibdev, ndev, &port_num);
+		if (!roce)
+			return NOTIFY_DONE;
 		if ((upper == ndev || (!upper && ndev == roce->netdev))
 		    && ibdev->ib_active) {
 			struct ib_event ibev = { };
@@ -257,11 +284,11 @@ static struct net_device *mlx5_ib_get_netdev(struct ib_device *device,
 
 	/* Ensure ndev does not disappear before we invoke dev_hold()
 	 */
-	read_lock(&ibdev->roce[port_num - 1].netdev_lock);
-	ndev = ibdev->roce[port_num - 1].netdev;
+	read_lock(&ibdev->port[port_num - 1].roce.netdev_lock);
+	ndev = ibdev->port[port_num - 1].roce.netdev;
 	if (ndev)
 		dev_hold(ndev);
-	read_unlock(&ibdev->roce[port_num - 1].netdev_lock);
+	read_unlock(&ibdev->port[port_num - 1].roce.netdev_lock);
 
 out:
 	mlx5_ib_put_native_port_mdev(ibdev, port_num);
@@ -479,9 +506,14 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 
 	/* Possible bad flows are checked before filling out props so in case
 	 * of an error it will still be zeroed out.
+	 * Use native port in case of reps
 	 */
-	err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN,
-				   mdev_port_num);
+	if (dev->is_rep)
+		err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN,
+					   1);
+	else
+		err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN,
+					   mdev_port_num);
 	if (err)
 		goto out;
 	ext = MLX5_CAP_PCAM_FEATURE(dev->mdev, ptys_extended_ethernet);
@@ -542,52 +574,22 @@ out:
 	return err;
 }
 
-struct mlx5_ib_vlan_info {
-	u16 vlan_id;
-	bool vlan;
-};
-
-static int get_lower_dev_vlan(struct net_device *lower_dev, void *data)
-{
-	struct mlx5_ib_vlan_info *vlan_info = data;
-
-	if (is_vlan_dev(lower_dev)) {
-		vlan_info->vlan = true;
-		vlan_info->vlan_id = vlan_dev_vlan_id(lower_dev);
-	}
-	/* We are interested only in first level vlan device, so
-	 * always return 1 to stop iterating over next level devices.
-	 */
-	return 1;
-}
-
 static int set_roce_addr(struct mlx5_ib_dev *dev, u8 port_num,
 			 unsigned int index, const union ib_gid *gid,
 			 const struct ib_gid_attr *attr)
 {
 	enum ib_gid_type gid_type = IB_GID_TYPE_IB;
-	struct mlx5_ib_vlan_info vlan_info = { };
+	u16 vlan_id = 0xffff;
 	u8 roce_version = 0;
 	u8 roce_l3_type = 0;
 	u8 mac[ETH_ALEN];
+	int ret;
 
 	if (gid) {
 		gid_type = attr->gid_type;
-		ether_addr_copy(mac, attr->ndev->dev_addr);
-
-		if (is_vlan_dev(attr->ndev)) {
-			vlan_info.vlan = true;
-			vlan_info.vlan_id = vlan_dev_vlan_id(attr->ndev);
-		} else {
-			/* If the netdev is upper device and if it's lower
-			 * lower device is vlan device, consider vlan id of
-			 * the lower vlan device for this gid entry.
-			 */
-			rcu_read_lock();
-			netdev_walk_all_lower_dev_rcu(attr->ndev,
-					get_lower_dev_vlan, &vlan_info);
-			rcu_read_unlock();
-		}
+		ret = rdma_read_gid_l2_fields(attr, &vlan_id, &mac[0]);
+		if (ret)
+			return ret;
 	}
 
 	switch (gid_type) {
@@ -608,7 +610,7 @@ static int set_roce_addr(struct mlx5_ib_dev *dev, u8 port_num,
 
 	return mlx5_core_roce_gid_set(dev->mdev, index, roce_version,
 				      roce_l3_type, gid->raw, mac,
-				      vlan_info.vlan, vlan_info.vlan_id,
+				      vlan_id < VLAN_CFI_MASK, vlan_id,
 				      port_num);
 }
 
@@ -1407,7 +1409,9 @@ static int mlx5_ib_rep_query_port(struct ib_device *ibdev, u8 port,
 {
 	int ret;
 
-	/* Only link layer == ethernet is valid for representors */
+	/* Only link layer == ethernet is valid for representors
+	 * and we always use port 1
+	 */
 	ret = mlx5_query_port_roce(ibdev, port, props);
 	if (ret || !props)
 		return ret;
@@ -1954,11 +1958,11 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx,
 	print_lib_caps(dev, context->lib_caps);
 
 	if (dev->lag_active) {
-		u8 port = mlx5_core_native_port_num(dev->mdev);
+		u8 port = mlx5_core_native_port_num(dev->mdev) - 1;
 
 		atomic_set(&context->tx_port_affinity,
 			   atomic_add_return(
-				   1, &dev->roce[port].tx_port_affinity));
+				   1, &dev->port[port].roce.tx_port_affinity));
 	}
 
 	return 0;
@@ -2060,21 +2064,22 @@ static int mlx5_ib_mmap_clock_info_page(struct mlx5_ib_dev *dev,
 					struct vm_area_struct *vma,
 					struct mlx5_ib_ucontext *context)
 {
-	if (vma->vm_end - vma->vm_start != PAGE_SIZE)
+	if ((vma->vm_end - vma->vm_start != PAGE_SIZE) ||
+	    !(vma->vm_flags & VM_SHARED))
 		return -EINVAL;
 
 	if (get_index(vma->vm_pgoff) != MLX5_IB_CLOCK_INFO_V1)
 		return -EOPNOTSUPP;
 
-	if (vma->vm_flags & VM_WRITE)
+	if (vma->vm_flags & (VM_WRITE | VM_EXEC))
 		return -EPERM;
 	vma->vm_flags &= ~VM_MAYWRITE;
 
-	if (!dev->mdev->clock_info_page)
+	if (!dev->mdev->clock_info)
 		return -EOPNOTSUPP;
 
-	return rdma_user_mmap_page(&context->ibucontext, vma,
-				   dev->mdev->clock_info_page, PAGE_SIZE);
+	return vm_insert_page(vma, vma->vm_start,
+			      virt_to_page(dev->mdev->clock_info));
 }
 
 static int uar_mmap(struct mlx5_ib_dev *dev, enum mlx5_ib_mmap_cmd cmd,
@@ -2259,89 +2264,200 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm
 	return 0;
 }
 
