On Mon, Apr 21, 2014 at 5:31 PM, Linus Torvalds
<torvalds@linux-foundation.org> wrote:
>
> Does this work for people? It *looks* sane. It compiles for me (tested
> on x86 that uses generic mmu gather, and on UM that does not).

Just to make it easier for people to test, here's both of them with
commit logs. I've committed them in my tree, but not pushed out, so I
can still edit them or add acks and tested-by's.

I think Russell and Tony are both on linux-arch, so they probably saw
at least part of this discussion flow past already, but just in case
I'm adding them explicitly to the cc, because both ia64 and arm seem
to implement their own version of TLB batching rather than use the
generic code. I *thought* the generic code was supposed to be generic
enough for arm and ia64 too, but if not, they'd need to do the proper
dirty bit batching in those private implementations.

             Linus