1 files changed, 490 insertions, 184 deletions

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index da3bf6c081de..5b3355268725 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -53,6 +53,7 @@
 #include <linux/in.h>
 #include <linux/etherdevice.h>
 #include <linux/mlx5/fs.h>
+#include <linux/mlx5/vport.h>
 #include "mlx5_ib.h"
 
 #define DRIVER_NAME "mlx5_ib"
@@ -64,10 +65,6 @@ MODULE_DESCRIPTION("Mellanox Connect-IB HCA IB driver");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_VERSION(DRIVER_VERSION);
 
-static int deprecated_prof_sel = 2;
-module_param_named(prof_sel, deprecated_prof_sel, int, 0444);
-MODULE_PARM_DESC(prof_sel, "profile selector. Deprecated here. Moved to module mlx5_core");
-
 static char mlx5_version[] =
 	DRIVER_NAME ": Mellanox Connect-IB Infiniband driver v"
 	DRIVER_VERSION " (" DRIVER_RELDATE ")\n";
@@ -174,7 +171,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 	enum ib_mtu ndev_ib_mtu;
 	u16 qkey_viol_cntr;
 
-	memset(props, 0, sizeof(*props));
+	/* props being zeroed by the caller, avoid zeroing it here */
 
 	props->port_cap_flags  |= IB_PORT_CM_SUP;
 	props->port_cap_flags  |= IB_PORT_IP_BASED_GIDS;
@@ -325,6 +322,27 @@ __be16 mlx5_get_roce_udp_sport(struct mlx5_ib_dev *dev, u8 port_num,
 	return cpu_to_be16(MLX5_CAP_ROCE(dev->mdev, r_roce_min_src_udp_port));
 }
 
+int mlx5_get_roce_gid_type(struct mlx5_ib_dev *dev, u8 port_num,
+			   int index, enum ib_gid_type *gid_type)
+{
+	struct ib_gid_attr attr;
+	union ib_gid gid;
+	int ret;
+
+	ret = ib_get_cached_gid(&dev->ib_dev, port_num, index, &gid, &attr);
+	if (ret)
+		return ret;
+
+	if (!attr.ndev)
+		return -ENODEV;
+
+	dev_put(attr.ndev);
+
+	*gid_type = attr.gid_type;
+
+	return 0;
+}
+
 static int mlx5_use_mad_ifc(struct mlx5_ib_dev *dev)
 {
 	if (MLX5_CAP_GEN(dev->mdev, port_type) == MLX5_CAP_PORT_TYPE_IB)
@@ -564,8 +582,15 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		props->device_cap_flags |= IB_DEVICE_BLOCK_MULTICAST_LOOPBACK;
 
 	if (MLX5_CAP_GEN(dev->mdev, eth_net_offloads)) {
-		if (MLX5_CAP_ETH(mdev, csum_cap))
+		if (MLX5_CAP_ETH(mdev, csum_cap)) {
+			/* Legacy bit to support old userspace libraries */
 			props->device_cap_flags |= IB_DEVICE_RAW_IP_CSUM;
+			props->raw_packet_caps |= IB_RAW_PACKET_CAP_IP_CSUM;
+		}
+
+		if (MLX5_CAP_ETH(dev->mdev, vlan_cap))
+			props->raw_packet_caps |=
+				IB_RAW_PACKET_CAP_CVLAN_STRIPPING;
 
 		if (field_avail(typeof(resp), tso_caps, uhw->outlen)) {
 			max_tso = MLX5_CAP_ETH(mdev, max_lso_cap);
@@ -604,8 +629,11 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	}
 
 	if (MLX5_CAP_GEN(dev->mdev, eth_net_offloads) &&
-	    MLX5_CAP_ETH(dev->mdev, scatter_fcs))
+	    MLX5_CAP_ETH(dev->mdev, scatter_fcs)) {
+		/* Legacy bit to support old userspace libraries */
 		props->device_cap_flags |= IB_DEVICE_RAW_SCATTER_FCS;
+		props->raw_packet_caps |= IB_RAW_PACKET_CAP_SCATTER_FCS;
+	}
 
 	if (mlx5_get_flow_namespace(dev->mdev, MLX5_FLOW_NAMESPACE_BYPASS))
 		props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
@@ -672,17 +700,6 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 			1 << MLX5_CAP_GEN(dev->mdev, log_max_rq);
 	}
 
-	if (field_avail(typeof(resp), mlx5_ib_support_multi_pkt_send_wqes,
-			uhw->outlen)) {
-		resp.mlx5_ib_support_multi_pkt_send_wqes =
-			MLX5_CAP_ETH(mdev, multi_pkt_send_wqe);
-		resp.response_length +=
-			sizeof(resp.mlx5_ib_support_multi_pkt_send_wqes);
-	}
-
-	if (field_avail(typeof(resp), reserved, uhw->outlen))
-		resp.response_length += sizeof(resp.reserved);
-
 	if (field_avail(typeof(resp), cqe_comp_caps, uhw->outlen)) {
 		resp.cqe_comp_caps.max_num =
 			MLX5_CAP_GEN(dev->mdev, cqe_compression) ?
@@ -706,6 +723,17 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		resp.response_length += sizeof(resp.packet_pacing_caps);
 	}
 
+	if (field_avail(typeof(resp), mlx5_ib_support_multi_pkt_send_wqes,
+			uhw->outlen)) {
+		resp.mlx5_ib_support_multi_pkt_send_wqes =
+			MLX5_CAP_ETH(mdev, multi_pkt_send_wqe);
+		resp.response_length +=
+			sizeof(resp.mlx5_ib_support_multi_pkt_send_wqes);
+	}
+
+	if (field_avail(typeof(resp), reserved, uhw->outlen))
+		resp.response_length += sizeof(resp.reserved);
+
 	if (uhw->outlen) {
 		err = ib_copy_to_udata(uhw, &resp, resp.response_length);
 
@@ -830,7 +858,7 @@ static int mlx5_query_hca_port(struct ib_device *ibdev, u8 port,
 		goto out;
 	}
 
