[PATCH 0/5] Simplify kernel-mode NEON

Dave P Martin Dave.Martin at arm.com
Fri Aug 4 06:26:06 PDT 2017


On Fri, Aug 04, 2017 at 02:21:52PM +0100, Ard Biesheuvel wrote:
> On 4 August 2017 at 14:12, Catalin Marinas <catalin.marinas at arm.com> wrote:
> > On Fri, Aug 04, 2017 at 01:25:03PM +0100, Ard Biesheuvel wrote:
> >> On 4 August 2017 at 13:22, Catalin Marinas <catalin.marinas at arm.com> wrote:
> >> > On Fri, Aug 04, 2017 at 01:08:58PM +0100, Catalin Marinas wrote:
> >> >> On Thu, Aug 03, 2017 at 05:23:18PM +0100, Dave P Martin wrote:
> >> >> > This series depends on Ard's v4.14 crypto rework [2].
> >> > [...]
> >> >> > [2] http://lists.infradead.org/pipermail/linux-arm-kernel/2017-July/520664.html
> >> > [...]
> >> >> > Ard Biesheuvel (1):
> >> >> >   arm64: neon: replace generic definition of may_use_simd()
> >> >> >
> >> >> > Dave Martin (4):
> >> >> >   arm64: neon: Add missing header guard in <asm/neon.h>
> >> >> >   arm64: fpsimd: Consistently use __this_cpu_ ops where appropriate
> >> >> >   arm64: neon: Allow EFI runtime services to use FPSIMD in irq context
> >> >> >   arm64: neon: Remove support for nested or hardirq kernel-mode NEON
> >> >>
> >> >> Queued for 4.14. Thanks.
> >> >
> >> > ... and reverted.
> >> >
> >> > I now realised that it doesn't build without Ard's crypto series (I had
> >> > the wrong impression it is just a performance impact). I get errors
> >> > like:
> >> >
> >> > arch/arm64/crypto/sha1-ce-glue.c|41 col 2| error: implicit declaration
> >> > of function ‘kernel_neon_begin_partial’
> >>
> >> Ah yes. Apologies for failing to mention that. Apparently, there are
> >> in fact build time cross-dependencies that I forgot about.
> >>
> >> To avoid delaying this unnecessarily, we just alias
> >> kernel_neon_begin_partial() to kernel_neon_begin() and ignore the
> >> argument. We can remove that again when everything has gone upstream.
> >
> > But would kernel_neon_begin() be called in an interrupt context from the
> > crypto code? I'd like the arm64 for-next/core branch (to be based on
> > -rc4 next week) to still be fully working.
> >
>
> Well, theoretically. In the new situation we allow KMN from process
> and softirq context, but the latter only if no process context KMN is
> in progress. This last rule could be violated by the old crypto code,
> but the chances of actually hitting that are very low: if your wifi
> chip lacks a h/w implementation of CCMP (which is uncommon these
> days), and it gets invoked while KMN crypto is being used on the same
> core, i.e., for IPsec or block encryption, you may get a splat. It
> wouldn't corrupt your encrypted file system.
>
> Perhaps we could stick it on a separate branch for this cycle (with
> the suggested tweak) and get it pulled it into -next separately? That
> way, you can forward it as a late pull, after Herbert's stuff gets in.

Or I could prepend the patches to the SVE series, and we wait for Linux
to pull the crypto branch before merging that.  (I still need to repost
and the SVE patches need to be reviewed, so that isn't imminent.)

Cheers
---Dave
IMPORTANT NOTICE: The contents of this email and any attachments are confidential and may also be privileged. If you are not the intended recipient, please notify the sender immediately and do not disclose the contents to any other person, use it for any purpose, or store or copy the information in any medium. Thank you.



More information about the linux-arm-kernel mailing list