From: Andrii Anisov
Taking decission by `need_iommu_pt_sync()` make us never kicking
`iommu_iotlb_flush()` for IOMMUs which do share TLB with CPU.
So check `has_iommu_pt()` instead.
Signed-off-by: Andrii Anisov
---
Julien,
Could you please look at this, IMO there is a mistake here.
x86 uses
(+ Paul)
Hello,
On 23/01/2019 10:12, Andrii Anisov wrote:
From: Andrii Anisov
Taking decission by `need_iommu_pt_sync()` make us never kicking
s/decission/decision/
`iommu_iotlb_flush()` for IOMMUs which do share TLB with CPU.
I am not aware of platform where we share the TLB with the C
> -Original Message-
> From: Julien Grall [mailto:julien.gr...@arm.com]
> Sent: 23 January 2019 11:34
> To: Andrii Anisov ; xen-
> de...@lists.xenproject.org
> Cc: Stefano Stabellini ; Andrii Anisov
> ; Paul Durrant
> Subject: Re: [RFC] arm/p2m: call iommu iotlb flush if iommu exists and
>
On 23.01.19 13:33, Julien Grall wrote:
Do you mean sharing the P2M?
For sure!
--
Sincerely,
Andrii Anisov.
___
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
Hello Paul,
On 23.01.19 13:45, Paul Durrant wrote:
Yes, this was a mistake when moving from the old macros and need_iommu. Andrii
is correct that need_iommu_pt_sync() is supposed to gate whether an explicit
map/unmap is needed. The need for flush should only depend on has_iommu_pt().
So I fix
> -Original Message-
> From: Andrii Anisov [mailto:andrii.ani...@gmail.com]
> Sent: 23 January 2019 12:40
> To: Paul Durrant ; 'Julien Grall'
> ; xen-devel@lists.xenproject.org
> Cc: Stefano Stabellini ; Andrii Anisov
>
> Subject: Re: [RFC] arm/p2m: call iommu iotlb flush if iommu exists a
