On 2020/5/22 23:49, Catalin Marinas wrote: > On Thu, Apr 23, 2020 at 09:56:53PM +0800, Zhenyu Ye wrote: >> @@ -190,8 +196,8 @@ static inline void flush_tlb_page_nosync(struct vm_area_struct *vma, >> unsigned long addr = __TLBI_VADDR(uaddr, ASID(vma->vm_mm)); >> >> dsb(ishst); >> - __tlbi(vale1is, addr); >> - __tlbi_user(vale1is, addr); >> + __tlbi_level(vale1is, addr, 0); >> + __tlbi_user_level(vale1is, addr, 0); >> } > > This one remains with a level 0 throughout the series. Is this > intentional? If we can't guarantee the level here, better to use the > non-level __tlbi(). > OK, I will change it back to non-level __tlbi(). Thanks, Zhenyu
