X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fmigrate.c;h=4e0eccca5e265ac19bc507a171a2f720d27f8c21;hb=0feed274d2dfa2162d2c37c254eede96926d3717;hp=b5000d463893ffcb8af281aef6635b61904e4680;hpb=04e62a29bf157ce1edd168f2b71b533c80d13628;p=safe%2Fjmp%2Flinux-2.6

diff --git a/mm/migrate.c b/mm/migrate.c
index b5000d4..4e0eccc 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -19,18 +19,20 @@
 #include <linux/pagemap.h>
 #include <linux/buffer_head.h>
 #include <linux/mm_inline.h>
+#include <linux/nsproxy.h>
 #include <linux/pagevec.h>
 #include <linux/rmap.h>
 #include <linux/topology.h>
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
 #include <linux/writeback.h>
+#include <linux/mempolicy.h>
+#include <linux/vmalloc.h>
+#include <linux/security.h>
+#include <linux/memcontrol.h>
 
 #include "internal.h"
 
-/* The maximum number of pages to take off the LRU for migration */
-#define MIGRATE_CHUNK_SIZE 256
-
 #define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))
 
 /*
@@ -49,9 +51,8 @@ int isolate_lru_page(struct page *page, struct list_head *pagelist)
 		struct zone *zone = page_zone(page);
 
 		spin_lock_irq(&zone->lru_lock);
-		if (PageLRU(page)) {
+		if (PageLRU(page) && get_page_unless_zero(page)) {
 			ret = 0;
-			get_page(page);
 			ClearPageLRU(page);
 			if (PageActive(page))
 				del_page_from_active_list(zone, page);
@@ -65,9 +66,8 @@ int isolate_lru_page(struct page *page, struct list_head *pagelist)
 }
 
 /*
- * migrate_prep() needs to be called after we have compiled the list of pages
- * to be migrated using isolate_lru_page() but before we begin a series of calls
- * to migrate_pages().
+ * migrate_prep() needs to be called before we start compiling a list of pages
+ * to be migrated using isolate_lru_page().
  */
 int migrate_prep(void)
 {
@@ -84,7 +84,6 @@ int migrate_prep(void)
 
 static inline void move_to_lru(struct page *page)
 {
-	list_del(&page->lru);
 	if (PageActive(page)) {
 		/*
 		 * lru_cache_add_active checks that
@@ -110,17 +109,13 @@ int putback_lru_pages(struct list_head *l)
 	int count = 0;
 
 	list_for_each_entry_safe(page, page2, l, lru) {
+		list_del(&page->lru);
 		move_to_lru(page);
 		count++;
 	}
 	return count;
 }
 
-static inline int is_swap_pte(pte_t pte)
-{
-	return !pte_none(pte) && !pte_present(pte) && !pte_file(pte);
-}
-
 /*
  * Restore a potential migration pte to a working pte entry
  */
@@ -169,10 +164,25 @@ static void remove_migration_pte(struct vm_area_struct *vma,
 	if (!is_migration_entry(entry) || migration_entry_to_page(entry) != old)
 		goto out;
 
+	/*
+	 * Yes, ignore the return value from a GFP_ATOMIC mem_cgroup_charge.
+	 * Failure is not an option here: we're now expected to remove every
+	 * migration pte, and will cause crashes otherwise.  Normally this
+	 * is not an issue: mem_cgroup_prepare_migration bumped up the old
+	 * page_cgroup count for safety, that's now attached to the new page,
+	 * so this charge should just be another incrementation of the count,
+	 * to keep in balance with rmap.c's mem_cgroup_uncharging.  But if
+	 * there's been a force_empty, those reference counts may no longer
+	 * be reliable, and this charge can actually fail: oh well, we don't
+	 * make the situation any worse by proceeding as if it had succeeded.
+	 */
+	mem_cgroup_charge(new, mm, GFP_ATOMIC);
+
 	get_page(new);
 	pte = pte_mkold(mk_pte(new, vma->vm_page_prot));
 	if (is_write_migration_entry(entry))
 		pte = pte_mkwrite(pte);
+	flush_cache_page(vma, addr, pte_pfn(pte));
 	set_pte_at(mm, addr, ptep, pte);
 
 	if (PageAnon(new))
@@ -182,7 +192,6 @@ static void remove_migration_pte(struct vm_area_struct *vma,
 