-struct ib_dm *mlx5_ib_alloc_dm(struct ib_device *ibdev,
-			       struct ib_ucontext *context,
-			       struct ib_dm_alloc_attr *attr,
-			       struct uverbs_attr_bundle *attrs)
+static inline int check_dm_type_support(struct mlx5_ib_dev *dev,
+					u32 type)
 {
-	u64 act_size = roundup(attr->length, MLX5_MEMIC_BASE_SIZE);
-	struct mlx5_memic *memic = &to_mdev(ibdev)->memic;
-	phys_addr_t memic_addr;
-	struct mlx5_ib_dm *dm;
+	switch (type) {
+	case MLX5_IB_UAPI_DM_TYPE_MEMIC:
+		if (!MLX5_CAP_DEV_MEM(dev->mdev, memic))
+			return -EOPNOTSUPP;
+		break;
+	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
+		if (!capable(CAP_SYS_RAWIO) ||
+		    !capable(CAP_NET_RAW))
+			return -EPERM;
+
+		if (!(MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev, sw_owner) ||
+		      MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev, sw_owner)))
+			return -EOPNOTSUPP;
+		break;
+	}
+
+	return 0;
+}
+
+static int handle_alloc_dm_memic(struct ib_ucontext *ctx,
+				 struct mlx5_ib_dm *dm,
+				 struct ib_dm_alloc_attr *attr,
+				 struct uverbs_attr_bundle *attrs)
+{
+	struct mlx5_dm *dm_db = &to_mdev(ctx->device)->dm;
 	u64 start_offset;
 	u32 page_idx;
 	int err;
 
-	dm = kzalloc(sizeof(*dm), GFP_KERNEL);
-	if (!dm)
-		return ERR_PTR(-ENOMEM);
-
-	mlx5_ib_dbg(to_mdev(ibdev), "alloc_memic req: user_length=0x%llx act_length=0x%llx log_alignment=%d\n",
-		    attr->length, act_size, attr->alignment);
+	dm->size = roundup(attr->length, MLX5_MEMIC_BASE_SIZE);
 
-	err = mlx5_cmd_alloc_memic(memic, &memic_addr,
-				   act_size, attr->alignment);
+	err = mlx5_cmd_alloc_memic(dm_db, &dm->dev_addr,
+				   dm->size, attr->alignment);
 	if (err)
-		goto err_free;
+		return err;
 
-	start_offset = memic_addr & ~PAGE_MASK;
-	page_idx = (memic_addr - memic->dev->bar_addr -
-		    MLX5_CAP64_DEV_MEM(memic->dev, memic_bar_start_addr)) >>
+	page_idx = (dm->dev_addr - pci_resource_start(dm_db->dev->pdev, 0) -
+		    MLX5_CAP64_DEV_MEM(dm_db->dev, memic_bar_start_addr)) >>
 		    PAGE_SHIFT;
 
 	err = uverbs_copy_to(attrs,
+			     MLX5_IB_ATTR_ALLOC_DM_RESP_PAGE_INDEX,
+			     &page_idx, sizeof(page_idx));
+	if (err)
+		goto err_dealloc;
+
+	start_offset = dm->dev_addr & ~PAGE_MASK;
+	err = uverbs_copy_to(attrs,
 			     MLX5_IB_ATTR_ALLOC_DM_RESP_START_OFFSET,
 			     &start_offset, sizeof(start_offset));
 	if (err)
 		goto err_dealloc;
 
+	bitmap_set(to_mucontext(ctx)->dm_pages, page_idx,
+		   DIV_ROUND_UP(dm->size, PAGE_SIZE));
+
+	return 0;
+
+err_dealloc:
+	mlx5_cmd_dealloc_memic(dm_db, dm->dev_addr, dm->size);
+
+	return err;
+}
+
+static int handle_alloc_dm_sw_icm(struct ib_ucontext *ctx,
+				  struct mlx5_ib_dm *dm,
+				  struct ib_dm_alloc_attr *attr,
+				  struct uverbs_attr_bundle *attrs,
+				  int type)
+{
+	struct mlx5_dm *dm_db = &to_mdev(ctx->device)->dm;
+	u64 act_size;
+	int err;
+
+	/* Allocation size must a multiple of the basic block size
+	 * and a power of 2.
+	 */
+	act_size = roundup(attr->length, MLX5_SW_ICM_BLOCK_SIZE(dm_db->dev));
+	act_size = roundup_pow_of_two(act_size);
+
+	dm->size = act_size;
+	err = mlx5_cmd_alloc_sw_icm(dm_db, type, act_size,
+				    to_mucontext(ctx)->devx_uid, &dm->dev_addr,
+				    &dm->icm_dm.obj_id);
+	if (err)
+		return err;
+
 	err = uverbs_copy_to(attrs,
-			     MLX5_IB_ATTR_ALLOC_DM_RESP_PAGE_INDEX,
-			     &page_idx, sizeof(page_idx));
+			     MLX5_IB_ATTR_ALLOC_DM_RESP_START_OFFSET,
+			     &dm->dev_addr, sizeof(dm->dev_addr));
 	if (err)
-		goto err_dealloc;
+		mlx5_cmd_dealloc_sw_icm(dm_db, type, dm->size,
+					to_mucontext(ctx)->devx_uid,
+					dm->dev_addr, dm->icm_dm.obj_id);
+
+	return err;
+}
+
+struct ib_dm *mlx5_ib_alloc_dm(struct ib_device *ibdev,
+			       struct ib_ucontext *context,
+			       struct ib_dm_alloc_attr *attr,
+			       struct uverbs_attr_bundle *attrs)
+{
+	struct mlx5_ib_dm *dm;
+	enum mlx5_ib_uapi_dm_type type;
+	int err;
 
-	bitmap_set(to_mucontext(context)->dm_pages, page_idx,
-		   DIV_ROUND_UP(act_size, PAGE_SIZE));
+	err = uverbs_get_const_default(&type, attrs,
+				       MLX5_IB_ATTR_ALLOC_DM_REQ_TYPE,
+				       MLX5_IB_UAPI_DM_TYPE_MEMIC);
+	if (err)
+		return ERR_PTR(err);
 
-	dm->dev_addr = memic_addr;
+	mlx5_ib_dbg(to_mdev(ibdev), "alloc_dm req: dm_type=%d user_length=0x%llx log_alignment=%d\n",
+		    type, attr->length, attr->alignment);
+
+	err = check_dm_type_support(to_mdev(ibdev), type);
+	if (err)
+		return ERR_PTR(err);
+
+	dm = kzalloc(sizeof(*dm), GFP_KERNEL);
+	if (!dm)
+		return ERR_PTR(-ENOMEM);
+
+	dm->type = type;
+
+	switch (type) {
+	case MLX5_IB_UAPI_DM_TYPE_MEMIC:
+		err = handle_alloc_dm_memic(context, dm,
+					    attr,
+					    attrs);
+		break;
+	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
+	case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM:
+		err = handle_alloc_dm_sw_icm(context, dm, attr, attrs, type);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+	}
+
+	if (err)
+		goto err_free;
 
 	return &dm->ibdm;
 
