1 files changed, 55 insertions, 39 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index cfb6c8678754..1d771e4200d2 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -390,7 +390,7 @@ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask,
 {
 	if (!pol)
 		return;
-	if (!mpol_store_user_nodemask(pol) && step == 0 &&
+	if (!mpol_store_user_nodemask(pol) && step == MPOL_REBIND_ONCE &&
 	    nodes_equal(pol->w.cpuset_mems_allowed, *newmask))
 		return;
 
@@ -607,27 +607,6 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 	return first;
 }
 
-/* Apply policy to a single VMA */
-static int policy_vma(struct vm_area_struct *vma, struct mempolicy *new)
-{
-	int err = 0;
-	struct mempolicy *old = vma->vm_policy;
-
-	pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n",
-		 vma->vm_start, vma->vm_end, vma->vm_pgoff,
-		 vma->vm_ops, vma->vm_file,
-		 vma->vm_ops ? vma->vm_ops->set_policy : NULL);
-
-	if (vma->vm_ops && vma->vm_ops->set_policy)
-		err = vma->vm_ops->set_policy(vma, new);
-	if (!err) {
-		mpol_get(new);
-		vma->vm_policy = new;
-		mpol_put(old);
-	}
-	return err;
-}
-
 /* Step 2: apply policy to a range and do splits. */
 static int mbind_range(struct mm_struct *mm, unsigned long start,
 		       unsigned long end, struct mempolicy *new_pol)
@@ -676,9 +655,23 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
 			if (err)
 				goto out;
 		}
-		err = policy_vma(vma, new_pol);
-		if (err)
-			goto out;
+
+		/*
+		 * Apply policy to a single VMA. The reference counting of
+		 * policy for vma_policy linkages has already been handled by
+		 * vma_merge and split_vma as necessary. If this is a shared
+		 * policy then ->set_policy will increment the reference count
+		 * for an sp node.
+		 */
+		pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n",
+			vma->vm_start, vma->vm_end, vma->vm_pgoff,
+			vma->vm_ops, vma->vm_file,
+			vma->vm_ops ? vma->vm_ops->set_policy : NULL);
+		if (vma->vm_ops && vma->vm_ops->set_policy) {
+			err = vma->vm_ops->set_policy(vma, new_pol);
+			if (err)
+				goto out;
+		}
 	}
 
  out:
@@ -957,8 +950,8 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
  *
  * Returns the number of page that could not be moved.
  */
-int do_migrate_pages(struct mm_struct *mm,
-	const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
+int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
+		     const nodemask_t *to, int flags)
 {
 	int busy = 0;
 	int err;
@@ -970,7 +963,7 @@ int do_migrate_pages(struct mm_struct *mm,
 
 	down_read(&mm->mmap_sem);
 
-	err = migrate_vmas(mm, from_nodes, to_nodes, flags);
+	err = migrate_vmas(mm, from, to, flags);
 	if (err)
 		goto out;
 
@@ -1005,14 +998,34 @@ int do_migrate_pages(struct mm_struct *mm,
 	 * moved to an empty node, then there is nothing left worth migrating.
 	 */
 
-	tmp = *from_nodes;
+	tmp = *from;
 	while (!nodes_empty(tmp)) {
 		int s,d;
 		int source = -1;
 		int dest = 0;
 
 		for_each_node_mask(s, tmp) {
-			d = node_remap(s, *from_nodes, *to_nodes);
+
+			/*
+			 * do_migrate_pages() tries to maintain the relative
+			 * node relationship of the pages established between
+			 * threads and memory areas.
+                         *
+			 * However if the number of source nodes is not equal to
+			 * the number of destination nodes we can not preserve
+			 * this node relative relationship.  In that case, skip
+			 * copying memory from a node that is in the destination
+			 * mask.
+			 *
+			 * Example: [2,3,4] -> [3,4,5] moves everything.
+			 *          [0-7] - > [3,4,5] moves only 0,1,2,6,7.
+			 */
+
+			if ((nodes_weight(*from) != nodes_weight(*to)) &&
+						(node_isset(s, *to)))
+				continue;
+
+			d = node_remap(s, *from, *to);
 			if (s == d)
 				continue;
 
@@ -1072,8 +1085,8 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist,
 {
 }
 
-int do_migrate_pages(struct mm_struct *mm,
-	const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
+int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
+		     const nodemask_t *to, int flags)
 {
 	return -ENOSYS;
 }
@@ -1164,7 +1177,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 		if (!list_empty(&pagelist)) {
 			nr_failed = migrate_pages(&pagelist, new_vma_page,
 						(unsigned long)vma,
-						false, true);
+						false, MIGRATE_SYNC);
 			if (nr_failed)
 				putback_lru_pages(&pagelist);
 		}
@@ -1334,8 +1347,8 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,
 	 * userid as the target process.
 	 */
 	tcred = __task_cred(task);
-	if (cred->euid != tcred->suid && cred->euid != tcred->uid &&
-	    cred->uid  != tcred->suid && cred->uid  != tcred->uid &&
+	if (!uid_eq(cred->euid, tcred->suid) && !uid_eq(cred->euid, tcred->uid) &&
+	    !uid_eq(cred->uid,  tcred->suid) && !uid_eq(cred->uid,  tcred->uid) &&
 	    !capable(CAP_SYS_NICE)) {
 		rcu_read_unlock();
 		err = -EPERM;
@@ -1361,11 +1374,14 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,
 
 	mm = get_task_mm(task);
 	put_task_struct(task);
-	if (mm)
-		err = do_migrate_pages(mm, old, new,
-			capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE);
-	else
+
+	if (!mm) {
 		err = -EINVAL;
+		goto out;
+	}
+
+	err = do_migrate_pages(mm, old, new,
+		capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE);
 
 	mmput(mm);
 out: