public inbox for netdev@vger.kernel.org
 help / color / mirror / Atom feed
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: Leon Romanovsky <leon@kernel.org>, Jason Gunthorpe <jgg@ziepe.ca>,
	"Saeed Mahameed" <saeedm@nvidia.com>,
	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>,
	Maher Sanalla <msanalla@nvidia.com>,
	Simon Horman <horms@kernel.org>,
	Gerd Bayer <gbayer@linux.ibm.com>,
	Moshe Shemesh <moshe@nvidia.com>, Kees Cook <kees@kernel.org>,
	Patrisious Haddad <phaddad@nvidia.com>,
	Parav Pandit <parav@nvidia.com>,
	Carolina Jubran <cjubran@nvidia.com>,
	Cosmin Ratiu <cratiu@nvidia.com>, <linux-rdma@vger.kernel.org>,
	<linux-kernel@vger.kernel.org>, <netdev@vger.kernel.org>,
	Gal Pressman <gal@nvidia.com>,
	Dragos Tatulea <dtatulea@nvidia.com>
Subject: [PATCH net-next V2 7/7] net/mlx5: Add profile to auto-enable switchdev mode at device init
Date: Fri, 1 May 2026 07:16:33 +0300	[thread overview]
Message-ID: <20260501041633.231662-8-tariqt@nvidia.com> (raw)
In-Reply-To: <20260501041633.231662-1-tariqt@nvidia.com>

From: Mark Bloch <mbloch@nvidia.com>

Deployments that always operate in switchdev mode currently require
manual devlink configuration after driver probe, which complicates
automated provisioning.

Introduce MLX5_PROF_MASK_DEF_SWITCHDEV, a new profile mask bit, and
profile index 8. When a device is initialized or reloaded with this
profile, the driver automatically switches the e-switch to switchdev
mode by calling mlx5_devlink_eswitch_mode_set() immediately after
bringing the device online.

A no-op stub of mlx5_devlink_eswitch_mode_set() is added for builds
without CONFIG_MLX5_ESWITCH.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/eswitch.h |  6 +++
 .../net/ethernet/mellanox/mlx5/core/main.c    | 43 ++++++++++++++++++-
 include/linux/mlx5/driver.h                   |  2 +
 3 files changed, 50 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 3858690e09b4..cfb9595f9de8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -1049,6 +1049,12 @@ mlx5_esw_lag_demux_rule_create(struct mlx5_eswitch *esw, u16 vport_num,
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
+static inline int
+mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
+			      struct netlink_ext_ack *extack)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* CONFIG_MLX5_ESWITCH */
 
 #endif /* __MLX5_ESWITCH_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 74827e8ca125..4cdda15ed7f5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -86,7 +86,7 @@ MODULE_PARM_DESC(debug_mask, "debug mask: 1 = dump cmd data, 2 = dump cmd exec t
 
 static unsigned int prof_sel = MLX5_DEFAULT_PROF;
 module_param_named(prof_sel, prof_sel, uint, 0444);
-MODULE_PARM_DESC(prof_sel, "profile selector. Valid range 0 - 2");
+MODULE_PARM_DESC(prof_sel, "profile selector. Valid range 0 - 3 and 8");
 
 static u32 sw_owner_id[4];
 #define MAX_SW_VHCA_ID (BIT(__mlx5_bit_sz(cmd_hca_cap_2, sw_vhca_id)) - 1)
@@ -99,6 +99,8 @@ enum {
 
 #define LOG_MAX_SUPPORTED_QPS 0xff
 
+#define MLX5_PROF_SEL_LAST_NIC 3
+#define MLX5_PROF_SEL_FIRST_ESW 8
 static struct mlx5_profile profile[] = {
 	[0] = {
 		.mask           = 0,
@@ -120,6 +122,11 @@ static struct mlx5_profile profile[] = {
 		.log_max_qp	= LOG_MAX_SUPPORTED_QPS,
 		.num_cmd_caches = 0,
 	},
+	[8] = {
+		.mask = MLX5_PROF_MASK_DEF_SWITCHDEV | MLX5_PROF_MASK_QP_SIZE,
+		.log_max_qp = LOG_MAX_SUPPORTED_QPS,
+		.num_cmd_caches = MLX5_NUM_COMMAND_CACHES,
+	},
 };
 
 static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili,
@@ -1385,6 +1392,22 @@ static void mlx5_unload(struct mlx5_core_dev *dev)
 	mlx5_free_bfreg(dev, &dev->priv.bfreg);
 }
 
