17 files changed, 579 insertions, 331 deletions

diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index c8d62d49a44e..bb01e298f260 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -1,3 +1,12 @@
+config DEBUG_PAGEALLOC
+        bool "Debug page memory allocations"
+        depends on DEBUG_KERNEL && ARCH_SUPPORTS_DEBUG_PAGEALLOC
+        depends on !HIBERNATION || !PPC && !SPARC
+        ---help---
+          Unmap pages from the kernel linear mapping after free_pages().
+          This results in a large slowdown, but helps to find certain types
+          of memory corruptions.
+
 config WANT_PAGE_DEBUG_FLAGS
         bool
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 126d3973b3d1..fc11974f2bee 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -565,6 +565,24 @@ void wait_on_page_bit(struct page *page, int bit_nr)
 EXPORT_SYMBOL(wait_on_page_bit);
 
 /**
+ * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
+ * @page - Page defining the wait queue of interest
+ * @waiter - Waiter to add to the queue
+ *
+ * Add an arbitrary @waiter to the wait queue for the nominated @page.
+ */
+void add_page_wait_queue(struct page *page, wait_queue_t *waiter)
+{
+        wait_queue_head_t *q = page_waitqueue(page);
+        unsigned long flags;
+
+        spin_lock_irqsave(&q->lock, flags);
+        __add_wait_queue(q, waiter);
+        spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL_GPL(add_page_wait_queue);
+
+/**
  * unlock_page - unlock a locked page
  * @page: the page
  *
@@ -2463,6 +2481,9 @@ EXPORT_SYMBOL(generic_file_aio_write);
  * (presumably at page->private).  If the release was successful, return `1'.
  * Otherwise return zero.
  *
+ * This may also be called if PG_fscache is set on a page, indicating that the
+ * page is known to the local caching routines.
+ *
  * The @gfp_mask argument specifies whether I/O may be performed to release
  * this page (__GFP_IO), and whether the call may block (__GFP_WAIT & __GFP_FS).
  *
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 0c04615651b7..427dfe3ce78c 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -89,8 +89,8 @@ do_xip_mapping_read(struct address_space *mapping,
                         }
                 }
                 nr = nr - offset;
-                if (nr > len)
-                        nr = len;
+                if (nr > len - copied)
+                        nr = len - copied;
 
                 error = mapping->a_ops->get_xip_mem(mapping, index, 0,
                                                         &xip_mem, &xip_pfn);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 8e4be9cb2a6a..2fc6d6c48238 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -27,6 +27,7 @@
 #include <linux/backing-dev.h>
 #include <linux/bit_spinlock.h>
 #include <linux/rcupdate.h>
+#include <linux/limits.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
@@ -95,6 +96,15 @@ static s64 mem_cgroup_read_stat(struct mem_cgroup_stat *stat,
         return ret;
 }
 
+static s64 mem_cgroup_local_usage(struct mem_cgroup_stat *stat)
+{
+        s64 ret;
+
+        ret = mem_cgroup_read_stat(stat, MEM_CGROUP_STAT_CACHE);
+        ret += mem_cgroup_read_stat(stat, MEM_CGROUP_STAT_RSS);
+        return ret;
+}
+
 /*
  * per-zone information in memory controller.
  */
@@ -154,9 +164,9 @@ struct mem_cgroup {
 
         /*
          * While reclaiming in a hiearchy, we cache the last child we
-         * reclaimed from. Protected by hierarchy_mutex
+         * reclaimed from.
          */
-        struct mem_cgroup *last_scanned_child;
+        int last_scanned_child;
         /*
          * Should the accounting and control be hierarchical, per subtree?
          */
@@ -247,7 +257,7 @@ page_cgroup_zoneinfo(struct page_cgroup *pc)
         return mem_cgroup_zoneinfo(mem, nid, zid);
 }
 
-static unsigned long mem_cgroup_get_all_zonestat(struct mem_cgroup *mem,
+static unsigned long mem_cgroup_get_local_zonestat(struct mem_cgroup *mem,
                                         enum lru_list idx)
 {
         int nid, zid;
@@ -286,6 +296,9 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
 {
         struct mem_cgroup *mem = NULL;
+
+        if (!mm)
+                return NULL;
         /*
          * Because we have no locks, mm->owner's may be being moved to other
          * cgroup. We use css_tryget() here even if this looks
@@ -308,6 +321,42 @@ static bool mem_cgroup_is_obsolete(struct mem_cgroup *mem)
         return css_is_removed(&mem->css);
 }
 
+
+/*
+ * Call callback function against all cgroup under hierarchy tree.
+ */
+static int mem_cgroup_walk_tree(struct mem_cgroup *root, void *data,
+                          int (*func)(struct mem_cgroup *, void *))
+{
+        int found, ret, nextid;
+        struct cgroup_subsys_state *css;
+        struct mem_cgroup *mem;
+
+        if (!root->use_hierarchy)
+                return (*func)(root, data);
+
+        nextid = 1;
+        do {
+                ret = 0;
+                mem = NULL;
+
+                rcu_read_lock();
+                css = css_get_next(&mem_cgroup_subsys, nextid, &root->css,
+                                   &found);
+                if (css && css_tryget(css))
+                        mem = container_of(css, struct mem_cgroup, css);
+                rcu_read_unlock();
+
+                if (mem) {
+                        ret = (*func)(mem, data);
+                        css_put(&mem->css);
+                }
+                nextid = found + 1;
+        } while (!ret && css);
+
+        return ret;
+}
+
 /*
  * Following LRU functions are allowed to be used without PCG_LOCK.
  * Operations are called by routine of global LRU independently from memcg.
@@ -441,31 +490,24 @@ void mem_cgroup_move_lists(struct page *page,
 int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
 {
         int ret;
+        struct mem_cgroup *curr = NULL;
 
         task_lock(task);
-        ret = task->mm && mm_match_cgroup(task->mm, mem);
+        rcu_read_lock();
+        curr = try_get_mem_cgroup_from_mm(task->mm);
+        rcu_read_unlock();
         task_unlock(task);
+        if (!curr)
+                return 0;
+        if (curr->use_hierarchy)
+                ret = css_is_ancestor(&curr->css, &mem->css);
+        else
+                ret = (curr == mem);
+        css_put(&curr->css);
         return ret;
 }
 
 /*
- * Calculate mapped_ratio under memory controller. This will be used in
- * vmscan.c for deteremining we have to reclaim mapped pages.
- */
-int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)
-{
-        long total, rss;
-
-        /*
-         * usage is recorded in bytes. But, here, we assume the number of
-         * physical pages can be represented by "long" on any arch.
-         */
-        total = (long) (mem->res.usage >> PAGE_SHIFT) + 1L;
-        rss = (long)mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS);
-        return (int)((rss * 100L) / total);
-}
-
-/*
  * prev_priority control...this will be used in memory reclaim path.
  */
 int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem)
@@ -501,8 +543,8 @@ static int calc_inactive_ratio(struct mem_cgroup *memcg, unsigned long *present_
         unsigned long gb;
         unsigned long inactive_ratio;
 
-        inactive = mem_cgroup_get_all_zonestat(memcg, LRU_INACTIVE_ANON);
-        active = mem_cgroup_get_all_zonestat(memcg, LRU_ACTIVE_ANON);
+        inactive = mem_cgroup_get_local_zonestat(memcg, LRU_INACTIVE_ANON);
+        active = mem_cgroup_get_local_zonestat(memcg, LRU_ACTIVE_ANON);
 
         gb = (inactive + active) >> (30 - PAGE_SHIFT);
         if (gb)
@@ -629,172 +671,202 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 #define mem_cgroup_from_res_counter(counter, member)    \
         container_of(counter, struct mem_cgroup, member)
 
