[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20200213080043.GF14897@hirez.programming.kicks-ass.net>
Date: Thu, 13 Feb 2020 09:00:43 +0100
From: Peter Zijlstra <peterz@...radead.org>
To: Michal Simek <michal.simek@...inx.com>
Cc: linux-kernel@...r.kernel.org, monstr@...str.eu, git@...inx.com,
arnd@...db.de, Stefan Asserhall <stefan.asserhall@...inx.com>,
Ingo Molnar <mingo@...hat.com>, Will Deacon <will@...nel.org>
Subject: Re: [PATCH 6/7] microblaze: Implement architecture spinlock
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.
Powered by blists - more mailing lists