On Wed, Sep 25, 2002 at 12:47:19AM -0700, David S. Miller wrote:
> Ingo said that arches that cannot do cmpxchg in hardware should
> provide spinlock-based version.
> That doesn't make any sense.
Yes, I know.
> If cmpxchg cannot work with user bits of memory, like
> cmpxchg is supposed to, it's really a crutch more than
> anything else.
Ingo's argument was that since there is only one place in code that accesses
that variable (map->page), it is safe to rely on such a crippled
cmpxchg implementation.
To not retell you whole story and avoid the role of broken phone,
here's info on prevous discussion on this topic:
Subject: Re: [patch] generic-pidhash-2.5.36-D4, BK-curr
September 20, From Ingo Molnar <mingo@elte.hu>, Message-ID: <Pine.LNX.4.44.0209201139290.1261-100000@localhost.localdomain>
September 20, From Ingo Molnar <mingo@elte.hu>, Message-ID: <Pine.LNX.4.44.0209201828090.8547-100000@localhost.localdomain>
Bye,
Oleg
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/