7 files changed, 433 insertions, 71 deletions

diff --git a/drivers/infiniband/hw/mlx5/counters.c b/drivers/infiniband/hw/mlx5/counters.c
index 1c06920505d2..93257fa5aae8 100644
--- a/drivers/infiniband/hw/mlx5/counters.c
+++ b/drivers/infiniband/hw/mlx5/counters.c
@@ -209,7 +209,8 @@ static const struct mlx5_ib_counters *get_counters(struct mlx5_ib_dev *dev,
 	     !vport_qcounters_supported(dev)) || !port_num)
 		return &dev->port[0].cnts;
 
-	return &dev->port[port_num - 1].cnts;
+	return is_mdev_switchdev_mode(dev->mdev) ?
+	       &dev->port[1].cnts : &dev->port[port_num - 1].cnts;
 }
 
 /**
@@ -262,7 +263,7 @@ static struct rdma_hw_stats *
 mlx5_ib_alloc_hw_port_stats(struct ib_device *ibdev, u32 port_num)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
-	const struct mlx5_ib_counters *cnts = &dev->port[port_num - 1].cnts;
+	const struct mlx5_ib_counters *cnts = get_counters(dev, port_num);
 
 	return do_alloc_stats(cnts);
 }
@@ -329,6 +330,7 @@ static int mlx5_ib_query_q_counters_vport(struct mlx5_ib_dev *dev,
 {
 	u32 out[MLX5_ST_SZ_DW(query_q_counter_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(query_q_counter_in)] = {};
+	struct mlx5_core_dev *mdev;
 	__be32 val;
 	int ret, i;
 
@@ -336,12 +338,16 @@ static int mlx5_ib_query_q_counters_vport(struct mlx5_ib_dev *dev,
 	    dev->port[port_num].rep->vport == MLX5_VPORT_UPLINK)
 		return 0;
 
+	mdev = mlx5_eswitch_get_core_dev(dev->port[port_num].rep->esw);
+	if (!mdev)
+		return -EOPNOTSUPP;
+
 	MLX5_SET(query_q_counter_in, in, opcode, MLX5_CMD_OP_QUERY_Q_COUNTER);
 	MLX5_SET(query_q_counter_in, in, other_vport, 1);
 	MLX5_SET(query_q_counter_in, in, vport_number,
 		 dev->port[port_num].rep->vport);
 	MLX5_SET(query_q_counter_in, in, aggregate, 1);
-	ret = mlx5_cmd_exec_inout(dev->mdev, query_q_counter, in, out);
+	ret = mlx5_cmd_exec_inout(mdev, query_q_counter, in, out);
 	if (ret)
 		return ret;
 
@@ -575,43 +581,53 @@ static void mlx5_ib_fill_counters(struct mlx5_ib_dev *dev,
 	bool is_vport = is_mdev_switchdev_mode(dev->mdev) &&
 			port_num != MLX5_VPORT_PF;
 	const struct mlx5_ib_counter *names;
-	int j = 0, i;
+	int j = 0, i, size;
 
 	names = is_vport ? vport_basic_q_cnts : basic_q_cnts;
-	for (i = 0; i < ARRAY_SIZE(basic_q_cnts); i++, j++) {
+	size = is_vport ? ARRAY_SIZE(vport_basic_q_cnts) :
+			  ARRAY_SIZE(basic_q_cnts);
+	for (i = 0; i < size; i++, j++) {
 		descs[j].name = names[i].name;
-		offsets[j] = basic_q_cnts[i].offset;
+		offsets[j] = names[i].offset;
 	}
 
 	names = is_vport ? vport_out_of_seq_q_cnts : out_of_seq_q_cnts;
+	size = is_vport ? ARRAY_SIZE(vport_out_of_seq_q_cnts) :
+			  ARRAY_SIZE(out_of_seq_q_cnts);
 	if (MLX5_CAP_GEN(dev->mdev, out_of_seq_cnt)) {
-		for (i = 0; i < ARRAY_SIZE(out_of_seq_q_cnts); i++, j++) {
+		for (i = 0; i < size; i++, j++) {
 			descs[j].name = names[i].name;
-			offsets[j] = out_of_seq_q_cnts[i].offset;
+			offsets[j] = names[i].offset;
 		}
 	}
 