-	memset(props, 0, sizeof(*props));
+	/* props being zeroed by the caller, avoid zeroing it here */
 
 	err = mlx5_query_hca_vport_context(mdev, 0, port, 0, rep);
 	if (err)
@@ -968,6 +996,31 @@ static int mlx5_ib_modify_device(struct ib_device *ibdev, int mask,
 	return err;
 }
 
+static int set_port_caps_atomic(struct mlx5_ib_dev *dev, u8 port_num, u32 mask,
+				u32 value)
+{
+	struct mlx5_hca_vport_context ctx = {};
+	int err;
+
+	err = mlx5_query_hca_vport_context(dev->mdev, 0,
+					   port_num, 0, &ctx);
+	if (err)
+		return err;
+
+	if (~ctx.cap_mask1_perm & mask) {
+		mlx5_ib_warn(dev, "trying to change bitmask 0x%X but change supported 0x%X\n",
+			     mask, ctx.cap_mask1_perm);
+		return -EINVAL;
+	}
+
+	ctx.cap_mask1 = value;
+	ctx.cap_mask1_perm = mask;
+	err = mlx5_core_modify_hca_vport_context(dev->mdev, 0,
+						 port_num, 0, &ctx);
+
+	return err;
+}
+
 static int mlx5_ib_modify_port(struct ib_device *ibdev, u8 port, int mask,
 			       struct ib_port_modify *props)
 {
@@ -975,10 +1028,20 @@ static int mlx5_ib_modify_port(struct ib_device *ibdev, u8 port, int mask,
 	struct ib_port_attr attr;
 	u32 tmp;
 	int err;
+	u32 change_mask;
+	u32 value;
+	bool is_ib = (mlx5_ib_port_link_layer(ibdev, port) ==
+		      IB_LINK_LAYER_INFINIBAND);
+
+	if (MLX5_CAP_GEN(dev->mdev, ib_virt) && is_ib) {
+		change_mask = props->clr_port_cap_mask | props->set_port_cap_mask;
+		value = ~props->clr_port_cap_mask | props->set_port_cap_mask;
+		return set_port_caps_atomic(dev, port, change_mask, value);
+	}
 
 	mutex_lock(&dev->cap_mask_mutex);
 
-	err = mlx5_ib_query_port(ibdev, port, &attr);
+	err = ib_query_port(ibdev, port, &attr);
 	if (err)
 		goto out;
 
@@ -992,6 +1055,86 @@ out:
 	return err;
 }
 
+static void print_lib_caps(struct mlx5_ib_dev *dev, u64 caps)
+{
+	mlx5_ib_dbg(dev, "MLX5_LIB_CAP_4K_UAR = %s\n",
+		    caps & MLX5_LIB_CAP_4K_UAR ? "y" : "n");
+}
+
+static int calc_total_bfregs(struct mlx5_ib_dev *dev, bool lib_uar_4k,
+			     struct mlx5_ib_alloc_ucontext_req_v2 *req,
+			     u32 *num_sys_pages)
+{
+	int uars_per_sys_page;
+	int bfregs_per_sys_page;
+	int ref_bfregs = req->total_num_bfregs;
+
+	if (req->total_num_bfregs == 0)
+		return -EINVAL;
+
+	BUILD_BUG_ON(MLX5_MAX_BFREGS % MLX5_NON_FP_BFREGS_IN_PAGE);
+	BUILD_BUG_ON(MLX5_MAX_BFREGS < MLX5_NON_FP_BFREGS_IN_PAGE);
+
+	if (req->total_num_bfregs > MLX5_MAX_BFREGS)
+		return -ENOMEM;
+
+	uars_per_sys_page = get_uars_per_sys_page(dev, lib_uar_4k);
+	bfregs_per_sys_page = uars_per_sys_page * MLX5_NON_FP_BFREGS_PER_UAR;
+	req->total_num_bfregs = ALIGN(req->total_num_bfregs, bfregs_per_sys_page);
+	*num_sys_pages = req->total_num_bfregs / bfregs_per_sys_page;
+
+	if (req->num_low_latency_bfregs > req->total_num_bfregs - 1)
+		return -EINVAL;
+
+	mlx5_ib_dbg(dev, "uar_4k: fw support %s, lib support %s, user requested %d bfregs, alloated %d, using %d sys pages\n",
+		    MLX5_CAP_GEN(dev->mdev, uar_4k) ? "yes" : "no",
+		    lib_uar_4k ? "yes" : "no", ref_bfregs,
+		    req->total_num_bfregs, *num_sys_pages);
+
+	return 0;
+}
+
+static int allocate_uars(struct mlx5_ib_dev *dev, struct mlx5_ib_ucontext *context)
+{
+	struct mlx5_bfreg_info *bfregi;
+	int err;
+	int i;
+
+	bfregi = &context->bfregi;
+	for (i = 0; i < bfregi->num_sys_pages; i++) {
+		err = mlx5_cmd_alloc_uar(dev->mdev, &bfregi->sys_pages[i]);
+		if (err)
+			goto error;
+
+		mlx5_ib_dbg(dev, "allocated uar %d\n", bfregi->sys_pages[i]);
+	}
+	return 0;
+
+error:
+	for (--i; i >= 0; i--)
+		if (mlx5_cmd_free_uar(dev->mdev, bfregi->sys_pages[i]))
+			mlx5_ib_warn(dev, "failed to free uar %d\n", i);
+
+	return err;
+}
+
+static int deallocate_uars(struct mlx5_ib_dev *dev, struct mlx5_ib_ucontext *context)
+{
+	struct mlx5_bfreg_info *bfregi;
+	int err;
+	int i;
+
+	bfregi = &context->bfregi;
+	for (i = 0; i < bfregi->num_sys_pages; i++) {
+		err = mlx5_cmd_free_uar(dev->mdev, bfregi->sys_pages[i]);
+		if (err) {
+			mlx5_ib_warn(dev, "failed to free uar %d\n", i);
+			return err;
+		}
+	}
+	return 0;
+}
+
 static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 						  struct ib_udata *udata)
 {
@@ -999,17 +1142,13 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	struct mlx5_ib_alloc_ucontext_req_v2 req = {};
 	struct mlx5_ib_alloc_ucontext_resp resp = {};
 	struct mlx5_ib_ucontext *context;
-	struct mlx5_uuar_info *uuari;
-	struct mlx5_uar *uars;
-	int gross_uuars;
-	int num_uars;
+	struct mlx5_bfreg_info *bfregi;
 	int ver;
-	int uuarn;
 	int err;
-	int i;
 	size_t reqlen;
 	size_t min_req_v2 = offsetof(struct mlx5_ib_alloc_ucontext_req_v2,
 				     max_cqe_version);
+	bool lib_uar_4k;
 
 	if (!dev->ib_active)
 		return ERR_PTR(-EAGAIN);
@@ -1032,27 +1171,14 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	if (req.flags)
 		return ERR_PTR(-EINVAL);
 
