8 files changed, 154 insertions, 47 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 9abc6008544b..85e80a57db29 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -623,11 +623,12 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
                         (*zap_work)--;
                         continue;
                 }
+
+                (*zap_work) -= PAGE_SIZE;
+
                 if (pte_present(ptent)) {
                         struct page *page;
 
-                        (*zap_work) -= PAGE_SIZE;
-
                         page = vm_normal_page(vma, addr, ptent);
                         if (unlikely(details) && page) {
                                 /*
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a918f77f02f3..1fe76d963ac2 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -130,6 +130,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
                 onlined_pages++;
         }
         zone->present_pages += onlined_pages;
+        zone->zone_pgdat->node_present_pages += onlined_pages;
 
         setup_per_zone_pages_min();
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index d80fa7d8f720..b21869a39f0b 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -330,9 +330,19 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
         int err;
         struct vm_area_struct *first, *vma, *prev;
 
-        /* Clear the LRU lists so pages can be isolated */
-        if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
+        if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
+                /* Must have swap device for migration */
+                if (nr_swap_pages <= 0)
+                        return ERR_PTR(-ENODEV);
+
+                /*
+                 * Clear the LRU lists so pages can be isolated.
+                 * Note that pages may be moved off the LRU after we have
+                 * drained them. Those pages will fail to migrate like other
+                 * pages that may be busy.
+                 */
                 lru_add_drain_all();
+        }
 
         first = find_vma(mm, start);
         if (!first)
@@ -748,7 +758,7 @@ long do_mbind(unsigned long start, unsigned long len,
                                       MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
             || mode > MPOL_MAX)
                 return -EINVAL;
-        if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_RESOURCE))
+        if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE))
                 return -EPERM;
 
         if (start & ~PAGE_MASK)
@@ -942,20 +952,20 @@ asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode,
          */
         if ((current->euid != task->suid) && (current->euid != task->uid) &&
             (current->uid != task->suid) && (current->uid != task->uid) &&
-            !capable(CAP_SYS_ADMIN)) {
+            !capable(CAP_SYS_NICE)) {
                 err = -EPERM;
                 goto out;
         }
 
         task_nodes = cpuset_mems_allowed(task);
         /* Is the user allowed to access the target nodes? */
-        if (!nodes_subset(new, task_nodes) && !capable(CAP_SYS_ADMIN)) {
+        if (!nodes_subset(new, task_nodes) && !capable(CAP_SYS_NICE)) {
                 err = -EPERM;
                 goto out;
         }
 
         err = do_migrate_pages(mm, &old, &new,
-                capable(CAP_SYS_ADMIN) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE);
+                capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE);
 out:
         mmput(mm);
         return err;
@@ -1789,6 +1799,7 @@ static void gather_stats(struct page *page, void *private, int pte_dirty)
         cond_resched();
 }
 
+#ifdef CONFIG_HUGETLB_PAGE
 static void check_huge_range(struct vm_area_struct *vma,
                 unsigned long start, unsigned long end,
                 struct numa_maps *md)
@@ -1814,6 +1825,13 @@ static void check_huge_range(struct vm_area_struct *vma,
                 gather_stats(page, md, pte_dirty(*ptep));
         }
 }
+#else
+static inline void check_huge_range(struct vm_area_struct *vma,
+                unsigned long start, unsigned long end,
+                struct numa_maps *md)
+{
+}
+#endif
 
 int show_numa_map(struct seq_file *m, void *v)
 {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 791690d7d3fa..234bd4895d14 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -590,21 +590,20 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 }
 
 #ifdef CONFIG_NUMA
-/* Called from the slab reaper to drain remote pagesets */
-void drain_remote_pages(void)
+/*
+ * Called from the slab reaper to drain pagesets on a particular node that
+ * belong to the currently executing processor.
+ */
+void drain_node_pages(int nodeid)
 {
-        struct zone *zone;
-        int i;
+        int i, z;
         unsigned long flags;
 
         local_irq_save(flags);
-        for_each_zone(zone) {
+        for (z = 0; z < MAX_NR_ZONES; z++) {
+                struct zone *zone = NODE_DATA(nodeid)->node_zones + z;
                 struct per_cpu_pageset *pset;
 
-                /* Do not drain local pagesets */
-                if (zone->zone_pgdat->node_id == numa_node_id())
-                        continue;
-
                 pset = zone_pcp(zone, smp_processor_id());
                 for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) {
                         struct per_cpu_pages *pcp;
diff --git a/mm/rmap.c b/mm/rmap.c
index d8ce5ff61454..67f0e20b101f 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -537,9 +537,6 @@ void page_add_new_anon_rmap(struct page *page,
  */
 void page_add_file_rmap(struct page *page)
 {
-        BUG_ON(PageAnon(page));
-        BUG_ON(!pfn_valid(page_to_pfn(page)));
-
         if (atomic_inc_and_test(&page->_mapcount))
                 __inc_page_state(nr_mapped);
 }
diff --git a/mm/slab.c b/mm/slab.c
index f2e92dc1c9ce..d0bd7f07ab04 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -789,6 +789,47 @@ static void __slab_error(const char *function, struct kmem_cache *cachep, char *
         dump_stack();
 }
 
