lkml.org 
[lkml]   [2023]   [Feb]   [7]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
SubjectRe: [PATCH] iommu/vt-d: Avoid superfluous IOTLB tracking in lazy mode
From
On 2023/2/6 19:20, Robin Murphy wrote:
> On 2023-02-04 06:32, Baolu Lu wrote:
>> On 2023/2/4 7:04, Jacob Pan wrote:
>>> Intel IOMMU driver implements IOTLB flush queue with domain selective
>>> or PASID selective invalidations. In this case there's no need to track
>>> IOVA page range and sync IOTLBs, which may cause significant performance
>>> hit.
>>
>> [Add cc Robin]
>>
>> If I understand this patch correctly, this might be caused by below
>> helper:
>>
>> /**
>>   * iommu_iotlb_gather_add_page - Gather for page-based TLB invalidation
>>   * @domain: IOMMU domain to be invalidated
>>   * @gather: TLB gather data
>>   * @iova: start of page to invalidate
>>   * @size: size of page to invalidate
>>   *
>>   * Helper for IOMMU drivers to build invalidation commands based on
>> individual
>>   * pages, or with page size/table level hints which cannot be
>> gathered if they
>>   * differ.
>>   */
>> static inline void iommu_iotlb_gather_add_page(struct iommu_domain
>> *domain,
>>                                                 struct
>> iommu_iotlb_gather *gather,
>>                                                 unsigned long iova,
>> size_t size)
>> {
>>          /*
>>           * If the new page is disjoint from the current range or is
>> mapped at
>>           * a different granularity, then sync the TLB so that the gather
>>           * structure can be rewritten.
>>           */
>>          if ((gather->pgsize && gather->pgsize != size) ||
>>              iommu_iotlb_gather_is_disjoint(gather, iova, size))
>>                  iommu_iotlb_sync(domain, gather);
>>
>>          gather->pgsize = size;
>>          iommu_iotlb_gather_add_range(gather, iova, size);
>> }
>>
>> As the comments for iommu_iotlb_gather_is_disjoint() says,
>>
>> "...For many IOMMUs, flushing the IOMMU in this case is better
>>   than merging the two, which might lead to unnecessary invalidations.
>>   ..."
>>
>> So, perhaps the right fix for this performance issue is to add
>>
>>      if (!gather->queued)
>>
>> in iommu_iotlb_gather_add_page() or iommu_iotlb_gather_is_disjoint()?
>> It should benefit other arch's as well.
>
> The iotlb_gather helpers are really just that - little tools to help
> drivers with various common iotlb_gather accounting patterns. The
> decision whether to bother with that accounting at all should really
> come beforehand, and whether a driver supports flush queues is
> orthogonal to whether it uses any particular gather helper(s) or not, so
> I think the patch as-is is correct.

Okay, that's fine. Thanks for the explanation.

>
>>> This patch adds a check to avoid IOVA gather page and IOTLB sync for
>>> the lazy path.
>>>
>>> The performance difference on Sapphire Rapids 100Gb NIC is improved by
>>> the following (as measured by iperf send):
>>
>> Which test case have you done? Post the real data if you have any.
>>
>>>
>>> w/o this fix~48 Gbits/s. with this fix ~54 Gbits/s
>>>
>>> Cc: <stable@vger.kernel.org>
>>
>> Again, add a Fixes tag so that people know how far this fix should be
>> back ported.
>
> Note that the overall issue probably dates back to the initial iommu-dma
> conversion, but if you think it's important enough to go back beyond
> 5.15 when gather->queued was introduced, that'll need a different fix.

So perhaps

Cc: stable@vger.kernel.org # 5.15+

is enough?

Best regards,
baolu

\
 
 \ /
  Last update: 2023-03-27 00:12    [W:0.102 / U:0.080 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site