Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull namespace fixes from Eric Biederman:
 "This tree includes two bug fixes for problems Oleg spotted on his
  review of the recent pid namespace work.  A small fix to not enable
  bottom halves with irqs disabled, and a trivial build fix for f2fs
  with user namespaces enabled."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  f2fs: Don't assign e_id in f2fs_acl_from_disk
  proc: Allow proc_free_inum to be called from any context
  pidns: Stop pid allocation when init dies
  pidns: Outlaw thread creation after unshare(CLONE_NEWPID)

fs/f2fs/acl.c

@@ -82,7 +82,6 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size)
 		case ACL_GROUP_OBJ:
 		case ACL_MASK:
 		case ACL_OTHER:
-			acl->a_entries[i].e_id = ACL_UNDEFINED_ID;
 			entry = (struct f2fs_acl_entry *)((char *)entry +
 					sizeof(struct f2fs_acl_entry_short));
 			break;

fs/proc/generic.c

@@ -352,18 +352,18 @@ retry:
 	if (!ida_pre_get(&proc_inum_ida, GFP_KERNEL))
 		return -ENOMEM;
 
-	spin_lock_bh(&proc_inum_lock);
+	spin_lock_irq(&proc_inum_lock);
 	error = ida_get_new(&proc_inum_ida, &i);
-	spin_unlock_bh(&proc_inum_lock);
+	spin_unlock_irq(&proc_inum_lock);
 	if (error == -EAGAIN)
 		goto retry;
 	else if (error)
 		return error;
 
 	if (i > UINT_MAX - PROC_DYNAMIC_FIRST) {
-		spin_lock_bh(&proc_inum_lock);
+		spin_lock_irq(&proc_inum_lock);
 		ida_remove(&proc_inum_ida, i);
-		spin_unlock_bh(&proc_inum_lock);
+		spin_unlock_irq(&proc_inum_lock);
 		return -ENOSPC;
 	}
 	*inum = PROC_DYNAMIC_FIRST + i;
@@ -372,9 +372,10 @@ retry:
 
 void proc_free_inum(unsigned int inum)
 {
-	spin_lock_bh(&proc_inum_lock);
+	unsigned long flags;
+	spin_lock_irqsave(&proc_inum_lock, flags);
 	ida_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
-	spin_unlock_bh(&proc_inum_lock);
+	spin_unlock_irqrestore(&proc_inum_lock, flags);
 }
 
 static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd)

include/linux/pid.h

@@ -121,6 +121,7 @@ int next_pidmap(struct pid_namespace *pid_ns, unsigned int last);
 
 extern struct pid *alloc_pid(struct pid_namespace *ns);
 extern void free_pid(struct pid *pid);
+extern void disable_pid_allocation(struct pid_namespace *ns);
 
 /*
  * ns_of_pid() returns the pid namespace in which the specified pid was

include/linux/pid_namespace.h

@@ -21,7 +21,7 @@ struct pid_namespace {
 	struct kref kref;
 	struct pidmap pidmap[PIDMAP_ENTRIES];
 	int last_pid;
-	int nr_hashed;
+	unsigned int nr_hashed;
 	struct task_struct *child_reaper;
 	struct kmem_cache *pid_cachep;
 	unsigned int level;
@@ -42,6 +42,8 @@ struct pid_namespace {
 
 extern struct pid_namespace init_pid_ns;
 
+#define PIDNS_HASH_ADDING (1U << 31)
+
 #ifdef CONFIG_PID_NS
 static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns)
 {

kernel/fork.c

@@ -1166,6 +1166,14 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 				current->signal->flags & SIGNAL_UNKILLABLE)
 		return ERR_PTR(-EINVAL);
 
+	/*
+	 * If the new process will be in a different pid namespace
+	 * don't allow the creation of threads.
+	 */
+	if ((clone_flags & (CLONE_VM|CLONE_NEWPID)) &&
+	    (task_active_pid_ns(current) != current->nsproxy->pid_ns))
+		return ERR_PTR(-EINVAL);
+
 	retval = security_task_create(clone_flags);
 	if (retval)
 		goto fork_out;

kernel/pid.c

@@ -270,7 +270,6 @@ void free_pid(struct pid *pid)
 			wake_up_process(ns->child_reaper);
 			break;
 		case 0:
-			ns->nr_hashed = -1;
 			schedule_work(&ns->proc_work);
 			break;
 		}
@@ -319,7 +318,7 @@ struct pid *alloc_pid(struct pid_namespace *ns)
 
 	upid = pid->numbers + ns->level;
 	spin_lock_irq(&pidmap_lock);
-	if (ns->nr_hashed < 0)
+	if (!(ns->nr_hashed & PIDNS_HASH_ADDING))
 		goto out_unlock;
 	for ( ; upid >= pid->numbers; --upid) {
 		hlist_add_head_rcu(&upid->pid_chain,
@@ -342,6 +341,13 @@ out_free:
 	goto out;
 }
 
+void disable_pid_allocation(struct pid_namespace *ns)
+{
+	spin_lock_irq(&pidmap_lock);
+	ns->nr_hashed &= ~PIDNS_HASH_ADDING;
+	spin_unlock_irq(&pidmap_lock);
+}
+
 struct pid *find_pid_ns(int nr, struct pid_namespace *ns)
 {
 	struct hlist_node *elem;
@@ -573,6 +579,9 @@ void __init pidhash_init(void)
 
 void __init pidmap_init(void)
 {
+	/* Veryify no one has done anything silly */
+	BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_HASH_ADDING);
+
 	/* bump default and minimum pid_max based on number of cpus */
 	pid_max = min(pid_max_max, max_t(int, pid_max,
 				PIDS_PER_CPU_DEFAULT * num_possible_cpus()));
@@ -584,7 +593,7 @@ void __init pidmap_init(void)
 	/* Reserve PID 0. We never call free_pidmap(0) */
 	set_bit(0, init_pid_ns.pidmap[0].page);
 	atomic_dec(&init_pid_ns.pidmap[0].nr_free);
-	init_pid_ns.nr_hashed = 1;
+	init_pid_ns.nr_hashed = PIDNS_HASH_ADDING;
 
 	init_pid_ns.pid_cachep = KMEM_CACHE(pid,
 			SLAB_HWCACHE_ALIGN | SLAB_PANIC);

kernel/pid_namespace.c

@@ -115,6 +115,7 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
 	ns->level = level;
 	ns->parent = get_pid_ns(parent_pid_ns);
 	ns->user_ns = get_user_ns(user_ns);
+	ns->nr_hashed = PIDNS_HASH_ADDING;
 	INIT_WORK(&ns->proc_work, proc_cleanup_work);
 
 	set_bit(0, ns->pidmap[0].page);
@@ -181,6 +182,9 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	int rc;
 	struct task_struct *task, *me = current;
 
+	/* Don't allow any more processes into the pid namespace */
+	disable_pid_allocation(pid_ns);
+
 	/* Ignore SIGCHLD causing any terminated children to autoreap */
 	spin_lock_irq(&me->sighand->siglock);
 	me->sighand->action[SIGCHLD - 1].sa.sa_handler = SIG_IGN;