-err_dealloc:
-	mlx5_cmd_dealloc_memic(memic, memic_addr,
-			       act_size);
 err_free:
 	kfree(dm);
 	return ERR_PTR(err);
 }
 
-int mlx5_ib_dealloc_dm(struct ib_dm *ibdm)
+int mlx5_ib_dealloc_dm(struct ib_dm *ibdm, struct uverbs_attr_bundle *attrs)
 {
-	struct mlx5_memic *memic = &to_mdev(ibdm->device)->memic;
+	struct mlx5_ib_ucontext *ctx = rdma_udata_to_drv_context(
+		&attrs->driver_udata, struct mlx5_ib_ucontext, ibucontext);
+	struct mlx5_dm *dm_db = &to_mdev(ibdm->device)->dm;
 	struct mlx5_ib_dm *dm = to_mdm(ibdm);
-	u64 act_size = roundup(dm->ibdm.length, MLX5_MEMIC_BASE_SIZE);
 	u32 page_idx;
 	int ret;
 
-	ret = mlx5_cmd_dealloc_memic(memic, dm->dev_addr, act_size);
-	if (ret)
-		return ret;
+	switch (dm->type) {
+	case MLX5_IB_UAPI_DM_TYPE_MEMIC:
+		ret = mlx5_cmd_dealloc_memic(dm_db, dm->dev_addr, dm->size);
+		if (ret)
+			return ret;
 
-	page_idx = (dm->dev_addr - memic->dev->bar_addr -
-		    MLX5_CAP64_DEV_MEM(memic->dev, memic_bar_start_addr)) >>
-		    PAGE_SHIFT;
-	bitmap_clear(to_mucontext(ibdm->uobject->context)->dm_pages,
-		     page_idx,
-		     DIV_ROUND_UP(act_size, PAGE_SIZE));
+		page_idx = (dm->dev_addr -
+			    pci_resource_start(dm_db->dev->pdev, 0) -
+			    MLX5_CAP64_DEV_MEM(dm_db->dev,
+					       memic_bar_start_addr)) >>
+			   PAGE_SHIFT;
+		bitmap_clear(ctx->dm_pages, page_idx,
+			     DIV_ROUND_UP(dm->size, PAGE_SIZE));
+		break;
+	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
+	case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM:
+		ret = mlx5_cmd_dealloc_sw_icm(dm_db, dm->type, dm->size,
+					      ctx->devx_uid, dm->dev_addr,
+					      dm->icm_dm.obj_id);
+		if (ret)
+			return ret;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
 
 	kfree(dm);
 
 	return 0;
 }
 
-static int mlx5_ib_alloc_pd(struct ib_pd *ibpd, struct ib_ucontext *context,
-			    struct ib_udata *udata)
+static int mlx5_ib_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 {
 	struct mlx5_ib_pd *pd = to_mpd(ibpd);
 	struct ib_device *ibdev = ibpd->device;
@@ -2350,8 +2466,10 @@ static int mlx5_ib_alloc_pd(struct ib_pd *ibpd, struct ib_ucontext *context,
 	u32 out[MLX5_ST_SZ_DW(alloc_pd_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(alloc_pd_in)]   = {};
 	u16 uid = 0;
+	struct mlx5_ib_ucontext *context = rdma_udata_to_drv_context(
+		udata, struct mlx5_ib_ucontext, ibucontext);
 
-	uid = context ? to_mucontext(context)->devx_uid : 0;
+	uid = context ? context->devx_uid : 0;
 	MLX5_SET(alloc_pd_in, in, opcode, MLX5_CMD_OP_ALLOC_PD);
 	MLX5_SET(alloc_pd_in, in, uid, uid);
 	err = mlx5_cmd_exec(to_mdev(ibdev)->mdev, in, sizeof(in),
@@ -2361,7 +2479,7 @@ static int mlx5_ib_alloc_pd(struct ib_pd *ibpd, struct ib_ucontext *context,
 
 	pd->pdn = MLX5_GET(alloc_pd_out, out, pd);
 	pd->uid = uid;
-	if (context) {
+	if (udata) {
 		resp.pdn = pd->pdn;
 		if (ib_copy_to_udata(udata, &resp, sizeof(resp))) {
 			mlx5_cmd_dealloc_pd(to_mdev(ibdev)->mdev, pd->pdn, uid);
@@ -2372,7 +2490,7 @@ static int mlx5_ib_alloc_pd(struct ib_pd *ibpd, struct ib_ucontext *context,
 	return 0;
 }
 
-static void mlx5_ib_dealloc_pd(struct ib_pd *pd)
+static void mlx5_ib_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
 {
 	struct mlx5_ib_dev *mdev = to_mdev(pd->device);
 	struct mlx5_ib_pd *mpd = to_mpd(pd);
@@ -3151,10 +3269,10 @@ static struct mlx5_ib_flow_prio *get_flow_table(struct mlx5_ib_dev *dev,
 		if (ft_type == MLX5_IB_FT_RX) {
 			fn_type = MLX5_FLOW_NAMESPACE_BYPASS;
 			prio = &dev->flow_db->prios[priority];
-			if (!dev->rep &&
+			if (!dev->is_rep &&
 			    MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev, decap))
 				flags |= MLX5_FLOW_TABLE_TUNNEL_EN_DECAP;
-			if (!dev->rep &&
+			if (!dev->is_rep &&
 			    MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev,
 					reformat_l3_tunnel_to_l2))
 				flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
@@ -3164,7 +3282,7 @@ static struct mlx5_ib_flow_prio *get_flow_table(struct mlx5_ib_dev *dev,
 							      log_max_ft_size));
 			fn_type = MLX5_FLOW_NAMESPACE_EGRESS;
 			prio = &dev->flow_db->egress_prios[priority];
-			if (!dev->rep &&
+			if (!dev->is_rep &&
 			    MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev, reformat))
 				flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
 		}
@@ -3197,12 +3315,11 @@ static struct mlx5_ib_flow_prio *get_flow_table(struct mlx5_ib_dev *dev,
 	if (!ns)
 		return ERR_PTR(-ENOTSUPP);
 
