Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma

Pull rdma updates from Doug Ledford:
 "Initial roundup of 4.6 merge window patches.

  This is the first of two pull requests.  It is the smaller request,
  but touches for more different things (this is everything but what is
  in or going into staging).  The pull request for the code in
  staging/rdma is on hold until after we decide what to do on the
  write/writev API issue and may be partially deferred until 4.7 as a
  result.

  Summary:

   - cxgb4 updates
   - nes updates
   - unification of iwarp portmapper code to core
   - add drain_cq API
   - various ib_core updates
   - minor ipoib updates
   - minor mlx4 updates
   - more significant mlx5 updates (including a minor merge conflict
     with net-next tree...merge is simple to resolve and Stephen's
     resolution was confirmed by Mellanox)
   - trivial net/9p rdma conversion
   - ocrdma RoCEv2 update
   - srpt updates"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (85 commits)
  iwpm: crash fix for large connections test
  iw_cxgb3: support for iWARP port mapping
  iw_cxgb4: remove port mapper related code
  iw_nes: remove port mapper related code
  iwcm: common code for port mapper
  net/9p: convert to new CQ API
  IB/mlx5: Add support for don't trap rules
  net/mlx5_core: Introduce forward to next priority action
  net/mlx5_core: Create anchor of last flow table
  iser: Accept arbitrary sg lists mapping if the device supports it
  mlx5: Add arbitrary sg list support
  IB/core: Add arbitrary sg_list support
  IB/mlx5: Expose correct max_fast_reg_page_list_len
  IB/mlx5: Make coding style more consistent
  IB/mlx5: Convert UMR CQ to new CQ API
  IB/ocrdma: Skip using unneeded intermediate variable
  IB/ocrdma: Skip using unneeded intermediate variable
  IB/ocrdma: Delete unnecessary variable initialisations in 11 functions
  IB/core: Documentation fix in the MAD header file
  IB/core: trivial prink cleanup.
  ...

12 files changed, 339 insertions, 52 deletions

diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index a072d341e205..1d2d1da40c80 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -1021,6 +1021,8 @@ struct cpl_l2t_write_req {
 #define L2T_W_NOREPLY_V(x) ((x) << L2T_W_NOREPLY_S)
 #define L2T_W_NOREPLY_F    L2T_W_NOREPLY_V(1U)
 
+#define CPL_L2T_VLAN_NONE 0xfff
+
 struct cpl_l2t_write_rpl {
 	union opcode_tid ot;
 	u8 status;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
index a32de30ea663..c8661c77b4e3 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
@@ -561,6 +561,7 @@ enum fw_flowc_mnem {
 	FW_FLOWC_MNEM_SNDBUF,
 	FW_FLOWC_MNEM_MSS,
 	FW_FLOWC_MNEM_TXDATAPLEN_MAX,
+	FW_FLOWC_MNEM_SCHEDCLASS = 11,
 };
 
 struct fw_flowc_mnemval {
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index d66c690a8597..e97094598b2d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -157,7 +157,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
 		[29] = "802.1ad offload support",
 		[31] = "Modifying loopback source checks using UPDATE_QP support",
 		[32] = "Loopback source checks support",
-		[33] = "RoCEv2 support"
+		[33] = "RoCEv2 support",
+		[34] = "DMFS Sniffer support (UC & MC)"
 	};
 	int i;
 
@@ -810,6 +811,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	if (field & 0x80)
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_FS_EN;
 	dev_cap->fs_log_max_ucast_qp_range_size = field & 0x1f;
+	if (field & 0x20)
+		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_DMFS_UC_MC_SNIFFER;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_PORT_BEACON_OFFSET);
 	if (field & 0x80)
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_PORT_BEACON;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index 1d4e2e054647..42d8de892bfe 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -752,8 +752,10 @@ static const u8 __promisc_mode[] = {
 	[MLX4_FS_REGULAR]   = 0x0,
 	[MLX4_FS_ALL_DEFAULT] = 0x1,
 	[MLX4_FS_MC_DEFAULT] = 0x3,
-	[MLX4_FS_UC_SNIFFER] = 0x4,
-	[MLX4_FS_MC_SNIFFER] = 0x5,
+	[MLX4_FS_MIRROR_RX_PORT] = 0x4,
+	[MLX4_FS_MIRROR_SX_PORT] = 0x5,
+	[MLX4_FS_UC_SNIFFER] = 0x6,
+	[MLX4_FS_MC_SNIFFER] = 0x7,
 };
 
