On 2015/6/18 18:07, Tim Deegan wrote:
At 14:13 +0800 on 12 Jun (1434118407), Chen, Tiejun wrote:
could you explain why existing guest_physmap_remove_page can't
serve the purpose so you need invent a new identity mapping
specific one? For unmapping suppose it should be common regardless
of whethe
At 14:13 +0800 on 12 Jun (1434118407), Chen, Tiejun wrote:
> > could you explain why existing guest_physmap_remove_page can't
> > serve the purpose so you need invent a new identity mapping
> > specific one? For unmapping suppose it should be common regardless
> > of whether it's identity-mapped or
On 2015/6/17 18:03, Jan Beulich wrote:
On 11.06.15 at 03:15, wrote:
--- a/xen/arch/x86/mm/p2m.c
+++ b/xen/arch/x86/mm/p2m.c
@@ -927,10 +927,16 @@ int set_identity_p2m_entry(struct domain *d, unsigned
long gfn,
}
gfn_unlock(p2m, gfn, 0);
-return ret;
}
+el
>>> On 11.06.15 at 03:15, wrote:
> --- a/xen/arch/x86/mm/p2m.c
> +++ b/xen/arch/x86/mm/p2m.c
> @@ -927,10 +927,16 @@ int set_identity_p2m_entry(struct domain *d, unsigned
> long gfn,
> }
>
> gfn_unlock(p2m, gfn, 0);
> -return ret;
> }
> +else
> +ret =
On 2015/6/12 13:59, Tian, Kevin wrote:
From: Chen, Tiejun
Sent: Friday, June 12, 2015 1:58 PM
On 2015/6/12 10:43, Chen, Tiejun wrote:
On 2015/6/11 22:07, Tim Deegan wrote:
At 17:31 +0800 on 11 Jun (1434043916), Chen, Tiejun wrote:
while ( base_pfn < end_pfn )
{
-int er
> From: Chen, Tiejun
> Sent: Friday, June 12, 2015 1:58 PM
>
> On 2015/6/12 10:43, Chen, Tiejun wrote:
> > On 2015/6/11 22:07, Tim Deegan wrote:
> >> At 17:31 +0800 on 11 Jun (1434043916), Chen, Tiejun wrote:
> >while ( base_pfn < end_pfn )
> >{
> > -int err = i
On 2015/6/12 10:43, Chen, Tiejun wrote:
On 2015/6/11 22:07, Tim Deegan wrote:
At 17:31 +0800 on 11 Jun (1434043916), Chen, Tiejun wrote:
while ( base_pfn < end_pfn )
{
-int err = intel_iommu_map_page(d, base_pfn, base_pfn,
-
IOMMUF_readable|IOMMUF_writable);
+int e
On 2015/6/11 22:07, Tim Deegan wrote:
At 17:31 +0800 on 11 Jun (1434043916), Chen, Tiejun wrote:
while ( base_pfn < end_pfn )
{
-int err = intel_iommu_map_page(d, base_pfn, base_pfn,
- IOMMUF_readable|IOMMUF_writable);
+int err
At 17:31 +0800 on 11 Jun (1434043916), Chen, Tiejun wrote:
> >> while ( base_pfn < end_pfn )
> >> {
> >> -int err = intel_iommu_map_page(d, base_pfn, base_pfn,
> >> - IOMMUF_readable|IOMMUF_writable);
> >> +int err = set_identity_p2m
On 2015/6/11 17:14, Tian, Kevin wrote:
From: Chen, Tiejun
Sent: Thursday, June 11, 2015 9:15 AM
RMRR reserved regions must be setup in the pfn space with an identity
mapping to reported mfn. However existing code has problem to setup
correct mapping when VT-d shares EPT page table, so lead to pr
> From: Chen, Tiejun
> Sent: Thursday, June 11, 2015 9:15 AM
>
> RMRR reserved regions must be setup in the pfn space with an identity
> mapping to reported mfn. However existing code has problem to setup
> correct mapping when VT-d shares EPT page table, so lead to problem
> when assigning device
RMRR reserved regions must be setup in the pfn space with an identity
mapping to reported mfn. However existing code has problem to setup
correct mapping when VT-d shares EPT page table, so lead to problem
when assigning devices (e.g GPU) with RMRR reported. So instead, this
patch aims to setup ide
12 matches
Mail list logo
