pidfd: add NSpid entries to fdinfo

Currently, the fdinfo file contains the Pid field which shows the
pid a given pidfd refers to in the pid namespace of the procfs
instance. If pid namespaces are configured, also show an NSpid field
for easy retrieval of the pid in all descendant pid namespaces. If
the pid namespace of the process is not a descendant of the pid
namespace of the procfs instance 0 will be shown as its first NSpid
entry and no other entries will be shown. Add a block comment to
pidfd_show_fdinfo with a detailed explanation of Pid and NSpid fields.

Co-developed-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Christian Kellner <christian@kellner.me>
Reviewed-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/20191014162034.2185-1-ckellner@redhat.com
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>

1 files changed, 52 insertions, 1 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index bcdf53125210..782986962d47 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1695,12 +1695,63 @@ static int pidfd_release(struct inode *inode, struct file *file)
 }
 
 #ifdef CONFIG_PROC_FS
+/**
+ * pidfd_show_fdinfo - print information about a pidfd
+ * @m: proc fdinfo file
+ * @f: file referencing a pidfd
+ *
+ * Pid:
+ * This function will print the pid that a given pidfd refers to in the
+ * pid namespace of the procfs instance.
+ * If the pid namespace of the process is not a descendant of the pid
+ * namespace of the procfs instance 0 will be shown as its pid. This is
+ * similar to calling getppid() on a process whose parent is outside of
+ * its pid namespace.
+ *
+ * NSpid:
+ * If pid namespaces are supported then this function will also print
+ * the pid of a given pidfd refers to for all descendant pid namespaces
+ * starting from the current pid namespace of the instance, i.e. the
+ * Pid field and the first entry in the NSpid field will be identical.
+ * If the pid namespace of the process is not a descendant of the pid
+ * namespace of the procfs instance 0 will be shown as its first NSpid
+ * entry and no others will be shown.
+ * Note that this differs from the Pid and NSpid fields in
+ * /proc/<pid>/status where Pid and NSpid are always shown relative to
+ * the  pid namespace of the procfs instance. The difference becomes
+ * obvious when sending around a pidfd between pid namespaces from a
+ * different branch of the tree, i.e. where no ancestoral relation is
+ * present between the pid namespaces:
+ * - create two new pid namespaces ns1 and ns2 in the initial pid
+ *   namespace (also take care to create new mount namespaces in the
+ *   new pid namespace and mount procfs)
+ * - create a process with a pidfd in ns1
+ * - send pidfd from ns1 to ns2
+ * - read /proc/self/fdinfo/<pidfd> and observe that both Pid and NSpid
+ *   have exactly one entry, which is 0
+ */
 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;
+	pid_t nr = pid_nr_ns(pid, ns);
+
+	seq_put_decimal_ull(m, "Pid:\t", nr);
 
-	seq_put_decimal_ull(m, "Pid:\t", pid_nr_ns(pid, ns));
+#ifdef CONFIG_PID_NS
+	seq_put_decimal_ull(m, "\nNSpid:\t", nr);
+	if (nr) {
+		int i;
+
+		/* If nr is non-zero it means that 'pid' is valid and that
+		 * ns, i.e. the pid namespace associated with the procfs
+		 * instance, is in the pid namespace hierarchy of pid.
+		 * Start at one below the already printed level.
+		 */
+		for (i = ns->level + 1; i <= pid->level; i++)
+			seq_put_decimal_ull(m, "\t", pid->numbers[i].nr);
+	}
+#endif
 	seq_putc(m, '\n');
 }
 #endif