9 files changed, 129 insertions, 187 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index e4a33b9479b2..9c61158308dc 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -199,7 +199,7 @@ config BOUNCE
 config NR_QUICK
         int
         depends on QUICKLIST
-        default "2" if SUPERH || AVR32
+        default "2" if AVR32
         default "1"
 
 config VIRT_TO_BUS
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 2d16fa6b8c2d..3a5aeb37c110 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2087,7 +2087,7 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma,
 
         entry = pte_mkwrite(pte_mkdirty(huge_ptep_get(ptep)));
         if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) {
-                update_mmu_cache(vma, address, entry);
+                update_mmu_cache(vma, address, ptep);
         }
 }
 
@@ -2558,7 +2558,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
         entry = pte_mkyoung(entry);
         if (huge_ptep_set_access_flags(vma, address, ptep, entry,
                                                 flags & FAULT_FLAG_WRITE))
-                update_mmu_cache(vma, address, entry);
+                update_mmu_cache(vma, address, ptep);
 
 out_page_table_lock:
         spin_unlock(&mm->page_table_lock);
diff --git a/mm/memory.c b/mm/memory.c
index 09e4b1be7b67..72fb5f39bccc 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1593,7 +1593,7 @@ static int insert_pfn(struct vm_area_struct *vma, unsigned long addr,
         /* Ok, finally just insert the thing.. */
         entry = pte_mkspecial(pfn_pte(pfn, prot));
         set_pte_at(mm, addr, pte, entry);
-        update_mmu_cache(vma, addr, entry); /* XXX: why not for insert_page? */
+        update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */
 
         retval = 0;
 out_unlock:
@@ -2116,7 +2116,7 @@ reuse:
                 entry = pte_mkyoung(orig_pte);
                 entry = maybe_mkwrite(pte_mkdirty(entry), vma);
                 if (ptep_set_access_flags(vma, address, page_table, entry,1))
-                        update_mmu_cache(vma, address, entry);
+                        update_mmu_cache(vma, address, page_table);
                 ret |= VM_FAULT_WRITE;
                 goto unlock;
         }
@@ -2185,7 +2185,7 @@ gotten:
                  * new page to be mapped directly into the secondary page table.
                  */
                 set_pte_at_notify(mm, address, page_table, entry);
-                update_mmu_cache(vma, address, entry);
+                update_mmu_cache(vma, address, page_table);
                 if (old_page) {
                         /*
                          * Only after switching the pte to the new page may
@@ -2629,7 +2629,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
         }
 
         /* No need to invalidate - it was non-present before */
-        update_mmu_cache(vma, address, pte);
+        update_mmu_cache(vma, address, page_table);
 unlock:
         pte_unmap_unlock(page_table, ptl);
 out:
@@ -2694,7 +2694,7 @@ setpte:
         set_pte_at(mm, address, page_table, entry);
 
         /* No need to invalidate - it was non-present before */
-        update_mmu_cache(vma, address, entry);
+        update_mmu_cache(vma, address, page_table);
 unlock:
         pte_unmap_unlock(page_table, ptl);
         return 0;
@@ -2855,7 +2855,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
                 set_pte_at(mm, address, page_table, entry);
 
                 /* no need to invalidate: a not-present page won't be cached */
-                update_mmu_cache(vma, address, entry);
+                update_mmu_cache(vma, address, page_table);
         } else {
                 if (charged)
                         mem_cgroup_uncharge_page(page);
@@ -2992,7 +2992,7 @@ static inline int handle_pte_fault(struct mm_struct *mm,
         }
         entry = pte_mkyoung(entry);
         if (ptep_set_access_flags(vma, address, pte, entry, flags & FAULT_FLAG_WRITE)) {
-                update_mmu_cache(vma, address, entry);
+                update_mmu_cache(vma, address, pte);
         } else {
                 /*
                  * This is needed only for protection faults but the arch code
diff --git a/mm/migrate.c b/mm/migrate.c
index 9a0db5bbabe4..edb6101ed774 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -134,7 +134,7 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
                 page_add_file_rmap(new);
 
