net/mlx5: Suspend auxiliary devices only in case of PCI device suspend

Jiri Pirko · Saeed Mahameed · commit 72ed5d5624af · 2023-02-14T14:08:27.000-08:00
The original behavior introduced by commit c6acd62 ("net/mlx5e: Add support for devlink-port in non-representors mode") correctly re-instantiated uplink devlink port and related netdevice during devlink reload. However with migration to auxiliary devices, this behaviour changed. Restore the original behaviour and tear down auxiliary devices completely during devlink reload. Signed-off-by: Jiri Pirko <jiri@nvidia.com> Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -396,7 +396,7 @@ int mlx5_attach_device(struct mlx5_core_dev *dev)
 	return ret;
 }
 
-void mlx5_detach_device(struct mlx5_core_dev *dev)
+void mlx5_detach_device(struct mlx5_core_dev *dev, bool suspend)
 {
 	struct mlx5_priv *priv = &dev->priv;
 	struct auxiliary_device *adev;
@@ -425,7 +425,7 @@ void mlx5_detach_device(struct mlx5_core_dev *dev)
 
 		adrv = to_auxiliary_drv(adev->dev.driver);
 
-		if (adrv->suspend) {
+		if (adrv->suspend && suspend) {
 			adrv->suspend(adev, pm);
 			continue;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -105,7 +105,7 @@ static int mlx5_devlink_reload_fw_activate(struct devlink *devlink, struct netli
 	if (err)
 		return err;
 
-	mlx5_unload_one_devl_locked(dev);
+	mlx5_unload_one_devl_locked(dev, true);
 	err = mlx5_health_wait_pci_up(dev);
 	if (err)
 		NL_SET_ERR_MSG_MOD(extack, "FW activate aborted, PCI reads fail after reset");
@@ -168,7 +168,7 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change,
 
 	switch (action) {
 	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT:
-		mlx5_unload_one_devl_locked(dev);
+		mlx5_unload_one_devl_locked(dev, false);
 		break;
 	case DEVLINK_RELOAD_ACTION_FW_ACTIVATE:
 		if (limit == DEVLINK_RELOAD_LIMIT_NO_RESET)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -163,7 +163,7 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev)
 	if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) {
 		complete(&fw_reset->done);
 	} else {
-		mlx5_unload_one(dev);
+		mlx5_unload_one(dev, false);
 		if (mlx5_health_wait_pci_up(dev))
 			mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n");
 		else
@@ -498,7 +498,7 @@ int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev)
 	}
 	err = fw_reset->ret;
 	if (test_and_clear_bit(MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED, &fw_reset->reset_flags)) {
-		mlx5_unload_one_devl_locked(dev);
+		mlx5_unload_one_devl_locked(dev, false);
 		mlx5_load_one_devl_locked(dev, false);
 	}
 out:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -699,7 +699,7 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work)
 		 * requests from the kernel.
 		 */
 		mlx5_core_err(dev, "Driver is in error state. Unloading\n");
-		mlx5_unload_one(dev);
+		mlx5_unload_one(dev, false);
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1520,12 +1520,12 @@ int mlx5_load_one(struct mlx5_core_dev *dev)
 	return ret;
 }
 
-void mlx5_unload_one_devl_locked(struct mlx5_core_dev *dev)
+void mlx5_unload_one_devl_locked(struct mlx5_core_dev *dev, bool suspend)
 {
 	devl_assert_locked(priv_to_devlink(dev));
 	mutex_lock(&dev->intf_state_mutex);
 
-	mlx5_detach_device(dev);
+	mlx5_detach_device(dev, suspend);
 
 	if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
 		mlx5_core_warn(dev, "%s: interface is down, NOP\n",
@@ -1540,12 +1540,12 @@ void mlx5_unload_one_devl_locked(struct mlx5_core_dev *dev)
 	mutex_unlock(&dev->intf_state_mutex);
 }
 
-void mlx5_unload_one(struct mlx5_core_dev *dev)
+void mlx5_unload_one(struct mlx5_core_dev *dev, bool suspend)
 {
 	struct devlink *devlink = priv_to_devlink(dev);
 
 	devl_lock(devlink);
-	mlx5_unload_one_devl_locked(dev);
+	mlx5_unload_one_devl_locked(dev, suspend);
 	devl_unlock(devlink);
 }
 
@@ -1830,7 +1830,7 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev,
 
 	mlx5_enter_error_state(dev, false);
 	mlx5_error_sw_reset(dev);
-	mlx5_unload_one(dev);
+	mlx5_unload_one(dev, true);
 	mlx5_drain_health_wq(dev);
 	mlx5_pci_disable_device(dev);
 
