Merge tag 'mlx5-updates-2023-01-18' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2023-01-18

1) From Rahul,
  1.1) extended range for PTP adjtime and adjphase
  1.2) adjphase function to support hardware-only offset control

2) From Roi, code cleanup to the TC module.

3) From Maor, TC support for Geneve and GRE with VF tunnel offload

4) Cleanups and minor updates.

* tag 'mlx5-updates-2023-01-18' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
  net/mlx5e: Use read lock for eswitch get callbacks
  net/mlx5e: Remove redundant allocation of spec in create indirect fwd group
  net/mlx5e: Support Geneve and GRE with VF tunnel offload
  net/mlx5: E-Switch, Fix typo for egress
  net/mlx5e: Warn when destroying mod hdr hash table that is not empty
  net/mlx5e: TC, Use common function allocating flow mod hdr or encap mod hdr
  net/mlx5e: TC, Add tc prefix to attach/detach hdr functions
  net/mlx5e: TC, Pass flow attr to attach/detach mod hdr functions
  net/mlx5e: Add warning when log WQE size is smaller than log stride size
  net/mlx5e: Fail with messages when params are not valid for XSK
  net/mlx5: E-switch, Remove redundant comment about meta rules
  net/mlx5: Add hardware extended range support for PTP adjtime and adjphase
  net/mlx5: Add adjphase function to support hardware-only offset control
  net/mlx5: Suppress error logging on UCTX creation
  net/mlx5e: Suppress Send WQEBB room warning for PAGE_SIZE >= 16KB
====================

Link: https://lore.kernel.org/r/20230118183602.124323-1-saeed@kernel.orgSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/mellanox/mlx5/core/cmd.c

@@ -813,7 +813,8 @@ static void cmd_status_print(struct mlx5_core_dev *dev, void *in, void *out)
 	op_mod = MLX5_GET(mbox_in, in, op_mod);
 	uid    = MLX5_GET(mbox_in, in, uid);
 
-	if (!uid && opcode != MLX5_CMD_OP_DESTROY_MKEY)
+	if (!uid && opcode != MLX5_CMD_OP_DESTROY_MKEY &&
+	    opcode != MLX5_CMD_OP_CREATE_UCTX)
 		mlx5_cmd_out_err(dev, opcode, op_mod, out);
 }
 

drivers/net/ethernet/mellanox/mlx5/core/en/mod_hdr.c

@@ -47,6 +47,7 @@ void mlx5e_mod_hdr_tbl_init(struct mod_hdr_tbl *tbl)
 
 void mlx5e_mod_hdr_tbl_destroy(struct mod_hdr_tbl *tbl)
 {
+	WARN_ON(!hash_empty(tbl->hlist));
 	mutex_destroy(&tbl->lock);
 }
 

drivers/net/ethernet/mellanox/mlx5/core/en/params.c

@@ -411,9 +411,14 @@ u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
 {
 	enum mlx5e_mpwrq_umr_mode umr_mode = mlx5e_mpwrq_umr_mode(mdev, xsk);
 	u8 page_shift = mlx5e_mpwrq_page_shift(mdev, xsk);
+	u8 log_wqe_size, log_stride_size;
 
-	return mlx5e_mpwrq_log_wqe_sz(mdev, page_shift, umr_mode) -
-		mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk);
+	log_wqe_size = mlx5e_mpwrq_log_wqe_sz(mdev, page_shift, umr_mode);
+	log_stride_size = mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk);
+	WARN(log_wqe_size < log_stride_size,
+	     "Log WQE size %u < log stride size %u (page shift %u, umr mode %d, xsk on? %d)\n",
+	     log_wqe_size, log_stride_size, page_shift, umr_mode, !!xsk);
+	return log_wqe_size - log_stride_size;
 }
 
 u8 mlx5e_mpwqe_get_min_wqe_bulk(unsigned int wq_sz)
@@ -581,11 +586,16 @@ int mlx5e_mpwrq_validate_xsk(struct mlx5_core_dev *mdev, struct mlx5e_params *pa
 	bool unaligned = xsk ? xsk->unaligned : false;
 	u16 max_mtu_pkts;
 
-	if (!mlx5e_check_fragmented_striding_rq_cap(mdev, page_shift, umr_mode))
+	if (!mlx5e_check_fragmented_striding_rq_cap(mdev, page_shift, umr_mode)) {
+		mlx5_core_err(mdev, "Striding RQ for XSK can't be activated with page_shift %u and umr_mode %d\n",
+			      page_shift, umr_mode);
 		return -EOPNOTSUPP;
+	}
 
-	if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, xsk))
+	if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, xsk)) {
+		mlx5_core_err(mdev, "Striding RQ linear mode for XSK can't be activated with current params\n");
 		return -EINVAL;
+	}
 
 	/* Current RQ length is too big for the given frame size, the
 	 * needed number of WQEs exceeds the maximum.

drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h

@@ -95,8 +95,6 @@ struct mlx5e_tc_flow {
 	 */
 	struct encap_flow_item encaps[MLX5_MAX_FLOW_FWD_VPORTS];
 	struct mlx5e_tc_flow *peer_flow;
-	struct mlx5e_mod_hdr_handle *mh; /* attached mod header instance */
-	struct mlx5e_mod_hdr_handle *slow_mh; /* attached mod header instance for slow path */
 	struct mlx5e_hairpin_entry *hpe; /* attached hairpin instance */
 	struct list_head hairpin; /* flows sharing the same hairpin */
 	struct list_head peer;    /* flows with peer flow */

drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c

@@ -745,8 +745,6 @@ int mlx5e_tc_tun_route_lookup(struct mlx5e_priv *priv,
 		if (err)
 			goto out;
 
-		esw_attr->rx_tun_attr->vni = MLX5_GET(fte_match_param, spec->match_value,
-						      misc_parameters.vxlan_vni);
 		esw_attr->rx_tun_attr->decap_vport = vport_num;
 	} else if (netif_is_ovs_master(attr.route_dev) && mlx5e_tc_int_port_supported(esw)) {
 		int_port = mlx5e_tc_int_port_get(mlx5e_get_int_port_priv(priv),

drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c

@@ -1349,7 +1349,8 @@ static void mlx5e_invalidate_encap(struct mlx5e_priv *priv,
 			mlx5e_tc_unoffload_from_slow_path(esw, flow);
 		else
 			mlx5e_tc_unoffload_fdb_rules(esw, flow, flow->attr);
-		mlx5_modify_header_dealloc(priv->mdev, attr->modify_hdr);
+
+		mlx5e_tc_detach_mod_hdr(priv, flow, attr);
 		attr->modify_hdr = NULL;
 
 		esw_attr->dests[flow->tmp_entry_index].flags &=
@@ -1405,7 +1406,7 @@ static void mlx5e_reoffload_encap(struct mlx5e_priv *priv,
 			continue;
 		}
 
