[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Xen-devel] [PATCH v6 2/4] x86/hvm: Treat non-instruction fetch nested page faults also as read violations
- To: "Kevin Tian" <kevin.tian@xxxxxxxxx>
- From: "Jan Beulich" <JBeulich@xxxxxxxx>
- Date: Fri, 15 Aug 2014 22:23:47 +0100
- Cc: "ian.campbell@xxxxxxxxxx" <ian.campbell@xxxxxxxxxx>, "stefano.stabellini@xxxxxxxxxxxxx" <stefano.stabellini@xxxxxxxxxxxxx>, Jun Nakajima <jun.nakajima@xxxxxxxxx>, AndrewCooper <andrew.cooper3@xxxxxxxxxx>, "ian.jackson@xxxxxxxxxxxxx" <ian.jackson@xxxxxxxxxxxxx>, "xen-devel@xxxxxxxxxxxxx" <xen-devel@xxxxxxxxxxxxx>, Eddie Dong <eddie.dong@xxxxxxxxx>, "Aravind.Gopalakrishnan@xxxxxxx" <Aravind.Gopalakrishnan@xxxxxxx>, "suravee.suthikulpanit@xxxxxxx" <suravee.suthikulpanit@xxxxxxx>, Tamas Lengyel <tamas.lengyel@xxxxxxxxxxxx>, "boris.ostrovsky@xxxxxxxxxx" <boris.ostrovsky@xxxxxxxxxx>
- Delivery-date: Fri, 15 Aug 2014 21:23:56 +0000
- List-id: Xen developer discussion <xen-devel.lists.xen.org>
>>> On 15.08.14 at 22:17, <kevin.tian@xxxxxxxxx> wrote:
> Though I understand the merit of your overall patch, the discussion
> around r/w violations are not directly related to the optimization
> your patch brings (the real reason is from available GLA info at
> VM-exit). It' just because you code the patch that way, so
> __hvmemul_read purely assumes NPFEC_read_access if not is
> NPFEC_insn_fetch, and then read-modify-write can't enter the
> fast path w/o faking read.
That's right, yes.
> If my understanding is correct, why not just do whatever tricks
> here in nestedhvm_hap_nested_page_fault, while keeping arch
> specific code unchanged?
Because the net effect is the same, and because getting is into
final shape right away rather than having two layers fiddling with
it seems cleaner? Counter question: Why can't the hardware
report true characteristics right away?
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel
|
