Re: [PATCH] drm/radeon/dpm: fix a memleak in sumo_parse_power_table

[Christian König]

Am 03.12.23 um 18:16 schrieb Zhipeng Lu:
> The rdev->pm.dpm.ps allocated by kcalloc should be freed in every
> following error-handling path. However, in the error-handling of
> rdev->pm.power_state[i].clock_info the rdev->pm.dpm.ps is not freed,
> resulting in a memleak in this function.
>
> Fixes: 80ea2c129c76 ("drm/radeon/kms: add dpm support for sumo asics (v2)")
> Signed-off-by: Zhipeng Lu <alexious@xxxxxxxxxx>
> ---
>   drivers/gpu/drm/radeon/sumo_dpm.c | 1 +
>   1 file changed, 1 insertion(+)
>
> diff --git a/drivers/gpu/drm/radeon/sumo_dpm.c b/drivers/gpu/drm/radeon/sumo_dpm.c
> index f74f381af05f..bde640053708 100644
> --- a/drivers/gpu/drm/radeon/sumo_dpm.c
> +++ b/drivers/gpu/drm/radeon/sumo_dpm.c
> @@ -1494,6 +1494,7 @@ static int sumo_parse_power_table(struct radeon_device *rdev)
>   		non_clock_info = (struct _ATOM_PPLIB_NONCLOCK_INFO *)
>   			&non_clock_info_array->nonClockInfo[non_clock_array_index];
>   		if (!rdev->pm.power_state[i].clock_info)
> +			kfree(rdev->pm.dpm.ps);
>   			return -EINVAL;

That change is obviously not correct since you now always return -EINVAL.

You need to at least add {} here.

Regards,
Christian.

>   		ps = kzalloc(sizeof(struct sumo_ps), GFP_KERNEL);
>   		if (ps == NULL) {