 int mlx4_map_sw_to_hw_steering_mode(struct mlx4_dev *dev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 5b1753233c5d..81b2013ef968 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -516,7 +516,7 @@ struct mlx5e_priv {
 	struct mlx5_uar            cq_uar;
 	u32                        pdn;
 	u32                        tdn;
-	struct mlx5_core_mr        mr;
+	struct mlx5_core_mkey      mkey;
 	struct mlx5e_rq            drop_rq;
 
 	struct mlx5e_channel     **channel;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 402994bf7e16..0c49951606b6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -973,7 +973,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->cpu      = cpu;
 	c->pdev     = &priv->mdev->pdev->dev;
 	c->netdev   = priv->netdev;
-	c->mkey_be  = cpu_to_be32(priv->mr.key);
+	c->mkey_be  = cpu_to_be32(priv->mkey.key);
 	c->num_tc   = priv->params.num_tc;
 
 	mlx5e_build_channeltc_to_txq_map(priv, ix);
@@ -2204,7 +2204,7 @@ static void mlx5e_build_netdev(struct net_device *netdev)
 }
 
 static int mlx5e_create_mkey(struct mlx5e_priv *priv, u32 pdn,
-			     struct mlx5_core_mr *mr)
+			     struct mlx5_core_mkey *mkey)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5_create_mkey_mbox_in *in;
@@ -2220,7 +2220,7 @@ static int mlx5e_create_mkey(struct mlx5e_priv *priv, u32 pdn,
 	in->seg.flags_pd = cpu_to_be32(pdn | MLX5_MKEY_LEN64);
 	in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
 
-	err = mlx5_core_create_mkey(mdev, mr, in, sizeof(*in), NULL, NULL,
+	err = mlx5_core_create_mkey(mdev, mkey, in, sizeof(*in), NULL, NULL,
 				    NULL);
 
 	kvfree(in);
@@ -2269,7 +2269,7 @@ static void *mlx5e_create_netdev(struct mlx5_core_dev *mdev)
 		goto err_dealloc_pd;
 	}
 
-	err = mlx5e_create_mkey(priv, priv->pdn, &priv->mr);
+	err = mlx5e_create_mkey(priv, priv->pdn, &priv->mkey);
 	if (err) {
 		mlx5_core_err(mdev, "create mkey failed, %d\n", err);
 		goto err_dealloc_transport_domain;
@@ -2343,7 +2343,7 @@ err_destroy_tises:
 	mlx5e_destroy_tises(priv);
 
 err_destroy_mkey:
-	mlx5_core_destroy_mkey(mdev, &priv->mr);
+	mlx5_core_destroy_mkey(mdev, &priv->mkey);
 
 err_dealloc_transport_domain:
 	mlx5_core_dealloc_transport_domain(mdev, priv->tdn);
@@ -2377,7 +2377,7 @@ static void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, void *vpriv)
 	mlx5e_destroy_rqt(priv, MLX5E_INDIRECTION_RQT);
 	mlx5e_close_drop_rq(priv);
 	mlx5e_destroy_tises(priv);
-	mlx5_core_destroy_mkey(priv->mdev, &priv->mr);
+	mlx5_core_destroy_mkey(priv->mdev, &priv->mkey);
 	mlx5_core_dealloc_transport_domain(priv->mdev, priv->tdn);
 	mlx5_core_dealloc_pd(priv->mdev, priv->pdn);
 	mlx5_unmap_free_uar(priv->mdev, &priv->cq_uar);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 6f68dba8d7ed..bf3446794bd5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -77,6 +77,9 @@
 #define KERNEL_NUM_PRIOS 1
 #define KENREL_MIN_LEVEL 2
 
