1 files changed, 191 insertions, 58 deletions

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 340290b883fe..0569bcab02d4 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -52,6 +52,7 @@
 #include <linux/mlx5/port.h>
 #include <linux/mlx5/vport.h>
 #include <linux/mlx5/fs.h>
+#include <linux/mlx5/eswitch.h>
 #include <linux/list.h>
 #include <rdma/ib_smi.h>
 #include <rdma/ib_umem.h>
@@ -888,7 +889,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	}
 	props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS;
 	if (MLX5_CAP_GEN(mdev, sho)) {
-		props->device_cap_flags |= IB_DEVICE_SIGNATURE_HANDOVER;
+		props->device_cap_flags |= IB_DEVICE_INTEGRITY_HANDOVER;
 		/* At this stage no support for signature handover */
 		props->sig_prot_cap = IB_PROT_T10DIF_TYPE_1 |
 				      IB_PROT_T10DIF_TYPE_2 |
@@ -1008,6 +1009,8 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	props->max_srq_sge	   = max_rq_sg - 1;
 	props->max_fast_reg_page_list_len =
 		1 << MLX5_CAP_GEN(mdev, log_max_klm_list_size);
+	props->max_pi_fast_reg_page_list_len =
+		props->max_fast_reg_page_list_len / 2;
 	get_atomic_caps_qp(dev, props);
 	props->masked_atomic_cap   = IB_ATOMIC_NONE;
 	props->max_mcast_grp	   = 1 << MLX5_CAP_GEN(mdev, log_max_mcg);
@@ -1020,7 +1023,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	props->timestamp_mask = 0x7FFFFFFFFFFFFFFFULL;
 
 	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
-		if (MLX5_CAP_GEN(mdev, pg))
+		if (dev->odp_caps.general_caps & IB_ODP_SUPPORT)
 			props->device_cap_flags |= IB_DEVICE_ON_DEMAND_PAGING;
 		props->odp_caps = dev->odp_caps;
 	}
@@ -1043,15 +1046,19 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	}
 
 	if (MLX5_CAP_GEN(mdev, tag_matching)) {
-		props->tm_caps.max_rndv_hdr_size = MLX5_TM_MAX_RNDV_MSG_SIZE;
 		props->tm_caps.max_num_tags =
 			(1 << MLX5_CAP_GEN(mdev, log_tag_matching_list_sz)) - 1;
-		props->tm_caps.flags = IB_TM_CAP_RC;
 		props->tm_caps.max_ops =
 			1 << MLX5_CAP_GEN(mdev, log_max_qp_sz);
 		props->tm_caps.max_sge = MLX5_TM_MAX_SGE;
 	}
 
+	if (MLX5_CAP_GEN(mdev, tag_matching) &&
+	    MLX5_CAP_GEN(mdev, rndv_offload_rc)) {
+		props->tm_caps.flags = IB_TM_CAP_RNDV_RC;
+		props->tm_caps.max_rndv_hdr_size = MLX5_TM_MAX_RNDV_MSG_SIZE;
+	}
+
 	if (MLX5_CAP_GEN(dev->mdev, cq_moderation)) {
 		props->cq_caps.max_cq_moderation_count =
 						MLX5_MAX_CQ_COUNT;
@@ -2666,11 +2673,15 @@ int parse_flow_flow_action(struct mlx5_ib_flow_action *maction,
 	}
 }
 
-static int parse_flow_attr(struct mlx5_core_dev *mdev, u32 *match_c,
-			   u32 *match_v, const union ib_flow_spec *ib_spec,
+static int parse_flow_attr(struct mlx5_core_dev *mdev,
+			   struct mlx5_flow_spec *spec,
+			   const union ib_flow_spec *ib_spec,
 			   const struct ib_flow_attr *flow_attr,
 			   struct mlx5_flow_act *action, u32 prev_type)
 {
+	struct mlx5_flow_context *flow_context = &spec->flow_context;
+	u32 *match_c = spec->match_criteria;
+	u32 *match_v = spec->match_value;
 	void *misc_params_c = MLX5_ADDR_OF(fte_match_param, match_c,
 					   misc_parameters);
 	void *misc_params_v = MLX5_ADDR_OF(fte_match_param, match_v,
@@ -2989,8 +3000,8 @@ static int parse_flow_attr(struct mlx5_core_dev *mdev, u32 *match_c,
 		if (ib_spec->flow_tag.tag_id >= BIT(24))
 			return -EINVAL;
 
-		action->flow_tag = ib_spec->flow_tag.tag_id;
-		action->flags |= FLOW_ACT_HAS_TAG;
+		flow_context->flow_tag = ib_spec->flow_tag.tag_id;
+		flow_context->flags |= FLOW_CONTEXT_HAS_TAG;
 		break;
 	case IB_FLOW_SPEC_ACTION_DROP:
 		if (FIELDS_NOT_SUPPORTED(ib_spec->drop,
@@ -3084,7 +3095,8 @@ is_valid_esp_aes_gcm(struct mlx5_core_dev *mdev,
 		return VALID_SPEC_NA;
 
 	return is_crypto && is_ipsec &&
-		(!egress || (!is_drop && !(flow_act->flags & FLOW_ACT_HAS_TAG))) ?
+		(!egress || (!is_drop &&
+			     !(spec->flow_context.flags & FLOW_CONTEXT_HAS_TAG))) ?
 		VALID_SPEC_VALID : VALID_SPEC_INVALID;
 }
 
@@ -3252,11 +3264,14 @@ static struct mlx5_ib_flow_prio *get_flow_table(struct mlx5_ib_dev *dev,
 	int max_table_size;
 	int num_entries;
 	int num_groups;
+	bool esw_encap;
 	u32 flags = 0;
 	int priority;
 
 	max_table_size = BIT(MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev,
 						       log_max_ft_size));
+	esw_encap = mlx5_eswitch_get_encap_mode(dev->mdev) !=
+		DEVLINK_ESWITCH_ENCAP_MODE_NONE;
 	if (flow_attr->type == IB_FLOW_ATTR_NORMAL) {
 		enum mlx5_flow_namespace_type fn_type;
 
@@ -3269,10 +3284,10 @@ 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->is_rep &&
+			if (!dev->is_rep && !esw_encap &&
 			    MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev, decap))
 				flags |= MLX5_FLOW_TABLE_TUNNEL_EN_DECAP;
-			if (!dev->is_rep &&
+			if (!dev->is_rep && !esw_encap &&
 			    MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev,
 					reformat_l3_tunnel_to_l2))
 				flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
@@ -3282,7 +3297,7 @@ 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->is_rep &&
+			if (!dev->is_rep && !esw_encap &&
 			    MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev, reformat))
 				flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
 		}
@@ -3464,6 +3479,37 @@ free:
 	return ret;
 }
 
+static void mlx5_ib_set_rule_source_port(struct mlx5_ib_dev *dev,
+					 struct mlx5_flow_spec *spec,
+					 struct mlx5_eswitch_rep *rep)
+{
+	struct mlx5_eswitch *esw = dev->mdev->priv.eswitch;
+	void *misc;
+
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				    misc_parameters_2);
+
+		MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0,
+			 mlx5_eswitch_get_vport_metadata_for_match(esw,
+								   rep->vport));
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    misc_parameters_2);
+
+		MLX5_SET_TO_ONES(fte_match_set_misc2, misc, metadata_reg_c_0);
+	} else {
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				    misc_parameters);
+
+		MLX5_SET(fte_match_set_misc, misc, source_port, 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);
+	}
+}
+
 static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 						      struct mlx5_ib_flow_prio *ft_prio,
 						      const struct ib_flow_attr *flow_attr,
@@ -3473,7 +3519,7 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 {
 	struct mlx5_flow_table	*ft = ft_prio->flow_table;
 	struct mlx5_ib_flow_handler *handler;
-	struct mlx5_flow_act flow_act = {.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG};
+	struct mlx5_flow_act flow_act = {};
 	struct mlx5_flow_spec *spec;
 	struct mlx5_flow_destination dest_arr[2] = {};
 	struct mlx5_flow_destination *rule_dst = dest_arr;
@@ -3504,8 +3550,7 @@ 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(dev->mdev, spec->match_criteria,
-				      spec->match_value,
+		err = parse_flow_attr(dev->mdev, spec,
 				      ib_flow, flow_attr, &flow_act,
 				      prev_type);
 		if (err < 0)
@@ -3519,19 +3564,15 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 		set_underlay_qp(dev, spec, underlay_qpn);
 
 	if (dev->is_rep) {
-		void *misc;
+		struct mlx5_eswitch_rep *rep;
 
-		if (!dev->port[flow_attr->port - 1].rep) {
+		rep = dev->port[flow_attr->port - 1].rep;
+		if (!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->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);
+
+		mlx5_ib_set_rule_source_port(dev, spec, rep);
 	}
 
 	spec->match_criteria_enable = get_match_criteria_enable(spec->match_criteria);
@@ -3572,11 +3613,11 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 					MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
 	}
 
-	if ((flow_act.flags & FLOW_ACT_HAS_TAG)  &&
+	if ((spec->flow_context.flags & FLOW_CONTEXT_HAS_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_act.flow_tag, flow_attr->type);
+			     spec->flow_context.flow_tag, flow_attr->type);
 		err = -EINVAL;
 		goto free;
 	}
@@ -3892,6 +3933,7 @@ _get_flow_table(struct mlx5_ib_dev *dev,
 	struct mlx5_flow_namespace *ns = NULL;
 	struct mlx5_ib_flow_prio *prio = NULL;
 	int max_table_size = 0;
+	bool esw_encap;
 	u32 flags = 0;
 	int priority;
 
@@ -3900,22 +3942,30 @@ _get_flow_table(struct mlx5_ib_dev *dev,
 	else
 		priority = ib_prio_to_core_prio(fs_matcher->priority, false);
 
+	esw_encap = mlx5_eswitch_get_encap_mode(dev->mdev) !=
+		DEVLINK_ESWITCH_ENCAP_MODE_NONE;
 	if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_BYPASS) {
 		max_table_size = BIT(MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev,
 					log_max_ft_size));
-		if (MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev, decap))
+		if (MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev, decap) && !esw_encap)
 			flags |= MLX5_FLOW_TABLE_TUNNEL_EN_DECAP;
 		if (MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev,
-					      reformat_l3_tunnel_to_l2))
+					      reformat_l3_tunnel_to_l2) &&
+		    !esw_encap)
 			flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
 	} 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))
+		if (MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev, reformat) && !esw_encap)
 			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));
+		if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev->mdev, decap) && esw_encap)
+			flags |= MLX5_FLOW_TABLE_TUNNEL_EN_DECAP;
+		if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev->mdev, reformat_l3_tunnel_to_l2) &&
+		    esw_encap)
+			flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
 		priority = FDB_BYPASS_PATH;
 	}
 
@@ -3947,6 +3997,7 @@ _create_raw_flow_rule(struct mlx5_ib_dev *dev,
 		      struct mlx5_ib_flow_prio *ft_prio,
 		      struct mlx5_flow_destination *dst,
 		      struct mlx5_ib_flow_matcher  *fs_matcher,
+		      struct mlx5_flow_context *flow_context,
 		      struct mlx5_flow_act *flow_act,
 		      void *cmd_in, int inlen,
 		      int dst_num)
@@ -3969,6 +4020,7 @@ _create_raw_flow_rule(struct mlx5_ib_dev *dev,
 	memcpy(spec->match_criteria, fs_matcher->matcher_mask.match_params,
 	       fs_matcher->mask_len);
 	spec->match_criteria_enable = fs_matcher->match_criteria_enable;
+	spec->flow_context = *flow_context;
 
