Re: [PATCH v5 01/33] thermal/of: Rework the thermal device tree initialization

[Ido Schimmel <idosch@idosch.org>]

On Fri, Aug 05, 2022 at 12:43:17AM +0200, Daniel Lezcano wrote:
> +struct thermal_zone_device *thermal_of_zone_register(struct device_node *sensor, int id, void *data,
> +						     const struct thermal_zone_device_ops *ops)
> +{
> +	struct thermal_zone_device *tz;
> +	struct thermal_trip *trips;
> +	struct thermal_zone_params *tzp;
> +	struct thermal_zone_device_ops *of_ops;
> +	struct device_node *np;
> +	int delay, pdelay;
> +	int ntrips, mask;
> +	int ret;
> +
> +	of_ops = kmemdup(ops, sizeof(*ops), GFP_KERNEL);
> +	if (!of_ops)
> +		return ERR_PTR(-ENOMEM);
> +	
> +	np = of_thermal_zone_find(sensor, id);
> +	if (IS_ERR(np)) {
> +		pr_err("Failed to find thermal zone for %pOFn id=%d\n", sensor, id);
> +		return ERR_CAST(np);
> +	}
> +
> +	trips = thermal_of_trips_init(np, &ntrips);
> +	if (IS_ERR(trips)) {
> +		pr_err("Failed to find trip points for %pOFn id=%d\n", sensor, id);
> +		return ERR_CAST(trips);
> +	}
> +
> +	ret = thermal_of_monitor_init(np, &delay, &pdelay);
> +	if (ret) {
> +		pr_err("Failed to initialize monitoring delays from %pOFn\n", np);
> +		goto out_kfree_trips;
> +	}
> +
> +	tzp = thermal_of_parameters_init(np);
> +	if (IS_ERR(tzp)) {
> +		ret = PTR_ERR(tzp);
> +		pr_err("Failed to initialize parameter from %pOFn: %d\n", np, ret);
> +		goto out_kfree_trips;
> +	}
> +
> +	of_ops->get_trip_type = of_ops->get_trip_type ? : of_thermal_get_trip_type;
> +	of_ops->get_trip_temp = of_ops->get_trip_temp ? : of_thermal_get_trip_temp;
> +	of_ops->get_trip_hyst = of_ops->get_trip_hyst ? : of_thermal_get_trip_hyst;
> +	of_ops->set_trip_hyst = of_ops->set_trip_hyst ? : of_thermal_set_trip_hyst;
> +	of_ops->get_crit_temp = of_ops->get_crit_temp ? : of_thermal_get_crit_temp;
> +	of_ops->bind = thermal_of_bind;
> +	of_ops->unbind = thermal_of_unbind;
> +
> +	mask = GENMASK_ULL((ntrips) - 1, 0);
> +
> +	tz = thermal_zone_device_register_with_trips(np->name, trips, ntrips,
> +						     mask, data, of_ops, tzp,
> +						     pdelay, delay);
> +	if (IS_ERR(tz)) {
> +		ret = PTR_ERR(tz);
> +		pr_err("Failed to register thermal zone %pOFn: %d\n", np, ret);
> +		goto out_kfree_tzp;
> +	}
> +
> +	ret = thermal_zone_device_enable(tz);
> +	if (ret) {
> +		pr_err("Failed to enabled thermal zone '%s', id=%d: %d\n",
> +		       tz->type, tz->id, ret);
> +		thermal_of_zone_unregister(tz);
> +		return ERR_PTR(ret);
> +	}
> +
> +	return tz;
> +
> +out_kfree_tzp:
> +	kfree(tzp);
> +out_kfree_trips:
> +	kfree(trips);
> +
> +	return ERR_PTR(ret);
> +}
> +EXPORT_SYMBOL_GPL(thermal_of_zone_register);

Daniel, I started seeing these memory leaks [1] since commit
613ed3f67609 ("hwmon: pm_bus: core: Switch to new of thermal API").
Seems to be fixed by the following patch [2].

Do you already have a patch for this issue or should I submit it?

