[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20160129095958.GA4541@arm.com>
Date: Fri, 29 Jan 2016 09:59:59 +0000
From: Will Deacon <will.deacon@....com>
To: "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@...radead.org>,
"Maciej W. Rozycki" <macro@...tec.com>,
David Daney <ddaney@...iumnetworks.com>,
Måns Rullgård <mans@...sr.com>,
Ralf Baechle <ralf@...ux-mips.org>,
linux-kernel@...r.kernel.org, torvalds@...ux-foundation.org,
boqun.feng@...il.com
Subject: Re: [RFC][PATCH] mips: Fix arch_spin_unlock()
Hi Paul,
On Thu, Jan 28, 2016 at 02:31:31PM -0800, Paul E. McKenney wrote:
> On Thu, Jan 28, 2016 at 09:57:19AM +0000, Will Deacon wrote:
> > On Wed, Jan 27, 2016 at 03:38:36PM -0800, Paul E. McKenney wrote:
> > > On Wed, Jan 27, 2016 at 03:21:58PM +0000, Will Deacon wrote:
> > Yes, sorry for the shorthand:
> >
> > - Each paragraph is a separate thread
> > - Wx=1 means WRITE_ONCE(x, 1), Rx=1 means READ_ONCE(x) returns 1
> > - WxRel means smp_store_release(x,1), RxAcq=1 means smp_load_acquire(x)
> > returns 1
> > - Everything is initially zero
> >
> > > > and I suppose a variant of that:
> > > >
> > > >
> > > > Wx=1
> > > > WyRel=1
> > > >
> > > > RyAcq=1
> > > > Wz=1
> > > >
> > > > Rz=1
> > > > <address dependency>
> > > > Rx=0
> > >
> > > Agreed, this would be needed as well, along with the read-read and
> > > read-write variants. I picked the write-read version (Will's first
> > > test above) because write-read reordering is the most likely on
> > > hardware that I am aware of.
> >
> > Question: if you replaced "Wz=1" with "WzRel=1" in my second test, would
> > it then be forbidden?
>
> On Power, yes. I would guess on ARM as well.
Indeed.
> For Linux in general, this is a question: How strict do we want to be
> about matching the type of write with the corresponding read? My
> default approach is to initially be quite strict and loosen as needed.
> Here "quite strict" might mean requiring an rcu_assign_pointer() for
> the write and rcu_dereference() for the read, as opposed to (say)
> ACCESS_ONCE() for the read. (I am guessing that this would be too
> tight, but it makes a good example.)
>
> Thoughts?
That sounds broadly sensible to me and allows rcu_assign_pointer and
rcu_dereference to be used as drop-in replacements for release/acquire
where local transitivity isn't required. However, I don't think we can
rule out READ_ONCE/WRITE_ONCE interactions as they seem to be used
already in things like the osq_lock (albeit without the address
dependency).
Will
Powered by blists - more mailing lists