Thread (18 messages) 18 messages, 2 authors, 2026-06-12

[PATCH net-next V2 12/15] net/mlx5: LAG, add MPESW over SD LAG support

flat view
STALE134d SUPERSEDED: 1 (1M)

From: Tariq Toukan <tariqt@nvidia.com>
Date: 2026-06-08 13:58:04
Also in: linux-rdma, lkml
Subsystem: mellanox mlx5 core vpi driver, networking drivers, the rest · Maintainers: Saeed Mahameed, Leon Romanovsky, Tariq Toukan, Mark Bloch, Andrew Lunn, "David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, Linus Torvalds

Revision v2 of 3 in this series; 1 review trailer (1 from subsystem maintainers).

Revisions (3)
  1. v1 [diff vs current]
  2. v2 current
  3. v3 [diff vs current]
From: Shay Drory <redacted>

Enable MPESW LAG creation over SD LAG members, forming a composite LAG
hierarchy. This allows bonding multiple SD groups together under a
single MPESW configuration with shared FDB.

When enabling composite MPESW, the individual SD LAG shared FDB
configurations are temporarily torn down and recreated when the
composite LAG is disabled.

Signed-off-by: Shay Drory <redacted>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/lag/lag.c |  6 ++
 .../net/ethernet/mellanox/mlx5/core/lag/lag.h |  8 ++
 .../ethernet/mellanox/mlx5/core/lag/mpesw.c   | 95 +++++++++++++++++--
 .../ethernet/mellanox/mlx5/core/lag/mpesw.h   |  4 +
 4 files changed, 105 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 06e1a61d1f58..424478e649ef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -2545,6 +2545,7 @@ void mlx5_lag_disable_change(struct mlx5_core_dev *dev)
 	struct mlx5_core_dev *primary = dev;
 	struct mlx5_lag *ldev;
 	struct lag_func *pf;
+	bool mpesw;
 	int i;
 
 	ldev = mlx5_lag_dev(dev);
@@ -2557,6 +2558,9 @@ void mlx5_lag_disable_change(struct mlx5_core_dev *dev)
 		mlx5_devcom_comp_unlock(sd_devcom);
 	}
 	mlx5_devcom_comp_lock(primary->priv.hca_devcom_comp);
+	mpesw = ldev->mode == MLX5_LAG_MODE_MPESW;
+	if (mpesw)
+		mlx5_mpesw_sd_devcoms_lock(ldev);
 	mutex_lock(&ldev->lock);
 
 	ldev->mode_changes_in_progress++;
@@ -2568,6 +2572,8 @@ void mlx5_lag_disable_change(struct mlx5_core_dev *dev)
 	}
 
 	mutex_unlock(&ldev->lock);
+	if (mpesw)
+		mlx5_mpesw_sd_devcoms_unlock(ldev);
 	mlx5_devcom_comp_unlock(primary->priv.hca_devcom_comp);
 
 	if (!sd_devcom)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
index 57e6f82713b0..8481ce55c10a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
@@ -157,6 +157,14 @@ __mlx5_lag_is_sd(struct mlx5_lag *ldev, struct mlx5_core_dev *dev)
 	return pf && pf->group_id != 0;
 }
 
+static inline bool
+__mlx5_lag_dev_is_port(struct mlx5_lag *ldev, struct mlx5_core_dev *dev)
+{
+	struct lag_func *pf = mlx5_lag_pf_by_dev(ldev, dev);
+
+	return pf && xa_get_mark(&ldev->pfs, pf->idx, MLX5_LAG_XA_MARK_PORT);
+}
+
 static inline bool
 __mlx5_lag_is_active(struct mlx5_lag *ldev)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
index 2cb44084e239..50bfb450c71e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
@@ -15,7 +15,7 @@ static void mlx5_mpesw_metadata_cleanup(struct mlx5_lag *ldev)
 	u32 pf_metadata;
 	int i;
 