+static void mlx5_set_default_switchdev(struct mlx5_core_dev *dev)
+{
+	int err;
+
+	/* Default switchdev is best-effort; keep the device usable on
+	 * failure.
+	 */
+	err = mlx5_devlink_eswitch_mode_set(priv_to_devlink(dev),
+					    DEVLINK_ESWITCH_MODE_SWITCHDEV,
+					    NULL);
+	if (err && err != -EOPNOTSUPP)
+		mlx5_core_warn(dev,
+			       "Failed to set switchdev as default, continuing in current mode, err(%d)\n",
+			       err);
+}
+
 int mlx5_init_one_devl_locked(struct mlx5_core_dev *dev)
 {
 	bool light_probe = mlx5_dev_is_lightweight(dev);
@@ -1431,6 +1454,10 @@ int mlx5_init_one_devl_locked(struct mlx5_core_dev *dev)
 		mlx5_core_err(dev, "mlx5_hwmon_dev_register failed with error code %d\n", err);
 
 	mutex_unlock(&dev->intf_state_mutex);
+
+	if (dev->profile.mask & MLX5_PROF_MASK_DEF_SWITCHDEV)
+		mlx5_set_default_switchdev(dev);
+
 	return 0;
 
 err_register:
@@ -1532,6 +1559,10 @@ int mlx5_load_one_devl_locked(struct mlx5_core_dev *dev, bool recovery)
 		goto err_attach;
 
 	mutex_unlock(&dev->intf_state_mutex);
+
+	if (dev->profile.mask & MLX5_PROF_MASK_DEF_SWITCHDEV)
+		mlx5_set_default_switchdev(dev);
+
 	return 0;
 
 err_attach:
@@ -2314,6 +2345,16 @@ static void mlx5_core_verify_params(void)
 			MLX5_DEFAULT_PROF);
 		prof_sel = MLX5_DEFAULT_PROF;
 	}
+
+	if (prof_sel > MLX5_PROF_SEL_LAST_NIC &&
+	    prof_sel < MLX5_PROF_SEL_FIRST_ESW) {
+		pr_warn("mlx5_core: WARNING: Invalid module parameter prof_sel %d invalid range %d - %d, changing back to default (%d)\n",
+			prof_sel,
+			MLX5_PROF_SEL_LAST_NIC + 1,
+			MLX5_PROF_SEL_FIRST_ESW - 1,
+			MLX5_DEFAULT_PROF);
+		prof_sel = MLX5_DEFAULT_PROF;
+	}
 }
 
 static int __init mlx5_init(void)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 04b96c5abb57..65298c07df4d 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -705,6 +705,8 @@ struct mlx5_st;
 
 enum {
 	MLX5_PROF_MASK_QP_SIZE		= (u64)1 << 0,
+	MLX5_PROF_MASK_MR_CACHE		= (u64)1 << 1,
+	MLX5_PROF_MASK_DEF_SWITCHDEV    = (u64)1 << 2,
 };
 
 struct mlx5_profile {
-- 
2.44.0


  parent reply	other threads:[~2026-05-01  4:18 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-05-01  4:16 [PATCH net-next V2 0/7] net/mlx5: Improve representor lifecycle and allow switchdev by default Tariq Toukan
2026-05-01  4:16 ` [PATCH net-next V2 1/7] net/mlx5: Lag: refactor representor reload handling Tariq Toukan
2026-05-01  4:16 ` [PATCH net-next V2 2/7] net/mlx5: E-Switch, add representor lifecycle lock Tariq Toukan
2026-05-01  4:16 ` [PATCH net-next V2 3/7] net/mlx5: Lag, avoid LAG and representor lock cycles Tariq Toukan
2026-05-02 20:04   ` Mark Bloch
2026-05-01  4:16 ` [PATCH net-next V2 4/7] net/mlx5: E-Switch, serialize representor lifecycle Tariq Toukan
2026-05-02 20:05   ` Mark Bloch
2026-05-03  1:42   ` Jakub Kicinski
2026-05-03  8:18     ` Mark Bloch
2026-05-01  4:16 ` [PATCH net-next V2 5/7] net/mlx5: E-Switch, unwind only newly loaded representor types Tariq Toukan
2026-05-02 20:06   ` Mark Bloch
2026-05-01  4:16 ` [PATCH net-next V2 6/7] net/mlx5: E-switch, load reps via work queue after registration Tariq Toukan
2026-05-02 20:07   ` Mark Bloch
2026-05-03  1:42   ` Jakub Kicinski
2026-05-03  8:01     ` Mark Bloch
2026-05-01  4:16 ` Tariq Toukan [this message]
2026-05-02 20:08   ` [PATCH net-next V2 7/7] net/mlx5: Add profile to auto-enable switchdev mode at device init Mark Bloch
2026-05-03  1:41     ` Jakub Kicinski
2026-05-03  7:51       ` Mark Bloch
2026-05-05  1:21         ` Jakub Kicinski
2026-05-05  2:00           ` Mark Bloch
2026-05-05  2:19             ` Jakub Kicinski

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=20260501041633.231662-8-tariqt@nvidia.com \
    --to=tariqt@nvidia.com \
    --cc=andrew+netdev@lunn.ch \
    --cc=cjubran@nvidia.com \
    --cc=cratiu@nvidia.com \
    --cc=davem@davemloft.net \
    --cc=dtatulea@nvidia.com \
    --cc=edumazet@google.com \
    --cc=edwards@nvidia.com \
    --cc=gal@nvidia.com \
    --cc=gbayer@linux.ibm.com \
    --cc=horms@kernel.org \
    --cc=jgg@ziepe.ca \
    --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