Re: [PATCH 2/2] swiotlb: Add swiotlb=nobounce debug option

From	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Newsgroups	linux.kernel
Subject	Re: [PATCH 2/2] swiotlb: Add swiotlb=nobounce debug option
Date	2016-11-07 20:30 +0100
Message-ID	<sAXMd-7uI-1@gated-at.bofh.it> (permalink)
References	<syn0t-4i5-5@gated-at.bofh.it> <syn0t-4i5-7@gated-at.bofh.it> <syp2i-5zh-43@gated-at.bofh.it> <sAXCx-7rh-11@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On Mon, Nov 07, 2016 at 07:57:11PM +0100, Geert Uytterhoeven wrote:
> Hi Konrad,
> 
> On Mon, Oct 31, 2016 at 6:52 PM, Konrad Rzeszutek Wilk
> <konrad.wilk@oracle.com> wrote:
> > On Mon, Oct 31, 2016 at 04:45:04PM +0100, Geert Uytterhoeven wrote:
> >> On architectures like arm64, swiotlb is tied intimately to the core
> >> architecture DMA support. In addition, ZONE_DMA cannot be disabled.
> >>
> >> To aid debugging and catch devices not supporting DMA to memory outside
> >> the 32-bit address space, add a kernel command line option
> >> "swiotlb=nobounce", which disables the use of bounce buffers.
> >> If specified, trying to map memory that cannot be used with DMA will
> >> fail, and a warning will be printed (rate-limited).
> >
> > I would make the 'swiotlb_force' an enum. And then instead of this
> > being 'nobounce' just do the inverse of 'force', that is the
> > 'noforce' would trigger this no bounce effect.
> >
> > So:
> >
> > enum {
> >         NORMAL,         /* Default - depending on the hardware DMA mask and such. */
> >         FORCE,          /* swiotlb=force */
> >         NO_FORCE,       /* swiotlb=noforce */
> 
> Fine for me, but swiotlb_force is exported to platform code. Hence all users
> should be updated?

Yeah it would have to be moved to the swiotlb.h (the enum).

Thanks!

Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread

Thread

[PATCH 0/2] swiotlb: Rate-limit printing and 64-bit memory debugging Geert Uytterhoeven <geert+renesas@glider.be> - 2016-10-31 16:50 +0100
  [PATCH 1/2] swiotlb: Rate-limit printing when running out of SW-IOMMU space Geert Uytterhoeven <geert+renesas@glider.be> - 2016-10-31 16:50 +0100
    Re: [PATCH 1/2] swiotlb: Rate-limit printing when running out of  SW-IOMMU space Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> - 2016-10-31 17:10 +0100
    Re: [PATCH 1/2] swiotlb: Rate-limit printing when running out of  SW-IOMMU space Konrad Rzeszutek Wilk <konrad@darnok.org> - 2016-11-05 20:50 +0100
  [PATCH 2/2] swiotlb: Add swiotlb=nobounce debug option Geert Uytterhoeven <geert+renesas@glider.be> - 2016-10-31 16:50 +0100
    Re: [PATCH 2/2] swiotlb: Add swiotlb=nobounce debug option Robin Murphy <robin.murphy@arm.com> - 2016-10-31 18:50 +0100
      Re: [PATCH 2/2] swiotlb: Add swiotlb=nobounce debug option Geert Uytterhoeven <geert@linux-m68k.org> - 2016-10-31 19:30 +0100
        Re: [PATCH 2/2] swiotlb: Add swiotlb=nobounce debug option Robin Murphy <robin.murphy@arm.com> - 2016-11-01 12:50 +0100
          Re: [PATCH 2/2] swiotlb: Add swiotlb=nobounce debug option Geert Uytterhoeven <geert@linux-m68k.org> - 2016-11-07 16:50 +0100
            Re: [PATCH 2/2] swiotlb: Add swiotlb=nobounce debug option Robin Murphy <robin.murphy@arm.com> - 2016-11-07 18:20 +0100
    Re: [PATCH 2/2] swiotlb: Add swiotlb=nobounce debug option Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> - 2016-10-31 19:00 +0100
      Re: [PATCH 2/2] swiotlb: Add swiotlb=nobounce debug option Geert Uytterhoeven <geert@linux-m68k.org> - 2016-11-07 20:20 +0100
        Re: [PATCH 2/2] swiotlb: Add swiotlb=nobounce debug option Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> - 2016-11-07 20:30 +0100

csiph-web