mm, vmscan: cleanup lru size claculations

BugLink: http://bugs.launchpad.net/bugs/1672544
commit fd538803731e50367b7c59ce4ad3454426a3d671 upstream.

lruvec_lru_size returns the full size of the LRU list while we sometimes
need a value reduced only to eligible zones (e.g.  for lowmem requests).
inactive_list_is_low is one such user.  Later patches will add more of
them.  Add a new parameter to lruvec_lru_size and allow it filter out
zones which are not eligible for the given context.

Link: http://lkml.kernel.org/r/20170117103702.28542-2-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Tim Gardner <tim.gardner@canonical.com>

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index f4aac87adcc3555014f6215d6599b604c70388e6..82fc632fd11d1f70a40826778df66efff20d0c76 100644 (file)
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -779,7 +779,7 @@ static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec)
 #endif
 }
 
-extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru);
+extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx);
 
 #ifdef CONFIG_HAVE_MEMORY_PRESENT
 void memory_present(int nid, unsigned long start, unsigned long end);

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 532a2a750952daffed4e4242d36a449eb9ba8837..41c5617dd0f7ca4b615ef82ff989f903fb08db21 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -234,22 +234,39 @@ bool pgdat_reclaimable(struct pglist_data *pgdat)
                pgdat_reclaimable_pages(pgdat) * 6;
 }
 
-unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru)
+/**
+ * lruvec_lru_size -  Returns the number of pages on the given LRU list.
+ * @lruvec: lru vector
+ * @lru: lru to use
+ * @zone_idx: zones to consider (use MAX_NR_ZONES for the whole LRU list)
+ */
+unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx)
 {
+       unsigned long lru_size;
+       int zid;
+
        if (!mem_cgroup_disabled())
-               return mem_cgroup_get_lru_size(lruvec, lru);
+               lru_size = mem_cgroup_get_lru_size(lruvec, lru);
+       else
+               lru_size = node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru);
 
-       return node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru);
-}
+       for (zid = zone_idx + 1; zid < MAX_NR_ZONES; zid++) {
+               struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid];
+               unsigned long size;
 
-unsigned long lruvec_zone_lru_size(struct lruvec *lruvec, enum lru_list lru,
-                                  int zone_idx)
-{
-       if (!mem_cgroup_disabled())
-               return mem_cgroup_get_zone_lru_size(lruvec, lru, zone_idx);
+               if (!managed_zone(zone))
+                       continue;
+
+               if (!mem_cgroup_disabled())
+                       size = mem_cgroup_get_zone_lru_size(lruvec, lru, zid);
+               else
+                       size = zone_page_state(&lruvec_pgdat(lruvec)->node_zones[zid],
+                                      NR_ZONE_LRU_BASE + lru);
+               lru_size -= min(size, lru_size);
+       }
+
+       return lru_size;
 
-       return zone_page_state(&lruvec_pgdat(lruvec)->node_zones[zone_idx],
-                              NR_ZONE_LRU_BASE + lru);
 }
 
 /*
@@ -2028,11 +2045,10 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
                                                struct scan_control *sc)
 {
        unsigned long inactive_ratio;
-       unsigned long inactive;
-       unsigned long active;
+       unsigned long inactive, active;
+       enum lru_list inactive_lru = file * LRU_FILE;
+       enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE;
        unsigned long gb;
-       struct pglist_data *pgdat = lruvec_pgdat(lruvec);
-       int zid;
 
        /*
         * If we don't have swap space, anonymous page deactivation
@@ -2041,27 +2057,8 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
        if (!file && !total_swap_pages)
                return false;
 
-       inactive = lruvec_lru_size(lruvec, file * LRU_FILE);
-       active = lruvec_lru_size(lruvec, file * LRU_FILE + LRU_ACTIVE);
-
-       /*
-        * For zone-constrained allocations, it is necessary to check if
-        * deactivations are required for lowmem to be reclaimed. This
-        * calculates the inactive/active pages available in eligible zones.
-        */
-       for (zid = sc->reclaim_idx + 1; zid < MAX_NR_ZONES; zid++) {
-               struct zone *zone = &pgdat->node_zones[zid];
-               unsigned long inactive_zone, active_zone;
-
-               if (!managed_zone(zone))
-                       continue;
-
-               inactive_zone = lruvec_zone_lru_size(lruvec, file * LRU_FILE, zid);
-               active_zone = lruvec_zone_lru_size(lruvec, (file * LRU_FILE) + LRU_ACTIVE, zid);
-
-               inactive -= min(inactive, inactive_zone);
-               active -= min(active, active_zone);
-       }
+       inactive = lruvec_lru_size(lruvec, inactive_lru, sc->reclaim_idx);
+       active = lruvec_lru_size(lruvec, active_lru, sc->reclaim_idx);
 
        gb = (inactive + active) >> (30 - PAGE_SHIFT);
        if (gb)
@@ -2208,7 +2205,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
         * system is under heavy pressure.
         */
        if (!inactive_list_is_low(lruvec, true, sc) &&
-           lruvec_lru_size(lruvec, LRU_INACTIVE_FILE) >> sc->priority) {
+           lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, MAX_NR_ZONES) >> sc->priority) {
                scan_balance = SCAN_FILE;
                goto out;
        }
@@ -2234,10 +2231,10 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
         * anon in [0], file in [1]
         */
 
-       anon  = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON) +
-               lruvec_lru_size(lruvec, LRU_INACTIVE_ANON);
-       file  = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE) +
-               lruvec_lru_size(lruvec, LRU_INACTIVE_FILE);
+       anon  = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON, MAX_NR_ZONES) +
+               lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, MAX_NR_ZONES);
+       file  = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES) +
+               lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, MAX_NR_ZONES);
 
        spin_lock_irq(&pgdat->lru_lock);
        if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
@@ -2275,7 +2272,7 @@ out:
                        unsigned long size;
                        unsigned long scan;
 
-                       size = lruvec_lru_size(lruvec, lru);
+                       size = lruvec_lru_size(lruvec, lru, MAX_NR_ZONES);
                        scan = size >> sc->priority;
 
                        if (!scan && pass && force_scan)

diff --git a/mm/workingset.c b/mm/workingset.c
index abb58ffa3c64cb330d7e3d7aca7897aab0fea6a4..a67f5796b9951b617334a54adf06869bdc537f47 100644 (file)
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -267,7 +267,7 @@ bool workingset_refault(void *shadow)
        }
        lruvec = mem_cgroup_lruvec(pgdat, memcg);
        refault = atomic_long_read(&lruvec->inactive_age);
-       active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE);
+       active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES);
        rcu_read_unlock();
 
        /*