+#define ANCHOR_MAX_FT 1
+#define ANCHOR_NUM_PRIOS 1
+#define ANCHOR_MIN_LEVEL (BY_PASS_MIN_LEVEL + 1)
 struct node_caps {
 	size_t	arr_sz;
 	long	*caps;
@@ -92,7 +95,7 @@ static struct init_tree_node {
 	int max_ft;
 } root_fs = {
 	.type = FS_TYPE_NAMESPACE,
-	.ar_size = 3,
+	.ar_size = 4,
 	.children = (struct init_tree_node[]) {
 		ADD_PRIO(0, BY_PASS_MIN_LEVEL, 0,
 			 FS_REQUIRED_CAPS(FS_CAP(flow_table_properties_nic_receive.flow_modify_en),
@@ -108,6 +111,8 @@ static struct init_tree_node {
 					  FS_CAP(flow_table_properties_nic_receive.identified_miss_table_mode),
 					  FS_CAP(flow_table_properties_nic_receive.flow_table_modify)),
 			 ADD_NS(ADD_MULTIPLE_PRIO(LEFTOVERS_NUM_PRIOS, LEFTOVERS_MAX_FT))),
+		ADD_PRIO(0, ANCHOR_MIN_LEVEL, 0, {},
+			 ADD_NS(ADD_MULTIPLE_PRIO(ANCHOR_NUM_PRIOS, ANCHOR_MAX_FT))),
 	}
 };
 
@@ -196,8 +201,10 @@ static void tree_put_node(struct fs_node *node)
 
 static int tree_remove_node(struct fs_node *node)
 {
-	if (atomic_read(&node->refcount) > 1)
-		return -EPERM;
+	if (atomic_read(&node->refcount) > 1) {
+		atomic_dec(&node->refcount);
+		return -EEXIST;
+	}
 	tree_put_node(node);
 	return 0;
 }
@@ -360,6 +367,11 @@ static void del_rule(struct fs_node *node)
 	memcpy(match_value, fte->val, sizeof(fte->val));
 	fs_get_obj(ft, fg->node.parent);
 	list_del(&rule->node.list);
+	if (rule->sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
+		mutex_lock(&rule->dest_attr.ft->lock);
+		list_del(&rule->next_ft);
+		mutex_unlock(&rule->dest_attr.ft->lock);
+	}
 	fte->dests_size--;
 	if (fte->dests_size) {
 		err = mlx5_cmd_update_fte(dev, ft,
@@ -465,6 +477,8 @@ static struct mlx5_flow_table *alloc_flow_table(int level, int max_fte,
 	ft->node.type = FS_TYPE_FLOW_TABLE;
 	ft->type = table_type;
 	ft->max_fte = max_fte;
+	INIT_LIST_HEAD(&ft->fwd_rules);
+	mutex_init(&ft->lock);
 
 	return ft;
 }
@@ -601,9 +615,63 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio
 	return err;
 }
 
+static int mlx5_modify_rule_destination(struct mlx5_flow_rule *rule,
+					struct mlx5_flow_destination *dest)
+{
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_group *fg;
+	struct fs_fte *fte;
+	int err = 0;
+
+	fs_get_obj(fte, rule->node.parent);
+	if (!(fte->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST))
+		return -EINVAL;
+	lock_ref_node(&fte->node);
+	fs_get_obj(fg, fte->node.parent);
+	fs_get_obj(ft, fg->node.parent);
+
+	memcpy(&rule->dest_attr, dest, sizeof(*dest));
+	err = mlx5_cmd_update_fte(get_dev(&ft->node),
+				  ft, fg->id, fte);
+	unlock_ref_node(&fte->node);
+
+	return err;
+}
+
+/* Modify/set FWD rules that point on old_next_ft to point on new_next_ft  */
+static int connect_fwd_rules(struct mlx5_core_dev *dev,
+			     struct mlx5_flow_table *new_next_ft,
+			     struct mlx5_flow_table *old_next_ft)
+{
+	struct mlx5_flow_destination dest;
+	struct mlx5_flow_rule *iter;
+	int err = 0;
+
+	/* new_next_ft and old_next_ft could be NULL only
+	 * when we create/destroy the anchor flow table.
+	 */
+	if (!new_next_ft || !old_next_ft)
+		return 0;
+
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest.ft = new_next_ft;
+
+	mutex_lock(&old_next_ft->lock);
+	list_splice_init(&old_next_ft->fwd_rules, &new_next_ft->fwd_rules);
+	mutex_unlock(&old_next_ft->lock);
+	list_for_each_entry(iter, &new_next_ft->fwd_rules, next_ft) {
+		err = mlx5_modify_rule_destination(iter, &dest);
+		if (err)
+			pr_err("mlx5_core: failed to modify rule to point on flow table %d\n",
+			       new_next_ft->id);
+	}
+	return 0;
+}
+
 static int connect_flow_table(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft,
 			      struct fs_prio *prio)
 {
+	struct mlx5_flow_table *next_ft;
 	int err = 0;
 