Thanks

[1]
unreferenced object 0xffff8ee846198c80 (size 128):
  comm "swapper/0", pid 1, jiffies 4294699704 (age 70.076s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    d0 3f 6e 8c ff ff ff ff 00 00 00 00 00 00 00 00  .?n.............
  backtrace:
    [<00000000d136f562>] __kmalloc_node_track_caller+0x42/0x120
    [<0000000063f31678>] kmemdup+0x1d/0x40
    [<00000000e6d24096>] thermal_of_zone_register+0x49/0x520
    [<000000005e78c755>] devm_thermal_of_zone_register+0x54/0x90
    [<00000000ee6b209e>] pmbus_add_sensor+0x1b4/0x1d0
    [<00000000896105e3>] pmbus_add_sensor_attrs_one+0x123/0x440
    [<0000000049e990a6>] pmbus_add_sensor_attrs+0xfe/0x1d0
    [<00000000466b5440>] pmbus_do_probe+0x66b/0x14e0
    [<0000000084d42285>] i2c_device_probe+0x13b/0x2f0
    [<0000000029e2ae74>] really_probe+0xce/0x2c0
    [<00000000692df15c>] driver_probe_device+0x19/0xd0
    [<00000000547d9cce>] __device_attach_driver+0x6f/0x100
    [<0000000020abd24b>] bus_for_each_drv+0x76/0xc0
    [<00000000665d9563>] __device_attach+0xfc/0x180
    [<000000008ddd4d6a>] bus_probe_device+0x82/0xa0
    [<000000009e61132b>] device_add+0x3fe/0x920
unreferenced object 0xffff8ee846199200 (size 128):
  comm "swapper/0", pid 1, jiffies 4294699710 (age 70.070s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    d0 3f 6e 8c ff ff ff ff 00 00 00 00 00 00 00 00  .?n.............
  backtrace:
    [<00000000d136f562>] __kmalloc_node_track_caller+0x42/0x120
    [<0000000063f31678>] kmemdup+0x1d/0x40
    [<00000000e6d24096>] thermal_of_zone_register+0x49/0x520
    [<000000005e78c755>] devm_thermal_of_zone_register+0x54/0x90
    [<00000000ee6b209e>] pmbus_add_sensor+0x1b4/0x1d0
    [<00000000896105e3>] pmbus_add_sensor_attrs_one+0x123/0x440
    [<0000000049e990a6>] pmbus_add_sensor_attrs+0xfe/0x1d0
    [<00000000466b5440>] pmbus_do_probe+0x66b/0x14e0
    [<0000000084d42285>] i2c_device_probe+0x13b/0x2f0
    [<0000000029e2ae74>] really_probe+0xce/0x2c0
    [<00000000692df15c>] driver_probe_device+0x19/0xd0
    [<00000000547d9cce>] __device_attach_driver+0x6f/0x100
    [<0000000020abd24b>] bus_for_each_drv+0x76/0xc0
    [<00000000665d9563>] __device_attach+0xfc/0x180
    [<000000008ddd4d6a>] bus_probe_device+0x82/0xa0
    [<000000009e61132b>] device_add+0x3fe/0x920
unreferenced object 0xffff8ee846199780 (size 128):
  comm "swapper/0", pid 1, jiffies 4294699716 (age 70.064s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    d0 3f 6e 8c ff ff ff ff 00 00 00 00 00 00 00 00  .?n.............
  backtrace:
    [<00000000d136f562>] __kmalloc_node_track_caller+0x42/0x120
    [<0000000063f31678>] kmemdup+0x1d/0x40
    [<00000000e6d24096>] thermal_of_zone_register+0x49/0x520
    [<000000005e78c755>] devm_thermal_of_zone_register+0x54/0x90
    [<00000000ee6b209e>] pmbus_add_sensor+0x1b4/0x1d0
    [<00000000896105e3>] pmbus_add_sensor_attrs_one+0x123/0x440
    [<0000000049e990a6>] pmbus_add_sensor_attrs+0xfe/0x1d0
    [<00000000466b5440>] pmbus_do_probe+0x66b/0x14e0
    [<0000000084d42285>] i2c_device_probe+0x13b/0x2f0
    [<0000000029e2ae74>] really_probe+0xce/0x2c0
    [<00000000692df15c>] driver_probe_device+0x19/0xd0
    [<00000000547d9cce>] __device_attach_driver+0x6f/0x100
    [<0000000020abd24b>] bus_for_each_drv+0x76/0xc0
    [<00000000665d9563>] __device_attach+0xfc/0x180
    [<000000008ddd4d6a>] bus_probe_device+0x82/0xa0
    [<000000009e61132b>] device_add+0x3fe/0x920

[2]
diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c
index d4b6335ace15..43d55c29a29a 100644
--- a/drivers/thermal/thermal_of.c
+++ b/drivers/thermal/thermal_of.c
@@ -604,13 +604,15 @@ struct thermal_zone_device *thermal_of_zone_register(struct device_node *sensor,
        if (IS_ERR(np)) {
                if (PTR_ERR(np) != -ENODEV)
                        pr_err("Failed to find thermal zone for %pOFn id=%d\n", sensor, id);
-               return ERR_CAST(np);
+               ret = PTR_ERR(np);
+               goto out_kfree_of_ops;
        }
 
        trips = thermal_of_trips_init(np, &ntrips);
        if (IS_ERR(trips)) {
                pr_err("Failed to find trip points for %pOFn id=%d\n", sensor, id);
-               return ERR_CAST(trips);
+               ret = PTR_ERR(np);
+               goto out_kfree_of_ops;
        }
 
        ret = thermal_of_monitor_init(np, &delay, &pdelay);
@@ -659,6 +661,8 @@ struct thermal_zone_device *thermal_of_zone_register(struct device_node *sensor,
        kfree(tzp);
 out_kfree_trips:
        kfree(trips);
+out_kfree_of_ops:
+       kfree(of_ops);
 
        return ERR_PTR(ret);
 }