 	/* No need to invalidate - it was non-present before */
 	update_mmu_cache(vma, addr, pte);
-	lazy_mmu_prot_update(pte);
 
 out:
 	pte_unmap_unlock(ptep, ptl);
@@ -295,10 +304,10 @@ out:
 static int migrate_page_move_mapping(struct address_space *mapping,
 		struct page *newpage, struct page *page)
 {
-	struct page **radix_pointer;
+	void **pslot;
 
 	if (!mapping) {
-		/* Anonymous page */
+		/* Anonymous page without mapping */
 		if (page_count(page) != 1)
 			return -EAGAIN;
 		return 0;
@@ -306,12 +315,11 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 
 	write_lock_irq(&mapping->tree_lock);
 
-	radix_pointer = (struct page **)radix_tree_lookup_slot(
-						&mapping->page_tree,
-						page_index(page));
+	pslot = radix_tree_lookup_slot(&mapping->page_tree,
+ 					page_index(page));
 
 	if (page_count(page) != 2 + !!PagePrivate(page) ||
-			*radix_pointer != page) {
+			(struct page *)radix_tree_deref_slot(pslot) != page) {
 		write_unlock_irq(&mapping->tree_lock);
 		return -EAGAIN;
 	}
@@ -319,7 +327,7 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 	/*
 	 * Now we know that no one else is looking at the page.
 	 */
-	get_page(newpage);
+	get_page(newpage);	/* add cache reference */
 #ifdef CONFIG_SWAP
 	if (PageSwapCache(page)) {
 		SetPageSwapCache(newpage);
@@ -327,8 +335,27 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 	}
 #endif
 
-	*radix_pointer = newpage;
+	radix_tree_replace_slot(pslot, newpage);
+
+	/*
+	 * Drop cache reference from old page.
+	 * We know this isn't the last reference.
+	 */
 	__put_page(page);
+
+	/*
+	 * If moved to a different zone then also account
+	 * the page for that zone. Other VM counters will be
+	 * taken care of when we establish references to the
+	 * new page and drop references to the old page.
+	 *
+	 * Note that anonymous pages are accounted for
+	 * via NR_FILE_PAGES and NR_ANON_PAGES if they
+	 * are mapped to swap space.
+	 */
+	__dec_zone_page_state(page, NR_FILE_PAGES);
+	__inc_zone_page_state(newpage, NR_FILE_PAGES);
+
 	write_unlock_irq(&mapping->tree_lock);
 
 	return 0;
@@ -410,6 +437,7 @@ int migrate_page(struct address_space *mapping,
 }
 EXPORT_SYMBOL(migrate_page);
 
+#ifdef CONFIG_BLOCK
 /*
  * Migration function for pages with buffers. This function can only be used
  * if the underlying filesystem guarantees that no other references to "page"
@@ -467,6 +495,7 @@ int buffer_migrate_page(struct address_space *mapping,
 	return 0;
 }
 EXPORT_SYMBOL(buffer_migrate_page);
+#endif
 
 /*
  * Writeback a page to clean the dirty state
@@ -526,7 +555,7 @@ static int fallback_migrate_page(struct address_space *mapping,
 	 * Buffers may be managed in a filesystem specific way.
 	 * We must have no buffers or drop them.
 	 */
-	if (page_has_buffers(page) &&
+	if (PagePrivate(page) &&
 	    !try_to_release_page(page, GFP_KERNEL))
 		return -EAGAIN;
 
@@ -534,23 +563,192 @@ static int fallback_migrate_page(struct address_space *mapping,
 }
 