 	/* Connect_prev_fts and update_root_ft_create are mutually exclusive */
@@ -612,6 +680,11 @@ static int connect_flow_table(struct mlx5_core_dev *dev, struct mlx5_flow_table
 		err = connect_prev_fts(dev, ft, prio);
 		if (err)
 			return err;
+
+		next_ft = find_next_chained_ft(prio);
+		err = connect_fwd_rules(dev, ft, next_ft);
+		if (err)
+			return err;
 	}
 
 	if (MLX5_CAP_FLOWTABLE(dev,
@@ -762,6 +835,7 @@ static struct mlx5_flow_rule *alloc_rule(struct mlx5_flow_destination *dest)
 	if (!rule)
 		return NULL;
 
+	INIT_LIST_HEAD(&rule->next_ft);
 	rule->node.type = FS_TYPE_FLOW_DEST;
 	memcpy(&rule->dest_attr, dest, sizeof(*dest));
 
@@ -782,9 +856,14 @@ static struct mlx5_flow_rule *add_rule_fte(struct fs_fte *fte,
 		return ERR_PTR(-ENOMEM);
 
 	fs_get_obj(ft, fg->node.parent);
-	/* Add dest to dests list- added as first element after the head */
+	/* Add dest to dests list- we need flow tables to be in the
+	 * end of the list for forward to next prio rules.
+	 */
 	tree_init_node(&rule->node, 1, del_rule);
-	list_add_tail(&rule->node.list, &fte->node.children);
+	if (dest && dest->type != MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE)
+		list_add(&rule->node.list, &fte->node.children);
+	else
+		list_add_tail(&rule->node.list, &fte->node.children);
 	fte->dests_size++;
 	if (fte->dests_size == 1)
 		err = mlx5_cmd_create_fte(get_dev(&ft->node),
@@ -903,6 +982,25 @@ out:
 	return fg;
 }
 
+static struct mlx5_flow_rule *find_flow_rule(struct fs_fte *fte,
+					     struct mlx5_flow_destination *dest)
+{
+	struct mlx5_flow_rule *rule;
+
+	list_for_each_entry(rule, &fte->node.children, node.list) {
+		if (rule->dest_attr.type == dest->type) {
+			if ((dest->type == MLX5_FLOW_DESTINATION_TYPE_VPORT &&
+			     dest->vport_num == rule->dest_attr.vport_num) ||
+			    (dest->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE &&
+			     dest->ft == rule->dest_attr.ft) ||
+			    (dest->type == MLX5_FLOW_DESTINATION_TYPE_TIR &&
+			     dest->tir_num == rule->dest_attr.tir_num))
+				return rule;
+		}
+	}
+	return NULL;
+}
+
 static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg,
 					  u32 *match_value,
 					  u8 action,
@@ -919,6 +1017,13 @@ static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg,
 		nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD);
 		if (compare_match_value(&fg->mask, match_value, &fte->val) &&
 		    action == fte->action && flow_tag == fte->flow_tag) {
+			rule = find_flow_rule(fte, dest);
+			if (rule) {
+				atomic_inc(&rule->node.refcount);
+				unlock_ref_node(&fte->node);
+				unlock_ref_node(&fg->node);
+				return rule;
+			}
 			rule = add_rule_fte(fte, fg, dest);
 			unlock_ref_node(&fte->node);
 			if (IS_ERR(rule))
@@ -984,14 +1089,14 @@ static struct mlx5_flow_rule *add_rule_to_auto_fg(struct mlx5_flow_table *ft,
 	return rule;
 }
 