-	if (num_entries > max_table_size)
-		return ERR_PTR(-ENOMEM);
+	max_table_size = min_t(int, num_entries, max_table_size);
 
 	ft = prio->flow_table;
 	if (!ft)
-		return _get_prio(ns, prio, priority, num_entries, num_groups,
+		return _get_prio(ns, prio, priority, max_table_size, num_groups,
 				 flags);
 
 	return prio;
@@ -3370,7 +3487,7 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 	if (!is_valid_attr(dev->mdev, flow_attr))
 		return ERR_PTR(-EINVAL);
 
-	if (dev->rep && is_egress)
+	if (dev->is_rep && is_egress)
 		return ERR_PTR(-EINVAL);
 
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
@@ -3401,13 +3518,17 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 	if (!flow_is_multicast_only(flow_attr))
 		set_underlay_qp(dev, spec, underlay_qpn);
 
-	if (dev->rep) {
+	if (dev->is_rep) {
 		void *misc;
 
+		if (!dev->port[flow_attr->port - 1].rep) {
+			err = -EINVAL;
+			goto free;
+		}
 		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				    misc_parameters);
 		MLX5_SET(fte_match_set_misc, misc, source_port,
-			 dev->rep->vport);
+			 dev->port[flow_attr->port - 1].rep->vport);
 		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
 				    misc_parameters);
 		MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
@@ -3769,11 +3890,16 @@ _get_flow_table(struct mlx5_ib_dev *dev,
 		bool mcast)
 {
 	struct mlx5_flow_namespace *ns = NULL;
-	struct mlx5_ib_flow_prio *prio;
-	int max_table_size;
+	struct mlx5_ib_flow_prio *prio = NULL;
+	int max_table_size = 0;
 	u32 flags = 0;
 	int priority;
 
+	if (mcast)
+		priority = MLX5_IB_FLOW_MCAST_PRIO;
+	else
+		priority = ib_prio_to_core_prio(fs_matcher->priority, false);
+
 	if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_BYPASS) {
 		max_table_size = BIT(MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev,
 					log_max_ft_size));
@@ -3782,20 +3908,18 @@ _get_flow_table(struct mlx5_ib_dev *dev,
 		if (MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev,
 					      reformat_l3_tunnel_to_l2))
 			flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
-	} else { /* Can only be MLX5_FLOW_NAMESPACE_EGRESS */
-		max_table_size = BIT(MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev,
-					log_max_ft_size));
+	} else if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_EGRESS) {
+		max_table_size = BIT(
+			MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev, log_max_ft_size));
 		if (MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev, reformat))
 			flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
+	} else if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB) {
+		max_table_size = BIT(
+			MLX5_CAP_ESW_FLOWTABLE_FDB(dev->mdev, log_max_ft_size));
+		priority = FDB_BYPASS_PATH;
 	}
 
-	if (max_table_size < MLX5_FS_MAX_ENTRIES)
-		return ERR_PTR(-ENOMEM);
-
-	if (mcast)
-		priority = MLX5_IB_FLOW_MCAST_PRIO;
-	else
-		priority = ib_prio_to_core_prio(fs_matcher->priority, false);
+	max_table_size = min_t(int, max_table_size, MLX5_FS_MAX_ENTRIES);
 
 	ns = mlx5_get_flow_namespace(dev->mdev, fs_matcher->ns_type);
 	if (!ns)
@@ -3803,13 +3927,18 @@ _get_flow_table(struct mlx5_ib_dev *dev,
 
 	if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_BYPASS)
 		prio = &dev->flow_db->prios[priority];
-	else
+	else if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_EGRESS)
 		prio = &dev->flow_db->egress_prios[priority];
+	else if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB)
+		prio = &dev->flow_db->fdb;
+
+	if (!prio)
+		return ERR_PTR(-EINVAL);
 
 	if (prio->flow_table)
 		return prio;
 
-	return _get_prio(ns, prio, priority, MLX5_FS_MAX_ENTRIES,
+	return _get_prio(ns, prio, priority, max_table_size,
 			 MLX5_FS_MAX_TYPES, flags);
 }
 
@@ -4509,7 +4638,7 @@ static int set_has_smi_cap(struct mlx5_ib_dev *dev)
 	int err;
 	int port;
 
-	for (port = 1; port <= dev->num_ports; port++) {
+	for (port = 1; port <= ARRAY_SIZE(dev->mdev->port_caps); port++) {
 		dev->mdev->port_caps[port - 1].has_smi = false;
 		if (MLX5_CAP_GEN(dev->mdev, port_type) ==
 		    MLX5_CAP_PORT_TYPE_IB) {
@@ -4540,7 +4669,7 @@ static void get_ext_port_caps(struct mlx5_ib_dev *dev)
 		mlx5_query_ext_port_caps(dev, port);
 }
 
-static int get_port_caps(struct mlx5_ib_dev *dev, u8 port)
+static int __get_port_caps(struct mlx5_ib_dev *dev, u8 port)
 {
 	struct ib_device_attr *dprops = NULL;
 	struct ib_port_attr *pprops = NULL;
@@ -4555,10 +4684,6 @@ static int get_port_caps(struct mlx5_ib_dev *dev, u8 port)
 	if (!dprops)
 		goto out;
 
-	err = set_has_smi_cap(dev);
-	if (err)
-		goto out;
-
 	err = mlx5_ib_query_device(&dev->ib_dev, dprops, &uhw);
 	if (err) {
 		mlx5_ib_warn(dev, "query_device failed %d\n", err);
@@ -4587,6 +4712,16 @@ out:
 	return err;
 }
 
+static int get_port_caps(struct mlx5_ib_dev *dev, u8 port)
+{
+	/* For representors use port 1, is this is the only native
+	 * port
+	 */
+	if (dev->is_rep)
+		return __get_port_caps(dev, 1);
+	return __get_port_caps(dev, port);
+}
+
 static void destroy_umrc_res(struct mlx5_ib_dev *dev)
 {
 	int err;
@@ -4596,7 +4731,7 @@ static void destroy_umrc_res(struct mlx5_ib_dev *dev)
 		mlx5_ib_warn(dev, "mr cache cleanup failed\n");
 
 	if (dev->umrc.qp)
-		mlx5_ib_destroy_qp(dev->umrc.qp);
+		mlx5_ib_destroy_qp(dev->umrc.qp, NULL);
 	if (dev->umrc.cq)
 		ib_free_cq(dev->umrc.cq);
 	if (dev->umrc.pd)
@@ -4701,7 +4836,7 @@ static int create_umr_res(struct mlx5_ib_dev *dev)
 	return 0;
 
 error_4:
-	mlx5_ib_destroy_qp(qp);
+	mlx5_ib_destroy_qp(qp, NULL);
 	dev->umrc.qp = NULL;
 
 error_3:
@@ -4752,11 +4887,11 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 	devr->p0->uobject = NULL;
 	atomic_set(&devr->p0->usecnt, 0);
 
