All of lore.kernel.org
 help / color / mirror / Atom feed
From: Saeed Mahameed <saeed@kernel.org>
To: "David S. Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	Eric Dumazet <edumazet@google.com>
Cc: Saeed Mahameed <saeedm@nvidia.com>,
	netdev@vger.kernel.org, Tariq Toukan <tariqt@nvidia.com>,
	Roi Dayan <roid@nvidia.com>, Maor Dickman <maord@nvidia.com>
Subject: [net-next V2 04/15] net/mlx5: Lag, set different uplink vport metadata in multiport eswitch mode
Date: Tue, 14 Feb 2023 14:12:28 -0800	[thread overview]
Message-ID: <20230214221239.159033-5-saeed@kernel.org> (raw)
In-Reply-To: <20230214221239.159033-1-saeed@kernel.org>

From: Roi Dayan <roid@nvidia.com>

In a follow-up commit multiport eswitch mode will use a shared fdb.
In shared fdb there is a single eswitch fdb and traffic could come from any
port. to distinguish between the ports set a different metadata per uplink port.

Signed-off-by: Roi Dayan <roid@nvidia.com>
Reviewed-by: Maor Dickman <maord@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_rep.c  | 35 ++++++++++
 .../net/ethernet/mellanox/mlx5/core/en_rep.h  |  2 +
 .../ethernet/mellanox/mlx5/core/lag/mpesw.c   | 67 ++++++++++++++++++-
 .../ethernet/mellanox/mlx5/core/lag/mpesw.h   |  1 +
 include/linux/mlx5/driver.h                   |  1 +
 5 files changed, 105 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 8d29310c7e48..9b9203443085 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1007,8 +1007,23 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
 	priv->rx_res = NULL;
 }
 
+static void mlx5e_rep_mpesw_work(struct work_struct *work)
+{
+	struct mlx5_rep_uplink_priv *uplink_priv =
+		container_of(work, struct mlx5_rep_uplink_priv,
+			     mpesw_work);
+	struct mlx5e_rep_priv *rpriv =
+		container_of(uplink_priv, struct mlx5e_rep_priv,
+			     uplink_priv);
+	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
+
+	rep_vport_rx_rule_destroy(priv);
+	mlx5e_create_rep_vport_rx_rule(priv);
+}
+
 static int mlx5e_init_ul_rep_rx(struct mlx5e_priv *priv)
 {
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	int err;
 
 	mlx5e_create_q_counters(priv);
@@ -1018,12 +1033,17 @@ static int mlx5e_init_ul_rep_rx(struct mlx5e_priv *priv)
 
 	mlx5e_tc_int_port_init_rep_rx(priv);
 
+	INIT_WORK(&rpriv->uplink_priv.mpesw_work, mlx5e_rep_mpesw_work);
+
 out:
 	return err;
 }
 
 static void mlx5e_cleanup_ul_rep_rx(struct mlx5e_priv *priv)
 {
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+
+	cancel_work_sync(&rpriv->uplink_priv.mpesw_work);
 	mlx5e_tc_int_port_cleanup_rep_rx(priv);
 	mlx5e_cleanup_rep_rx(priv);
 	mlx5e_destroy_q_counters(priv);
@@ -1132,6 +1152,19 @@ static int mlx5e_update_rep_rx(struct mlx5e_priv *priv)
 	return 0;
 }
 
+static int mlx5e_rep_event_mpesw(struct mlx5e_priv *priv)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
+
+	if (rep->vport != MLX5_VPORT_UPLINK)
+		return NOTIFY_DONE;
+
+	queue_work(priv->wq, &rpriv->uplink_priv.mpesw_work);
+
+	return NOTIFY_OK;
+}
+
 static int uplink_rep_async_event(struct notifier_block *nb, unsigned long event, void *data)
 {
 	struct mlx5e_priv *priv = container_of(nb, struct mlx5e_priv, events_nb);
@@ -1153,6 +1186,8 @@ static int uplink_rep_async_event(struct notifier_block *nb, unsigned long event
 
 	if (event == MLX5_DEV_EVENT_PORT_AFFINITY)
 		return mlx5e_rep_tc_event_port_affinity(priv);
+	else if (event == MLX5_DEV_EVENT_MULTIPORT_ESW)
+		return mlx5e_rep_event_mpesw(priv);
 
 	return NOTIFY_DONE;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 0abe3313c673..dcfad0bf0f45 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -103,6 +103,8 @@ struct mlx5_rep_uplink_priv {
 