-		err = mlx5e_tc_add_flow_mod_hdr(priv, flow, attr);
+		err = mlx5e_tc_attach_mod_hdr(priv, flow, attr);
 		if (err) {
 			mlx5_core_warn(priv->mdev, "Failed to update flow mod_hdr err=%d",
 				       err);

drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h

@@ -445,7 +445,7 @@ mlx5e_set_eseg_swp(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg,
 
 static inline u16 mlx5e_stop_room_for_wqe(struct mlx5_core_dev *mdev, u16 wqe_size)
 {
-	WARN_ON_ONCE(PAGE_SIZE / MLX5_SEND_WQE_BB < mlx5e_get_max_sq_wqebbs(mdev));
+	WARN_ON_ONCE(PAGE_SIZE / MLX5_SEND_WQE_BB < (u16)mlx5e_get_max_sq_wqebbs(mdev));
 
 	/* A WQE must not cross the page boundary, hence two conditions:
 	 * 1. Its size must not exceed the page size.

drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c

@@ -7,6 +7,18 @@
 #include "en/health.h"
 #include <net/xdp_sock_drv.h>
 
+static int mlx5e_legacy_rq_validate_xsk(struct mlx5_core_dev *mdev,
+					struct mlx5e_params *params,
+					struct mlx5e_xsk_param *xsk)
+{
+	if (!mlx5e_rx_is_linear_skb(mdev, params, xsk)) {
+		mlx5_core_err(mdev, "Legacy RQ linear mode for XSK can't be activated with current params\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /* The limitation of 2048 can be altered, but shouldn't go beyond the minimal
  * stride size of striding RQ.
  */
@@ -17,8 +29,11 @@ bool mlx5e_validate_xsk_param(struct mlx5e_params *params,
 			      struct mlx5_core_dev *mdev)
 {
 	/* AF_XDP doesn't support frames larger than PAGE_SIZE. */
-	if (xsk->chunk_size > PAGE_SIZE || xsk->chunk_size < MLX5E_MIN_XSK_CHUNK_SIZE)
+	if (xsk->chunk_size > PAGE_SIZE || xsk->chunk_size < MLX5E_MIN_XSK_CHUNK_SIZE) {
+		mlx5_core_err(mdev, "XSK chunk size %u out of bounds [%u, %lu]\n", xsk->chunk_size,
+			      MLX5E_MIN_XSK_CHUNK_SIZE, PAGE_SIZE);
 		return false;
+	}
 
 	/* frag_sz is different for regular and XSK RQs, so ensure that linear
 	 * SKB mode is possible.
@@ -27,7 +42,7 @@ bool mlx5e_validate_xsk_param(struct mlx5e_params *params,
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		return !mlx5e_mpwrq_validate_xsk(mdev, params, xsk);
 	default: /* MLX5_WQ_TYPE_CYCLIC */
-		return mlx5e_rx_is_linear_skb(mdev, params, xsk);
+		return !mlx5e_legacy_rq_validate_xsk(mdev, params, xsk);
 	}
 }
 

drivers/net/ethernet/mellanox/mlx5/core/en_tc.c

@@ -646,36 +646,36 @@ get_mod_hdr_table(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow)
 		&tc->mod_hdr;
 }
 
-static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv,
+int mlx5e_tc_attach_mod_hdr(struct mlx5e_priv *priv,
 			    struct mlx5e_tc_flow *flow,
-				struct mlx5e_tc_flow_parse_attr *parse_attr)
+			    struct mlx5_flow_attr *attr)
 {
-	struct mlx5_modify_hdr *modify_hdr;
 	struct mlx5e_mod_hdr_handle *mh;
 
 	mh = mlx5e_mod_hdr_attach(priv->mdev, get_mod_hdr_table(priv, flow),
 				  mlx5e_get_flow_namespace(flow),
-				  &parse_attr->mod_hdr_acts);
+				  &attr->parse_attr->mod_hdr_acts);
 	if (IS_ERR(mh))
 		return PTR_ERR(mh);
 
-	modify_hdr = mlx5e_mod_hdr_get(mh);
-	flow->attr->modify_hdr = modify_hdr;
-	flow->mh = mh;
+	WARN_ON(attr->modify_hdr);
+	attr->modify_hdr = mlx5e_mod_hdr_get(mh);
+	attr->mh = mh;
 
 	return 0;
 }
 
-static void mlx5e_detach_mod_hdr(struct mlx5e_priv *priv,
-				 struct mlx5e_tc_flow *flow)
+void mlx5e_tc_detach_mod_hdr(struct mlx5e_priv *priv,
+			     struct mlx5e_tc_flow *flow,
+			     struct mlx5_flow_attr *attr)
 {
 	/* flow wasn't fully initialized */
-	if (!flow->mh)
+	if (!attr->mh)
 		return;
 
 	mlx5e_mod_hdr_detach(priv->mdev, get_mod_hdr_table(priv, flow),
-			     flow->mh);
-	flow->mh = NULL;
+			     attr->mh);
+	attr->mh = NULL;
 }
 
 static
@@ -1433,7 +1433,7 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
 	}
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
-		err = mlx5e_attach_mod_hdr(priv, flow, parse_attr);
+		err = mlx5e_tc_attach_mod_hdr(priv, flow, attr);
 		if (err)
 			return err;
 	}
@@ -1493,7 +1493,7 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv,
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
 		mlx5e_mod_hdr_dealloc(&attr->parse_attr->mod_hdr_acts);
-		mlx5e_detach_mod_hdr(priv, flow);
+		mlx5e_tc_detach_mod_hdr(priv, flow, attr);
 	}
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT)
@@ -1604,7 +1604,7 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw,
 		goto err_offload;
 	}
 
-	flow->slow_mh = mh;
+	flow->attr->slow_mh = mh;
 	flow->chain_mapping = chain_mapping;
 	flow_flag_set(flow, SLOW);
 
@@ -1629,6 +1629,7 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw,
 void mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw,
 				       struct mlx5e_tc_flow *flow)
 {
+	struct mlx5e_mod_hdr_handle *slow_mh = flow->attr->slow_mh;
 	struct mlx5_flow_attr *slow_attr;
 
 	slow_attr = mlx5_alloc_flow_attr(MLX5_FLOW_NAMESPACE_FDB);
@@ -1641,16 +1642,16 @@ void mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw,
 	slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 	slow_attr->esw_attr->split_count = 0;
 	slow_attr->flags |= MLX5_ATTR_FLAG_SLOW_PATH;
-	if (flow->slow_mh) {
+	if (slow_mh) {
 		slow_attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
-		slow_attr->modify_hdr = mlx5e_mod_hdr_get(flow->slow_mh);
+		slow_attr->modify_hdr = mlx5e_mod_hdr_get(slow_mh);
 	}
 	mlx5e_tc_unoffload_fdb_rules(esw, flow, slow_attr);
-	if (flow->slow_mh) {
-		mlx5e_mod_hdr_detach(esw->dev, get_mod_hdr_table(flow->priv, flow), flow->slow_mh);
+	if (slow_mh) {
+		mlx5e_mod_hdr_detach(esw->dev, get_mod_hdr_table(flow->priv, flow), slow_mh);
 		mlx5_chains_put_chain_mapping(esw_chains(esw), flow->chain_mapping);
 		flow->chain_mapping = 0;
-		flow->slow_mh = NULL;
+		flow->attr->slow_mh = NULL;
 	}
 	flow_flag_clear(flow, SLOW);
 	kfree(slow_attr);
@@ -1761,26 +1762,6 @@ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *ro
 	return err;
 }
 
-int mlx5e_tc_add_flow_mod_hdr(struct mlx5e_priv *priv,
-			      struct mlx5e_tc_flow *flow,
-			      struct mlx5_flow_attr *attr)
-{
-	struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts = &attr->parse_attr->mod_hdr_acts;
-	struct mlx5_modify_hdr *mod_hdr;
-
-	mod_hdr = mlx5_modify_header_alloc(priv->mdev,
-					   mlx5e_get_flow_namespace(flow),
-					   mod_hdr_acts->num_actions,
-					   mod_hdr_acts->actions);
-	if (IS_ERR(mod_hdr))
-		return PTR_ERR(mod_hdr);
-
-	WARN_ON(attr->modify_hdr);
-	attr->modify_hdr = mod_hdr;
-
-	return 0;
-}
-
 static int
 set_encap_dests(struct mlx5e_priv *priv,
 		struct mlx5e_tc_flow *flow,
@@ -1900,7 +1881,6 @@ verify_attr_actions(u32 actions, struct netlink_ext_ack *extack)
 static int
 post_process_attr(struct mlx5e_tc_flow *flow,
 		  struct mlx5_flow_attr *attr,
-		  bool is_post_act_attr,
 		  struct netlink_ext_ack *extack)
 {
 	struct mlx5_eswitch *esw = flow->priv->mdev->priv.eswitch;
@@ -1922,27 +1902,21 @@ post_process_attr(struct mlx5e_tc_flow *flow,
 	}
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
-		if (vf_tun || is_post_act_attr) {
-			err = mlx5e_tc_add_flow_mod_hdr(flow->priv, flow, attr);
+		err = mlx5e_tc_attach_mod_hdr(flow->priv, flow, attr);
 		if (err)
 			goto err_out;
-		} else {
-			err = mlx5e_attach_mod_hdr(flow->priv, flow, attr->parse_attr);
-			if (err)
-				goto err_out;
-		}
 	}
 
 	if (attr->branch_true &&
 	    attr->branch_true->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
-		err = mlx5e_tc_add_flow_mod_hdr(flow->priv, flow, attr->branch_true);
+		err = mlx5e_tc_attach_mod_hdr(flow->priv, flow, attr->branch_true);
 		if (err)
 			goto err_out;
 	}
 
 	if (attr->branch_false &&
 	    attr->branch_false->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
-		err = mlx5e_tc_add_flow_mod_hdr(flow->priv, flow, attr->branch_false);
+		err = mlx5e_tc_attach_mod_hdr(flow->priv, flow, attr->branch_false);
 		if (err)
 			goto err_out;
 	}
@@ -2056,7 +2030,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		esw_attr->int_port = int_port;
 	}
 
-	err = post_process_attr(flow, attr, false, extack);
+	err = post_process_attr(flow, attr, extack);
 	if (err)
 		goto err_out;
 
@@ -2141,10 +2115,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
 		mlx5e_mod_hdr_dealloc(&attr->parse_attr->mod_hdr_acts);
-		if (vf_tun && attr->modify_hdr)
-			mlx5_modify_header_dealloc(priv->mdev, attr->modify_hdr);
-		else
-			mlx5e_detach_mod_hdr(priv, flow);
+		mlx5e_tc_detach_mod_hdr(priv, flow, attr);
 	}
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT)
@@ -2624,13 +2595,13 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 		err = mlx5e_tc_set_attr_rx_tun(flow, spec);
 		if (err)
 			return err;
-	} else if (tunnel && tunnel->tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
+	} else if (tunnel) {
 		struct mlx5_flow_spec *tmp_spec;
 
 		tmp_spec = kvzalloc(sizeof(*tmp_spec), GFP_KERNEL);
 		if (!tmp_spec) {
-			NL_SET_ERR_MSG_MOD(extack, "Failed to allocate memory for vxlan tmp spec");
-			netdev_warn(priv->netdev, "Failed to allocate memory for vxlan tmp spec");
+			NL_SET_ERR_MSG_MOD(extack, "Failed to allocate memory for tunnel tmp spec");
+			netdev_warn(priv->netdev, "Failed to allocate memory for tunnel tmp spec");
 			return -ENOMEM;
 		}
 		memcpy(tmp_spec, spec, sizeof(*tmp_spec));
@@ -3963,7 +3934,7 @@ alloc_flow_post_acts(struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack)
 		if (err)
 			goto out_free;
 
-		err = post_process_attr(flow, attr, true, extack);
+		err = post_process_attr(flow, attr, extack);
 		if (err)
 			goto out_free;
 
@@ -4530,8 +4501,7 @@ mlx5_free_flow_attr(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr)
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
 		mlx5e_mod_hdr_dealloc(&attr->parse_attr->mod_hdr_acts);
-		if (attr->modify_hdr)
-			mlx5_modify_header_dealloc(flow->priv->mdev, attr->modify_hdr);
+		mlx5e_tc_detach_mod_hdr(flow->priv, flow, attr);
 	}
 }
 
@@ -4653,9 +4623,6 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 	if (err)
 		goto err_free;
 
-	/* always set IP version for indirect table handling */
-	flow->attr->ip_version = mlx5e_tc_get_ip_version(&parse_attr->spec, true);
-
 	err = parse_tc_fdb_actions(priv, &rule->action, flow, extack);
 	if (err)
 		goto err_free;

drivers/net/ethernet/mellanox/mlx5/core/en_tc.h

@@ -71,6 +71,8 @@ struct mlx5_flow_attr {
 	u32 action;
 	struct mlx5_fc *counter;
 	struct mlx5_modify_hdr *modify_hdr;
+	struct mlx5e_mod_hdr_handle *mh; /* attached mod header instance */
+	struct mlx5e_mod_hdr_handle *slow_mh; /* attached mod header instance for slow path */
 	struct mlx5_ct_attr ct_attr;
 	struct mlx5e_sample_attr sample_attr;
 	struct mlx5e_meter_attr meter_attr;
@@ -82,7 +84,6 @@ struct mlx5_flow_attr {
 	struct mlx5_flow_table *dest_ft;
 	u8 inner_match_level;
 	u8 outer_match_level;
-	u8 ip_version;
 	u8 tun_ip_version;
 	int tunnel_id; /* mapped tunnel id */
 	u32 flags;
@@ -134,7 +135,6 @@ struct mlx5_rx_tun_attr {
 		__be32 v4;
 		struct in6_addr v6;
 	} dst_ip; /* Valid if decap_vport is not zero */
-	u32 vni;
 };
 
