Re: [RFC PATCH] arm64/fpsimd: Don't disable softirq when touching FPSIMD/SVE state

[Julien Grall]

Hi,

On 14/02/2019 10:34, Dave Martin wrote:
> On Wed, Feb 13, 2019 at 05:52:27PM +0100, Sebastian Andrzej Siewior wrote:
> > On 2019-02-13 16:40:00 [+0100], Ard Biesheuvel wrote:
> > > > > This is equal what x86 is currently doing. The naming is slightly
> > > > > different, there is irq_fpu_usable().
> > > >
> > > > Yes, I think it's basically the same idea.
> > > >
> > > > It's been evolving a bit on both sides, but is quite similar now.
> > >
> > > may_use_simd() only exists because we have a generic crypto SIMD
> > > helper, and so we needed something arch agnostic to wrap around
> > > irq_fpu_usable()
> >
> > My question was more if this is helpful and we want to keep or if
> > it would be better to remove it and always disable BH as part of SIMD
> > operations.
>
> Wouldn't this arbitrarily increase softirq latency?  Unconditionally
> forbidding SIMD in softirq might make more sense.  It depends on how
> important the use cases are...

Looking at the commit message from cb84d11e1625 "arm64: neon: Remove support for 
nested or hardirq kernel-mode NEON", one of the use case for crypto in softirq 
is certain mac80211 drivers.

Is there any other use case for use crypto in softirqs?

Cheers,

--
Julien Grall