-	mlx5_ldev_for_each(i, 0, ldev) {
+	mlx5_lag_for_each(i, 0, ldev, MLX5_LAG_FILTER_ALL) {
 		dev = mlx5_lag_pf(ldev, i)->dev;
 		esw = dev->priv.eswitch;
 		pf_metadata = ldev->lag_mpesw.pf_metadata[i];
@@ -36,7 +36,7 @@ static int mlx5_mpesw_metadata_set(struct mlx5_lag *ldev)
 	u32 pf_metadata;
 	int i, err;
 
-	mlx5_ldev_for_each(i, 0, ldev) {
+	mlx5_lag_for_each(i, 0, ldev, MLX5_LAG_FILTER_ALL) {
 		dev = mlx5_lag_pf(ldev, i)->dev;
 		esw = dev->priv.eswitch;
 		pf_metadata = mlx5_esw_match_metadata_alloc(esw);
@@ -52,7 +52,7 @@ static int mlx5_mpesw_metadata_set(struct mlx5_lag *ldev)
 			goto err_metadata;
 	}
 
-	mlx5_ldev_for_each(i, 0, ldev) {
+	mlx5_lag_for_each(i, 0, ldev, MLX5_LAG_FILTER_ALL) {
 		dev = mlx5_lag_pf(ldev, i)->dev;
 		mlx5_notifier_call_chain(dev->priv.events, MLX5_DEV_EVENT_MULTIPORT_ESW,
 					 (void *)0);
@@ -65,6 +65,48 @@ static int mlx5_mpesw_metadata_set(struct mlx5_lag *ldev)
 	return err;
 }
 
+static void mlx5_mpesw_restore_sd_fdb(struct mlx5_lag *ldev)
+{
+	struct lag_func *pf;
+	int err, i;
+
+	mlx5_ldev_for_each(i, 0, ldev) {
+		pf = mlx5_lag_pf(ldev, i);
+		err = mlx5_lag_shared_fdb_create(ldev, NULL, 0, pf->group_id);
+		if (err)
+			mlx5_core_warn(pf->dev,
+				       "Failed to restore SD shared FDB (%d)\n",
+				       err);
+	}
+}
+
+static int mlx5_mpesw_teardown_sd_fdb(struct mlx5_lag *ldev)
+{
+	struct lag_func *pf;
+	int i;
+
+	mlx5_ldev_for_each(i, 0, ldev) {
+		pf = mlx5_lag_pf(ldev, i);
+		if (!pf->sd_fdb_active)
+			continue;
+		mlx5_lag_shared_fdb_destroy(ldev, pf->group_id);
+	}
+	return 0;
+}
+
+static bool mlx5_lag_has_sd_group(struct mlx5_lag *ldev)
+{
+	struct lag_func *pf;
+	int i;
+
+	mlx5_ldev_for_each(i, 0, ldev) {
+		pf = mlx5_lag_pf(ldev, i);
+		if (pf->group_id)
+			return true;
+	}
+	return false;
+}
+
 static int mlx5_lag_enable_mpesw(struct mlx5_lag *ldev)
 {
 	int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
@@ -92,10 +134,17 @@ static int mlx5_lag_enable_mpesw(struct mlx5_lag *ldev)
 	if (err)
 		return err;
 
+	if (mlx5_lag_has_sd_group(ldev))
+		mlx5_mpesw_teardown_sd_fdb(ldev);
+
 	err = mlx5_lag_shared_fdb_create(ldev, NULL, MLX5_LAG_MODE_MPESW,
 					 MLX5_LAG_FILTER_ALL);
 	if (err) {
-		mlx5_core_warn(dev0, "Failed to create LAG in MPESW mode (%d)\n", err);
+		mlx5_core_warn(dev0,
+			       "Failed to create LAG in MPESW mode (%d)\n",
+			       err);
+		if (mlx5_lag_has_sd_group(ldev))
+			mlx5_mpesw_restore_sd_fdb(ldev);
 		mlx5_mpesw_metadata_cleanup(ldev);
 		return err;
 	}
@@ -105,9 +154,36 @@ static int mlx5_lag_enable_mpesw(struct mlx5_lag *ldev)
 
