On Mon, Dec 4, 2023 at 5:55 PM Zhipeng Lu <alexious@xxxxxxxxxx> wrote:
>
> 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: d70229f70447 ("drm/radeon/kms: add dpm support for trinity asics")
> Signed-off-by: Zhipeng Lu <alexious@xxxxxxxxxx>
> ---
> drivers/gpu/drm/radeon/trinity_dpm.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/drivers/gpu/drm/radeon/trinity_dpm.c b/drivers/gpu/drm/radeon/trinity_dpm.c
> index 08ea1c864cb2..8bf56fb7b933 100644
> --- a/drivers/gpu/drm/radeon/trinity_dpm.c
> +++ b/drivers/gpu/drm/radeon/trinity_dpm.c
> @@ -1727,6 +1727,7 @@ static int trinity_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);
I just confirmed the memleak problem in the code. But the fix has a
problem, it lacks the brackets.
diff --git a/drivers/gpu/drm/radeon/trinity_dpm.c
b/drivers/gpu/drm/radeon/trinity_dpm.c
index 08ea1c864cb2..ef1cc7bad20a 100644
--- a/drivers/gpu/drm/radeon/trinity_dpm.c
+++ b/drivers/gpu/drm/radeon/trinity_dpm.c
@@ -1726,8 +1726,10 @@ static int trinity_parse_power_table(struct
radeon_device *rdev)
non_clock_array_index = power_state->v2.nonClockInfoIndex;
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)
+ 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) {
kfree(rdev->pm.dpm.ps);
> return -EINVAL;
> ps = kzalloc(sizeof(struct sumo_ps), GFP_KERNEL);
> if (ps == NULL) {
> --
> 2.34.1
>
