From: Tariq Toukan <tariqt@nvidia.com>
To: Andrew Lunn <andrew+netdev@lunn.ch>,
"David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, <netdev@vger.kernel.org>,
Paolo Abeni <pabeni@redhat.com>
Cc: Edward Srouji <edwards@nvidia.com>, Gal Pressman <gal@nvidia.com>,
"Jason Gunthorpe" <jgg@ziepe.ca>,
Leon Romanovsky <leon@kernel.org>,
open list <linux-kernel@vger.kernel.org>,
<linux-rdma@vger.kernel.org>, Maher Sanalla <msanalla@nvidia.com>,
Mark Bloch <mbloch@nvidia.com>, Or Har-Toov <ohartoov@nvidia.com>,
Saeed Mahameed <saeedm@nvidia.com>, Shay Drori <shayd@nvidia.com>,
Tariq Toukan <tariqt@nvidia.com>
Subject: [PATCH net 5/5] {RDMA,net}/mlx5: notify RoCE LAG speed change via driver event
Date: Thu, 10 Sep 2026 13:24:32 +0300 [thread overview]
Message-ID: <20260910102432.3845360-6-tariqt@nvidia.com> (raw)
In-Reply-To: <20260910102432.3845360-1-tariqt@nvidia.com>
From: Or Har-Toov <ohartoov@nvidia.com>
In RoCE LAG we don't modify any max_tx_speed, so no
IB_EVENT_DEVICE_SPEED_CHANGE is ever fired.
Raise IB_EVENT_DEVICE_SPEED_CHANGE from the LAG layer, in
mlx5_lag_update_agg_speed(), right after the cached aggregate is
updated. That cache is where the IB layer now takes the effective speed
from, so a consumer that queries after receiving the event is
guaranteed to read the new value.
Fixes: c6df9a65cbb0 ("net/mlx5: Skip disabled vports when setting max TX speed")
Signed-off-by: Or Har-Toov <ohartoov@nvidia.com>
Reviewed-by: Shay Drori <shayd@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
drivers/infiniband/hw/mlx5/main.c | 10 ++++++++++
.../net/ethernet/mellanox/mlx5/core/lag/lag.c | 20 +++++++++++++++++++
.../net/ethernet/mellanox/mlx5/core/lag/lag.h | 1 +
include/linux/mlx5/device.h | 1 +
4 files changed, 32 insertions(+)
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 6ab7f945e712..bd54af47eda7 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3693,6 +3693,16 @@ static int lag_event(struct notifier_block *nb, unsigned long event, void *data)
rdma_roce_rescan_port(ibdev, portnum + 1);
}
break;
+ case MLX5_DRIVER_EVENT_LAG_SPEED_CHANGE: {
+ struct ib_event speed_event = {};
+
+ if (!dev->ib_active)
+ break;
+ speed_event.device = ibdev;
+ speed_event.event = IB_EVENT_DEVICE_SPEED_CHANGE;
+ ib_dispatch_event(&speed_event);
+ break;
+ }
default:
return NOTIFY_DONE;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index fd91becd6848..5e70ca3b09ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -1503,8 +1503,24 @@ static int mlx5_lag_get_devices_max_speed(struct mlx5_lag *ldev, u32 *max_speed)
return 0;
}
+void mlx5_lag_notify_speed_change(struct mlx5_lag *ldev)
+{
+ struct lag_func *pf;
+ int idx;
+
+ idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
+ if (idx < 0)
+ return;
+ pf = mlx5_lag_pf(ldev, idx);
+ if (!pf)
+ return;
+ blocking_notifier_call_chain(&pf->dev->priv.lag_nh,
+ MLX5_DRIVER_EVENT_LAG_SPEED_CHANGE, NULL);
+}
+
void mlx5_lag_update_agg_speed(struct mlx5_lag *ldev)
{
+ u32 old_speed;
u32 speed;
lockdep_assert_held(&ldev->lock);
@@ -1516,7 +1532,11 @@ void mlx5_lag_update_agg_speed(struct mlx5_lag *ldev)
if (!speed && mlx5_lag_get_devices_max_speed(ldev, &speed))
return;
+ old_speed = ldev->agg_speed_mbps;
ldev->agg_speed_mbps = speed;
+
+ if (mlx5_lag_is_roce_lag(ldev) && speed != old_speed)
+ mlx5_lag_notify_speed_change(ldev);
}
void mlx5_lag_reset_agg_speed(struct mlx5_lag *ldev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
index 744fbf9a0078..2b15a0b70fdf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
@@ -259,6 +259,7 @@ void mlx5_lag_rescan_dev_locked(struct mlx5_lag *ldev,
void mlx5_lag_add_devices_filter(struct mlx5_lag *ldev, u32 filter);
struct mlx5_devcom_comp_dev *mlx5_lag_get_devcom_comp(struct mlx5_lag *ldev);
+void mlx5_lag_notify_speed_change(struct mlx5_lag *ldev);
void mlx5_lag_update_agg_speed(struct mlx5_lag *ldev);
void mlx5_lag_reset_agg_speed(struct mlx5_lag *ldev);
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 8cb321a9fb3d..1ec2331c24ee 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -374,6 +374,7 @@ enum mlx5_driver_event {
MLX5_DRIVER_EVENT_AFFILIATION_DONE,
MLX5_DRIVER_EVENT_AFFILIATION_REMOVED,
MLX5_DRIVER_EVENT_ACTIVE_BACKUP_LAG_CHANGE_LOWERSTATE,
+ MLX5_DRIVER_EVENT_LAG_SPEED_CHANGE,
};
enum {
--
2.44.0
prev parent reply other threads:[~2026-09-10 10:25 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-10 10:24 [PATCH net 0/5] net/mlx5: fixes for LAG max_tx_speed update flow Tariq Toukan
2026-09-10 10:24 ` [PATCH net 1/5] net/mlx5: Lag, split aggregate speed into oper and max helpers Tariq Toukan
2026-09-10 10:24 ` [PATCH net 2/5] net/mlx5: Lag, reset vport speed on teardown Tariq Toukan
2026-09-10 10:24 ` [PATCH net 3/5] {RDMA,net}/mlx5: cache and use TX-enabled aggregate speed for vports Tariq Toukan
2026-09-10 10:24 ` [PATCH net 4/5] net/mlx5: Lag, limit aggregated TX speed by PCIe bandwidth Tariq Toukan
2026-09-10 10:24 ` Tariq Toukan [this message]
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=20260910102432.3845360-6-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=jgg@ziepe.ca \
--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=msanalla@nvidia.com \
--cc=netdev@vger.kernel.org \
--cc=ohartoov@nvidia.com \
--cc=pabeni@redhat.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