         /* No need to invalidate - it was non-present before */
-        update_mmu_cache(vma, addr, pte);
+        update_mmu_cache(vma, addr, ptep);
 unlock:
         pte_unmap_unlock(ptep, ptl);
 out:
@@ -1002,33 +1002,27 @@ static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages,
 #define DO_PAGES_STAT_CHUNK_NR 16
         const void __user *chunk_pages[DO_PAGES_STAT_CHUNK_NR];
         int chunk_status[DO_PAGES_STAT_CHUNK_NR];
-        unsigned long i, chunk_nr = DO_PAGES_STAT_CHUNK_NR;
-        int err;
 
-        for (i = 0; i < nr_pages; i += chunk_nr) {
-                if (chunk_nr > nr_pages - i)
-                        chunk_nr = nr_pages - i;
+        while (nr_pages) {
+                unsigned long chunk_nr;
 
-                err = copy_from_user(chunk_pages, &pages[i],
-                                     chunk_nr * sizeof(*chunk_pages));
-                if (err) {
-                        err = -EFAULT;
-                        goto out;
-                }
+                chunk_nr = nr_pages;
+                if (chunk_nr > DO_PAGES_STAT_CHUNK_NR)
+                        chunk_nr = DO_PAGES_STAT_CHUNK_NR;
+
+                if (copy_from_user(chunk_pages, pages, chunk_nr * sizeof(*chunk_pages)))
+                        break;
 
                 do_pages_stat_array(mm, chunk_nr, chunk_pages, chunk_status);
 
-                err = copy_to_user(&status[i], chunk_status,
-                                   chunk_nr * sizeof(*chunk_status));
-                if (err) {
-                        err = -EFAULT;
-                        goto out;
-                }
-        }
-        err = 0;
+                if (copy_to_user(status, chunk_status, chunk_nr * sizeof(*status)))
+                        break;
 
-out:
-        return err;
+                pages += chunk_nr;
+                status += chunk_nr;
+                nr_pages -= chunk_nr;
+        }
+        return nr_pages ? -EFAULT : 0;
 }
 
 /*
diff --git a/mm/mmu_context.c b/mm/mmu_context.c
index ded9081f4021..0777654147c9 100644
--- a/mm/mmu_context.c
+++ b/mm/mmu_context.c
@@ -5,6 +5,7 @@
 
 #include <linux/mm.h>
 #include <linux/mmu_context.h>
+#include <linux/module.h>
 #include <linux/sched.h>
 
 #include <asm/mmu_context.h>
@@ -37,6 +38,7 @@ void use_mm(struct mm_struct *mm)
         if (active_mm != mm)
                 mmdrop(active_mm);
 }
+EXPORT_SYMBOL_GPL(use_mm);
 
 /*
  * unuse_mm
@@ -56,3 +58,4 @@ void unuse_mm(struct mm_struct *mm)
         enter_lazy_tlb(mm, tsk);
         task_unlock(tsk);
 }
+EXPORT_SYMBOL_GPL(unuse_mm);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index f52481b1c1e5..237050478f28 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -459,6 +459,8 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
         list_for_each_entry(c, &p->children, sibling) {
                 if (c->mm == p->mm)
                         continue;
+                if (mem && !task_in_mem_cgroup(c, mem))
+                        continue;
                 if (!oom_kill_task(c))
                         return 0;
         }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1fa93bd2bb9f..a6b17aa4740b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1009,10 +1009,10 @@ static void drain_pages(unsigned int cpu)
                 struct per_cpu_pageset *pset;
                 struct per_cpu_pages *pcp;
 
-                pset = zone_pcp(zone, cpu);
+                local_irq_save(flags);
+                pset = per_cpu_ptr(zone->pageset, cpu);
 
                 pcp = &pset->pcp;
-                local_irq_save(flags);
                 free_pcppages_bulk(zone, pcp->count, pcp);
                 pcp->count = 0;
                 local_irq_restore(flags);
@@ -1096,7 +1096,6 @@ static void free_hot_cold_page(struct page *page, int cold)
         arch_free_page(page, 0);
         kernel_map_pages(page, 1, 0);
 
-        pcp = &zone_pcp(zone, get_cpu())->pcp;
         migratetype = get_pageblock_migratetype(page);
         set_page_private(page, migratetype);
         local_irq_save(flags);
@@ -1119,6 +1118,7 @@ static void free_hot_cold_page(struct page *page, int cold)
                 migratetype = MIGRATE_MOVABLE;
         }
 
