Merge commit 'v2.6.28' into core/core

10 files changed, 124 insertions, 62 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index f2e574dbc300..801c08b046e6 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -176,6 +176,9 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
         int ret = 0;
         struct device *dev;
 
+        if (bdi->dev)   /* The driver needs to use separate queues per device */
+                goto exit;
+
         va_start(args, fmt);
         dev = device_create_vargs(bdi_class, parent, MKDEV(0, 0), bdi, fmt, args);
         va_end(args);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b5b2b15085a8..b17371185468 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -189,7 +189,7 @@ static void grow_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn,
                                         pgdat->node_start_pfn;
 }
 
-static int __add_zone(struct zone *zone, unsigned long phys_start_pfn)
+static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
 {
         struct pglist_data *pgdat = zone->zone_pgdat;
         int nr_pages = PAGES_PER_SECTION;
@@ -216,7 +216,7 @@ static int __add_zone(struct zone *zone, unsigned long phys_start_pfn)
         return 0;
 }
 
-static int __add_section(struct zone *zone, unsigned long phys_start_pfn)
+static int __meminit __add_section(struct zone *zone, unsigned long phys_start_pfn)
 {
         int nr_pages = PAGES_PER_SECTION;
         int ret;
@@ -273,7 +273,7 @@ static int __remove_section(struct zone *zone, struct mem_section *ms)
  * call this function after deciding the zone to which to
  * add the new pages.
  */
-int __add_pages(struct zone *zone, unsigned long phys_start_pfn,
+int __ref __add_pages(struct zone *zone, unsigned long phys_start_pfn,
                  unsigned long nr_pages)
 {
         unsigned long i;
@@ -470,7 +470,8 @@ static void rollback_node_hotadd(int nid, pg_data_t *pgdat)
 }
 
 
-int add_memory(int nid, u64 start, u64 size)
+/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
+int __ref add_memory(int nid, u64 start, u64 size)
 {
         pg_data_t *pgdat = NULL;
         int new_pgdat = 0;
diff --git a/mm/migrate.c b/mm/migrate.c
index 1e0d6b237f44..037b0967c1e3 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -987,25 +987,18 @@ out:
 /*
  * Determine the nodes of an array of pages and store it in an array of status.
  */
-static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages,
-                         const void __user * __user *pages,
-                         int __user *status)
+static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages,
+                                const void __user **pages, int *status)
 {
         unsigned long i;
-        int err;
 
         down_read(&mm->mmap_sem);
 
         for (i = 0; i < nr_pages; i++) {
-                const void __user *p;
-                unsigned long addr;
+                unsigned long addr = (unsigned long)(*pages);
                 struct vm_area_struct *vma;
                 struct page *page;
-
-                err = -EFAULT;
-                if (get_user(p, pages+i))
-                        goto out;
-                addr = (unsigned long) p;
+                int err = -EFAULT;
 
                 vma = find_vma(mm, addr);
                 if (!vma)
@@ -1024,12 +1017,52 @@ static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages,
 
                 err = page_to_nid(page);
 set_status:
-                put_user(err, status+i);
+                *status = err;
+
+                pages++;
+                status++;
+        }
+
+        up_read(&mm->mmap_sem);
+}
+
+/*
+ * Determine the nodes of a user array of pages and store it in
+ * a user array of status.
+ */
+static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages,
+                         const void __user * __user *pages,
+                         int __user *status)
+{
+#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 + i > nr_pages)
+                        chunk_nr = nr_pages - i;
+
+                err = copy_from_user(chunk_pages, &pages[i],
+                                     chunk_nr * sizeof(*chunk_pages));
+                if (err) {
+                        err = -EFAULT;
+                        goto out;
+                }
+
+                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;
 
 out:
-        up_read(&mm->mmap_sem);
         return err;
 }
 
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 1223d927904d..ab27ff750519 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -21,7 +21,7 @@ static unsigned long total_usage;
 #if !defined(CONFIG_SPARSEMEM)
 