-/*
- * This routine finds the DFS walk successor. This routine should be
- * called with hierarchy_mutex held
- */
-static struct mem_cgroup *
-__mem_cgroup_get_next_node(struct mem_cgroup *curr, struct mem_cgroup *root_mem)
+static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem)
 {
-        struct cgroup *cgroup, *curr_cgroup, *root_cgroup;
-
-        curr_cgroup = curr->css.cgroup;
-        root_cgroup = root_mem->css.cgroup;
+        if (do_swap_account) {
+                if (res_counter_check_under_limit(&mem->res) &&
+                        res_counter_check_under_limit(&mem->memsw))
+                        return true;
+        } else
+                if (res_counter_check_under_limit(&mem->res))
+                        return true;
+        return false;
+}
 
-        if (!list_empty(&curr_cgroup->children)) {
-                /*
-                 * Walk down to children
-                 */
-                cgroup = list_entry(curr_cgroup->children.next,
-                                                struct cgroup, sibling);
-                curr = mem_cgroup_from_cont(cgroup);
-                goto done;
-        }
+static unsigned int get_swappiness(struct mem_cgroup *memcg)
+{
+        struct cgroup *cgrp = memcg->css.cgroup;
+        unsigned int swappiness;
 
-visit_parent:
-        if (curr_cgroup == root_cgroup) {
-                /* caller handles NULL case */
-                curr = NULL;
-                goto done;
-        }
+        /* root ? */
+        if (cgrp->parent == NULL)
+                return vm_swappiness;
 
-        /*
-         * Goto next sibling
-         */
-        if (curr_cgroup->sibling.next != &curr_cgroup->parent->children) {
-                cgroup = list_entry(curr_cgroup->sibling.next, struct cgroup,
-                                                sibling);
-                curr = mem_cgroup_from_cont(cgroup);
-                goto done;
-        }
+        spin_lock(&memcg->reclaim_param_lock);
+        swappiness = memcg->swappiness;
+        spin_unlock(&memcg->reclaim_param_lock);
 
-        /*
-         * Go up to next parent and next parent's sibling if need be
-         */
-        curr_cgroup = curr_cgroup->parent;
-        goto visit_parent;
+        return swappiness;
+}
 
-done:
-        return curr;
+static int mem_cgroup_count_children_cb(struct mem_cgroup *mem, void *data)
+{
+        int *val = data;
+        (*val)++;
+        return 0;
 }
 
-/*
- * Visit the first child (need not be the first child as per the ordering
- * of the cgroup list, since we track last_scanned_child) of @mem and use
- * that to reclaim free pages from.
+/**
+ * mem_cgroup_print_mem_info: Called from OOM with tasklist_lock held in read mode.
+ * @memcg: The memory cgroup that went over limit
+ * @p: Task that is going to be killed
+ *
+ * NOTE: @memcg and @p's mem_cgroup can be different when hierarchy is
+ * enabled
  */
-static struct mem_cgroup *
-mem_cgroup_get_next_node(struct mem_cgroup *root_mem)
+void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 {
-        struct cgroup *cgroup;
-        struct mem_cgroup *orig, *next;
-        bool obsolete;
-
+        struct cgroup *task_cgrp;
+        struct cgroup *mem_cgrp;
         /*
-         * Scan all children under the mem_cgroup mem
+         * Need a buffer in BSS, can't rely on allocations. The code relies
+         * on the assumption that OOM is serialized for memory controller.
+         * If this assumption is broken, revisit this code.
          */
-        mutex_lock(&mem_cgroup_subsys.hierarchy_mutex);
+        static char memcg_name[PATH_MAX];
+        int ret;
+
+        if (!memcg)
+                return;
 
-        orig = root_mem->last_scanned_child;
-        obsolete = mem_cgroup_is_obsolete(orig);
 
-        if (list_empty(&root_mem->css.cgroup->children)) {
+        rcu_read_lock();
+
+        mem_cgrp = memcg->css.cgroup;
+        task_cgrp = task_cgroup(p, mem_cgroup_subsys_id);
+
+        ret = cgroup_path(task_cgrp, memcg_name, PATH_MAX);
+        if (ret < 0) {
                 /*
-                 * root_mem might have children before and last_scanned_child
-                 * may point to one of them. We put it later.
+                 * Unfortunately, we are unable to convert to a useful name
+                 * But we'll still print out the usage information
                  */
-                if (orig)
-                        VM_BUG_ON(!obsolete);
-                next = NULL;
+                rcu_read_unlock();
                 goto done;
         }
+        rcu_read_unlock();
 
-        if (!orig || obsolete) {
-                cgroup = list_first_entry(&root_mem->css.cgroup->children,
-                                struct cgroup, sibling);
-                next = mem_cgroup_from_cont(cgroup);
-        } else
-                next = __mem_cgroup_get_next_node(orig, root_mem);
+        printk(KERN_INFO "Task in %s killed", memcg_name);
 
+        rcu_read_lock();
+        ret = cgroup_path(mem_cgrp, memcg_name, PATH_MAX);
+        if (ret < 0) {
+                rcu_read_unlock();
+                goto done;
+        }
+        rcu_read_unlock();
+
+        /*
+         * Continues from above, so we don't need an KERN_ level
+         */
+        printk(KERN_CONT " as a result of limit of %s\n", memcg_name);
 done:
-        if (next)
-                mem_cgroup_get(next);
-        root_mem->last_scanned_child = next;
-        if (orig)
-                mem_cgroup_put(orig);
-        mutex_unlock(&mem_cgroup_subsys.hierarchy_mutex);
-        return (next) ? next : root_mem;
+
+        printk(KERN_INFO "memory: usage %llukB, limit %llukB, failcnt %llu\n",
+                res_counter_read_u64(&memcg->res, RES_USAGE) >> 10,
+                res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10,
+                res_counter_read_u64(&memcg->res, RES_FAILCNT));
+        printk(KERN_INFO "memory+swap: usage %llukB, limit %llukB, "
+                "failcnt %llu\n",
+                res_counter_read_u64(&memcg->memsw, RES_USAGE) >> 10,
+                res_counter_read_u64(&memcg->memsw, RES_LIMIT) >> 10,
+                res_counter_read_u64(&memcg->memsw, RES_FAILCNT));
 }
 
-static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem)
+/*
+ * This function returns the number of memcg under hierarchy tree. Returns
+ * 1(self count) if no children.
+ */
+static int mem_cgroup_count_children(struct mem_cgroup *mem)
 {
-        if (do_swap_account) {
-                if (res_counter_check_under_limit(&mem->res) &&
-                        res_counter_check_under_limit(&mem->memsw))
-                        return true;
-        } else
-                if (res_counter_check_under_limit(&mem->res))
-                        return true;
-        return false;
+        int num = 0;
+        mem_cgroup_walk_tree(mem, &num, mem_cgroup_count_children_cb);
+        return num;
 }
 
-static unsigned int get_swappiness(struct mem_cgroup *memcg)
+/*
+ * Visit the first child (need not be the first child as per the ordering
+ * of the cgroup list, since we track last_scanned_child) of @mem and use
+ * that to reclaim free pages from.
+ */
+static struct mem_cgroup *
+mem_cgroup_select_victim(struct mem_cgroup *root_mem)
 {
-        struct cgroup *cgrp = memcg->css.cgroup;
-        unsigned int swappiness;
+        struct mem_cgroup *ret = NULL;
+        struct cgroup_subsys_state *css;
+        int nextid, found;
 
