Merge tag 'mlx5e-updates-2018-05-17' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5e-updates-2018-05-17

From: Or Gerlitz <[email protected]>

This series addresses a regression introduced by the
shared block TC changes [1]. Currently, for VF->VF and uplink->VF rules, the
TC core (cls_api) attempts to offload the same flow multiple times into
the driver, as a side effect of the mlx5 registration to the egdev callback.

We use the flow cookie to ignore attempts to add such flows, we can't
reject them (return error), b/c this will fail the offload attempt, so we
ignore that.

The last patch of the series deals with exposing HW stats counters through
ethtool for the vport reps.

Dave - the regression that we are addressing was introduced in 4.15 [1] and applies
to nfp and mlx5. Jiri suggested to push driver side fixes to net-next, this is
already done for nfp [2][3]. Once this is upstream, we will submit a small/point
single patch fix for the TC core code which can serve for net and stable, but not
carried into net-next, b/c it might limit some future use-cases.

[1] 208c0f4 "net: sched: use tc_setup_cb_call to call per-block callbacks"
[2] c50647d "nfp: flower: ignore duplicate cb requests for same rule"
[3] 54a4a03 "nfp: flower: support offloading multiple rules with same cookie"
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

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

@@ -634,7 +634,6 @@ struct mlx5e_flow_table {
 struct mlx5e_tc_table {
 	struct mlx5_flow_table		*t;
 
-	struct rhashtable_params        ht_params;
 	struct rhashtable               ht;
 
 	DECLARE_HASHTABLE(mod_hdr_tbl, 8);
@@ -1118,9 +1117,6 @@ int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
 int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv,
 			       struct ethtool_flash *flash);
 
-int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
-			    void *cb_priv);
-
 /* mlx5e generic netdev management API */
 struct net_device*
 mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile,

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

@@ -3136,22 +3136,23 @@ static int mlx5e_setup_tc_mqprio(struct net_device *netdev,
 
 #ifdef CONFIG_MLX5_ESWITCH
 static int mlx5e_setup_tc_cls_flower(struct mlx5e_priv *priv,
-				     struct tc_cls_flower_offload *cls_flower)
+				     struct tc_cls_flower_offload *cls_flower,
+				     int flags)
 {
 	switch (cls_flower->command) {
 	case TC_CLSFLOWER_REPLACE:
-		return mlx5e_configure_flower(priv, cls_flower);
+		return mlx5e_configure_flower(priv, cls_flower, flags);
 	case TC_CLSFLOWER_DESTROY:
-		return mlx5e_delete_flower(priv, cls_flower);
+		return mlx5e_delete_flower(priv, cls_flower, flags);
 	case TC_CLSFLOWER_STATS:
-		return mlx5e_stats_flower(priv, cls_flower);
+		return mlx5e_stats_flower(priv, cls_flower, flags);
 	default:
 		return -EOPNOTSUPP;
 	}
 }
 
-int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
-			    void *cb_priv)
+static int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+				   void *cb_priv)
 {
 	struct mlx5e_priv *priv = cb_priv;
 
@@ -3160,7 +3161,7 @@ int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
-		return mlx5e_setup_tc_cls_flower(priv, type_data);
+		return mlx5e_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -4461,7 +4462,7 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
 		goto err_destroy_direct_tirs;
 	}
 
-	err = mlx5e_tc_init(priv);
+	err = mlx5e_tc_nic_init(priv);
 	if (err)
 		goto err_destroy_flow_steering;
 
@@ -4482,7 +4483,7 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
 
 static void mlx5e_cleanup_nic_rx(struct mlx5e_priv *priv)
 {
-	mlx5e_tc_cleanup(priv);
+	mlx5e_tc_nic_cleanup(priv);
 	mlx5e_destroy_flow_steering(priv);
 	mlx5e_destroy_direct_tirs(priv);
 	mlx5e_destroy_indirect_tirs(priv);

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

@@ -66,18 +66,36 @@ static const struct counter_desc sw_rep_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_bytes) },
 };
 