-	if (req.total_num_uuars > MLX5_MAX_UUARS)
-		return ERR_PTR(-ENOMEM);
-
-	if (req.total_num_uuars == 0)
-		return ERR_PTR(-EINVAL);
-
 	if (req.comp_mask || req.reserved0 || req.reserved1 || req.reserved2)
 		return ERR_PTR(-EOPNOTSUPP);
 
-	if (reqlen > sizeof(req) &&
-	    !ib_is_udata_cleared(udata, sizeof(req),
-				 reqlen - sizeof(req)))
-		return ERR_PTR(-EOPNOTSUPP);
-
-	req.total_num_uuars = ALIGN(req.total_num_uuars,
-				    MLX5_NON_FP_BF_REGS_PER_PAGE);
-	if (req.num_low_latency_uuars > req.total_num_uuars - 1)
+	req.total_num_bfregs = ALIGN(req.total_num_bfregs,
+				    MLX5_NON_FP_BFREGS_PER_UAR);
+	if (req.num_low_latency_bfregs > req.total_num_bfregs - 1)
 		return ERR_PTR(-EINVAL);
 
-	num_uars = req.total_num_uuars / MLX5_NON_FP_BF_REGS_PER_PAGE;
-	gross_uuars = num_uars * MLX5_BF_REGS_PER_PAGE;
 	resp.qp_tab_size = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp);
 	if (mlx5_core_is_pf(dev->mdev) && MLX5_CAP_GEN(dev->mdev, bf))
 		resp.bf_reg_size = 1 << MLX5_CAP_GEN(dev->mdev, log_bf_reg_size);
@@ -1065,6 +1191,10 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	resp.cqe_version = min_t(__u8,
 				 (__u8)MLX5_CAP_GEN(dev->mdev, cqe_version),
 				 req.max_cqe_version);
+	resp.log_uar_size = MLX5_CAP_GEN(dev->mdev, uar_4k) ?
+				MLX5_ADAPTER_PAGE_SHIFT : PAGE_SHIFT;
+	resp.num_uars_per_page = MLX5_CAP_GEN(dev->mdev, uar_4k) ?
+					MLX5_CAP_GEN(dev->mdev, num_of_uars_per_page) : 1;
 	resp.response_length = min(offsetof(typeof(resp), response_length) +
 				   sizeof(resp.response_length), udata->outlen);
 
@@ -1072,58 +1202,58 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	if (!context)
 		return ERR_PTR(-ENOMEM);
 
-	uuari = &context->uuari;
-	mutex_init(&uuari->lock);
-	uars = kcalloc(num_uars, sizeof(*uars), GFP_KERNEL);
-	if (!uars) {
-		err = -ENOMEM;
+	lib_uar_4k = req.lib_caps & MLX5_LIB_CAP_4K_UAR;
+	bfregi = &context->bfregi;
+
+	/* updates req->total_num_bfregs */
+	err = calc_total_bfregs(dev, lib_uar_4k, &req, &bfregi->num_sys_pages);
+	if (err)
 		goto out_ctx;
-	}
 
-	uuari->bitmap = kcalloc(BITS_TO_LONGS(gross_uuars),
-				sizeof(*uuari->bitmap),
+	mutex_init(&bfregi->lock);
+	bfregi->lib_uar_4k = lib_uar_4k;
+	bfregi->count = kcalloc(req.total_num_bfregs, sizeof(*bfregi->count),
 				GFP_KERNEL);
-	if (!uuari->bitmap) {
+	if (!bfregi->count) {
 		err = -ENOMEM;
-		goto out_uar_ctx;
-	}
-	/*
-	 * clear all fast path uuars
-	 */
-	for (i = 0; i < gross_uuars; i++) {
-		uuarn = i & 3;
-		if (uuarn == 2 || uuarn == 3)
-			set_bit(i, uuari->bitmap);
+		goto out_ctx;
 	}
 
-	uuari->count = kcalloc(gross_uuars, sizeof(*uuari->count), GFP_KERNEL);
-	if (!uuari->count) {
+	bfregi->sys_pages = kcalloc(bfregi->num_sys_pages,
+				    sizeof(*bfregi->sys_pages),
+				    GFP_KERNEL);
+	if (!bfregi->sys_pages) {
 		err = -ENOMEM;
-		goto out_bitmap;
+		goto out_count;
 	}
 
-	for (i = 0; i < num_uars; i++) {
-		err = mlx5_cmd_alloc_uar(dev->mdev, &uars[i].index);
-		if (err)
-			goto out_count;
-	}
+	err = allocate_uars(dev, context);
+	if (err)
+		goto out_sys_pages;
 
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 	context->ibucontext.invalidate_range = &mlx5_ib_invalidate_range;
 #endif
 
+	context->upd_xlt_page = __get_free_page(GFP_KERNEL);
+	if (!context->upd_xlt_page) {
+		err = -ENOMEM;
+		goto out_uars;
+	}
+	mutex_init(&context->upd_xlt_page_mutex);
+
 	if (MLX5_CAP_GEN(dev->mdev, log_max_transport_domain)) {
 		err = mlx5_core_alloc_transport_domain(dev->mdev,
 						       &context->tdn);
 		if (err)
-			goto out_uars;
+			goto out_page;
 	}
 
 	INIT_LIST_HEAD(&context->vma_private_list);
 	INIT_LIST_HEAD(&context->db_page_list);
 	mutex_init(&context->db_page_mutex);
 