 	names = is_vport ? vport_retrans_q_cnts : retrans_q_cnts;
+	size = is_vport ? ARRAY_SIZE(vport_retrans_q_cnts) :
+			  ARRAY_SIZE(retrans_q_cnts);
 	if (MLX5_CAP_GEN(dev->mdev, retransmission_q_counters)) {
-		for (i = 0; i < ARRAY_SIZE(retrans_q_cnts); i++, j++) {
+		for (i = 0; i < size; i++, j++) {
 			descs[j].name = names[i].name;
-			offsets[j] = retrans_q_cnts[i].offset;
+			offsets[j] = names[i].offset;
 		}
 	}
 
 	names = is_vport ? vport_extended_err_cnts : extended_err_cnts;
+	size = is_vport ? ARRAY_SIZE(vport_extended_err_cnts) :
+			  ARRAY_SIZE(extended_err_cnts);
 	if (MLX5_CAP_GEN(dev->mdev, enhanced_error_q_counters)) {
-		for (i = 0; i < ARRAY_SIZE(extended_err_cnts); i++, j++) {
+		for (i = 0; i < size; i++, j++) {
 			descs[j].name = names[i].name;
-			offsets[j] = extended_err_cnts[i].offset;
+			offsets[j] = names[i].offset;
 		}
 	}
 
 	names = is_vport ? vport_roce_accl_cnts : roce_accl_cnts;
+	size = is_vport ? ARRAY_SIZE(vport_roce_accl_cnts) :
+			  ARRAY_SIZE(roce_accl_cnts);
 	if (MLX5_CAP_GEN(dev->mdev, roce_accl)) {
-		for (i = 0; i < ARRAY_SIZE(roce_accl_cnts); i++, j++) {
+		for (i = 0; i < size; i++, j++) {
 			descs[j].name = names[i].name;
-			offsets[j] = roce_accl_cnts[i].offset;
+			offsets[j] = names[i].offset;
 		}
 	}
 
@@ -661,25 +677,37 @@ static void mlx5_ib_fill_counters(struct mlx5_ib_dev *dev,
 static int __mlx5_ib_alloc_counters(struct mlx5_ib_dev *dev,
 				    struct mlx5_ib_counters *cnts, u32 port_num)
 {
-	u32 num_counters, num_op_counters = 0;
+	bool is_vport = is_mdev_switchdev_mode(dev->mdev) &&
+			port_num != MLX5_VPORT_PF;
+	u32 num_counters, num_op_counters = 0, size;
 
-	num_counters = ARRAY_SIZE(basic_q_cnts);
+	size = is_vport ? ARRAY_SIZE(vport_basic_q_cnts) :
+			  ARRAY_SIZE(basic_q_cnts);
+	num_counters = size;
 
+	size = is_vport ? ARRAY_SIZE(vport_out_of_seq_q_cnts) :
+			  ARRAY_SIZE(out_of_seq_q_cnts);
 	if (MLX5_CAP_GEN(dev->mdev, out_of_seq_cnt))
-		num_counters += ARRAY_SIZE(out_of_seq_q_cnts);
+		num_counters += size;
 
+	size = is_vport ? ARRAY_SIZE(vport_retrans_q_cnts) :
+			  ARRAY_SIZE(retrans_q_cnts);
 	if (MLX5_CAP_GEN(dev->mdev, retransmission_q_counters))
-		num_counters += ARRAY_SIZE(retrans_q_cnts);
+		num_counters += size;
 
+	size = is_vport ? ARRAY_SIZE(vport_extended_err_cnts) :
+			  ARRAY_SIZE(extended_err_cnts);
 	if (MLX5_CAP_GEN(dev->mdev, enhanced_error_q_counters))
-		num_counters += ARRAY_SIZE(extended_err_cnts);
+		num_counters += size;
 
+	size = is_vport ? ARRAY_SIZE(vport_roce_accl_cnts) :
+			  ARRAY_SIZE(roce_accl_cnts);
 	if (MLX5_CAP_GEN(dev->mdev, roce_accl))
-		num_counters += ARRAY_SIZE(roce_accl_cnts);
+		num_counters += size;
 
 	cnts->num_q_counters = num_counters;
 
-	if (is_mdev_switchdev_mode(dev->mdev) && port_num != MLX5_VPORT_PF)
+	if (is_vport)
 		goto skip_non_qcounters;
 
 	if (MLX5_CAP_GEN(dev->mdev, cc_query_allowed)) {
@@ -725,11 +753,11 @@ err:
 static void mlx5_ib_dealloc_counters(struct mlx5_ib_dev *dev)
 {
 	u32 in[MLX5_ST_SZ_DW(dealloc_q_counter_in)] = {};
-	int num_cnt_ports;
+	int num_cnt_ports = dev->num_ports;
 	int i, j;
 