@@ -1986,15 +1986,15 @@ static void shutdown(struct pci_dev *pdev)
 	set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state);
 	err = mlx5_try_fast_unload(dev);
 	if (err)
-		mlx5_unload_one(dev);
+		mlx5_unload_one(dev, false);
 	mlx5_pci_disable_device(dev);
 }
 
 static int mlx5_suspend(struct pci_dev *pdev, pm_message_t state)
 {
 	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
 
-	mlx5_unload_one(dev);
+	mlx5_unload_one(dev, true);
 
 	return 0;
 }
@@ -2037,7 +2037,7 @@ MODULE_DEVICE_TABLE(pci, mlx5_core_pci_table);
 void mlx5_disable_device(struct mlx5_core_dev *dev)
 {
 	mlx5_error_sw_reset(dev);
-	mlx5_unload_one_devl_locked(dev);
+	mlx5_unload_one_devl_locked(dev, false);
 }
 
 int mlx5_recover_device(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -236,7 +236,7 @@ void mlx5_adev_cleanup(struct mlx5_core_dev *dev);
 int mlx5_adev_init(struct mlx5_core_dev *dev);
 
 int mlx5_attach_device(struct mlx5_core_dev *dev);
-void mlx5_detach_device(struct mlx5_core_dev *dev);
+void mlx5_detach_device(struct mlx5_core_dev *dev, bool suspend);
 int mlx5_register_device(struct mlx5_core_dev *dev);
 void mlx5_unregister_device(struct mlx5_core_dev *dev);
 struct mlx5_core_dev *mlx5_get_next_phys_dev_lag(struct mlx5_core_dev *dev);
@@ -319,8 +319,8 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx);
 void mlx5_mdev_uninit(struct mlx5_core_dev *dev);
 int mlx5_init_one(struct mlx5_core_dev *dev);
 void mlx5_uninit_one(struct mlx5_core_dev *dev);
-void mlx5_unload_one(struct mlx5_core_dev *dev);
-void mlx5_unload_one_devl_locked(struct mlx5_core_dev *dev);
+void mlx5_unload_one(struct mlx5_core_dev *dev, bool suspend);
+void mlx5_unload_one_devl_locked(struct mlx5_core_dev *dev, bool suspend);
 int mlx5_load_one(struct mlx5_core_dev *dev);
 int mlx5_load_one_devl_locked(struct mlx5_core_dev *dev, bool recovery);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
@@ -74,7 +74,7 @@ static void mlx5_sf_dev_shutdown(struct auxiliary_device *adev)
 {
 	struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev);
 
