net/mlx5: E-Switch, unwind only newly loaded representor types

__esw_offloads_load_rep() may return success without invoking the
representor load callback when the representor type is already loaded.

On a later load failure, mlx5_esw_offloads_rep_load() unconditionally
unloaded all previously iterated representor types. This could unload
representor types that were already loaded before this load attempt.

Track which representor types were actually loaded by the current call and
unwind only those on error. Also restore the representor state back to
REP_REGISTERED when the load callback itself fails.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260503202726.266415-7-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 29 insertions, 9 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index a393efaa2fd7..8a7491e9f13d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2786,13 +2786,28 @@ void esw_offloads_cleanup(struct mlx5_eswitch *esw)
 }
 
 static int __esw_offloads_load_rep(struct mlx5_eswitch *esw,
-				   struct mlx5_eswitch_rep *rep, u8 rep_type)
+				   struct mlx5_eswitch_rep *rep,
+				   u8 rep_type, bool *newly_loaded)
 {
+	int err;
+
 	mlx5_esw_assert_reps_locked(esw);
 
+	if (newly_loaded)
+		*newly_loaded = false;
+
 	if (atomic_cmpxchg(&rep->rep_data[rep_type].state,
-			   REP_REGISTERED, REP_LOADED) == REP_REGISTERED)
-		return esw->offloads.rep_ops[rep_type]->load(esw->dev, rep);
+			   REP_REGISTERED, REP_LOADED) != REP_REGISTERED)
+		return 0;
+
+	err = esw->offloads.rep_ops[rep_type]->load(esw->dev, rep);
+	if (err) {
+		atomic_set(&rep->rep_data[rep_type].state, REP_REGISTERED);
+		return err;
+	}
+
+	if (newly_loaded)
+		*newly_loaded = true;
 
 	return 0;
 }
@@ -2822,22 +2837,27 @@ static void __unload_reps_all_vport(struct mlx5_eswitch *esw, u8 rep_type)
 static int mlx5_esw_offloads_rep_load(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	struct mlx5_eswitch_rep *rep;
+	unsigned long loaded = 0;
+	bool newly_loaded;
 	int rep_type;
 	int err;
 
 	rep = mlx5_eswitch_get_rep(esw, vport_num);
 	for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) {
-		err = __esw_offloads_load_rep(esw, rep, rep_type);
+		err = __esw_offloads_load_rep(esw, rep, rep_type,
+					      &newly_loaded);
 		if (err)
 			goto err_reps;
+		if (newly_loaded)
+			loaded |= BIT(rep_type);
 	}
 
 	return 0;
 
 err_reps:
-	atomic_set(&rep->rep_data[rep_type].state, REP_REGISTERED);
-	for (--rep_type; rep_type >= 0; rep_type--)
-		__esw_offloads_unload_rep(esw, rep, rep_type);
+	while (--rep_type >= 0)
+		if (test_bit(rep_type, &loaded))
+			__esw_offloads_unload_rep(esw, rep, rep_type);
 	return err;
 }
 
@@ -3591,13 +3611,13 @@ int mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw)
 	if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED)
 		return 0;
 
-	ret = __esw_offloads_load_rep(esw, rep, REP_IB);
+	ret = __esw_offloads_load_rep(esw, rep, REP_IB, NULL);
 	if (ret)
 		return ret;
 
 	mlx5_esw_for_each_rep(esw, i, rep) {
 		if (atomic_read(&rep->rep_data[REP_ETH].state) == REP_LOADED)
-			__esw_offloads_load_rep(esw, rep, REP_IB);
+			__esw_offloads_load_rep(esw, rep, REP_IB, NULL);
 	}
 
 	return 0;