Re: Packet gets stuck in NOLOCK pfifo_fast qdisc

[Josh Hunt]

On 4/2/21 12:25 PM, Jiri Kosina wrote:
> On Thu, 3 Sep 2020, John Fastabend wrote:
>
> > > > At this point I fear we could consider reverting the NOLOCK stuff.
> > > > I personally would hate doing so, but it looks like NOLOCK benefits are
> > > > outweighed by its issues.
> > >
> > > I agree, NOLOCK brings more pains than gains. There are many race
> > > conditions hidden in generic qdisc layer, another one is enqueue vs.
> > > reset which is being discussed in another thread.
> >
> > Sure. Seems they crept in over time. I had some plans to write a
> > lockless HTB implementation. But with fq+EDT with BPF it seems that
> > it is no longer needed, we have a more generic/better solution.  So
> > I dropped it. Also most folks should really be using fq, fq_codel,
> > etc. by default anyways. Using pfifo_fast alone is not ideal IMO.
>
> Half a year later, we still have the NOLOCK implementation
> present, and pfifo_fast still does set the TCQ_F_NOLOCK flag on itself.
>
> And we've just been bitten by this very same race which appears to be
> still unfixed, with single packet being stuck in pfifo_fast qdisc
> basically indefinitely due to this very race that this whole thread began
> with back in 2019.
>
> Unless there are
>
> 	(a) any nice ideas how to solve this in an elegant way without
> 	    (re-)introducing extra spinlock (Cong's fix) or
>
> 	(b) any objections to revert as per the argumentation above
>
> I'll be happy to send a revert of the whole NOLOCK implementation next
> week.

Jiri

If you have a reproducer can you try 
https://lkml.org/lkml/2021/3/24/1485 ? If that doesn't work I think your 
suggestion of reverting nolock makes sense to me. We've moved to using 
fq as our default now b/c of this bug.

Josh