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>

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index b7413cb46dcb1f1a331068861e766a6c03a5da40..27eb1aecd82882b3dd637b16fd4a5fb3718bf9fb 100644 (file)
--- 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
@@ -1577,6 +1578,23 @@ 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 f9bd395b3473f6f1ca5f0697679d7d469e9fdb7c..4d48dfa4f4478fd0eec312a56060c09c89a0866a 100644 (file)
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -556,3 +556,126 @@ 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 1c8b280146d7a0956dddd1f06e431f49671bd269..4d1185455503a7ed4511361b7955a328fb598a27 100644 (file)
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2990,6 +2990,9 @@ static const struct pid_entry tgid_base_stuff[] = {
        ONE("stat",       S_IRUGO, proc_tgid_stat),
        ONE("statm",      S_IRUGO, proc_pid_statm),
        REG("maps",       S_IRUGO, proc_pid_maps_operations),
+#ifdef CONFIG_CHECKPOINT_RESTORE
+       REG("children",  S_IRUGO, proc_tid_children_operations),
+#endif
 #ifdef CONFIG_NUMA
        REG("numa_maps",  S_IRUGO, proc_pid_numa_maps_operations),
 #endif

diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 5f79bb8b4c60211620c8af8212e9ec97c0978dc1..df65f26076d4fc49ad53f6aa18b70ea87cff367f 100644 (file)
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -56,6 +56,7 @@ 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;