2023-12-03 17:19:45

by Zhipeng Lu

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

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 <[email protected]>
---
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;
ps = kzalloc(sizeof(struct sumo_ps), GFP_KERNEL);
if (ps == NULL) {
--
2.34.1

2023-12-04 08:17:30

by Christian König

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

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 <[email protected]>
> ---
> 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) {

2023-12-04 08:47:19

by Zhipeng Lu

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

> 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 <[email protected]>
> > ---
> > 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