-struct mlx5_flow_rule *
-mlx5_add_flow_rule(struct mlx5_flow_table *ft,
-		   u8 match_criteria_enable,
-		   u32 *match_criteria,
-		   u32 *match_value,
-		   u32 action,
-		   u32 flow_tag,
-		   struct mlx5_flow_destination *dest)
+static struct mlx5_flow_rule *
+_mlx5_add_flow_rule(struct mlx5_flow_table *ft,
+		    u8 match_criteria_enable,
+		    u32 *match_criteria,
+		    u32 *match_value,
+		    u32 action,
+		    u32 flow_tag,
+		    struct mlx5_flow_destination *dest)
 {
 	struct mlx5_flow_group *g;
 	struct mlx5_flow_rule *rule;
@@ -1014,6 +1119,63 @@ unlock:
 	unlock_ref_node(&ft->node);
 	return rule;
 }
+
+static bool fwd_next_prio_supported(struct mlx5_flow_table *ft)
+{
+	return ((ft->type == FS_FT_NIC_RX) &&
+		(MLX5_CAP_FLOWTABLE(get_dev(&ft->node), nic_rx_multi_path_tirs)));
+}
+
+struct mlx5_flow_rule *
+mlx5_add_flow_rule(struct mlx5_flow_table *ft,
+		   u8 match_criteria_enable,
+		   u32 *match_criteria,
+		   u32 *match_value,
+		   u32 action,
+		   u32 flow_tag,
+		   struct mlx5_flow_destination *dest)
+{
+	struct mlx5_flow_root_namespace *root = find_root(&ft->node);
+	struct mlx5_flow_destination gen_dest;
+	struct mlx5_flow_table *next_ft = NULL;
+	struct mlx5_flow_rule *rule = NULL;
+	u32 sw_action = action;
+	struct fs_prio *prio;
+
+	fs_get_obj(prio, ft->node.parent);
+	if (action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
+		if (!fwd_next_prio_supported(ft))
+			return ERR_PTR(-EOPNOTSUPP);
+		if (dest)
+			return ERR_PTR(-EINVAL);
+		mutex_lock(&root->chain_lock);
+		next_ft = find_next_chained_ft(prio);
+		if (next_ft) {
+			gen_dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+			gen_dest.ft = next_ft;
+			dest = &gen_dest;
+			action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+		} else {
+			mutex_unlock(&root->chain_lock);
+			return ERR_PTR(-EOPNOTSUPP);
+		}
+	}
+
+	rule =	_mlx5_add_flow_rule(ft, match_criteria_enable, match_criteria,
+				    match_value, action, flow_tag, dest);
+
+	if (sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
+		if (!IS_ERR_OR_NULL(rule) &&
+		    (list_empty(&rule->next_ft))) {
+			mutex_lock(&next_ft->lock);
+			list_add(&rule->next_ft, &next_ft->fwd_rules);
+			mutex_unlock(&next_ft->lock);
+			rule->sw_action = MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
+		}
+		mutex_unlock(&root->chain_lock);
+	}
+	return rule;
+}
 EXPORT_SYMBOL(mlx5_add_flow_rule);
 
 void mlx5_del_flow_rule(struct mlx5_flow_rule *rule)
@@ -1077,6 +1239,10 @@ static int disconnect_flow_table(struct mlx5_flow_table *ft)
 		return 0;
 
 	next_ft = find_next_chained_ft(prio);
+	err = connect_fwd_rules(dev, next_ft, ft);
+	if (err)
+		return err;
+
 	err = connect_prev_fts(dev, next_ft, prio);
 	if (err)
 		mlx5_core_warn(dev, "Failed to disconnect flow table %d\n",
@@ -1126,6 +1292,7 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 	case MLX5_FLOW_NAMESPACE_BYPASS:
 	case MLX5_FLOW_NAMESPACE_KERNEL:
 	case MLX5_FLOW_NAMESPACE_LEFTOVERS:
+	case MLX5_FLOW_NAMESPACE_ANCHOR:
 		prio = type;
 		break;
 	case MLX5_FLOW_NAMESPACE_FDB:
@@ -1351,6 +1518,25 @@ static void set_prio_attrs(struct mlx5_flow_root_namespace *root_ns)
 	}
 }
 
+#define ANCHOR_PRIO 0
+#define ANCHOR_SIZE 1
+static int create_anchor_flow_table(struct mlx5_core_dev
+							*dev)
+{
+	struct mlx5_flow_namespace *ns = NULL;
+	struct mlx5_flow_table *ft;
+
+	ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ANCHOR);
+	if (!ns)
+		return -EINVAL;
+	ft = mlx5_create_flow_table(ns, ANCHOR_PRIO, ANCHOR_SIZE);
+	if (IS_ERR(ft)) {
+		mlx5_core_err(dev, "Failed to create last anchor flow table");
+		return PTR_ERR(ft);
+	}
+	return 0;
+}
+
 static int init_root_ns(struct mlx5_core_dev *dev)
 {
 
@@ -1363,6 +1549,9 @@ static int init_root_ns(struct mlx5_core_dev *dev)
 
 	set_prio_attrs(dev->priv.root_ns);
 
