vmscan: factor out kswapd sleeping logic from kswapd()

Currently, kswapd() has deep nesting and is slightly hard to read.  Clean
this up.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 86f8c34..cacdf66 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2371,6 +2371,50 @@ out:
        return sc.nr_reclaimed;
 }
 
+static void kswapd_try_to_sleep(pg_data_t *pgdat, int order)
+{
+       long remaining = 0;
+       DEFINE_WAIT(wait);
+
+       if (freezing(current) || kthread_should_stop())
+               return;
+
+       prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
+
+       /* Try to sleep for a short interval */
+       if (!sleeping_prematurely(pgdat, order, remaining)) {
+               remaining = schedule_timeout(HZ/10);
+               finish_wait(&pgdat->kswapd_wait, &wait);
+               prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
+       }
+
+       /*
+        * After a short sleep, check if it was a premature sleep. If not, then
+        * go fully to sleep until explicitly woken up.
+        */
+       if (!sleeping_prematurely(pgdat, order, remaining)) {
+               trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
+
+               /*
+                * vmstat counters are not perfectly accurate and the estimated
+                * value for counters such as NR_FREE_PAGES can deviate from the
+                * true value by nr_online_cpus * threshold. To avoid the zone
+                * watermarks being breached while under pressure, we reduce the
+                * per-cpu vmstat threshold while kswapd is awake and restore
+                * them before going back to sleep.
+                */
+               set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold);
+               schedule();
+               set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold);
+       } else {
+               if (remaining)
+                       count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY);
+               else
+                       count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY);
+       }
+       finish_wait(&pgdat->kswapd_wait, &wait);
+}
+
 /*
  * The background pageout daemon, started as a kernel thread
  * from the init process.
@@ -2389,7 +2433,7 @@ static int kswapd(void *p)
        unsigned long order;
        pg_data_t *pgdat = (pg_data_t*)p;
        struct task_struct *tsk = current;
-       DEFINE_WAIT(wait);
+
        struct reclaim_state reclaim_state = {
                .reclaimed_slab = 0,
        };
@@ -2421,7 +2465,6 @@ static int kswapd(void *p)
                unsigned long new_order;
                int ret;
 
-               prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
                new_order = pgdat->kswapd_max_order;
                pgdat->kswapd_max_order = 0;
                if (order < new_order) {
@@ -2431,52 +2474,9 @@ static int kswapd(void *p)
                         */
                        order = new_order;
                } else {
-                       if (!freezing(current) && !kthread_should_stop()) {
-                               long remaining = 0;
-
-                               /* Try to sleep for a short interval */
-                               if (!sleeping_prematurely(pgdat, order, remaining)) {
-                                       remaining = schedule_timeout(HZ/10);
-                                       finish_wait(&pgdat->kswapd_wait, &wait);
-                                       prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
-                               }
-
-                               /*
-                                * After a short sleep, check if it was a
-                                * premature sleep. If not, then go fully
-                                * to sleep until explicitly woken up
-                                */
-                               if (!sleeping_prematurely(pgdat, order, remaining)) {
-                                       trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
-
-                                       /*
-                                        * vmstat counters are not perfectly
-                                        * accurate and the estimated value
-                                        * for counters such as NR_FREE_PAGES
-                                        * can deviate from the true value by
-                                        * nr_online_cpus * threshold. To
-                                        * avoid the zone watermarks being
-                                        * breached while under pressure, we
-                                        * reduce the per-cpu vmstat threshold
-                                        * while kswapd is awake and restore
-                                        * them before going back to sleep.
-                                        */
-                                       set_pgdat_percpu_threshold(pgdat,
-                                               calculate_normal_threshold);
-                                       schedule();
-                                       set_pgdat_percpu_threshold(pgdat,
-                                               calculate_pressure_threshold);
-                               } else {
-                                       if (remaining)
-                                               count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY);
-                                       else
-                                               count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY);
-                               }
-                       }
-
+                       kswapd_try_to_sleep(pgdat, order);
                        order = pgdat->kswapd_max_order;
                }
-               finish_wait(&pgdat->kswapd_wait, &wait);
 
                ret = try_to_freeze();
                if (kthread_should_stop())