Messages in this thread | | | Date | Fri, 24 Aug 2012 16:15:17 +0800 | From | Alex Shi <> | Subject | Re: apparent regressions from TLB range flushing page set |
| |
On 08/22/2012 09:22 PM, Jan Beulich wrote:
>>>> On 22.08.12 at 10:54, Alex Shi <alex.shi@intel.com> wrote: >> On 08/22/2012 03:39 PM, Jan Beulich wrote: >> >>>>>> Alex Shi <alex.shi@intel.com> 08/22/12 5:24 AM >>> >>>> On 08/20/2012 10:12 PM, Jan Beulich wrote: >>>> I was thought you have 'Agreed' for xen part code. :) >>> >>> I had agreed to it being done the right way, and I had pointed out the >>> problem once. I can't say for sure that I looked at the most recent rev >>> closely enough to spot the issue still being unfixed. >>> >>>>> For one, while TLB_FLUSH_ALL gets passed as 'end' argument to >>>>> flush_tlb_others(), the Xen code was made to check its 'start' >>>>> parameter. >>>> >>>> Do you mean need the following change? --untested. >>> >>> Yes. I'd question though whether for that special case it shouldn't be >>> start _and_ end to get passed the special value. >> >> >> Actually the special value is already there in old code. >> so, what's your meaning of the question? > > I'm saying that I'd rather see > > #define flush_tlb_mm(mm) flush_tlb_mm_range(mm, TLB_FLUSH_ALL, TLB_FLUSH_ALL, 0UL)
It bring logical confusing, and is no much help. flush_tlb_mm_range still will call: flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
So, since we already fix code error, we'd better not to do this change.
>
> Jan >
| |