-        /* root ? */
-        if (cgrp->parent == NULL)
-                return vm_swappiness;
+        if (!root_mem->use_hierarchy) {
+                css_get(&root_mem->css);
+                ret = root_mem;
+        }
 
-        spin_lock(&memcg->reclaim_param_lock);
-        swappiness = memcg->swappiness;
-        spin_unlock(&memcg->reclaim_param_lock);
+        while (!ret) {
+                rcu_read_lock();
+                nextid = root_mem->last_scanned_child + 1;
+                css = css_get_next(&mem_cgroup_subsys, nextid, &root_mem->css,
+                                   &found);
+                if (css && css_tryget(css))
+                        ret = container_of(css, struct mem_cgroup, css);
+
+                rcu_read_unlock();
+                /* Updates scanning parameter */
+                spin_lock(&root_mem->reclaim_param_lock);
+                if (!css) {
+                        /* this means start scan from ID:1 */
+                        root_mem->last_scanned_child = 0;
+                } else
+                        root_mem->last_scanned_child = found;
+                spin_unlock(&root_mem->reclaim_param_lock);
+        }
 
-        return swappiness;
+        return ret;
 }
 
 /*
- * Dance down the hierarchy if needed to reclaim memory. We remember the
- * last child we reclaimed from, so that we don't end up penalizing
- * one child extensively based on its position in the children list.
+ * Scan the hierarchy if needed to reclaim memory. We remember the last child
+ * we reclaimed from, so that we don't end up penalizing one child extensively
+ * based on its position in the children list.
  *
  * root_mem is the original ancestor that we've been reclaim from.
+ *
+ * We give up and return to the caller when we visit root_mem twice.
+ * (other groups can be removed while we're walking....)
+ *
+ * If shrink==true, for avoiding to free too much, this returns immedieately.
  */
 static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
-                                                gfp_t gfp_mask, bool noswap)
-{
-        struct mem_cgroup *next_mem;
-        int ret = 0;
-
-        /*
-         * Reclaim unconditionally and don't check for return value.
-         * We need to reclaim in the current group and down the tree.
-         * One might think about checking for children before reclaiming,
-         * but there might be left over accounting, even after children
-         * have left.
-         */
-        ret += try_to_free_mem_cgroup_pages(root_mem, gfp_mask, noswap,
-                                           get_swappiness(root_mem));
-        if (mem_cgroup_check_under_limit(root_mem))
-                return 1;       /* indicate reclaim has succeeded */
-        if (!root_mem->use_hierarchy)
-                return ret;
-
-        next_mem = mem_cgroup_get_next_node(root_mem);
-
-        while (next_mem != root_mem) {
-                if (mem_cgroup_is_obsolete(next_mem)) {
-                        next_mem = mem_cgroup_get_next_node(root_mem);
+                                   gfp_t gfp_mask, bool noswap, bool shrink)
+{
+        struct mem_cgroup *victim;
+        int ret, total = 0;
+        int loop = 0;
+
+        while (loop < 2) {
+                victim = mem_cgroup_select_victim(root_mem);
+                if (victim == root_mem)
+                        loop++;
+                if (!mem_cgroup_local_usage(&victim->stat)) {
+                        /* this cgroup's local usage == 0 */
+                        css_put(&victim->css);
                         continue;
                 }
-                ret += try_to_free_mem_cgroup_pages(next_mem, gfp_mask, noswap,
-                                                   get_swappiness(next_mem));
+                /* we use swappiness of local cgroup */
+                ret = try_to_free_mem_cgroup_pages(victim, gfp_mask, noswap,
+                                                   get_swappiness(victim));
+                css_put(&victim->css);
+                /*
+                 * At shrinking usage, we can't check we should stop here or
+                 * reclaim more. It's depends on callers. last_scanned_child
+                 * will work enough for keeping fairness under tree.
+                 */
+                if (shrink)
+                        return ret;
+                total += ret;
                 if (mem_cgroup_check_under_limit(root_mem))
-                        return 1;       /* indicate reclaim has succeeded */
-                next_mem = mem_cgroup_get_next_node(root_mem);
+                        return 1 + total;
         }
-        return ret;
+        return total;
 }
 
 bool mem_cgroup_oom_called(struct task_struct *task)
@@ -813,6 +885,19 @@ bool mem_cgroup_oom_called(struct task_struct *task)
         rcu_read_unlock();
         return ret;
 }
+
+static int record_last_oom_cb(struct mem_cgroup *mem, void *data)
+{
+        mem->last_oom_jiffies = jiffies;
+        return 0;
+}
+
+static void record_last_oom(struct mem_cgroup *mem)
+{
+        mem_cgroup_walk_tree(mem, NULL, record_last_oom_cb);
+}
+
+
 /*
  * Unlike exported interface, "oom" parameter is added. if oom==true,
  * oom-killer can be invoked.
@@ -875,7 +960,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
                         goto nomem;
 
                 ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, gfp_mask,
-                                                        noswap);
+                                                        noswap, false);
                 if (ret)
                         continue;
 
@@ -895,7 +980,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
                                 mutex_lock(&memcg_tasklist);
                                 mem_cgroup_out_of_memory(mem_over_limit, gfp_mask);
                                 mutex_unlock(&memcg_tasklist);
-                                mem_over_limit->last_oom_jiffies = jiffies;
+                                record_last_oom(mem_over_limit);
                         }
                         goto nomem;
                 }
@@ -906,20 +991,55 @@ nomem:
         return -ENOMEM;
 }
 
+
+/*
+ * A helper function to get mem_cgroup from ID. must be called under
+ * rcu_read_lock(). The caller must check css_is_removed() or some if
+ * it's concern. (dropping refcnt from swap can be called against removed
+ * memcg.)
+ */
+static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
+{
+        struct cgroup_subsys_state *css;
+
+        /* ID 0 is unused ID */
+        if (!id)
+                return NULL;
+        css = css_lookup(&mem_cgroup_subsys, id);
+        if (!css)
+                return NULL;
+        return container_of(css, struct mem_cgroup, css);
+}
+
 static struct mem_cgroup *try_get_mem_cgroup_from_swapcache(struct page *page)
 {
         struct mem_cgroup *mem;
+        struct page_cgroup *pc;
+        unsigned short id;
         swp_entry_t ent;
 
+        VM_BUG_ON(!PageLocked(page));
+
         if (!PageSwapCache(page))
                 return NULL;
 
-        ent.val = page_private(page);
-        mem = lookup_swap_cgroup(ent);
-        if (!mem)
-                return NULL;
-        if (!css_tryget(&mem->css))
-                return NULL;
+        pc = lookup_page_cgroup(page);
+        /*
+         * Used bit of swapcache is solid under page lock.
+         */
+        if (PageCgroupUsed(pc)) {
+                mem = pc->mem_cgroup;
+                if (mem && !css_tryget(&mem->css))
+                        mem = NULL;
+        } else {
+                ent.val = page_private(page);
+                id = lookup_swap_cgroup(ent);
+                rcu_read_lock();
+                mem = mem_cgroup_lookup(id);
+                if (mem && !css_tryget(&mem->css))
+                        mem = NULL;
+                rcu_read_unlock();
+        }
         return mem;
 }
 
@@ -1118,6 +1238,10 @@ int mem_cgroup_newpage_charge(struct page *page,
                                 MEM_CGROUP_CHARGE_TYPE_MAPPED, NULL);
 }
 
