Re: Re: [RFC][PATCH 2/5] mips/atomic: Fix loongson_llsc_mb() wreckage

[Peter Zijlstra]

I think this thread got 'lost'

On Thu, Apr 25, 2019 at 11:12:58AM +0200, Peter Zijlstra wrote:
> On Thu, Apr 25, 2019 at 09:33:48AM +0200, Peter Zijlstra wrote:
> > > Let me explain the bug more specific:
> > > 
> > > the bug ONLY matters in following situation:
> > > 
> > > #. more than one cpu (assume cpu A and B) doing ll/sc on same shared
> > > var V
> > > 
> > > #. speculative memory access from A cause A erroneously succeed sc
> > > operation, since the erroneously successful sc operation violate the
> > > coherence protocol. (here coherence protocol means the rules that CPU
> > > follow to implement ll/sc right)
> > > 
> > > #. B succeed sc operation too, but this sc operation is right both
> > > logically and follow the coherence protocol, and makes A's sc wrong
> > > logically since only ONE sc operation can succeed.
> 
> > > In one wordï the bug only affect local cpuâs ll/sc operation, and
> > > affect MP system.
> 
> > > PS:
> > > 
> > > If local_t is only ll/sc manipulated by current CPUï then no need fix it.
> > 
> > It _should_ be CPU local, but this was not at all clear from reading the
> > original changelog nor the comment with loongson_llsc_mb().
> 
> However, if it is a coherence issue, the thing is at the cacheline
> level, and there is nothing that says the line isn't shared, just the
> one variable isn't.
> 
> Ideally there should be minimal false sharing, but....

So if two variables share a line, and one is local while the other is
shared atomic, can contention on the line, but not the variable, cause
issues for the local variable?

If not; why not? Because so far the issue is line granular due to the
coherence aspect.