[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: Lazy page reclamation on SMP machines: memory barriers

To: "Stephen C. Tweedie" <sct@dcs.ed.ac.uk>
Subject: Re: Lazy page reclamation on SMP machines: memory barriers
From: Linus Torvalds <torvalds@transmeta.com>
Date: Tue, 24 Mar 1998 16:11:56 -0800 (PST)
cc: linux-mm@kvack.org, linux-smp@vger.rutgers.edu
In-Reply-To: <199803242254.WAA03274@dax.dcs.ed.ac.uk>
Sender: owner-linux-mm@kvack.org

On Tue, 24 Mar 1998, Stephen C. Tweedie wrote:
> > Intel guarantees total ordering around any locked instruction, so the
> > spinlocks themselves act as the barriers. 
> 
> Fine.  Can we assume that spinlocks and atomic set/clear_bit
> instructions have the same semantics on other CPUs?

We can certainly guarantee that a spinlock has the necessary locking
semantics - anything else would make spinlocks useless. 

The other atomic instructions I'd be inclined to claim to be weakly
ordered.

		Linus

References:
- Re: Lazy page reclamation on SMP machines: memory barriers
  - From: "Stephen C. Tweedie" <sct@dcs.ed.ac.uk>

Prev by Date: Re: Lazy page reclamation on SMP machines: memory barriers
Next by Date: free_memory_available() bug in pre-91-1
Prev by thread: Re: Lazy page reclamation on SMP machines: memory barriers
Next by thread: Re: Lazy page reclamation on SMP machines: memory barriers
Index(es):
- Date
- Thread