Re: [PATCH kernel RFC 0/2] powerpc/ioda2: An attempt to allow DMA masks between 32 and 59

[Russell Currey]

I'm gonna try and benchmark this on a few different devices for performance, with 64k TCEs (as is), with larger TCE sizes, and against sketchy bypass.  Hopefully if performance isn't too far off, we can get rid of sketchy bypass entirely and have a more robust solution.

-- 
  Russell Currey
  ruscur at russell.cc

On Fri, Apr 12, 2019, at 4:44 PM, Alexey Kardashevskiy wrote:
> 
> This is an attempt to allow DMA mask 40 or similar which are not large
> enough to use either a PHB3 bypass mode or a sketchy bypass.
> 
> This is based on sha1
> 582549e3fbe1 Linus Torvalds Merge tag 'for-linus' of 
> git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma 
> 
> Please comment. Thanks.
> 
> 
> 
> Alexey Kardashevskiy (2):
>   powerpc/powernv/ioda: Allocate TCE table levels on demand for default
>     DMA window
>   powerpc/powernv/ioda2: Create bigger default window with 64k IOMMU
>     pages
> 
>  arch/powerpc/include/asm/iommu.h              |  8 ++-
>  arch/powerpc/platforms/powernv/pci.h          |  2 +-
>  arch/powerpc/kernel/iommu.c                   | 58 +++++++++++++------
>  arch/powerpc/platforms/powernv/pci-ioda-tce.c | 19 +++---
>  arch/powerpc/platforms/powernv/pci-ioda.c     | 14 ++++-
>  5 files changed, 66 insertions(+), 35 deletions(-)
> 
> -- 
> 2.17.1
> 
>