-	ret = mlx5_ib_alloc_pd(devr->p0, NULL, NULL);
+	ret = mlx5_ib_alloc_pd(devr->p0, NULL);
 	if (ret)
 		goto error0;
 
-	devr->c0 = mlx5_ib_create_cq(&dev->ib_dev, &cq_attr, NULL, NULL);
+	devr->c0 = mlx5_ib_create_cq(&dev->ib_dev, &cq_attr, NULL);
 	if (IS_ERR(devr->c0)) {
 		ret = PTR_ERR(devr->c0);
 		goto error1;
@@ -4768,7 +4903,7 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 	devr->c0->cq_context    = NULL;
 	atomic_set(&devr->c0->usecnt, 0);
 
-	devr->x0 = mlx5_ib_alloc_xrcd(&dev->ib_dev, NULL, NULL);
+	devr->x0 = mlx5_ib_alloc_xrcd(&dev->ib_dev, NULL);
 	if (IS_ERR(devr->x0)) {
 		ret = PTR_ERR(devr->x0);
 		goto error2;
@@ -4779,7 +4914,7 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 	mutex_init(&devr->x0->tgt_qp_mutex);
 	INIT_LIST_HEAD(&devr->x0->tgt_qp_list);
 
-	devr->x1 = mlx5_ib_alloc_xrcd(&dev->ib_dev, NULL, NULL);
+	devr->x1 = mlx5_ib_alloc_xrcd(&dev->ib_dev, NULL);
 	if (IS_ERR(devr->x1)) {
 		ret = PTR_ERR(devr->x1);
 		goto error3;
@@ -4797,19 +4932,21 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 	attr.ext.cq = devr->c0;
 	attr.ext.xrc.xrcd = devr->x0;
 
-	devr->s0 = mlx5_ib_create_srq(devr->p0, &attr, NULL);
-	if (IS_ERR(devr->s0)) {
-		ret = PTR_ERR(devr->s0);
+	devr->s0 = rdma_zalloc_drv_obj(ibdev, ib_srq);
+	if (!devr->s0) {
+		ret = -ENOMEM;
 		goto error4;
 	}
+
 	devr->s0->device	= &dev->ib_dev;
 	devr->s0->pd		= devr->p0;
-	devr->s0->uobject       = NULL;
-	devr->s0->event_handler = NULL;
-	devr->s0->srq_context   = NULL;
 	devr->s0->srq_type      = IB_SRQT_XRC;
 	devr->s0->ext.xrc.xrcd	= devr->x0;
 	devr->s0->ext.cq	= devr->c0;
+	ret = mlx5_ib_create_srq(devr->s0, &attr, NULL);
+	if (ret)
+		goto err_create;
+
 	atomic_inc(&devr->s0->ext.xrc.xrcd->usecnt);
 	atomic_inc(&devr->s0->ext.cq->usecnt);
 	atomic_inc(&devr->p0->usecnt);
@@ -4819,18 +4956,21 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 	attr.attr.max_sge = 1;
 	attr.attr.max_wr = 1;
 	attr.srq_type = IB_SRQT_BASIC;
-	devr->s1 = mlx5_ib_create_srq(devr->p0, &attr, NULL);
-	if (IS_ERR(devr->s1)) {
-		ret = PTR_ERR(devr->s1);
+	devr->s1 = rdma_zalloc_drv_obj(ibdev, ib_srq);
+	if (!devr->s1) {
+		ret = -ENOMEM;
 		goto error5;
 	}
+
 	devr->s1->device	= &dev->ib_dev;
 	devr->s1->pd		= devr->p0;
-	devr->s1->uobject       = NULL;
-	devr->s1->event_handler = NULL;
-	devr->s1->srq_context   = NULL;
 	devr->s1->srq_type      = IB_SRQT_BASIC;
 	devr->s1->ext.cq	= devr->c0;
+
+	ret = mlx5_ib_create_srq(devr->s1, &attr, NULL);
+	if (ret)
+		goto error6;
+
 	atomic_inc(&devr->p0->usecnt);
 	atomic_set(&devr->s1->usecnt, 0);
 
@@ -4842,16 +4982,20 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 
 	return 0;
 
+error6:
+	kfree(devr->s1);
 error5:
-	mlx5_ib_destroy_srq(devr->s0);
+	mlx5_ib_destroy_srq(devr->s0, NULL);
+err_create:
+	kfree(devr->s0);
 error4:
-	mlx5_ib_dealloc_xrcd(devr->x1);
+	mlx5_ib_dealloc_xrcd(devr->x1, NULL);
 error3:
-	mlx5_ib_dealloc_xrcd(devr->x0);
+	mlx5_ib_dealloc_xrcd(devr->x0, NULL);
 error2:
-	mlx5_ib_destroy_cq(devr->c0);
+	mlx5_ib_destroy_cq(devr->c0, NULL);
 error1:
-	mlx5_ib_dealloc_pd(devr->p0);
+	mlx5_ib_dealloc_pd(devr->p0, NULL);
 error0:
 	kfree(devr->p0);
 	return ret;
@@ -4859,20 +5003,20 @@ error0:
 
 static void destroy_dev_resources(struct mlx5_ib_resources *devr)
 {
-	struct mlx5_ib_dev *dev =
-		container_of(devr, struct mlx5_ib_dev, devr);
 	int port;
 
-	mlx5_ib_destroy_srq(devr->s1);
-	mlx5_ib_destroy_srq(devr->s0);
-	mlx5_ib_dealloc_xrcd(devr->x0);
-	mlx5_ib_dealloc_xrcd(devr->x1);
-	mlx5_ib_destroy_cq(devr->c0);
-	mlx5_ib_dealloc_pd(devr->p0);
+	mlx5_ib_destroy_srq(devr->s1, NULL);
+	kfree(devr->s1);
+	mlx5_ib_destroy_srq(devr->s0, NULL);
+	kfree(devr->s0);
+	mlx5_ib_dealloc_xrcd(devr->x0, NULL);
+	mlx5_ib_dealloc_xrcd(devr->x1, NULL);
+	mlx5_ib_destroy_cq(devr->c0, NULL);
+	mlx5_ib_dealloc_pd(devr->p0, NULL);
 	kfree(devr->p0);
 
