[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-ppc] [PATCH RFC 3/4] target-ppc: use atomic_cmpxchg for ld/st
From: |
Alex Bennée |
Subject: |
Re: [Qemu-ppc] [PATCH RFC 3/4] target-ppc: use atomic_cmpxchg for ld/st reservation |
Date: |
Wed, 07 Sep 2016 08:13:31 +0100 |
User-agent: |
mu4e 0.9.17; emacs 25.1.11 |
David Gibson <address@hidden> writes:
> On Wed, Sep 07, 2016 at 10:17:42AM +0530, Nikunj A Dadhania wrote:
>> David Gibson <address@hidden> writes:
>>
>> > [ Unknown signature status ]
>> > On Fri, Sep 02, 2016 at 12:02:55PM +0530, Nikunj A Dadhania wrote:
>> >> Signed-off-by: Nikunj A Dadhania <address@hidden>
>> >
>> > This really needs a comment indicating that this implementation isn't
>> > strictly correct (although probably good enough in practice).
>>
>> Sure. And it also does not help if someone uses any store other than
>> store conditional, that isn't taken care.
>>
>> Assumption here is the locking primitives use load with reservation and
>> store conditional. And no other ld/st variant touch this memory.
>
> So, a) I don't think this really relies on that: an ordinary store
> (assuming it changes the value) will still get picked up the cmpxchg.
> Well.. at least after a suitable memory barrier. Matching memory
> models between emulated and host cpus is a whole other kettle of fish.
Have you seen Pranith's memory barrier patches?
>
> I think this does matter, IIRC a kernel spin unlock on ppc is a
> barrier + plain store, no load locked or store conditional.
>
>> > Specifically a racing store which happens to store the same value
>> > which was already in memory should clobber the reservation, but won't
>> > with this implementation.
>> >
>> > I had a long discussion at KVM Forum with Emilio Costa about this, in
>> > which I discovered just how hard it is to strictly implement
>> > store-conditional semantics in terms of anything else. So, this is
>> > probably a reasonable substitute, but we should note the fact that
>> > it's not 100%.
>>
>> I will update the commit log.
>>
>> Regards,
>> Nikunj
>>
--
Alex Bennée
- Re: [Qemu-ppc] [PATCH RFC 4/4] target-ppc: flush tlb from all the cpu, (continued)
[Qemu-ppc] [PATCH RFC 3/4] target-ppc: use atomic_cmpxchg for ld/st reservation, Nikunj A Dadhania, 2016/09/02
- Re: [Qemu-ppc] [PATCH RFC 3/4] target-ppc: use atomic_cmpxchg for ld/st reservation, David Gibson, 2016/09/07
- Re: [Qemu-ppc] [PATCH RFC 3/4] target-ppc: use atomic_cmpxchg for ld/st reservation, David Gibson, 2016/09/07
- Re: [Qemu-ppc] [PATCH RFC 3/4] target-ppc: use atomic_cmpxchg for ld/st reservation,
Alex Bennée <=
- Re: [Qemu-ppc] [PATCH RFC 3/4] target-ppc: use atomic_cmpxchg for ld/st reservation, David Gibson, 2016/09/11
- Re: [Qemu-ppc] [PATCH RFC 3/4] target-ppc: use atomic_cmpxchg for ld/st reservation, Alex Bennée, 2016/09/12
- Re: [Qemu-ppc] [PATCH RFC 3/4] target-ppc: use atomic_cmpxchg for ld/st reservation, Benjamin Herrenschmidt, 2016/09/12
Re: [Qemu-ppc] [Qemu-devel] [PATCH RFC 0/4] Enable MTTCG on PowerPC, Cédric Le Goater, 2016/09/02
Re: [Qemu-ppc] [PATCH RFC 0/4] Enable MTTCG on PowerPC, Benjamin Herrenschmidt, 2016/09/02