On 2022/10/6 18:15, Yafang Shao wrote:
> PGFREE and PGALLOC represent the number of freed and allocated pages.
> So the page order must be considered.
>
> Fixes: 44042b449872 ("mm/page_alloc: allow high-order pages to be stored on the per-cpu lists")
> Signed-off-by: Yafang Shao <laoar.shao@xxxxxxxxx>
LGTM. Thanks for fixing.
Reviewed-by: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Thanks,
Miaohe Lin
> Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
> ---
> mm/page_alloc.c | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index e5486d4..3c0ee3b 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -3440,7 +3440,7 @@ static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp,
> int pindex;
> bool free_high;
>
> - __count_vm_event(PGFREE);
> + __count_vm_events(PGFREE, 1 << order);
> pindex = order_to_pindex(migratetype, order);
> list_add(&page->pcp_list, &pcp->lists[pindex]);
> pcp->count += 1 << order;
> @@ -3808,7 +3808,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone,
> pcp_spin_unlock_irqrestore(pcp, flags);
> pcp_trylock_finish(UP_flags);
> if (page) {
> - __count_zid_vm_events(PGALLOC, page_zonenum(page), 1);
> + __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
> zone_statistics(preferred_zone, zone, 1);
> }
> return page;
>