 	/* Make sure no change P_Key work items are still executing */
-	for (port = 0; port < dev->num_ports; ++port)
+	for (port = 0; port < ARRAY_SIZE(devr->ports); ++port)
 		cancel_work_sync(&devr->ports[port].pkey_change_work);
 }
 
@@ -5015,10 +5159,10 @@ static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
 {
 	int err;
 
-	dev->roce[port_num].nb.notifier_call = mlx5_netdev_event;
-	err = register_netdevice_notifier(&dev->roce[port_num].nb);
+	dev->port[port_num].roce.nb.notifier_call = mlx5_netdev_event;
+	err = register_netdevice_notifier(&dev->port[port_num].roce.nb);
 	if (err) {
-		dev->roce[port_num].nb.notifier_call = NULL;
+		dev->port[port_num].roce.nb.notifier_call = NULL;
 		return err;
 	}
 
@@ -5027,9 +5171,9 @@ static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
 
 static void mlx5_remove_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
 {
-	if (dev->roce[port_num].nb.notifier_call) {
-		unregister_netdevice_notifier(&dev->roce[port_num].nb);
-		dev->roce[port_num].nb.notifier_call = NULL;
+	if (dev->port[port_num].roce.nb.notifier_call) {
+		unregister_netdevice_notifier(&dev->port[port_num].roce.nb);
+		dev->port[port_num].roce.nb.notifier_call = NULL;
 	}
 }
 
@@ -5578,7 +5722,7 @@ static void mlx5_ib_unbind_slave_port(struct mlx5_ib_dev *ibdev,
 		mlx5_ib_err(ibdev, "Failed to unaffiliate port %u\n",
 			    port_num + 1);
 
-	ibdev->roce[port_num].last_port_state = IB_PORT_DOWN;
+	ibdev->port[port_num].roce.last_port_state = IB_PORT_DOWN;
 }
 
 /* The mlx5_ib_multiport_mutex should be held when calling this function */
@@ -5738,7 +5882,10 @@ ADD_UVERBS_ATTRIBUTES_SIMPLE(
 			    UA_MANDATORY),
 	UVERBS_ATTR_PTR_OUT(MLX5_IB_ATTR_ALLOC_DM_RESP_PAGE_INDEX,
 			    UVERBS_ATTR_TYPE(u16),
-			    UA_MANDATORY));
+			    UA_OPTIONAL),
+	UVERBS_ATTR_CONST_IN(MLX5_IB_ATTR_ALLOC_DM_REQ_TYPE,
+			     enum mlx5_ib_uapi_dm_type,
+			     UA_OPTIONAL));
 
 ADD_UVERBS_ATTRIBUTES_SIMPLE(
 	mlx5_ib_flow_action,
@@ -5829,35 +5976,58 @@ static struct ib_counters *mlx5_ib_create_counters(struct ib_device *device,
 	return &mcounters->ibcntrs;
 }
 
-void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev)
+static void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev)
 {
+	struct mlx5_core_dev *mdev = dev->mdev;
+
 	mlx5_ib_cleanup_multiport_master(dev);
 	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
 		srcu_barrier(&dev->mr_srcu);
 		cleanup_srcu_struct(&dev->mr_srcu);
 	}
-	kfree(dev->port);
+
+	WARN_ON(!bitmap_empty(dev->dm.memic_alloc_pages, MLX5_MAX_MEMIC_PAGES));
+
+	WARN_ON(dev->dm.steering_sw_icm_alloc_blocks &&
+		!bitmap_empty(
+			dev->dm.steering_sw_icm_alloc_blocks,
+			BIT(MLX5_CAP_DEV_MEM(mdev, log_steering_sw_icm_size) -
+			    MLX5_LOG_SW_ICM_BLOCK_SIZE(mdev))));
+
+	kfree(dev->dm.steering_sw_icm_alloc_blocks);
+
+	WARN_ON(dev->dm.header_modify_sw_icm_alloc_blocks &&
+		!bitmap_empty(dev->dm.header_modify_sw_icm_alloc_blocks,
+			      BIT(MLX5_CAP_DEV_MEM(
+					  mdev, log_header_modify_sw_icm_size) -
+				  MLX5_LOG_SW_ICM_BLOCK_SIZE(mdev))));
+
+	kfree(dev->dm.header_modify_sw_icm_alloc_blocks);
 }
 
-int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
+static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 {
 	struct mlx5_core_dev *mdev = dev->mdev;
+	u64 header_modify_icm_blocks = 0;
+	u64 steering_icm_blocks = 0;
 	int err;
 	int i;
 
-	dev->port = kcalloc(dev->num_ports, sizeof(*dev->port),
-			    GFP_KERNEL);
-	if (!dev->port)
-		return -ENOMEM;
-
 	for (i = 0; i < dev->num_ports; i++) {
 		spin_lock_init(&dev->port[i].mp.mpi_lock);
-		rwlock_init(&dev->roce[i].netdev_lock);
+		rwlock_init(&dev->port[i].roce.netdev_lock);
+		dev->port[i].roce.dev = dev;
+		dev->port[i].roce.native_port_num = i + 1;
+		dev->port[i].roce.last_port_state = IB_PORT_DOWN;
 	}
 
 	err = mlx5_ib_init_multiport_master(dev);
 	if (err)
-		goto err_free_port;
+		return err;
+
+	err = set_has_smi_cap(dev);
+	if (err)
+		return err;
 
 	if (!mlx5_core_mp_enabled(mdev)) {
 		for (i = 1; i <= dev->num_ports; i++) {
@@ -5885,22 +6055,54 @@ int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 	INIT_LIST_HEAD(&dev->qp_list);
 	spin_lock_init(&dev->reset_flow_resource_lock);
 
-	spin_lock_init(&dev->memic.memic_lock);
-	dev->memic.dev = mdev;
+	if (MLX5_CAP_GEN_64(mdev, general_obj_types) &
+	    MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM) {
+		if (MLX5_CAP64_DEV_MEM(mdev, steering_sw_icm_start_address)) {
+			steering_icm_blocks =
+				BIT(MLX5_CAP_DEV_MEM(mdev,
+						     log_steering_sw_icm_size) -
+				    MLX5_LOG_SW_ICM_BLOCK_SIZE(mdev));
+
+			dev->dm.steering_sw_icm_alloc_blocks =
+				kcalloc(BITS_TO_LONGS(steering_icm_blocks),
+					sizeof(unsigned long), GFP_KERNEL);
+			if (!dev->dm.steering_sw_icm_alloc_blocks)
+				goto err_mp;
+		}
+
+		if (MLX5_CAP64_DEV_MEM(mdev,
+				       header_modify_sw_icm_start_address)) {
+			header_modify_icm_blocks = BIT(
+				MLX5_CAP_DEV_MEM(
+					mdev, log_header_modify_sw_icm_size) -
+				MLX5_LOG_SW_ICM_BLOCK_SIZE(mdev));
+
+			dev->dm.header_modify_sw_icm_alloc_blocks =
+				kcalloc(BITS_TO_LONGS(header_modify_icm_blocks),
+					sizeof(unsigned long), GFP_KERNEL);
+			if (!dev->dm.header_modify_sw_icm_alloc_blocks)
+				goto err_dm;
+		}
+	}
+
+	spin_lock_init(&dev->dm.lock);
+	dev->dm.dev = mdev;
 
