Re: [PATCH v4 0/5] KVM: x86: flush tlb out of mmu-lock after write protection

[Hu Yaohui]

Hi Guangrong,
Thanks a lot!
I will reopen a new discussion next time.
Does that means once the level 1 guest page table entry is modified,
the host should make a decision in page fault handler whether the page
sync or unsync?
My question is that since all level 1 guest page tables are writable,
when the entry in the page table is modified. there is no page fault
will happen, how can the mmu_need_write_protect to be called to make
whether sync or unsync decision?
Thanks for your time!

Best Wishes,
Yaohui

On Wed, Mar 26, 2014 at 1:07 AM, Xiao Guangrong
<xiaoguangrong@xxxxxxxxxxxxxxxxxx> wrote:
> On 03/26/2014 12:40 PM, Hu Yaohui wrote:
>> Hi all,
>> I hope you have a good day!
>> I have debugged the code myself. I have called dump_stack() in
>> function "__kvm_unsync_page"
>> and function "invlpg".  Actually every time before invlpg is called,
>> the page fault handled will call "__kvm_unsync_page" before invlpg to
>> mark the specified sp as unsynced. (correct me if I am wrong). I am
>> wondering why there is a page fault. AFAIK when calling flush_tlb_page
>> in the guest os. it will issue invlpg instruction directly, I did not
>> see any operation which could always cause the page fault.I would
>> really appreciate if if someone could shed me some lights on it.
>> Thanks for your time!
>
> Page fault is used to map a page into guest and set the proper permission
> on for it so this is the right place to make decision if the page need be
> writable.
>
> Tlb flush is used when guest wants to have a clean tlb so that host syncs the
> unsync page tables when it is happing.
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/