Manuel Bouyer wrote:
>>>Remplace __insn_barrier() with x86_lfence() where appropriate.
>>>While here, replace a panic() with a return of error code in  
>>>xbdback.c.
>>
>>Why not make __insn_barrier() equivalent to x86_lfence() on all x86?
> 
> 
> This would probablt be a good idea, but isn't __insn_barrier() a
> gcc builtin ?

Would that really be correct?  I thought __insn_barries() was there
to stop gcc from reordering instructions, whereas x86_lfence() is
there to stop the processor from reordering loads and stores.

	-- Lennart