Re: [PATCH v4 3/6] drm/amdgpu: always clear stable_pstate_ctx in amdgpu_ctx_fini

From: Christian König

Date: Tue Nov 10 2026 - 04:39:53 EST


On 11/9/26 18:13, Pierre-Eric Pelloux-Prayer wrote:
> Even if the hardware is not available we should clear the pointer when
> the owning context is destroyed, otherwise nobody will be able to
> use this feature again.
>
> Reported-by: Sashiko-bot <sashiko-bot@xxxxxxxxxx>
> Closes: https://sashiko.dev/#/patchset/20261029152000.22001-1-pierre-eric.pelloux-prayer@xxxxxxx?part=5
> Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@xxxxxxx>

Reviewed-by: Christian König <christian.koenig@xxxxxxx>

> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 12 ++++++------
> 1 file changed, 6 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
> index 25b1cf7dc988..2b318ccc9aa6 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
> @@ -426,15 +426,15 @@ void amdgpu_ctx_fini(struct kref *ref)
> }
> }
>
> - if (drm_dev_enter(adev_to_drm(adev), &idx)) {
> - mutex_lock(&adev->pm.stable_pstate_ctx_lock);
> - if (adev->pm.stable_pstate_ctx == ctx) {
> + mutex_lock(&adev->pm.stable_pstate_ctx_lock);
> + if (adev->pm.stable_pstate_ctx == ctx) {
> + if (drm_dev_enter(adev_to_drm(adev), &idx)) {
> __amdgpu_ctx_set_stable_pstate(ctx, ctx->stable_pstate);
> - adev->pm.stable_pstate_ctx = NULL;
> + drm_dev_exit(idx);
> }
> - mutex_unlock(&adev->pm.stable_pstate_ctx_lock);
> - drm_dev_exit(idx);
> + adev->pm.stable_pstate_ctx = NULL;
> }
> + mutex_unlock(&adev->pm.stable_pstate_ctx_lock);
>
> kfree(ctx);
> }