[PATCH] drm/radeon/dpm: fix a memleak in sumo_parse_power_table
alexious at zju.edu.cn
alexious at zju.edu.cn
Mon Dec 4 08:46:54 UTC 2023
> 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 at zju.edu.cn>
> > ---
> > 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.
>
I'm sorry for my mistake and I'll send a new patch soon.
Regards,
Zhipeng
More information about the amd-gfx
mailing list