On 04/10/17 15:46, Masahiro Yamada wrote:
> The revmap_trees_mutex protects domain->revmap_tree. It is allowed
> to modify revmap_tree of two different domains concurrently. Change
> the global mutex to per-domain mutex.
>
> Signed-off-by: Masahiro Yamada <[email protected]>
Whilst this doesn't seem completely outlandish from a data-structure
PoV, I really wonder if that's an actual bottleneck. Do you have a
use-case where the rate of interrupt being mapped/unmapped is so high
that this becomes an actual contention point? If so, it would be good to
mention it in the commit message.
Thanks,
M.
--
Jazz is not dead. It just smells funny...