 
-void __init pgdat_page_cgroup_init(struct pglist_data *pgdat)
+void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
 {
         pgdat->node_page_cgroup = NULL;
 }
@@ -49,6 +49,9 @@ static int __init alloc_node_page_cgroup(int nid)
         start_pfn = NODE_DATA(nid)->node_start_pfn;
         nr_pages = NODE_DATA(nid)->node_spanned_pages;
 
+        if (!nr_pages)
+                return 0;
+
         table_size = sizeof(struct page_cgroup) * nr_pages;
 
         base = __alloc_bootmem_node_nopanic(NODE_DATA(nid),
@@ -97,7 +100,8 @@ struct page_cgroup *lookup_page_cgroup(struct page *page)
         return section->page_cgroup + pfn;
 }
 
-int __meminit init_section_page_cgroup(unsigned long pfn)
+/* __alloc_bootmem...() is protected by !slab_available() */
+int __init_refok init_section_page_cgroup(unsigned long pfn)
 {
         struct mem_section *section;
         struct page_cgroup *base, *pc;
@@ -106,19 +110,29 @@ int __meminit init_section_page_cgroup(unsigned long pfn)
 
         section = __pfn_to_section(pfn);
 
-        if (section->page_cgroup)
-                return 0;
-
-        nid = page_to_nid(pfn_to_page(pfn));
-
-        table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
-        if (slab_is_available()) {
-                base = kmalloc_node(table_size, GFP_KERNEL, nid);
-                if (!base)
-                        base = vmalloc_node(table_size, nid);
-        } else {
-                base = __alloc_bootmem_node_nopanic(NODE_DATA(nid), table_size,
+        if (!section->page_cgroup) {
+                nid = page_to_nid(pfn_to_page(pfn));
+                table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
+                if (slab_is_available()) {
+                        base = kmalloc_node(table_size, GFP_KERNEL, nid);
+                        if (!base)
+                                base = vmalloc_node(table_size, nid);
+                } else {
+                        base = __alloc_bootmem_node_nopanic(NODE_DATA(nid),
+                                table_size,
                                 PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+                }
+        } else {
+                /*
+                 * We don't have to allocate page_cgroup again, but
+                 * address of memmap may be changed. So, we have to initialize
+                 * again.
+                 */
+                base = section->page_cgroup + pfn;
+                table_size = 0;
+                /* check address of memmap is changed or not. */
+                if (base->page == pfn_to_page(pfn))
+                        return 0;
         }
 
         if (!base) {
@@ -158,7 +172,7 @@ void __free_page_cgroup(unsigned long pfn)
         }
 }
 
-int online_page_cgroup(unsigned long start_pfn,
+int __meminit online_page_cgroup(unsigned long start_pfn,
                         unsigned long nr_pages,
                         int nid)
 {
@@ -183,7 +197,7 @@ int online_page_cgroup(unsigned long start_pfn,
         return -ENOMEM;
 }
 
-int offline_page_cgroup(unsigned long start_pfn,
+int __meminit offline_page_cgroup(unsigned long start_pfn,
                 unsigned long nr_pages, int nid)
 {
         unsigned long start, end, pfn;
@@ -197,7 +211,7 @@ int offline_page_cgroup(unsigned long start_pfn,
 