-	resp.tot_uuars = req.total_num_uuars;
+	resp.tot_bfregs = req.total_num_bfregs;
 	resp.num_ports = MLX5_CAP_GEN(dev->mdev, num_ports);
 
 	if (field_avail(typeof(resp), cqe_version, udata->outlen))
@@ -1135,32 +1265,46 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 		resp.response_length += sizeof(resp.cmds_supp_uhw);
 	}
 
+	if (field_avail(typeof(resp), eth_min_inline, udata->outlen)) {
+		if (mlx5_ib_port_link_layer(ibdev, 1) == IB_LINK_LAYER_ETHERNET) {
+			mlx5_query_min_inline(dev->mdev, &resp.eth_min_inline);
+			resp.eth_min_inline++;
+		}
+		resp.response_length += sizeof(resp.eth_min_inline);
+	}
+
 	/*
 	 * We don't want to expose information from the PCI bar that is located
 	 * after 4096 bytes, so if the arch only supports larger pages, let's
 	 * pretend we don't support reading the HCA's core clock. This is also
 	 * forced by mmap function.
 	 */
-	if (PAGE_SIZE <= 4096 &&
-	    field_avail(typeof(resp), hca_core_clock_offset, udata->outlen)) {
-		resp.comp_mask |=
-			MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_CORE_CLOCK_OFFSET;
-		resp.hca_core_clock_offset =
-			offsetof(struct mlx5_init_seg, internal_timer_h) %
-			PAGE_SIZE;
+	if (field_avail(typeof(resp), hca_core_clock_offset, udata->outlen)) {
+		if (PAGE_SIZE <= 4096) {
+			resp.comp_mask |=
+				MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_CORE_CLOCK_OFFSET;
+			resp.hca_core_clock_offset =
+				offsetof(struct mlx5_init_seg, internal_timer_h) % PAGE_SIZE;
+		}
 		resp.response_length += sizeof(resp.hca_core_clock_offset) +
 					sizeof(resp.reserved2);
 	}
 
+	if (field_avail(typeof(resp), log_uar_size, udata->outlen))
+		resp.response_length += sizeof(resp.log_uar_size);
+
+	if (field_avail(typeof(resp), num_uars_per_page, udata->outlen))
+		resp.response_length += sizeof(resp.num_uars_per_page);
+
 	err = ib_copy_to_udata(udata, &resp, resp.response_length);
 	if (err)
 		goto out_td;
 
-	uuari->ver = ver;
-	uuari->num_low_latency_uuars = req.num_low_latency_uuars;
-	uuari->uars = uars;
-	uuari->num_uars = num_uars;
+	bfregi->ver = ver;
+	bfregi->num_low_latency_bfregs = req.num_low_latency_bfregs;
 	context->cqe_version = resp.cqe_version;
+	context->lib_caps = req.lib_caps;
+	print_lib_caps(dev, context->lib_caps);
 
 	return &context->ibucontext;
 
@@ -1168,20 +1312,21 @@ out_td:
 	if (MLX5_CAP_GEN(dev->mdev, log_max_transport_domain))
 		mlx5_core_dealloc_transport_domain(dev->mdev, context->tdn);
 
+out_page:
+	free_page(context->upd_xlt_page);
+
 out_uars:
-	for (i--; i >= 0; i--)
-		mlx5_cmd_free_uar(dev->mdev, uars[i].index);
-out_count:
-	kfree(uuari->count);
+	deallocate_uars(dev, context);
 
-out_bitmap:
-	kfree(uuari->bitmap);
+out_sys_pages:
+	kfree(bfregi->sys_pages);
 
-out_uar_ctx:
-	kfree(uars);
+out_count:
+	kfree(bfregi->count);
 
 out_ctx:
 	kfree(context);
+
 	return ERR_PTR(err);
 }
 
@@ -1189,28 +1334,31 @@ static int mlx5_ib_dealloc_ucontext(struct ib_ucontext *ibcontext)
 {
 	struct mlx5_ib_ucontext *context = to_mucontext(ibcontext);
 	struct mlx5_ib_dev *dev = to_mdev(ibcontext->device);
-	struct mlx5_uuar_info *uuari = &context->uuari;
-	int i;
+	struct mlx5_bfreg_info *bfregi;
 
+	bfregi = &context->bfregi;
 	if (MLX5_CAP_GEN(dev->mdev, log_max_transport_domain))
 		mlx5_core_dealloc_transport_domain(dev->mdev, context->tdn);
 
-	for (i = 0; i < uuari->num_uars; i++) {
-		if (mlx5_cmd_free_uar(dev->mdev, uuari->uars[i].index))
-			mlx5_ib_warn(dev, "failed to free UAR 0x%x\n", uuari->uars[i].index);
-	}
-
-	kfree(uuari->count);
-	kfree(uuari->bitmap);
-	kfree(uuari->uars);
+	free_page(context->upd_xlt_page);
+	deallocate_uars(dev, context);
+	kfree(bfregi->sys_pages);
+	kfree(bfregi->count);
 	kfree(context);
 
 	return 0;
 }
 
-static phys_addr_t uar_index2pfn(struct mlx5_ib_dev *dev, int index)
+static phys_addr_t uar_index2pfn(struct mlx5_ib_dev *dev,
+				 struct mlx5_bfreg_info *bfregi,
+				 int idx)
 {
-	return (pci_resource_start(dev->mdev->pdev, 0) >> PAGE_SHIFT) + index;
+	int fw_uars_per_page;
+
+	fw_uars_per_page = MLX5_CAP_GEN(dev->mdev, uar_4k) ? MLX5_UARS_IN_PAGE : 1;
+
+	return (pci_resource_start(dev->mdev->pdev, 0) >> PAGE_SHIFT) +
+			bfregi->sys_pages[idx] / fw_uars_per_page;
 }
 