+static void
+__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
+                                        enum charge_type ctype);
+
 int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
                                 gfp_t gfp_mask)
 {
@@ -1154,16 +1278,6 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
                 unlock_page_cgroup(pc);
         }
 
-        if (do_swap_account && PageSwapCache(page)) {
-                mem = try_get_mem_cgroup_from_swapcache(page);
-                if (mem)
-                        mm = NULL;
-                  else
-                        mem = NULL;
-                /* SwapCache may be still linked to LRU now. */
-                mem_cgroup_lru_del_before_commit_swapcache(page);
-        }
-
         if (unlikely(!mm && !mem))
                 mm = &init_mm;
 
@@ -1171,22 +1285,16 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
                 return mem_cgroup_charge_common(page, mm, gfp_mask,
                                 MEM_CGROUP_CHARGE_TYPE_CACHE, NULL);
 
-        ret = mem_cgroup_charge_common(page, mm, gfp_mask,
-                                MEM_CGROUP_CHARGE_TYPE_SHMEM, mem);
-        if (mem)
-                css_put(&mem->css);
-        if (PageSwapCache(page))
-                mem_cgroup_lru_add_after_commit_swapcache(page);
+        /* shmem */
+        if (PageSwapCache(page)) {
+                ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem);
+                if (!ret)
+                        __mem_cgroup_commit_charge_swapin(page, mem,
+                                        MEM_CGROUP_CHARGE_TYPE_SHMEM);
+        } else
+                ret = mem_cgroup_charge_common(page, mm, gfp_mask,
+                                        MEM_CGROUP_CHARGE_TYPE_SHMEM, mem);
 
-        if (do_swap_account && !ret && PageSwapCache(page)) {
-                swp_entry_t ent = {.val = page_private(page)};
-                /* avoid double counting */
-                mem = swap_cgroup_record(ent, NULL);
-                if (mem) {
-                        res_counter_uncharge(&mem->memsw, PAGE_SIZE);
-                        mem_cgroup_put(mem);
-                }
-        }
         return ret;
 }
 
@@ -1229,7 +1337,9 @@ charge_cur_mm:
         return __mem_cgroup_try_charge(mm, mask, ptr, true);
 }
 
-void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
+static void
+__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
+                                        enum charge_type ctype)
 {
         struct page_cgroup *pc;
 
@@ -1239,7 +1349,7 @@ void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
                 return;
         pc = lookup_page_cgroup(page);
         mem_cgroup_lru_del_before_commit_swapcache(page);
-        __mem_cgroup_commit_charge(ptr, pc, MEM_CGROUP_CHARGE_TYPE_MAPPED);
+        __mem_cgroup_commit_charge(ptr, pc, ctype);
         mem_cgroup_lru_add_after_commit_swapcache(page);
         /*
          * Now swap is on-memory. This means this page may be
@@ -1250,18 +1360,32 @@ void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
          */
         if (do_swap_account && PageSwapCache(page)) {
                 swp_entry_t ent = {.val = page_private(page)};
+                unsigned short id;
                 struct mem_cgroup *memcg;
-                memcg = swap_cgroup_record(ent, NULL);
+
+                id = swap_cgroup_record(ent, 0);
+                rcu_read_lock();
+                memcg = mem_cgroup_lookup(id);
                 if (memcg) {
+                        /*
+                         * This recorded memcg can be obsolete one. So, avoid
+                         * calling css_tryget
+                         */
                         res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
                         mem_cgroup_put(memcg);
                 }
-
+                rcu_read_unlock();
         }
         /* add this page(page_cgroup) to the LRU we want. */
 
 }
 
+void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
+{
+        __mem_cgroup_commit_charge_swapin(page, ptr,
+                                        MEM_CGROUP_CHARGE_TYPE_MAPPED);
+}
+
 void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem)
 {
         if (mem_cgroup_disabled())
@@ -1324,8 +1448,8 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
         res_counter_uncharge(&mem->res, PAGE_SIZE);
         if (do_swap_account && (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT))
                 res_counter_uncharge(&mem->memsw, PAGE_SIZE);
-
         mem_cgroup_charge_statistics(mem, pc, false);
+
         ClearPageCgroupUsed(pc);
         /*
          * pc->mem_cgroup is not cleared here. It will be accessed when it's
@@ -1377,7 +1501,7 @@ void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
                                         MEM_CGROUP_CHARGE_TYPE_SWAPOUT);
         /* record memcg information */
         if (do_swap_account && memcg) {
-                swap_cgroup_record(ent, memcg);
+                swap_cgroup_record(ent, css_id(&memcg->css));
                 mem_cgroup_get(memcg);
         }
         if (memcg)
@@ -1392,15 +1516,23 @@ void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
 void mem_cgroup_uncharge_swap(swp_entry_t ent)
 {
         struct mem_cgroup *memcg;
+        unsigned short id;
 
         if (!do_swap_account)
                 return;
 
-        memcg = swap_cgroup_record(ent, NULL);
+        id = swap_cgroup_record(ent, 0);
+        rcu_read_lock();
+        memcg = mem_cgroup_lookup(id);
         if (memcg) {
+                /*
+                 * We uncharge this because swap is freed.
+                 * This memcg can be obsolete one. We avoid calling css_tryget
+                 */
                 res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
                 mem_cgroup_put(memcg);
         }
+        rcu_read_unlock();
 }
 #endif
 
@@ -1508,7 +1640,8 @@ int mem_cgroup_shrink_usage(struct page *page,
                 return 0;
 
         do {
-                progress = mem_cgroup_hierarchical_reclaim(mem, gfp_mask, true);
+                progress = mem_cgroup_hierarchical_reclaim(mem,
+                                        gfp_mask, true, false);
                 progress += mem_cgroup_check_under_limit(mem);
         } while (!progress && --retry);
 
@@ -1523,11 +1656,21 @@ static DEFINE_MUTEX(set_limit_mutex);
 static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
                                 unsigned long long val)
 {
-
-        int retry_count = MEM_CGROUP_RECLAIM_RETRIES;
+        int retry_count;
         int progress;
         u64 memswlimit;
         int ret = 0;
+        int children = mem_cgroup_count_children(memcg);
+        u64 curusage, oldusage;
+
+        /*
+         * For keeping hierarchical_reclaim simple, how long we should retry
+         * is depends on callers. We set our retry-count to be function
+         * of # of children which we should visit in this loop.
+         */
+        retry_count = MEM_CGROUP_RECLAIM_RETRIES * children;
+
+        oldusage = res_counter_read_u64(&memcg->res, RES_USAGE);
 
         while (retry_count) {
                 if (signal_pending(current)) {
@@ -1553,8 +1696,13 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
                         break;
 
                 progress = mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL,
-                                                           false);
-                if (!progress)                  retry_count--;
+                                                   false, true);
+                curusage = res_counter_read_u64(&memcg->res, RES_USAGE);
+                /* Usage is reduced ? */
+                if (curusage >= oldusage)
+                        retry_count--;
+                else
+                        oldusage = curusage;
         }
 
         return ret;
@@ -1563,13 +1711,16 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
                                 unsigned long long val)
 {
-        int retry_count = MEM_CGROUP_RECLAIM_RETRIES;
+        int retry_count;
         u64 memlimit, oldusage, curusage;
-        int ret;
+        int children = mem_cgroup_count_children(memcg);
+        int ret = -EBUSY;
 
         if (!do_swap_account)
                 return -EINVAL;
-
+        /* see mem_cgroup_resize_res_limit */
+        retry_count = children * MEM_CGROUP_RECLAIM_RETRIES;
+        oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
         while (retry_count) {
                 if (signal_pending(current)) {
                         ret = -EINTR;
@@ -1593,11 +1744,13 @@ int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
                 if (!ret)
                         break;
 
