Re: [patch 2/21] reduced locking in buffer.c

[Andrew Morton <akpm@zip.com.au>]

Linus Torvalds wrote:
> 
> On Sun, 11 Aug 2002, Andrew Morton wrote:
> >
> > Resend.  Replace the buffer lru spinlock protection with
> > local_irq_disable and a cross-CPU call to invalidate them.
> 
> This almost certainly breaks on sparc, where CPU cross-calls are
> non-maskable, so local_irq_disable doesn't do anything for them.
> 
> Talk to Davem about this - there may be some workaround.

I have discussed it with David - he said it's OK in 2.5, but
not in 2.4, and he has eyeballed the diff.

However there's another thing to think about:

	local_irq_disable();
	atomic_inc();

If the architecture implements atomic_inc with spinlocks, this will
schedule with interrupts off with CONFIG_PREEMPT=y, I expect.

I can fix that with a preempt_disable() in there, but ick.