 static int get_command(unsigned long offset)
@@ -1365,11 +1513,23 @@ static int uar_mmap(struct mlx5_ib_dev *dev, enum mlx5_ib_mmap_cmd cmd,
 		    struct vm_area_struct *vma,
 		    struct mlx5_ib_ucontext *context)
 {
-	struct mlx5_uuar_info *uuari = &context->uuari;
+	struct mlx5_bfreg_info *bfregi = &context->bfregi;
 	int err;
 	unsigned long idx;
 	phys_addr_t pfn, pa;
 	pgprot_t prot;
+	int uars_per_page;
+
+	if (vma->vm_end - vma->vm_start != PAGE_SIZE)
+		return -EINVAL;
+
+	uars_per_page = get_uars_per_sys_page(dev, bfregi->lib_uar_4k);
+	idx = get_index(vma->vm_pgoff);
+	if (idx % uars_per_page ||
+	    idx * uars_per_page >= bfregi->num_sys_pages) {
+		mlx5_ib_warn(dev, "invalid uar index %lu\n", idx);
+		return -EINVAL;
+	}
 
 	switch (cmd) {
 	case MLX5_IB_MMAP_WC_PAGE:
@@ -1392,14 +1552,7 @@ static int uar_mmap(struct mlx5_ib_dev *dev, enum mlx5_ib_mmap_cmd cmd,
 		return -EINVAL;
 	}
 
-	if (vma->vm_end - vma->vm_start != PAGE_SIZE)
-		return -EINVAL;
-
-	idx = get_index(vma->vm_pgoff);
-	if (idx >= uuari->num_uars)
-		return -EINVAL;
-
-	pfn = uar_index2pfn(dev, uuari->uars[idx].index);
+	pfn = uar_index2pfn(dev, bfregi, idx);
 	mlx5_ib_dbg(dev, "uar idx 0x%lx, pfn %pa\n", idx, &pfn);
 
 	vma->vm_page_prot = prot;
@@ -1570,6 +1723,7 @@ static void set_tos(void *outer_c, void *outer_v, u8 mask, u8 val)
 #define LAST_IPV6_FIELD traffic_class
 #define LAST_TCP_UDP_FIELD src_port
 #define LAST_TUNNEL_FIELD tunnel_id
+#define LAST_FLOW_TAG_FIELD tag_id
 
 /* Field is the last supported field */
 #define FIELDS_NOT_SUPPORTED(filter, field)\
@@ -1580,7 +1734,7 @@ static void set_tos(void *outer_c, void *outer_v, u8 mask, u8 val)
 		   sizeof(filter.field))
 
 static int parse_flow_attr(u32 *match_c, u32 *match_v,
-			   const union ib_flow_spec *ib_spec)
+			   const union ib_flow_spec *ib_spec, u32 *tag_id)
 {
 	void *misc_params_c = MLX5_ADDR_OF(fte_match_param, match_c,
 					   misc_parameters);
@@ -1604,7 +1758,7 @@ static int parse_flow_attr(u32 *match_c, u32 *match_v,
 	switch (ib_spec->type & ~IB_FLOW_SPEC_INNER) {
 	case IB_FLOW_SPEC_ETH:
 		if (FIELDS_NOT_SUPPORTED(ib_spec->eth.mask, LAST_ETH_FIELD))
-			return -ENOTSUPP;
+			return -EOPNOTSUPP;
 
 		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
 					     dmac_47_16),
@@ -1622,9 +1776,9 @@ static int parse_flow_attr(u32 *match_c, u32 *match_v,
 
 		if (ib_spec->eth.mask.vlan_tag) {
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
-				 vlan_tag, 1);
+				 cvlan_tag, 1);
 			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
-				 vlan_tag, 1);
+				 cvlan_tag, 1);
 
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
 				 first_vid, ntohs(ib_spec->eth.mask.vlan_tag));
@@ -1652,7 +1806,7 @@ static int parse_flow_attr(u32 *match_c, u32 *match_v,
 		break;
 	case IB_FLOW_SPEC_IPV4:
 		if (FIELDS_NOT_SUPPORTED(ib_spec->ipv4.mask, LAST_IPV4_FIELD))
-			return -ENOTSUPP;
+			return -EOPNOTSUPP;
 
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c,
 			 ethertype, 0xffff);
@@ -1684,7 +1838,7 @@ static int parse_flow_attr(u32 *match_c, u32 *match_v,
 		break;
 	case IB_FLOW_SPEC_IPV6:
 		if (FIELDS_NOT_SUPPORTED(ib_spec->ipv6.mask, LAST_IPV6_FIELD))
-			return -ENOTSUPP;
+			return -EOPNOTSUPP;
 
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c,
 			 ethertype, 0xffff);
@@ -1725,7 +1879,7 @@ static int parse_flow_attr(u32 *match_c, u32 *match_v,
 	case IB_FLOW_SPEC_TCP:
 		if (FIELDS_NOT_SUPPORTED(ib_spec->tcp_udp.mask,
 					 LAST_TCP_UDP_FIELD))
-			return -ENOTSUPP;
+			return -EOPNOTSUPP;
 
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol,
 			 0xff);
@@ -1745,7 +1899,7 @@ static int parse_flow_attr(u32 *match_c, u32 *match_v,
 	case IB_FLOW_SPEC_UDP:
 		if (FIELDS_NOT_SUPPORTED(ib_spec->tcp_udp.mask,
 					 LAST_TCP_UDP_FIELD))
-			return -ENOTSUPP;
+			return -EOPNOTSUPP;
 
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol,
 			 0xff);
@@ -1765,13 +1919,22 @@ static int parse_flow_attr(u32 *match_c, u32 *match_v,
 	case IB_FLOW_SPEC_VXLAN_TUNNEL:
 		if (FIELDS_NOT_SUPPORTED(ib_spec->tunnel.mask,
 					 LAST_TUNNEL_FIELD))
-			return -ENOTSUPP;
+			return -EOPNOTSUPP;
 
 		MLX5_SET(fte_match_set_misc, misc_params_c, vxlan_vni,
 			 ntohl(ib_spec->tunnel.mask.tunnel_id));
 		MLX5_SET(fte_match_set_misc, misc_params_v, vxlan_vni,
 			 ntohl(ib_spec->tunnel.val.tunnel_id));
 		break;
+	case IB_FLOW_SPEC_ACTION_TAG:
+		if (FIELDS_NOT_SUPPORTED(ib_spec->flow_tag,
+					 LAST_FLOW_TAG_FIELD))
+			return -EOPNOTSUPP;
+		if (ib_spec->flow_tag.tag_id >= BIT(24))
+			return -EINVAL;
+
+		*tag_id = ib_spec->flow_tag.tag_id;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1955,6 +2118,7 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
 	struct mlx5_flow_spec *spec;
 	const void *ib_flow = (const void *)flow_attr + sizeof(*flow_attr);
 	unsigned int spec_index;
+	u32 flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
 	int err = 0;
 
 	if (!is_valid_attr(flow_attr))
@@ -1971,7 +2135,7 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
 
 	for (spec_index = 0; spec_index < flow_attr->num_of_specs; spec_index++) {
 		err = parse_flow_attr(spec->match_criteria,
-				      spec->match_value, ib_flow);
+				      spec->match_value, ib_flow, &flow_tag);
 		if (err < 0)
 			goto free;
 
@@ -1981,7 +2145,16 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
 	spec->match_criteria_enable = get_match_criteria_enable(spec->match_criteria);
 	flow_act.action = dst ? MLX5_FLOW_CONTEXT_ACTION_FWD_DEST :
 		MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
-	flow_act.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
+
+	if (flow_tag != MLX5_FS_DEFAULT_FLOW_TAG &&
+	    (flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT ||
+	     flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT)) {
+		mlx5_ib_warn(dev, "Flow tag %u and attribute type %x isn't allowed in leftovers\n",
+			     flow_tag, flow_attr->type);
+		err = -EINVAL;
+		goto free;
+	}
+	flow_act.flow_tag = flow_tag;
 	handler->rule = mlx5_add_flow_rules(ft, spec,
 					    &flow_act,
 					    dst, 1);
@@ -2451,6 +2624,35 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context,
 		ibdev->ib_active = false;
 }
 
+static int set_has_smi_cap(struct mlx5_ib_dev *dev)
+{
+	struct mlx5_hca_vport_context vport_ctx;
+	int err;
+	int port;
+
+	for (port = 1; port <= MLX5_CAP_GEN(dev->mdev, num_ports); port++) {
+		dev->mdev->port_caps[port - 1].has_smi = false;
+		if (MLX5_CAP_GEN(dev->mdev, port_type) ==
+		    MLX5_CAP_PORT_TYPE_IB) {
+			if (MLX5_CAP_GEN(dev->mdev, ib_virt)) {
+				err = mlx5_query_hca_vport_context(dev->mdev, 0,
+								   port, 0,
+								   &vport_ctx);
+				if (err) {
+					mlx5_ib_err(dev, "query_hca_vport_context for port=%d failed %d\n",
+						    port, err);
+					return err;
+				}
+				dev->mdev->port_caps[port - 1].has_smi =
+					vport_ctx.has_smi;
+			} else {
+				dev->mdev->port_caps[port - 1].has_smi = true;
+			}
+		}
+	}
+	return 0;
+}
+
 static void get_ext_port_caps(struct mlx5_ib_dev *dev)
 {
 	int port;
@@ -2475,6 +2677,10 @@ static int get_port_caps(struct mlx5_ib_dev *dev)
 	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);
@@ -2482,6 +2688,7 @@ static int get_port_caps(struct mlx5_ib_dev *dev)
 	}
 
 	for (port = 1; port <= MLX5_CAP_GEN(dev->mdev, num_ports); port++) {
+		memset(pprops, 0, sizeof(*pprops));
 		err = mlx5_ib_query_port(&dev->ib_dev, port, pprops);
 		if (err) {
 			mlx5_ib_warn(dev, "query_port %d failed %d\n",
@@ -2776,11 +2983,13 @@ static u32 get_core_cap_flags(struct ib_device *ibdev)
 	if (ll == IB_LINK_LAYER_INFINIBAND)
 		return RDMA_CORE_PORT_IBA_IB;
 
+	ret = RDMA_CORE_PORT_RAW_PACKET;
+
 	if (!(l3_type_cap & MLX5_ROCE_L3_TYPE_IPV4_CAP))
-		return 0;
+		return ret;
 
 	if (!(l3_type_cap & MLX5_ROCE_L3_TYPE_IPV6_CAP))
-		return 0;
+		return ret;
 
 	if (roce_version_cap & MLX5_ROCE_VERSION_1_CAP)
 		ret |= RDMA_CORE_PORT_IBA_ROCE;
@@ -2799,7 +3008,9 @@ static int mlx5_port_immutable(struct ib_device *ibdev, u8 port_num,
 	enum rdma_link_layer ll = mlx5_ib_port_link_layer(ibdev, port_num);
 	int err;
 
-	err = mlx5_ib_query_port(ibdev, port_num, &attr);
+	immutable->core_cap_flags = get_core_cap_flags(ibdev);
+
+	err = ib_query_port(ibdev, port_num, &attr);
 	if (err)
 		return err;
 
@@ -2920,13 +3131,102 @@ static void mlx5_disable_eth(struct mlx5_ib_dev *dev)
 		mlx5_nic_vport_disable_roce(dev->mdev);
 }
 
+struct mlx5_ib_q_counter {
+	const char *name;
+	size_t offset;
+};
+
+#define INIT_Q_COUNTER(_name)		\
+	{ .name = #_name, .offset = MLX5_BYTE_OFF(query_q_counter_out, _name)}
+
+static const struct mlx5_ib_q_counter basic_q_cnts[] = {
+	INIT_Q_COUNTER(rx_write_requests),
+	INIT_Q_COUNTER(rx_read_requests),
+	INIT_Q_COUNTER(rx_atomic_requests),
+	INIT_Q_COUNTER(out_of_buffer),
+};
+
+static const struct mlx5_ib_q_counter out_of_seq_q_cnts[] = {
+	INIT_Q_COUNTER(out_of_sequence),
+};
+
+static const struct mlx5_ib_q_counter retrans_q_cnts[] = {
+	INIT_Q_COUNTER(duplicate_request),
+	INIT_Q_COUNTER(rnr_nak_retry_err),
+	INIT_Q_COUNTER(packet_seq_err),
+	INIT_Q_COUNTER(implied_nak_seq_err),
+	INIT_Q_COUNTER(local_ack_timeout_err),
+};
+
 static void mlx5_ib_dealloc_q_counters(struct mlx5_ib_dev *dev)
 {
 	unsigned int i;
 
