1 files changed, 101 insertions, 7 deletions

diff --git a/kernel/pid.c b/kernel/pid.c
index 2278e249141d..c835b844aca7 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -144,9 +144,6 @@ void free_pid(struct pid *pid)
 			/* Handle a fork failure of the first process */
 			WARN_ON(ns->child_reaper);
 			ns->pid_allocated = 0;
-			/* fall through */
-		case 0:
-			schedule_work(&ns->proc_work);
 			break;
 		}
 
@@ -247,17 +244,24 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 		tmp = tmp->parent;
 	}
 
-	if (unlikely(is_child_reaper(pid))) {
-		if (pid_ns_prepare_proc(ns))
-			goto out_free;
-	}
+	/*
+	 * ENOMEM is not the most obvious choice especially for the case
+	 * where the child subreaper has already exited and the pid
+	 * namespace denies the creation of any new processes. But ENOMEM
+	 * is what we have exposed to userspace for a long time and it is
+	 * documented behavior for pid namespaces. So we can't easily
+	 * change it even if there were an error code better suited.
+	 */
+	retval = -ENOMEM;
 
 	get_pid_ns(ns);
 	refcount_set(&pid->count, 1);
+	spin_lock_init(&pid->lock);
 	for (type = 0; type < PIDTYPE_MAX; ++type)
 		INIT_HLIST_HEAD(&pid->tasks[type]);
 
 	init_waitqueue_head(&pid->wait_pidfd);
+	INIT_HLIST_HEAD(&pid->inodes);
 
 	upid = pid->numbers + ns->level;
 	spin_lock_irq(&pidmap_lock);
@@ -578,3 +582,93 @@ void __init pid_idr_init(void)
 	init_pid_ns.pid_cachep = KMEM_CACHE(pid,
 			SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT);
 }
+
+static struct file *__pidfd_fget(struct task_struct *task, int fd)
+{
+	struct file *file;
+	int ret;
+
+	ret = mutex_lock_killable(&task->signal->exec_update_mutex);
+	if (ret)
+		return ERR_PTR(ret);
+
+	if (ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS))
+		file = fget_task(task, fd);
+	else
+		file = ERR_PTR(-EPERM);
+
+	mutex_unlock(&task->signal->exec_update_mutex);
+
+	return file ?: ERR_PTR(-EBADF);
+}
+
+static int pidfd_getfd(struct pid *pid, int fd)
+{
+	struct task_struct *task;
+	struct file *file;
+	int ret;
+
+	task = get_pid_task(pid, PIDTYPE_PID);
+	if (!task)
+		return -ESRCH;
+
+	file = __pidfd_fget(task, fd);
+	put_task_struct(task);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	ret = security_file_receive(file);
+	if (ret) {
+		fput(file);
+		return ret;
+	}
+
+	ret = get_unused_fd_flags(O_CLOEXEC);
+	if (ret < 0)
+		fput(file);
+	else
+		fd_install(ret, file);
+
+	return ret;
+}
+
+/**
+ * sys_pidfd_getfd() - Get a file descriptor from another process
+ *
+ * @pidfd:	the pidfd file descriptor of the process
+ * @fd:		the file descriptor number to get
+ * @flags:	flags on how to get the fd (reserved)
+ *
+ * This syscall gets a copy of a file descriptor from another process
+ * based on the pidfd, and file descriptor number. It requires that
+ * the calling process has the ability to ptrace the process represented
+ * by the pidfd. The process which is having its file descriptor copied
+ * is otherwise unaffected.
+ *
+ * Return: On success, a cloexec file descriptor is returned.
+ *         On error, a negative errno number will be returned.
+ */
+SYSCALL_DEFINE3(pidfd_getfd, int, pidfd, int, fd,
+		unsigned int, flags)
+{
+	struct pid *pid;
+	struct fd f;
+	int ret;
+
+	/* flags is currently unused - make sure it's unset */
+	if (flags)
+		return -EINVAL;
+
+	f = fdget(pidfd);
+	if (!f.file)
+		return -EBADF;
+
+	pid = pidfd_pid(f.file);
+	if (IS_ERR(pid))
+		ret = PTR_ERR(pid);
+	else
+		ret = pidfd_getfd(pid, fd);
+
+	fdput(f);
+	return ret;
+}