-	mlx5_unload_one(sf_dev->mdev);
+	mlx5_unload_one(sf_dev->mdev, false);
 }
 
 static const struct auxiliary_device_id mlx5_sf_dev_id_table[] = {

Original file line number	Diff line number	Diff line change
`@@ -396,7 +396,7 @@ int mlx5_attach_device(struct mlx5_core_dev *dev)`
`396`	`396`	`return ret;`
`397`	`397`	`}`
`398`	`398`
`399`		`-void mlx5_detach_device(struct mlx5_core_dev *dev)`
	`399`	`+void mlx5_detach_device(struct mlx5_core_dev *dev, bool suspend)`
`400`	`400`	`{`
`401`	`401`	`struct mlx5_priv *priv = &dev->priv;`
`402`	`402`	`struct auxiliary_device *adev;`
`@@ -425,7 +425,7 @@ void mlx5_detach_device(struct mlx5_core_dev *dev)`
`425`	`425`
`426`	`426`	`adrv = to_auxiliary_drv(adev->dev.driver);`
`427`	`427`
`428`		`- if (adrv->suspend) {`
	`428`	`+ if (adrv->suspend && suspend) {`
`429`	`429`	`adrv->suspend(adev, pm);`
`430`	`430`	`continue;`
`431`	`431`	`}`
Original file line number	Diff line number	Diff line change
`@@ -699,7 +699,7 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work)`
`699`	`699`	`* requests from the kernel.`
`700`	`700`	`*/`
`701`	`701`	`mlx5_core_err(dev, "Driver is in error state. Unloading\n");`
`702`		`- mlx5_unload_one(dev);`
	`702`	`+ mlx5_unload_one(dev, false);`
`703`	`703`	`}`
`704`	`704`	`}`
`705`	`705`
Original file line number	Diff line number	Diff line change
`@@ -1520,12 +1520,12 @@ int mlx5_load_one(struct mlx5_core_dev *dev)`
`1520`	`1520`	`return ret;`
`1521`	`1521`	`}`
`1522`	`1522`
`1523`		`-void mlx5_unload_one_devl_locked(struct mlx5_core_dev *dev)`
	`1523`	`+void mlx5_unload_one_devl_locked(struct mlx5_core_dev *dev, bool suspend)`
`1524`	`1524`	`{`
`1525`	`1525`	`devl_assert_locked(priv_to_devlink(dev));`
`1526`	`1526`	`mutex_lock(&dev->intf_state_mutex);`
`1527`	`1527`
`1528`		`- mlx5_detach_device(dev);`
	`1528`	`+ mlx5_detach_device(dev, suspend);`
`1529`	`1529`
`1530`	`1530`	`if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {`
`1531`	`1531`	`mlx5_core_warn(dev, "%s: interface is down, NOP\n",`
`@@ -1540,12 +1540,12 @@ void mlx5_unload_one_devl_locked(struct mlx5_core_dev *dev)`
`1540`	`1540`	`mutex_unlock(&dev->intf_state_mutex);`
`1541`	`1541`	`}`
`1542`	`1542`
`1543`		`-void mlx5_unload_one(struct mlx5_core_dev *dev)`
	`1543`	`+void mlx5_unload_one(struct mlx5_core_dev *dev, bool suspend)`
`1544`	`1544`	`{`
`1545`	`1545`	`struct devlink *devlink = priv_to_devlink(dev);`
`1546`	`1546`
`1547`	`1547`	`devl_lock(devlink);`
`1548`		`- mlx5_unload_one_devl_locked(dev);`
	`1548`	`+ mlx5_unload_one_devl_locked(dev, suspend);`
`1549`	`1549`	`devl_unlock(devlink);`
`1550`	`1550`	`}`
`1551`	`1551`
`@@ -1830,7 +1830,7 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev,`
`1830`	`1830`
`1831`	`1831`	`mlx5_enter_error_state(dev, false);`
`1832`	`1832`	`mlx5_error_sw_reset(dev);`
`1833`		`- mlx5_unload_one(dev);`
	`1833`	`+ mlx5_unload_one(dev, true);`
`1834`	`1834`	`mlx5_drain_health_wq(dev);`
`1835`	`1835`	`mlx5_pci_disable_device(dev);`
`1836`	`1836`
`@@ -1986,15 +1986,15 @@ static void shutdown(struct pci_dev *pdev)`
`1986`	`1986`	`set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state);`
`1987`	`1987`	`err = mlx5_try_fast_unload(dev);`
`1988`	`1988`	`if (err)`
`1989`		`- mlx5_unload_one(dev);`
	`1989`	`+ mlx5_unload_one(dev, false);`
`1990`	`1990`	`mlx5_pci_disable_device(dev);`
`1991`	`1991`	`}`
`1992`	`1992`
`1993`	`1993`	`static int mlx5_suspend(struct pci_dev *pdev, pm_message_t state)`
`1994`	`1994`	`{`
`1995`	`1995`	`struct mlx5_core_dev *dev = pci_get_drvdata(pdev);`
`1996`	`1996`
`1997`		`- mlx5_unload_one(dev);`
	`1997`	`+ mlx5_unload_one(dev, true);`
`1998`	`1998`
`1999`	`1999`	`return 0;`
`2000`	`2000`	`}`
`@@ -2037,7 +2037,7 @@ MODULE_DEVICE_TABLE(pci, mlx5_core_pci_table);`
`2037`	`2037`	`void mlx5_disable_device(struct mlx5_core_dev *dev)`
`2038`	`2038`	`{`
`2039`	`2039`	`mlx5_error_sw_reset(dev);`
`2040`		`- mlx5_unload_one_devl_locked(dev);`
	`2040`	`+ mlx5_unload_one_devl_locked(dev, false);`
`2041`	`2041`	`}`
`2042`	`2042`
`2043`	`2043`	`int mlx5_recover_device(struct mlx5_core_dev *dev)`
Original file line number	Diff line number	Diff line change
`@@ -74,7 +74,7 @@ static void mlx5_sf_dev_shutdown(struct auxiliary_device *adev)`
`74`	`74`	`{`
`75`	`75`	`struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev);`
`76`	`76`
`77`		`- mlx5_unload_one(sf_dev->mdev);`
	`77`	`+ mlx5_unload_one(sf_dev->mdev, false);`
`78`	`78`	`}`
`79`	`79`
`80`	`80`	`static const struct auxiliary_device_id mlx5_sf_dev_id_table[] = {`