[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-Id: <BD651F14-7C88-4553-A4E8-986042271CAD@in.tum.de>
Date: Mon, 18 Jul 2022 10:24:19 +0200
From: Paul Heidekrüger <Paul.Heidekrueger@...tum.de>
To: "Paul E. McKenney" <paulmck@...nel.org>
Cc: Alan Stern <stern@...land.harvard.edu>,
clang-built-linux <llvm@...ts.linux.dev>,
linux-toolchains@...r.kernel.org,
Andrea Parri <parri.andrea@...il.com>,
Will Deacon <will@...nel.org>,
Peter Zijlstra <peterz@...radead.org>,
Boqun Feng <boqun.feng@...il.com>,
Nicholas Piggin <npiggin@...il.com>,
David Howells <dhowells@...hat.com>,
Jade Alglave <j.alglave@....ac.uk>,
Luc Maranget <luc.maranget@...ia.fr>,
Akira Yokosawa <akiyks@...il.com>,
Daniel Lustig <dlustig@...dia.com>,
Joel Fernandes <joel@...lfernandes.org>,
Nathan Chancellor <nathan@...nel.org>,
Nick Desaulniers <ndesaulniers@...gle.com>,
Tom Rix <trix@...hat.com>, Palmer Dabbelt <palmer@...belt.com>,
LKML <linux-kernel@...r.kernel.org>,
linux-arch <linux-arch@...r.kernel.org>,
Marco Elver <elver@...gle.com>,
Charalampos Mainas <charalampos.mainas@...il.com>,
Pramod Bhatotia <pramod.bhatotia@...tum.de>,
Soham Chakraborty <s.s.chakraborty@...elft.nl>,
Martin Fink <martin.fink@...tum.de>
Subject: Re: [PATCH RFC] tools/memory-model: Adjust ctrl dependency definition
Paul E. McKenney <paulmck@...nel.org> wrote:
> On Fri, Jul 15, 2022 at 09:27:26AM -0400, Alan Stern wrote:
>> On Fri, Jul 15, 2022 at 02:27:28PM +0200, Paul Heidekrüger wrote:
>>> I have just been thinking about how to word this patch; am I correct in
>>> assuming that the LKMM does not deal with loop conditions? Or in other
>>> words, there is no way for a loop condition to impose a ctrl dependency on
>>> any WRITE_ONCE's in the loop body? It are only if and switch statements the
>>> LKMM is concerned with in the case of ctrl dependencies?
>>
>> In theory, the LKMM does say that a loop condition imposes a control
>> dependency on any memory accesses within the loop body. However, the
>> herd7 tool has only very limited support for looping constructs, so in
>> practice it's not possible to create suitable litmus tests with loops.
>
> And Alan isn't joking. The closest simulation that I know of is to
> combine limited loop unrolling with the "filter" clause. The point of
> the filter clause is to eliminate from consideration executions that
> need the more iterations of the loop to be unrolled.
>
> And that means that as far as LKMM is concerned, loop-based control
> dependencies are similar to those for nested "if" statements.
>
> Thanx, Paul
Makes sense, thank you both!
Paul
Powered by blists - more mailing lists