 	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
 		err = init_srcu_struct(&dev->mr_srcu);
 		if (err)
-			goto err_mp;
+			goto err_dm;
 	}
 
 	return 0;
+
+err_dm:
+	kfree(dev->dm.steering_sw_icm_alloc_blocks);
+	kfree(dev->dm.header_modify_sw_icm_alloc_blocks);
+
 err_mp:
 	mlx5_ib_cleanup_multiport_master(dev);
 
-err_free_port:
-	kfree(dev->port);
-
 	return -ENOMEM;
 }
 
@@ -5916,20 +6118,6 @@ static int mlx5_ib_stage_flow_db_init(struct mlx5_ib_dev *dev)
 	return 0;
 }
 
-int mlx5_ib_stage_rep_flow_db_init(struct mlx5_ib_dev *dev)
-{
-	struct mlx5_ib_dev *nic_dev;
-
-	nic_dev = mlx5_ib_get_uplink_ibdev(dev->mdev->priv.eswitch);
-
-	if (!nic_dev)
-		return -EINVAL;
-
-	dev->flow_db = nic_dev->flow_db;
-
-	return 0;
-}
-
 static void mlx5_ib_stage_flow_db_cleanup(struct mlx5_ib_dev *dev)
 {
 	kfree(dev->flow_db);
@@ -5989,7 +6177,10 @@ static const struct ib_device_ops mlx5_ib_dev_ops = {
 	.req_notify_cq = mlx5_ib_arm_cq,
 	.rereg_user_mr = mlx5_ib_rereg_user_mr,
 	.resize_cq = mlx5_ib_resize_cq,
+
+	INIT_RDMA_OBJ_SIZE(ib_ah, mlx5_ib_ah, ibah),
 	INIT_RDMA_OBJ_SIZE(ib_pd, mlx5_ib_pd, ibpd),
+	INIT_RDMA_OBJ_SIZE(ib_srq, mlx5_ib_srq, ibsrq),
 	INIT_RDMA_OBJ_SIZE(ib_ucontext, mlx5_ib_ucontext, ibucontext),
 };
 
@@ -6025,7 +6216,7 @@ static const struct ib_device_ops mlx5_ib_dev_dm_ops = {
 	.reg_dm_mr = mlx5_ib_reg_dm_mr,
 };
 
-int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev)
+static int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev)
 {
 	struct mlx5_core_dev *mdev = dev->mdev;
 	int err;
@@ -6091,7 +6282,9 @@ int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev)
 		ib_set_device_ops(&dev->ib_dev, &mlx5_ib_dev_xrc_ops);
 	}
 
-	if (MLX5_CAP_DEV_MEM(mdev, memic))
+	if (MLX5_CAP_DEV_MEM(mdev, memic) ||
+	    MLX5_CAP_GEN_64(dev->mdev, general_obj_types) &
+	    MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM)
 		ib_set_device_ops(&dev->ib_dev, &mlx5_ib_dev_dm_ops);
 
 	if (mlx5_accel_ipsec_device_caps(dev->mdev) &
@@ -6131,7 +6324,7 @@ static const struct ib_device_ops mlx5_ib_dev_port_rep_ops = {
 	.query_port = mlx5_ib_rep_query_port,
 };
 
-int mlx5_ib_stage_rep_non_default_cb(struct mlx5_ib_dev *dev)
+static int mlx5_ib_stage_rep_non_default_cb(struct mlx5_ib_dev *dev)
 {
 	ib_set_device_ops(&dev->ib_dev, &mlx5_ib_dev_port_rep_ops);
 	return 0;
@@ -6149,13 +6342,6 @@ static const struct ib_device_ops mlx5_ib_dev_common_roce_ops = {
 static int mlx5_ib_stage_common_roce_init(struct mlx5_ib_dev *dev)
 {
 	u8 port_num;
-	int i;
-
-	for (i = 0; i < dev->num_ports; i++) {
-		dev->roce[i].dev = dev;
-		dev->roce[i].native_port_num = i + 1;
-		dev->roce[i].last_port_state = IB_PORT_DOWN;
-	}
 
 	dev->ib_dev.uverbs_ex_cmd_mask |=
 			(1ull << IB_USER_VERBS_EX_CMD_CREATE_WQ) |
@@ -6167,6 +6353,7 @@ static int mlx5_ib_stage_common_roce_init(struct mlx5_ib_dev *dev)
 
 	port_num = mlx5_core_native_port_num(dev->mdev) - 1;
 
+	/* Register only for native ports */
 	return mlx5_add_netdev_notifier(dev, port_num);
 }
 
@@ -6177,7 +6364,7 @@ static void mlx5_ib_stage_common_roce_cleanup(struct mlx5_ib_dev *dev)
 	mlx5_remove_netdev_notifier(dev, port_num);
 }
 
-int mlx5_ib_stage_rep_roce_init(struct mlx5_ib_dev *dev)
+static int mlx5_ib_stage_rep_roce_init(struct mlx5_ib_dev *dev)
 {
 	struct mlx5_core_dev *mdev = dev->mdev;
 	enum rdma_link_layer ll;
@@ -6193,7 +6380,7 @@ int mlx5_ib_stage_rep_roce_init(struct mlx5_ib_dev *dev)
 	return err;
 }
 
-void mlx5_ib_stage_rep_roce_cleanup(struct mlx5_ib_dev *dev)
+static void mlx5_ib_stage_rep_roce_cleanup(struct mlx5_ib_dev *dev)
 {
 	mlx5_ib_stage_common_roce_cleanup(dev);
 }
@@ -6240,12 +6427,12 @@ static void mlx5_ib_stage_roce_cleanup(struct mlx5_ib_dev *dev)
 	}
 }
 
