Merge ../linux-2.6

6 files changed, 89 insertions, 26 deletions

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 954981b14303..2a8206009422 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -748,7 +748,7 @@ 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 +942,20 @@ 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;
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 61800b88e241..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)
 {
@@ -3497,8 +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,
@@ -3548,7 +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/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;