Re: [Xen-devel] [PATCH 1/6] x86: move invocations of hvm_flush_guest_tlbs()

["Jan Beulich" <JBeulich@xxxxxxxx>]

>>> On 19.01.18 at 18:29, <dunlapg@xxxxxxxxx> wrote:
> On Fri, Jan 19, 2018 at 4:02 PM, Jan Beulich <JBeulich@xxxxxxxx> wrote:
>> Their need is not tied to the actual flushing of TLBs, but the ticking
>> of the TLB clock. Make this more obvious by folding the two invocations
>> into a single one in pre_flush().
> 
> So now pre_flush() actually does the flush?
> 
> I don't object to the change per se (and from what I can tell it's
> technically correct), but I think you're making things any clearer.

Did you mean "I don't think"?

hvm_flush_guest_tlbs(), despite its name, does not actually do any
flushing. It is a simple wrapper around hvm_asid_flush_core(),
which only increments the ASID generation counter. I very much
view this as something that at least equally well can be done in
pre_flush().

Jan


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel