| |
|
 |
|
 |
|
|
|
| |
|
|
xen-devel
[Xen-devel] Re: [RFC] fix xen_in_range()
|
To: |
"Keir Fraser" <keir.fraser@xxxxxxxxxxxxx> |
|
Subject: |
[Xen-devel] Re: [RFC] fix xen_in_range() |
|
From: |
"Jan Beulich" <jbeulich@xxxxxxxxxx> |
|
Date: |
Thu, 23 Apr 2009 08:58:12 +0100 |
|
Cc: |
Yunhong Jiang <yunhong.jiang@xxxxxxxxx>, Dexuan Cui <dexuan.cui@xxxxxxxxx>, Shane Wang <shane.wang@xxxxxxxxx>, Joseph Cihula <joseph.cihula@xxxxxxxxx>, Xiaowei Yang <xiaowei.yang@xxxxxxxxx>, Liping Ke <liping.ke@xxxxxxxxx>, "xen-devel@xxxxxxxxxxxxxxxxxxx" <xen-devel@xxxxxxxxxxxxxxxxxxx>, Xin Li <xin.li@xxxxxxxxx> |
|
Delivery-date: |
Thu, 23 Apr 2009 00:57:06 -0700 |
|
Envelope-to: |
www-data@xxxxxxxxxxxxxxxxxxx |
|
In-reply-to: |
<C615D676.947F%keir.fraser@xxxxxxxxxxxxx> |
|
List-help: |
<mailto:xen-devel-request@lists.xensource.com?subject=help> |
|
List-id: |
Xen developer discussion <xen-devel.lists.xensource.com> |
|
List-post: |
<mailto:xen-devel@lists.xensource.com> |
|
List-subscribe: |
<http://lists.xensource.com/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=subscribe> |
|
List-unsubscribe: |
<http://lists.xensource.com/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe> |
|
References: |
<4F65016F6CB04E49BFFA15D4F7B798D9988CF1A3@xxxxxxxxxxxxxxxxxxxxxxxxxxxx> <C615D676.947F%keir.fraser@xxxxxxxxxxxxx> |
|
Sender: |
xen-devel-bounces@xxxxxxxxxxxxxxxxxxx |
>>> Keir Fraser <keir.fraser@xxxxxxxxxxxxx> 23.04.09 09:25 >>>
>On 23/04/2009 00:53, "Cihula, Joseph" <joseph.cihula@xxxxxxxxx> wrote:
>
>> Unfortunately, the frametable is only contiguous in the virtual address
>> space,
>> so one can't simply take __pa() of its start and end. And since it is quite
>> large, iterating through each page to gets its phys addr adds a perceptible
>> delay when that check has to be done for each page of physical memory (as is
>> the case in the only caller, the VT-d routine that maps memory for dom0).
>> But
>> it also appears that we can't convert the phys addr arguments into their virt
>> addrs to compare with the contiguous frametable range because they will
>> convert to the DIRECTMAP va's instead.
>
>The frametable is allocated in aligned 2MB chunks. So you can check at that
>granularity rather than 4kB.
... and perhaps allocation should be attempted in 1Gb chunks when the table
size is getting close to or exceeding 1Gb (and 1Gb-pages are supported). Or,
since the space mapped is larger than the space allocated anyway, the
condition might be just that of 1Gb-pages being supported (provided a 1Gb-
aligned chunk can be allocated).
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel
|
|
|
| |
|
Home