 /*
+ * Move a page to a newly allocated page
+ * The page is locked and all ptes have been successfully removed.
+ *
+ * The new page will have replaced the old page if this function
+ * is successful.
+ */
+static int move_to_new_page(struct page *newpage, struct page *page)
+{
+	struct address_space *mapping;
+	int rc;
+
+	/*
+	 * Block others from accessing the page when we get around to
+	 * establishing additional references. We are the only one
+	 * holding a reference to the new page at this point.
+	 */
+	if (TestSetPageLocked(newpage))
+		BUG();
+
+	/* Prepare mapping for the new page.*/
+	newpage->index = page->index;
+	newpage->mapping = page->mapping;
+
+	mapping = page_mapping(page);
+	if (!mapping)
+		rc = migrate_page(mapping, newpage, page);
+	else if (mapping->a_ops->migratepage)
+		/*
+		 * Most pages have a mapping and most filesystems
+		 * should provide a migration function. Anonymous
+		 * pages are part of swap space which also has its
+		 * own migration function. This is the most common
+		 * path for page migration.
+		 */
+		rc = mapping->a_ops->migratepage(mapping,
+						newpage, page);
+	else
+		rc = fallback_migrate_page(mapping, newpage, page);
+
+	if (!rc) {
+		mem_cgroup_page_migration(page, newpage);
+		remove_migration_ptes(page, newpage);
+	} else
+		newpage->mapping = NULL;
+
+	unlock_page(newpage);
+
+	return rc;
+}
+
+/*
+ * Obtain the lock on page, remove all ptes and migrate the page
+ * to the newly allocated page in newpage.
+ */
+static int unmap_and_move(new_page_t get_new_page, unsigned long private,
+			struct page *page, int force)
+{
+	int rc = 0;
+	int *result = NULL;
+	struct page *newpage = get_new_page(page, private, &result);
+	int rcu_locked = 0;
+	int charge = 0;
+
+	if (!newpage)
+		return -ENOMEM;
+
+	if (page_count(page) == 1)
+		/* page was freed from under us. So we are done. */
+		goto move_newpage;
+
+	rc = -EAGAIN;
+	if (TestSetPageLocked(page)) {
+		if (!force)
+			goto move_newpage;
+		lock_page(page);
+	}
+
+	if (PageWriteback(page)) {
+		if (!force)
+			goto unlock;
+		wait_on_page_writeback(page);
+	}
+	/*
+	 * By try_to_unmap(), page->mapcount goes down to 0 here. In this case,
+	 * we cannot notice that anon_vma is freed while we migrates a page.
+	 * This rcu_read_lock() delays freeing anon_vma pointer until the end
+	 * of migration. File cache pages are no problem because of page_lock()
+	 * File Caches may use write_page() or lock_page() in migration, then,
+	 * just care Anon page here.
+	 */
+	if (PageAnon(page)) {
+		rcu_read_lock();
+		rcu_locked = 1;
+	}
+
+	/*
+	 * Corner case handling:
+	 * 1. When a new swap-cache page is read into, it is added to the LRU
+	 * and treated as swapcache but it has no rmap yet.
+	 * Calling try_to_unmap() against a page->mapping==NULL page will
+	 * trigger a BUG.  So handle it here.
+	 * 2. An orphaned page (see truncate_complete_page) might have
+	 * fs-private metadata. The page can be picked up due to memory
+	 * offlining.  Everywhere else except page reclaim, the page is
+	 * invisible to the vm, so the page can not be migrated.  So try to
+	 * free the metadata, so the page can be freed.
+	 */
+	if (!page->mapping) {
+		if (!PageAnon(page) && PagePrivate(page)) {
+			/*
+			 * Go direct to try_to_free_buffers() here because
+			 * a) that's what try_to_release_page() would do anyway
+			 * b) we may be under rcu_read_lock() here, so we can't
+			 *    use GFP_KERNEL which is what try_to_release_page()
+			 *    needs to be effective.
+			 */
+			try_to_free_buffers(page);
+		}
+		goto rcu_unlock;
+	}
+
+	charge = mem_cgroup_prepare_migration(page);
+	/* Establish migration ptes or remove ptes */
+	try_to_unmap(page, 1);
+
+	if (!page_mapped(page))
+		rc = move_to_new_page(newpage, page);
+
+	if (rc) {
+		remove_migration_ptes(page, page);
+		if (charge)
+			mem_cgroup_end_migration(page);
+	} else if (charge)
+ 		mem_cgroup_end_migration(newpage);
+rcu_unlock:
+	if (rcu_locked)
+		rcu_read_unlock();
+
+unlock:
+
+	unlock_page(page);
+
+	if (rc != -EAGAIN) {
+ 		/*
+ 		 * A page that has been migrated has all references
+ 		 * removed and will be freed. A page that has not been
+ 		 * migrated will have kepts its references and be
+ 		 * restored.
+ 		 */
+ 		list_del(&page->lru);
+ 		move_to_lru(page);
+	}
+
+move_newpage:
+	/*
+	 * Move the new page to the LRU. If migration was not successful
+	 * then this will free the page.
+	 */
+	move_to_lru(newpage);
+	if (result) {
+		if (rc)
+			*result = rc;
+		else
+			*result = page_to_nid(newpage);
+	}
+	return rc;
+}
+
+/*
  * migrate_pages
  *
- * Two lists are passed to this function. The first list
- * contains the pages isolated from the LRU to be migrated.
- * The second list contains new pages that the pages isolated
- * can be moved to.
+ * The function takes one list of pages to migrate and a function
+ * that determines from the page to be migrated and the private data
+ * the target of the move and allocates the page.
  *
  * The function returns after 10 attempts or if no pages
  * are movable anymore because to has become empty
- * or no retryable pages exist anymore.
+ * or no retryable pages exist anymore. All pages will be
+ * returned to the LRU or freed.
  *
- * Return: Number of pages not migrated when "to" ran empty.
+ * Return: Number of pages not migrated or error code.
  */
-int migrate_pages(struct list_head *from, struct list_head *to,
-		  struct list_head *moved, struct list_head *failed)
+int migrate_pages(struct list_head *from,
+		new_page_t get_new_page, unsigned long private)
 {
-	int retry;
+	int retry = 1;
 	int nr_failed = 0;
 	int pass = 0;
 	struct page *page;
@@ -561,193 +759,319 @@ int migrate_pages(struct list_head *from, struct list_head *to,
 	if (!swapwrite)
 		current->flags |= PF_SWAPWRITE;
 