+#ifdef CONFIG_NUMA
+/*
+ * Special reaping functions for NUMA systems called from cache_reap().
+ * These take care of doing round robin flushing of alien caches (containing
+ * objects freed on different nodes from which they were allocated) and the
+ * flushing of remote pcps by calling drain_node_pages.
+ */
+static DEFINE_PER_CPU(unsigned long, reap_node);
+
+static void init_reap_node(int cpu)
+{
+        int node;
+
+        node = next_node(cpu_to_node(cpu), node_online_map);
+        if (node == MAX_NUMNODES)
+                node = 0;
+
+        __get_cpu_var(reap_node) = node;
+}
+
+static void next_reap_node(void)
+{
+        int node = __get_cpu_var(reap_node);
+
+        /*
+         * Also drain per cpu pages on remote zones
+         */
+        if (node != numa_node_id())
+                drain_node_pages(node);
+
+        node = next_node(node, node_online_map);
+        if (unlikely(node >= MAX_NUMNODES))
+                node = first_node(node_online_map);
+        __get_cpu_var(reap_node) = node;
+}
+
+#else
+#define init_reap_node(cpu) do { } while (0)
+#define next_reap_node(void) do { } while (0)
+#endif
+
 /*
  * Initiate the reap timer running on the target CPU.  We run at around 1 to 2Hz
  * via the workqueue/eventd.
@@ -806,6 +847,7 @@ static void __devinit start_cpu_timer(int cpu)
          * at that time.
          */
         if (keventd_up() && reap_work->func == NULL) {
+                init_reap_node(cpu);
                 INIT_WORK(reap_work, cache_reap, NULL);
                 schedule_delayed_work_on(cpu, reap_work, HZ + 3 * cpu);
         }
@@ -884,6 +926,23 @@ static void __drain_alien_cache(struct kmem_cache *cachep,
         }
 }
 
+/*
+ * Called from cache_reap() to regularly drain alien caches round robin.
+ */
+static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3)
+{
+        int node = __get_cpu_var(reap_node);
+
+        if (l3->alien) {
+                struct array_cache *ac = l3->alien[node];
+                if (ac && ac->avail) {
+                        spin_lock_irq(&ac->lock);
+                        __drain_alien_cache(cachep, ac, node);
+                        spin_unlock_irq(&ac->lock);
+                }
+        }
+}
+
 static void drain_alien_cache(struct kmem_cache *cachep, struct array_cache **alien)
 {
         int i = 0;
@@ -902,6 +961,7 @@ static void drain_alien_cache(struct kmem_cache *cachep, struct array_cache **al
 #else
 
 #define drain_alien_cache(cachep, alien) do { } while (0)
+#define reap_alien(cachep, l3) do { } while (0)
 
 static inline struct array_cache **alloc_alien_cache(int node, int limit)
 {
@@ -1124,6 +1184,7 @@ void __init kmem_cache_init(void)
         struct cache_sizes *sizes;
         struct cache_names *names;
         int i;
+        int order;
 
         for (i = 0; i < NUM_INIT_LISTS; i++) {
                 kmem_list3_init(&initkmem_list3[i]);
@@ -1167,11 +1228,15 @@ void __init kmem_cache_init(void)
 
         cache_cache.buffer_size = ALIGN(cache_cache.buffer_size, cache_line_size());
 
-        cache_estimate(0, cache_cache.buffer_size, cache_line_size(), 0,
-                       &left_over, &cache_cache.num);
+        for (order = 0; order < MAX_ORDER; order++) {
+                cache_estimate(order, cache_cache.buffer_size,
+                        cache_line_size(), 0, &left_over, &cache_cache.num);
+                if (cache_cache.num)
+                        break;
+        }
         if (!cache_cache.num)
                 BUG();
-
+        cache_cache.gfporder = order;
         cache_cache.colour = left_over / cache_cache.colour_off;
         cache_cache.slab_size = ALIGN(cache_cache.num * sizeof(kmem_bufctl_t) +
                                       sizeof(struct slab), cache_line_size());
@@ -1648,6 +1713,14 @@ static inline size_t calculate_slab_order(struct kmem_cache *cachep,
                 left_over = remainder;
 
                 /*
+                 * A VFS-reclaimable slab tends to have most allocations
+                 * as GFP_NOFS and we really don't want to have to be allocating
+                 * higher-order pages when we are unable to shrink dcache.
+                 */
+                if (flags & SLAB_RECLAIM_ACCOUNT)
+                        break;
+
+                /*
                  * Large number of objects is good, but very large slabs are
                  * currently bad for the gfp()s.
                  */
@@ -1869,17 +1942,7 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 
         size = ALIGN(size, align);
 
