Re: tty breakage in X (Was: tty vs workqueue oddities)

[Benjamin Herrenschmidt <benh@kernel.crashing.org>]

On Thu, 2011-06-02 at 11:07 +0100, Alan Cox wrote:
> On Thu, 02 Jun 2011 18:37:01 +1000
> Benjamin Herrenschmidt <benh@kernel.crashing.org> wrote:
> 
> > On Thu, 2011-06-02 at 17:17 +1000, Benjamin Herrenschmidt wrote:
> > > Hi Alan !
> > 
> > Hrm... looks like Alan is innocent ... interesting tho, the culprit
> > patch looks like something he (or somebody known to understand the tty
> > code :-) should have reviewed.
> 
> I did review it, and ran it and it worked beautifully on my system 8)
> 
> I do wonder if it has an interaction with Linus earlier changes to queue
> flushing as I've never tested both together.

I just noticed it doesn't happen (or if it does, it recovers fast enough
to not be noticable) on an SMP machine (dual G5). However, if I boot the
same machine with maxcpus=1, the problem is back. A simple "dmesg" in
gnome terminal shows it.

However, on that much faster machine, it also recovers a lot faster. On
the powerbook, it hangs a few minutes, on the G5 it hangs a few seconds.

I don't have the bandwidth to dive into the workqueue/tty before this
week-end, I'll give it a shot next week if nobody beats me to it.

Cheers,
Ben.