@@ -18,6 +18,9 @@ struct page_reporting_dev_info {
/* Current state of page reporting */
atomic_t state;
+
+ /* Minimal order of page reporting */
+ unsigned int order;
};
/* Tear-down and bring-up for page reporting devices */
@@ -328,6 +328,10 @@ int page_reporting_register(struct page_reporting_dev_info *prdev)
goto err_out;
}
+ /* Use the page reporting order if it's specified by driver */
+ page_reporting_order = prdev->order ?
+ prdev->order : page_reporting_order;
+
/* initialize state and work structures */
atomic_set(&prdev->state, PAGE_REPORTING_IDLE);
INIT_DELAYED_WORK(&prdev->work, &page_reporting_process);
The page reporting order (threshold) is sticky to @pageblock_order by default. The page reporting can never be triggered because the freeing page can't come up with a free area like that huge. The situation becomes worse when the system memory becomes heavily fragmented. For example, the following configurations are used on ARM64 when 64KB base page size is enabled. In this specific case, the page reporting won't be triggered until the freeing page comes up with a 512MB free area. That's hard to be met, especially when the system memory becomes heavily fragmented. PAGE_SIZE: 64KB HPAGE_SIZE: 512MB pageblock_order: 13 (512MB) MAX_ORDER: 14 This allows the drivers to specify the page reporting order when the page reporting device is registered. It falls back to @pageblock_order if it's not specified by the driver. The existing users (hv_balloon and virtio_balloon) don't specify it and @pageblock_order is still taken as their page reporting order. So this shouldn't introduce any functional changes. Signed-off-by: Gavin Shan <gshan@redhat.com> --- include/linux/page_reporting.h | 3 +++ mm/page_reporting.c | 4 ++++ 2 files changed, 7 insertions(+)