 #define MLX5E_TC_TABLE_CHAIN_TAG_BITS 16
@@ -285,7 +285,11 @@ int mlx5e_tc_match_to_reg_set_and_get_id(struct mlx5_core_dev *mdev,
 					 enum mlx5e_tc_attr_to_reg type,
 					 u32 data);
 
-int mlx5e_tc_add_flow_mod_hdr(struct mlx5e_priv *priv,
+int mlx5e_tc_attach_mod_hdr(struct mlx5e_priv *priv,
+			    struct mlx5e_tc_flow *flow,
+			    struct mlx5_flow_attr *attr);
+
+void mlx5e_tc_detach_mod_hdr(struct mlx5e_priv *priv,
 			     struct mlx5e_tc_flow *flow,
 			     struct mlx5_flow_attr *attr);
 

drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c

@@ -16,18 +16,12 @@
 #include "lib/fs_chains.h"
 #include "en/mod_hdr.h"
 
-#define MLX5_ESW_INDIR_TABLE_SIZE 128
-#define MLX5_ESW_INDIR_TABLE_RECIRC_IDX_MAX (MLX5_ESW_INDIR_TABLE_SIZE - 2)
+#define MLX5_ESW_INDIR_TABLE_SIZE 2
+#define MLX5_ESW_INDIR_TABLE_RECIRC_IDX (MLX5_ESW_INDIR_TABLE_SIZE - 2)
 #define MLX5_ESW_INDIR_TABLE_FWD_IDX (MLX5_ESW_INDIR_TABLE_SIZE - 1)
 
 struct mlx5_esw_indir_table_rule {
-	struct list_head list;
 	struct mlx5_flow_handle *handle;
-	union {
-		__be32 v4;
-		struct in6_addr v6;
-	} dst_ip;
-	u32 vni;
 	struct mlx5_modify_hdr *mh;
 	refcount_t refcnt;
 };
@@ -38,12 +32,10 @@ struct mlx5_esw_indir_table_entry {
 	struct mlx5_flow_group *recirc_grp;
 	struct mlx5_flow_group *fwd_grp;
 	struct mlx5_flow_handle *fwd_rule;
-	struct list_head recirc_rules;
-	int recirc_cnt;
+	struct mlx5_esw_indir_table_rule *recirc_rule;
 	int fwd_ref;
 
 	u16 vport;
-	u8 ip_version;
 };
 
 struct mlx5_esw_indir_table {
@@ -89,7 +81,6 @@ mlx5_esw_indir_table_needed(struct mlx5_eswitch *esw,
 	return esw_attr->in_rep->vport == MLX5_VPORT_UPLINK &&
 		vf_sf_vport &&
 		esw->dev == dest_mdev &&
-		attr->ip_version &&
 		attr->flags & MLX5_ATTR_FLAG_SRC_REWRITE;
 }
 
@@ -101,27 +92,8 @@ mlx5_esw_indir_table_decap_vport(struct mlx5_flow_attr *attr)
 	return esw_attr->rx_tun_attr ? esw_attr->rx_tun_attr->decap_vport : 0;
 }
 
-static struct mlx5_esw_indir_table_rule *
-mlx5_esw_indir_table_rule_lookup(struct mlx5_esw_indir_table_entry *e,
-				 struct mlx5_esw_flow_attr *attr)
-{
-	struct mlx5_esw_indir_table_rule *rule;
-
-	list_for_each_entry(rule, &e->recirc_rules, list)
-		if (rule->vni == attr->rx_tun_attr->vni &&
-		    !memcmp(&rule->dst_ip, &attr->rx_tun_attr->dst_ip,
-			    sizeof(attr->rx_tun_attr->dst_ip)))
-			goto found;
-	return NULL;
-
-found:
-	refcount_inc(&rule->refcnt);
-	return rule;
-}
-
 static int mlx5_esw_indir_table_rule_get(struct mlx5_eswitch *esw,
 					 struct mlx5_flow_attr *attr,
-					 struct mlx5_flow_spec *spec,
 					 struct mlx5_esw_indir_table_entry *e)
 {
 	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
@@ -130,73 +102,18 @@ static int mlx5_esw_indir_table_rule_get(struct mlx5_eswitch *esw,
 	struct mlx5_flow_destination dest = {};
 	struct mlx5_esw_indir_table_rule *rule;
 	struct mlx5_flow_act flow_act = {};
-	struct mlx5_flow_spec *rule_spec;
 	struct mlx5_flow_handle *handle;
 	int err = 0;
 	u32 data;
 
-	rule = mlx5_esw_indir_table_rule_lookup(e, esw_attr);
-	if (rule)
+	if (e->recirc_rule) {
+		refcount_inc(&e->recirc_rule->refcnt);
 		return 0;
-
-	if (e->recirc_cnt == MLX5_ESW_INDIR_TABLE_RECIRC_IDX_MAX)
-		return -EINVAL;
-
-	rule_spec = kvzalloc(sizeof(*rule_spec), GFP_KERNEL);
-	if (!rule_spec)
-		return -ENOMEM;
-
-	rule = kzalloc(sizeof(*rule), GFP_KERNEL);
-	if (!rule) {
-		err = -ENOMEM;
-		goto out;
-	}
-
-	rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS |
-					   MLX5_MATCH_MISC_PARAMETERS |
-					   MLX5_MATCH_MISC_PARAMETERS_2;
-	if (MLX5_CAP_FLOWTABLE_NIC_RX(esw->dev, ft_field_support.outer_ip_version)) {
-		MLX5_SET(fte_match_param, rule_spec->match_criteria,
-			 outer_headers.ip_version, 0xf);
-		MLX5_SET(fte_match_param, rule_spec->match_value, outer_headers.ip_version,
-			 attr->ip_version);
-	} else if (attr->ip_version) {
-		MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria,
-				 outer_headers.ethertype);
-		MLX5_SET(fte_match_param, rule_spec->match_value, outer_headers.ethertype,
-			 (attr->ip_version == 4 ? ETH_P_IP : ETH_P_IPV6));
-	} else {
-		err = -EOPNOTSUPP;
-		goto err_ethertype;
-	}
-
-	if (attr->ip_version == 4) {
-		MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria,
-				 outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4);
-		MLX5_SET(fte_match_param, rule_spec->match_value,
-			 outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4,
-			 ntohl(esw_attr->rx_tun_attr->dst_ip.v4));
-	} else if (attr->ip_version == 6) {
-		int len = sizeof(struct in6_addr);
-
-		memset(MLX5_ADDR_OF(fte_match_param, rule_spec->match_criteria,
-				    outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
-		       0xff, len);
-		memcpy(MLX5_ADDR_OF(fte_match_param, rule_spec->match_value,
-				    outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
-		       &esw_attr->rx_tun_attr->dst_ip.v6, len);
 	}
 