-        if ((flags & SLAB_RECLAIM_ACCOUNT) && size <= PAGE_SIZE) {
-                /*
-                 * A VFS-reclaimable slab tends to have most allocations
-                 * as GFP_NOFS and we really don't want to have to be allocating
-                 * higher-order pages when we are unable to shrink dcache.
-                 */
-                cachep->gfporder = 0;
-                cache_estimate(cachep->gfporder, size, align, flags,
-                               &left_over, &cachep->num);
-        } else
-                left_over = calculate_slab_order(cachep, size, align, flags);
+        left_over = calculate_slab_order(cachep, size, align, flags);
 
         if (!cachep->num) {
                 printk("kmem_cache_create: couldn't create cache %s.\n", name);
@@ -3494,8 +3557,7 @@ static void cache_reap(void *unused)
                 check_irq_on();
 
                 l3 = searchp->nodelists[numa_node_id()];
-                if (l3->alien)
-                        drain_alien_cache(searchp, l3->alien);
+                reap_alien(searchp, l3);
                 spin_lock_irq(&l3->list_lock);
 
                 drain_array_locked(searchp, cpu_cache_get(searchp), 0,
@@ -3545,7 +3607,7 @@ static void cache_reap(void *unused)
         }
         check_irq_on();
         mutex_unlock(&cache_chain_mutex);
-        drain_remote_pages();
+        next_reap_node();
         /* Setup the next iteration */
         schedule_delayed_work(&__get_cpu_var(reap_work), REAPTIMEOUT_CPUC);
 }
diff --git a/mm/swap.c b/mm/swap.c
index cce3dda59c59..b524ea90bddb 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -393,7 +393,8 @@ void pagevec_strip(struct pagevec *pvec)
                 struct page *page = pvec->pages[i];
 
                 if (PagePrivate(page) && !TestSetPageLocked(page)) {
-                        try_to_release_page(page, 0);
+                        if (PagePrivate(page))
+                                try_to_release_page(page, 0);
                         unlock_page(page);
                 }
         }
@@ -489,13 +490,34 @@ void percpu_counter_mod(struct percpu_counter *fbc, long amount)
         if (count >= FBC_BATCH || count <= -FBC_BATCH) {
                 spin_lock(&fbc->lock);
                 fbc->count += count;
+                *pcount = 0;
                 spin_unlock(&fbc->lock);
-                count = 0;
+        } else {
+                *pcount = count;
         }
-        *pcount = count;
         put_cpu();
 }
 EXPORT_SYMBOL(percpu_counter_mod);
+
+/*
+ * Add up all the per-cpu counts, return the result.  This is a more accurate
+ * but much slower version of percpu_counter_read_positive()
+ */
+long percpu_counter_sum(struct percpu_counter *fbc)
+{
+        long ret;
+        int cpu;
+
+        spin_lock(&fbc->lock);
+        ret = fbc->count;
+        for_each_cpu(cpu) {
+                long *pcount = per_cpu_ptr(fbc->counters, cpu);
+                ret += *pcount;
+        }
+        spin_unlock(&fbc->lock);
+        return ret < 0 ? 0 : ret;
+}
+EXPORT_SYMBOL(percpu_counter_sum);
 #endif
 
 /*
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b0af7593d01e..4fe7e3aa02e2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -700,7 +700,7 @@ int migrate_page_remove_references(struct page *newpage,
          * the page.
          */
         if (!mapping || page_mapcount(page) + nr_refs != page_count(page))
-                return 1;
+                return -EAGAIN;
 
         /*
          * Establish swap ptes for anonymous pages or destroy pte
@@ -721,13 +721,15 @@ int migrate_page_remove_references(struct page *newpage,
          * If the page was not migrated then the PageSwapCache bit
          * is still set and the operation may continue.
          */
-        try_to_unmap(page, 1);
+        if (try_to_unmap(page, 1) == SWAP_FAIL)
+                /* A vma has VM_LOCKED set -> Permanent failure */
+                return -EPERM;
 
         /*
          * Give up if we were unable to remove all mappings.
          */
         if (page_mapcount(page))
-                return 1;
+                return -EAGAIN;
 
         write_lock_irq(&mapping->tree_lock);
 
@@ -738,7 +740,7 @@ int migrate_page_remove_references(struct page *newpage,
         if (!page_mapping(page) || page_count(page) != nr_refs ||
                         *radix_pointer != page) {
                 write_unlock_irq(&mapping->tree_lock);
-                return 1;
+                return -EAGAIN;
         }
 
         /*
@@ -813,10 +815,14 @@ EXPORT_SYMBOL(migrate_page_copy);
  */
 int migrate_page(struct page *newpage, struct page *page)
 {
+        int rc;
+
         BUG_ON(PageWriteback(page));    /* Writeback must be complete */
 
-        if (migrate_page_remove_references(newpage, page, 2))
-                return -EAGAIN;
+        rc = migrate_page_remove_references(newpage, page, 2);
+
+        if (rc)
+                return rc;
 
         migrate_page_copy(newpage, page);
 
@@ -1883,7 +1889,8 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 
         if (!(gfp_mask & __GFP_WAIT) ||
                 zone->all_unreclaimable ||
-                atomic_read(&zone->reclaim_in_progress) > 0)
+                atomic_read(&zone->reclaim_in_progress) > 0 ||
+                (p->flags & PF_MEMALLOC))
                         return 0;
 
         node_id = zone->zone_pgdat->node_id;