-	for (i = 0; i < dev->num_ports; i++)
+	for (i = 0; i < dev->num_ports; i++) {
 		mlx5_core_dealloc_q_counter(dev->mdev,
-					    dev->port[i].q_cnt_id);
+					    dev->port[i].q_cnts.set_id);
+		kfree(dev->port[i].q_cnts.names);
+		kfree(dev->port[i].q_cnts.offsets);
+	}
+}
+
+static int __mlx5_ib_alloc_q_counters(struct mlx5_ib_dev *dev,
+				      const char ***names,
+				      size_t **offsets,
+				      u32 *num)
+{
+	u32 num_counters;
+
+	num_counters = ARRAY_SIZE(basic_q_cnts);
+
+	if (MLX5_CAP_GEN(dev->mdev, out_of_seq_cnt))
+		num_counters += ARRAY_SIZE(out_of_seq_q_cnts);
+
+	if (MLX5_CAP_GEN(dev->mdev, retransmission_q_counters))
+		num_counters += ARRAY_SIZE(retrans_q_cnts);
+
+	*names = kcalloc(num_counters, sizeof(**names), GFP_KERNEL);
+	if (!*names)
+		return -ENOMEM;
+
+	*offsets = kcalloc(num_counters, sizeof(**offsets), GFP_KERNEL);
+	if (!*offsets)
+		goto err_names;
+
+	*num = num_counters;
+
+	return 0;
+
+err_names:
+	kfree(*names);
+	return -ENOMEM;
+}
+
+static void mlx5_ib_fill_q_counters(struct mlx5_ib_dev *dev,
+				    const char **names,
+				    size_t *offsets)
+{
+	int i;
+	int j = 0;
+
+	for (i = 0; i < ARRAY_SIZE(basic_q_cnts); i++, j++) {
+		names[j] = basic_q_cnts[i].name;
+		offsets[j] = basic_q_cnts[i].offset;
+	}
+
+	if (MLX5_CAP_GEN(dev->mdev, out_of_seq_cnt)) {
+		for (i = 0; i < ARRAY_SIZE(out_of_seq_q_cnts); i++, j++) {
+			names[j] = out_of_seq_q_cnts[i].name;
+			offsets[j] = out_of_seq_q_cnts[i].offset;
+		}
+	}
+
+	if (MLX5_CAP_GEN(dev->mdev, retransmission_q_counters)) {
+		for (i = 0; i < ARRAY_SIZE(retrans_q_cnts); i++, j++) {
+			names[j] = retrans_q_cnts[i].name;
+			offsets[j] = retrans_q_cnts[i].offset;
+		}
+	}
 }
 
 static int mlx5_ib_alloc_q_counters(struct mlx5_ib_dev *dev)
@@ -2935,14 +3235,26 @@ static int mlx5_ib_alloc_q_counters(struct mlx5_ib_dev *dev)
 	int ret;
 
 	for (i = 0; i < dev->num_ports; i++) {
+		struct mlx5_ib_port *port = &dev->port[i];
+
 		ret = mlx5_core_alloc_q_counter(dev->mdev,
-						&dev->port[i].q_cnt_id);
+						&port->q_cnts.set_id);
 		if (ret) {
 			mlx5_ib_warn(dev,
 				     "couldn't allocate queue counter for port %d, err %d\n",
 				     i + 1, ret);
 			goto dealloc_counters;
 		}
+
+		ret = __mlx5_ib_alloc_q_counters(dev,
+						 &port->q_cnts.names,
+						 &port->q_cnts.offsets,
+						 &port->q_cnts.num_counters);
+		if (ret)
+			goto dealloc_counters;
+
+		mlx5_ib_fill_q_counters(dev, port->q_cnts.names,
+					port->q_cnts.offsets);
 	}
 
 	return 0;
@@ -2950,62 +3262,39 @@ static int mlx5_ib_alloc_q_counters(struct mlx5_ib_dev *dev)
 dealloc_counters:
 	while (--i >= 0)
 		mlx5_core_dealloc_q_counter(dev->mdev,
-					    dev->port[i].q_cnt_id);
+					    dev->port[i].q_cnts.set_id);
 
 	return ret;
 }
 
-static const char * const names[] = {
-	"rx_write_requests",
-	"rx_read_requests",
-	"rx_atomic_requests",
-	"out_of_buffer",
-	"out_of_sequence",
-	"duplicate_request",
-	"rnr_nak_retry_err",
-	"packet_seq_err",
-	"implied_nak_seq_err",
-	"local_ack_timeout_err",
-};
-
-static const size_t stats_offsets[] = {
-	MLX5_BYTE_OFF(query_q_counter_out, rx_write_requests),
-	MLX5_BYTE_OFF(query_q_counter_out, rx_read_requests),
-	MLX5_BYTE_OFF(query_q_counter_out, rx_atomic_requests),
-	MLX5_BYTE_OFF(query_q_counter_out, out_of_buffer),
-	MLX5_BYTE_OFF(query_q_counter_out, out_of_sequence),
-	MLX5_BYTE_OFF(query_q_counter_out, duplicate_request),
-	MLX5_BYTE_OFF(query_q_counter_out, rnr_nak_retry_err),
-	MLX5_BYTE_OFF(query_q_counter_out, packet_seq_err),
-	MLX5_BYTE_OFF(query_q_counter_out, implied_nak_seq_err),
-	MLX5_BYTE_OFF(query_q_counter_out, local_ack_timeout_err),
-};
-
 static struct rdma_hw_stats *mlx5_ib_alloc_hw_stats(struct ib_device *ibdev,
 						    u8 port_num)
 {
-	BUILD_BUG_ON(ARRAY_SIZE(names) != ARRAY_SIZE(stats_offsets));
+	struct mlx5_ib_dev *dev = to_mdev(ibdev);
+	struct mlx5_ib_port *port = &dev->port[port_num - 1];
 
 	/* We support only per port stats */
 	if (port_num == 0)
 		return NULL;
 