-	MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria,
-			 misc_parameters.vxlan_vni);
-	MLX5_SET(fte_match_param, rule_spec->match_value, misc_parameters.vxlan_vni,
-		 MLX5_GET(fte_match_param, spec->match_value, misc_parameters.vxlan_vni));
-
-	MLX5_SET(fte_match_param, rule_spec->match_criteria,
-		 misc_parameters_2.metadata_reg_c_0, mlx5_eswitch_get_vport_metadata_mask());
-	MLX5_SET(fte_match_param, rule_spec->match_value, misc_parameters_2.metadata_reg_c_0,
-		 mlx5_eswitch_get_vport_metadata_for_match(esw_attr->in_mdev->priv.eswitch,
-							   MLX5_VPORT_UPLINK));
+	rule = kzalloc(sizeof(*rule), GFP_KERNEL);
+	if (!rule)
+		return -ENOMEM;
 
 	/* Modify flow source to recirculate packet */
 	data = mlx5_eswitch_get_vport_metadata_for_set(esw, esw_attr->rx_tun_attr->decap_vport);
@@ -219,13 +136,14 @@ static int mlx5_esw_indir_table_rule_get(struct mlx5_eswitch *esw,
 
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
 	flow_act.flags = FLOW_ACT_IGNORE_FLOW_LEVEL | FLOW_ACT_NO_APPEND;
+	flow_act.fg = e->recirc_grp;
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 	dest.ft = mlx5_chains_get_table(chains, 0, 1, 0);
 	if (IS_ERR(dest.ft)) {
 		err = PTR_ERR(dest.ft);
 		goto err_table;
 	}
-	handle = mlx5_add_flow_rules(e->ft, rule_spec, &flow_act, &dest, 1);
+	handle = mlx5_add_flow_rules(e->ft, NULL, &flow_act, &dest, 1);
 	if (IS_ERR(handle)) {
 		err = PTR_ERR(handle);
 		goto err_handle;
@@ -233,14 +151,10 @@ static int mlx5_esw_indir_table_rule_get(struct mlx5_eswitch *esw,
 
 	mlx5e_mod_hdr_dealloc(&mod_acts);
 	rule->handle = handle;
-	rule->vni = esw_attr->rx_tun_attr->vni;
 	rule->mh = flow_act.modify_hdr;
-	memcpy(&rule->dst_ip, &esw_attr->rx_tun_attr->dst_ip,
-	       sizeof(esw_attr->rx_tun_attr->dst_ip));
 	refcount_set(&rule->refcnt, 1);
-	list_add(&rule->list, &e->recirc_rules);
-	e->recirc_cnt++;
-	goto out;
+	e->recirc_rule = rule;
+	return 0;
 
 err_handle:
 	mlx5_chains_put_table(chains, 0, 1, 0);
@@ -250,89 +164,44 @@ static int mlx5_esw_indir_table_rule_get(struct mlx5_eswitch *esw,
 err_mod_hdr_regc1:
 	mlx5e_mod_hdr_dealloc(&mod_acts);
 err_mod_hdr_regc0:
-err_ethertype:
 	kfree(rule);
-out:
-	kvfree(rule_spec);
 	return err;
 }
 
 static void mlx5_esw_indir_table_rule_put(struct mlx5_eswitch *esw,
-					  struct mlx5_flow_attr *attr,
 					  struct mlx5_esw_indir_table_entry *e)
 {
-	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
+	struct mlx5_esw_indir_table_rule *rule = e->recirc_rule;
 	struct mlx5_fs_chains *chains = esw_chains(esw);
-	struct mlx5_esw_indir_table_rule *rule;
-
-	list_for_each_entry(rule, &e->recirc_rules, list)
-		if (rule->vni == esw_attr->rx_tun_attr->vni &&
-		    !memcmp(&rule->dst_ip, &esw_attr->rx_tun_attr->dst_ip,
-			    sizeof(esw_attr->rx_tun_attr->dst_ip)))
-			goto found;
 
+	if (!rule)
 		return;
 
-found:
 	if (!refcount_dec_and_test(&rule->refcnt))
 		return;
 
 	mlx5_del_flow_rules(rule->handle);
 	mlx5_chains_put_table(chains, 0, 1, 0);
 	mlx5_modify_header_dealloc(esw->dev, rule->mh);
-	list_del(&rule->list);
 	kfree(rule);
-	e->recirc_cnt--;
+	e->recirc_rule = NULL;
 }
 
-static int mlx5_create_indir_recirc_group(struct mlx5_eswitch *esw,
-					  struct mlx5_flow_attr *attr,
-					  struct mlx5_flow_spec *spec,
-					  struct mlx5_esw_indir_table_entry *e)
+static int mlx5_create_indir_recirc_group(struct mlx5_esw_indir_table_entry *e)
 {
 	int err = 0, inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
-	u32 *in, *match;
+	u32 *in;
 
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
 
-	MLX5_SET(create_flow_group_in, in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS |
-		 MLX5_MATCH_MISC_PARAMETERS | MLX5_MATCH_MISC_PARAMETERS_2);
-	match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
-
-	if (MLX5_CAP_FLOWTABLE_NIC_RX(esw->dev, ft_field_support.outer_ip_version))
-		MLX5_SET(fte_match_param, match, outer_headers.ip_version, 0xf);
-	else
-		MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.ethertype);
-
-	if (attr->ip_version == 4) {
-		MLX5_SET_TO_ONES(fte_match_param, match,
-				 outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4);
-	} else if (attr->ip_version == 6) {
-		memset(MLX5_ADDR_OF(fte_match_param, match,
-				    outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
-		       0xff, sizeof(struct in6_addr));
-	} else {
-		err = -EOPNOTSUPP;
-		goto out;
-	}
-
-	MLX5_SET_TO_ONES(fte_match_param, match, misc_parameters.vxlan_vni);
-	MLX5_SET(fte_match_param, match, misc_parameters_2.metadata_reg_c_0,
-		 mlx5_eswitch_get_vport_metadata_mask());
 	MLX5_SET(create_flow_group_in, in, start_flow_index, 0);
-	MLX5_SET(create_flow_group_in, in, end_flow_index, MLX5_ESW_INDIR_TABLE_RECIRC_IDX_MAX);
+	MLX5_SET(create_flow_group_in, in, end_flow_index, MLX5_ESW_INDIR_TABLE_RECIRC_IDX);
 	e->recirc_grp = mlx5_create_flow_group(e->ft, in);
-	if (IS_ERR(e->recirc_grp)) {
+	if (IS_ERR(e->recirc_grp))
 		err = PTR_ERR(e->recirc_grp);
-		goto out;
-	}
 
