net/mlx5: Refactor LAG peer device lookout bus logic to mlx5 devcom

LAG peer device lookout bus logic required the usage of global lock,
mlx5_intf_mutex.
As part of the effort to remove this global lock, refactor LAG peer
device lookout to use mlx5 devcom layer.
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

drivers/net/ethernet/mellanox/mlx5/core/dev.c

@@ -566,74 +566,6 @@ bool mlx5_same_hw_devs(struct mlx5_core_dev *dev, struct mlx5_core_dev *peer_dev
 	return (fsystem_guid && psystem_guid && fsystem_guid == psystem_guid);
 }
 
-static u32 mlx5_gen_pci_id(const struct mlx5_core_dev *dev)
-{
-	return (u32)((pci_domain_nr(dev->pdev->bus) << 16) |
-		     (dev->pdev->bus->number << 8) |
-		     PCI_SLOT(dev->pdev->devfn));
-}
-
-static int _next_phys_dev(struct mlx5_core_dev *mdev,
-			  const struct mlx5_core_dev *curr)
-{
-	if (!mlx5_core_is_pf(mdev))
-		return 0;
-
-	if (mdev == curr)
-		return 0;
-
-	if (!mlx5_same_hw_devs(mdev, (struct mlx5_core_dev *)curr) &&
-	    mlx5_gen_pci_id(mdev) != mlx5_gen_pci_id(curr))
-		return 0;
-
-	return 1;
-}
-
-static void *pci_get_other_drvdata(struct device *this, struct device *other)
-{
-	if (this->driver != other->driver)
-		return NULL;
-
-	return pci_get_drvdata(to_pci_dev(other));
-}
-
-static int next_phys_dev_lag(struct device *dev, const void *data)
-{
-	struct mlx5_core_dev *mdev, *this = (struct mlx5_core_dev *)data;
-
-	mdev = pci_get_other_drvdata(this->device, dev);
-	if (!mdev)
-		return 0;
-
-	if (!mlx5_lag_is_supported(mdev))
-		return 0;
-
-	return _next_phys_dev(mdev, data);
-}
-
-static struct mlx5_core_dev *mlx5_get_next_dev(struct mlx5_core_dev *dev,
-					       int (*match)(struct device *dev, const void *data))
-{
-	struct device *next;
-
-	if (!mlx5_core_is_pf(dev))
-		return NULL;
-
-	next = bus_find_device(&pci_bus_type, NULL, dev, match);
-	if (!next)
-		return NULL;
-
-	put_device(next);
-	return pci_get_drvdata(to_pci_dev(next));
-}
-
-/* Must be called with intf_mutex held */
-struct mlx5_core_dev *mlx5_get_next_phys_dev_lag(struct mlx5_core_dev *dev)
-{
-	lockdep_assert_held(&mlx5_intf_mutex);
-	return mlx5_get_next_dev(dev, &next_phys_dev_lag);
-}
-
 void mlx5_dev_list_lock(void)
 {
 	mutex_lock(&mlx5_intf_mutex);

drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c

@@ -1212,13 +1212,14 @@ static void mlx5_ldev_remove_mdev(struct mlx5_lag *ldev,
 	dev->priv.lag = NULL;
 }
 
-/* Must be called with intf_mutex held */
+/* Must be called with HCA devcom component lock held */
 static int __mlx5_lag_dev_add_mdev(struct mlx5_core_dev *dev)
 {
+	struct mlx5_devcom_comp_dev *pos = NULL;
 	struct mlx5_lag *ldev = NULL;
 	struct mlx5_core_dev *tmp_dev;
 
-	tmp_dev = mlx5_get_next_phys_dev_lag(dev);
+	tmp_dev = mlx5_devcom_get_next_peer_data(dev->priv.hca_devcom_comp, &pos);
 	if (tmp_dev)
 		ldev = mlx5_lag_dev(tmp_dev);
 
@@ -1275,10 +1276,13 @@ void mlx5_lag_add_mdev(struct mlx5_core_dev *dev)
 	if (!mlx5_lag_is_supported(dev))
 		return;
 
