Re: [PATCH v2 2/5] x86: enable DMA CMA with swiotlb

[Konrad Rzeszutek Wilk <konrad.wilk-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>]

On Fri, Jan 17, 2014 at 08:32:09AM +0900, Akinobu Mita wrote:
> 2014/1/16 Konrad Rzeszutek Wilk <konrad.wilk-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>:
> > On Tue, Jan 14, 2014 at 11:13:47PM +0900, Akinobu Mita wrote:
> >> The DMA Contiguous Memory Allocator support on x86 is disabled when
> >> swiotlb config option is enabled.  So DMA CMA is always disabled on
> >> x86_64 because swiotlb is always enabled.  This attempts to support
> >> for DMA CMA with enabling swiotlb config option.
> >>
> >> The contiguous memory allocator on x86 is integrated in the function
> >> dma_generic_alloc_coherent() which is .alloc callback in nommu_dma_ops
> >> for dma_alloc_coherent().
> >>
> >> x86_swiotlb_alloc_coherent() which is .alloc callback in swiotlb_dma_ops
> >> tries to allocate with dma_generic_alloc_coherent() firstly and then
> >> swiotlb_alloc_coherent() is called as a fallback.
> >>
> >> The main part of supporting DMA CMA with swiotlb is that changing
> >> x86_swiotlb_free_coherent() which is .free callback in swiotlb_dma_ops
> >> for dma_free_coherent() so that it can distinguish memory allocated by
> >> dma_generic_alloc_coherent() from one allocated by swiotlb_alloc_coherent()
> >> and release it with dma_generic_free_coherent() which can handle contiguous
> >> memory.  This change requires making is_swiotlb_buffer() global function.
> >>
> >> This also needs to change .free callback in the dma_map_ops for amd_gart
> >> and sta2x11, because these dma_ops are also using
> >> dma_generic_alloc_coherent().
> >>
> >> Cc: Marek Szyprowski <m.szyprowski-Sze3O3UU22JBDgjK7y7TUQ@public.gmane.org>
> >> Cc: Konrad Rzeszutek Wilk <konrad.wilk-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
> >> Cc: David Woodhouse <dwmw2-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
> >> Cc: Don Dutile <ddutile-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
> >> Cc: Thomas Gleixner <tglx-hfZtesqFncYOwBW4kG4KsQ@public.gmane.org>
> >> Cc: Ingo Molnar <mingo-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
> >> Cc: "H. Peter Anvin" <hpa-YMNOUZJC4hwAvxtiuMwx3w@public.gmane.org>
> >> Cc: Andi Kleen <andi-Vw/NltI1exuRpAAqCnN02g@public.gmane.org>
> >> Cc: x86-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org
> >> Cc: iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org
> >> Signed-off-by: Akinobu Mita <akinobu.mita-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
> >> Acked-by: Marek Szyprowski <m.szyprowski-Sze3O3UU22JBDgjK7y7TUQ@public.gmane.org>
> >> ---
> >> No change from the previous version
> >>
> >>  arch/x86/Kconfig               | 2 +-
> >>  arch/x86/include/asm/swiotlb.h | 7 +++++++
> >>  arch/x86/kernel/amd_gart_64.c  | 2 +-
> >>  arch/x86/kernel/pci-swiotlb.c  | 9 ++++++---
> >>  arch/x86/pci/sta2x11-fixup.c   | 6 ++----
> >>  include/linux/swiotlb.h        | 2 ++
> >>  lib/swiotlb.c                  | 2 +-
> >
> > It looks reasonable from my perspective (as swiotlb maintainer).
> >
> > Not too thrilled about the  'is_swiotlb_buffer' but that code is
> > quite small so it should be fast enough.
> 
> Thanks.  Can I get your Acked-by for this patch?

Yes. Acked-by: Konrad Rzeszutek Wilk <konrad.wilk-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>