+	if (create_anchor_flow_table(dev))
+		goto cleanup;
+
 	return 0;
 
 cleanup:
@@ -1392,6 +1581,15 @@ static void cleanup_single_prio_root_ns(struct mlx5_core_dev *dev,
 	root_ns = NULL;
 }
 
+static void destroy_flow_tables(struct fs_prio *prio)
+{
+	struct mlx5_flow_table *iter;
+	struct mlx5_flow_table *tmp;
+
+	fs_for_each_ft_safe(iter, tmp, prio)
+		mlx5_destroy_flow_table(iter);
+}
+
 static void cleanup_root_ns(struct mlx5_core_dev *dev)
 {
 	struct mlx5_flow_root_namespace *root_ns = dev->priv.root_ns;
@@ -1420,6 +1618,7 @@ static void cleanup_root_ns(struct mlx5_core_dev *dev)
 							 list);
 
 				fs_get_obj(obj_iter_prio2, iter_prio2);
+				destroy_flow_tables(obj_iter_prio2);
 				if (tree_remove_node(iter_prio2)) {
 					mlx5_core_warn(dev,
 						       "Priority %d wasn't destroyed, refcount > 1\n",
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 00245fd7e4bc..f37a6248a27b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -68,6 +68,11 @@ struct fs_node {
 struct mlx5_flow_rule {
 	struct fs_node				node;
 	struct mlx5_flow_destination		dest_attr;
+	/* next_ft should be accessed under chain_lock and only of
+	 * destination type is FWD_NEXT_fT.
+	 */
+	struct list_head			next_ft;
+	u32					sw_action;
 };
 
 /* Type of children is mlx5_flow_group */
@@ -82,6 +87,10 @@ struct mlx5_flow_table {
 		unsigned int		required_groups;
 		unsigned int		num_groups;
 	} autogroup;
+	/* Protect fwd_rules */
+	struct mutex			lock;
+	/* FWD rules that point on this flow table */
+	struct list_head		fwd_rules;
 };
 
 /* Type of children is mlx5_flow_rule */
@@ -142,6 +151,9 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev);
 #define fs_list_for_each_entry(pos, root)		\
 	list_for_each_entry(pos, root, node.list)
 
+#define fs_list_for_each_entry_safe(pos, tmp, root)		\
+	list_for_each_entry_safe(pos, tmp, root, node.list)
+
 #define fs_for_each_ns_or_ft_reverse(pos, prio)				\
 	list_for_each_entry_reverse(pos, &(prio)->node.children, list)
 
@@ -157,6 +169,9 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev);
 #define fs_for_each_ft(pos, prio)			\
 	fs_list_for_each_entry(pos, &(prio)->node.children)
 
+#define fs_for_each_ft_safe(pos, tmp, prio)			\
+	fs_list_for_each_entry_safe(pos, tmp, &(prio)->node.children)
+
 #define fs_for_each_fg(pos, ft)			\
 	fs_list_for_each_entry(pos, &(ft)->node.children)
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 1545a944c309..0916bbc69269 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1117,7 +1117,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 	mlx5_init_cq_table(dev);
 	mlx5_init_qp_table(dev);
 	mlx5_init_srq_table(dev);
-	mlx5_init_mr_table(dev);
+	mlx5_init_mkey_table(dev);
 
 	err = mlx5_init_fs(dev);
 	if (err) {
@@ -1164,7 +1164,7 @@ err_sriov:
 err_reg_dev:
 	mlx5_cleanup_fs(dev);
 err_fs:
-	mlx5_cleanup_mr_table(dev);
+	mlx5_cleanup_mkey_table(dev);
 	mlx5_cleanup_srq_table(dev);
 	mlx5_cleanup_qp_table(dev);
 	mlx5_cleanup_cq_table(dev);
@@ -1237,7 +1237,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 #endif
 
 	mlx5_cleanup_fs(dev);
-	mlx5_cleanup_mr_table(dev);
+	mlx5_cleanup_mkey_table(dev);
 	mlx5_cleanup_srq_table(dev);
 	mlx5_cleanup_qp_table(dev);
 	mlx5_cleanup_cq_table(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index 6fa22b51e460..77a7293921d5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -36,25 +36,26 @@
 #include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
 
