From: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Date: Mon, 23 Mar 2015 10:12:30 -0700
> Oh well. I'm actually somewhat surprised this didn't hit anything
> else. Doesn't networking also end up doing overlapping memmove() on
> the skb data occasionally?
The only case I can think of is when {en,de}capsulating VLANs in
software.
But those are really small header sized copies, and would never
trigger the unrolled loop which requires len >= 128.
A quick grep shows something similar for wireless WEP/WPA, but not
only are these small copies too but I don't have any wireless on
any of my sparc boxes :-)
It really is just SLAB/SLUB with large NR_CPU configurations.
--
To unsubscribe from this list: send the line "unsubscribe sparclinux" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
