Re: [RFC PATCH v5 5/5] riscv/cmpxchg: Implement xchg for variables of size 1 and 2

[Conor Dooley]

On Fri, Aug 11, 2023 at 07:27:28AM +0100, Conor Dooley wrote:
> On Fri, Aug 11, 2023 at 09:40:30AM +0800, Guo Ren wrote:
> > On Fri, Aug 11, 2023 at 12:23 AM Palmer Dabbelt <palmer@xxxxxxxxxxxx> wrote:
> > >
> > > On Thu, 10 Aug 2023 09:04:04 PDT (-0700), leobras@xxxxxxxxxx wrote:
> > > > On Thu, 2023-08-10 at 08:51 +0200, Arnd Bergmann wrote:
> > > >> On Thu, Aug 10, 2023, at 06:03, Leonardo Bras wrote:
> > > >> > xchg for variables of size 1-byte and 2-bytes is not yet available for
> > > >> > riscv, even though its present in other architectures such as arm64 and
> > > >> > x86. This could lead to not being able to implement some locking mechanisms
> > > >> > or requiring some rework to make it work properly.
> > > >> >
> > > >> > Implement 1-byte and 2-bytes xchg in order to achieve parity with other
> > > >> > architectures.
> > > >> >
> > > >> > Signed-off-by: Leonardo Bras <leobras@xxxxxxxxxx>
> > > >>
> > > >
> > > > Hello Arnd Bergmann, thanks for reviewing!
> > > >
> > > >> Parity with other architectures by itself is not a reason to do this,
> > > >> in particular the other architectures you listed have the instructions
> > > >> in hardware while riscv does not.
> > > >
> > > > Sure, I understand RISC-V don't have native support for xchg on variables of
> > > > size < 4B. My argument is that it's nice to have even an emulated version for
> > > > this in case any future mechanism wants to use it.
> > > >
> > > > Not having it may mean we won't be able to enable given mechanism in RISC-V.
> > >
> > > IIUC the ask is to have a user within the kernel for these functions.
> > > That's the general thing to do, and last time this came up there was no
> > > in-kernel use of it -- the qspinlock stuff would, but we haven't enabled
> > > it yet because we're worried about the performance/fairness stuff that
> > > other ports have seen and nobody's got concrete benchmarks yet (though
> > > there's another patch set out that I haven't had time to look through,
> > > so that may have changed).
> > Conor doesn't agree with using an alternative as a detour mechanism
> > between qspinlock & ticket lock.
> 
> Hold on a sec, I don't recall having a problem with alternatives - it
> was calling the stronger forward progress guarantee an erratum
> (which it isn't) and an ISA extension w/o any "abusing" that framework
> that I did not like.

Hmm, what I wrote here makes no sense reading it back. Let me try again:

	Hold on a sec, I don't recall having a problem with alternatives - it
	was calling the stronger forward progress guarantee an erratum
	(which it isn't) and "abusing" that framework that I did not like.
	The series effectively mixed and matched whichever part of ISA
	extensions and errata that was convenient.

> 
> > So I'm preparing V11 with static_key
> > (jump_label) style.
> 
> I don't think there's much point rushing into making it based on static
> keys when no progress has been made on implementing support for
> non-standard extensions. Changing to a static key doesn't change the
> detection mechanism, I've not got a problem with using alternatives for
> this stuff.
> 
> Thanks,
> Conor.
> 
> > Next version, I would separate paravirt_qspinlock
> > & CNA_qspinlock from V10. That would make it easy to review the
> > qspinlock patch series. You can review the next version V11. Now I'm
> > debugging a static_key init problem when load_modules, which is
> > triggered by our combo_qspinlock.
> > 
> > The qspinlock is being tested on the riscv platform [1] with 128 cores
> > with 8 NUMA nodes, next, I would update the comparison results of
> > qspinlock & ticket lock.
> > 
> > [1]: https://www.sophon.ai/
> > 
> > >
> > > So if something uses these I'm happy to go look closer.
> > >
> > > >> Emulating the small xchg() through cmpxchg() is particularly tricky
> > > >> since it's easy to run into a case where this does not guarantee
> > > >> forward progress.
> > > >>
> > > >
> > > > Didn't get this part:
> > > > By "emulating small xchg() through cmpxchg()", did you mean like emulating an
> > > > xchg (usually 1 instruction) with lr & sc (same used in cmpxchg) ?
> > > >
> > > > If so, yeah, it's a fair point: in some extreme case we could have multiple
> > > > threads accessing given cacheline and have sc always failing. On the other hand,
> > > > there are 2 arguments on that:
> > > >
> > > > 1 - Other architectures, (such as powerpc, arm and arm64 without LSE atomics)
> > > > also seem to rely in this mechanism for every xchg size. Another archs like csky
> > > > and loongarch use asm that look like mine to handle size < 4B xchg.
> > > >
> > > >
> > > >>  This is also something that almost no architecture
> > > >> specific code relies on (generic qspinlock being a notable exception).
> > > >>
> > > >
> > > > 2 - As you mentioned, there should be very little code that will actually make
> > > > use of xchg for vars < 4B, so it should be safe to assume its fine to not
> > > > guarantee forward progress for those rare usages (like some of above mentioned
> > > > archs).
> > > >
> > > >> I would recommend just dropping this patch from the series, at least
> > > >> until there is a need for it.
> > > >
> > > > While I agree this is a valid point, I believe its more interesting to have it
> > > > implemented if any future mechanism wants to make use of this.
> > > >
> > > >
> > > > Thanks!
> > > > Leo
> > 
> > 
> > 
> > -- 
> > Best Regards
> >  Guo Ren

Attachment: signature.asc
Description: PGP signature