-	num_cnt_ports = (!is_mdev_switchdev_mode(dev->mdev) ||
-			 vport_qcounters_supported(dev)) ? dev->num_ports : 1;
+	if (is_mdev_switchdev_mode(dev->mdev))
+		num_cnt_ports = min(2, num_cnt_ports);
 
 	MLX5_SET(dealloc_q_counter_in, in, opcode,
 		 MLX5_CMD_OP_DEALLOC_Q_COUNTER);
@@ -761,15 +789,22 @@ static int mlx5_ib_alloc_counters(struct mlx5_ib_dev *dev)
 {
 	u32 out[MLX5_ST_SZ_DW(alloc_q_counter_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(alloc_q_counter_in)] = {};
-	int num_cnt_ports;
+	int num_cnt_ports = dev->num_ports;
 	int err = 0;
 	int i;
 	bool is_shared;
 
 	MLX5_SET(alloc_q_counter_in, in, opcode, MLX5_CMD_OP_ALLOC_Q_COUNTER);
 	is_shared = MLX5_CAP_GEN(dev->mdev, log_max_uctx) != 0;
-	num_cnt_ports = (!is_mdev_switchdev_mode(dev->mdev) ||
-			 vport_qcounters_supported(dev)) ? dev->num_ports : 1;
+
+	/*
+	 * In switchdev we need to allocate two ports, one that is used for
+	 * the device Q_counters and it is essentially the real Q_counters of
+	 * this device, while the other is used as a helper for PF to be able to
+	 * query all other vports.
+	 */
+	if (is_mdev_switchdev_mode(dev->mdev))
+		num_cnt_ports = min(2, num_cnt_ports);
 
 	for (i = 0; i < num_cnt_ports; i++) {
 		err = __mlx5_ib_alloc_counters(dev, &dev->port[i].cnts, i);
diff --git a/drivers/infiniband/hw/mlx5/fs.c b/drivers/infiniband/hw/mlx5/fs.c
index 3008632a6c20..1e419e080b53 100644
--- a/drivers/infiniband/hw/mlx5/fs.c
+++ b/drivers/infiniband/hw/mlx5/fs.c
@@ -695,8 +695,6 @@ static struct mlx5_ib_flow_prio *_get_prio(struct mlx5_ib_dev *dev,
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_flow_table *ft;
 
-	if (mlx5_ib_shared_ft_allowed(&dev->ib_dev))
-		ft_attr.uid = MLX5_SHARED_RESOURCE_UID;
 	ft_attr.prio = priority;
 	ft_attr.max_fte = num_entries;
 	ft_attr.flags = flags;
@@ -2025,6 +2023,237 @@ static int flow_matcher_cleanup(struct ib_uobject *uobject,
 	return 0;
 }
 
