🇰🇷 한글 설명
Linux 커널의 hmm_range_fault() 함수에서 디바이스-프라이빗 folio 락 대기 시 livelock/starvation 문제 발생. migrate_device_unmap()에서 lru_add_drain_all() 호출 중 같은 CPU의 워크 아이템이 blocked되어 무한 대기 상황 유발. do_swap_page()에서 folio_trylock() 실패 시 unlock 대기로 수정.
💡 쉬운 설명
Linux 커널의 메모리 관리 루틴이 특정 조건에서 자기 자신이 완료되기를 기다리는 교착 상태에 빠지는 버그입니다. GPU 메모리와 시스템 메모리 간 데이터 이동 중에 발생 가능합니다.
🇺🇸 원문 (English)
In the Linux kernel, the following vulnerability has been resolved:
mm: Fix a hmm_range_fault() livelock / starvation problem
If hmm_range_fault() fails a folio_trylock() in do_swap_page,
trying to acquire the lock of a device-private folio for migration,
to ram, the function will spin until it succeeds grabbing the lock.
However, if the process holding the lock is depending on a work
item to be completed, which is scheduled on the same CPU as the
spinning hmm_range_fault(), that work item might be starved and
we end up in a livelock / starvation situation which is never
resolved.
This can happen, for example if the process holding the
device-private folio lock is stuck in
migrate_device_unmap()->lru_add_drain_all()
sinc lru_add_drain_all() requires a short work-item
to be run on all online cpus to complete.
A prerequisite for this to happen is:
a) Both zone device and system memory folios are considered in
migrate_device_unmap(), so that there is a reason to call
lru_add_drain_all() for a system memory folio while a
folio lock is held on a zone device folio.
b) The zone device folio has an initial mapcount > 1 which causes
at least one migration PTE entry insertion to be deferred to
try_to_migrate(), which can happen after the call to
lru_add_drain_all().
c) No or voluntary only preemption.
This all seems pretty unlikely to happen, but indeed is hit by
the "xe_exec_system_allocator" igt test.
Resolve this by waiting for the folio to be unlocked if the
folio_trylock() fails in do_swap_page().
Rename migration_entry_wait_on_locked() to
softleaf_entry_wait_unlock() and update its documentation to
indicate the new use-case.
Future code improvements might consider moving
the lru_add_drain_all() call in migrate_device_unmap() to be
called *after* all pages have migration entries inserted.
That would eliminate also b) above.
v2:
- Instead of a cond_resched() in hmm_range_fault(),
eliminate the problem by waiting for the folio to be unlocked
in do_swap_page() (Alistair Popple, Andrew Morton)
v3:
- Add a stub migration_entry_wait_on_locked() for the
!CONFIG_MIGRATION case. (Kernel Test Robot)
v4:
- Rename migrate_entry_wait_on_locked() to
softleaf_entry_wait_on_locked() and update docs (Alistair Popple)
v5:
- Add a WARN_ON_ONCE() for the !CONFIG_MIGRATION
version of softleaf_entry_wait_on_locked().
- Modify wording around function names in the commit message
(Andrew Morton)
(cherry picked from commit a69d1ab971a624c6f112cea61536569d579c3215)
📍 영향받는 시스템
Linux kernel (패치 적용 전 버전, 특히 xe_exec_system_allocator 테스트 실행 환경)
⚔️ 공격 벡터
직접 공격 벡터 없음. 커널 내부 로직의 교착 상태 버그로 인한 DoS 발생 가능
🛡️ 대응 방법
Linux 커널을 최신 버전으로 업데이트하여 commit a69d1ab971a624c6f112cea61536569d579c3215 패치 포함
🔧 검증 코드
현재 커널 버전 확인 후 패치가 적용된 버전인지 확인. dmesg에서 livelock/starvation 관련 경고 메시지 검색으로 문제 발생 여부 확인.
uname -r | grep -E '^[0-9]+\.[0-9]+' && dmesg | grep -i 'livelock\|starvation' || echo 'Kernel version check complete'