[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20180717194001.GA3781@andrea>
Date: Tue, 17 Jul 2018 21:40:01 +0200
From: Andrea Parri <andrea.parri@...rulasolutions.com>
To: "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@...ux-foundation.org>,
Michael Ellerman <mpe@...erman.id.au>,
Peter Zijlstra <peterz@...radead.org>,
Alan Stern <stern@...land.harvard.edu>,
Will Deacon <will.deacon@....com>,
Akira Yokosawa <akiyks@...il.com>,
Boqun Feng <boqun.feng@...il.com>,
Daniel Lustig <dlustig@...dia.com>,
David Howells <dhowells@...hat.com>,
Jade Alglave <j.alglave@....ac.uk>,
Luc Maranget <luc.maranget@...ia.fr>,
Nick Piggin <npiggin@...il.com>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH v2] tools/memory-model: Add extra ordering for locks and
remove it for ordinary release/acquire
> > That said, I don't understand the powerpc memory ordering. I thought
> > the rules were "isync on lock, lwsync on unlock".
> >
> > That's what the AIX docs imply, at least.
> >
> > In particular, I find:
> >
> > "isync is not a memory barrier instruction, but the
> > load-compare-conditional branch-isync sequence can provide this
> > ordering property"
> >
> > so why are you doing "sync/lwsync", when it sounds like "isync/lwsync"
> > (for lock/unlock) is the right thing and would already give memory
> > barrier semantics?
>
> The PowerPC guys will correct me if I miss something here...
[Same here.]
>
> The isync provides ordering roughly similar to lwsync, but nowhere near
> as strong as sync, and it is sync that would be needed to cause lock
> acquisition to provide full ordering.
IIRC, ctrl+isync is even *weaker* than lwsync in certain respects, e.g.,
the former doesn't provide A-cumulativity according to the architectural
intent.
>The reason for using lwsync instead
> of isync is that the former proved to be faster on recent hardware.
Interesting; can you add some references about this?
Andrea
> The reason that the kernel still has the ability to instead generate
> isync instructions is that some older PowerPC hardware does not provide
> the lwsync instruction. If the hardware does support lwsync, the isync
> instructions are overwritten with lwsync at boot time.
>
> Thanx, Paul
>
Powered by blists - more mailing lists