-	INIT_LIST_HEAD(&e->recirc_rules);
-	e->recirc_cnt = 0;
-
-out:
 	kvfree(in);
 	return err;
 }
@@ -343,19 +212,12 @@ static int mlx5_create_indir_fwd_group(struct mlx5_eswitch *esw,
 	int err = 0, inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_flow_destination dest = {};
 	struct mlx5_flow_act flow_act = {};
-	struct mlx5_flow_spec *spec;
 	u32 *in;
 
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
 
-	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
-	if (!spec) {
-		kvfree(in);
-		return -ENOMEM;
-	}
-
 	/* Hold one entry */
 	MLX5_SET(create_flow_group_in, in, start_flow_index, MLX5_ESW_INDIR_TABLE_FWD_IDX);
 	MLX5_SET(create_flow_group_in, in, end_flow_index, MLX5_ESW_INDIR_TABLE_FWD_IDX);
@@ -366,25 +228,25 @@ static int mlx5_create_indir_fwd_group(struct mlx5_eswitch *esw,
 	}
 
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	flow_act.fg = e->fwd_grp;
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
 	dest.vport.num = e->vport;
 	dest.vport.vhca_id = MLX5_CAP_GEN(esw->dev, vhca_id);
 	dest.vport.flags = MLX5_FLOW_DEST_VPORT_VHCA_ID;
-	e->fwd_rule = mlx5_add_flow_rules(e->ft, spec, &flow_act, &dest, 1);
+	e->fwd_rule = mlx5_add_flow_rules(e->ft, NULL, &flow_act, &dest, 1);
 	if (IS_ERR(e->fwd_rule)) {
 		mlx5_destroy_flow_group(e->fwd_grp);
 		err = PTR_ERR(e->fwd_rule);
 	}
 
 err_out:
-	kvfree(spec);
 	kvfree(in);
 	return err;
 }
 
 static struct mlx5_esw_indir_table_entry *
 mlx5_esw_indir_table_entry_create(struct mlx5_eswitch *esw, struct mlx5_flow_attr *attr,
-				  struct mlx5_flow_spec *spec, u16 vport, bool decap)
+				  u16 vport, bool decap)
 {
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_flow_namespace *root_ns;
@@ -412,15 +274,14 @@ mlx5_esw_indir_table_entry_create(struct mlx5_eswitch *esw, struct mlx5_flow_att
 	}
 	e->ft = ft;
 	e->vport = vport;
-	e->ip_version = attr->ip_version;
 	e->fwd_ref = !decap;
 
-	err = mlx5_create_indir_recirc_group(esw, attr, spec, e);
+	err = mlx5_create_indir_recirc_group(e);
 	if (err)
 		goto recirc_grp_err;
 
 	if (decap) {
-		err = mlx5_esw_indir_table_rule_get(esw, attr, spec, e);
+		err = mlx5_esw_indir_table_rule_get(esw, attr, e);
 		if (err)
 			goto recirc_rule_err;
 	}
@@ -430,13 +291,13 @@ mlx5_esw_indir_table_entry_create(struct mlx5_eswitch *esw, struct mlx5_flow_att
 		goto fwd_grp_err;
 
 	hash_add(esw->fdb_table.offloads.indir->table, &e->hlist,
-		 vport << 16 | attr->ip_version);
+		 vport << 16);
 
 	return e;
 
 fwd_grp_err:
 	if (decap)
-		mlx5_esw_indir_table_rule_put(esw, attr, e);
+		mlx5_esw_indir_table_rule_put(esw, e);
 recirc_rule_err:
 	mlx5_destroy_flow_group(e->recirc_grp);
 recirc_grp_err:
@@ -447,13 +308,13 @@ mlx5_esw_indir_table_entry_create(struct mlx5_eswitch *esw, struct mlx5_flow_att
 }
 
 static struct mlx5_esw_indir_table_entry *
-mlx5_esw_indir_table_entry_lookup(struct mlx5_eswitch *esw, u16 vport, u8 ip_version)
+mlx5_esw_indir_table_entry_lookup(struct mlx5_eswitch *esw, u16 vport)
 {
 	struct mlx5_esw_indir_table_entry *e;
-	u32 key = vport << 16 | ip_version;
+	u32 key = vport << 16;
 
 	hash_for_each_possible(esw->fdb_table.offloads.indir->table, e, hlist, key)
-		if (e->vport == vport && e->ip_version == ip_version)
+		if (e->vport == vport)
 			return e;
 
 	return NULL;
@@ -461,24 +322,23 @@ mlx5_esw_indir_table_entry_lookup(struct mlx5_eswitch *esw, u16 vport, u8 ip_ver
 
 struct mlx5_flow_table *mlx5_esw_indir_table_get(struct mlx5_eswitch *esw,
 						 struct mlx5_flow_attr *attr,
-						 struct mlx5_flow_spec *spec,
 						 u16 vport, bool decap)
 {
 	struct mlx5_esw_indir_table_entry *e;
 	int err;
 
 	mutex_lock(&esw->fdb_table.offloads.indir->lock);
-	e = mlx5_esw_indir_table_entry_lookup(esw, vport, attr->ip_version);
+	e = mlx5_esw_indir_table_entry_lookup(esw, vport);
 	if (e) {
 		if (!decap) {
 			e->fwd_ref++;
 		} else {
-			err = mlx5_esw_indir_table_rule_get(esw, attr, spec, e);
+			err = mlx5_esw_indir_table_rule_get(esw, attr, e);
 			if (err)
 				goto out_err;
 		}
 	} else {
-		e = mlx5_esw_indir_table_entry_create(esw, attr, spec, vport, decap);
+		e = mlx5_esw_indir_table_entry_create(esw, attr, vport, decap);
 		if (IS_ERR(e)) {
 			err = PTR_ERR(e);
 			esw_warn(esw->dev, "Failed to create indirection table, err %d.\n", err);
@@ -494,22 +354,21 @@ struct mlx5_flow_table *mlx5_esw_indir_table_get(struct mlx5_eswitch *esw,
 }
 
 void mlx5_esw_indir_table_put(struct mlx5_eswitch *esw,
-			      struct mlx5_flow_attr *attr,
 			      u16 vport, bool decap)
 {
 	struct mlx5_esw_indir_table_entry *e;
 
 	mutex_lock(&esw->fdb_table.offloads.indir->lock);
-	e = mlx5_esw_indir_table_entry_lookup(esw, vport, attr->ip_version);
+	e = mlx5_esw_indir_table_entry_lookup(esw, vport);
 	if (!e)
 		goto out;
 
 	if (!decap)
 		e->fwd_ref--;
 	else
-		mlx5_esw_indir_table_rule_put(esw, attr, e);
+		mlx5_esw_indir_table_rule_put(esw, e);
 
