Re: [PATCH v3 07/33] nds32: MMU initialization

[Greentime Hu]

Hi, Guo Ren:

2017-12-18 20:22 GMT+08:00 Guo Ren <ren_guo@xxxxxxxxx>:
> On Mon, Dec 18, 2017 at 07:21:30PM +0800, Greentime Hu wrote:
>> Hi, Guo Ren:
>>
>> 2017-12-18 17:08 GMT+08:00 Guo Ren <ren_guo@xxxxxxxxx>:
>> > Hi Greentime,
>> >
>> > On Fri, Dec 08, 2017 at 05:11:50PM +0800, Greentime Hu wrote:
>> > [...]
>> >>
>> >> diff --git a/arch/nds32/mm/highmem.c b/arch/nds32/mm/highmem.c
>> > [...]
>> >> +void *kmap(struct page *page)
>> >> +{
>> >> +     unsigned long vaddr;
>> >> +     might_sleep();
>> >> +     if (!PageHighMem(page))
>> >> +             return page_address(page);
>> >> +     vaddr = (unsigned long)kmap_high(page);
>> > Here should invalid the cpu_mmu_tlb's entry, Or invalid it in the
>> > set_pte().
>> >
>> > eg:
>> > vaddr0 = kmap(page0)
>> > *vaddr0 = val0 //It will cause tlb-miss, and hard-refill to MMU-tlb
>> > kunmap(page0)
>> > vaddr1 = kmap(page1) // Mostly vaddr1 = vaddr0
>> > val = vaddr1; //No tlb-miss and it will get page0's val not page1, because
>> >                 last expired vaddr0's entry is left in CPU-MMU-tlb.
>> >
>>
>> Thanks.
>> I will add __nds32__tlbop_inv(vaddr); to invalidate this mapping
>> before retrun vaddr.
>
> Sorry, perhaps I'm wrong. See
> kmap->kmap_high->map_new_virtual->get_next_pkmap_nr(color).
>
> Seems pkmap will return the vaddr by vaddr + 1 until
> no_more_pkmaps(), and then flush_all_zero_pkmaps.
> Just kmap_atomic need it, and you've done.

Thanks for double checking this case. :)
As you said, it will flush tlb in the generic code flow.