[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAJF2gTR2ON33wc87iV564rkDbNiE56h_t0kzKKXdJtGqgJ1sOQ@mail.gmail.com>
Date: Tue, 1 Aug 2023 18:49:45 +0800
From: Guo Ren <guoren@...nel.org>
To: WANG Rui <wangrui@...ngson.cn>
Cc: chenhuacai@...nel.or, kernel@...0n.name, arnd@...db.de,
andi.shyti@...ux.intel.com, andrzej.hajda@...el.com,
peterz@...radead.org, will@...nel.org, boqun.feng@...il.com,
mark.rutland@....com, loongarch@...ts.linux.dev,
linux-kernel@...r.kernel.org, Guo Ren <guoren@...ux.alibaba.com>
Subject: Re: [PATCH] LoongArch: Fixup cmpxchg sematic for memory barrier
On Tue, Aug 1, 2023 at 5:32 PM WANG Rui <wangrui@...ngson.cn> wrote:
>
> Hello,
>
> On Tue, Aug 1, 2023 at 5:05 PM Guo Ren <guoren@...nel.org> wrote:
> >
> > > The CoRR problem would cause wider problems than this.For this case,
> > > do you mean your LL -> LL would be reordered?
> > >
> > > CPU 0
> > > CPU1
> > > LL(2) (set ex-monitor)
> > >
> > > store (break the ex-monitor)
> > > LL(1) (reordered instruction set ex-monitor
> > > SC(3) (successes ?)
> > Sorry for the mail client reformat, I mean:
> >
> > CPU0 LL(2) (set ex-monitor)
> > CPU1 STORE (break the ex-monitor)
> > CPU0 LL(1) (reordered instruction set ex-monitor
> > CPU0 SC(3) (success?)
>
> No. LL and LL won't reorder because LL implies a memory barrier(though
> not acquire semantics).
That means we could remove __WEAK_LLSC_MB totally, right?
>
> Regards,
> --
> WANG Rui
>
--
Best Regards
Guo Ren
Powered by blists - more mailing lists