+        pcp = &this_cpu_ptr(zone->pageset)->pcp;
         if (cold)
                 list_add_tail(&page->lru, &pcp->lists[migratetype]);
         else
@@ -1131,7 +1131,6 @@ static void free_hot_cold_page(struct page *page, int cold)
 
 out:
         local_irq_restore(flags);
-        put_cpu();
 }
 
 void free_hot_page(struct page *page)
@@ -1181,17 +1180,15 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
         unsigned long flags;
         struct page *page;
         int cold = !!(gfp_flags & __GFP_COLD);
-        int cpu;
 
 again:
-        cpu  = get_cpu();
         if (likely(order == 0)) {
                 struct per_cpu_pages *pcp;
                 struct list_head *list;
 
-                pcp = &zone_pcp(zone, cpu)->pcp;
-                list = &pcp->lists[migratetype];
                 local_irq_save(flags);
+                pcp = &this_cpu_ptr(zone->pageset)->pcp;
+                list = &pcp->lists[migratetype];
                 if (list_empty(list)) {
                         pcp->count += rmqueue_bulk(zone, 0,
                                         pcp->batch, list,
@@ -1232,7 +1229,6 @@ again:
         __count_zone_vm_events(PGALLOC, zone, 1 << order);
         zone_statistics(preferred_zone, zone);
         local_irq_restore(flags);
-        put_cpu();
 
         VM_BUG_ON(bad_range(zone, page));
         if (prep_new_page(page, order, gfp_flags))
@@ -1241,7 +1237,6 @@ again:
 
 failed:
         local_irq_restore(flags);
-        put_cpu();
         return NULL;
 }
 
@@ -2180,7 +2175,7 @@ void show_free_areas(void)
                 for_each_online_cpu(cpu) {
                         struct per_cpu_pageset *pageset;
 
-                        pageset = zone_pcp(zone, cpu);
+                        pageset = per_cpu_ptr(zone->pageset, cpu);
 
                         printk("CPU %4d: hi:%5d, btch:%4d usd:%4d\n",
                                cpu, pageset->pcp.high,
@@ -2745,10 +2740,29 @@ static void build_zonelist_cache(pg_data_t *pgdat)
 
 #endif  /* CONFIG_NUMA */
 
+/*
+ * Boot pageset table. One per cpu which is going to be used for all
+ * zones and all nodes. The parameters will be set in such a way
+ * that an item put on a list will immediately be handed over to
+ * the buddy list. This is safe since pageset manipulation is done
+ * with interrupts disabled.
+ *
+ * The boot_pagesets must be kept even after bootup is complete for
+ * unused processors and/or zones. They do play a role for bootstrapping
+ * hotplugged processors.
+ *
+ * zoneinfo_show() and maybe other functions do
+ * not check if the processor is online before following the pageset pointer.
+ * Other parts of the kernel may not check if the zone is available.
+ */
+static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch);
+static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset);
+
 /* return values int ....just for stop_machine() */
 static int __build_all_zonelists(void *dummy)
 {
         int nid;
+        int cpu;
 
 #ifdef CONFIG_NUMA
         memset(node_load, 0, sizeof(node_load));
@@ -2759,6 +2773,23 @@ static int __build_all_zonelists(void *dummy)
                 build_zonelists(pgdat);
                 build_zonelist_cache(pgdat);
         }
+
+        /*
+         * Initialize the boot_pagesets that are going to be used
+         * for bootstrapping processors. The real pagesets for
+         * each zone will be allocated later when the per cpu
+         * allocator is available.
+         *
+         * boot_pagesets are used also for bootstrapping offline
+         * cpus if the system is already booted because the pagesets
+         * are needed to initialize allocators on a specific cpu too.
+         * F.e. the percpu allocator needs the page allocator which
+         * needs the percpu allocator in order to allocate its pagesets
+         * (a chicken-egg dilemma).
+         */
+        for_each_possible_cpu(cpu)
+                setup_pageset(&per_cpu(boot_pageset, cpu), 0);
+
         return 0;
 }
 