-redo:
-	retry = 0;
+	for(pass = 0; pass < 10 && retry; pass++) {
+		retry = 0;
 
-	list_for_each_entry_safe(page, page2, from, lru) {
-		struct page *newpage = NULL;
-		struct address_space *mapping;
+		list_for_each_entry_safe(page, page2, from, lru) {
+			cond_resched();
 
-		cond_resched();
+			rc = unmap_and_move(get_new_page, private,
+						page, pass > 2);
 
-		rc = 0;
-		if (page_count(page) == 1)
-			/* page was freed from under us. So we are done. */
-			goto next;
+			switch(rc) {
+			case -ENOMEM:
+				goto out;
+			case -EAGAIN:
+				retry++;
+				break;
+			case 0:
+				break;
+			default:
+				/* Permanent failure */
+				nr_failed++;
+				break;
+			}
+		}
+	}
+	rc = 0;
+out:
+	if (!swapwrite)
+		current->flags &= ~PF_SWAPWRITE;
 
-		if (to && list_empty(to))
-			break;
+	putback_lru_pages(from);
 
-		/*
-		 * Skip locked pages during the first two passes to give the
-		 * functions holding the lock time to release the page. Later we
-		 * use lock_page() to have a higher chance of acquiring the
-		 * lock.
-		 */
-		rc = -EAGAIN;
-		if (pass > 2)
-			lock_page(page);
-		else
-			if (TestSetPageLocked(page))
-				goto next;
+	if (rc)
+		return rc;
 
-		/*
-		 * Only wait on writeback if we have already done a pass where
-		 * we we may have triggered writeouts for lots of pages.
-		 */
-		if (pass > 0)
-			wait_on_page_writeback(page);
-		else
-			if (PageWriteback(page))
-				goto unlock_page;
+	return nr_failed + retry;
+}
 