 	handler->rule = mlx5_add_flow_rules(ft, spec,
 					    flow_act, dst, dst_num);
@@ -4033,6 +4085,7 @@ static bool raw_fs_is_multicast(struct mlx5_ib_flow_matcher *fs_matcher,
 struct mlx5_ib_flow_handler *
 mlx5_ib_raw_fs_rule_add(struct mlx5_ib_dev *dev,
 			struct mlx5_ib_flow_matcher *fs_matcher,
+			struct mlx5_flow_context *flow_context,
 			struct mlx5_flow_act *flow_act,
 			u32 counter_id,
 			void *cmd_in, int inlen, int dest_id,
@@ -4085,7 +4138,8 @@ mlx5_ib_raw_fs_rule_add(struct mlx5_ib_dev *dev,
 		dst_num++;
 	}
 
-	handler = _create_raw_flow_rule(dev, ft_prio, dst, fs_matcher, flow_act,
+	handler = _create_raw_flow_rule(dev, ft_prio, dst, fs_matcher,
+					flow_context, flow_act,
 					cmd_in, inlen, dst_num);
 
 	if (IS_ERR(handler)) {
@@ -4457,7 +4511,7 @@ static void mlx5_ib_handle_internal_error(struct mlx5_ib_dev *ibdev)
 	 * lock/unlock above locks Now need to arm all involved CQs.
 	 */
 	list_for_each_entry(mcq, &cq_armed_list, reset_notify) {
-		mcq->comp(mcq);
+		mcq->comp(mcq, NULL);
 	}
 	spin_unlock_irqrestore(&ibdev->reset_flow_resource_lock, flags);
 }
@@ -4676,7 +4730,7 @@ static int __get_port_caps(struct mlx5_ib_dev *dev, u8 port)
 	int err = -ENOMEM;
 	struct ib_udata uhw = {.inlen = 0, .outlen = 0};
 
-	pprops = kmalloc(sizeof(*pprops), GFP_KERNEL);
+	pprops = kzalloc(sizeof(*pprops), GFP_KERNEL);
 	if (!pprops)
 		goto out;
 
@@ -4690,7 +4744,6 @@ static int __get_port_caps(struct mlx5_ib_dev *dev, u8 port)
 		goto out;
 	}
 
-	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",
@@ -4891,18 +4944,19 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 	if (ret)
 		goto error0;
 
-	devr->c0 = mlx5_ib_create_cq(&dev->ib_dev, &cq_attr, NULL);
-	if (IS_ERR(devr->c0)) {
-		ret = PTR_ERR(devr->c0);
+	devr->c0 = rdma_zalloc_drv_obj(ibdev, ib_cq);
+	if (!devr->c0) {
+		ret = -ENOMEM;
 		goto error1;
 	}
-	devr->c0->device        = &dev->ib_dev;
-	devr->c0->uobject       = NULL;
-	devr->c0->comp_handler  = NULL;
-	devr->c0->event_handler = NULL;
-	devr->c0->cq_context    = NULL;
+
+	devr->c0->device = &dev->ib_dev;
 	atomic_set(&devr->c0->usecnt, 0);
 
+	ret = mlx5_ib_create_cq(devr->c0, &cq_attr, NULL);
+	if (ret)
+		goto err_create_cq;
+
 	devr->x0 = mlx5_ib_alloc_xrcd(&dev->ib_dev, NULL);
 	if (IS_ERR(devr->x0)) {
 		ret = PTR_ERR(devr->x0);
@@ -4994,6 +5048,8 @@ error3:
 	mlx5_ib_dealloc_xrcd(devr->x0, NULL);
 error2:
 	mlx5_ib_destroy_cq(devr->c0, NULL);
+err_create_cq:
+	kfree(devr->c0);
 error1:
 	mlx5_ib_dealloc_pd(devr->p0, NULL);
 error0:
@@ -5012,6 +5068,7 @@ static void destroy_dev_resources(struct mlx5_ib_resources *devr)
 	mlx5_ib_dealloc_xrcd(devr->x0, NULL);
 	mlx5_ib_dealloc_xrcd(devr->x1, NULL);
 	mlx5_ib_destroy_cq(devr->c0, NULL);
+	kfree(devr->c0);
 	mlx5_ib_dealloc_pd(devr->p0, NULL);
 	kfree(devr->p0);
 