 	/* tc action stats */
 	struct mlx5e_tc_act_stats_handle *action_stats_handle;
+
+	struct work_struct mpesw_work;
 };
 
 struct mlx5e_rep_priv {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
index dd3cb9aa06fd..2f7f2af312d7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
@@ -5,8 +5,66 @@
 #include <net/nexthop.h>
 #include "lag/lag.h"
 #include "eswitch.h"
+#include "esw/acl/ofld.h"
 #include "lib/mlx5.h"
 
+static void mlx5_mpesw_metadata_cleanup(struct mlx5_lag *ldev)
+{
+	struct mlx5_core_dev *dev;
+	struct mlx5_eswitch *esw;
+	u32 pf_metadata;
+	int i;
+
+	for (i = 0; i < ldev->ports; i++) {
+		dev = ldev->pf[i].dev;
+		esw = dev->priv.eswitch;
+		pf_metadata = ldev->lag_mpesw.pf_metadata[i];
+		if (!pf_metadata)
+			continue;
+		mlx5_esw_acl_ingress_vport_metadata_update(esw, MLX5_VPORT_UPLINK, 0);
+		mlx5_notifier_call_chain(dev->priv.events, MLX5_DEV_EVENT_MULTIPORT_ESW,
+					 (void *)0);
+		mlx5_esw_match_metadata_free(esw, pf_metadata);
+		ldev->lag_mpesw.pf_metadata[i] = 0;
+	}
+}
+
+static int mlx5_mpesw_metadata_set(struct mlx5_lag *ldev)
+{
+	struct mlx5_core_dev *dev;
+	struct mlx5_eswitch *esw;
+	u32 pf_metadata;
+	int i, err;
+
+	for (i = 0; i < ldev->ports; i++) {
+		dev = ldev->pf[i].dev;
+		esw = dev->priv.eswitch;
+		pf_metadata = mlx5_esw_match_metadata_alloc(esw);
+		if (!pf_metadata) {
+			err = -ENOSPC;
+			goto err_metadata;
+		}
+
+		ldev->lag_mpesw.pf_metadata[i] = pf_metadata;
+		err = mlx5_esw_acl_ingress_vport_metadata_update(esw, MLX5_VPORT_UPLINK,
+								 pf_metadata);
+		if (err)
+			goto err_metadata;
+	}
+
+	for (i = 0; i < ldev->ports; i++) {
+		dev = ldev->pf[i].dev;
+		mlx5_notifier_call_chain(dev->priv.events, MLX5_DEV_EVENT_MULTIPORT_ESW,
+					 (void *)0);
+	}
+
+	return 0;
+
+err_metadata:
+	mlx5_mpesw_metadata_cleanup(ldev);
+	return err;
+}
+
 static int enable_mpesw(struct mlx5_lag *ldev)
 {
 	struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev;
@@ -21,6 +79,10 @@ static int enable_mpesw(struct mlx5_lag *ldev)
 	    !mlx5_lag_check_prereq(ldev))
 		return -EOPNOTSUPP;
 
+	err = mlx5_mpesw_metadata_set(ldev);
+	if (err)
+		return err;
+
 	err = mlx5_activate_lag(ldev, NULL, MLX5_LAG_MODE_MPESW, false);
 	if (err) {
 		mlx5_core_warn(dev, "Failed to create LAG in MPESW mode (%d)\n", err);
@@ -30,13 +92,16 @@ static int enable_mpesw(struct mlx5_lag *ldev)
 	return 0;
 
 out_err:
+	mlx5_mpesw_metadata_cleanup(ldev);
 	return err;
 }
 
 static void disable_mpesw(struct mlx5_lag *ldev)
 {
-	if (ldev->mode == MLX5_LAG_MODE_MPESW)
+	if (ldev->mode == MLX5_LAG_MODE_MPESW) {
+		mlx5_mpesw_metadata_cleanup(ldev);
 		mlx5_disable_lag(ldev);
+	}
 }
 
 static void mlx5_mpesw_work(struct work_struct *work)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h
index d857ea988bf2..02520f27a033 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h
@@ -9,6 +9,7 @@
 
 struct lag_mpesw {
 	struct work_struct mpesw_work;
+	u32 pf_metadata[MLX5_MAX_PORTS];
 };
 
 enum mpesw_op {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index ecd3b5448fe9..a4bb5842a948 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -217,6 +217,7 @@ struct mlx5_rsc_debug {
 enum mlx5_dev_event {
 	MLX5_DEV_EVENT_SYS_ERROR = 128, /* 0 - 127 are FW events */
 	MLX5_DEV_EVENT_PORT_AFFINITY = 129,
+	MLX5_DEV_EVENT_MULTIPORT_ESW = 130,
 };
 
 enum mlx5_port_status {
-- 
2.39.1


  parent reply	other threads:[~2023-02-14 22:14 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-02-14 22:12 [pull request][net-next V2 00/15] mlx5 updates 2023-02-10 Saeed Mahameed
2023-02-14 22:12 ` [net-next V2 01/15] net/mlx5: Lag, Control MultiPort E-Switch single FDB mode Saeed Mahameed
2023-02-15  7:53   ` Jiri Pirko
2023-02-16  3:30   ` patchwork-bot+netdevbpf
2023-02-14 22:12 ` [net-next V2 02/15] net/mlx5e: TC, Add peer flow in mpesw mode Saeed Mahameed
2023-02-14 22:12 ` [net-next V2 03/15] net/mlx5: E-Switch, rename bond update function to be reused Saeed Mahameed
2023-02-14 22:12 ` Saeed Mahameed [this message]
2023-02-14 22:12 ` [net-next V2 05/15] net/mlx5: Lag, Add single RDMA device in multiport mode Saeed Mahameed
2023-02-14 22:12 ` [net-next V2 06/15] net/mlx5e: Use a simpler comparison for uplink rep Saeed Mahameed
2023-02-14 22:12 ` [net-next V2 07/15] net/mlx5e: TC, Remove redundant parse_attr argument Saeed Mahameed
2023-02-14 22:12 ` [net-next V2 08/15] net/mlx5: Remove outdated comment Saeed Mahameed
2023-02-14 22:12 ` [net-next V2 09/15] net/mlx5e: Pass mdev to mlx5e_devlink_port_register() Saeed Mahameed
2023-02-14 22:12 ` [net-next V2 10/15] net/mlx5e: Replace usage of mlx5e_devlink_get_dl_port() by netdev->devlink_port Saeed Mahameed
2023-02-14 22:12 ` [net-next V2 11/15] net/mlx5e: Move dl_port to struct mlx5e_dev Saeed Mahameed
2023-02-14 22:12 ` [net-next V2 12/15] net/mlx5e: Move devlink port registration to be done before netdev alloc Saeed Mahameed
2023-02-14 22:12 ` [net-next V2 13/15] net/mlx5e: Create auxdev devlink instance in the same ns as parent devlink Saeed Mahameed
2023-02-14 22:12 ` [net-next V2 14/15] net/mlx5: Remove "recovery" arg from mlx5_load_one() function Saeed Mahameed
2023-02-14 22:12 ` [net-next V2 15/15] net/mlx5: Suspend auxiliary devices only in case of PCI device suspend Saeed Mahameed

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=20230214221239.159033-5-saeed@kernel.org \
    --to=saeed@kernel.org \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=kuba@kernel.org \
    --cc=maord@nvidia.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=roid@nvidia.com \
    --cc=saeedm@nvidia.com \
    --cc=tariqt@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.