summaryrefslogtreecommitdiff
path: root/kernel/pid.c
diff options
context:
space:
mode:
authorSargun Dhillon <sargun@sargun.me>2020-01-07 09:59:25 -0800
committerChristian Brauner <christian.brauner@ubuntu.com>2020-01-13 21:49:36 +0100
commit8649c322f75c96e7ced2fec201e123b2b073bf09 (patch)
tree791d90016044b13207400609c491f71654fc5f34 /kernel/pid.c
parent5e876fb43dbf24c941a323139752bcb2f0a80da0 (diff)
pid: Implement pidfd_getfd syscall
This syscall allows for the retrieval of file descriptors from other processes, based on their pidfd. This is possible using ptrace, and injection of parasitic code to inject code which leverages SCM_RIGHTS to move file descriptors between a tracee and a tracer. Unfortunately, ptrace comes with a high cost of requiring the process to be stopped, and breaks debuggers. This does not require stopping the process under manipulation. One reason to use this is to allow sandboxers to take actions on file descriptors on the behalf of another process. For example, this can be combined with seccomp-bpf's user notification to do on-demand fd extraction and take privileged actions. One such privileged action is binding a socket to a privileged port. /* prototype */ /* flags is currently reserved and should be set to 0 */ int sys_pidfd_getfd(int pidfd, int fd, unsigned int flags); /* testing */ Ran self-test suite on x86_64 Signed-off-by: Sargun Dhillon <sargun@sargun.me> Acked-by: Christian Brauner <christian.brauner@ubuntu.com> Reviewed-by: Arnd Bergmann <arnd@arndb.de> Link: https://lore.kernel.org/r/20200107175927.4558-3-sargun@sargun.me Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Diffstat (limited to 'kernel/pid.c')
-rw-r--r--kernel/pid.c90
1 files changed, 90 insertions, 0 deletions
diff --git a/kernel/pid.c b/kernel/pid.c
index 2278e249141d..0f4ecb57214c 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -578,3 +578,93 @@ 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->cred_guard_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->cred_guard_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;
+}