fs, proc: introduce /proc/<pid>/task/<tid>/children entry

When we do checkpoint of a task we need to know the list of children the
task, has but there is no easy and fast way to generate reverse
parent->children chain from arbitrary <pid> (while a parent pid is
provided in "PPid" field of /proc/<pid>/status).

So instead of walking over all pids in the system (creating one big
process tree in memory, just to figure out which children a task has) --
we add explicit /proc/<pid>/task/<tid>/children entry, because the kernel
already has this kind of information but it is not yet exported.

This is a first level children, not the whole process tree.

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Serge Hallyn <serge.hallyn@canonical.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 145 insertions, 0 deletions

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 912af6ce562..d8d3f9a8e5a 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -40,6 +40,7 @@ Table of Contents
   3.4   /proc/<pid>/coredump_filter - Core dump filtering settings
   3.5   /proc/<pid>/mountinfo - Information about mounts
   3.6   /proc/<pid>/comm  & /proc/<pid>/task/<tid>/comm
+  3.7   /proc/<pid>/task/<tid>/children - Information about task children
 
   4     Configuring procfs
   4.1   Mount options
@@ -1578,6 +1579,23 @@ then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated
 comm value.
 
 
+3.7     /proc/<pid>/task/<tid>/children - Information about task children
+-------------------------------------------------------------------------
+This file provides a fast way to retrieve first level children pids
+of a task pointed by <pid>/<tid> pair. The format is a space separated
+stream of pids.
+
+Note the "first level" here -- if a child has own children they will
+not be listed here, one needs to read /proc/<children-pid>/task/<tid>/children
+to obtain the descendants.
+
+Since this interface is intended to be fast and cheap it doesn't
+guarantee to provide precise results and some children might be
+skipped, especially if they've exited right after we printed their
+pids, so one need to either stop or freeze processes being inspected
+if precise results are needed.
+
+
 ------------------------------------------------------------------------------
 Configuring procfs
 ------------------------------------------------------------------------------
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 3a26d23420c..62887e39a2d 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -565,3 +565,126 @@ int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
 
         return 0;
 }
+
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static struct pid *
+get_children_pid(struct inode *inode, struct pid *pid_prev, loff_t pos)
+{
+        struct task_struct *start, *task;
+        struct pid *pid = NULL;
+
+        read_lock(&tasklist_lock);
+
+        start = pid_task(proc_pid(inode), PIDTYPE_PID);
+        if (!start)
+                goto out;
+
+        /*
+         * Lets try to continue searching first, this gives
+         * us significant speedup on children-rich processes.
+         */
+        if (pid_prev) {
+                task = pid_task(pid_prev, PIDTYPE_PID);
+                if (task && task->real_parent == start &&
+                    !(list_empty(&task->sibling))) {
+                        if (list_is_last(&task->sibling, &start->children))
+                                goto out;
+                        task = list_first_entry(&task->sibling,
+                                                struct task_struct, sibling);
+                        pid = get_pid(task_pid(task));
+                        goto out;
+                }
+        }
+
+        /*
+         * Slow search case.
+         *
+         * We might miss some children here if children
+         * are exited while we were not holding the lock,
+         * but it was never promised to be accurate that
+         * much.
+         *
+         * "Just suppose that the parent sleeps, but N children
+         *  exit after we printed their tids. Now the slow paths
+         *  skips N extra children, we miss N tasks." (c)
+         *
+         * So one need to stop or freeze the leader and all
+         * its children to get a precise result.
+         */
+        list_for_each_entry(task, &start->children, sibling) {
+                if (pos-- == 0) {
+                        pid = get_pid(task_pid(task));
+                        break;
+                }
+        }
+
+out:
+        read_unlock(&tasklist_lock);
+        return pid;
+}
+
+static int children_seq_show(struct seq_file *seq, void *v)
+{
+        struct inode *inode = seq->private;
+        pid_t pid;
+
+        pid = pid_nr_ns(v, inode->i_sb->s_fs_info);
+        return seq_printf(seq, "%d ", pid);
+}
+
+static void *children_seq_start(struct seq_file *seq, loff_t *pos)
+{
+        return get_children_pid(seq->private, NULL, *pos);
+}
+
+static void *children_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+        struct pid *pid;
+
+        pid = get_children_pid(seq->private, v, *pos + 1);
+        put_pid(v);
+
+        ++*pos;
+        return pid;
+}
+
+static void children_seq_stop(struct seq_file *seq, void *v)
+{
+        put_pid(v);
+}
+
+static const struct seq_operations children_seq_ops = {
+        .start  = children_seq_start,
+        .next   = children_seq_next,
+        .stop   = children_seq_stop,
+        .show   = children_seq_show,
+};
+
+static int children_seq_open(struct inode *inode, struct file *file)
+{
+        struct seq_file *m;
+        int ret;
+
+        ret = seq_open(file, &children_seq_ops);
+        if (ret)
+                return ret;
+
+        m = file->private_data;
+        m->private = inode;
+
+        return ret;
+}
+
+int children_seq_release(struct inode *inode, struct file *file)
+{
+        seq_release(inode, file);
+        return 0;
+}
+
+const struct file_operations proc_tid_children_operations = {
+        .open    = children_seq_open,
+        .read    = seq_read,
+        .llseek  = seq_lseek,
+        .release = children_seq_release,
+};
+#endif /* CONFIG_CHECKPOINT_RESTORE */
diff --git a/fs/proc/base.c b/fs/proc/base.c
index bd8b4ca6a61..616f41a7cde 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -3400,6 +3400,9 @@ static const struct pid_entry tid_base_stuff[] = {
         ONE("stat",      S_IRUGO, proc_tid_stat),
         ONE("statm",     S_IRUGO, proc_pid_statm),
         REG("maps",      S_IRUGO, proc_tid_maps_operations),
+#ifdef CONFIG_CHECKPOINT_RESTORE
+        REG("children",  S_IRUGO, proc_tid_children_operations),
+#endif
 #ifdef CONFIG_NUMA
         REG("numa_maps", S_IRUGO, proc_tid_numa_maps_operations),
 #endif
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index a30643784db..eca4aca5b6e 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -54,6 +54,7 @@ extern int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
                                 struct pid *pid, struct task_struct *task);
 extern loff_t mem_lseek(struct file *file, loff_t offset, int orig);
 
+extern const struct file_operations proc_tid_children_operations;
 extern const struct file_operations proc_pid_maps_operations;
 extern const struct file_operations proc_tid_maps_operations;
 extern const struct file_operations proc_pid_numa_maps_operations;