On Thu, Mar 08, 2007 at 03:14:38PM +0900, [EMAIL PROTECTED] wrote:
+
guest_physmap_remove_page(d, gpfn, mfn);
+
+/* post-set PGC_allocated flag */
+do {
+x = mfn_to_page(mfn)-count_info;
+if ((x PGC_count_mask) ==
You (yamahata) said:
+
guest_physmap_remove_page(d, gpfn, mfn);
+
+/* post-set PGC_allocated flag */
+do {
+x = mfn_to_page(mfn)-count_info;
+if ((x PGC_count_mask) == 0)
+goto out;
+
On Thu, Mar 08, 2007 at 05:54:07PM +0900, [EMAIL PROTECTED] wrote:
You (yamahata) said:
+
guest_physmap_remove_page(d, gpfn, mfn);
+
+/* post-set PGC_allocated flag */
+do {
+x = mfn_to_page(mfn)-count_info;
+if
You (yamahata) said:
Probably it should looks like the following.
if (page-count_info != 1) { /* no one but us is using this page */
put_page(page);
goto out;
}
__set_bit(page-count_info, _PGC_allocated);
Does `page-count_info' have to be operated with atomic ?
Atomic
Hi,
is there a simple way to map a bigger part or all of the domU memory into dom0
driver address space?
I'am looking for a function like xc_map_foreign_range() in libxc just for
drivers.
Thanks.
Dietmar.
___
Xen-ia64-devel mailing list
Hi, Alex
Thank you for various comments. It helps many
I will post a patch tomorrow, now testing.
Anyway I reply it in inline.
Why do we have to do these one at a time, instead of in bulk. Seems
very inefficient. Also, please explain the local_irq_enable/disable at
the end of each.
I
Hi all,
I've modified it, so submit the patch.
[EMAIL PROTECTED] wrote:
You (yamahata) said:
Probably it should looks like the following.
if (page-count_info != 1) { /* no one but us is using this page */
put_page(page);
goto out;
}
__set_bit(page-count_info, _PGC_allocated);
On Thu, Mar 08, 2007 at 12:31:34PM +0100, Dietmar Hahn wrote:
Hi,
is there a simple way to map a bigger part or all of the domU memory into
dom0 driver address space?
I'am looking for a function like xc_map_foreign_range() in libxc just for
drivers.
Thanks.
1. allocate pseudo physical
Am Donnerstag, 8. März 2007 12:56 schrieb Isaku Yamahata:
1. allocate pseudo physical address range by xen_ia64_alloate_resource.
2. then use HYPERVISOR_add_physmap_with_gmfn().
3. use xen_ia64_unmap_resource() to unmap.
Really cool stuff, it is running like a charm!
This is ia64 specific
On Mon, 2007-03-05 at 12:35 +0900, Isaku Yamahata wrote:
Here is the work around patch. I was able to boot dom0 with this patch.
The right fix is to modify memory_exchange() to be aware of
ia64 page reference count convention, and convince x86 developper.
Since It may take a while, I sent
On Thu, 2007-03-08 at 20:52 +0900, Atsushi SAKAI wrote:
Hi, Alex
Thank you for various comments. It helps many
I will post a patch tomorrow, now testing.
I went ahead and applied the first 2 patches and the vcpu_op part of
this patch to fix a build failure with the latest merge of
Hi,
I report a benchmark result of this week on IPF using
xen-ia64-unstable.
I did not test a VT-i domain because linking PV-on-HVM drivers still
failed.
In LTP, test cases related with direct IO still failed.
# dio02 dio03 dio06 dio08 dio09 dio12 dio14 dio15 dio17 dio18 dio19
# dio21 dio22
12 matches
Mail list logo