+static int steering_anchor_create_ft(struct mlx5_ib_dev *dev,
+				     struct mlx5_ib_flow_prio *ft_prio,
+				     enum mlx5_flow_namespace_type ns_type)
+{
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5_flow_namespace *ns;
+	struct mlx5_flow_table *ft;
+
+	if (ft_prio->anchor.ft)
+		return 0;
+
+	ns = mlx5_get_flow_namespace(dev->mdev, ns_type);
+	if (!ns)
+		return -EOPNOTSUPP;
+
+	ft_attr.flags = MLX5_FLOW_TABLE_UNMANAGED;
+	ft_attr.uid = MLX5_SHARED_RESOURCE_UID;
+	ft_attr.prio = 0;
+	ft_attr.max_fte = 2;
+	ft_attr.level = 1;
+
+	ft = mlx5_create_flow_table(ns, &ft_attr);
+	if (IS_ERR(ft))
+		return PTR_ERR(ft);
+
+	ft_prio->anchor.ft = ft;
+
+	return 0;
+}
+
+static void steering_anchor_destroy_ft(struct mlx5_ib_flow_prio *ft_prio)
+{
+	if (ft_prio->anchor.ft) {
+		mlx5_destroy_flow_table(ft_prio->anchor.ft);
+		ft_prio->anchor.ft = NULL;
+	}
+}
+
+static int
+steering_anchor_create_fg_drop(struct mlx5_ib_flow_prio *ft_prio)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_group *fg;
+	void *flow_group_in;
+	int err = 0;
+
+	if (ft_prio->anchor.fg_drop)
+		return 0;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!flow_group_in)
+		return -ENOMEM;
+
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 1);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1);
+
+	fg = mlx5_create_flow_group(ft_prio->anchor.ft, flow_group_in);
+	if (IS_ERR(fg)) {
+		err = PTR_ERR(fg);
+		goto out;
+	}
+
+	ft_prio->anchor.fg_drop = fg;
+
+out:
+	kvfree(flow_group_in);
+
+	return err;
+}
+
+static void
+steering_anchor_destroy_fg_drop(struct mlx5_ib_flow_prio *ft_prio)
+{
+	if (ft_prio->anchor.fg_drop) {
+		mlx5_destroy_flow_group(ft_prio->anchor.fg_drop);
+		ft_prio->anchor.fg_drop = NULL;
+	}
+}
+
+static int
+steering_anchor_create_fg_goto_table(struct mlx5_ib_flow_prio *ft_prio)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_group *fg;
+	void *flow_group_in;
+	int err = 0;
+
+	if (ft_prio->anchor.fg_goto_table)
+		return 0;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!flow_group_in)
+		return -ENOMEM;
+
+	fg = mlx5_create_flow_group(ft_prio->anchor.ft, flow_group_in);
+	if (IS_ERR(fg)) {
+		err = PTR_ERR(fg);
+		goto out;
+	}
+	ft_prio->anchor.fg_goto_table = fg;
+
+out:
+	kvfree(flow_group_in);
+
+	return err;
+}
+
+static void
+steering_anchor_destroy_fg_goto_table(struct mlx5_ib_flow_prio *ft_prio)
+{
+	if (ft_prio->anchor.fg_goto_table) {
+		mlx5_destroy_flow_group(ft_prio->anchor.fg_goto_table);
+		ft_prio->anchor.fg_goto_table = NULL;
+	}
+}
+
+static int
+steering_anchor_create_rule_drop(struct mlx5_ib_flow_prio *ft_prio)
+{
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *handle;
+
+	if (ft_prio->anchor.rule_drop)
+		return 0;
+
+	flow_act.fg = ft_prio->anchor.fg_drop;
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
+
+	handle = mlx5_add_flow_rules(ft_prio->anchor.ft, NULL, &flow_act,
+				     NULL, 0);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	ft_prio->anchor.rule_drop = handle;
+
+	return 0;
+}
+
+static void steering_anchor_destroy_rule_drop(struct mlx5_ib_flow_prio *ft_prio)
+{
+	if (ft_prio->anchor.rule_drop) {
+		mlx5_del_flow_rules(ft_prio->anchor.rule_drop);
+		ft_prio->anchor.rule_drop = NULL;
+	}
+}
+
+static int
+steering_anchor_create_rule_goto_table(struct mlx5_ib_flow_prio *ft_prio)
+{
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *handle;
+
+	if (ft_prio->anchor.rule_goto_table)
+		return 0;
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
+	flow_act.fg = ft_prio->anchor.fg_goto_table;
+
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest.ft = ft_prio->flow_table;
+
+	handle = mlx5_add_flow_rules(ft_prio->anchor.ft, NULL, &flow_act,
+				     &dest, 1);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	ft_prio->anchor.rule_goto_table = handle;
+
+	return 0;
+}
+
+static void
+steering_anchor_destroy_rule_goto_table(struct mlx5_ib_flow_prio *ft_prio)
+{
+	if (ft_prio->anchor.rule_goto_table) {
+		mlx5_del_flow_rules(ft_prio->anchor.rule_goto_table);
+		ft_prio->anchor.rule_goto_table = NULL;
+	}
+}
+
+static int steering_anchor_create_res(struct mlx5_ib_dev *dev,
+				      struct mlx5_ib_flow_prio *ft_prio,
+				      enum mlx5_flow_namespace_type ns_type)
+{
+	int err;
+
+	err = steering_anchor_create_ft(dev, ft_prio, ns_type);
+	if (err)
+		return err;
+
+	err = steering_anchor_create_fg_drop(ft_prio);
+	if (err)
+		goto destroy_ft;
+
+	err = steering_anchor_create_fg_goto_table(ft_prio);
+	if (err)
+		goto destroy_fg_drop;
+
+	err = steering_anchor_create_rule_drop(ft_prio);
+	if (err)
+		goto destroy_fg_goto_table;
+
+	err = steering_anchor_create_rule_goto_table(ft_prio);
+	if (err)
+		goto destroy_rule_drop;
+
+	return 0;
+
+destroy_rule_drop:
+	steering_anchor_destroy_rule_drop(ft_prio);
+destroy_fg_goto_table:
+	steering_anchor_destroy_fg_goto_table(ft_prio);
+destroy_fg_drop:
+	steering_anchor_destroy_fg_drop(ft_prio);
+destroy_ft:
+	steering_anchor_destroy_ft(ft_prio);
+
+	return err;
+}
+
+static void mlx5_steering_anchor_destroy_res(struct mlx5_ib_flow_prio *ft_prio)
+{
+	steering_anchor_destroy_rule_goto_table(ft_prio);
+	steering_anchor_destroy_rule_drop(ft_prio);
+	steering_anchor_destroy_fg_goto_table(ft_prio);
+	steering_anchor_destroy_fg_drop(ft_prio);
+	steering_anchor_destroy_ft(ft_prio);
+}
+
 static int steering_anchor_cleanup(struct ib_uobject *uobject,
 				   enum rdma_remove_reason why,
 				   struct uverbs_attr_bundle *attrs)
@@ -2035,6 +2264,9 @@ static int steering_anchor_cleanup(struct ib_uobject *uobject,
 		return -EBUSY;
 