@@ -3096,121 +3127,33 @@ static void setup_pagelist_highmark(struct per_cpu_pageset *p,
                 pcp->batch = PAGE_SHIFT * 8;
 }
 
-
-#ifdef CONFIG_NUMA
-/*
- * Boot pageset table. One per cpu which is going to be used for all
- * zones and all nodes. The parameters will be set in such a way
- * that an item put on a list will immediately be handed over to
- * the buddy list. This is safe since pageset manipulation is done
- * with interrupts disabled.
- *
- * Some NUMA counter updates may also be caught by the boot pagesets.
- *
- * The boot_pagesets must be kept even after bootup is complete for
- * unused processors and/or zones. They do play a role for bootstrapping
- * hotplugged processors.
- *
- * zoneinfo_show() and maybe other functions do
- * not check if the processor is online before following the pageset pointer.
- * Other parts of the kernel may not check if the zone is available.
- */
-static struct per_cpu_pageset boot_pageset[NR_CPUS];
-
 /*
- * Dynamically allocate memory for the
- * per cpu pageset array in struct zone.
+ * Allocate per cpu pagesets and initialize them.
+ * Before this call only boot pagesets were available.
+ * Boot pagesets will no longer be used by this processorr
+ * after setup_per_cpu_pageset().
  */
-static int __cpuinit process_zones(int cpu)
+void __init setup_per_cpu_pageset(void)
 {
-        struct zone *zone, *dzone;
-        int node = cpu_to_node(cpu);
-
-        node_set_state(node, N_CPU);    /* this node has a cpu */
+        struct zone *zone;
+        int cpu;
 
         for_each_populated_zone(zone) {
-                zone_pcp(zone, cpu) = kmalloc_node(sizeof(struct per_cpu_pageset),
-                                         GFP_KERNEL, node);
-                if (!zone_pcp(zone, cpu))
-                        goto bad;
-
-                setup_pageset(zone_pcp(zone, cpu), zone_batchsize(zone));
-
-                if (percpu_pagelist_fraction)
-                        setup_pagelist_highmark(zone_pcp(zone, cpu),
-                            (zone->present_pages / percpu_pagelist_fraction));
-        }
-
-        return 0;
-bad:
-        for_each_zone(dzone) {
-                if (!populated_zone(dzone))
-                        continue;
-                if (dzone == zone)
-                        break;
-                kfree(zone_pcp(dzone, cpu));
-                zone_pcp(dzone, cpu) = &boot_pageset[cpu];
-        }
-        return -ENOMEM;
-}
+                zone->pageset = alloc_percpu(struct per_cpu_pageset);
 
-static inline void free_zone_pagesets(int cpu)
-{
-        struct zone *zone;
-
-        for_each_zone(zone) {
-                struct per_cpu_pageset *pset = zone_pcp(zone, cpu);
+                for_each_possible_cpu(cpu) {
+                        struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu);
 
-                /* Free per_cpu_pageset if it is slab allocated */
-                if (pset != &boot_pageset[cpu])
-                        kfree(pset);
-                zone_pcp(zone, cpu) = &boot_pageset[cpu];
-        }
-}
+                        setup_pageset(pcp, zone_batchsize(zone));
 
-static int __cpuinit pageset_cpuup_callback(struct notifier_block *nfb,
-                unsigned long action,
-                void *hcpu)
-{
-        int cpu = (long)hcpu;
-        int ret = NOTIFY_OK;
-
-        switch (action) {
-        case CPU_UP_PREPARE:
-        case CPU_UP_PREPARE_FROZEN:
-                if (process_zones(cpu))
-                        ret = NOTIFY_BAD;
-                break;
-        case CPU_UP_CANCELED:
-        case CPU_UP_CANCELED_FROZEN:
-        case CPU_DEAD:
-        case CPU_DEAD_FROZEN:
-                free_zone_pagesets(cpu);
-                break;
-        default:
-                break;
+                        if (percpu_pagelist_fraction)
+                                setup_pagelist_highmark(pcp,
+                                        (zone->present_pages /
+                                                percpu_pagelist_fraction));
+                }
         }
-        return ret;
 }
 
