From: Tariq Toukan <tariqt@nvidia.com>
To: Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
Andrew Lunn <andrew+netdev@lunn.ch>,
"David S. Miller" <davem@davemloft.net>
Cc: Saeed Mahameed <saeedm@nvidia.com>,
Leon Romanovsky <leon@kernel.org>,
Tariq Toukan <tariqt@nvidia.com>, Mark Bloch <mbloch@nvidia.com>,
Shay Drory <shayd@nvidia.com>, Or Har-Toov <ohartoov@nvidia.com>,
Edward Srouji <edwards@nvidia.com>,
Simon Horman <horms@kernel.org>,
Maher Sanalla <msanalla@nvidia.com>,
Parav Pandit <parav@nvidia.com>, Kees Cook <kees@kernel.org>,
Moshe Shemesh <moshe@nvidia.com>,
Patrisious Haddad <phaddad@nvidia.com>, <netdev@vger.kernel.org>,
<linux-rdma@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
Gal Pressman <gal@nvidia.com>
Subject: [PATCH net-next 14/15] net/mlx5: SD, defer vport metadata init until SD is ready
Date: Thu, 4 Jun 2026 14:44:54 +0300 [thread overview]
Message-ID: <20260604114455.434711-15-tariqt@nvidia.com> (raw)
In-Reply-To: <20260604114455.434711-1-tariqt@nvidia.com>
From: Shay Drory <shayd@nvidia.com>
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@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
.../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
next prev parent reply other threads:[~2026-06-04 11:47 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-06-04 11:44 [PATCH net-next 00/15] net/mlx5: Add switchdev mode support for Socket Direct single netdev, part 2/2 Tariq Toukan
2026-06-04 11:44 ` [PATCH net-next 01/15] net/mlx5: E-Switch, skip uplink IB rep load for SD secondary devices Tariq Toukan
2026-06-04 11:44 ` [PATCH net-next 02/15] net/mlx5: devcom, expose locked variant of send_event Tariq Toukan
2026-06-04 11:44 ` [PATCH net-next 03/15] net/mlx5: devcom, add DEVCOM_CANT_FAIL for non-rollback events Tariq Toukan
2026-06-04 11:44 ` [PATCH net-next 04/15] net/mlx5: SD, make primary/secondary role determination more robust Tariq Toukan
2026-06-04 11:44 ` [PATCH net-next 05/15] net/mlx5: SD, add L2 table silent mode query support Tariq Toukan
2026-06-04 11:44 ` [PATCH net-next 06/15] net/mlx5: SD, expend vport metadata for SD secondary devices Tariq Toukan
2026-06-04 11:44 ` [PATCH net-next 07/15] net/mlx5: SD, support switchdev mode transition with shared FDB Tariq Toukan
2026-06-04 11:44 ` [PATCH net-next 08/15] net/mlx5: E-Switch, notify SD on eswitch disable Tariq Toukan
2026-06-04 11:44 ` [PATCH net-next 09/15] net/mlx5: LAG, store demux resources per master lag_func Tariq Toukan
2026-06-04 11:44 ` [PATCH net-next 10/15] net/mlx5: LAG, disable both regular and SD LAG on lag_disable_change Tariq Toukan
2026-06-04 11:44 ` [PATCH net-next 11/15] net/mlx5: LAG, introduce software vport LAG implementation Tariq Toukan
2026-06-04 11:44 ` [PATCH net-next 12/15] net/mlx5: LAG, add MPESW over SD LAG support Tariq Toukan
2026-06-04 11:44 ` [PATCH net-next 13/15] net/mlx5: E-Switch, defer rep load while SD LAG is not active Tariq Toukan
2026-06-04 11:44 ` Tariq Toukan [this message]
2026-06-04 11:44 ` [PATCH net-next 15/15] net/mlx5: SD, enable SD over ECPF and allow switchdev transition Tariq Toukan
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260604114455.434711-15-tariqt@nvidia.com \
--to=tariqt@nvidia.com \
--cc=andrew+netdev@lunn.ch \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=edwards@nvidia.com \
--cc=gal@nvidia.com \
--cc=horms@kernel.org \
--cc=kees@kernel.org \
--cc=kuba@kernel.org \
--cc=leon@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=mbloch@nvidia.com \
--cc=moshe@nvidia.com \
--cc=msanalla@nvidia.com \
--cc=netdev@vger.kernel.org \
--cc=ohartoov@nvidia.com \
--cc=pabeni@redhat.com \
--cc=parav@nvidia.com \
--cc=phaddad@nvidia.com \
--cc=saeedm@nvidia.com \
--cc=shayd@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox