[Xen-devel] RE: [RFC] [PATCH] Dom0: Don't switch back to user space stack in syscall entry

["Jiang, Yunhong" <yunhong.jiang@xxxxxxxxx>]

>-----Original Message-----
>From: Jan Beulich [mailto:JBeulich@xxxxxxxxxx]
>Sent: Thursday, February 11, 2010 4:54 PM
>To: Jeremy Fitzhardinge; Jiang, Yunhong
>Cc: Keir Fraser; xen-devel@xxxxxxxxxxxxxxxxxxx
>Subject: Re: [RFC] [PATCH] Dom0: Don't switch back to user space stack in 
>syscall
>entry
>
>>>> Jeremy Fitzhardinge <jeremy@xxxxxxxx> 10.02.10 19:13 >>>
>>> b) Add IST support to xen hypervisor, Considering the ptrace issue in
>http://lists.xensource.com/archives/html/xen-devel/2009-05/msg00200.html and
>also Ingo's comments in
>http://lkml.indiana.edu/hypermail/linux/kernel/0905.1/00087.html, maybe it 
>still
>have value to add such support. But not sure if that is accepetable for xen
>hypervisor.
>>>
>>
>>That would depend on Keir's thoughts, which I would guess depend on what
>>the patch and ABI would look like.  It's certainly the most general
>>solution if it can be done in a reasonable way.
>
>But if at all, I'd recommend considering a properly nesting solution
>rather than just to mimic hardware behavior (since there's no IDT,
>functionality needs to differ from native anyway).

Are there any issue currently for nesting interrupt? The issue here is because 
of the syscall's stack, which is not strictly related to nesting interrupt, I 
think.

--jyh

>
>Jan


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel