linux-kernel - Re: [PATCH] Documentation: atomic_t.txt: Explain ordering provided by smp_mb__{before,after}

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20190423201955.GX3923@linux.ibm.com>
Date:   Tue, 23 Apr 2019 13:19:55 -0700
From:   "Paul E. McKenney" <paulmck@...ux.ibm.com>
To:     Peter Zijlstra <peterz@...radead.org>
Cc:     Nicholas Piggin <npiggin@...il.com>,
        LKMM Maintainers -- Akira Yokosawa <akiyks@...il.com>,
        Andrea Parri <andrea.parri@...rulasolutions.com>,
        Boqun Feng <boqun.feng@...il.com>,
        David Howells <dhowells@...hat.com>,
        Daniel Lustig <dlustig@...dia.com>,
        Jade Alglave <j.alglave@....ac.uk>,
        Kernel development list <linux-kernel@...r.kernel.org>,
        Luc Maranget <luc.maranget@...ia.fr>,
        Alan Stern <stern@...land.harvard.edu>,
        Will Deacon <will.deacon@....com>
Subject: Re: [PATCH] Documentation: atomic_t.txt: Explain ordering provided
 by smp_mb__{before,after}_atomic()

On Tue, Apr 23, 2019 at 03:40:03PM +0200, Peter Zijlstra wrote:
> On Tue, Apr 23, 2019 at 06:30:10AM -0700, Paul E. McKenney wrote:
> > There are a great many that look like this:
> > 
> > 	smp_mb__before_atomic();
> > 	clear_bit(NFSD4_CLIENT_UPCALL_LOCK, &clp->cl_flags);
> > 	smp_mb__after_atomic();
> 
> Ooh, marvel at the comment describing the ordering there. Oh wait :-(
> So much for checkpatch.pl I suppose.

Especially if the code was in the kernel before checkpatch.pl started
asking for comments.  Which might or might not be the case with this
code.  No idea either way.

> I think the first is a release order for the 'LOCK' bit and the second
> is because of wake_up_bit() being a shitty interface.
> 
> So maybe that should've been:
> 
> 	clear_bit_unlock(NFSD4_CLIENT_UPCALL_LOCK, &clp->cl_flags);
> 	smp_mb__after_atomic();
> 	wake_up_bit(&clp->cl_flags, NFSD4_CLIENT_UPCALL_LOCK);
> 
> instead?

Quite possibly, but my brain is too fried to be sure.

							Thanx, Paul