3 files changed, 48 insertions, 4 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 62b70334a13d..8f2b3abe0092 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -6774,8 +6774,10 @@ static int mlx5e_resume(struct auxiliary_device *adev)
 		return err;
 
 	actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx);
-	if (actual_adev)
+	if (actual_adev) {
 		err = _mlx5e_resume(actual_adev);
+		mlx5_sd_put_adev(actual_adev, adev);
+	}
 	return err;
 }
 
@@ -6815,6 +6817,8 @@ static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state)
 		err = _mlx5e_suspend(actual_adev, false);
 
 	mlx5_sd_cleanup(mdev);
+	if (actual_adev)
+		mlx5_sd_put_adev(actual_adev, adev);
 	return err;
 }
 
@@ -6916,11 +6920,14 @@ static int mlx5e_probe(struct auxiliary_device *adev,
 		err = _mlx5e_probe(actual_adev);
 		if (err)
 			goto sd_cleanup;
+		mlx5_sd_put_adev(actual_adev, adev);
 	}
 	return 0;
 
 sd_cleanup:
 	mlx5_sd_cleanup(mdev);
+	if (actual_adev)
+		mlx5_sd_put_adev(actual_adev, adev);
 	return err;
 }
 
@@ -6973,6 +6980,8 @@ static void mlx5e_remove(struct auxiliary_device *adev)
 		_mlx5e_remove(actual_adev);
 
 	mlx5_sd_cleanup(mdev);
+	if (actual_adev)
+		mlx5_sd_put_adev(actual_adev, adev);
 }
 
 static const struct auxiliary_device_id mlx5e_id_table[] = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
index 89b7e4d67303..6e199161b008 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
@@ -562,22 +562,55 @@ out_unlock:
 	sd_cleanup(dev);
 }
 
+/* Lock order:
+ *   primary:   actual_adev_lock -> SD devcom comp lock
+ *   secondary: SD devcom comp lock -> (drop) -> actual_adev_lock
+ * The two locks are never held together, so no ABBA.
+ */
 struct auxiliary_device *mlx5_sd_get_adev(struct mlx5_core_dev *dev,
 					  struct auxiliary_device *adev,
 					  int idx)
 {
 	struct mlx5_sd *sd = mlx5_get_sd(dev);
 	struct mlx5_core_dev *primary;
+	struct mlx5_adev *primary_adev;
 
 	if (!sd)
 		return adev;
 
-	if (!mlx5_devcom_comp_is_ready(sd->devcom))
+	mlx5_devcom_comp_lock(sd->devcom);
+	if (!mlx5_devcom_comp_is_ready(sd->devcom)) {
+		mlx5_devcom_comp_unlock(sd->devcom);
 		return NULL;
+	}
 
 	primary = mlx5_sd_get_primary(dev);
-	if (dev == primary)
+	if (!primary || dev == primary) {
+		mlx5_devcom_comp_unlock(sd->devcom);
 		return adev;
+	}
+
+	primary_adev = primary->priv.adev[idx];
+	get_device(&primary_adev->adev.dev);
+	mlx5_devcom_comp_unlock(sd->devcom);
 
-	return &primary->priv.adev[idx]->adev;
+	device_lock(&primary_adev->adev.dev);
+	/* Primary may have completed remove between dropping devcom and
+	 * acquiring device_lock; recheck.
+	 */
+	if (!mlx5_devcom_comp_is_ready(sd->devcom)) {
+		device_unlock(&primary_adev->adev.dev);
+		put_device(&primary_adev->adev.dev);
+		return NULL;
+	}
+	return &primary_adev->adev;
+}
+
+void mlx5_sd_put_adev(struct auxiliary_device *actual_adev,
+		      struct auxiliary_device *adev)
+{
+	if (actual_adev != adev) {
+		device_unlock(&actual_adev->dev);
+		put_device(&actual_adev->dev);
+	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h
index 137efaf9aabc..9bfd5b9756b5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h
@@ -15,6 +15,8 @@ struct mlx5_core_dev *mlx5_sd_ch_ix_get_dev(struct mlx5_core_dev *primary, int c
 struct auxiliary_device *mlx5_sd_get_adev(struct mlx5_core_dev *dev,
 					  struct auxiliary_device *adev,
 					  int idx);
+void mlx5_sd_put_adev(struct auxiliary_device *actual_adev,
+		      struct auxiliary_device *adev);
 
 int mlx5_sd_init(struct mlx5_core_dev *dev);
 void mlx5_sd_cleanup(struct mlx5_core_dev *dev);