clone: add CLONE_PIDFD

This patchset makes it possible to retrieve pid file descriptors at
process creation time by introducing the new flag CLONE_PIDFD to the
clone() system call.  Linus originally suggested to implement this as a
new flag to clone() instead of making it a separate system call.  As
spotted by Linus, there is exactly one bit for clone() left.

CLONE_PIDFD creates file descriptors based on the anonymous inode
implementation in the kernel that will also be used to implement the new
mount api.  They serve as a simple opaque handle on pids.  Logically,
this makes it possible to interpret a pidfd differently, narrowing or
widening the scope of various operations (e.g. signal sending).  Thus, a
pidfd cannot just refer to a tgid, but also a tid, or in theory - given
appropriate flag arguments in relevant syscalls - a process group or
session. A pidfd does not represent a privilege.  This does not imply it
cannot ever be that way but for now this is not the case.

A pidfd comes with additional information in fdinfo if the kernel supports
procfs.  The fdinfo file contains the pid of the process in the callers
pid namespace in the same format as the procfs status file, i.e. "Pid:\t%d".

As suggested by Oleg, with CLONE_PIDFD the pidfd is returned in the
parent_tidptr argument of clone.  This has the advantage that we can
give back the associated pid and the pidfd at the same time.

To remove worries about missing metadata access this patchset comes with
a sample program that illustrates how a combination of CLONE_PIDFD, and
pidfd_send_signal() can be used to gain race-free access to process
metadata through /proc/<pid>.  The sample program can easily be
translated into a helper that would be suitable for inclusion in libc so
that users don't have to worry about writing it themselves.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Christian Brauner <christian@brauner.io>
Co-developed-by: Jann Horn <jannh@google.com>
Signed-off-by: Jann Horn <jannh@google.com>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: David Howells <dhowells@redhat.com>
Cc: "Michael Kerrisk (man-pages)" <mtk.manpages@gmail.com>
Cc: Andy Lutomirsky <luto@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>

1 files changed, 103 insertions, 4 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 9dcd18aa210b..e45f0acaf451 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -11,6 +11,7 @@
  * management can be a bitch. See 'mm/memory.c': 'copy_page_range()'
  */
 
+#include <linux/anon_inodes.h>
 #include <linux/slab.h>
 #include <linux/sched/autogroup.h>
 #include <linux/sched/mm.h>
@@ -21,6 +22,7 @@
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/sched/cputime.h>
+#include <linux/seq_file.h>
 #include <linux/rtmutex.h>
 #include <linux/init.h>
 #include <linux/unistd.h>
@@ -1662,6 +1664,58 @@ static inline void rcu_copy_process(struct task_struct *p)
 #endif /* #ifdef CONFIG_TASKS_RCU */
 }
 
+static int pidfd_release(struct inode *inode, struct file *file)
+{
+	struct pid *pid = file->private_data;
+
+	file->private_data = NULL;
+	put_pid(pid);
+	return 0;
+}
+
+#ifdef CONFIG_PROC_FS
+static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
+{
+	struct pid_namespace *ns = proc_pid_ns(file_inode(m->file));
+	struct pid *pid = f->private_data;
+
+	seq_put_decimal_ull(m, "Pid:\t", pid_nr_ns(pid, ns));
+	seq_putc(m, '\n');
+}
+#endif
+
+const struct file_operations pidfd_fops = {
+	.release = pidfd_release,
+#ifdef CONFIG_PROC_FS
+	.show_fdinfo = pidfd_show_fdinfo,
+#endif
+};
+
+/**
+ * pidfd_create() - Create a new pid file descriptor.
+ *
+ * @pid:  struct pid that the pidfd will reference
+ *
+ * This creates a new pid file descriptor with the O_CLOEXEC flag set.
+ *
+ * Note, that this function can only be called after the fd table has
+ * been unshared to avoid leaking the pidfd to the new process.
+ *
+ * Return: On success, a cloexec pidfd is returned.
+ *         On error, a negative errno number will be returned.
+ */
+static int pidfd_create(struct pid *pid)
+{
+	int fd;
+
+	fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid),
+			      O_RDWR | O_CLOEXEC);
+	if (fd < 0)
+		put_pid(pid);
+
+	return fd;
+}
+
 /*
  * This creates a new process as a copy of the old one,
  * but does not actually start it yet.
@@ -1674,13 +1728,14 @@ static __latent_entropy struct task_struct *copy_process(
 					unsigned long clone_flags,
 					unsigned long stack_start,
 					unsigned long stack_size,
+					int __user *parent_tidptr,
 					int __user *child_tidptr,
 					struct pid *pid,
 					int trace,
 					unsigned long tls,
 					int node)
 {
-	int retval;
+	int pidfd = -1, retval;
 	struct task_struct *p;
 	struct multiprocess_signals delayed;
 
