Summary

vega10_ih_prescreen_iv L288-301 kfifo_put block #if 0 replaced by unconditional kprintf fires on every VM retry page fault whose PASID resolves through pasid_idr (common case for any GPU workload touching unmapped VA). amdgpu_ih_process calls callback->prescreen_iv once per IV L154-157 no rate limiting. Local user render-node access submits CS touching unmapped GPU VM -> GPU emits retry-fault IVs continuously -> kprintf from hardirq context thousands/sec -> fills /var/log burns CPU. No privilege gain/info-leak/corruption; log/disk/CPU exhaustion. Fix: delete #if 0/#else block let control fall through to existing lockmgr(LK_RELEASE);return true at L303-305 or replace kprintf with ratelimited DRM_DEBUG.