Merge branch 'modsplit-Oct31_2011' of git://git.kernel.org/pub/scm/linux/kernel/git...

[pandora-kernel.git] / mm / memcontrol.c

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9e38abd..6aff93c 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -33,6 +33,7 @@
 #include <linux/bit_spinlock.h>
 #include <linux/rcupdate.h>
 #include <linux/limits.h>
+#include <linux/export.h>
 #include <linux/mutex.h>
 #include <linux/rbtree.h>
 #include <linux/slab.h>
@@ -686,8 +687,8 @@ static bool __memcg_event_check(struct mem_cgroup *memcg, int target)
 {
        unsigned long val, next;
 
-       val = this_cpu_read(memcg->stat->events[MEM_CGROUP_EVENTS_COUNT]);
-       next = this_cpu_read(memcg->stat->targets[target]);
+       val = __this_cpu_read(memcg->stat->events[MEM_CGROUP_EVENTS_COUNT]);
+       next = __this_cpu_read(memcg->stat->targets[target]);
        /* from time_after() in jiffies.h */
        return ((long)next - (long)val < 0);
 }
@@ -696,7 +697,7 @@ static void __mem_cgroup_target_update(struct mem_cgroup *memcg, int target)
 {
        unsigned long val, next;
 
-       val = this_cpu_read(memcg->stat->events[MEM_CGROUP_EVENTS_COUNT]);
+       val = __this_cpu_read(memcg->stat->events[MEM_CGROUP_EVENTS_COUNT]);
 
        switch (target) {
        case MEM_CGROUP_TARGET_THRESH:
@@ -712,7 +713,7 @@ static void __mem_cgroup_target_update(struct mem_cgroup *memcg, int target)
                return;
        }
 
-       this_cpu_write(memcg->stat->targets[target], next);
+       __this_cpu_write(memcg->stat->targets[target], next);
 }
 
 /*
@@ -721,6 +722,7 @@ static void __mem_cgroup_target_update(struct mem_cgroup *memcg, int target)
  */
 static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
 {
+       preempt_disable();
        /* threshold event is triggered in finer grain than soft limit */
        if (unlikely(__memcg_event_check(memcg, MEM_CGROUP_TARGET_THRESH))) {
                mem_cgroup_threshold(memcg);
@@ -740,6 +742,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
                }
 #endif
        }
+       preempt_enable();
 }
 
 static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
@@ -993,6 +996,16 @@ void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru)
                return;
        pc = lookup_page_cgroup(page);
        VM_BUG_ON(PageCgroupAcctLRU(pc));
+       /*
+        * putback:                             charge:
+        * SetPageLRU                           SetPageCgroupUsed
+        * smp_mb                               smp_mb
+        * PageCgroupUsed && add to memcg LRU   PageLRU && add to memcg LRU
+        *
+        * Ensure that one of the two sides adds the page to the memcg
+        * LRU during a race.
+        */
+       smp_mb();
        if (!PageCgroupUsed(pc))
                return;
        /* Ensure pc->mem_cgroup is visible after reading PCG_USED. */
@@ -1044,7 +1057,16 @@ static void mem_cgroup_lru_add_after_commit(struct page *page)
        unsigned long flags;
        struct zone *zone = page_zone(page);
        struct page_cgroup *pc = lookup_page_cgroup(page);
-
+       /*
+        * putback:                             charge:
+        * SetPageLRU                           SetPageCgroupUsed
+        * smp_mb                               smp_mb
+        * PageCgroupUsed && add to memcg LRU   PageLRU && add to memcg LRU
+        *
+        * Ensure that one of the two sides adds the page to the memcg
+        * LRU during a race.
+        */
+       smp_mb();
        /* taking care of that the page is added to LRU while we commit it */
        if (likely(!PageLRU(page)))
                return;
@@ -1104,15 +1126,19 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *memcg)
        return ret;
 }
 
-static int calc_inactive_ratio(struct mem_cgroup *memcg, unsigned long *present_pages)
+int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg, struct zone *zone)
 {
-       unsigned long active;
+       unsigned long inactive_ratio;
+       int nid = zone_to_nid(zone);
+       int zid = zone_idx(zone);
        unsigned long inactive;
+       unsigned long active;
        unsigned long gb;
-       unsigned long inactive_ratio;
 
-       inactive = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_INACTIVE_ANON));
-       active = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_ACTIVE_ANON));
+       inactive = mem_cgroup_zone_nr_lru_pages(memcg, nid, zid,
+                                               BIT(LRU_INACTIVE_ANON));
+       active = mem_cgroup_zone_nr_lru_pages(memcg, nid, zid,
+                                             BIT(LRU_ACTIVE_ANON));
 
        gb = (inactive + active) >> (30 - PAGE_SHIFT);
        if (gb)
@@ -1120,39 +1146,20 @@ static int calc_inactive_ratio(struct mem_cgroup *memcg, unsigned long *present_
        else
                inactive_ratio = 1;
 
-       if (present_pages) {
-               present_pages[0] = inactive;
-               present_pages[1] = active;
-       }
-
-       return inactive_ratio;
+       return inactive * inactive_ratio < active;
 }
 
-int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg)
-{
-       unsigned long active;
-       unsigned long inactive;
-       unsigned long present_pages[2];
-       unsigned long inactive_ratio;
-
-       inactive_ratio = calc_inactive_ratio(memcg, present_pages);
-
-       inactive = present_pages[0];
-       active = present_pages[1];
-
-       if (inactive * inactive_ratio < active)
-               return 1;
-
-       return 0;
-}
-
-int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg)
+int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg, struct zone *zone)
 {
        unsigned long active;
        unsigned long inactive;
+       int zid = zone_idx(zone);
+       int nid = zone_to_nid(zone);
 
-       inactive = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_INACTIVE_FILE));
-       active = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_ACTIVE_FILE));
+       inactive = mem_cgroup_zone_nr_lru_pages(memcg, nid, zid,
+                                               BIT(LRU_INACTIVE_FILE));
+       active = mem_cgroup_zone_nr_lru_pages(memcg, nid, zid,
+                                             BIT(LRU_ACTIVE_FILE));
 
        return (active > inactive);
 }
@@ -1898,7 +1905,7 @@ bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask)
        if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current))
                return false;
        /* Give chance to dying process */
-       schedule_timeout(1);
+       schedule_timeout_uninterruptible(1);
        return true;
 }
 
@@ -4192,8 +4199,6 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
        }
 
 #ifdef CONFIG_DEBUG_VM
-       cb->fill(cb, "inactive_ratio", calc_inactive_ratio(mem_cont, NULL));
-
        {
                int nid, zid;
                struct mem_cgroup_per_zone *mz;
@@ -4742,7 +4747,6 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
        if (!pn)
                return 1;
 
-       memcg->info.nodeinfo[node] = pn;
        for (zone = 0; zone < MAX_NR_ZONES; zone++) {
                mz = &pn->zoneinfo[zone];
                for_each_lru(l)
@@ -4751,6 +4755,7 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
                mz->on_tree = false;
                mz->mem = memcg;
        }
+       memcg->info.nodeinfo[node] = pn;
        return 0;
 }