Merge commit 'v2.6.28-rc7' into core/locking

11 files changed, 103 insertions, 98 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index d143ab67be44..6058b53dcb89 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1796,6 +1796,7 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
                                 struct page *page, unsigned long address)
 {
+        struct hstate *h = hstate_vma(vma);
         struct vm_area_struct *iter_vma;
         struct address_space *mapping;
         struct prio_tree_iter iter;
@@ -1805,7 +1806,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
          * vm_pgoff is in PAGE_SIZE units, hence the different calculation
          * from page cache lookup which is in HPAGE_SIZE units.
          */
-        address = address & huge_page_mask(hstate_vma(vma));
+        address = address & huge_page_mask(h);
         pgoff = ((address - vma->vm_start) >> PAGE_SHIFT)
                 + (vma->vm_pgoff >> PAGE_SHIFT);
         mapping = (struct address_space *)page_private(page);
@@ -1824,7 +1825,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
                  */
                 if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER))
                         unmap_hugepage_range(iter_vma,
-                                address, address + HPAGE_SIZE,
+                                address, address + huge_page_size(h),
                                 page);
         }
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 6837a1014372..b17371185468 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -22,7 +22,6 @@
 #include <linux/highmem.h>
 #include <linux/vmalloc.h>
 #include <linux/ioport.h>
-#include <linux/cpuset.h>
 #include <linux/delay.h>
 #include <linux/migrate.h>
 #include <linux/page-isolation.h>
@@ -190,7 +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;
@@ -217,7 +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;
@@ -274,7 +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;
@@ -471,7 +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;
@@ -498,8 +498,6 @@ int add_memory(int nid, u64 start, u64 size)
         /* we online node here. we can't roll back from here. */
         node_set_online(nid);
 
-        cpuset_track_online_nodes();
-
         if (new_pgdat) {
                 ret = register_one_node(nid);
                 /*
diff --git a/mm/migrate.c b/mm/migrate.c
index 385db89f0c33..1e0d6b237f44 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -522,15 +522,12 @@ static int writeout(struct address_space *mapping, struct page *page)
         remove_migration_ptes(page, page);
 
         rc = mapping->a_ops->writepage(page, &wbc);
-        if (rc < 0)
-                /* I/O Error writing */
-                return -EIO;
 
         if (rc != AOP_WRITEPAGE_ACTIVATE)
                 /* unlocked. Relock */
                 lock_page(page);
 
-        return -EAGAIN;
+        return (rc < 0) ? -EIO : -EAGAIN;
 }
 
 /*
diff --git a/mm/mlock.c b/mm/mlock.c
index 008ea70b7afa..1ada366570cb 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -66,14 +66,10 @@ void __clear_page_mlock(struct page *page)
                 putback_lru_page(page);
         } else {
                 /*
-                 * Page not on the LRU yet.  Flush all pagevecs and retry.
+                 * We lost the race. the page already moved to evictable list.
                  */
-                lru_add_drain_all();
-                if (!isolate_lru_page(page))
-                        putback_lru_page(page);
-                else if (PageUnevictable(page))
+                if (PageUnevictable(page))
                         count_vm_event(UNEVICTABLE_PGSTRANDED);
-
         }
 }
 
@@ -166,7 +162,7 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma,
         unsigned long addr = start;
         struct page *pages[16]; /* 16 gives a reasonable batch */
         int nr_pages = (end - start) / PAGE_SIZE;
-        int ret;
+        int ret = 0;
         int gup_flags = 0;
 
         VM_BUG_ON(start & ~PAGE_MASK);
@@ -187,8 +183,6 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma,
         if (vma->vm_flags & VM_WRITE)
                 gup_flags |= GUP_FLAGS_WRITE;
 
-        lru_add_drain_all();    /* push cached pages to LRU */
-
         while (nr_pages > 0) {
                 int i;
 