@@ -5424,7 +5481,8 @@ static struct rdma_hw_stats *mlx5_ib_alloc_hw_stats(struct ib_device *ibdev,
 
 static int mlx5_ib_query_q_counters(struct mlx5_core_dev *mdev,
 				    struct mlx5_ib_port *port,
-				    struct rdma_hw_stats *stats)
+				    struct rdma_hw_stats *stats,
+				    u16 set_id)
 {
 	int outlen = MLX5_ST_SZ_BYTES(query_q_counter_out);
 	void *out;
@@ -5435,9 +5493,7 @@ static int mlx5_ib_query_q_counters(struct mlx5_core_dev *mdev,
 	if (!out)
 		return -ENOMEM;
 
-	ret = mlx5_core_query_q_counter(mdev,
-					port->cnts.set_id, 0,
-					out, outlen);
+	ret = mlx5_core_query_q_counter(mdev, set_id, 0, out, outlen);
 	if (ret)
 		goto free;
 
@@ -5497,7 +5553,8 @@ static int mlx5_ib_get_hw_stats(struct ib_device *ibdev,
 		       port->cnts.num_ext_ppcnt_counters;
 
 	/* q_counters are per IB device, query the master mdev */
-	ret = mlx5_ib_query_q_counters(dev->mdev, port, stats);
+	ret = mlx5_ib_query_q_counters(dev->mdev, port, stats,
+				       port->cnts.set_id);
 	if (ret)
 		return ret;
 
@@ -5533,6 +5590,68 @@ done:
 	return num_counters;
 }
 
+static struct rdma_hw_stats *
+mlx5_ib_counter_alloc_stats(struct rdma_counter *counter)
+{
+	struct mlx5_ib_dev *dev = to_mdev(counter->device);
+	struct mlx5_ib_port *port = &dev->port[counter->port - 1];
+
+	/* Q counters are in the beginning of all counters */
+	return rdma_alloc_hw_stats_struct(port->cnts.names,
+					  port->cnts.num_q_counters,
+					  RDMA_HW_STATS_DEFAULT_LIFESPAN);
+}
+
+static int mlx5_ib_counter_update_stats(struct rdma_counter *counter)
+{
+	struct mlx5_ib_dev *dev = to_mdev(counter->device);
+	struct mlx5_ib_port *port = &dev->port[counter->port - 1];
+
+	return mlx5_ib_query_q_counters(dev->mdev, port,
+					counter->stats, counter->id);
+}
+
+static int mlx5_ib_counter_bind_qp(struct rdma_counter *counter,
+				   struct ib_qp *qp)
+{
+	struct mlx5_ib_dev *dev = to_mdev(qp->device);
+	u16 cnt_set_id = 0;
+	int err;
+
+	if (!counter->id) {
+		err = mlx5_cmd_alloc_q_counter(dev->mdev,
+					       &cnt_set_id,
+					       MLX5_SHARED_RESOURCE_UID);
+		if (err)
+			return err;
+		counter->id = cnt_set_id;
+	}
+
+	err = mlx5_ib_qp_set_counter(qp, counter);
+	if (err)
+		goto fail_set_counter;
+
+	return 0;
+
+fail_set_counter:
+	mlx5_core_dealloc_q_counter(dev->mdev, cnt_set_id);
+	counter->id = 0;
+
+	return err;
+}
+
+static int mlx5_ib_counter_unbind_qp(struct ib_qp *qp)
+{
+	return mlx5_ib_qp_set_counter(qp, NULL);
+}
+
+static int mlx5_ib_counter_dealloc(struct rdma_counter *counter)
+{
+	struct mlx5_ib_dev *dev = to_mdev(counter->device);
+
+	return mlx5_core_dealloc_q_counter(dev->mdev, counter->id);
+}
+
 static int mlx5_ib_rn_get_params(struct ib_device *device, u8 port_num,
 				 enum rdma_netdev_t type,
 				 struct rdma_netdev_alloc_params *params)
@@ -5683,13 +5802,12 @@ static void mlx5_ib_unbind_slave_port(struct mlx5_ib_dev *ibdev,
 		return;
 	}
 
-	if (mpi->mdev_events.notifier_call)
-		mlx5_notifier_unregister(mpi->mdev, &mpi->mdev_events);
-	mpi->mdev_events.notifier_call = NULL;
-
 	mpi->ibdev = NULL;
 
 	spin_unlock(&port->mp.mpi_lock);
+	if (mpi->mdev_events.notifier_call)
+		mlx5_notifier_unregister(mpi->mdev, &mpi->mdev_events);
+	mpi->mdev_events.notifier_call = NULL;
 	mlx5_remove_netdev_notifier(ibdev, port_num);
 	spin_lock(&port->mp.mpi_lock);
 
@@ -6021,6 +6139,8 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 		dev->port[i].roce.last_port_state = IB_PORT_DOWN;
 	}
 
+	mlx5_ib_internal_fill_odp_caps(dev);
+
 	err = mlx5_ib_init_multiport_master(dev);
 	if (err)
 		return err;
@@ -6044,7 +6164,6 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 	if (mlx5_use_mad_ifc(dev))
 		get_ext_port_caps(dev);
 
-	dev->ib_dev.owner		= THIS_MODULE;
 	dev->ib_dev.node_type		= RDMA_NODE_IB_CA;
 	dev->ib_dev.local_dma_lkey	= 0 /* not supported for now */;
 	dev->ib_dev.phys_port_cnt	= dev->num_ports;
@@ -6124,8 +6243,13 @@ static void mlx5_ib_stage_flow_db_cleanup(struct mlx5_ib_dev *dev)
 }
 
 static const struct ib_device_ops mlx5_ib_dev_ops = {
+	.owner = THIS_MODULE,
+	.driver_id = RDMA_DRIVER_MLX5,
+	.uverbs_abi_ver	= MLX5_IB_UVERBS_ABI_VERSION,
+
 	.add_gid = mlx5_ib_add_gid,
 	.alloc_mr = mlx5_ib_alloc_mr,
+	.alloc_mr_integrity = mlx5_ib_alloc_mr_integrity,
 	.alloc_pd = mlx5_ib_alloc_pd,
 	.alloc_ucontext = mlx5_ib_alloc_ucontext,
 	.attach_mcast = mlx5_ib_mcg_attach,
@@ -6155,6 +6279,7 @@ static const struct ib_device_ops mlx5_ib_dev_ops = {
 	.get_dma_mr = mlx5_ib_get_dma_mr,
 	.get_link_layer = mlx5_ib_port_link_layer,
 	.map_mr_sg = mlx5_ib_map_mr_sg,
+	.map_mr_sg_pi = mlx5_ib_map_mr_sg_pi,
 	.mmap = mlx5_ib_mmap,
 	.modify_cq = mlx5_ib_modify_cq,
 	.modify_device = mlx5_ib_modify_device,
@@ -6179,6 +6304,7 @@ static const struct ib_device_ops mlx5_ib_dev_ops = {
 	.resize_cq = mlx5_ib_resize_cq,
 
 	INIT_RDMA_OBJ_SIZE(ib_ah, mlx5_ib_ah, ibah),
+	INIT_RDMA_OBJ_SIZE(ib_cq, mlx5_ib_cq, ibcq),
 	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),
@@ -6221,7 +6347,6 @@ static int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev)
 	struct mlx5_core_dev *mdev = dev->mdev;
 	int err;
 
