xfs
[Top] [All Lists]

Re: [patch] mm: fix lockless pagecache reordering bug (was Re:

To: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Subject: Re: [patch] mm: fix lockless pagecache reordering bug (was Re:
From: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx>
Date: Mon, 5 Jan 2009 13:58:32 -0800
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>, Nick Piggin <npiggin@xxxxxxx>, Peter Klotz <peter.klotz@xxxxxx>, stable@xxxxxxxxxx, Linux Memory Management List <linux-mm@xxxxxxxxx>, Christoph Hellwig <hch@xxxxxxxxxxxxx>, Roman Kononov <kernel@xxxxxxxxxxxxxxxx>, linux-kernel@xxxxxxxxxxxxxxx, xfs@xxxxxxxxxxx, Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
In-reply-to: <1231189491.11687.22.camel@twins>
References: <20090105014821.GA367@xxxxxxxxxxxxx> <20090105041959.GC367@xxxxxxxxxxxxx> <20090105064838.GA5209@xxxxxxxxxxxxx> <49623384.2070801@xxxxxx> <20090105164135.GC32675@xxxxxxxxxxxxx> <alpine.LFD.2.00.0901050859430.3057@xxxxxxxxxxxxxxxxxxxxx> <20090105180008.GE32675@xxxxxxxxxxxxx> <alpine.LFD.2.00.0901051027011.3057@xxxxxxxxxxxxxxxxxxxxx> <20090105201258.GN6959@xxxxxxxxxxxxxxxxxx> <1231189491.11687.22.camel@twins>
Reply-to: paulmck@xxxxxxxxxxxxxxxxxx
User-agent: Mutt/1.5.15+20070412 (2007-04-11)
On Mon, Jan 05, 2009 at 10:04:51PM +0100, Peter Zijlstra wrote:
> On Mon, 2009-01-05 at 12:12 -0800, Paul E. McKenney wrote:
> > On Mon, Jan 05, 2009 at 10:44:27AM -0800, Linus Torvalds wrote:
> > > On Mon, 5 Jan 2009, Nick Piggin wrote:
> > > > On Mon, Jan 05, 2009 at 09:30:55AM -0800, Linus Torvalds wrote:
> > > > Putting an rcu_dereference there might work, but I think it misses a 
> > > > subtlety of this code.
> > > 
> > > No, _you_ miss the subtlety of something that can change under you.
> > > 
> > > Look at radix_tree_deref_slot(), and realize that without the 
> > > rcu_dereference(), the compiler would actually be allowed to think that 
> > > it 
> > > can re-load anything from *pslot several times. So without my one-liner 
> > > patch, the compiler can actually do this:
> > > 
> > >   register = load_from_memory(pslot)
> > >   if (radix_tree_is_indirect_ptr(register))
> > >           goto fail:
> > >   return load_from_memory(pslot);
> > > 
> > >    fail:
> > >   return RADIX_TREE_RETRY;
> > 
> > My guess is that Nick believes that the value in *pslot cannot change
> > in such as way as to cause radix_tree_is_indirect_ptr()'s return value
> > to change within a given RCU grace period, and that Linus disagrees.
> 
> Nick's belief would indeed be true IFF all modifying ops including all
> uses of radix_tree_replace_slot() are serialized wrt. each other.
> 
> However, since radix_tree_deref_slot() is the counterpart of
> radix_tree_replace_slot(), one would indeed expect rcu_dereference()
> therein, much like Linus suggests.
> 
> While what Nick says is true, the lifetime management of the data
> objects is arranged externally from the radix tree -- I still think we
> need the rcu_dereference() even for that argument, as we want to support
> RCU lifetime management as well.

Makes sense to me!

                                                        Thanx, Paul

<Prev in Thread] Current Thread [Next in Thread>