1 files changed, 27 insertions, 18 deletions

diff --git a/kernel/pid.c b/kernel/pid.c
index 3b96571d0fe6..f55189a3d07d 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -128,12 +128,11 @@ void free_pid(struct pid *pid)
 			 * is the reaper wake up the reaper.  The reaper
 			 * may be sleeping in zap_pid_ns_processes().
 			 */
-			wake_up_process(ns->child_reaper);
+			wake_up_process(READ_ONCE(ns->child_reaper));
 			break;
 		case PIDNS_ADDING:
-			/* Handle a fork failure of the first process */
-			WARN_ON(ns->child_reaper);
-			ns->pid_allocated = 0;
+			/* Only possible if the 1st fork fails */
+			WARN_ON(READ_ONCE(ns->child_reaper));
 			break;
 		}
 
@@ -215,12 +214,6 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *arg_set_tid,
 			retval = -EINVAL;
 			if (tid < 1 || tid >= pid_max[ns->level - i])
 				goto out_abort;
-			/*
-			 * Also fail if a PID != 1 is requested and
-			 * no PID 1 exists.
-			 */
-			if (tid != 1 && !tmp->child_reaper)
-				goto out_abort;
 			retval = -EPERM;
 			if (!checkpoint_restore_ns_capable(tmp->user_ns))
 				goto out_abort;
@@ -236,6 +229,10 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *arg_set_tid,
 	retried_preload = false;
 	idr_preload(GFP_KERNEL);
 	spin_lock(&pidmap_lock);
+	/* For the case when the previous attempt to create init failed */
+	if (ns->pid_allocated == PIDNS_ADDING)
+		idr_set_cursor(&ns->idr, 0);
+
 	for (tmp = ns, i = ns->level; i >= 0;) {
 		int tid = set_tid[ns->level - i];
 
@@ -296,9 +293,18 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *arg_set_tid,
 
 		pid->numbers[i].nr = nr;
 		pid->numbers[i].ns = tmp;
-		tmp = tmp->parent;
 		i--;
 		retried_preload = false;
+
+		/*
+		 * PID 1 (init) must be created first.
+		 */
+		if (!READ_ONCE(tmp->child_reaper) && nr != 1) {
+			retval = -EINVAL;
+			goto out_free;
+		}
+
+		tmp = tmp->parent;
 	}
 
 	/*
@@ -311,6 +317,11 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *arg_set_tid,
 	 *
 	 * This can't be done earlier because we need to preserve other
 	 * error conditions.
+	 *
+	 * We need this even if copy_process() does the same check. If two
+	 * or more tasks from parent namespace try to inject a child into a
+	 * dead namespace, one of free_pid() calls from the copy_process()
+	 * error path may try to wakeup the possibly freed ns->child_reaper.
 	 */
 	retval = -ENOMEM;
 	if (unlikely(!(ns->pid_allocated & PIDNS_ADDING)))
@@ -338,10 +349,6 @@ out_free:
 		idr_remove(&upid->ns->idr, upid->nr);
 	}
 
-	/* On failure to allocate the first pid, reset the state */
-	if (ns->pid_allocated == PIDNS_ADDING)
-		idr_set_cursor(&ns->idr, 0);
-
 	spin_unlock(&pidmap_lock);
 	idr_preload_end();
 
@@ -878,10 +885,12 @@ static struct file *__pidfd_fget(struct task_struct *task, int fd)
 	if (ret)
 		return ERR_PTR(ret);
 
-	if (ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS))
-		file = fget_task(task, fd);
-	else
+	if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS))
 		file = ERR_PTR(-EPERM);
+	else if (task->flags & PF_EXITING)
+		file = ERR_PTR(-ESRCH);
+	else
+		file = fget_task(task, fd);
 
 	up_read(&task->signal->exec_update_lock);