From: Benjamin Poirier <bpoirier@nvidia.com>
Date: Wed, 16 Oct 2024 17:36:15 +0000 (+0300)
Subject: net/mlx5: Only create VEPA flow table when in VEPA mode
X-Git-Tag: v6.13-rc1~135^2~259^2~2
X-Git-Url: https://git.kernel.dk/?a=commitdiff_plain;h=f0ac6209460e8cc9bddf161d7210da5b72aa4846;p=linux-block.git

net/mlx5: Only create VEPA flow table when in VEPA mode

Currently, when VFs are created, two flow tables are added for the eswitch:
the "fdb" table, which contains rules for each VF and the "vepa_fdb" table.
In the default VEB mode, the vepa_fdb table is empty. When switching to
VEPA mode, flow steering rules are added to vepa_fdb. Even though the
vepa_fdb table is empty in VEB mode, its presence adds some cost to packet
processing. In some workloads, this leads to drops which are reported by
the rx_discards_phy ethtool counter.

In order to improve performance, only create vepa_fdb when in VEPA mode.

Tests were done on a ConnectX-6 Lx adapter forwarding 64B packets between
both ports using dpdk-testpmd. Numbers are Rx-pps for each port, as
reported by testpmd.

Without changes:
traffic to unknown mac
	testpmd on PF
		numvfs=0,0
			35257998,35264499
		numvfs=1,1
			24590124,24590888
	testpmd on VF with numvfs=1,1
		20434338,20434887
traffic to VF mac
	testpmd on VF with numvfs=1,1
		30341014,30340749

With changes:
traffic to unknown mac
	testpmd on PF
		numvfs=0,0
			35404361,35383378
		numvfs=1,1
			29801247,29790757
	testpmd on VF with numvfs=1,1
		24310435,24309084
traffic to VF mac
	testpmd on VF with numvfs=1,1
		34811436,34781706

Signed-off-by: Benjamin Poirier <bpoirier@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
index 288c797e4a78..45183de424f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
@@ -176,20 +176,10 @@ static void esw_destroy_legacy_vepa_table(struct mlx5_eswitch *esw)
 
 static int esw_create_legacy_table(struct mlx5_eswitch *esw)
 {
-	int err;
-
 	memset(&esw->fdb_table.legacy, 0, sizeof(struct legacy_fdb));
 	atomic64_set(&esw->user_count, 0);
 
-	err = esw_create_legacy_vepa_table(esw);
-	if (err)
-		return err;
-
-	err = esw_create_legacy_fdb_table(esw);
-	if (err)
-		esw_destroy_legacy_vepa_table(esw);
-
-	return err;
+	return esw_create_legacy_fdb_table(esw);
 }
 
 static void esw_cleanup_vepa_rules(struct mlx5_eswitch *esw)
@@ -259,15 +249,22 @@ static int _mlx5_eswitch_set_vepa_locked(struct mlx5_eswitch *esw,
 
 	if (!setting) {
 		esw_cleanup_vepa_rules(esw);
+		esw_destroy_legacy_vepa_table(esw);
 		return 0;
 	}
 
 	if (esw->fdb_table.legacy.vepa_uplink_rule)
 		return 0;
 
+	err = esw_create_legacy_vepa_table(esw);
+	if (err)
+		return err;
+
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
-	if (!spec)
-		return -ENOMEM;
+	if (!spec) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	/* Uplink rule forward uplink traffic to FDB */
 	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
@@ -303,8 +300,10 @@ static int _mlx5_eswitch_set_vepa_locked(struct mlx5_eswitch *esw,
 
 out:
 	kvfree(spec);
-	if (err)
+	if (err) {
 		esw_cleanup_vepa_rules(esw);
+		esw_destroy_legacy_vepa_table(esw);
+	}
 	return err;
 }