[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Thu, 6 Jun 2019 06:48:56 -0700
From: "Paul E. McKenney" <paulmck@...ux.ibm.com>
To: Herbert Xu <herbert@...dor.apana.org.au>
Cc: Alan Stern <stern@...land.harvard.edu>,
Boqun Feng <boqun.feng@...il.com>,
Linus Torvalds <torvalds@...ux-foundation.org>,
Frederic Weisbecker <fweisbec@...il.com>,
Fengguang Wu <fengguang.wu@...el.com>, LKP <lkp@...org>,
LKML <linux-kernel@...r.kernel.org>,
Netdev <netdev@...r.kernel.org>,
"David S. Miller" <davem@...emloft.net>,
Andrea Parri <andrea.parri@...rulasolutions.com>,
Luc Maranget <luc.maranget@...ia.fr>,
Jade Alglave <j.alglave@....ac.uk>
Subject: Re: rcu_read_lock lost its compiler barrier
On Thu, Jun 06, 2019 at 09:38:24PM +0800, Herbert Xu wrote:
> On Thu, Jun 06, 2019 at 03:58:17AM -0700, Paul E. McKenney wrote:
> >
> > I cannot immediately think of a way that the compiler could get this
> > wrong even in theory, but similar code sequences can be messed up.
> > The reason for this is that in theory, the compiler could use the
> > stored-to location as temporary storage, like this:
> >
> > a = whatever; // Compiler uses "a" as a temporary
> > do_something();
> > whatever = a;
> > a = 1; // Intended store
>
> Well if the compiler is going to do this then surely it would
> continue to do this even if you used WRITE_ONCE. Remember a is
> not volatile, only the access of a through WRITE_ONCE is volatile.
I disagree. Given a volatile store, the compiler cannot assume that the
stored-to location is normal memory at that point in time, and therefore
cannot assume that it is safe to invent a store to that location (as
shown above). Thus far, the C++ standards committee seems on-board with
this, though time will tell.
http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2019/p1382r1.pdf
Thanx, Paul
Powered by blists - more mailing lists