On Tue, 10 Oct 2017 15:40:54 +0200
Joerg Roedel wrote:
> On Thu, Oct 05, 2017 at 04:03:38PM -0700, Jacob Pan wrote:
> > Traditionally, device specific faults are detected and handled
> > within their own device drivers. When IOMMU is enabled, faults such
> > as DMA related
On Wed, Oct 11, 2017 at 4:54 AM, Joerg Roedel wrote:
> On Tue, Oct 10, 2017 at 07:50:12AM -0700, Dan Williams wrote:
>> +static void ib_umem_lease_break(void *__umem)
>> +{
>> + struct ib_umem *umem = umem;
>> + struct ib_device *idev = umem->context->device;
>> +
On Wed, Oct 11, 2017 at 4:16 PM, Robin Murphy wrote:
> On 11/10/17 14:59, Arnd Bergmann wrote:
>
> That said, I think the third option is now viable as well, namely to
> shuffle some lines and get rid of the almost-duplicated ops entirely.
> I'll have a quick go at that
On 11/10/17 14:59, Arnd Bergmann wrote:
> There are two sets of iommu_ops in this driver, and only
> one of them contains a reference to the ipmmu_iotlb_sync
> function. This leads to a compiler warning when these
> operations are not in use:
>
> drivers/iommu/ipmmu-vmsa.c:622:13: error:
On Wed, Oct 11, 2017 at 12:43 AM, Jan Kara wrote:
> On Tue 10-10-17 07:49:01, Dan Williams wrote:
>> The mmap(2) syscall suffers from the ABI anti-pattern of not validating
>> unknown flags. However, proposals like MAP_SYNC and MAP_DIRECT need a
>> mechanism to define new behavior
There are two sets of iommu_ops in this driver, and only
one of them contains a reference to the ipmmu_iotlb_sync
function. This leads to a compiler warning when these
operations are not in use:
drivers/iommu/ipmmu-vmsa.c:622:13: error: 'ipmmu_iotlb_sync' defined but not
used
xHCI requires that data buffers do not cross 64KB boundaries (and are
thus at most 64KB long as well) - whilst xhci_queue_{bulk,isoc}_tx()
already split their input buffers into individual TRBs as necessary,
it's still a good idea to advertise the limitations via the standard DMA
API mechanism, so
On 11/10/17 13:15, Joerg Roedel wrote:
> On Wed, Oct 11, 2017 at 11:54:52AM +, Liu, Yi L wrote:
>> I didn't quite get 'iovm' mean. Can you explain a bit about the idea?
>
> It's short for IO Virtual Memory, basically a replacement term for 'svm'
> that is not ambiguous (afaik) and not
On Wed, Oct 11, 2017 at 11:54:52AM +, Liu, Yi L wrote:
> I didn't quite get 'iovm' mean. Can you explain a bit about the idea?
It's short for IO Virtual Memory, basically a replacement term for 'svm'
that is not ambiguous (afaik) and not specific to Intel.
Joerg
> On Wed, Oct 11, 2017 at 07:54:32AM +, Liu, Yi L wrote:
> > I agree that iommu_invalidate() is too generic. Additionally, also
> > better to avoid making it svm specific.
>
> I also don't like to name the functions after the Intel feature, but I failed
> to come up
> with a better
On Tue, Oct 10, 2017 at 07:50:12AM -0700, Dan Williams wrote:
> +static void ib_umem_lease_break(void *__umem)
> +{
> + struct ib_umem *umem = umem;
> + struct ib_device *idev = umem->context->device;
> + struct device *dev = idev->dma_device;
> + struct scatterlist *sgl =
Hi Will,
Any further comments on this series, please?
We do have the ack from all relevant people for the "[PATCH v9 4/4] PCI: hisi:
blacklist
hip06/hip07 controllers behind SMMUv3" now.
Really appreciate if you can take a look and let us know.
Many thanks,
Shameer
> -Original
Hi Jean-Philipe,
Thanks for your patches, this is definitly a step in the right direction
to get generic support for IO virtual memory into the IOMMU core code.
But I see an issue with the design around task_struct, please see
below.
On Fri, Oct 06, 2017 at 02:31:32PM +0100, Jean-Philippe
On Wed, Oct 11, 2017 at 07:54:32AM +, Liu, Yi L wrote:
> I agree that iommu_invalidate() is too generic. Additionally, also
> better to avoid making it svm specific.
I also don't like to name the functions after the Intel feature, but I
failed to come up with a better alternative so far. The
On 10/10/17 22:42, Jacob Pan wrote:
[...]
>>> +/**
>>> + * PASID table data used to bind guest PASID table to the host
>>> IOMMU. This will
>>> + * enable guest managed first level page tables.
>>> + * @version: for future extensions and identification of the data
>>> format
>>> + * @bytes: size
On Tue 10-10-17 07:49:01, Dan Williams wrote:
> The mmap(2) syscall suffers from the ABI anti-pattern of not validating
> unknown flags. However, proposals like MAP_SYNC and MAP_DIRECT need a
> mechanism to define new behavior that is known to fail on older kernels
> without the support. Define a
> On Tue, 10 Oct 2017 15:35:42 +0200
> Joerg Roedel wrote:
>
> > On Thu, Oct 05, 2017 at 04:03:31PM -0700, Jacob Pan wrote:
> > > +int iommu_invalidate(struct iommu_domain *domain,
> > > + struct device *dev, struct tlb_invalidate_info
> > > *inv_info)
> >
> > This name
On Wed, Oct 11, 2017 at 07:49:05AM +0200, Marek Szyprowski wrote:
> Could you also apply it to v4.14-fixes, or is it too late for that?
Well, I already pushed it out, but I guess I can still move the patch to
another branch.
Joerg
___
iommu
18 matches
Mail list logo