-static struct notifier_block __cpuinitdata pageset_notifier =
-        { &pageset_cpuup_callback, NULL, 0 };
-
-void __init setup_per_cpu_pageset(void)
-{
-        int err;
-
-        /* Initialize per_cpu_pageset for cpu 0.
-         * A cpuup callback will do this for every cpu
-         * as it comes online
-         */
-        err = process_zones(smp_processor_id());
-        BUG_ON(err);
-        register_cpu_notifier(&pageset_notifier);
-}
-
-#endif
-
 static noinline __init_refok
 int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
 {
@@ -3264,7 +3207,7 @@ static int __zone_pcp_update(void *data)
                 struct per_cpu_pageset *pset;
                 struct per_cpu_pages *pcp;
 
-                pset = zone_pcp(zone, cpu);
+                pset = per_cpu_ptr(zone->pageset, cpu);
                 pcp = &pset->pcp;
 
                 local_irq_save(flags);
@@ -3282,21 +3225,17 @@ void zone_pcp_update(struct zone *zone)
 
 static __meminit void zone_pcp_init(struct zone *zone)
 {
-        int cpu;
-        unsigned long batch = zone_batchsize(zone);
+        /*
+         * per cpu subsystem is not up at this point. The following code
+         * relies on the ability of the linker to provide the
+         * offset of a (static) per cpu variable into the per cpu area.
+         */
+        zone->pageset = &boot_pageset;
 
-        for (cpu = 0; cpu < NR_CPUS; cpu++) {
-#ifdef CONFIG_NUMA
-                /* Early boot. Slab allocator not functional yet */
-                zone_pcp(zone, cpu) = &boot_pageset[cpu];
-                setup_pageset(&boot_pageset[cpu],0);
-#else
-                setup_pageset(zone_pcp(zone,cpu), batch);
-#endif
-        }
         if (zone->present_pages)
-                printk(KERN_DEBUG "  %s zone: %lu pages, LIFO batch:%lu\n",
-                        zone->name, zone->present_pages, batch);
+                printk(KERN_DEBUG "  %s zone: %lu pages, LIFO batch:%u\n",
+                        zone->name, zone->present_pages,
+                                         zone_batchsize(zone));
 }
 
 __meminit int init_currently_empty_zone(struct zone *zone,
@@ -4869,10 +4808,11 @@ int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
         if (!write || (ret == -EINVAL))
                 return ret;
         for_each_populated_zone(zone) {
-                for_each_online_cpu(cpu) {
+                for_each_possible_cpu(cpu) {
                         unsigned long  high;
                         high = zone->present_pages / percpu_pagelist_fraction;
-                        setup_pagelist_highmark(zone_pcp(zone, cpu), high);
+                        setup_pagelist_highmark(
+                                per_cpu_ptr(zone->pageset, cpu), high);
                 }
         }
         return 0;
diff --git a/mm/percpu.c b/mm/percpu.c
index 083e7c91e5f6..768419d44ad7 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -80,13 +80,15 @@
 /* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */
 #ifndef __addr_to_pcpu_ptr
 #define __addr_to_pcpu_ptr(addr)                                        \
-        (void *)((unsigned long)(addr) - (unsigned long)pcpu_base_addr  \
-                 + (unsigned long)__per_cpu_start)
+        (void __percpu *)((unsigned long)(addr) -                       \
+                          (unsigned long)pcpu_base_addr +               \
+                          (unsigned long)__per_cpu_start)
 #endif
 #ifndef __pcpu_ptr_to_addr
 #define __pcpu_ptr_to_addr(ptr)                                         \
-        (void *)((unsigned long)(ptr) + (unsigned long)pcpu_base_addr   \
-                 - (unsigned long)__per_cpu_start)
+        (void __force *)((unsigned long)(ptr) +                         \
+                         (unsigned long)pcpu_base_addr -                \
+                         (unsigned long)__per_cpu_start)
 #endif
 
 struct pcpu_chunk {
@@ -913,11 +915,10 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size)
         int rs, re;
 
         /* quick path, check whether it's empty already */
-        pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) {
-                if (rs == page_start && re == page_end)
-                        return;
-                break;
-        }
+        rs = page_start;
+        pcpu_next_unpop(chunk, &rs, &re, page_end);
+        if (rs == page_start && re == page_end)
+                return;
 
