[parisc-linux-cvs] linux-2.6 jejb

[Grant Grundler]

On Sun, Aug 15, 2004 at 10:20:55AM -0400, James Bottomley wrote:
> This was rather subtle.  It turns out that gcc was doing a small
> amount of reordering around the file_lock because it doesn't see our
> spinlock implementation as being a barrier.


It's not clear to me how adding mb() to before the ldcw()
fixes this problem since ldcw() is an asm().
asm() is not instruction barrier?

mb() is a NOP on parisc because we have strongly ordered memory.

PA20 arch allows weakly ordered mem.
John Marvin was clear all implementations are strongly ordered.
(See the mail archive for discussion about this)

Though I'm not argueing against the commit since it obviously works
better than previous code.

thanks,
grant