Re: [PATCH] ftrace: use only 5 byte nops for x86

[Jeremy Fitzhardinge]

Linus Torvalds wrote:
> I also suspect that we'd really be much better off just fixing the generic 
> NOP tables for the 5-byte nop. As far as I could tell, from all the 
> numbers that have been posted, absolutely _none_ show that there is any 
> point at all to the 2-instruction 3/2-byte sequence.
>
> So instead of having a magic special ftrace-only thing, why not just do it 
> right, and fix the generic 5-byte nop sequence?
>   

Well, there's two distinct issues here.  There's the need for a
single-instruction 5 byte nop, and the need for efficient nops.  It so
happens in this case that they're the same thing.  But in general, the
generic nop interface is intended to return the most efficient nop, not
an atomic nop (or with any other properties).  To handle it generically,
we'd either need to redefine the meaning of the existing nop-padding
interface, or add an "atomic nop" interface.

    J
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/