 }
 
-static int page_cgroup_callback(struct notifier_block *self,
+static int __meminit page_cgroup_callback(struct notifier_block *self,
                                unsigned long action, void *arg)
 {
         struct memory_notify *mn = arg;
@@ -207,18 +221,23 @@ static int page_cgroup_callback(struct notifier_block *self,
                 ret = online_page_cgroup(mn->start_pfn,
                                    mn->nr_pages, mn->status_change_nid);
                 break;
-        case MEM_CANCEL_ONLINE:
         case MEM_OFFLINE:
                 offline_page_cgroup(mn->start_pfn,
                                 mn->nr_pages, mn->status_change_nid);
                 break;
+        case MEM_CANCEL_ONLINE:
         case MEM_GOING_OFFLINE:
                 break;
         case MEM_ONLINE:
         case MEM_CANCEL_OFFLINE:
                 break;
         }
-        ret = notifier_from_errno(ret);
+
+        if (ret)
+                ret = notifier_from_errno(ret);
+        else
+                ret = NOTIFY_OK;
+
         return ret;
 }
 
@@ -248,7 +267,7 @@ void __init page_cgroup_init(void)
         " want\n");
 }
 
-void __init pgdat_page_cgroup_init(struct pglist_data *pgdat)
+void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
 {
         return;
 }
diff --git a/mm/slob.c b/mm/slob.c
index cb675d126791..bf7e8fc3aed8 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -535,7 +535,7 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
         struct kmem_cache *c;
 
         c = slob_alloc(sizeof(struct kmem_cache),
-                flags, ARCH_KMALLOC_MINALIGN, -1);
+                GFP_KERNEL, ARCH_KMALLOC_MINALIGN, -1);
 
         if (c) {
                 c->name = name;
diff --git a/mm/slub.c b/mm/slub.c
index 7ad489af9561..a2cd47d89e0a 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2931,8 +2931,10 @@ static int slab_memory_callback(struct notifier_block *self,
         case MEM_CANCEL_OFFLINE:
                 break;
         }
-
-        ret = notifier_from_errno(ret);
+        if (ret)
+                ret = notifier_from_errno(ret);
+        else
+                ret = NOTIFY_OK;
         return ret;
 }
 
@@ -3595,7 +3597,7 @@ static int list_locations(struct kmem_cache *s, char *buf,
         for (i = 0; i < t.count; i++) {
                 struct location *l = &t.loc[i];
 
-                if (len > PAGE_SIZE - 100)
+                if (len > PAGE_SIZE - KSYM_SYMBOL_LEN - 100)
                         break;
                 len += sprintf(buf + len, "%7ld ", l->count);
 
diff --git a/mm/sparse.c b/mm/sparse.c
index 39db301b920d..083f5b63e7a8 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -570,7 +570,7 @@ static void free_section_usemap(struct page *memmap, unsigned long *usemap)
  * set.  If this is <=0, then that means that the passed-in
  * map was not consumed and must be freed.
  */
-int sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
+int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
                            int nr_pages)
 {
         unsigned long section_nr = pfn_to_section_nr(start_pfn);
diff --git a/mm/swap.c b/mm/swap.c
index 2152e48a7b8f..b135ec90cdeb 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -299,7 +299,6 @@ void lru_add_drain(void)
         put_cpu();
 }
 
-#if defined(CONFIG_NUMA) || defined(CONFIG_UNEVICTABLE_LRU)
 static void lru_add_drain_per_cpu(struct work_struct *dummy)
 {
         lru_add_drain();
@@ -313,18 +312,6 @@ int lru_add_drain_all(void)
         return schedule_on_each_cpu(lru_add_drain_per_cpu);
 }
 
-#else
-
-/*
- * Returns 0 for success
- */
-int lru_add_drain_all(void)
-{
-        lru_add_drain();
-        return 0;
-}
-#endif
-
 /*
  * Batched page_cache_release().  Decrement the reference count on all the
  * passed pages.  If it fell to zero then remove the page from the LRU and
@@ -445,6 +432,7 @@ void ____pagevec_lru_add(struct pagevec *pvec, enum lru_list lru)
         for (i = 0; i < pagevec_count(pvec); i++) {
                 struct page *page = pvec->pages[i];
                 struct zone *pagezone = page_zone(page);
+                int file;
 
