All of lore.kernel.org
 help / color / mirror / Atom feed
From: Tariq Toukan <tariqt@nvidia.com>
To: Andrew Lunn <andrew+netdev@lunn.ch>,
	"David S. Miller" <davem@davemloft.net>,
	Eric Dumazet <edumazet@kernel.org>,
	Jakub Kicinski <kuba@kernel.org>, <netdev@vger.kernel.org>,
	Paolo Abeni <pabeni@redhat.com>
Cc: Carolina Jubran <cjubran@nvidia.com>,
	Cosmin Ratiu <cratiu@nvidia.com>, Gal Pressman <gal@nvidia.com>,
	Leon Romanovsky <leon@kernel.org>,
	open list <linux-kernel@vger.kernel.org>,
	<linux-rdma@vger.kernel.org>, Mark Bloch <mbloch@nvidia.com>,
	Moshe Shemesh <moshe@nvidia.com>,
	Or Har-Toov <ohartoov@nvidia.com>,
	Patrisious Haddad <phaddad@nvidia.com>,
	Saeed Mahameed <saeedm@nvidia.com>, Shay Drory <shayd@nvidia.com>,
	Tariq Toukan <tariqt@nvidia.com>, Uri Dar <udar@nvidia.com>
Subject: [PATCH net-next V2 08/10] net/mlx5: LAG: replace fixed MLX5_MAX_PORTS arrays with dynamic allocation
Date: Mon, 16 Nov 2026 12:30:08 +0200	[thread overview]
Message-ID: <20261116103010.1129666-9-tariqt@nvidia.com> (raw)
In-Reply-To: <20261116103010.1129666-1-tariqt@nvidia.com>

From: Shay Drory <shayd@nvidia.com>

Converts two fixed-size arrays sized to MLX5_MAX_PORTS into
dynamically allocated pointers:

- lag_mpesw.pf_metadata in mpesw.c/mpesw.h, sized by ldev->max_fns
- mdev array in mlx5_lag_query_cong_counters(), sized by ldev->ports

The cong-counters array is sized by ldev->ports, which is fixed at ldev
allocation, rather than by the LAG mode, so a mode change between the
allocation and filling the array cannot overflow it. The query loop is
bounded by the number of entries actually filled. A virt LAG is not
aggregated and queries only the given device, as its members are not
LAG ports.

Thus, removes the hard dependency on MLX5_MAX_PORTS.

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c | 15 +++++++--------
 .../net/ethernet/mellanox/mlx5/core/lag/mpesw.c   | 12 ++++++++++++
 .../net/ethernet/mellanox/mlx5/core/lag/mpesw.h   |  2 +-
 3 files changed, 20 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 5c9f200c9637..a7b12353b722 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -2916,7 +2916,9 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 	if (!out)
 		return -ENOMEM;
 
-	mdev = kvzalloc(sizeof(mdev[0]) * MLX5_MAX_PORTS, GFP_KERNEL);
+	ldev = mlx5_lag_dev(dev);
+	num_ports = ldev ? max_t(int, ldev->ports, 1) : 1;
+	mdev = kcalloc(num_ports, sizeof(mdev[0]), GFP_KERNEL);
 	if (!mdev) {
 		ret = -ENOMEM;
 		goto free_out;
@@ -2925,20 +2927,17 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 	memset(values, 0, sizeof(*values) * num_counters);
 
 	spin_lock_irqsave(&lag_lock, flags);
-	ldev = mlx5_lag_dev(dev);
-	if (ldev && __mlx5_lag_is_active(ldev)) {
-		num_ports = ldev->ports;
+	if (ldev && __mlx5_lag_is_active(ldev) && !ldev->virt_lag) {
 		mlx5_ldev_for_each(i, 0, ldev) {
 			fn = mlx5_lag_fn(ldev, i);
 			mdev[idx++] = fn->dev;
 		}
 	} else {
-		num_ports = 1;
-		mdev[MLX5_LAG_P1] = dev;
+		mdev[idx++] = dev;
 	}
 	spin_unlock_irqrestore(&lag_lock, flags);
 
-	for (i = 0; i < num_ports; ++i) {
+	for (i = 0; i < idx; ++i) {
 		u32 in[MLX5_ST_SZ_DW(query_cong_statistics_in)] = {};
 
 		MLX5_SET(query_cong_statistics_in, in, opcode,
@@ -2953,7 +2952,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 	}
 
 free_mdev:
-	kvfree(mdev);
+	kfree(mdev);
 free_out:
 	kvfree(out);
 	return ret;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
index 49602f830615..8a867a04916a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
@@ -15,6 +15,9 @@ static void mlx5_mpesw_metadata_cleanup(struct mlx5_lag *ldev)
 	u32 pf_metadata;
 	int i;
 