-	if (e->fwd_ref || e->recirc_cnt)
+	if (e->fwd_ref || e->recirc_rule)
 		goto out;
 
 	hash_del(&e->hlist);

drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.h

@@ -13,10 +13,8 @@ mlx5_esw_indir_table_destroy(struct mlx5_esw_indir_table *indir);
 
 struct mlx5_flow_table *mlx5_esw_indir_table_get(struct mlx5_eswitch *esw,
 						 struct mlx5_flow_attr *attr,
-						 struct mlx5_flow_spec *spec,
 						 u16 vport, bool decap);
 void mlx5_esw_indir_table_put(struct mlx5_eswitch *esw,
-			      struct mlx5_flow_attr *attr,
 			      u16 vport, bool decap);
 
 bool
@@ -44,7 +42,6 @@ mlx5_esw_indir_table_destroy(struct mlx5_esw_indir_table *indir)
 static inline struct mlx5_flow_table *
 mlx5_esw_indir_table_get(struct mlx5_eswitch *esw,
 			 struct mlx5_flow_attr *attr,
-			 struct mlx5_flow_spec *spec,
 			 u16 vport, bool decap)
 {
 	return ERR_PTR(-EOPNOTSUPP);
@@ -52,7 +49,6 @@ mlx5_esw_indir_table_get(struct mlx5_eswitch *esw,
 
 static inline void
 mlx5_esw_indir_table_put(struct mlx5_eswitch *esw,
-			 struct mlx5_flow_attr *attr,
 			 u16 vport, bool decap)
 {
 }

drivers/net/ethernet/mellanox/mlx5/core/eswitch.c

@@ -1250,7 +1250,7 @@ static int mlx5_esw_acls_ns_init(struct mlx5_eswitch *esw)
 		if (err)
 			return err;
 	} else {
-		esw_warn(dev, "engress ACL is not supported by FW\n");
+		esw_warn(dev, "egress ACL is not supported by FW\n");
 	}
 
 	if (MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support)) {
@@ -1406,9 +1406,7 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf)
 	mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs);
 	if (clear_vf)
 		mlx5_eswitch_clear_vf_vports_info(esw);
-	/* If disabling sriov in switchdev mode, free meta rules here
-	 * because it depends on num_vfs.
-	 */
+
 	if (esw->mode == MLX5_ESWITCH_OFFLOADS) {
 		struct devlink *devlink = priv_to_devlink(esw->dev);
 

drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c

@@ -179,15 +179,14 @@ mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw,
 
 static int
 esw_setup_decap_indir(struct mlx5_eswitch *esw,
-		      struct mlx5_flow_attr *attr,
-		      struct mlx5_flow_spec *spec)
+		      struct mlx5_flow_attr *attr)
 {
 	struct mlx5_flow_table *ft;
 
 	if (!(attr->flags & MLX5_ATTR_FLAG_SRC_REWRITE))
 		return -EOPNOTSUPP;
 
-	ft = mlx5_esw_indir_table_get(esw, attr, spec,
+	ft = mlx5_esw_indir_table_get(esw, attr,
 				      mlx5_esw_indir_table_decap_vport(attr), true);
 	return PTR_ERR_OR_ZERO(ft);
 }
@@ -197,7 +196,7 @@ esw_cleanup_decap_indir(struct mlx5_eswitch *esw,
 			struct mlx5_flow_attr *attr)
 {
 	if (mlx5_esw_indir_table_decap_vport(attr))
-		mlx5_esw_indir_table_put(esw, attr,
+		mlx5_esw_indir_table_put(esw,
 					 mlx5_esw_indir_table_decap_vport(attr),
 					 true);
 }
@@ -235,7 +234,6 @@ esw_setup_ft_dest(struct mlx5_flow_destination *dest,
 		  struct mlx5_flow_act *flow_act,
 		  struct mlx5_eswitch *esw,
 		  struct mlx5_flow_attr *attr,
-		  struct mlx5_flow_spec *spec,
 		  int i)
 {
 	flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
@@ -243,7 +241,7 @@ esw_setup_ft_dest(struct mlx5_flow_destination *dest,
 	dest[i].ft = attr->dest_ft;
 
 	if (mlx5_esw_indir_table_decap_vport(attr))
-		return esw_setup_decap_indir(esw, attr, spec);
+		return esw_setup_decap_indir(esw, attr);
 	return 0;
 }
 
@@ -298,7 +296,7 @@ static void esw_put_dest_tables_loop(struct mlx5_eswitch *esw, struct mlx5_flow_
 			mlx5_chains_put_table(chains, 0, 1, 0);
 		else if (mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].rep->vport,
 						     esw_attr->dests[i].mdev))
-			mlx5_esw_indir_table_put(esw, attr, esw_attr->dests[i].rep->vport,
+			mlx5_esw_indir_table_put(esw, esw_attr->dests[i].rep->vport,
 						 false);
 }
 
@@ -384,7 +382,6 @@ esw_setup_indir_table(struct mlx5_flow_destination *dest,
 		      struct mlx5_flow_act *flow_act,
 		      struct mlx5_eswitch *esw,
 		      struct mlx5_flow_attr *attr,
-		      struct mlx5_flow_spec *spec,
 		      bool ignore_flow_lvl,
 		      int *i)
 {
@@ -399,7 +396,7 @@ esw_setup_indir_table(struct mlx5_flow_destination *dest,
 			flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
 		dest[*i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 
-		dest[*i].ft = mlx5_esw_indir_table_get(esw, attr, spec,
+		dest[*i].ft = mlx5_esw_indir_table_get(esw, attr,
 						       esw_attr->dests[j].rep->vport, false);
 		if (IS_ERR(dest[*i].ft)) {
 			err = PTR_ERR(dest[*i].ft);
@@ -408,7 +405,7 @@ esw_setup_indir_table(struct mlx5_flow_destination *dest,
 	}
 