-                oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
-                mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, true);
+                mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, true, true);
                 curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
+                /* Usage is reduced ? */
                 if (curusage >= oldusage)
                         retry_count--;
+                else
+                        oldusage = curusage;
         }
         return ret;
 }
@@ -1893,54 +2046,90 @@ static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
         return 0;
 }
 
-static const struct mem_cgroup_stat_desc {
-        const char *msg;
-        u64 unit;
-} mem_cgroup_stat_desc[] = {
-        [MEM_CGROUP_STAT_CACHE] = { "cache", PAGE_SIZE, },
-        [MEM_CGROUP_STAT_RSS] = { "rss", PAGE_SIZE, },
-        [MEM_CGROUP_STAT_PGPGIN_COUNT] = {"pgpgin", 1, },
-        [MEM_CGROUP_STAT_PGPGOUT_COUNT] = {"pgpgout", 1, },
+
+/* For read statistics */
+enum {
+        MCS_CACHE,
+        MCS_RSS,
+        MCS_PGPGIN,
+        MCS_PGPGOUT,
+        MCS_INACTIVE_ANON,
+        MCS_ACTIVE_ANON,
+        MCS_INACTIVE_FILE,
+        MCS_ACTIVE_FILE,
+        MCS_UNEVICTABLE,
+        NR_MCS_STAT,
+};
+
+struct mcs_total_stat {
+        s64 stat[NR_MCS_STAT];
+};
+
+struct {
+        char *local_name;
+        char *total_name;
+} memcg_stat_strings[NR_MCS_STAT] = {
+        {"cache", "total_cache"},
+        {"rss", "total_rss"},
+        {"pgpgin", "total_pgpgin"},
+        {"pgpgout", "total_pgpgout"},
+        {"inactive_anon", "total_inactive_anon"},
+        {"active_anon", "total_active_anon"},
+        {"inactive_file", "total_inactive_file"},
+        {"active_file", "total_active_file"},
+        {"unevictable", "total_unevictable"}
 };
 
+
+static int mem_cgroup_get_local_stat(struct mem_cgroup *mem, void *data)
+{
+        struct mcs_total_stat *s = data;
+        s64 val;
+
+        /* per cpu stat */
+        val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_CACHE);
+        s->stat[MCS_CACHE] += val * PAGE_SIZE;
+        val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS);
+        s->stat[MCS_RSS] += val * PAGE_SIZE;
+        val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGIN_COUNT);
+        s->stat[MCS_PGPGIN] += val;
+        val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGOUT_COUNT);
+        s->stat[MCS_PGPGOUT] += val;
+
+        /* per zone stat */
+        val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_ANON);
+        s->stat[MCS_INACTIVE_ANON] += val * PAGE_SIZE;
+        val = mem_cgroup_get_local_zonestat(mem, LRU_ACTIVE_ANON);
+        s->stat[MCS_ACTIVE_ANON] += val * PAGE_SIZE;
+        val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_FILE);
+        s->stat[MCS_INACTIVE_FILE] += val * PAGE_SIZE;
+        val = mem_cgroup_get_local_zonestat(mem, LRU_ACTIVE_FILE);
+        s->stat[MCS_ACTIVE_FILE] += val * PAGE_SIZE;
+        val = mem_cgroup_get_local_zonestat(mem, LRU_UNEVICTABLE);
+        s->stat[MCS_UNEVICTABLE] += val * PAGE_SIZE;
+        return 0;
+}
+
+static void
+mem_cgroup_get_total_stat(struct mem_cgroup *mem, struct mcs_total_stat *s)
+{
+        mem_cgroup_walk_tree(mem, s, mem_cgroup_get_local_stat);
+}
+
 static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
                                  struct cgroup_map_cb *cb)
 {
         struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont);
-        struct mem_cgroup_stat *stat = &mem_cont->stat;
+        struct mcs_total_stat mystat;
         int i;
 
-        for (i = 0; i < ARRAY_SIZE(stat->cpustat[0].count); i++) {
-                s64 val;
+        memset(&mystat, 0, sizeof(mystat));
+        mem_cgroup_get_local_stat(mem_cont, &mystat);
 
-                val = mem_cgroup_read_stat(stat, i);
-                val *= mem_cgroup_stat_desc[i].unit;
-                cb->fill(cb, mem_cgroup_stat_desc[i].msg, val);
-        }
-        /* showing # of active pages */
-        {
-                unsigned long active_anon, inactive_anon;
-                unsigned long active_file, inactive_file;
-                unsigned long unevictable;
-
-                inactive_anon = mem_cgroup_get_all_zonestat(mem_cont,
-                                                LRU_INACTIVE_ANON);
-                active_anon = mem_cgroup_get_all_zonestat(mem_cont,
-                                                LRU_ACTIVE_ANON);
-                inactive_file = mem_cgroup_get_all_zonestat(mem_cont,
-                                                LRU_INACTIVE_FILE);
-                active_file = mem_cgroup_get_all_zonestat(mem_cont,
-                                                LRU_ACTIVE_FILE);
-                unevictable = mem_cgroup_get_all_zonestat(mem_cont,
-                                                        LRU_UNEVICTABLE);
-
-                cb->fill(cb, "active_anon", (active_anon) * PAGE_SIZE);
-                cb->fill(cb, "inactive_anon", (inactive_anon) * PAGE_SIZE);
-                cb->fill(cb, "active_file", (active_file) * PAGE_SIZE);
-                cb->fill(cb, "inactive_file", (inactive_file) * PAGE_SIZE);
-                cb->fill(cb, "unevictable", unevictable * PAGE_SIZE);
+        for (i = 0; i < NR_MCS_STAT; i++)
+                cb->fill(cb, memcg_stat_strings[i].local_name, mystat.stat[i]);
 
-        }
+        /* Hierarchical information */
         {
                 unsigned long long limit, memsw_limit;
                 memcg_get_hierarchical_limit(mem_cont, &limit, &memsw_limit);
@@ -1949,6 +2138,12 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
                         cb->fill(cb, "hierarchical_memsw_limit", memsw_limit);
         }
 
+        memset(&mystat, 0, sizeof(mystat));
+        mem_cgroup_get_total_stat(mem_cont, &mystat);
+        for (i = 0; i < NR_MCS_STAT; i++)
+                cb->fill(cb, memcg_stat_strings[i].total_name, mystat.stat[i]);
+
+
 #ifdef CONFIG_DEBUG_VM
         cb->fill(cb, "inactive_ratio", calc_inactive_ratio(mem_cont, NULL));
 
@@ -2178,6 +2373,8 @@ static void __mem_cgroup_free(struct mem_cgroup *mem)
 {
         int node;
 
+        free_css_id(&mem_cgroup_subsys, &mem->css);
+
         for_each_node_state(node, N_POSSIBLE)
                 free_mem_cgroup_per_zone_info(mem, node);
 
