1 files changed, 69 insertions, 13 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 5bc0a96beb51..f969da5dd8a2 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1275,33 +1275,42 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,
 		const unsigned long __user *, new_nodes)
 {
 	const struct cred *cred = current_cred(), *tcred;
-	struct mm_struct *mm;
+	struct mm_struct *mm = NULL;
 	struct task_struct *task;
-	nodemask_t old;
-	nodemask_t new;
 	nodemask_t task_nodes;
 	int err;
+	nodemask_t *old;
+	nodemask_t *new;
+	NODEMASK_SCRATCH(scratch);
+
+	if (!scratch)
+		return -ENOMEM;
+
+	old = &scratch->mask1;
+	new = &scratch->mask2;
 
-	err = get_nodes(&old, old_nodes, maxnode);
+	err = get_nodes(old, old_nodes, maxnode);
 	if (err)
-		return err;
+		goto out;
 
-	err = get_nodes(&new, new_nodes, maxnode);
+	err = get_nodes(new, new_nodes, maxnode);
 	if (err)
-		return err;
+		goto out;
 
 	/* Find the mm_struct */
 	read_lock(&tasklist_lock);
 	task = pid ? find_task_by_vpid(pid) : current;
 	if (!task) {
 		read_unlock(&tasklist_lock);
-		return -ESRCH;
+		err = -ESRCH;
+		goto out;
 	}
 	mm = get_task_mm(task);
 	read_unlock(&tasklist_lock);
 
+	err = -EINVAL;
 	if (!mm)
-		return -EINVAL;
+		goto out;
 
 	/*
 	 * Check if this process has the right to modify the specified
@@ -1322,12 +1331,12 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,
 
 	task_nodes = cpuset_mems_allowed(task);
 	/* Is the user allowed to access the target nodes? */
-	if (!nodes_subset(new, task_nodes) && !capable(CAP_SYS_NICE)) {
+	if (!nodes_subset(*new, task_nodes) && !capable(CAP_SYS_NICE)) {
 		err = -EPERM;
 		goto out;
 	}
 
-	if (!nodes_subset(new, node_states[N_HIGH_MEMORY])) {
+	if (!nodes_subset(*new, node_states[N_HIGH_MEMORY])) {
 		err = -EINVAL;
 		goto out;
 	}
@@ -1336,10 +1345,13 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,
 	if (err)
 		goto out;
 
-	err = do_migrate_pages(mm, &old, &new,
+	err = do_migrate_pages(mm, old, new,
 		capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE);
 out:
-	mmput(mm);
+	if (mm)
+		mmput(mm);
+	NODEMASK_SCRATCH_FREE(scratch);
+
 	return err;
 }
 
@@ -1712,6 +1724,50 @@ bool init_nodemask_of_mempolicy(nodemask_t *mask)
 }
 #endif
 
+/*
+ * mempolicy_nodemask_intersects
+ *
+ * If tsk's mempolicy is "default" [NULL], return 'true' to indicate default
+ * policy.  Otherwise, check for intersection between mask and the policy
+ * nodemask for 'bind' or 'interleave' policy.  For 'perferred' or 'local'
+ * policy, always return true since it may allocate elsewhere on fallback.
+ *
+ * Takes task_lock(tsk) to prevent freeing of its mempolicy.
+ */
+bool mempolicy_nodemask_intersects(struct task_struct *tsk,
+					const nodemask_t *mask)
+{
+	struct mempolicy *mempolicy;
+	bool ret = true;
+
+	if (!mask)
+		return ret;
+	task_lock(tsk);
+	mempolicy = tsk->mempolicy;
+	if (!mempolicy)
+		goto out;
+
+	switch (mempolicy->mode) {
+	case MPOL_PREFERRED:
+		/*
+		 * MPOL_PREFERRED and MPOL_F_LOCAL are only preferred nodes to
+		 * allocate from, they may fallback to other nodes when oom.
+		 * Thus, it's possible for tsk to have allocated memory from
+		 * nodes in mask.
+		 */
+		break;
+	case MPOL_BIND:
+	case MPOL_INTERLEAVE:
+		ret = nodes_intersects(mempolicy->v.nodes, *mask);
+		break;
+	default:
+		BUG();
+	}
+out:
+	task_unlock(tsk);
+	return ret;
+}
+
 /* Allocate a page in interleaved policy.
    Own path because it needs to do special accounting. */
 static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,