 	mutex_lock(&obj->dev->flow_db->lock);
+	if (!--obj->ft_prio->anchor.rule_goto_table_ref)
+		steering_anchor_destroy_rule_goto_table(obj->ft_prio);
+
 	put_flow_table(obj->dev, obj->ft_prio, true);
 	mutex_unlock(&obj->dev->flow_db->lock);
 
@@ -2042,6 +2274,24 @@ static int steering_anchor_cleanup(struct ib_uobject *uobject,
 	return 0;
 }
 
+static void fs_cleanup_anchor(struct mlx5_ib_flow_prio *prio,
+			      int count)
+{
+	while (count--)
+		mlx5_steering_anchor_destroy_res(&prio[count]);
+}
+
+void mlx5_ib_fs_cleanup_anchor(struct mlx5_ib_dev *dev)
+{
+	fs_cleanup_anchor(dev->flow_db->prios, MLX5_IB_NUM_FLOW_FT);
+	fs_cleanup_anchor(dev->flow_db->egress_prios, MLX5_IB_NUM_FLOW_FT);
+	fs_cleanup_anchor(dev->flow_db->sniffer, MLX5_IB_NUM_SNIFFER_FTS);
+	fs_cleanup_anchor(dev->flow_db->egress, MLX5_IB_NUM_EGRESS_FTS);
+	fs_cleanup_anchor(dev->flow_db->fdb, MLX5_IB_NUM_FDB_FTS);
+	fs_cleanup_anchor(dev->flow_db->rdma_rx, MLX5_IB_NUM_FLOW_FT);
+	fs_cleanup_anchor(dev->flow_db->rdma_tx, MLX5_IB_NUM_FLOW_FT);
+}
+
 static int mlx5_ib_matcher_ns(struct uverbs_attr_bundle *attrs,
 			      struct mlx5_ib_flow_matcher *obj)
 {
@@ -2182,21 +2432,31 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_STEERING_ANCHOR_CREATE)(
 		return -ENOMEM;
 
 	mutex_lock(&dev->flow_db->lock);
+
 	ft_prio = _get_flow_table(dev, priority, ns_type, 0);
 	if (IS_ERR(ft_prio)) {
-		mutex_unlock(&dev->flow_db->lock);
 		err = PTR_ERR(ft_prio);
 		goto free_obj;
 	}
 
 	ft_prio->refcount++;
-	ft_id = mlx5_flow_table_id(ft_prio->flow_table);
-	mutex_unlock(&dev->flow_db->lock);
+
+	if (!ft_prio->anchor.rule_goto_table_ref) {
+		err = steering_anchor_create_res(dev, ft_prio, ns_type);
+		if (err)
+			goto put_flow_table;
+	}
+
+	ft_prio->anchor.rule_goto_table_ref++;
+
+	ft_id = mlx5_flow_table_id(ft_prio->anchor.ft);
 
 	err = uverbs_copy_to(attrs, MLX5_IB_ATTR_STEERING_ANCHOR_FT_ID,
 			     &ft_id, sizeof(ft_id));
 	if (err)
-		goto put_flow_table;
+		goto destroy_res;
+
+	mutex_unlock(&dev->flow_db->lock);
 
 	uobj->object = obj;
 	obj->dev = dev;
@@ -2205,8 +2465,10 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_STEERING_ANCHOR_CREATE)(
 
 	return 0;
 
