get_page_from_freelist() checks many conditions for each zone, often with a big comment block explaining the conditions. Move the kswapd check and its comment into should_skip_kswapd_zone() to make the zone iteration cleaner to read. While moving this, also resolve a checkpatch warning which complains of a waitqueue_active() call with no corresponding comment explaining why the lockless use is OK in this case. No functional change intended. Reviewed-by: SJ Park Reviewed-by: Chris Down Reviewed-by: Zi Yan Reviewed-by: Gregory Price Reviewed-by: Dev Jain Tested-by: Chris Down Signed-off-by: Joshua Hahn --- mm/page_alloc.c | 49 +++++++++++++++++++++++++++++++------------------ 1 file changed, 31 insertions(+), 18 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 9e1261521b6a3..e7a7863e381ab 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3785,6 +3785,34 @@ static inline unsigned int alloc_flags_cma(gfp_t gfp_mask) return ALLOC_DEFAULT; } +/* + * If kswapd is already active on a node and the zone is below its kswapd + * watermark for this request, keep looking for other nodes that might be idle. + * This can happen if another process has NUMA bindings and is causing kswapd + * wakeups on only some nodes. Avoid accidental "node_reclaim_mode"-like + * behavior in this case. + */ +static inline bool +should_skip_kswapd_zone(struct zone *zone, unsigned int order, + const struct alloc_context *ac, gfp_t gfp_mask) +{ + unsigned long mark; + + /* + * This means kswapd is asleep, so don't skip the zone. This is a + * lockless check, since a stale result only affects zone selection. + */ + if (waitqueue_active(&zone->zone_pgdat->kswapd_wait)) + return false; + + if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) + mark = promo_wmark_pages(zone); + else + mark = high_wmark_pages(zone); + return !zone_watermark_fast(zone, order, mark, ac->highest_zoneidx, + 0, gfp_mask); +} + /* * get_page_from_freelist goes through the zonelist trying to allocate * a page. @@ -3796,9 +3824,6 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags, struct zoneref *z; struct zone *zone; struct pglist_data *last_pgdat = NULL; - enum zone_watermarks kswapd_watermark = - sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING ? - WMARK_PROMO : WMARK_HIGH; bool last_pgdat_dirty_ok = false; bool no_fallback; bool skip_kswapd_nodes = nr_online_nodes > 1; @@ -3865,22 +3890,10 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags, } } - /* - * If kswapd is already active on a node and the zone is below - * its kswapd watermark for this request, keep looking for - * other nodes that might be idle. This can happen if another - * process has NUMA bindings and is causing kswapd wakeups on - * only some nodes. Avoid accidental "node_reclaim_mode"-like - * behavior in this case. - */ if (skip_kswapd_nodes && - !waitqueue_active(&zone->zone_pgdat->kswapd_wait)) { - mark = wmark_pages(zone, kswapd_watermark); - if (!zone_watermark_fast(zone, order, mark, - ac->highest_zoneidx, 0, gfp_mask)) { - skipped_kswapd_nodes = true; - continue; - } + should_skip_kswapd_zone(zone, order, ac, gfp_mask)) { + skipped_kswapd_nodes = true; + continue; } cond_accept_memory(zone, order, alloc_flags); -- 2.53.1-Meta