-	return rdma_alloc_hw_stats_struct(names, ARRAY_SIZE(names),
+	return rdma_alloc_hw_stats_struct(port->q_cnts.names,
+					  port->q_cnts.num_counters,
 					  RDMA_HW_STATS_DEFAULT_LIFESPAN);
 }
 
 static int mlx5_ib_get_hw_stats(struct ib_device *ibdev,
 				struct rdma_hw_stats *stats,
-				u8 port, int index)
+				u8 port_num, int index)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
+	struct mlx5_ib_port *port = &dev->port[port_num - 1];
 	int outlen = MLX5_ST_SZ_BYTES(query_q_counter_out);
 	void *out;
 	__be32 val;
 	int ret;
 	int i;
 
-	if (!port || !stats)
+	if (!stats)
 		return -ENOSYS;
 
 	out = mlx5_vzalloc(outlen);
@@ -3013,18 +3302,19 @@ static int mlx5_ib_get_hw_stats(struct ib_device *ibdev,
 		return -ENOMEM;
 
 	ret = mlx5_core_query_q_counter(dev->mdev,
-					dev->port[port - 1].q_cnt_id, 0,
+					port->q_cnts.set_id, 0,
 					out, outlen);
 	if (ret)
 		goto free;
 
-	for (i = 0; i < ARRAY_SIZE(names); i++) {
-		val = *(__be32 *)(out + stats_offsets[i]);
+	for (i = 0; i < port->q_cnts.num_counters; i++) {
+		val = *(__be32 *)(out + port->q_cnts.offsets[i]);
 		stats->value[i] = (u64)be32_to_cpu(val);
 	}
+
 free:
 	kvfree(out);
-	return ARRAY_SIZE(names);
+	return port->q_cnts.num_counters;
 }
 
 static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
@@ -3060,8 +3350,6 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	if (mlx5_use_mad_ifc(dev))
 		get_ext_port_caps(dev);
 
-	MLX5_INIT_DOORBELL_LOCK(&dev->uar_lock);
-
 	if (!mlx5_lag_is_active(mdev))
 		name = "mlx5_%d";
 	else
@@ -3178,8 +3466,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 			(1ull << IB_USER_VERBS_CMD_DEALLOC_MW);
 	}
 
-	if (MLX5_CAP_GEN(dev->mdev, out_of_seq_cnt) &&
-	    MLX5_CAP_GEN(dev->mdev, retransmission_q_counters)) {
+	if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt)) {
 		dev->ib_dev.get_hw_stats	= mlx5_ib_get_hw_stats;
 		dev->ib_dev.alloc_hw_stats	= mlx5_ib_alloc_hw_stats;
 	}
@@ -3233,13 +3520,27 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	if (err)
 		goto err_rsrc;
 
-	err = mlx5_ib_alloc_q_counters(dev);
+	if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt)) {
+		err = mlx5_ib_alloc_q_counters(dev);
+		if (err)
+			goto err_odp;
+	}
+
+	dev->mdev->priv.uar = mlx5_get_uars_page(dev->mdev);
+	if (!dev->mdev->priv.uar)
+		goto err_q_cnt;
+
+	err = mlx5_alloc_bfreg(dev->mdev, &dev->bfreg, false, false);
+	if (err)
+		goto err_uar_page;
+
+	err = mlx5_alloc_bfreg(dev->mdev, &dev->fp_bfreg, false, true);
 	if (err)
-		goto err_odp;
+		goto err_bfreg;
 
 	err = ib_register_device(&dev->ib_dev, NULL);
 	if (err)
-		goto err_q_cnt;
+		goto err_fp_bfreg;
 
 	err = create_umr_res(dev);
 	if (err)
@@ -3262,8 +3563,18 @@ err_umrc:
 err_dev:
 	ib_unregister_device(&dev->ib_dev);
 
+err_fp_bfreg:
+	mlx5_free_bfreg(dev->mdev, &dev->fp_bfreg);
+
+err_bfreg:
+	mlx5_free_bfreg(dev->mdev, &dev->bfreg);
+
+err_uar_page:
+	mlx5_put_uars_page(dev->mdev, dev->mdev->priv.uar);
+
 err_q_cnt:
-	mlx5_ib_dealloc_q_counters(dev);
+	if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt))
+		mlx5_ib_dealloc_q_counters(dev);
 
 err_odp:
 	mlx5_ib_odp_remove_one(dev);
@@ -3293,7 +3604,11 @@ static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context)
 
 	mlx5_remove_netdev_notifier(dev);
 	ib_unregister_device(&dev->ib_dev);
-	mlx5_ib_dealloc_q_counters(dev);
+	mlx5_free_bfreg(dev->mdev, &dev->fp_bfreg);
+	mlx5_free_bfreg(dev->mdev, &dev->bfreg);
+	mlx5_put_uars_page(dev->mdev, mdev->priv.uar);
+	if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt))
+		mlx5_ib_dealloc_q_counters(dev);
 	destroy_umrc_res(dev);
 	mlx5_ib_odp_remove_one(dev);
 	destroy_dev_resources(&dev->devr);
@@ -3307,6 +3622,9 @@ static struct mlx5_interface mlx5_ib_interface = {
 	.add            = mlx5_ib_add,
 	.remove         = mlx5_ib_remove,
 	.event          = mlx5_ib_event,
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	.pfault		= mlx5_ib_pfault,
+#endif
 	.protocol	= MLX5_INTERFACE_PROTOCOL_IB,
 };
 
@@ -3314,28 +3632,16 @@ static int __init mlx5_ib_init(void)
 {
 	int err;
 
-	if (deprecated_prof_sel != 2)
-		pr_warn("prof_sel is deprecated for mlx5_ib, set it for mlx5_core\n");
-
-	err = mlx5_ib_odp_init();
-	if (err)
-		return err;
+	mlx5_ib_odp_init();
 
 	err = mlx5_register_interface(&mlx5_ib_interface);
-	if (err)
-		goto clean_odp;
-
-	return err;
 
-clean_odp:
-	mlx5_ib_odp_cleanup();
 	return err;
 }
 
 static void __exit mlx5_ib_cleanup(void)
 {
 	mlx5_unregister_interface(&mlx5_ib_interface);
-	mlx5_ib_odp_cleanup();
 }
 
 module_init(mlx5_ib_init);