-void mlx5_init_mr_table(struct mlx5_core_dev *dev)
+void mlx5_init_mkey_table(struct mlx5_core_dev *dev)
 {
-	struct mlx5_mr_table *table = &dev->priv.mr_table;
+	struct mlx5_mkey_table *table = &dev->priv.mkey_table;
 
 	memset(table, 0, sizeof(*table));
 	rwlock_init(&table->lock);
 	INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
 }
 
-void mlx5_cleanup_mr_table(struct mlx5_core_dev *dev)
+void mlx5_cleanup_mkey_table(struct mlx5_core_dev *dev)
 {
 }
 
-int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
+int mlx5_core_create_mkey(struct mlx5_core_dev *dev,
+			  struct mlx5_core_mkey *mkey,
 			  struct mlx5_create_mkey_mbox_in *in, int inlen,
 			  mlx5_cmd_cbk_t callback, void *context,
 			  struct mlx5_create_mkey_mbox_out *out)
 {
-	struct mlx5_mr_table *table = &dev->priv.mr_table;
+	struct mlx5_mkey_table *table = &dev->priv.mkey_table;
 	struct mlx5_create_mkey_mbox_out lout;
 	int err;
 	u8 key;
@@ -83,34 +84,35 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
 		return mlx5_cmd_status_to_err(&lout.hdr);
 	}
 
-	mr->iova = be64_to_cpu(in->seg.start_addr);
-	mr->size = be64_to_cpu(in->seg.len);
-	mr->key = mlx5_idx_to_mkey(be32_to_cpu(lout.mkey) & 0xffffff) | key;
-	mr->pd = be32_to_cpu(in->seg.flags_pd) & 0xffffff;
+	mkey->iova = be64_to_cpu(in->seg.start_addr);
+	mkey->size = be64_to_cpu(in->seg.len);
+	mkey->key = mlx5_idx_to_mkey(be32_to_cpu(lout.mkey) & 0xffffff) | key;
+	mkey->pd = be32_to_cpu(in->seg.flags_pd) & 0xffffff;
 
 	mlx5_core_dbg(dev, "out 0x%x, key 0x%x, mkey 0x%x\n",
-		      be32_to_cpu(lout.mkey), key, mr->key);
+		      be32_to_cpu(lout.mkey), key, mkey->key);
 
-	/* connect to MR tree */
+	/* connect to mkey tree */
 	write_lock_irq(&table->lock);
-	err = radix_tree_insert(&table->tree, mlx5_base_mkey(mr->key), mr);
+	err = radix_tree_insert(&table->tree, mlx5_base_mkey(mkey->key), mkey);
 	write_unlock_irq(&table->lock);
 	if (err) {
-		mlx5_core_warn(dev, "failed radix tree insert of mr 0x%x, %d\n",
-			       mlx5_base_mkey(mr->key), err);
-		mlx5_core_destroy_mkey(dev, mr);
+		mlx5_core_warn(dev, "failed radix tree insert of mkey 0x%x, %d\n",
+			       mlx5_base_mkey(mkey->key), err);
+		mlx5_core_destroy_mkey(dev, mkey);
 	}
 
 	return err;
 }
 EXPORT_SYMBOL(mlx5_core_create_mkey);
 
-int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr)
+int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev,
+			   struct mlx5_core_mkey *mkey)
 {
-	struct mlx5_mr_table *table = &dev->priv.mr_table;
+	struct mlx5_mkey_table *table = &dev->priv.mkey_table;
 	struct mlx5_destroy_mkey_mbox_in in;
 	struct mlx5_destroy_mkey_mbox_out out;
-	struct mlx5_core_mr *deleted_mr;
+	struct mlx5_core_mkey *deleted_mkey;
 	unsigned long flags;
 	int err;
 
@@ -118,16 +120,16 @@ int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr)
 	memset(&out, 0, sizeof(out));
 
 	write_lock_irqsave(&table->lock, flags);
-	deleted_mr = radix_tree_delete(&table->tree, mlx5_base_mkey(mr->key));
+	deleted_mkey = radix_tree_delete(&table->tree, mlx5_base_mkey(mkey->key));
 	write_unlock_irqrestore(&table->lock, flags);
-	if (!deleted_mr) {
-		mlx5_core_warn(dev, "failed radix tree delete of mr 0x%x\n",
-			       mlx5_base_mkey(mr->key));
+	if (!deleted_mkey) {
+		mlx5_core_warn(dev, "failed radix tree delete of mkey 0x%x\n",
+			       mlx5_base_mkey(mkey->key));
 		return -ENOENT;
 	}
 