-	dev->ib_dev.uverbs_abi_ver	= MLX5_IB_UVERBS_ABI_VERSION;
 	dev->ib_dev.uverbs_cmd_mask	=
 		(1ull << IB_USER_VERBS_CMD_GET_CONTEXT)		|
 		(1ull << IB_USER_VERBS_CMD_QUERY_DEVICE)	|
@@ -6290,7 +6415,6 @@ static int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev)
 	if (mlx5_accel_ipsec_device_caps(dev->mdev) &
 	    MLX5_ACCEL_IPSEC_CAP_DEVICE)
 		ib_set_device_ops(&dev->ib_dev, &mlx5_ib_dev_flow_ipsec_ops);
-	dev->ib_dev.driver_id = RDMA_DRIVER_MLX5;
 	ib_set_device_ops(&dev->ib_dev, &mlx5_ib_dev_ops);
 
 	if (IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS))
@@ -6305,6 +6429,8 @@ static int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev)
 	     MLX5_CAP_GEN(dev->mdev, disable_local_lb_mc)))
 		mutex_init(&dev->lb.mutex);
 
+	dev->ib_dev.use_cq_dim = true;
+
 	return 0;
 }
 
@@ -6439,8 +6565,6 @@ static void mlx5_ib_stage_dev_res_cleanup(struct mlx5_ib_dev *dev)
 
 static int mlx5_ib_stage_odp_init(struct mlx5_ib_dev *dev)
 {
-	mlx5_ib_internal_fill_odp_caps(dev);
-
 	return mlx5_ib_odp_init_one(dev);
 }
 
@@ -6452,6 +6576,11 @@ static void mlx5_ib_stage_odp_cleanup(struct mlx5_ib_dev *dev)
 static const struct ib_device_ops mlx5_ib_dev_hw_stats_ops = {
 	.alloc_hw_stats = mlx5_ib_alloc_hw_stats,
 	.get_hw_stats = mlx5_ib_get_hw_stats,
+	.counter_bind_qp = mlx5_ib_counter_bind_qp,
+	.counter_unbind_qp = mlx5_ib_counter_unbind_qp,
+	.counter_dealloc = mlx5_ib_counter_dealloc,
+	.counter_alloc_stats = mlx5_ib_counter_alloc_stats,
+	.counter_update_stats = mlx5_ib_counter_update_stats,
 };
 
 static int mlx5_ib_stage_counters_init(struct mlx5_ib_dev *dev)
@@ -6572,15 +6701,19 @@ static int mlx5_ib_stage_devx_init(struct mlx5_ib_dev *dev)
 	int uid;
 
 	uid = mlx5_ib_devx_create(dev, false);
-	if (uid > 0)
+	if (uid > 0) {
 		dev->devx_whitelist_uid = uid;
+		mlx5_ib_devx_init_event_table(dev);
+	}
 
 	return 0;
 }
 static void mlx5_ib_stage_devx_cleanup(struct mlx5_ib_dev *dev)
 {
-	if (dev->devx_whitelist_uid)
+	if (dev->devx_whitelist_uid) {
+		mlx5_ib_devx_cleanup_event_table(dev);
 		mlx5_ib_devx_destroy(dev, dev->devx_whitelist_uid);
+	}
 }
 
 void __mlx5_ib_remove(struct mlx5_ib_dev *dev,
@@ -6779,7 +6912,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	printk_once(KERN_INFO "%s", mlx5_version);
 
 	if (MLX5_ESWITCH_MANAGER(mdev) &&
-	    mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) {
+	    mlx5_ib_eswitch_mode(mdev->priv.eswitch) == MLX5_ESWITCH_OFFLOADS) {
 		if (!mlx5_core_mp_enabled(mdev))
 			mlx5_ib_register_vport_reps(mdev);
 		return mdev;