Re: [PATCH 6/7] microblaze: Implement architecture spinlock

[Peter Zijlstra]

On Thu, Feb 13, 2020 at 08:51:38AM +0100, Michal Simek wrote:
> On 12. 02. 20 16:47, Peter Zijlstra wrote:

> > 
> > That's a test-and-set spinlock if I read it correctly. Why? that's the
> > worst possible spinlock implementation possible.
> 
> This was written by Stefan and it is aligned with recommended
> implementation. What other options do we have?

A ticket lock should be simple enough; ARM has one you can borrow from.

The problem with TaS spinlocks is that they're unfair and exhibit
horrible starvation issues.