@@ -1730,6 +1785,31 @@ static __latent_entropy struct task_struct *copy_process(
 			return ERR_PTR(-EINVAL);
 	}
 
+	if (clone_flags & CLONE_PIDFD) {
+		int reserved;
+
+		/*
+		 * - CLONE_PARENT_SETTID is useless for pidfds and also
+		 *   parent_tidptr is used to return pidfds.
+		 * - CLONE_DETACHED is blocked so that we can potentially
+		 *   reuse it later for CLONE_PIDFD.
+		 * - CLONE_THREAD is blocked until someone really needs it.
+		 */
+		if (clone_flags &
+		    (CLONE_DETACHED | CLONE_PARENT_SETTID | CLONE_THREAD))
+			return ERR_PTR(-EINVAL);
+
+		/*
+		 * Verify that parent_tidptr is sane so we can potentially
+		 * reuse it later.
+		 */
+		if (get_user(reserved, parent_tidptr))
+			return ERR_PTR(-EFAULT);
+
+		if (reserved != 0)
+			return ERR_PTR(-EINVAL);
+	}
+
 	/*
 	 * Force any signals received before this point to be delivered
 	 * before the fork happens.  Collect up signals sent to multiple
@@ -1936,6 +2016,22 @@ static __latent_entropy struct task_struct *copy_process(
 		}
 	}
 
+	/*
+	 * This has to happen after we've potentially unshared the file
+	 * descriptor table (so that the pidfd doesn't leak into the child
+	 * if the fd table isn't shared).
+	 */
+	if (clone_flags & CLONE_PIDFD) {
+		retval = pidfd_create(pid);
+		if (retval < 0)
+			goto bad_fork_free_pid;
+
+		pidfd = retval;
+		retval = put_user(pidfd, parent_tidptr);
+		if (retval)
+			goto bad_fork_put_pidfd;
+	}
+
 #ifdef CONFIG_BLOCK
 	p->plug = NULL;
 #endif
@@ -1996,7 +2092,7 @@ static __latent_entropy struct task_struct *copy_process(
 	 */
 	retval = cgroup_can_fork(p);
 	if (retval)
-		goto bad_fork_free_pid;
+		goto bad_fork_put_pidfd;
 
 	/*
 	 * From this point on we must avoid any synchronous user-space
@@ -2111,6 +2207,9 @@ bad_fork_cancel_cgroup:
 	spin_unlock(&current->sighand->siglock);
 	write_unlock_irq(&tasklist_lock);
 	cgroup_cancel_fork(p);
+bad_fork_put_pidfd:
+	if (clone_flags & CLONE_PIDFD)
+		ksys_close(pidfd);
 bad_fork_free_pid:
 	cgroup_threadgroup_change_end(current);
 	if (pid != &init_struct_pid)
@@ -2176,7 +2275,7 @@ static inline void init_idle_pids(struct task_struct *idle)
 struct task_struct *fork_idle(int cpu)
 {
 	struct task_struct *task;
-	task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0,
+	task = copy_process(CLONE_VM, 0, 0, NULL, NULL, &init_struct_pid, 0, 0,
 			    cpu_to_node(cpu));
 	if (!IS_ERR(task)) {
 		init_idle_pids(task);
@@ -2223,7 +2322,7 @@ long _do_fork(unsigned long clone_flags,
 			trace = 0;
 	}
 
-	p = copy_process(clone_flags, stack_start, stack_size,
+	p = copy_process(clone_flags, stack_start, stack_size, parent_tidptr,
 			 child_tidptr, NULL, trace, tls, NUMA_NO_NODE);
 	add_latent_entropy();