 	if (mlx5_esw_indir_table_decap_vport(attr)) {
-		err = esw_setup_decap_indir(esw, attr, spec);
+		err = esw_setup_decap_indir(esw, attr);
 		if (err)
 			goto err_indir_tbl_get;
 	}
@@ -511,14 +508,14 @@ esw_setup_dests(struct mlx5_flow_destination *dest,
 		err = esw_setup_mtu_dest(dest, &attr->meter_attr, *i);
 		(*i)++;
 	} else if (esw_is_indir_table(esw, attr)) {
-		err = esw_setup_indir_table(dest, flow_act, esw, attr, spec, true, i);
+		err = esw_setup_indir_table(dest, flow_act, esw, attr, true, i);
 	} else if (esw_is_chain_src_port_rewrite(esw, esw_attr)) {
 		err = esw_setup_chain_src_port_rewrite(dest, flow_act, esw, chains, attr, i);
 	} else {
 		*i = esw_setup_vport_dests(dest, flow_act, esw, esw_attr, *i);
 
 		if (attr->dest_ft) {
-			err = esw_setup_ft_dest(dest, flow_act, esw, attr, spec, *i);
+			err = esw_setup_ft_dest(dest, flow_act, esw, attr, *i);
 			(*i)++;
 		} else if (attr->dest_chain) {
 			err = esw_setup_chain_dest(dest, flow_act, chains, attr->dest_chain,
@@ -727,7 +724,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 	for (i = 0; i < esw_attr->split_count; i++) {
 		if (esw_is_indir_table(esw, attr))
-			err = esw_setup_indir_table(dest, &flow_act, esw, attr, spec, false, &i);
+			err = esw_setup_indir_table(dest, &flow_act, esw, attr, false, &i);
 		else if (esw_is_chain_src_port_rewrite(esw, esw_attr))
 			err = esw_setup_chain_src_port_rewrite(dest, &flow_act, esw, chains, attr,
 							       &i);
@@ -3575,9 +3572,9 @@ int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
 	if (IS_ERR(esw))
 		return PTR_ERR(esw);
 
-	down_write(&esw->mode_lock);
+	down_read(&esw->mode_lock);
 	err = esw_mode_to_devlink(esw->mode, mode);
-	up_write(&esw->mode_lock);
+	up_read(&esw->mode_lock);
 	return err;
 }
 
@@ -3675,9 +3672,9 @@ int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode)
 	if (IS_ERR(esw))
 		return PTR_ERR(esw);
 
-	down_write(&esw->mode_lock);
+	down_read(&esw->mode_lock);
 	err = esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode);
-	up_write(&esw->mode_lock);
+	up_read(&esw->mode_lock);
 	return err;
 }
 
@@ -3749,9 +3746,9 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink,
 	if (IS_ERR(esw))
 		return PTR_ERR(esw);
 
-	down_write(&esw->mode_lock);
+	down_read(&esw->mode_lock);
 	*encap = esw->offloads.encap;
-	up_write(&esw->mode_lock);
+	up_read(&esw->mode_lock);
 	return 0;
 }
 

drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c

@@ -69,6 +69,13 @@ enum {
 	MLX5_MTPPS_FS_OUT_PULSE_DURATION_NS     = BIT(0xa),
 };
 
+enum {
+	MLX5_MTUTC_OPERATION_ADJUST_TIME_MIN          = S16_MIN,
+	MLX5_MTUTC_OPERATION_ADJUST_TIME_MAX          = S16_MAX,
+	MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MIN = -200000,
+	MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MAX = 200000,
+};
+
 static bool mlx5_real_time_mode(struct mlx5_core_dev *mdev)
 {
 	return (mlx5_is_real_time_rq(mdev) || mlx5_is_real_time_sq(mdev));
@@ -86,6 +93,22 @@ static bool mlx5_modify_mtutc_allowed(struct mlx5_core_dev *mdev)
 	return MLX5_CAP_MCAM_FEATURE(mdev, ptpcyc2realtime_modify);
 }
 
+static bool mlx5_is_mtutc_time_adj_cap(struct mlx5_core_dev *mdev, s64 delta)
+{
+	s64 min = MLX5_MTUTC_OPERATION_ADJUST_TIME_MIN;
+	s64 max = MLX5_MTUTC_OPERATION_ADJUST_TIME_MAX;
+
+	if (MLX5_CAP_MCAM_FEATURE(mdev, mtutc_time_adjustment_extended_range)) {
+		min = MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MIN;
+		max = MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MAX;
+	}
+
+	if (delta < min || delta > max)
+		return false;
+
+	return true;
+}
+
 static int mlx5_set_mtutc(struct mlx5_core_dev *dev, u32 *mtutc, u32 size)
 {
 	u32 out[MLX5_ST_SZ_DW(mtutc_reg)] = {};
@@ -288,8 +311,8 @@ static int mlx5_ptp_adjtime_real_time(struct mlx5_core_dev *mdev, s64 delta)
 	if (!mlx5_modify_mtutc_allowed(mdev))
 		return 0;
 
-	/* HW time adjustment range is s16. If out of range, settime instead */
-	if (delta < S16_MIN || delta > S16_MAX) {
+	/* HW time adjustment range is checked. If out of range, settime instead */
+	if (!mlx5_is_mtutc_time_adj_cap(mdev, delta)) {
 		struct timespec64 ts;
 		s64 ns;
 
@@ -326,6 +349,19 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 	return 0;
 }
 
+static int mlx5_ptp_adjphase(struct ptp_clock_info *ptp, s32 delta)
+{
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
+	struct mlx5_core_dev *mdev;
+
+	mdev = container_of(clock, struct mlx5_core_dev, clock);
+
+	if (!mlx5_is_mtutc_time_adj_cap(mdev, delta))
+		return -ERANGE;
+
+	return mlx5_ptp_adjtime(ptp, delta);
+}
+
 static int mlx5_ptp_adjfreq_real_time(struct mlx5_core_dev *mdev, s32 freq)
 {
 	u32 in[MLX5_ST_SZ_DW(mtutc_reg)] = {};
@@ -688,6 +724,7 @@ static const struct ptp_clock_info mlx5_ptp_clock_info = {
 	.n_pins		= 0,
 	.pps		= 0,
 	.adjfine	= mlx5_ptp_adjfine,
+	.adjphase	= mlx5_ptp_adjphase,
 	.adjtime	= mlx5_ptp_adjtime,
 	.gettimex64	= mlx5_ptp_gettimex,
 	.settime64	= mlx5_ptp_settime,

include/linux/mlx5/mlx5_ifc.h

@@ -9941,7 +9941,9 @@ struct mlx5_ifc_pcam_reg_bits {
 };
 
 struct mlx5_ifc_mcam_enhanced_features_bits {
-	u8         reserved_at_0[0x5d];
+	u8         reserved_at_0[0x51];
+	u8         mtutc_time_adjustment_extended_range[0x1];
+	u8         reserved_at_52[0xb];
 	u8         mcia_32dwords[0x1];
 	u8         out_pulse_duration_ns[0x1];
 	u8         npps_period[0x1];