[PATCH net-next 14/15] net/mlx5: SD, defer vport metadata init until SD is ready

[Tariq Toukan]

From: Shay Drory <shayd@xxxxxxxxxx>

Allow SD devices to transition to switchdev before the SD group is
fully up. Metadata allocation requires the SD group to be ready, so
defer it from esw_offloads_enable() until SD shared-FDB activation.

Add mlx5_esw_offloads_init_deferred_metadata() which allocates
per-vport metadata and refreshes the manager ingress ACLs that were
previously programmed with metadata=0. The helper is idempotent and
can be called multiple times.

Signed-off-by: Shay Drory <shayd@xxxxxxxxxx>
Reviewed-by: Mark Bloch <mbloch@xxxxxxxxxx>
Signed-off-by: Tariq Toukan <tariqt@xxxxxxxxxx>
---
 .../net/ethernet/mellanox/mlx5/core/eswitch.h |  1 +
 .../mellanox/mlx5/core/eswitch_offloads.c     | 46 ++++++++++++++++++-
 .../net/ethernet/mellanox/mlx5/core/lib/sd.c  | 16 +++++++
 3 files changed, 62 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index a5f0774834fe..ecf6a28a1c08 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -440,6 +440,7 @@ struct mlx5_eswitch {
 
 void esw_offloads_disable(struct mlx5_eswitch *esw);
 int esw_offloads_enable(struct mlx5_eswitch *esw);
+int mlx5_esw_offloads_init_deferred_metadata(struct mlx5_eswitch *esw);
 void esw_offloads_cleanup(struct mlx5_eswitch *esw);
 int esw_offloads_init(struct mlx5_eswitch *esw);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 4d3f80bd6af0..503530b0acba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -43,6 +43,7 @@
 #include "esw/acl/ofld.h"
 #include "rdma.h"
 #include "en.h"
+#include "en_rep.h"
 #include "fs_core.h"
 #include "lib/mlx5.h"
 #include "lib/devcom.h"
@@ -3675,6 +3676,7 @@ static void esw_offloads_vport_metadata_cleanup(struct mlx5_eswitch *esw,
 
 	WARN_ON(vport->metadata != vport->default_metadata);
 	mlx5_esw_match_metadata_free(esw, vport->default_metadata);
+	vport->default_metadata = 0;
 }
 
 static void esw_offloads_metadata_uninit(struct mlx5_eswitch *esw)
@@ -3711,6 +3713,38 @@ static int esw_offloads_metadata_init(struct mlx5_eswitch *esw)
 	return err;
 }
 
+/* Deferred metadata init for SD devices: allocate vport metadata
+ * Safe to call multiple times - subsequent calls are no-ops.
+ */
+int mlx5_esw_offloads_init_deferred_metadata(struct mlx5_eswitch *esw)
+{
+	struct mlx5_vport *manager;
+	int err;
+
+	if (!mlx5_eswitch_vport_match_metadata_enabled(esw))
+		return 0;
+
+	manager = mlx5_eswitch_get_vport(esw, esw->manager_vport);
+	if (IS_ERR(manager))
+		return PTR_ERR(manager);
+
+	/* Sanity check: skip if metadata was already initialized */
+	if (manager->default_metadata)
+		return 0;
+
+	err = esw_offloads_metadata_init(esw);
+	if (err)
+		return err;
+
+	/* Manager vport don't have a rep/netdev loaded but its ingress ACL
+	 * was programmed with metadata=0 in esw_create_offloads_acl_tables() -
+	 * refresh it explicitly.
+	 */
+	mlx5_esw_acl_ingress_vport_metadata_update(esw, esw->manager_vport, 0);
+
+	return 0;
+}
+
 int
 esw_vport_create_offloads_acl_tables(struct mlx5_eswitch *esw,
 				     struct mlx5_vport *vport)
@@ -4053,7 +4087,17 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 	if (err)
 		goto err_roce;
 
-	err = esw_offloads_metadata_init(esw);
+	/* SD devices defer metadata init until SD is ready and
+	 * mlx5_sd_pf_num_get() can return the correct pf_num.
+	 */
+	if (!mlx5_get_sd(esw->dev)) {
+		err = esw_offloads_metadata_init(esw);
+	} else if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+		struct mlx5_vport *uplink =
+			mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
+
+		err = esw_offloads_vport_metadata_setup(esw, uplink);
+	}
 	if (err)
 		goto err_metadata;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
index d2ed156ed1c6..82ae8c3969fe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
@@ -988,6 +988,7 @@ static bool mlx5_sd_all_paired(struct mlx5_core_dev *primary)
 static void mlx5_sd_activate_shared_fdb(struct mlx5_core_dev *primary)
 {
 	struct mlx5_sd *sd = mlx5_get_sd(primary);
+	struct mlx5_core_dev *pos;
 	struct mlx5_lag *ldev;
 	struct lag_func *pf;
 	int err;
@@ -1016,6 +1017,21 @@ static void mlx5_sd_activate_shared_fdb(struct mlx5_core_dev *primary)
 		goto unlock;
 	}
 
+	/* Initialize vport metadata for all group devices. This is deferred
+	 * from esw_offloads_enable() because mlx5_sd_pf_num_get() requires
+	 * the SD group to be ready.
+	 */
+	mlx5_sd_for_each_dev(i, primary, pos) {
+		struct mlx5_eswitch *esw = pos->priv.eswitch;
+
+		err = mlx5_esw_offloads_init_deferred_metadata(esw);
+		if (err) {
+			sd_warn(primary, "Failed to init metadata for %s: %d\n",
+				dev_name(pos->device), err);
+			goto unlock;
+		}
+	}
+
 	err = mlx5_lag_shared_fdb_create(ldev, NULL, 0, sd->group_id);
 	if (err)
 		sd_warn(primary, "Failed to create shared FDB: %d\n", err);
-- 
2.44.0