         /* immutable chunks can't be depopulated */
         WARN_ON(chunk->immutable);
@@ -968,11 +969,10 @@ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)
         int rs, re, rc;
 
         /* quick path, check whether all pages are already there */
-        pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end) {
-                if (rs == page_start && re == page_end)
-                        goto clear;
-                break;
-        }
+        rs = page_start;
+        pcpu_next_pop(chunk, &rs, &re, page_end);
+        if (rs == page_start && re == page_end)
+                goto clear;
 
         /* need to allocate and map pages, this chunk can't be immutable */
         WARN_ON(chunk->immutable);
@@ -1067,7 +1067,7 @@ static struct pcpu_chunk *alloc_pcpu_chunk(void)
  * RETURNS:
  * Percpu pointer to the allocated area on success, NULL on failure.
  */
-static void *pcpu_alloc(size_t size, size_t align, bool reserved)
+static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved)
 {
         static int warn_limit = 10;
         struct pcpu_chunk *chunk;
@@ -1196,7 +1196,7 @@ fail_unlock_mutex:
  * RETURNS:
  * Percpu pointer to the allocated area on success, NULL on failure.
  */
-void *__alloc_percpu(size_t size, size_t align)
+void __percpu *__alloc_percpu(size_t size, size_t align)
 {
         return pcpu_alloc(size, align, false);
 }
@@ -1217,7 +1217,7 @@ EXPORT_SYMBOL_GPL(__alloc_percpu);
  * RETURNS:
  * Percpu pointer to the allocated area on success, NULL on failure.
  */
-void *__alloc_reserved_percpu(size_t size, size_t align)
+void __percpu *__alloc_reserved_percpu(size_t size, size_t align)
 {
         return pcpu_alloc(size, align, true);
 }
@@ -1269,7 +1269,7 @@ static void pcpu_reclaim(struct work_struct *work)
  * CONTEXT:
  * Can be called from atomic context.
  */
-void free_percpu(void *ptr)
+void free_percpu(void __percpu *ptr)
 {
         void *addr;
         struct pcpu_chunk *chunk;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 6051fbab67ba..fc5aa183bc45 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -139,7 +139,8 @@ static void refresh_zone_stat_thresholds(void)
                 threshold = calculate_threshold(zone);
 
                 for_each_online_cpu(cpu)
-                        zone_pcp(zone, cpu)->stat_threshold = threshold;
+                        per_cpu_ptr(zone->pageset, cpu)->stat_threshold
+                                                        = threshold;
         }
 }
 
@@ -149,7 +150,8 @@ static void refresh_zone_stat_thresholds(void)
 void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
                                 int delta)
 {
-        struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id());
+        struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset);
+
         s8 *p = pcp->vm_stat_diff + item;
         long x;
 
@@ -202,7 +204,7 @@ EXPORT_SYMBOL(mod_zone_page_state);
  */
 void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
 {
-        struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id());
+        struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset);
         s8 *p = pcp->vm_stat_diff + item;
 
         (*p)++;
@@ -223,7 +225,7 @@ EXPORT_SYMBOL(__inc_zone_page_state);
 
 void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
 {
-        struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id());
+        struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset);
         s8 *p = pcp->vm_stat_diff + item;
 
         (*p)--;
@@ -300,7 +302,7 @@ void refresh_cpu_vm_stats(int cpu)
         for_each_populated_zone(zone) {
                 struct per_cpu_pageset *p;
 
-                p = zone_pcp(zone, cpu);
+                p = per_cpu_ptr(zone->pageset, cpu);
 
                 for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
                         if (p->vm_stat_diff[i]) {
@@ -741,7 +743,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
         for_each_online_cpu(i) {
                 struct per_cpu_pageset *pageset;
 
-                pageset = zone_pcp(zone, i);
+                pageset = per_cpu_ptr(zone->pageset, i);
                 seq_printf(m,
                            "\n    cpu: %i"
                            "\n              count: %i"
@@ -906,6 +908,7 @@ static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb,
         case CPU_ONLINE:
         case CPU_ONLINE_FROZEN:
                 start_cpu_timer(cpu);
+                node_set_state(cpu_to_node(cpu), N_CPU);
                 break;
         case CPU_DOWN_PREPARE:
         case CPU_DOWN_PREPARE_FROZEN: