On Tue, May 31, 2011 at 11:25 PM, Johannes Weiner <hannes@cmpxchg.org>wrote:

> Once the per-memcg lru lists are exclusive, the unevictable page
> rescue scanner can no longer work on the global zone lru lists.
>
> This converts it to go through all memcgs and scan their respective
> unevictable lists instead.
>
> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
> ---
>  include/linux/memcontrol.h |    2 +
>  mm/memcontrol.c            |   11 +++++++++
>  mm/vmscan.c                |   53
> +++++++++++++++++++++++++++----------------
>  3 files changed, 46 insertions(+), 20 deletions(-)
>
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index cb02c00..56c1def 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -60,6 +60,8 @@ extern void mem_cgroup_cancel_charge_swapin(struct
> mem_cgroup *ptr);
>
>  extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct
> *mm,
>                                        gfp_t gfp_mask);
> +struct page *mem_cgroup_lru_to_page(struct zone *, struct mem_cgroup *,
> +                                   enum lru_list);
>

Did we miss a #ifdef case for this function? I got compile error by
disabling memcg.

--Ying


> extern void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru);
>  extern void mem_cgroup_del_lru_list(struct page *page, enum lru_list lru);
>  extern void mem_cgroup_rotate_reclaimable_page(struct page *page);
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 78ae4dd..d9d1a7e 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -656,6 +656,17 @@ static inline bool mem_cgroup_is_root(struct
> mem_cgroup *mem)
>  * When moving account, the page is not on LRU. It's isolated.
>  */
>
> +struct page *mem_cgroup_lru_to_page(struct zone *zone, struct mem_cgroup
> *mem,
> +                                   enum lru_list lru)
> +{
> +       struct mem_cgroup_per_zone *mz;
> +       struct page_cgroup *pc;
> +
> +       mz = mem_cgroup_zoneinfo(mem, zone_to_nid(zone), zone_idx(zone));
> +       pc = list_entry(mz->lists[lru].prev, struct page_cgroup, lru);
> +       return lookup_cgroup_page(pc);
> +}
> +
>  void mem_cgroup_del_lru_list(struct page *page, enum lru_list lru)
>  {
>        struct page_cgroup *pc;
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 9c51ec8..23fd2b1 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -3233,6 +3233,14 @@ void scan_mapping_unevictable_pages(struct
> address_space *mapping)
>
>  }
>
> +static struct page *lru_tailpage(struct zone *zone, struct mem_cgroup
> *mem,
> +                                enum lru_list lru)
> +{
> +       if (mem)
> +               return mem_cgroup_lru_to_page(zone, mem, lru);
> +       return lru_to_page(&zone->lru[lru].list);
> +}
> +
>  /**
>  * scan_zone_unevictable_pages - check unevictable list for evictable pages
>  * @zone - zone of which to scan the unevictable list
> @@ -3246,32 +3254,37 @@ void scan_mapping_unevictable_pages(struct
> address_space *mapping)
>  #define SCAN_UNEVICTABLE_BATCH_SIZE 16UL /* arbitrary lock hold batch size
> */
>  static void scan_zone_unevictable_pages(struct zone *zone)
>  {
> -       struct list_head *l_unevictable = &zone->lru[LRU_UNEVICTABLE].list;
> -       unsigned long scan;
> -       unsigned long nr_to_scan = zone_page_state(zone, NR_UNEVICTABLE);
> +       struct mem_cgroup *first, *mem = NULL;
>
> -       while (nr_to_scan > 0) {
> -               unsigned long batch_size = min(nr_to_scan,
> -
> SCAN_UNEVICTABLE_BATCH_SIZE);
> +       first = mem = mem_cgroup_hierarchy_walk(NULL, mem);
> +       do {
> +               unsigned long nr_to_scan;
>
> -               spin_lock_irq(&zone->lru_lock);
> -               for (scan = 0;  scan < batch_size; scan++) {
> -                       struct page *page = lru_to_page(l_unevictable);
> +               nr_to_scan = zone_nr_lru_pages(zone, mem, LRU_UNEVICTABLE);
> +               while (nr_to_scan > 0) {
> +                       unsigned long batch_size;
> +                       unsigned long scan;
>
> -                       if (!trylock_page(page))
> -                               continue;
> +                       batch_size = min(nr_to_scan,
> +                                        SCAN_UNEVICTABLE_BATCH_SIZE);
>
> -                       prefetchw_prev_lru_page(page, l_unevictable,
> flags);
> -
> -                       if (likely(PageLRU(page) && PageUnevictable(page)))
> -                               check_move_unevictable_page(page, zone);
> +                       spin_lock_irq(&zone->lru_lock);
> +                       for (scan = 0; scan < batch_size; scan++) {
> +                               struct page *page;
>
> -                       unlock_page(page);
> +                               page = lru_tailpage(zone, mem,
> LRU_UNEVICTABLE);
> +                               if (!trylock_page(page))
> +                                       continue;
> +                               if (likely(PageLRU(page) &&
> +                                          PageUnevictable(page)))
> +                                       check_move_unevictable_page(page,
> zone);
> +                               unlock_page(page);
> +                       }
> +                       spin_unlock_irq(&zone->lru_lock);
> +                       nr_to_scan -= batch_size;
>                }
> -               spin_unlock_irq(&zone->lru_lock);
> -
> -               nr_to_scan -= batch_size;
> -       }
> +               mem = mem_cgroup_hierarchy_walk(NULL, mem);
> +       } while (mem != first);
>  }
>
>
> --
> 1.7.5.2
>
>