-		/*
-		 * Establish migration ptes or remove ptes
-		 */
-		rc = -EPERM;
-		if (try_to_unmap(page, 1) == SWAP_FAIL)
-			/* A vma has VM_LOCKED set -> permanent failure */
-			goto unlock_page;
+#ifdef CONFIG_NUMA
+/*
+ * Move a list of individual pages
+ */
+struct page_to_node {
+	unsigned long addr;
+	struct page *page;
+	int node;
+	int status;
+};
+
+static struct page *new_page_node(struct page *p, unsigned long private,
+		int **result)
+{
+	struct page_to_node *pm = (struct page_to_node *)private;
+
+	while (pm->node != MAX_NUMNODES && pm->page != p)
+		pm++;
 
-		rc = -EAGAIN;
-		if (page_mapped(page))
-			goto unlock_page;
+	if (pm->node == MAX_NUMNODES)
+		return NULL;
 
-		newpage = lru_to_page(to);
-		lock_page(newpage);
-		/* Prepare mapping for the new page.*/
-		newpage->index = page->index;
-		newpage->mapping = page->mapping;
+	*result = &pm->status;
+
+	return alloc_pages_node(pm->node,
+				GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0);
+}
+
+/*
+ * Move a set of pages as indicated in the pm array. The addr
+ * field must be set to the virtual address of the page to be moved
+ * and the node number must contain a valid target node.
+ */
+static int do_move_pages(struct mm_struct *mm, struct page_to_node *pm,
+				int migrate_all)
+{
+	int err;
+	struct page_to_node *pp;
+	LIST_HEAD(pagelist);
+
+	down_read(&mm->mmap_sem);
+
+	/*
+	 * Build a list of pages to migrate
+	 */
+	migrate_prep();
+	for (pp = pm; pp->node != MAX_NUMNODES; pp++) {
+		struct vm_area_struct *vma;
+		struct page *page;
 
 		/*
-		 * Pages are properly locked and writeback is complete.
-		 * Try to migrate the page.
+		 * A valid page pointer that will not match any of the
+		 * pages that will be moved.
 		 */
-		mapping = page_mapping(page);
-		if (!mapping)
-			rc = migrate_page(mapping, newpage, page);
+		pp->page = ZERO_PAGE(0);
 
-		else if (mapping->a_ops->migratepage)
-			/*
-			 * Most pages have a mapping and most filesystems
-			 * should provide a migration function. Anonymous
-			 * pages are part of swap space which also has its
-			 * own migration function. This is the most common
-			 * path for page migration.
-			 */
-			rc = mapping->a_ops->migratepage(mapping,
-							newpage, page);
-		else
-			rc = fallback_migrate_page(mapping, newpage, page);
+		err = -EFAULT;
+		vma = find_vma(mm, pp->addr);
+		if (!vma || !vma_migratable(vma))
+			goto set_status;
 
-		if (!rc)
-			remove_migration_ptes(page, newpage);
+		page = follow_page(vma, pp->addr, FOLL_GET);
+		err = -ENOENT;
+		if (!page)
+			goto set_status;
 
-		unlock_page(newpage);
+		if (PageReserved(page))		/* Check for zero page */
+			goto put_and_set;
 
-unlock_page:
-		if (rc)
-			remove_migration_ptes(page, page);
+		pp->page = page;
+		err = page_to_nid(page);
 
-		unlock_page(page);
+		if (err == pp->node)
+			/*
+			 * Node already in the right place
+			 */
+			goto put_and_set;
 
-next:
-		if (rc) {
-			if (newpage)
-				newpage->mapping = NULL;
+		err = -EACCES;
+		if (page_mapcount(page) > 1 &&
+				!migrate_all)
+			goto put_and_set;
 
