Re: [PATCH] x86 spinlock: Fix memory corruption on completing completions

[Oleg Nesterov <oleg@redhat.com>]

On 02/10, Jeremy Fitzhardinge wrote:
>
> On 02/10/2015 05:26 AM, Oleg Nesterov wrote:
> > On 02/10, Raghavendra K T wrote:
> >> Unfortunately xadd could result in head overflow as tail is high.
> >>
> >> The other option was repeated cmpxchg which is bad I believe.
> >> Any suggestions?
> > Stupid question... what if we simply move SLOWPATH from .tail to .head?
> > In this case arch_spin_unlock() could do xadd(tickets.head) and check
> > the result
>
> Well, right now, "tail" is manipulated by locked instructions by CPUs
> who are contending for the ticketlock, but head can be manipulated
> unlocked by the CPU which currently owns the ticketlock. If SLOWPATH
> moved into head, then non-owner CPUs would be touching head, requiring
> everyone to use locked instructions on it.
>
> That's the theory, but I don't see much (any?) code which depends on that.
>
> Ideally we could find a way so that pv ticketlocks could use a plain
> unlocked add for the unlock like the non-pv case, but I just don't see a
> way to do it.

I agree, and I have to admit I am not sure I fully understand why unlock
uses the locked add. Except we need a barrier to avoid the race with the
enter_slowpath() users, of course. Perhaps this is the only reason?

Anyway, I suggested this to avoid the overflow if we use xadd(), and I
guess we need the locked insn anyway if we want to eliminate the unsafe
read-after-unlock...

> > BTW. If we move "clear slowpath" into "lock" path, then probably trylock
> > should be changed too? Something like below, we just need to clear SLOWPATH
> > before cmpxchg.
>
> How important / widely used is trylock these days?

I am not saying this is that important. Just this looks more consistent imo
and we can do this for free.

Oleg.