+destroy_res:
+	--ft_prio->anchor.rule_goto_table_ref;
+	mlx5_steering_anchor_destroy_res(ft_prio);
 put_flow_table:
-	mutex_lock(&dev->flow_db->lock);
 	put_flow_table(dev, ft_prio, true);
 	mutex_unlock(&dev->flow_db->lock);
 free_obj:
diff --git a/drivers/infiniband/hw/mlx5/fs.h b/drivers/infiniband/hw/mlx5/fs.h
index ad320adaf321..b9734904f5f0 100644
--- a/drivers/infiniband/hw/mlx5/fs.h
+++ b/drivers/infiniband/hw/mlx5/fs.h
@@ -10,6 +10,7 @@
 
 #if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)
 int mlx5_ib_fs_init(struct mlx5_ib_dev *dev);
+void mlx5_ib_fs_cleanup_anchor(struct mlx5_ib_dev *dev);
 #else
 static inline int mlx5_ib_fs_init(struct mlx5_ib_dev *dev)
 {
@@ -21,9 +22,24 @@ static inline int mlx5_ib_fs_init(struct mlx5_ib_dev *dev)
 	mutex_init(&dev->flow_db->lock);
 	return 0;
 }
+
+inline void mlx5_ib_fs_cleanup_anchor(struct mlx5_ib_dev *dev) {}
 #endif
+
 static inline void mlx5_ib_fs_cleanup(struct mlx5_ib_dev *dev)
 {
+	/* When a steering anchor is created, a special flow table is also
+	 * created for the user to reference. Since the user can reference it,
+	 * the kernel cannot trust that when the user destroys the steering
+	 * anchor, they no longer reference the flow table.
+	 *
+	 * To address this issue, when a user destroys a steering anchor, only
+	 * the flow steering rule in the table is destroyed, but the table
+	 * itself is kept to deal with the above scenario. The remaining
+	 * resources are only removed when the RDMA device is destroyed, which
+	 * is a safe assumption that all references are gone.
+	 */
+	mlx5_ib_fs_cleanup_anchor(dev);
 	kfree(dev->flow_db);
 }
 #endif /* _MLX5_IB_FS_H */
diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c
index ddcfc116b19a..c7a4ee896121 100644
--- a/drivers/infiniband/hw/mlx5/ib_rep.c
+++ b/drivers/infiniband/hw/mlx5/ib_rep.c
@@ -30,45 +30,65 @@ mlx5_ib_set_vport_rep(struct mlx5_core_dev *dev,
 
 static void mlx5_ib_register_peer_vport_reps(struct mlx5_core_dev *mdev);
 
+static void mlx5_ib_num_ports_update(struct mlx5_core_dev *dev, u32 *num_ports)
+{
+	struct mlx5_core_dev *peer_dev;
+	int i;
+
+	mlx5_lag_for_each_peer_mdev(dev, peer_dev, i) {
+		u32 peer_num_ports = mlx5_eswitch_get_total_vports(peer_dev);
+
+		if (mlx5_lag_is_mpesw(peer_dev))
+			*num_ports += peer_num_ports;
+		else
+			/* Only 1 ib port is the representor for all uplinks */
+			*num_ports += peer_num_ports - 1;
+	}
+}
+
 static int
 mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 {
 	u32 num_ports = mlx5_eswitch_get_total_vports(dev);
+	struct mlx5_core_dev *lag_master = dev;
 	const struct mlx5_ib_profile *profile;
 	struct mlx5_core_dev *peer_dev;
 	struct mlx5_ib_dev *ibdev;
-	int second_uplink = false;
-	u32 peer_num_ports;
+	int new_uplink = false;
 	int vport_index;
 	int ret;
+	int i;
 
 	vport_index = rep->vport_index;
 
