mm/memcg: apply add/del_page to lruvec

Take lruvec further: pass it instead of zone to add_page_to_lru_list() and
del_page_from_lru_list(); and pagevec_lru_move_fn() pass lruvec down to
its target functions.

This cleanup eliminates a swathe of cruft in memcontrol.c, including
mem_cgroup_lru_add_list(), mem_cgroup_lru_del_list() and
mem_cgroup_lru_move_lists() - which never actually touched the lists.

In their place, mem_cgroup_page_lruvec() to decide the lruvec, previously
a side-effect of add, and mem_cgroup_update_lru_size() to maintain the
lru_size stats.

Whilst these are simplifications in their own right, the goal is to bring
the evaluation of lruvec next to the spin_locking of the lrus, in
preparation for a future patch.

Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Konstantin Khlebnikov <khlebnikov@openvz.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 24 insertions, 77 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 75198dac3fe8..bb8d7d3cf302 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1035,7 +1035,7 @@ EXPORT_SYMBOL(mem_cgroup_count_vm_event);
 /**
  * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg
  * @zone: zone of the wanted lruvec
- * @mem: memcg of the wanted lruvec
+ * @memcg: memcg of the wanted lruvec
  *
  * Returns the lru list vector holding pages for the given @zone and
  * @mem.  This can be the global zone lruvec, if the memory controller
@@ -1068,19 +1068,11 @@ struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
  */
 
 /**
- * mem_cgroup_lru_add_list - account for adding an lru page and return lruvec
- * @zone: zone of the page
+ * mem_cgroup_page_lruvec - return lruvec for adding an lru page
  * @page: the page
- * @lru: current lru
- *
- * This function accounts for @page being added to @lru, and returns
- * the lruvec for the given @zone and the memcg @page is charged to.
- *
- * The callsite is then responsible for physically linking the page to
- * the returned lruvec->lists[@lru].
+ * @zone: zone of the page
  */
-struct lruvec *mem_cgroup_lru_add_list(struct zone *zone, struct page *page,
-                                       enum lru_list lru)
+struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
 {
         struct mem_cgroup_per_zone *mz;
         struct mem_cgroup *memcg;
@@ -1093,7 +1085,7 @@ struct lruvec *mem_cgroup_lru_add_list(struct zone *zone, struct page *page,
         memcg = pc->mem_cgroup;
 
         /*
-         * Surreptitiously switch any uncharged page to root:
+         * Surreptitiously switch any uncharged offlist page to root:
          * an uncharged page off lru does nothing to secure
          * its former mem_cgroup from sudden removal.
          *
@@ -1101,65 +1093,35 @@ struct lruvec *mem_cgroup_lru_add_list(struct zone *zone, struct page *page,
          * under page_cgroup lock: between them, they make all uses
          * of pc->mem_cgroup safe.
          */
-        if (!PageCgroupUsed(pc) && memcg != root_mem_cgroup)
+        if (!PageLRU(page) && !PageCgroupUsed(pc) && memcg != root_mem_cgroup)
                 pc->mem_cgroup = memcg = root_mem_cgroup;
 
         mz = page_cgroup_zoneinfo(memcg, page);
-        /* compound_order() is stabilized through lru_lock */
-        mz->lru_size[lru] += 1 << compound_order(page);
         return &mz->lruvec;
 }
 
 /**
- * mem_cgroup_lru_del_list - account for removing an lru page
- * @page: the page
- * @lru: target lru
+ * mem_cgroup_update_lru_size - account for adding or removing an lru page
+ * @lruvec: mem_cgroup per zone lru vector
+ * @lru: index of lru list the page is sitting on
+ * @nr_pages: positive when adding or negative when removing
  *
- * This function accounts for @page being removed from @lru.
- *
- * The callsite is then responsible for physically unlinking
- * @page->lru.
+ * This function must be called when a page is added to or removed from an
+ * lru list.
  */
-void mem_cgroup_lru_del_list(struct page *page, enum lru_list lru)
+void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
+                                int nr_pages)
 {
         struct mem_cgroup_per_zone *mz;
-        struct mem_cgroup *memcg;
-        struct page_cgroup *pc;
+        unsigned long *lru_size;
 
         if (mem_cgroup_disabled())
                 return;
 
-        pc = lookup_page_cgroup(page);
-        memcg = pc->mem_cgroup;
-        VM_BUG_ON(!memcg);
-        mz = page_cgroup_zoneinfo(memcg, page);
-        /* huge page split is done under lru_lock. so, we have no races. */
-        VM_BUG_ON(mz->lru_size[lru] < (1 << compound_order(page)));
-        mz->lru_size[lru] -= 1 << compound_order(page);
-}
-
-/**
- * mem_cgroup_lru_move_lists - account for moving a page between lrus
- * @zone: zone of the page
- * @page: the page
- * @from: current lru
- * @to: target lru
- *
- * This function accounts for @page being moved between the lrus @from
- * and @to, and returns the lruvec for the given @zone and the memcg
- * @page is charged to.
- *
- * The callsite is then responsible for physically relinking
- * @page->lru to the returned lruvec->lists[@to].
- */
-struct lruvec *mem_cgroup_lru_move_lists(struct zone *zone,
-                                         struct page *page,
-                                         enum lru_list from,
-                                         enum lru_list to)
-{
-        /* XXX: Optimize this, especially for @from == @to */
-        mem_cgroup_lru_del_list(page, from);
-        return mem_cgroup_lru_add_list(zone, page, to);
+        mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
+        lru_size = mz->lru_size + lru;
+        *lru_size += nr_pages;
+        VM_BUG_ON((long)(*lru_size) < 0);
 }
 
 /*
@@ -1252,24 +1214,6 @@ int mem_cgroup_inactive_file_is_low(struct lruvec *lruvec)
         return (active > inactive);
 }
 
-struct zone_reclaim_stat *
-mem_cgroup_get_reclaim_stat_from_page(struct page *page)
-{
-        struct page_cgroup *pc;
-        struct mem_cgroup_per_zone *mz;
-
-        if (mem_cgroup_disabled())
-                return NULL;
-
-        pc = lookup_page_cgroup(page);
-        if (!PageCgroupUsed(pc))
-                return NULL;
-        /* Ensure pc->mem_cgroup is visible after reading PCG_USED. */
-        smp_rmb();
-        mz = page_cgroup_zoneinfo(pc->mem_cgroup, page);
-        return &mz->lruvec.reclaim_stat;
-}
-
 #define mem_cgroup_from_res_counter(counter, member)    \
         container_of(counter, struct mem_cgroup, member)
 
@@ -2509,6 +2453,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 {
         struct page_cgroup *pc = lookup_page_cgroup(page);
         struct zone *uninitialized_var(zone);
+        struct lruvec *lruvec;
         bool was_on_lru = false;
         bool anon;
 
@@ -2531,8 +2476,9 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
                 zone = page_zone(page);
                 spin_lock_irq(&zone->lru_lock);
                 if (PageLRU(page)) {
+                        lruvec = mem_cgroup_zone_lruvec(zone, pc->mem_cgroup);
                         ClearPageLRU(page);
-                        del_page_from_lru_list(zone, page, page_lru(page));
+                        del_page_from_lru_list(page, lruvec, page_lru(page));
                         was_on_lru = true;
                 }
         }
@@ -2550,9 +2496,10 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 
         if (lrucare) {
                 if (was_on_lru) {
+                        lruvec = mem_cgroup_zone_lruvec(zone, pc->mem_cgroup);
                         VM_BUG_ON(PageLRU(page));
                         SetPageLRU(page);
-                        add_page_to_lru_list(zone, page, page_lru(page));
+                        add_page_to_lru_list(page, lruvec, page_lru(page));
                 }
                 spin_unlock_irq(&zone->lru_lock);
         }