+	if (IS_ERR_OR_NULL(dev->priv.hca_devcom_comp))
+		return;
+
 recheck:
-	mlx5_dev_list_lock();
+	mlx5_devcom_comp_lock(dev->priv.hca_devcom_comp);
 	err = __mlx5_lag_dev_add_mdev(dev);
-	mlx5_dev_list_unlock();
+	mlx5_devcom_comp_unlock(dev->priv.hca_devcom_comp);
 
 	if (err) {
 		msleep(100);

drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c

@@ -387,3 +387,17 @@ void *mlx5_devcom_get_next_peer_data_rcu(struct mlx5_devcom_comp_dev *devcom,
 	*pos = tmp;
 	return data;
 }
+
+void mlx5_devcom_comp_lock(struct mlx5_devcom_comp_dev *devcom)
+{
+	if (IS_ERR_OR_NULL(devcom))
+		return;
+	down_write(&devcom->comp->sem);
+}
+
+void mlx5_devcom_comp_unlock(struct mlx5_devcom_comp_dev *devcom)
+{
+	if (IS_ERR_OR_NULL(devcom))
+		return;
+	up_write(&devcom->comp->sem);
+}

drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h

@@ -9,6 +9,7 @@
 enum mlx5_devcom_component {
 	MLX5_DEVCOM_ESW_OFFLOADS,
 	MLX5_DEVCOM_MPV,
+	MLX5_DEVCOM_HCA_PORTS,
 	MLX5_DEVCOM_NUM_COMPONENTS,
 };
 
@@ -52,4 +53,7 @@ void *mlx5_devcom_get_next_peer_data_rcu(struct mlx5_devcom_comp_dev *devcom,
 	     data;								  \
 	     data = mlx5_devcom_get_next_peer_data_rcu(devcom, &pos))
 
+void mlx5_devcom_comp_lock(struct mlx5_devcom_comp_dev *devcom);
+void mlx5_devcom_comp_unlock(struct mlx5_devcom_comp_dev *devcom);
+
 #endif /* __LIB_MLX5_DEVCOM_H__ */

drivers/net/ethernet/mellanox/mlx5/core/main.c

@@ -73,6 +73,7 @@
 #include "sf/sf.h"
 #include "mlx5_irq.h"
 #include "hwmon.h"
+#include "lag/lag.h"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver");
@@ -952,6 +953,27 @@ static void mlx5_pci_close(struct mlx5_core_dev *dev)
 	mlx5_pci_disable_device(dev);
 }
 
+static void mlx5_register_hca_devcom_comp(struct mlx5_core_dev *dev)
+{
+	/* This component is use to sync adding core_dev to lag_dev and to sync
+	 * changes of mlx5_adev_devices between LAG layer and other layers.
+	 */
+	if (!mlx5_lag_is_supported(dev))
+		return;
+
+	dev->priv.hca_devcom_comp =
+		mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_HCA_PORTS,
+					       mlx5_query_nic_system_image_guid(dev),
+					       NULL, dev);
+	if (IS_ERR_OR_NULL(dev->priv.hca_devcom_comp))
+		mlx5_core_err(dev, "Failed to register devcom HCA component\n");
+}
+
+static void mlx5_unregister_hca_devcom_comp(struct mlx5_core_dev *dev)
+{
+	mlx5_devcom_unregister_component(dev->priv.hca_devcom_comp);
+}
+
 static int mlx5_init_once(struct mlx5_core_dev *dev)
 {
 	int err;
@@ -960,6 +982,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 	if (IS_ERR(dev->priv.devc))
 		mlx5_core_warn(dev, "failed to register devcom device %ld\n",
 			       PTR_ERR(dev->priv.devc));
+	mlx5_register_hca_devcom_comp(dev);
 
 	err = mlx5_query_board_id(dev);
 	if (err) {
@@ -1094,6 +1117,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 err_irq_cleanup:
 	mlx5_irq_table_cleanup(dev);
 err_devcom:
+	mlx5_unregister_hca_devcom_comp(dev);
 	mlx5_devcom_unregister_device(dev->priv.devc);
 
 	return err;
@@ -1123,6 +1147,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_events_cleanup(dev);
 	mlx5_eq_table_cleanup(dev);
 	mlx5_irq_table_cleanup(dev);
+	mlx5_unregister_hca_devcom_comp(dev);
 	mlx5_devcom_unregister_device(dev->priv.devc);
 }
 

drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h

@@ -266,7 +266,6 @@ int mlx5_register_device(struct mlx5_core_dev *dev);
 void mlx5_unregister_device(struct mlx5_core_dev *dev);
 void mlx5_dev_set_lightweight(struct mlx5_core_dev *dev);
 bool mlx5_dev_is_lightweight(struct mlx5_core_dev *dev);
-struct mlx5_core_dev *mlx5_get_next_phys_dev_lag(struct mlx5_core_dev *dev);
 void mlx5_dev_list_lock(void);
 void mlx5_dev_list_unlock(void);
 int mlx5_dev_list_trylock(void);

include/linux/mlx5/driver.h

@@ -624,6 +624,7 @@ struct mlx5_priv {
 	struct mlx5_lag		*lag;
 	u32			flags;
 	struct mlx5_devcom_dev	*devc;
+	struct mlx5_devcom_comp_dev *hca_devcom_comp;
 	struct mlx5_fw_reset	*fw_reset;
 	struct mlx5_core_roce	roce;
 	struct mlx5_fc_stats		fc_stats;