-			if (rc == -EAGAIN)
-				retry++;
-			else {
-				/* Permanent failure */
-				list_move(&page->lru, failed);
-				nr_failed++;
-			}
-		} else {
-			if (newpage) {
-				/* Successful migration. Return page to LRU */
-				move_to_lru(newpage);
-			}
-			list_move(&page->lru, moved);
-		}
+		err = isolate_lru_page(page, &pagelist);
+put_and_set:
+		/*
+		 * Either remove the duplicate refcount from
+		 * isolate_lru_page() or drop the page ref if it was
+		 * not isolated.
+		 */
+		put_page(page);
+set_status:
+		pp->status = err;
 	}
-	if (retry && pass++ < 10)
-		goto redo;
 
-	if (!swapwrite)
-		current->flags &= ~PF_SWAPWRITE;
+	if (!list_empty(&pagelist))
+		err = migrate_pages(&pagelist, new_page_node,
+				(unsigned long)pm);
+	else
+		err = -ENOENT;
 
-	return nr_failed + retry;
+	up_read(&mm->mmap_sem);
+	return err;
 }
 
 /*
- * Migrate the list 'pagelist' of pages to a certain destination.
- *
- * Specify destination with either non-NULL vma or dest_node >= 0
- * Return the number of pages not migrated or error code
+ * Determine the nodes of a list of pages. The addr in the pm array
+ * must have been set to the virtual address of which we want to determine
+ * the node number.
+ */
+static int do_pages_stat(struct mm_struct *mm, struct page_to_node *pm)
+{
+	down_read(&mm->mmap_sem);
+
+	for ( ; pm->node != MAX_NUMNODES; pm++) {
+		struct vm_area_struct *vma;
+		struct page *page;
+		int err;
+
+		err = -EFAULT;
+		vma = find_vma(mm, pm->addr);
+		if (!vma)
+			goto set_status;
+
+		page = follow_page(vma, pm->addr, 0);
+		err = -ENOENT;
+		/* Use PageReserved to check for zero page */
+		if (!page || PageReserved(page))
+			goto set_status;
+
+		err = page_to_nid(page);
+set_status:
+		pm->status = err;
+	}
+
+	up_read(&mm->mmap_sem);
+	return 0;
+}
+
+/*
+ * Move a list of pages in the address space of the currently executing
+ * process.
  */
-int migrate_pages_to(struct list_head *pagelist,
-			struct vm_area_struct *vma, int dest)
+asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages,
+			const void __user * __user *pages,
+			const int __user *nodes,
+			int __user *status, int flags)
 {
-	LIST_HEAD(newlist);
-	LIST_HEAD(moved);
-	LIST_HEAD(failed);
 	int err = 0;
-	unsigned long offset = 0;
-	int nr_pages;
-	struct page *page;
-	struct list_head *p;
+	int i;
+	struct task_struct *task;
+	nodemask_t task_nodes;
+	struct mm_struct *mm;
+	struct page_to_node *pm = NULL;
+
+	/* Check flags */
+	if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL))
+		return -EINVAL;
 
-redo:
-	nr_pages = 0;
-	list_for_each(p, pagelist) {
-		if (vma) {
-			/*
-			 * The address passed to alloc_page_vma is used to
-			 * generate the proper interleave behavior. We fake
-			 * the address here by an increasing offset in order
-			 * to get the proper distribution of pages.
-			 *
-			 * No decision has been made as to which page
-			 * a certain old page is moved to so we cannot
-			 * specify the correct address.
-			 */
-			page = alloc_page_vma(GFP_HIGHUSER, vma,
-					offset + vma->vm_start);
-			offset += PAGE_SIZE;
-		}
-		else
-			page = alloc_pages_node(dest, GFP_HIGHUSER, 0);
+	if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE))
+		return -EPERM;
+
+	/* Find the mm_struct */
+	read_lock(&tasklist_lock);
+	task = pid ? find_task_by_vpid(pid) : current;
+	if (!task) {
+		read_unlock(&tasklist_lock);
+		return -ESRCH;
+	}
+	mm = get_task_mm(task);
+	read_unlock(&tasklist_lock);
+
+	if (!mm)
+		return -EINVAL;
+
+	/*
+	 * Check if this process has the right to modify the specified
+	 * process. The right exists if the process has administrative
+	 * capabilities, superuser privileges or the same
+	 * userid as the target process.
+	 */
+	if ((current->euid != task->suid) && (current->euid != task->uid) &&
+	    (current->uid != task->suid) && (current->uid != task->uid) &&
+	    !capable(CAP_SYS_NICE)) {
+		err = -EPERM;
+		goto out2;
+	}
+
+ 	err = security_task_movememory(task);
+ 	if (err)
+ 		goto out2;
+
+
+	task_nodes = cpuset_mems_allowed(task);
+
+	/* Limit nr_pages so that the multiplication may not overflow */
+	if (nr_pages >= ULONG_MAX / sizeof(struct page_to_node) - 1) {
+		err = -E2BIG;
+		goto out2;
+	}
+
+	pm = vmalloc((nr_pages + 1) * sizeof(struct page_to_node));
+	if (!pm) {
+		err = -ENOMEM;
+		goto out2;
+	}
+
+	/*
+	 * Get parameters from user space and initialize the pm
+	 * array. Return various errors if the user did something wrong.
+	 */
+	for (i = 0; i < nr_pages; i++) {
+		const void __user *p;
 