-int mlx5_ib_stage_dev_res_init(struct mlx5_ib_dev *dev)
+static int mlx5_ib_stage_dev_res_init(struct mlx5_ib_dev *dev)
 {
 	return create_dev_resources(&dev->devr);
 }
 
-void mlx5_ib_stage_dev_res_cleanup(struct mlx5_ib_dev *dev)
+static void mlx5_ib_stage_dev_res_cleanup(struct mlx5_ib_dev *dev)
 {
 	destroy_dev_resources(&dev->devr);
 }
@@ -6267,7 +6454,7 @@ static const struct ib_device_ops mlx5_ib_dev_hw_stats_ops = {
 	.get_hw_stats = mlx5_ib_get_hw_stats,
 };
 
-int mlx5_ib_stage_counters_init(struct mlx5_ib_dev *dev)
+static int mlx5_ib_stage_counters_init(struct mlx5_ib_dev *dev)
 {
 	if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt)) {
 		ib_set_device_ops(&dev->ib_dev, &mlx5_ib_dev_hw_stats_ops);
@@ -6278,7 +6465,7 @@ int mlx5_ib_stage_counters_init(struct mlx5_ib_dev *dev)
 	return 0;
 }
 
-void mlx5_ib_stage_counters_cleanup(struct mlx5_ib_dev *dev)
+static void mlx5_ib_stage_counters_cleanup(struct mlx5_ib_dev *dev)
 {
 	if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt))
 		mlx5_ib_dealloc_counters(dev);
@@ -6308,7 +6495,7 @@ static void mlx5_ib_stage_uar_cleanup(struct mlx5_ib_dev *dev)
 	mlx5_put_uars_page(dev->mdev, dev->mdev->priv.uar);
 }
 
-int mlx5_ib_stage_bfrag_init(struct mlx5_ib_dev *dev)
+static int mlx5_ib_stage_bfrag_init(struct mlx5_ib_dev *dev)
 {
 	int err;
 
@@ -6323,13 +6510,13 @@ int mlx5_ib_stage_bfrag_init(struct mlx5_ib_dev *dev)
 	return err;
 }
 
-void mlx5_ib_stage_bfrag_cleanup(struct mlx5_ib_dev *dev)
+static void mlx5_ib_stage_bfrag_cleanup(struct mlx5_ib_dev *dev)
 {
 	mlx5_free_bfreg(dev->mdev, &dev->fp_bfreg);
 	mlx5_free_bfreg(dev->mdev, &dev->bfreg);
 }
 
-int mlx5_ib_stage_ib_reg_init(struct mlx5_ib_dev *dev)
+static int mlx5_ib_stage_ib_reg_init(struct mlx5_ib_dev *dev)
 {
 	const char *name;
 
@@ -6341,17 +6528,17 @@ int mlx5_ib_stage_ib_reg_init(struct mlx5_ib_dev *dev)
 	return ib_register_device(&dev->ib_dev, name);
 }
 
-void mlx5_ib_stage_pre_ib_reg_umr_cleanup(struct mlx5_ib_dev *dev)
+static void mlx5_ib_stage_pre_ib_reg_umr_cleanup(struct mlx5_ib_dev *dev)
 {
 	destroy_umrc_res(dev);
 }
 
-void mlx5_ib_stage_ib_reg_cleanup(struct mlx5_ib_dev *dev)
+static void mlx5_ib_stage_ib_reg_cleanup(struct mlx5_ib_dev *dev)
 {
 	ib_unregister_device(&dev->ib_dev);
 }
 
-int mlx5_ib_stage_post_ib_reg_umr_init(struct mlx5_ib_dev *dev)
+static int mlx5_ib_stage_post_ib_reg_umr_init(struct mlx5_ib_dev *dev)
 {
 	return create_umr_res(dev);
 }
@@ -6406,6 +6593,9 @@ void __mlx5_ib_remove(struct mlx5_ib_dev *dev,
 		if (profile->stage[stage].cleanup)
 			profile->stage[stage].cleanup(dev);
 	}
+
+	kfree(dev->port);
+	ib_dealloc_device(&dev->ib_dev);
 }
 
 void *__mlx5_ib_add(struct mlx5_ib_dev *dev,
@@ -6527,6 +6717,9 @@ const struct mlx5_ib_profile uplink_rep_profile = {
 	STAGE_CREATE(MLX5_IB_STAGE_PRE_IB_REG_UMR,
 		     NULL,
 		     mlx5_ib_stage_pre_ib_reg_umr_cleanup),
+	STAGE_CREATE(MLX5_IB_STAGE_WHITELIST_UID,
+		     mlx5_ib_stage_devx_init,
+		     mlx5_ib_stage_devx_cleanup),
 	STAGE_CREATE(MLX5_IB_STAGE_IB_REG,
 		     mlx5_ib_stage_ib_reg_init,
 		     mlx5_ib_stage_ib_reg_cleanup),
@@ -6581,12 +6774,14 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	enum rdma_link_layer ll;
 	struct mlx5_ib_dev *dev;
 	int port_type_cap;
+	int num_ports;
 
 	printk_once(KERN_INFO "%s", mlx5_version);
 
 	if (MLX5_ESWITCH_MANAGER(mdev) &&
 	    mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) {
-		mlx5_ib_register_vport_reps(mdev);
+		if (!mlx5_core_mp_enabled(mdev))
+			mlx5_ib_register_vport_reps(mdev);
 		return mdev;
 	}
 
@@ -6596,13 +6791,20 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	if (mlx5_core_is_mp_slave(mdev) && ll == IB_LINK_LAYER_ETHERNET)
 		return mlx5_ib_add_slave_port(mdev);
 
+	num_ports = max(MLX5_CAP_GEN(mdev, num_ports),
+			MLX5_CAP_GEN(mdev, num_vhca_ports));
 	dev = ib_alloc_device(mlx5_ib_dev, ib_dev);
 	if (!dev)
 		return NULL;
+	dev->port = kcalloc(num_ports, sizeof(*dev->port),
+			     GFP_KERNEL);
+	if (!dev->port) {
+		ib_dealloc_device((struct ib_device *)dev);
+		return NULL;
+	}
 
 	dev->mdev = mdev;
-	dev->num_ports = max(MLX5_CAP_GEN(mdev, num_ports),
-			     MLX5_CAP_GEN(mdev, num_vhca_ports));
+	dev->num_ports = num_ports;
 
 	return __mlx5_ib_add(dev, &pf_profile);
 }
@@ -6629,8 +6831,6 @@ static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context)
 
 	dev = context;
 	__mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX);
-
-	ib_dealloc_device((struct ib_device *)dev);
 }
 
 static struct mlx5_interface mlx5_ib_interface = {