 	if (mlx5_lag_is_shared_fdb(dev)) {
-		peer_dev = mlx5_lag_get_peer_mdev(dev);
-		peer_num_ports = mlx5_eswitch_get_total_vports(peer_dev);
 		if (mlx5_lag_is_master(dev)) {
-			if (mlx5_lag_is_mpesw(dev))
-				num_ports += peer_num_ports;
-			else
-				num_ports += peer_num_ports - 1;
-
+			mlx5_ib_num_ports_update(dev, &num_ports);
 		} else {
 			if (rep->vport == MLX5_VPORT_UPLINK) {
 				if (!mlx5_lag_is_mpesw(dev))
 					return 0;
-				second_uplink = true;
+				new_uplink = true;
 			}
+			mlx5_lag_for_each_peer_mdev(dev, peer_dev, i) {
+				u32 peer_n_ports = mlx5_eswitch_get_total_vports(peer_dev);
+
+				if (mlx5_lag_is_master(peer_dev))
+					lag_master = peer_dev;
+				else if (!mlx5_lag_is_mpesw(dev))
+				/* Only 1 ib port is the representor for all uplinks */
+					peer_n_ports--;
 
-			vport_index += peer_num_ports;
-			dev = peer_dev;
+				if (mlx5_get_dev_index(peer_dev) < mlx5_get_dev_index(dev))
+					vport_index += peer_n_ports;
+			}
 		}
 	}
 
-	if (rep->vport == MLX5_VPORT_UPLINK && !second_uplink)
+	if (rep->vport == MLX5_VPORT_UPLINK && !new_uplink)
 		profile = &raw_eth_profile;
 	else
-		return mlx5_ib_set_vport_rep(dev, rep, vport_index);
+		return mlx5_ib_set_vport_rep(lag_master, rep, vport_index);
 
 	ibdev = ib_alloc_device(mlx5_ib_dev, ib_dev);
 	if (!ibdev)
@@ -85,8 +105,8 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	vport_index = rep->vport_index;
 	ibdev->port[vport_index].rep = rep;
 	ibdev->port[vport_index].roce.netdev =
-		mlx5_ib_get_rep_netdev(dev->priv.eswitch, rep->vport);
-	ibdev->mdev = dev;
+		mlx5_ib_get_rep_netdev(lag_master->priv.eswitch, rep->vport);
+	ibdev->mdev = lag_master;
 	ibdev->num_ports = num_ports;
 
 	ret = __mlx5_ib_add(ibdev, profile);
@@ -94,8 +114,8 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 		goto fail_add;
 
 	rep->rep_data[REP_IB].priv = ibdev;
-	if (mlx5_lag_is_shared_fdb(dev))
-		mlx5_ib_register_peer_vport_reps(dev);
+	if (mlx5_lag_is_shared_fdb(lag_master))
+		mlx5_ib_register_peer_vport_reps(lag_master);
 
 	return 0;
 
@@ -118,23 +138,27 @@ mlx5_ib_vport_rep_unload(struct mlx5_eswitch_rep *rep)
 	struct mlx5_ib_dev *dev = mlx5_ib_rep_to_dev(rep);
 	int vport_index = rep->vport_index;
 	struct mlx5_ib_port *port;
+	int i;
 
 	if (WARN_ON(!mdev))
 		return;
 
+	if (!dev)
+		return;
+
 	if (mlx5_lag_is_shared_fdb(mdev) &&
 	    !mlx5_lag_is_master(mdev)) {
-		struct mlx5_core_dev *peer_mdev;
-
-		if (rep->vport == MLX5_VPORT_UPLINK)
+		if (rep->vport == MLX5_VPORT_UPLINK && !mlx5_lag_is_mpesw(mdev))
 			return;
-		peer_mdev = mlx5_lag_get_peer_mdev(mdev);
-		vport_index += mlx5_eswitch_get_total_vports(peer_mdev);
+		for (i = 0; i < dev->num_ports; i++) {
+			if (dev->port[i].rep == rep)
+				break;
+		}
+		if (WARN_ON(i == dev->num_ports))
+			return;
+		vport_index = i;
 	}
 
-	if (!dev)
-		return;
-
 	port = &dev->port[vport_index];
 	write_lock(&port->roce.netdev_lock);
 	port->roce.netdev = NULL;
@@ -143,13 +167,18 @@ mlx5_ib_vport_rep_unload(struct mlx5_eswitch_rep *rep)
 	port->rep = NULL;
 
 	if (rep->vport == MLX5_VPORT_UPLINK) {
-		struct mlx5_core_dev *peer_mdev;
-		struct mlx5_eswitch *esw;
+
+		if (mlx5_lag_is_shared_fdb(mdev) && !mlx5_lag_is_master(mdev))
+			return;
 
