[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Xen-devel] Re: [patch 13/26] Xen-paravirt_ops: Consistently wrap paravirt ops callsites to make them patchable
- To: Jeremy Fitzhardinge <jeremy@xxxxxxxx>
- From: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
- Date: Tue, 20 Mar 2007 08:09:46 -0700 (PDT)
- Cc: Zachary Amsden <zach@xxxxxxxxxx>, xen-devel@xxxxxxxxxxxxxxxxxxx, akpm@xxxxxxxxxxxxxxxxxxxx, virtualization@xxxxxxxxxxxxxx, netdev@xxxxxxxxxxxxxxx, Rusty Russell <rusty@xxxxxxxxxxxxxxx>, linux-kernel@xxxxxxxxxxxxxxx, chrisw@xxxxxxxxxxxx, Andi Kleen <ak@xxxxxx>, "Eric W. Biederman" <ebiederm@xxxxxxxxxxxx>, anthony@xxxxxxxxxxxxx, mingo@xxxxxxx, David Miller <davem@xxxxxxxxxxxxx>
- Delivery-date: Wed, 21 Mar 2007 02:22:16 -0700
- List-id: Xen developer discussion <xen-devel.lists.xensource.com>
On Mon, 19 Mar 2007, Jeremy Fitzhardinge wrote:
>
> Zachary Amsden wrote:
> > For VMI, the default clobber was "cc", and you need a way to allow at
> > least that, because saving and restoring flags is too expensive on x86.
>
> According to lore (Andi, I think), asm() always clobbers cc.
On x86, yes. Practically any instruction will clobber cc anyway, so it's
the default.
Although the gcc guys have occasionally been suggesting we should set it
in our asms.
> Actually, it still does need a temp register. The sequence for cli is:
>
> mov %fs:xen_vcpu, %eax
> movb $1,1(%eax)
We should just do this natively. There's been several tests over the years
saying that it's much more efficient to do sti/cli as a simple store, and
handling the "oops, we got an interrupt while interrupts were disabled" as
a special case.
I have this dim memory that ARM has done it that way for a long time
because it's so expensive to do a "real" cli/sti.
And I think -rt does it for other reasons. It's just more flexible.
Linus
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel
|