@@ -251,8 +245,6 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma,
                 ret = 0;
         }
 
-        lru_add_drain_all();    /* to update stats */
-
         return ret;     /* count entire vma as locked_vm */
 }
 
@@ -546,6 +538,8 @@ asmlinkage long sys_mlock(unsigned long start, size_t len)
         if (!can_do_mlock())
                 return -EPERM;
 
+        lru_add_drain_all();    /* flush pagevec */
+
         down_write(&current->mm->mmap_sem);
         len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
         start &= PAGE_MASK;
@@ -612,6 +606,8 @@ asmlinkage long sys_mlockall(int flags)
         if (!can_do_mlock())
                 goto out;
 
+        lru_add_drain_all();    /* flush pagevec */
+
         down_write(&current->mm->mmap_sem);
 
         lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
diff --git a/mm/mmap.c b/mm/mmap.c
index de14ac21e5b5..d4855a682ab6 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1704,7 +1704,7 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr)
         vma = find_vma_prev(mm, addr, &prev);
         if (vma && (vma->vm_start <= addr))
                 return vma;
-        if (expand_stack(prev, addr))
+        if (!prev || expand_stack(prev, addr))
                 return NULL;
         if (prev->vm_flags & VM_LOCKED) {
                 if (mlock_vma_pages_range(prev, addr, prev->vm_end) < 0)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 54069e64e3a8..d8ac01474563 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1561,6 +1561,10 @@ nofail_alloc:
 
         /* We now go into synchronous reclaim */
         cpuset_memory_pressure_bump();
+        /*
+         * The task's cpuset might have expanded its set of allowable nodes
+         */
+        cpuset_update_task_memory_state();
         p->flags |= PF_MEMALLOC;
         reclaim_state.reclaimed_slab = 0;
         p->reclaim_state = &reclaim_state;
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index f59d797dc5a9..0b3cbf090a67 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;
 }
@@ -97,7 +97,8 @@ 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 +107,29 @@ 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) {
@@ -158,14 +169,14 @@ 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)
 {
         unsigned long start, end, pfn;
         int fail = 0;
 
-        start = start_pfn & (PAGES_PER_SECTION - 1);
+        start = start_pfn & ~(PAGES_PER_SECTION - 1);
         end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION);
 
         for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) {
@@ -183,12 +194,12 @@ 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;
 
-        start = start_pfn & (PAGES_PER_SECTION - 1);
+        start = start_pfn & ~(PAGES_PER_SECTION - 1);
         end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION);
 
         for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
@@ -197,7 +208,7 @@ 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 +218,23 @@ 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 +264,7 @@ 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/slub.c b/mm/slub.c
index 7ad489af9561..749588a50a5a 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;
 }
 
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/vmalloc.c b/mm/vmalloc.c
index ba6b0f5f7fac..f3f6e0758562 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))
@@ -324,14 +323,14 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
 
         BUG_ON(size & ~PAGE_MASK);
 
-        addr = ALIGN(vstart, align);
-
         va = kmalloc_node(sizeof(struct vmap_area),
                         gfp_mask & GFP_RECLAIM_MASK, node);
         if (unlikely(!va))
                 return ERR_PTR(-ENOMEM);
 
 retry:
+        addr = ALIGN(vstart, align);
+
         spin_lock(&vmap_area_lock);
         /* XXX: could have a last_hole cache */
         n = vmap_area_root.rb_node;
@@ -362,7 +361,7 @@ retry:
                                 goto found;
                 }
 
-                while (addr + size >= first->va_start && addr + size <= vend) {
+                while (addr + size > first->va_start && addr + size <= vend) {
                         addr = ALIGN(first->va_end + PAGE_SIZE, align);
 
                         n = rb_next(&first->rb_node);
@@ -522,24 +521,45 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end,
 }
 
