[PATCH v2 0/3] iommu: Avoid DMA ops domain refcount contention
john.garry at huawei.com
Thu Sep 20 05:51:40 PDT 2018
On 17/09/2018 12:20, John Garry wrote:
> On 14/09/2018 13:48, Will Deacon wrote:
>> Hi Robin,
> Hi Robin,
> I just spoke with Dongdong and we will test this version also so that we
> may provide a "Tested-by" tag.
I tested this, so for series:
Tested-by: John Garry <john.garry at huawei.com>
>> On Wed, Sep 12, 2018 at 04:24:11PM +0100, Robin Murphy wrote:
>>> John raised the issue that we have some unnecessary refcount
>>> in the DMA ops path which shows scalability problems now that we have
>>> real high-performance hardware using iommu-dma. The x86 IOMMU drivers
>>> sidestepping this by stashing domain references in archdata, but since
>>> that's not very nice for architecture-agnostic code, I think it's
>>> time to
>>> look at a generic API-level solution.
>>> These are a couple of quick patches based on the idea I had back when
>>> first implementing iommu-dma, but didn't have any way to justify at the
>>> time. However, the reports of 10-25% better networking performance on v1
>>> suggest that it's very worthwhile (and far more significant than I ever
>>> would have guessed).
>>> As far as merging goes, I don't mind at all whether this goes via IOMMU,
>>> or via dma-mapping provided Joerg's happy to ack it.
>> I think it makes most sense for Joerg to take this series via his tree.
>> Anyway, I've been running them on my TX2 box and things are happy enough,
>> Tested-by: Will Deacon <will.deacon at arm.com>
> iommu mailing list
> iommu at lists.linux-foundation.org
More information about the linux-arm-kernel