+	if (!ldev->lag_mpesw.pf_metadata)
+		return;
+
 	mlx5_lag_for_each(i, 0, ldev, MLX5_LAG_FILTER_ALL) {
 		dev = mlx5_lag_fn(ldev, i)->dev;
 		esw = dev->priv.eswitch;
@@ -27,6 +30,9 @@ static void mlx5_mpesw_metadata_cleanup(struct mlx5_lag *ldev)
 		mlx5_esw_match_metadata_free(esw, pf_metadata);
 		ldev->lag_mpesw.pf_metadata[i] = 0;
 	}
+
+	kfree(ldev->lag_mpesw.pf_metadata);
+	ldev->lag_mpesw.pf_metadata = NULL;
 }
 
 static int mlx5_mpesw_metadata_set(struct mlx5_lag *ldev)
@@ -36,6 +42,12 @@ static int mlx5_mpesw_metadata_set(struct mlx5_lag *ldev)
 	u32 pf_metadata;
 	int i, err;
 
+	ldev->lag_mpesw.pf_metadata =
+		kcalloc(ldev->max_fns, sizeof(*ldev->lag_mpesw.pf_metadata),
+			GFP_KERNEL);
+	if (!ldev->lag_mpesw.pf_metadata)
+		return -ENOMEM;
+
 	mlx5_lag_for_each(i, 0, ldev, MLX5_LAG_FILTER_ALL) {
 		dev = mlx5_lag_fn(ldev, i)->dev;
 		esw = dev->priv.eswitch;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h
index 5099723ba0f7..6296e3edd38c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h
@@ -9,7 +9,7 @@
 
 struct lag_mpesw {
 	struct work_struct mpesw_work;
-	u32 pf_metadata[MLX5_MAX_PORTS];
+	u32 *pf_metadata;
 };
 
 enum mpesw_op {
-- 
2.44.0


  parent reply	other threads:[~2026-11-16 10:31 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-16 10:30 [PATCH net-next V2 00/10] net/mlx5: LAG, preparations for LAG over VFs/SFs Tariq Toukan
2026-11-16 10:30 ` [PATCH net-next V2 01/10] net/mlx5: Distinguish VFs/SFs in the SW system image GUID for LAG grouping Tariq Toukan
2026-11-17 10:36   ` sashiko-bot
2026-11-16 10:30 ` [PATCH net-next V2 02/10] net/mlx5: LAG, select the MPESW master from the live member snapshot Tariq Toukan
2026-11-17 10:36   ` sashiko-bot
2026-11-16 10:30 ` [PATCH net-next V2 03/10] net/mlx5: LAG, skip phys LAG prerequisites for a virt LAG Tariq Toukan
2026-11-17 10:36   ` sashiko-bot
2026-11-16 10:30 ` [PATCH net-next V2 04/10] net/mlx5: LAG, treat virt LAG as a software managed LAG Tariq Toukan
2026-11-17 10:36   ` sashiko-bot
2026-11-16 10:30 ` [PATCH net-next V2 05/10] net/mlx5: LAG, decouple iteration end-of-walk from MLX5_MAX_PORTS Tariq Toukan
2026-11-17 10:36   ` sashiko-bot
2026-11-16 10:30 ` [PATCH net-next V2 06/10] net/mlx5: LAG, rename PF naming to fn Tariq Toukan
2026-11-17 10:36   ` sashiko-bot
2026-11-16 10:30 ` [PATCH net-next V2 07/10] net/mlx5: LAG, resolve affinity indices only in queue-affinity mode Tariq Toukan
2026-11-17 10:36   ` sashiko-bot
2026-11-16 10:30 ` Tariq Toukan [this message]
2026-11-17 10:36   ` [PATCH net-next V2 08/10] net/mlx5: LAG: replace fixed MLX5_MAX_PORTS arrays with dynamic allocation sashiko-bot
2026-11-16 10:30 ` [PATCH net-next V2 09/10] net/mlx5: LAG, drop MLX5_MAX_PORTS scratch array from device rescan Tariq Toukan
2026-11-17 10:36   ` sashiko-bot
2026-11-16 10:30 ` [PATCH net-next V2 10/10] net/mlx5: LAG, do not add a device to an already-active virt LAG Tariq Toukan
2026-11-17 10:36   ` sashiko-bot

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=20261116103010.1129666-9-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=edumazet@kernel.org \
    --cc=gal@nvidia.com \
    --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=netdev@vger.kernel.org \
    --cc=ohartoov@nvidia.com \
    --cc=pabeni@redhat.com \
    --cc=phaddad@nvidia.com \
    --cc=saeedm@nvidia.com \
    --cc=shayd@nvidia.com \
    --cc=udar@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.