 /*
+ * Kick off a purge of the outstanding lazy areas. Don't bother if somebody
+ * is already purging.
+ */
+static void try_purge_vmap_area_lazy(void)
+{
+        unsigned long start = ULONG_MAX, end = 0;
+
+        __purge_vmap_area_lazy(&start, &end, 0, 0);
+}
+
+/*
  * Kick off a purge of the outstanding lazy areas.
  */
 static void purge_vmap_area_lazy(void)
 {
         unsigned long start = ULONG_MAX, end = 0;
 
-        __purge_vmap_area_lazy(&start, &end, 0, 0);
+        __purge_vmap_area_lazy(&start, &end, 1, 0);
 }
 
 /*
- * 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);
         if (unlikely(atomic_read(&vmap_lazy_nr) > lazy_max_pages()))
-                purge_vmap_area_lazy();
+                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)
@@ -723,7 +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);
 }
 
@@ -785,6 +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);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 3b5860294bb6..62e7f62fb559 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -623,6 +623,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
                  * Try to allocate it some swap space here.
                  */
                 if (PageAnon(page) && !PageSwapCache(page)) {
+                        if (!(sc->gfp_mask & __GFP_IO))
+                                goto keep_locked;
                         switch (try_to_munlock(page)) {
                         case SWAP_FAIL:         /* shouldn't happen */
                         case SWAP_AGAIN:
@@ -634,6 +636,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
                         }
                         if (!add_to_swap(page, GFP_ATOMIC))
                                 goto activate_locked;
+                        may_enter_fs = 1;
                 }
 #endif /* CONFIG_SWAP */
 
@@ -1245,6 +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.
@@ -1260,7 +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);
@@ -1386,9 +1389,9 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
         file_prio = 200 - sc->swappiness;
 
         /*
-         *                  anon       recent_rotated[0]
-         * %anon = 100 * ----------- / ----------------- * IO cost
-         *               anon + file      rotate_sum
+         * The amount of pressure on anon vs file pages is inversely
+         * proportional to the fraction of recently scanned pages on
+         * each list that were recently referenced and in active use.
          */
         ap = (anon_prio + 1) * (zone->recent_scanned[0] + 1);
         ap /= zone->recent_rotated[0] + 1;
@@ -2368,39 +2371,6 @@ int page_evictable(struct page *page, struct vm_area_struct *vma)
         return 1;
 }
 
-static void show_page_path(struct page *page)
-{
-        char buf[256];
-        if (page_is_file_cache(page)) {
-                struct address_space *mapping = page->mapping;
-                struct dentry *dentry;
-                pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
-
-                spin_lock(&mapping->i_mmap_lock);
-                dentry = d_find_alias(mapping->host);
-                printk(KERN_INFO "rescued: %s %lu\n",
-                       dentry_path(dentry, buf, 256), pgoff);
-                spin_unlock(&mapping->i_mmap_lock);
-        } else {
-#if defined(CONFIG_MM_OWNER) && defined(CONFIG_MMU)
-                struct anon_vma *anon_vma;
-                struct vm_area_struct *vma;
-
-                anon_vma = page_lock_anon_vma(page);
-                if (!anon_vma)
-                        return;
-
-                list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
-                        printk(KERN_INFO "rescued: anon %s\n",
-                               vma->vm_mm->owner->comm);
-                        break;
-                }
-                page_unlock_anon_vma(anon_vma);
-#endif
-        }
-}
-
-
 /**
  * check_move_unevictable_page - check page for evictability and move to appropriate zone lru list
  * @page: page to check evictability and move to appropriate lru list
@@ -2421,8 +2391,6 @@ retry:
         if (page_evictable(page, NULL)) {
                 enum lru_list l = LRU_INACTIVE_ANON + page_is_file_cache(page);
 
-                show_page_path(page);
-
                 __dec_zone_state(zone, NR_UNEVICTABLE);
                 list_move(&page->lru, &zone->lru[l].list);
                 __inc_zone_state(zone, NR_INACTIVE_ANON + l);