@@ -2228,11 +2425,12 @@ static struct cgroup_subsys_state * __ref
 mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 {
         struct mem_cgroup *mem, *parent;
+        long error = -ENOMEM;
         int node;
 
         mem = mem_cgroup_alloc();
         if (!mem)
-                return ERR_PTR(-ENOMEM);
+                return ERR_PTR(error);
 
         for_each_node_state(node, N_POSSIBLE)
                 if (alloc_mem_cgroup_per_zone_info(mem, node))
@@ -2260,7 +2458,7 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
                 res_counter_init(&mem->res, NULL);
                 res_counter_init(&mem->memsw, NULL);
         }
-        mem->last_scanned_child = NULL;
+        mem->last_scanned_child = 0;
         spin_lock_init(&mem->reclaim_param_lock);
 
         if (parent)
@@ -2269,26 +2467,22 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
         return &mem->css;
 free_out:
         __mem_cgroup_free(mem);
-        return ERR_PTR(-ENOMEM);
+        return ERR_PTR(error);
 }
 
-static void mem_cgroup_pre_destroy(struct cgroup_subsys *ss,
+static int mem_cgroup_pre_destroy(struct cgroup_subsys *ss,
                                         struct cgroup *cont)
 {
         struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
-        mem_cgroup_force_empty(mem, false);
+
+        return mem_cgroup_force_empty(mem, false);
 }
 
 static void mem_cgroup_destroy(struct cgroup_subsys *ss,
                                 struct cgroup *cont)
 {
         struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
-        struct mem_cgroup *last_scanned_child = mem->last_scanned_child;
 
-        if (last_scanned_child) {
-                VM_BUG_ON(!mem_cgroup_is_obsolete(last_scanned_child));
-                mem_cgroup_put(last_scanned_child);
-        }
         mem_cgroup_put(mem);
 }
 
@@ -2327,6 +2521,7 @@ struct cgroup_subsys mem_cgroup_subsys = {
         .populate = mem_cgroup_populate,
         .attach = mem_cgroup_move_task,
         .early_init = 0,
+        .use_id = 1,
 };
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
diff --git a/mm/migrate.c b/mm/migrate.c
index a9eff3f092f6..068655d8f883 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -250,7 +250,7 @@ out:
  * The number of remaining references must be:
  * 1 for anonymous pages without a mapping
  * 2 for pages with a mapping
- * 3 for pages with a mapping and PagePrivate set.
+ * 3 for pages with a mapping and PagePrivate/PagePrivate2 set.
  */
 static int migrate_page_move_mapping(struct address_space *mapping,
                 struct page *newpage, struct page *page)
@@ -270,7 +270,7 @@ static int migrate_page_move_mapping(struct address_space *mapping,
         pslot = radix_tree_lookup_slot(&mapping->page_tree,
                                         page_index(page));
 
-        expected_count = 2 + !!PagePrivate(page);
+        expected_count = 2 + !!page_has_private(page);
         if (page_count(page) != expected_count ||
                         (struct page *)radix_tree_deref_slot(pslot) != page) {
                 spin_unlock_irq(&mapping->tree_lock);
@@ -386,7 +386,7 @@ EXPORT_SYMBOL(fail_migrate_page);
 
 /*
  * Common logic to directly migrate a single page suitable for
- * pages that do not use PagePrivate.
+ * pages that do not use PagePrivate/PagePrivate2.
  *
  * Pages are locked upon entry and exit.
  */
@@ -522,7 +522,7 @@ static int fallback_migrate_page(struct address_space *mapping,
          * Buffers may be managed in a filesystem specific way.
          * We must have no buffers or drop them.
          */
-        if (PagePrivate(page) &&
+        if (page_has_private(page) &&
             !try_to_release_page(page, GFP_KERNEL))
                 return -EAGAIN;
 
@@ -655,7 +655,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
          * free the metadata, so the page can be freed.
          */
         if (!page->mapping) {
-                if (!PageAnon(page) && PagePrivate(page)) {
+                if (!PageAnon(page) && page_has_private(page)) {
                         /*
                          * Go direct to try_to_free_buffers() here because
                          * a) that's what try_to_release_page() would do anyway
diff --git a/mm/mmap.c b/mm/mmap.c
index 1abb9185a686..4a3841186c11 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2481,7 +2481,4 @@ void mm_drop_all_locks(struct mm_struct *mm)
  */
 void __init mmap_init(void)
 {
-        vm_area_cachep = kmem_cache_create("vm_area_struct",
-                        sizeof(struct vm_area_struct), 0,
-                        SLAB_PANIC, NULL);
 }
diff --git a/mm/nommu.c b/mm/nommu.c
index 2fcf47d449b4..72eda4aee2cb 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -69,7 +69,7 @@ int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
 int sysctl_nr_trim_pages = 1; /* page trimming behaviour */
 int heap_stack_gap = 0;
 
-atomic_t mmap_pages_allocated;
+atomic_long_t mmap_pages_allocated;
 
 EXPORT_SYMBOL(mem_map);
 EXPORT_SYMBOL(num_physpages);
@@ -463,12 +463,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
  */
 void __init mmap_init(void)
 {
-        vm_region_jar = kmem_cache_create("vm_region_jar",
-                                          sizeof(struct vm_region), 0,
-                                          SLAB_PANIC, NULL);
-        vm_area_cachep = kmem_cache_create("vm_area_struct",
-                                           sizeof(struct vm_area_struct), 0,
-                                           SLAB_PANIC, NULL);
+        vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC);
 }
 
 /*
@@ -486,27 +481,24 @@ static noinline void validate_nommu_regions(void)
                 return;
 
         last = rb_entry(lastp, struct vm_region, vm_rb);
-        if (unlikely(last->vm_end <= last->vm_start))
-                BUG();
-        if (unlikely(last->vm_top < last->vm_end))
-                BUG();
+        BUG_ON(unlikely(last->vm_end <= last->vm_start));
+        BUG_ON(unlikely(last->vm_top < last->vm_end));
 
         while ((p = rb_next(lastp))) {
                 region = rb_entry(p, struct vm_region, vm_rb);
                 last = rb_entry(lastp, struct vm_region, vm_rb);
 
-                if (unlikely(region->vm_end <= region->vm_start))
-                        BUG();
-                if (unlikely(region->vm_top < region->vm_end))
-                        BUG();
-                if (unlikely(region->vm_start < last->vm_top))
-                        BUG();
+                BUG_ON(unlikely(region->vm_end <= region->vm_start));
+                BUG_ON(unlikely(region->vm_top < region->vm_end));
+                BUG_ON(unlikely(region->vm_start < last->vm_top));
 
                 lastp = p;
         }
 }
 #else
-#define validate_nommu_regions() do {} while(0)
+static void validate_nommu_regions(void)
+{
+}
 #endif
 
 /*
@@ -563,16 +555,17 @@ static void free_page_series(unsigned long from, unsigned long to)
                 struct page *page = virt_to_page(from);
 
                 kdebug("- free %lx", from);
-                atomic_dec(&mmap_pages_allocated);
+                atomic_long_dec(&mmap_pages_allocated);
                 if (page_count(page) != 1)
-                        kdebug("free page %p [%d]", page, page_count(page));
+                        kdebug("free page %p: refcount not one: %d",
+                               page, page_count(page));
                 put_page(page);
         }
 }
 
 /*
  * release a reference to a region
- * - the caller must hold the region semaphore, which this releases
+ * - the caller must hold the region semaphore for writing, which this releases
  * - the region may not have been added to the tree yet, in which case vm_top
  *   will equal vm_start
  */
@@ -1096,7 +1089,7 @@ static int do_mmap_private(struct vm_area_struct *vma,
                 goto enomem;
 
         total = 1 << order;
-        atomic_add(total, &mmap_pages_allocated);
+        atomic_long_add(total, &mmap_pages_allocated);
 
         point = rlen >> PAGE_SHIFT;
 