 	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_DESTROY_MKEY);
-	in.mkey = cpu_to_be32(mlx5_mkey_to_idx(mr->key));
+	in.mkey = cpu_to_be32(mlx5_mkey_to_idx(mkey->key));
 	err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
 	if (err)
 		return err;
@@ -139,7 +141,7 @@ int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr)
 }
 EXPORT_SYMBOL(mlx5_core_destroy_mkey);
 
-int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
+int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey,
 			 struct mlx5_query_mkey_mbox_out *out, int outlen)
 {
 	struct mlx5_query_mkey_mbox_in in;
@@ -149,7 +151,7 @@ int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
 	memset(out, 0, outlen);
 
 	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_QUERY_MKEY);
-	in.mkey = cpu_to_be32(mlx5_mkey_to_idx(mr->key));
+	in.mkey = cpu_to_be32(mlx5_mkey_to_idx(mkey->key));
 	err = mlx5_cmd_exec(dev, &in, sizeof(in), out, outlen);
 	if (err)
 		return err;
@@ -161,7 +163,7 @@ int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
 }
 EXPORT_SYMBOL(mlx5_core_query_mkey);
 
-int mlx5_core_dump_fill_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
+int mlx5_core_dump_fill_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *_mkey,
 			     u32 *mkey)
 {
 	struct mlx5_query_special_ctxs_mbox_in in;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index a87e773e93f3..5635ce7ad693 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -324,6 +324,29 @@ int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev,
 }
 EXPORT_SYMBOL_GPL(mlx5_query_port_vl_hw_cap);
 
+int mlx5_core_query_ib_ppcnt(struct mlx5_core_dev *dev,
+			     u8 port_num, void *out, size_t sz)
+{
+	u32 *in;
+	int err;
+
+	in  = mlx5_vzalloc(sz);
+	if (!in) {
+		err = -ENOMEM;
+		return err;
+	}
+
+	MLX5_SET(ppcnt_reg, in, local_port, port_num);
+
+	MLX5_SET(ppcnt_reg, in, grp, MLX5_INFINIBAND_PORT_COUNTERS_GROUP);
+	err = mlx5_core_access_reg(dev, in, sz, out,
+				   sz, MLX5_REG_PPCNT, 0, 0);
+
+	kvfree(in);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx5_core_query_ib_ppcnt);
+
 int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause)
 {
 	u32 in[MLX5_ST_SZ_DW(pfcc_reg)];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index c7398b95aecd..90ab09e375b8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -850,3 +850,43 @@ int mlx5_nic_vport_disable_roce(struct mlx5_core_dev *mdev)
 	return mlx5_nic_vport_update_roce_state(mdev, MLX5_VPORT_ROCE_DISABLED);
 }
 EXPORT_SYMBOL_GPL(mlx5_nic_vport_disable_roce);
+
+int mlx5_core_query_vport_counter(struct mlx5_core_dev *dev, u8 other_vport,
+				  u8 port_num, void *out, size_t out_sz)
+{
+	int	in_sz = MLX5_ST_SZ_BYTES(query_vport_counter_in);
+	int	is_group_manager;
+	void   *in;
+	int	err;
+
+	is_group_manager = MLX5_CAP_GEN(dev, vport_group_manager);
+	in = mlx5_vzalloc(in_sz);
+	if (!in) {
+		err = -ENOMEM;
+		return err;
+	}
+
+	MLX5_SET(query_vport_counter_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_VPORT_COUNTER);
+	if (other_vport) {
+		if (is_group_manager) {
+			MLX5_SET(query_vport_counter_in, in, other_vport, 1);
+			MLX5_SET(query_vport_counter_in, in, vport_number, 0);
+		} else {
+			err = -EPERM;
+			goto free;
+		}
+	}
+	if (MLX5_CAP_GEN(dev, num_ports) == 2)
+		MLX5_SET(query_vport_counter_in, in, port_num, port_num);
+
+	err = mlx5_cmd_exec(dev, in, in_sz, out,  out_sz);
+	if (err)
+		goto free;
+	err = mlx5_cmd_status_to_err_v2(out);
+
+free:
+	kvfree(in);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx5_core_query_vport_counter);