On Fri, Jun 24, 2016 at 06:13:14AM -0700, Nadav Amit wrote:
> According to the manual: "Hardware access to ... invalidation queue ...
> are always coherent."
>
> Remove unnecassary clflushes accordingly.
>
> Signed-off-by: Nadav Amit
Applied, thanks.
On 05/07/2016 18:50, Nadav Amit wrote:
> Paolo Bonzini wrote:
>
>>
>>
>> On 05/07/2016 18:27, Nadav Amit wrote:
Although such hardware is old, there are some hypervisors that do not set
the ecap.coherency of emulated IOMMUs. Yes, it is unwise, but there is no
Paolo Bonzini wrote:
>
>
> On 05/07/2016 18:27, Nadav Amit wrote:
>>> Although such hardware is old, there are some hypervisors that do not set
>>> the ecap.coherency of emulated IOMMUs. Yes, it is unwise, but there is no
>>> reason to further punish these hypervisors.
>
On 05/07/2016 18:27, Nadav Amit wrote:
>> Although such hardware is old, there are some hypervisors that do not set
>> the ecap.coherency of emulated IOMMUs. Yes, it is unwise, but there is no
>> reason to further punish these hypervisors.
QEMU will need the kernel to respect ecap.coherency in
Nadav Amit wrote:
> Joerg Roedel wrote:
>
>> On Fri, Jun 24, 2016 at 06:13:14AM -0700, Nadav Amit wrote:
>>> According to the manual: "Hardware access to ... invalidation queue ...
>>> are always coherent."
>>>
>>> Remove unnecassary clflushes
Joerg Roedel wrote:
> On Fri, Jun 24, 2016 at 06:13:14AM -0700, Nadav Amit wrote:
>> According to the manual: "Hardware access to ... invalidation queue ...
>> are always coherent."
>>
>> Remove unnecassary clflushes accordingly.
>
> It is one thing what the spec says and
On Fri, Jun 24, 2016 at 06:13:14AM -0700, Nadav Amit wrote:
> According to the manual: "Hardware access to ... invalidation queue ...
> are always coherent."
>
> Remove unnecassary clflushes accordingly.
It is one thing what the spec says and another how hardware really
behaves. Have you tested
According to the manual: "Hardware access to ... invalidation queue ...
are always coherent."
Remove unnecassary clflushes accordingly.
Signed-off-by: Nadav Amit
---
Build-tested since I do not have an IOMMU that does not support
coherency.
---
drivers/iommu/dmar.c | 5