mm/compaction: do not call suitable_migration_target() on every page

[platform/adaptation/renesas_rcar/renesas_kernel.git] / mm / vmscan.c

diff --git a/mm/vmscan.c b/mm/vmscan.c
index a9c74b4..6ef484f 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1540,19 +1540,18 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
                 * If dirty pages are scanned that are not queued for IO, it
                 * implies that flushers are not keeping up. In this case, flag
                 * the zone ZONE_TAIL_LRU_DIRTY and kswapd will start writing
-                * pages from reclaim context. It will forcibly stall in the
-                * next check.
+                * pages from reclaim context.
                 */
                if (nr_unqueued_dirty == nr_taken)
                        zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY);
 
                /*
-                * In addition, if kswapd scans pages marked marked for
-                * immediate reclaim and under writeback (nr_immediate), it
-                * implies that pages are cycling through the LRU faster than
+                * If kswapd scans pages marked marked for immediate
+                * reclaim and under writeback (nr_immediate), it implies
+                * that pages are cycling through the LRU faster than
                 * they are written so also forcibly stall.
                 */
-               if (nr_unqueued_dirty == nr_taken || nr_immediate)
+               if (nr_immediate)
                        congestion_wait(BLK_RW_ASYNC, HZ/10);
        }
 
@@ -2502,10 +2501,17 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 
        for (i = 0; i <= ZONE_NORMAL; i++) {
                zone = &pgdat->node_zones[i];
+               if (!populated_zone(zone))
+                       continue;
+
                pfmemalloc_reserve += min_wmark_pages(zone);
                free_pages += zone_page_state(zone, NR_FREE_PAGES);
        }
 
+       /* If there are no reserves (unexpected config) then do not throttle */
+       if (!pfmemalloc_reserve)
+               return true;
+
        wmark_ok = free_pages > pfmemalloc_reserve / 2;
 
        /* kswapd must be awake if processes are being throttled */
@@ -2530,9 +2536,9 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
                                        nodemask_t *nodemask)
 {
+       struct zoneref *z;
        struct zone *zone;
-       int high_zoneidx = gfp_zone(gfp_mask);
-       pg_data_t *pgdat;
+       pg_data_t *pgdat = NULL;
 
        /*
         * Kernel threads should not be throttled as they may be indirectly
@@ -2551,10 +2557,34 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
        if (fatal_signal_pending(current))
                goto out;
 
-       /* Check if the pfmemalloc reserves are ok */
-       first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone);
-       pgdat = zone->zone_pgdat;
-       if (pfmemalloc_watermark_ok(pgdat))
+       /*
+        * Check if the pfmemalloc reserves are ok by finding the first node
+        * with a usable ZONE_NORMAL or lower zone. The expectation is that
+        * GFP_KERNEL will be required for allocating network buffers when
+        * swapping over the network so ZONE_HIGHMEM is unusable.
+        *
+        * Throttling is based on the first usable node and throttled processes
+        * wait on a queue until kswapd makes progress and wakes them. There
+        * is an affinity then between processes waking up and where reclaim
+        * progress has been made assuming the process wakes on the same node.
+        * More importantly, processes running on remote nodes will not compete
+        * for remote pfmemalloc reserves and processes on different nodes
+        * should make reasonable progress.
+        */
+       for_each_zone_zonelist_nodemask(zone, z, zonelist,
+                                       gfp_mask, nodemask) {
+               if (zone_idx(zone) > ZONE_NORMAL)
+                       continue;
+
+               /* Throttle based on the first usable node */
+               pgdat = zone->zone_pgdat;
+               if (pfmemalloc_watermark_ok(pgdat))
+                       goto out;
+               break;
+       }
+
+       /* If no zone was usable by the allocation flags then do not throttle */
+       if (!pgdat)
                goto out;
 
        /* Account for the throttling */
@@ -3285,7 +3315,10 @@ static int kswapd(void *p)
                }
        }
 
+       tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
        current->reclaim_state = NULL;
+       lockdep_clear_current_reclaim_state();
+
        return 0;
 }