@@ -1107,7 +1100,7 @@ static int do_mmap_private(struct vm_area_struct *vma,
                         order = ilog2(total - point);
                         n = 1 << order;
                         kdebug("shave %lu/%lu @%lu", n, total - point, total);
-                        atomic_sub(n, &mmap_pages_allocated);
+                        atomic_long_sub(n, &mmap_pages_allocated);
                         total -= n;
                         set_page_refcounted(pages + total);
                         __free_pages(pages + total, order);
@@ -1536,10 +1529,15 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
         /* find the first potentially overlapping VMA */
         vma = find_vma(mm, start);
         if (!vma) {
-                printk(KERN_WARNING
-                       "munmap of memory not mmapped by process %d (%s):"
-                       " 0x%lx-0x%lx\n",
-                       current->pid, current->comm, start, start + len - 1);
+                static int limit = 0;
+                if (limit < 5) {
+                        printk(KERN_WARNING
+                               "munmap of memory not mmapped by process %d"
+                               " (%s): 0x%lx-0x%lx\n",
+                               current->pid, current->comm,
+                               start, start + len - 1);
+                        limit++;
+                }
                 return -EINVAL;
         }
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index d3b9bac085b5..2f3166e308d9 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -394,6 +394,7 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
                 cpuset_print_task_mems_allowed(current);
                 task_unlock(current);
                 dump_stack();
+                mem_cgroup_print_oom_info(mem, current);
                 show_mem();
                 if (sysctl_oom_dump_tasks)
                         dump_tasks(mem);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0284e528748d..e2f26991fff1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -331,7 +331,7 @@ static int destroy_compound_page(struct page *page, unsigned long order)
         for (i = 1; i < nr_pages; i++) {
                 struct page *p = page + i;
 
-                if (unlikely(!PageTail(p) | (p->first_page != page))) {
+                if (unlikely(!PageTail(p) || (p->first_page != page))) {
                         bad_page(page);
                         bad++;
                 }
@@ -2128,7 +2128,7 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
         int n, val;
         int min_val = INT_MAX;
         int best_node = -1;
-        node_to_cpumask_ptr(tmp, 0);
+        const struct cpumask *tmp = cpumask_of_node(0);
 
         /* Use the local node if we haven't already */
         if (!node_isset(node, *used_node_mask)) {
@@ -2149,8 +2149,8 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
                 val += (n < node);
 
                 /* Give preference to headless and unused nodes */
-                node_to_cpumask_ptr_next(tmp, n);
-                if (!cpus_empty(*tmp))
+                tmp = cpumask_of_node(n);
+                if (!cpumask_empty(tmp))
                         val += PENALTY_FOR_NODE_WITH_CPUS;
 
                 /* Slight preference for less loaded node */
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index ceecfbb143fa..791905c991df 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -285,12 +285,8 @@ struct swap_cgroup_ctrl {
 
 struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
 
-/*
- * This 8bytes seems big..maybe we can reduce this when we can use "id" for
- * cgroup rather than pointer.
- */
 struct swap_cgroup {
-        struct mem_cgroup       *val;
+        unsigned short          id;
 };
 #define SC_PER_PAGE     (PAGE_SIZE/sizeof(struct swap_cgroup))
 #define SC_POS_MASK     (SC_PER_PAGE - 1)
@@ -342,10 +338,10 @@ not_enough_page:
  * @ent: swap entry to be recorded into
  * @mem: mem_cgroup to be recorded
  *
- * Returns old value at success, NULL at failure.
- * (Of course, old value can be NULL.)
+ * Returns old value at success, 0 at failure.
+ * (Of course, old value can be 0.)
  */
-struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem)
+unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
 {
         int type = swp_type(ent);
         unsigned long offset = swp_offset(ent);
@@ -354,18 +350,18 @@ struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem)
         struct swap_cgroup_ctrl *ctrl;
         struct page *mappage;
         struct swap_cgroup *sc;
-        struct mem_cgroup *old;
+        unsigned short old;
 
         if (!do_swap_account)
-                return NULL;
+                return 0;
 
         ctrl = &swap_cgroup_ctrl[type];
 
         mappage = ctrl->map[idx];
         sc = page_address(mappage);
         sc += pos;
-        old = sc->val;
-        sc->val = mem;
+        old = sc->id;
+        sc->id = id;
 
         return old;
 }
@@ -374,9 +370,9 @@ struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem)
  * lookup_swap_cgroup - lookup mem_cgroup tied to swap entry
  * @ent: swap entry to be looked up.
  *
- * Returns pointer to mem_cgroup at success. NULL at failure.
+ * Returns CSS ID of mem_cgroup at success. 0 at failure. (0 is invalid ID)
  */
-struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent)
+unsigned short lookup_swap_cgroup(swp_entry_t ent)
 {
         int type = swp_type(ent);
         unsigned long offset = swp_offset(ent);
@@ -385,16 +381,16 @@ struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent)
         struct swap_cgroup_ctrl *ctrl;
         struct page *mappage;
         struct swap_cgroup *sc;
-        struct mem_cgroup *ret;
+        unsigned short ret;
 
         if (!do_swap_account)
-                return NULL;
+                return 0;
 
         ctrl = &swap_cgroup_ctrl[type];
         mappage = ctrl->map[idx];
         sc = page_address(mappage);
         sc += pos;
-        ret = sc->val;
+        ret = sc->id;
         return ret;
 }
 
@@ -430,13 +426,6 @@ int swap_cgroup_swapon(int type, unsigned long max_pages)
         }
         mutex_unlock(&swap_cgroup_mutex);
 
-        printk(KERN_INFO
-                "swap_cgroup: uses %ld bytes of vmalloc for pointer array space"
-                " and %ld bytes to hold mem_cgroup pointers on swap\n",
-                array_size, length * PAGE_SIZE);
-        printk(KERN_INFO
-        "swap_cgroup can be disabled by noswapaccount boot option.\n");
-
         return 0;
 nomem:
         printk(KERN_INFO "couldn't allocate enough memory for swap_cgroup.\n");
diff --git a/mm/quicklist.c b/mm/quicklist.c
index 8dbb6805ef35..e66d07d1b4ff 100644
--- a/mm/quicklist.c
+++ b/mm/quicklist.c
@@ -29,7 +29,7 @@ static unsigned long max_pages(unsigned long min_pages)
         int node = numa_node_id();
         struct zone *zones = NODE_DATA(node)->node_zones;
         int num_cpus_on_node;
-        node_to_cpumask_ptr(cpumask_on_node, node);
+        const struct cpumask *cpumask_on_node = cpumask_of_node(node);
 
         node_free_pages =
 #ifdef CONFIG_ZONE_DMA
diff --git a/mm/readahead.c b/mm/readahead.c
index 9ce303d4b810..133b6d525513 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -31,6 +31,42 @@ EXPORT_SYMBOL_GPL(file_ra_state_init);
 
 #define list_to_page(head) (list_entry((head)->prev, struct page, lru))
 