 void mlx5_lag_disable_mpesw(struct mlx5_lag *ldev)
 {
-	if (ldev->mode == MLX5_LAG_MODE_MPESW) {
-		mlx5_mpesw_metadata_cleanup(ldev);
-		mlx5_lag_shared_fdb_destroy(ldev, MLX5_LAG_FILTER_ALL);
+	if (ldev->mode != MLX5_LAG_MODE_MPESW)
+		return;
+
+	mlx5_mpesw_metadata_cleanup(ldev);
+	mlx5_lag_shared_fdb_destroy(ldev, MLX5_LAG_FILTER_ALL);
+	if (mlx5_lag_has_sd_group(ldev))
+		mlx5_mpesw_restore_sd_fdb(ldev);
+}
+
+void mlx5_mpesw_sd_devcoms_lock(struct mlx5_lag *ldev)
+{
+	struct mlx5_devcom_comp_dev *sd_devcom;
+	int i;
+
+	mlx5_ldev_for_each(i, 0, ldev) {
+		sd_devcom = mlx5_sd_get_devcom(mlx5_lag_pf(ldev, i)->dev);
+		if (sd_devcom)
+			mlx5_devcom_comp_lock(sd_devcom);
+	}
+}
+
+void mlx5_mpesw_sd_devcoms_unlock(struct mlx5_lag *ldev)
+{
+	struct mlx5_devcom_comp_dev *sd_devcom;
+	int i;
+
+	mlx5_ldev_for_each_reverse(i, MLX5_MAX_PORTS, 0, ldev) {
+		sd_devcom = mlx5_sd_get_devcom(mlx5_lag_pf(ldev, i)->dev);
+		if (sd_devcom)
+			mlx5_devcom_comp_unlock(sd_devcom);
 	}
 }
 
@@ -122,6 +198,7 @@ static void mlx5_mpesw_work(struct work_struct *work)
 		return;
 
 	mlx5_devcom_comp_lock(devcom);
+	mlx5_mpesw_sd_devcoms_lock(ldev);
 	mutex_lock(&ldev->lock);
 	if (ldev->mode_changes_in_progress) {
 		mpesww->result = -EAGAIN;
@@ -134,6 +211,7 @@ static void mlx5_mpesw_work(struct work_struct *work)
 		mlx5_lag_disable_mpesw(ldev);
 unlock:
 	mutex_unlock(&ldev->lock);
+	mlx5_mpesw_sd_devcoms_unlock(ldev);
 	mlx5_devcom_comp_unlock(devcom);
 	complete(&mpesww->comp);
 }
@@ -199,7 +277,8 @@ bool mlx5_lag_is_mpesw(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev = mlx5_lag_dev(dev);
 
-	return ldev && ldev->mode == MLX5_LAG_MODE_MPESW;
+	return ldev && ldev->mode == MLX5_LAG_MODE_MPESW &&
+	       __mlx5_lag_dev_is_port(ldev, dev);
 }
 EXPORT_SYMBOL(mlx5_lag_is_mpesw);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h
index b767dbb4f457..5099723ba0f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h
@@ -33,8 +33,12 @@ void mlx5_lag_mpesw_disable(struct mlx5_core_dev *dev);
 int mlx5_lag_mpesw_enable(struct mlx5_core_dev *dev);
 #ifdef CONFIG_MLX5_ESWITCH
 void mlx5_lag_disable_mpesw(struct mlx5_lag *ldev);
+void mlx5_mpesw_sd_devcoms_lock(struct mlx5_lag *ldev);
+void mlx5_mpesw_sd_devcoms_unlock(struct mlx5_lag *ldev);
 #else
 static inline void mlx5_lag_disable_mpesw(struct mlx5_lag *ldev) {}
+static inline void mlx5_mpesw_sd_devcoms_lock(struct mlx5_lag *ldev) {}
+static inline void mlx5_mpesw_sd_devcoms_unlock(struct mlx5_lag *ldev) {}
 #endif /* CONFIG_MLX5_ESWITCH */
 
 #ifdef CONFIG_MLX5_ESWITCH
-- 
2.44.0
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help