Re: [PATCH] futex: fix shared futex operations on nommu

From	Rich Felker <dalias@libc.org>
Newsgroups	linux.kernel
Subject	Re: [PATCH] futex: fix shared futex operations on nommu
Date	2016-04-27 00:40 +0200
Message-ID	<rsjOb-7f9-37@gated-at.bofh.it> (permalink)
References	(1 earlier) <rs7WI-5oQ-19@gated-at.bofh.it> <rsdz5-1JO-19@gated-at.bofh.it> <rsdSq-2bx-7@gated-at.bofh.it> <rse26-2io-9@gated-at.bofh.it> <rsjEu-7bd-19@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On Tue, Apr 26, 2016 at 03:27:10PM -0700, Andrew Morton wrote:
> On Tue, 26 Apr 2016 12:27:39 -0400 Rich Felker <dalias@libc.org> wrote:
> 
> > On Tue, Apr 26, 2016 at 06:11:07PM +0200, Sebastian Andrzej Siewior wrote:
> > > * Rich Felker | 2016-04-26 11:53:44 [-0400]:
> > > 
> > > >The whole shared futex logic is meaningless for nommu. Perhaps I
> > > >should have written a better message, though.
> > > >
> > > >With MMU, shared futex keys need to identify the physical backing for
> > > >a memory address because it may be mapped at different addresses in
> > > >different processes (or even multiple times in the same process).
> > > >Without MMU this cannot happen. You only have physical addresses. So
> > > >the "private futex" behavior of using the virtual address as the key
> > > >is always correct (for both shared and private cases) on nommu
> > > >systems.
> > > 
> > > So using a shared futex on NOMMU does work but it would be more
> > > efficient to always use a private futex instead.
> > > Is this what you are saying?
> > 
> > No. What I'm saying is that the current code paths for shared futex
> > are mmu-specific. They neither work (due to different mm internals, I
> > think) nor make sense (due to lack of virtual addresses that map to
> > the same physical address) on nommu.
> > 
> > The private futex code paths are correct for either private or shared
> > futexes on nommu. This is both the natural theoretical prediction, and
> > confirmed by testing the patch.
> 
> It is apparent from Sebastian's questioning that a code comment will be
> needed, please.

Indeed, I agree. I'll work on a better patch. At least this sufficed
to get discussion started.

> Also, what specifically is the runtime effect of the patch?  Does the
> futex code presently misbehave on NOMMU when FUTEX_PRIVATE_FLAG is
> unset?

Without this patch, all futex ops without FUTEX_PRIVATE_FLAG fail with
EFAULT. It's been a while since I tracked down where the EFAULT is
generated but it's somewhere in the shared get-key vm logic.

If userspace treats this as an error, the corresponding pthread, etc.
functions fail. Otherwise, userspace just spins at 100% cpu retrying
FUTEX_WAIT and FUTEX_WAKE "works" fine as a nop against such a wait,
etc. (In a sense an always-failing implementation of futex is a
working implementation for the basic ops, just a highly suboptimal
one.)

Rich

Thread

[PATCH] futex: fix shared futex operations on nommu Rich Felker <dalias@libc.org> - 2016-04-26 03:10 +0200
  Re: [PATCH] futex: fix shared futex operations on nommu Sebastian Andrzej Siewior <bigeasy@linutronix.de> - 2016-04-26 12:00 +0200
    Re: [PATCH] futex: fix shared futex operations on nommu Rich Felker <dalias@libc.org> - 2016-04-26 18:00 +0200
      Re: [PATCH] futex: fix shared futex operations on nommu Sebastian Andrzej Siewior <bigeasy@linutronix.de> - 2016-04-26 18:20 +0200
        Re: [PATCH] futex: fix shared futex operations on nommu Rich Felker <dalias@libc.org> - 2016-04-26 18:30 +0200
          Re: [PATCH] futex: fix shared futex operations on nommu Andrew Morton <akpm@linux-foundation.org> - 2016-04-27 00:30 +0200
            Re: [PATCH] futex: fix shared futex operations on nommu Rich Felker <dalias@libc.org> - 2016-04-27 00:40 +0200
  Re: [PATCH] futex: fix shared futex operations on nommu Thomas Gleixner <tglx@linutronix.de> - 2016-04-27 15:50 +0200

csiph-web