On Mon, May 06, 2019 at 07:52:03PM +0100, Tom Murphy via iommu wrote:
> We can remove the mutex lock from amd_iommu_map and amd_iommu_unmap.
> iommu_map doesn’t lock while mapping and so no two calls should touch
> the same iova range. The AMD driver already handles the page table page
>
On Wed 15 May 23:47 PDT 2019, Vivek Gautam wrote:
> On Thu, May 16, 2019 at 5:03 AM Bjorn Andersson
> wrote:
> >
> > Describe the memory related to page table walks as non-cachable for iommu
> > instances that are not DMA coherent.
> >
> > Signed-off-by: Bjorn Andersson
> > ---
> >
On Tue, Jun 4, 2019 at 11:11 AM Robin Murphy wrote:
>
> On 06/05/2019 19:52, Tom Murphy wrote:
> > Add a gfp_t parameter to the iommu_ops::map function.
> > Remove the needless locking in the AMD iommu driver.
> >
> > The iommu_ops::map function (or the iommu_map function which calls it)
> > was
On Tue, Jun 4, 2019 at 7:11 PM Robin Murphy wrote:
>
> On 06/05/2019 19:52, Tom Murphy wrote:
> > Add a gfp_t parameter to the iommu_ops::map function.
> > Remove the needless locking in the AMD iommu driver.
> >
> > The iommu_ops::map function (or the iommu_map function which calls it)
> > was
On 06/05/2019 19:52, Tom Murphy wrote:
Add a gfp_t parameter to the iommu_ops::map function.
Remove the needless locking in the AMD iommu driver.
The iommu_ops::map function (or the iommu_map function which calls it)
was always supposed to be sleepable (according to Joerg's comment in
this
Hi Alex,
On 6/4/19 12:31 AM, Alex Williamson wrote:
> On Sun, 26 May 2019 18:10:03 +0200
> Eric Auger wrote:
>
>> Add a new VFIO_PCI_DMA_FAULT_IRQ_INDEX index. This allows to
>> set/unset an eventfd that will be triggered when DMA translation
>> faults are detected at physical level when the
Hi Alex,
On 6/4/19 12:31 AM, Alex Williamson wrote:
> On Sun, 26 May 2019 18:10:01 +0200
> Eric Auger wrote:
>
>> This patch registers a fault handler which records faults in
>> a circular buffer and then signals an eventfd. This buffer is
>> exposed within the fault region.
>>
>>
On Tue, 4 Jun 2019 11:52:18 +0100
Jean-Philippe Brucker wrote:
> On 03/06/2019 23:32, Alex Williamson wrote:
> > It doesn't seem to make much sense to include this patch without
> > also including "iommu: handle page response timeout". Was that one
> > lost? Dropped? Lives elsewhere?
>
>
On Mon, 3 Jun 2019 16:31:45 -0600
Alex Williamson wrote:
> On Sun, 26 May 2019 18:09:39 +0200
> Eric Auger wrote:
>
> > From: Jean-Philippe Brucker
> >
> > Some IOMMU hardware features, for example PCI's PRI and Arm SMMU's
> > Stall, enable recoverable I/O page faults. Allow IOMMU drivers to
On 04/06/2019 07:05, Christoph Hellwig wrote:
> On Mon, Jun 03, 2019 at 08:47:57PM +0100, Jon Hunter wrote:
>> Since next-20190529 one of our tests for MMC has started failing, where
>> the symptom is that the data written to the MMC does not match the
>> source. Bisecting this is pointing to
On 03/06/2019 23:32, Alex Williamson wrote:
> It doesn't seem to make much sense to include this patch without also
> including "iommu: handle page response timeout". Was that one lost?
> Dropped? Lives elsewhere?
The first 7 patches come from my sva/api branch, where I had forgotten
to add the
On Mon, 3 Jun 2019 09:16:18 +0800
Lu Baolu wrote:
> +TRACE_EVENT(bounce_unmap_single,
> + TP_PROTO(struct device *dev, dma_addr_t dev_addr, size_t size),
> +
> + TP_ARGS(dev, dev_addr, size),
> +
> + TP_STRUCT__entry(
> + __string(dev_name, dev_name(dev))
> +
The arm architecture had a VM_ARM_DMA_CONSISTENT flag to mark DMA
coherent remapping for a while. Lift this flag to common code so
that we can use it generically. We also check it in the only place
VM_USERMAP is directly check so that we can entirely replace that
flag as well (although I'm not
A helper to find the backing page array based on a virtual address.
This also ensures we do the same vm_flags check everywhere instead
of slightly different or missing ones in a few places.
Signed-off-by: Christoph Hellwig
---
arch/arm/mm/dma-mapping.c | 7 +--
drivers/iommu/dma-iommu.c
Currently the generic dma remap allocator gets a vm_flags passed by
the caller that is a little confusing. We just introduced a generic
vmalloc-level flag to identify the dma coherent allocations, so use
that everywhere and remove the now pointless argument.
Signed-off-by: Christoph Hellwig
---
Hi all,
the common DMA remapping code uses the vmalloc/vmap code to create
page table entries for DMA mappings. This series lifts the currently
arm specific VM_* flag for that into common code, and also exposes
it to userspace in procfs to better understand the mappings, and cleans
up a couple
On Mon, Jun 03, 2019 at 08:47:57PM +0100, Jon Hunter wrote:
> Since next-20190529 one of our tests for MMC has started failing, where
> the symptom is that the data written to the MMC does not match the
> source. Bisecting this is pointing to this commit. Unfortunately, I am
> not able to cleanly
17 matches
Mail list logo