-		if (!page) {
-			err = -ENOMEM;
+		err = -EFAULT;
+		if (get_user(p, pages + i))
 			goto out;
-		}
-		list_add_tail(&page->lru, &newlist);
-		nr_pages++;
-		if (nr_pages > MIGRATE_CHUNK_SIZE)
-			break;
+
+		pm[i].addr = (unsigned long)p;
+		if (nodes) {
+			int node;
+
+			if (get_user(node, nodes + i))
+				goto out;
+
+			err = -ENODEV;
+			if (!node_state(node, N_HIGH_MEMORY))
+				goto out;
+
+			err = -EACCES;
+			if (!node_isset(node, task_nodes))
+				goto out;
+
+			pm[i].node = node;
+		} else
+			pm[i].node = 0;	/* anything to not match MAX_NUMNODES */
 	}
-	err = migrate_pages(pagelist, &newlist, &moved, &failed);
+	/* End marker */
+	pm[nr_pages].node = MAX_NUMNODES;
 
-	putback_lru_pages(&moved);	/* Call release pages instead ?? */
+	if (nodes)
+		err = do_move_pages(mm, pm, flags & MPOL_MF_MOVE_ALL);
+	else
+		err = do_pages_stat(mm, pm);
+
+	if (err >= 0)
+		/* Return status information */
+		for (i = 0; i < nr_pages; i++)
+			if (put_user(pm[i].status, status + i))
+				err = -EFAULT;
 
-	if (err >= 0 && list_empty(&newlist) && !list_empty(pagelist))
-		goto redo;
 out:
-	/* Return leftover allocated pages */
-	while (!list_empty(&newlist)) {
-		page = list_entry(newlist.next, struct page, lru);
-		list_del(&page->lru);
-		__free_page(page);
-	}
-	list_splice(&failed, pagelist);
-	if (err < 0)
-		return err;
-
-	/* Calculate number of leftover pages */
-	nr_pages = 0;
-	list_for_each(p, pagelist)
-		nr_pages++;
-	return nr_pages;
+	vfree(pm);
+out2:
+	mmput(mm);
+	return err;
+}
+#endif
+
+/*
+ * Call migration functions in the vma_ops that may prepare
+ * memory in a vm for migration. migration functions may perform
+ * the migration for vmas that do not have an underlying page struct.
+ */
+int migrate_vmas(struct mm_struct *mm, const nodemask_t *to,
+	const nodemask_t *from, unsigned long flags)
+{
+ 	struct vm_area_struct *vma;
+ 	int err = 0;
+
+ 	for(vma = mm->mmap; vma->vm_next && !err; vma = vma->vm_next) {
+ 		if (vma->vm_ops && vma->vm_ops->migrate) {
+ 			err = vma->vm_ops->migrate(vma, to, from, flags);
+ 			if (err)
+ 				break;
+ 		}
+ 	}
+ 	return err;
 }