+/*
+ * see if a page needs releasing upon read_cache_pages() failure
+ * - the caller of read_cache_pages() may have set PG_private or PG_fscache
+ *   before calling, such as the NFS fs marking pages that are cached locally
+ *   on disk, thus we need to give the fs a chance to clean up in the event of
+ *   an error
+ */
+static void read_cache_pages_invalidate_page(struct address_space *mapping,
+                                             struct page *page)
+{
+        if (page_has_private(page)) {
+                if (!trylock_page(page))
+                        BUG();
+                page->mapping = mapping;
+                do_invalidatepage(page, 0);
+                page->mapping = NULL;
+                unlock_page(page);
+        }
+        page_cache_release(page);
+}
+
+/*
+ * release a list of pages, invalidating them first if need be
+ */
+static void read_cache_pages_invalidate_pages(struct address_space *mapping,
+                                              struct list_head *pages)
+{
+        struct page *victim;
+
+        while (!list_empty(pages)) {
+                victim = list_to_page(pages);
+                list_del(&victim->lru);
+                read_cache_pages_invalidate_page(mapping, victim);
+        }
+}
+
 /**
  * read_cache_pages - populate an address space with some pages & start reads against them
  * @mapping: the address_space
@@ -52,14 +88,14 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages,
                 list_del(&page->lru);
                 if (add_to_page_cache_lru(page, mapping,
                                         page->index, GFP_KERNEL)) {
-                        page_cache_release(page);
+                        read_cache_pages_invalidate_page(mapping, page);
                         continue;
                 }
                 page_cache_release(page);
 
                 ret = filler(data, page);
                 if (unlikely(ret)) {
-                        put_pages_list(pages);
+                        read_cache_pages_invalidate_pages(mapping, pages);
                         break;
                 }
                 task_io_account_read(PAGE_CACHE_SIZE);
diff --git a/mm/slab.c b/mm/slab.c
index 9ec66c3e6ee0..4fc1761c6dc8 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1169,7 +1169,7 @@ static void __cpuinit cpuup_canceled(long cpu)
         struct kmem_cache *cachep;
         struct kmem_list3 *l3 = NULL;
         int node = cpu_to_node(cpu);
-        node_to_cpumask_ptr(mask, node);
+        const struct cpumask *mask = cpumask_of_node(node);
 
         list_for_each_entry(cachep, &cache_chain, next) {
                 struct array_cache *nc;
@@ -4049,8 +4049,7 @@ static void cache_reap(struct work_struct *w)
         struct kmem_cache *searchp;
         struct kmem_list3 *l3;
         int node = numa_node_id();
-        struct delayed_work *work =
-                container_of(w, struct delayed_work, work);
+        struct delayed_work *work = to_delayed_work(w);
 
         if (!mutex_trylock(&cache_chain_mutex))
                 /* Give up. Setup the next iteration. */
diff --git a/mm/swap.c b/mm/swap.c
index 6e83084c1f6c..bede23ce64ea 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -448,8 +448,8 @@ void pagevec_strip(struct pagevec *pvec)
         for (i = 0; i < pagevec_count(pvec); i++) {
                 struct page *page = pvec->pages[i];
 
-                if (PagePrivate(page) && trylock_page(page)) {
-                        if (PagePrivate(page))
+                if (page_has_private(page) && trylock_page(page)) {
+                        if (page_has_private(page))
                                 try_to_release_page(page, 0);
                         unlock_page(page);
                 }
diff --git a/mm/truncate.c b/mm/truncate.c
index 1229211104f8..55206fab7b99 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -50,7 +50,7 @@ void do_invalidatepage(struct page *page, unsigned long offset)
 static inline void truncate_partial_page(struct page *page, unsigned partial)
 {
         zero_user_segment(page, partial, PAGE_CACHE_SIZE);
-        if (PagePrivate(page))
+        if (page_has_private(page))
                 do_invalidatepage(page, partial);
 }
 
@@ -99,7 +99,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
         if (page->mapping != mapping)
                 return;
 
-        if (PagePrivate(page))
+        if (page_has_private(page))
                 do_invalidatepage(page, 0);
 
         cancel_dirty_page(page, PAGE_CACHE_SIZE);
@@ -126,7 +126,7 @@ invalidate_complete_page(struct address_space *mapping, struct page *page)
         if (page->mapping != mapping)
                 return 0;
 
-        if (PagePrivate(page) && !try_to_release_page(page, 0))
+        if (page_has_private(page) && !try_to_release_page(page, 0))
                 return 0;
 
         clear_page_mlock(page);
@@ -348,7 +348,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
         if (page->mapping != mapping)
                 return 0;
 
-        if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL))
+        if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL))
                 return 0;
 
         spin_lock_irq(&mapping->tree_lock);
@@ -356,7 +356,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
                 goto failed;
 
         clear_page_mlock(page);
-        BUG_ON(PagePrivate(page));
+        BUG_ON(page_has_private(page));
         __remove_from_page_cache(page);
         spin_unlock_irq(&mapping->tree_lock);
         page_cache_release(page);       /* pagecache ref */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 06e72693b458..39fdfb14eeaa 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -283,7 +283,7 @@ static inline int page_mapping_inuse(struct page *page)
 
 static inline int is_page_cache_freeable(struct page *page)
 {
-        return page_count(page) - !!PagePrivate(page) == 2;
+        return page_count(page) - !!page_has_private(page) == 2;
 }
 
 static int may_write_to_queue(struct backing_dev_info *bdi)
@@ -367,7 +367,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
                  * Some data journaling orphaned pages can have
                  * page->mapping == NULL while being dirty with clean buffers.
                  */
-                if (PagePrivate(page)) {
+                if (page_has_private(page)) {
                         if (try_to_free_buffers(page)) {
                                 ClearPageDirty(page);
                                 printk("%s: orphaned page\n", __func__);
@@ -727,7 +727,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
                  * process address space (page_count == 1) it can be freed.
                  * Otherwise, leave the page on the LRU so it is swappable.
                  */
-                if (PagePrivate(page)) {
+                if (page_has_private(page)) {
                         if (!try_to_release_page(page, sc->gfp_mask))
                                 goto activate_locked;
                         if (!mapping && page_count(page) == 1) {
@@ -1967,7 +1967,7 @@ static int kswapd(void *p)
         struct reclaim_state reclaim_state = {
                 .reclaimed_slab = 0,
         };
-        node_to_cpumask_ptr(cpumask, pgdat->node_id);
+        const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
 
         lockdep_set_current_reclaim_state(GFP_KERNEL);
 
@@ -2204,7 +2204,9 @@ static int __devinit cpu_callback(struct notifier_block *nfb,
         if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
                 for_each_node_state(nid, N_HIGH_MEMORY) {
                         pg_data_t *pgdat = NODE_DATA(nid);
-                        node_to_cpumask_ptr(mask, pgdat->node_id);
+                        const struct cpumask *mask;
+
+                        mask = cpumask_of_node(pgdat->node_id);
 
                         if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
                                 /* One of our CPUs online: restore mask */
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 9826766f1274..66f6130976cb 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -891,7 +891,7 @@ static void vmstat_update(struct work_struct *w)
 {
         refresh_cpu_vm_stats(smp_processor_id());
         schedule_delayed_work(&__get_cpu_var(vmstat_work),
-                sysctl_stat_interval);
+                round_jiffies_relative(sysctl_stat_interval));
 }
 
 static void __cpuinit start_cpu_timer(int cpu)
@@ -899,7 +899,8 @@ static void __cpuinit start_cpu_timer(int cpu)
         struct delayed_work *vmstat_work = &per_cpu(vmstat_work, cpu);
 
         INIT_DELAYED_WORK_DEFERRABLE(vmstat_work, vmstat_update);
-        schedule_delayed_work_on(cpu, vmstat_work, HZ + cpu);
+        schedule_delayed_work_on(cpu, vmstat_work,
+                                 __round_jiffies_relative(HZ, cpu));
 }
 
 /*