devcgroup: relax white-list protection down to RCU

Currently this list is protected with a simple spinlock, even for reading from one. This is OK, but can be better.

Actually I want it to be better very much, since after replacing the OpenVZ device permissions engine with the cgroup-based one I noticed, that we set 12 default device permissions for each newly created container (for /dev/null, full, terminals, ect devices), and people sometimes have up to 20 perms more, so traversing the ~30-40 elements list under a spinlock doesn't seem very good.

Here's the liter RCU protection for white-list.

Signed-off-by Pavel Emelyanov <[email protected]>

---

security/device_cgroup.c +10 -1

index 4ea5836..9d940c3 100644
@@ -41,6 +41,7 @@ struct dev_whitelist_item {
 	short type;
 	short access;
 	struct list_head list;
+	struct rcu_head rcu;
 };
 
 struct dev_cgroup {

@@ -110,11 +111,19 @@ static int dev_whitelist_add(struct dev_cgroup *dev_cgroup,
 
 	memcpy(whcopy, wh, sizeof(*whcopy));
 	spin_lock(&dev_cgroup->lock);
-	list_add_tail(&whcopy->list, &dev_cgroup->whitelist);
+	list_add_tail_rcu(&whcopy->list, &dev_cgroup->whitelist);
 	spin_unlock(&dev_cgroup->lock);
 	return 0;
 }
 
+static void whitelist_item_free(struct rcu_head *rcu)
+{
+	struct dev_whitelist_item *item;
+
+	item = container_of(rcu, struct dev_whitelist_item, rcu);
+	kfree(item);
+}
+
 /*
  * called under cgroup_lock()
  * since the list is visible to other tasks, we need the spinlock also

security/device_cgroup.c +10 -10

 		}
 	}
 	spin_unlock(&dev_cgroup->lock);

@@ -246,15 +255,15 @@ static int devcgroup_seq_read(struct cgroup *cgroup, struct cftype *cft,
 	struct dev_whitelist_item *wh;
 	char maj[MAJMINLEN], min[MAJMINLEN], acc[ACCLEN];
 
-	spin_lock(&devcgroup->lock);
-	list_for_each_entry(wh, &devcgroup->whitelist, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(wh, &devcgroup->whitelist, list) {
 		set_access(acc, wh->access);
 		set_majmin(maj, wh->major);
 		set_majmin(min, wh->minor);
 		seq_printf(m, "%c %s:%s %s\n", type_to_char(wh->type),
 			   maj, min, acc);
 	}
-	spin_unlock(&devcgroup->lock);
+	rcu_read_unlock();
 
 	return 0;
 }

@@ -516,8 +525,8 @@ int devcgroup_inode_permission(struct inode *inode, int mask)
 	if (!dev_cgroup)
 		return 0;
 
-	spin_lock(&dev_cgroup->lock);
-	list_for_each_entry(wh, &dev_cgroup->whitelist, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(wh, &dev_cgroup->whitelist, list) {
 		if (wh->type & DEV_ALL)
 			goto acc_check;
 		if ((wh->type & DEV_BLOCK) && !S_ISBLK(inode->i_mode))

@@ -533,10 +542,10 @@ acc_check:
 			continue;
 		if ((mask & MAY_READ) && !(wh->access & ACC_READ))
 			continue;
-		spin_unlock(&dev_cgroup->lock);
+		rcu_read_unlock();
 		return 0;
 	}
-	spin_unlock(&dev_cgroup->lock);
+	rcu_read_unlock();
 
 	return -EPERM;
 }

@@ -552,7 +561,7 @@ int devcgroup_inode_mknod(int mode, dev_t dev)
 	if (!dev_cgroup)
 		return 0;
 
-	spin_lock(&dev_cgroup->lock);
+	rcu_read_lock();
 	list_for_each_entry(wh, &dev_cgroup->whitelist, list) {
 		if (wh->type & DEV_ALL)
 			goto acc_check;

@@ -567,9 +576,9 @@ int devcgroup_inode_mknod(int mode, dev_t dev)
 acc_check:
 		if (!(wh->access & ACC_MKNOD))
 			continue;
-		spin_unlock(&dev_cgroup->lock);
+		rcu_read_unlock();
 		return 0;
 	}
-	spin_unlock(&dev_cgroup->lock);
+	rcu_read_unlock();
 	return -EPERM;
 }