 		if (mlx5_lag_is_shared_fdb(mdev)) {
-			peer_mdev = mlx5_lag_get_peer_mdev(mdev);
-			esw = peer_mdev->priv.eswitch;
-			mlx5_eswitch_unregister_vport_reps(esw, REP_IB);
+			struct mlx5_core_dev *peer_mdev;
+			struct mlx5_eswitch *esw;
+
+			mlx5_lag_for_each_peer_mdev(mdev, peer_mdev, i) {
+				esw = peer_mdev->priv.eswitch;
+				mlx5_eswitch_unregister_vport_reps(esw, REP_IB);
+			}
 		}
 		__mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX);
 	}
@@ -163,14 +192,14 @@ static const struct mlx5_eswitch_rep_ops rep_ops = {
 
 static void mlx5_ib_register_peer_vport_reps(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_core_dev *peer_mdev = mlx5_lag_get_peer_mdev(mdev);
+	struct mlx5_core_dev *peer_mdev;
 	struct mlx5_eswitch *esw;
+	int i;
 
-	if (!peer_mdev)
-		return;
-
-	esw = peer_mdev->priv.eswitch;
-	mlx5_eswitch_register_vport_reps(esw, &rep_ops, REP_IB);
+	mlx5_lag_for_each_peer_mdev(mdev, peer_mdev, i) {
+		esw = peer_mdev->priv.eswitch;
+		mlx5_eswitch_register_vport_reps(esw, &rep_ops, REP_IB);
+	}
 }
 
 struct net_device *mlx5_ib_get_rep_netdev(struct mlx5_eswitch *esw,
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 5d45de223c43..f0b394ed7452 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -4275,6 +4275,9 @@ const struct mlx5_ib_profile raw_eth_profile = {
 	STAGE_CREATE(MLX5_IB_STAGE_POST_IB_REG_UMR,
 		     mlx5_ib_stage_post_ib_reg_umr_init,
 		     NULL),
+	STAGE_CREATE(MLX5_IB_STAGE_DELAY_DROP,
+		     mlx5_ib_stage_delay_drop_init,
+		     mlx5_ib_stage_delay_drop_cleanup),
 	STAGE_CREATE(MLX5_IB_STAGE_RESTRACK,
 		     mlx5_ib_restrack_init,
 		     NULL),
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index efa4dc6e7dee..2dfa6f49a6f4 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -237,8 +237,19 @@ enum {
 #define MLX5_IB_NUM_SNIFFER_FTS		2
 #define MLX5_IB_NUM_EGRESS_FTS		1
 #define MLX5_IB_NUM_FDB_FTS		MLX5_BY_PASS_NUM_REGULAR_PRIOS
+
+struct mlx5_ib_anchor {
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_group *fg_goto_table;
+	struct mlx5_flow_group *fg_drop;
+	struct mlx5_flow_handle *rule_goto_table;
+	struct mlx5_flow_handle *rule_drop;
+	unsigned int rule_goto_table_ref;
+};
+
 struct mlx5_ib_flow_prio {
 	struct mlx5_flow_table		*flow_table;
+	struct mlx5_ib_anchor		anchor;
 	unsigned int			refcount;
 };
 
@@ -1587,6 +1598,9 @@ static inline bool mlx5_ib_lag_should_assign_affinity(struct mlx5_ib_dev *dev)
 	    MLX5_CAP_PORT_SELECTION(dev->mdev, port_select_flow_table_bypass))
 		return 0;
 
+	if (mlx5_lag_is_lacp_owner(dev->mdev) && !dev->lag_active)
+		return 0;
+
 	return dev->lag_active ||
 		(MLX5_CAP_GEN(dev->mdev, num_lag_ports) > 1 &&
 		 MLX5_CAP_GEN(dev->mdev, lag_tx_port_affinity));
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 70ca8ffa9256..78b96bfb4e6a 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1237,6 +1237,9 @@ static int create_raw_packet_qp_tis(struct mlx5_ib_dev *dev,
 
 	MLX5_SET(create_tis_in, in, uid, to_mpd(pd)->uid);
 	MLX5_SET(tisc, tisc, transport_domain, tdn);
+	if (!mlx5_ib_lag_should_assign_affinity(dev) &&
+	    mlx5_lag_is_lacp_owner(dev->mdev))
+		MLX5_SET(tisc, tisc, strict_lag_tx_port_affinity, 1);
 	if (qp->flags & IB_QP_CREATE_SOURCE_QPN)
 		MLX5_SET(tisc, tisc, underlay_qpn, qp->underlay_qpn);