-#define NUM_VPORT_REP_COUNTERS	ARRAY_SIZE(sw_rep_stats_desc)
+struct vport_stats {
+	u64 vport_rx_packets;
+	u64 vport_tx_packets;
+	u64 vport_rx_bytes;
+	u64 vport_tx_bytes;
+};
+
+static const struct counter_desc vport_rep_stats_desc[] = {
+	{ MLX5E_DECLARE_STAT(struct vport_stats, vport_rx_packets) },
+	{ MLX5E_DECLARE_STAT(struct vport_stats, vport_rx_bytes) },
+	{ MLX5E_DECLARE_STAT(struct vport_stats, vport_tx_packets) },
+	{ MLX5E_DECLARE_STAT(struct vport_stats, vport_tx_bytes) },
+};
+
+#define NUM_VPORT_REP_SW_COUNTERS ARRAY_SIZE(sw_rep_stats_desc)
+#define NUM_VPORT_REP_HW_COUNTERS ARRAY_SIZE(vport_rep_stats_desc)
 
 static void mlx5e_rep_get_strings(struct net_device *dev,
 				  u32 stringset, uint8_t *data)
 {
-	int i;
+	int i, j;
 
 	switch (stringset) {
 	case ETH_SS_STATS:
-		for (i = 0; i < NUM_VPORT_REP_COUNTERS; i++)
+		for (i = 0; i < NUM_VPORT_REP_SW_COUNTERS; i++)
 			strcpy(data + (i * ETH_GSTRING_LEN),
 			       sw_rep_stats_desc[i].format);
+		for (j = 0; j < NUM_VPORT_REP_HW_COUNTERS; j++, i++)
+			strcpy(data + (i * ETH_GSTRING_LEN),
+			       vport_rep_stats_desc[j].format);
 		break;
 	}
 }
@@ -140,26 +158,31 @@ static void mlx5e_rep_get_ethtool_stats(struct net_device *dev,
 					struct ethtool_stats *stats, u64 *data)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	int i;
+	int i, j;
 
 	if (!data)
 		return;
 
 	mutex_lock(&priv->state_lock);
 	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
 		mlx5e_rep_update_sw_counters(priv);
+	mlx5e_rep_update_hw_counters(priv);
 	mutex_unlock(&priv->state_lock);
 
-	for (i = 0; i < NUM_VPORT_REP_COUNTERS; i++)
+	for (i = 0; i < NUM_VPORT_REP_SW_COUNTERS; i++)
 		data[i] = MLX5E_READ_CTR64_CPU(&priv->stats.sw,
 					       sw_rep_stats_desc, i);
+
+	for (j = 0; j < NUM_VPORT_REP_HW_COUNTERS; j++, i++)
+		data[i] = MLX5E_READ_CTR64_CPU(&priv->stats.vf_vport,
+					       vport_rep_stats_desc, j);
 }
 
 static int mlx5e_rep_get_sset_count(struct net_device *dev, int sset)
 {
 	switch (sset) {
 	case ETH_SS_STATS:
-		return NUM_VPORT_REP_COUNTERS;
+		return NUM_VPORT_REP_SW_COUNTERS + NUM_VPORT_REP_HW_COUNTERS;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -723,15 +746,31 @@ static int mlx5e_rep_get_phys_port_name(struct net_device *dev,
 
 static int
 mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv,
-			      struct tc_cls_flower_offload *cls_flower)
+			      struct tc_cls_flower_offload *cls_flower, int flags)
 {
 	switch (cls_flower->command) {
 	case TC_CLSFLOWER_REPLACE:
-		return mlx5e_configure_flower(priv, cls_flower);
+		return mlx5e_configure_flower(priv, cls_flower, flags);
 	case TC_CLSFLOWER_DESTROY:
-		return mlx5e_delete_flower(priv, cls_flower);
+		return mlx5e_delete_flower(priv, cls_flower, flags);
 	case TC_CLSFLOWER_STATS:
-		return mlx5e_stats_flower(priv, cls_flower);
+		return mlx5e_stats_flower(priv, cls_flower, flags);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int mlx5e_rep_setup_tc_cb_egdev(enum tc_setup_type type, void *type_data,
+				       void *cb_priv)
+{
+	struct mlx5e_priv *priv = cb_priv;
+
+	if (!tc_cls_can_offload_and_chain0(priv->netdev, type_data))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return mlx5e_rep_setup_tc_cls_flower(priv, type_data, MLX5E_TC_EGRESS);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -747,7 +786,7 @@ static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data,
 
