On Thu, Jul 05, 2018 at 01:00:19PM -0400, Johannes Weiner wrote:
> This could be a matter of uptime, but the warning triggers on a thing
> that is supposed to happen everywhere eventually. Let's fix it.
Ahh! Thank you!
> xa_mk_value() doesn't understand that we're okay with it chopping off
> our upper-most bit. We shouldn't make this an API behavior, either, so
> let's fix the workingset code to always clear those bits before hand.
Makes sense. I'll just fold this in, if that's OK with you?
> Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx>
> ---
>
> diff --git a/mm/workingset.c b/mm/workingset.c
> index a466e731231d..1da19c04b6f7 100644
> --- a/mm/workingset.c
> +++ b/mm/workingset.c
> @@ -173,6 +173,7 @@ static unsigned int bucket_order __read_mostly;
> static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction)
> {
> eviction >>= bucket_order;
> + eviction &= EVICTION_MASK;
> eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid;
> eviction = (eviction << NODES_SHIFT) | pgdat->node_id;
>