                 if (pagezone != zone) {
                         if (zone)
@@ -456,8 +444,12 @@ void ____pagevec_lru_add(struct pagevec *pvec, enum lru_list lru)
                 VM_BUG_ON(PageUnevictable(page));
                 VM_BUG_ON(PageLRU(page));
                 SetPageLRU(page);
-                if (is_active_lru(lru))
+                file = is_file_lru(lru);
+                zone->recent_scanned[file]++;
+                if (is_active_lru(lru)) {
                         SetPageActive(page);
+                        zone->recent_rotated[file]++;
+                }
                 add_page_to_lru_list(zone, page, lru);
         }
         if (zone)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 30f826d484f0..1ddb77ba3995 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -77,7 +77,6 @@ static void vunmap_page_range(unsigned long addr, unsigned long end)
 
         BUG_ON(addr >= end);
         pgd = pgd_offset_k(addr);
-        flush_cache_vunmap(addr, end);
         do {
                 next = pgd_addr_end(addr, end);
                 if (pgd_none_or_clear_bad(pgd))
@@ -543,9 +542,10 @@ static void purge_vmap_area_lazy(void)
 }
 
 /*
- * Free and unmap a vmap area
+ * Free and unmap a vmap area, caller ensuring flush_cache_vunmap had been
+ * called for the correct range previously.
  */
-static void free_unmap_vmap_area(struct vmap_area *va)
+static void free_unmap_vmap_area_noflush(struct vmap_area *va)
 {
         va->flags |= VM_LAZY_FREE;
         atomic_add((va->va_end - va->va_start) >> PAGE_SHIFT, &vmap_lazy_nr);
@@ -553,6 +553,15 @@ static void free_unmap_vmap_area(struct vmap_area *va)
                 try_purge_vmap_area_lazy();
 }
 
+/*
+ * Free and unmap a vmap area
+ */
+static void free_unmap_vmap_area(struct vmap_area *va)
+{
+        flush_cache_vunmap(va->va_start, va->va_end);
+        free_unmap_vmap_area_noflush(va);
+}
+
 static struct vmap_area *find_vmap_area(unsigned long addr)
 {
         struct vmap_area *va;
@@ -734,7 +743,7 @@ static void free_vmap_block(struct vmap_block *vb)
         spin_unlock(&vmap_block_tree_lock);
         BUG_ON(tmp != vb);
 
-        free_unmap_vmap_area(vb->va);
+        free_unmap_vmap_area_noflush(vb->va);
         call_rcu(&vb->rcu_head, rcu_free_vb);
 }
 
@@ -796,6 +805,9 @@ static void vb_free(const void *addr, unsigned long size)
 
         BUG_ON(size & ~PAGE_MASK);
         BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
+
+        flush_cache_vunmap((unsigned long)addr, (unsigned long)addr + size);
+
         order = get_order(size);
 
         offset = (unsigned long)addr & (VMAP_BLOCK_SIZE - 1);
@@ -1705,7 +1717,7 @@ static int s_show(struct seq_file *m, void *p)
                 v->addr, v->addr + v->size, v->size);
 
         if (v->caller) {
-                char buff[2 * KSYM_NAME_LEN];
+                char buff[KSYM_SYMBOL_LEN];
 
                 seq_putc(m, ' ');
                 sprint_symbol(buff, (unsigned long)v->caller);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7ea1440b53db..62e7f62fb559 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1248,6 +1248,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
                 list_add(&page->lru, &l_inactive);
         }
 
+        spin_lock_irq(&zone->lru_lock);
         /*
          * Count referenced pages from currently used mappings as
          * rotated, even though they are moved to the inactive list.
@@ -1263,7 +1264,6 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 
         pgmoved = 0;
         lru = LRU_BASE + file * LRU_FILE;
-        spin_lock_irq(&zone->lru_lock);
         while (!list_empty(&l_inactive)) {
                 page = lru_to_page(&l_inactive);
                 prefetchw_prev_lru_page(page, &l_inactive, flags);