From: "Paul E. McKenney" <paulmck@kernel.org>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Florian Weimer <fweimer@redhat.com>,
linux-toolchains@vger.kernel.org, Will Deacon <will@kernel.org>,
linux-kernel@vger.kernel.org, stern@rowland.harvard.edu,
parri.andrea@gmail.com, boqun.feng@gmail.com, npiggin@gmail.com,
dhowells@redhat.com, j.alglave@ucl.ac.uk, luc.maranget@inria.fr,
akiyks@gmail.com, dlustig@nvidia.com, joel@joelfernandes.org,
torvalds@linux-foundation.org
Subject: Re: Control Dependencies vs C Compilers
Date: Wed, 7 Oct 2020 10:11:07 -0700 [thread overview]
Message-ID: <20201007171107.GO29330@paulmck-ThinkPad-P72> (raw)
In-Reply-To: <20201007115054.GD2628@hirez.programming.kicks-ass.net>
On Wed, Oct 07, 2020 at 01:50:54PM +0200, Peter Zijlstra wrote:
> On Wed, Oct 07, 2020 at 12:20:41PM +0200, Florian Weimer wrote:
> > * Peter Zijlstra:
[ . . . ]
> > >> I think in GCC, they are called __atomic_load_n(foo, __ATOMIC_RELAXED)
> > >> and __atomic_store_n(foo, __ATOMIC_RELAXED). GCC can't optimize relaxed
> > >> MO loads and stores because the C memory model is defective and does not
> > >> actually guarantee the absence of out-of-thin-air values (a property it
> > >> was supposed to have).
> > >
> > > AFAIK people want to get that flaw in the C memory model fixed (which to
> > > me seemd like a very good idea).
> >
> > It's been a long time since people realized that this problem exists,
> > with several standard releases since then.
>
> I've been given to believe it is a hard problem. Personally I hold the
> opinion that prohibiting store speculation (of all kinds) is both
> necesary and sufficient to avoid OOTA. But I have 0 proof for that.
There are proofs for some definitions of store speculation, for example,
as proposed by Demsky and Boehm [1] and as prototyped by Demsky's student,
Peizhao Ou [2]. But these require marking all accesses and end up being
optimized variants of acquire load and release store. One optimization
is that if you have a bunch of loads followed by a bunch of stores,
the compiler can emit a single memory-barrier instruction between the
last load and the first store.
I am not a fan of this approach.
Challenges include:
o Unmarked accesses. Compilers are quite aggressive about
moving normal code.
o Separately compiled code. For example, does the compiler have
unfortunatel optimization opportunities when "volatile if"
appears in one translation unit and the dependent stores in
some other translation unit?
o LTO, as has already been mentioned in this thread.
Probably other issues as well, but a starting point.
Thanx, Paul
[1] https://dl.acm.org/doi/10.1145/2618128.2618134
"Outlawing ghosts: avoiding out-of-thin-air results"
Hans-J. Boehm and Brian Demsky.
[2] https://escholarship.org/uc/item/2vm546k1
"An Initial Study of Two Approaches to Eliminating Out-of-Thin-Air
Results" Peizhao Ou.
next prev parent reply other threads:[~2020-10-07 17:11 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-10-06 11:47 Control Dependencies vs C Compilers Peter Zijlstra
2020-10-06 12:37 ` David Laight
2020-10-06 12:49 ` Willy Tarreau
2020-10-06 13:31 ` Peter Zijlstra
2020-10-06 14:23 ` stern
2020-10-06 14:43 ` Peter Zijlstra
2020-10-06 15:16 ` Nick Clifton
2020-10-06 15:37 ` David Laight
2020-10-06 15:50 ` Paul E. McKenney
2020-10-06 16:10 ` Willy Tarreau
2020-10-06 16:22 ` David Laight
2020-10-06 16:31 ` Paul E. McKenney
2020-10-06 15:07 ` David Laight
2020-10-06 21:20 ` Florian Weimer
2020-10-07 9:32 ` Peter Zijlstra
2020-10-07 10:20 ` Florian Weimer
2020-10-07 11:50 ` Peter Zijlstra
2020-10-07 17:11 ` Paul E. McKenney [this message]
2020-10-07 21:07 ` Peter Zijlstra
2020-10-07 21:20 ` Paul E. McKenney
2020-10-07 10:30 ` Willy Tarreau
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20201007171107.GO29330@paulmck-ThinkPad-P72 \
--to=paulmck@kernel.org \
--cc=akiyks@gmail.com \
--cc=boqun.feng@gmail.com \
--cc=dhowells@redhat.com \
--cc=dlustig@nvidia.com \
--cc=fweimer@redhat.com \
--cc=j.alglave@ucl.ac.uk \
--cc=joel@joelfernandes.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-toolchains@vger.kernel.org \
--cc=luc.maranget@inria.fr \
--cc=npiggin@gmail.com \
--cc=parri.andrea@gmail.com \
--cc=peterz@infradead.org \
--cc=stern@rowland.harvard.edu \
--cc=torvalds@linux-foundation.org \
--cc=will@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).