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
-		return mlx5e_rep_setup_tc_cls_flower(priv, type_data);
+		return mlx5e_rep_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -965,14 +1004,8 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 	}
 	rpriv->vport_rx_rule = flow_rule;
 
-	err = mlx5e_tc_init(priv);
-	if (err)
-		goto err_del_flow_rule;
-
 	return 0;
 
-err_del_flow_rule:
-	mlx5_del_flow_rules(rpriv->vport_rx_rule);
 err_destroy_direct_tirs:
 	mlx5e_destroy_direct_tirs(priv);
 err_destroy_direct_rqts:
@@ -984,7 +1017,6 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
 {
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 
-	mlx5e_tc_cleanup(priv);
 	mlx5_del_flow_rules(rpriv->vport_rx_rule);
 	mlx5e_destroy_direct_tirs(priv);
 	mlx5e_destroy_direct_rqts(priv);
@@ -1042,8 +1074,15 @@ mlx5e_nic_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	if (err)
 		goto err_remove_sqs;
 
+	/* init shared tc flow table */
+	err = mlx5e_tc_esw_init(&rpriv->tc_ht);
+	if (err)
+		goto  err_neigh_cleanup;
+
 	return 0;
 
+err_neigh_cleanup:
+	mlx5e_rep_neigh_cleanup(rpriv);
 err_remove_sqs:
 	mlx5e_remove_sqs_fwd_rules(priv);
 	return err;
@@ -1058,9 +1097,8 @@ mlx5e_nic_rep_unload(struct mlx5_eswitch_rep *rep)
 	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
 		mlx5e_remove_sqs_fwd_rules(priv);
 
-	/* clean (and re-init) existing uplink offloaded TC rules */
-	mlx5e_tc_cleanup(priv);
-	mlx5e_tc_init(priv);
+	/* clean uplink offloaded TC rules, delete shared tc flow table */
+	mlx5e_tc_esw_cleanup(&rpriv->tc_ht);
 
 	mlx5e_rep_neigh_cleanup(rpriv);
 }
@@ -1107,7 +1145,7 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 
 	uplink_rpriv = mlx5_eswitch_get_uplink_priv(dev->priv.eswitch, REP_ETH);
 	upriv = netdev_priv(uplink_rpriv->netdev);
-	err = tc_setup_cb_egdev_register(netdev, mlx5e_setup_tc_block_cb,
+	err = tc_setup_cb_egdev_register(netdev, mlx5e_rep_setup_tc_cb_egdev,
 					 upriv);
 	if (err)
 		goto err_neigh_cleanup;
@@ -1122,7 +1160,7 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	return 0;
 
 err_egdev_cleanup:
-	tc_setup_cb_egdev_unregister(netdev, mlx5e_setup_tc_block_cb,
+	tc_setup_cb_egdev_unregister(netdev, mlx5e_rep_setup_tc_cb_egdev,
 				     upriv);
 
 err_neigh_cleanup:
@@ -1151,7 +1189,7 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep)
 	uplink_rpriv = mlx5_eswitch_get_uplink_priv(priv->mdev->priv.eswitch,
 						    REP_ETH);
 	upriv = netdev_priv(uplink_rpriv->netdev);
-	tc_setup_cb_egdev_unregister(netdev, mlx5e_setup_tc_block_cb,
+	tc_setup_cb_egdev_unregister(netdev, mlx5e_rep_setup_tc_cb_egdev,
 				     upriv);
 	mlx5e_rep_neigh_cleanup(rpriv);
 	mlx5e_detach_netdev(priv);

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

@@ -59,6 +59,7 @@ struct mlx5e_rep_priv {
 	struct net_device      *netdev;
 	struct mlx5_flow_handle *vport_rx_rule;
 	struct list_head       vport_sqs_list;
+	struct rhashtable      tc_ht; /* valid for uplink rep */
 };
 
 static inline