On Mon, 2019-09-23 at 13:42 -0700, John Hubbard wrote:
> Somewhere, there should be a short comment that explains how the following
> functions
> are meant to be used. And it should include the interaction with irqs, so
> maybe
> if you end up adding that combined wrapper function that does
On 9/20/19 12:50 PM, Leonardo Bras wrote:
> It's necessary to monitor lockless pagetable walks, in order to avoid doing
> THP splitting/collapsing during them.
>
> Some methods rely on local_irq_{save,restore}, but that can be slow on
> cases with a lot of cpus are used for the process.
>
> In
It's necessary to monitor lockless pagetable walks, in order to avoid doing
THP splitting/collapsing during them.
Some methods rely on local_irq_{save,restore}, but that can be slow on
cases with a lot of cpus are used for the process.
In order to speedup some cases, I propose a refcount-based