cgroups: make procs file writable

Make procs file writable to move all threads by tgid at once.

Add functionality that enables users to move all threads in a threadgroup
at once to a cgroup by writing the tgid to the 'cgroup.procs' file.  This
current implementation makes use of a per-threadgroup rwsem that's taken
for reading in the fork() path to prevent newly forking threads within the
threadgroup from "escaping" while the move is in progress.

Signed-off-by: Ben Blum <bblum@andrew.cmu.edu>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Matt Helsley <matthltc@us.ibm.com>
Reviewed-by: Paul Menage <menage@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 401 insertions, 47 deletions

diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index b3bd3bdbe202..8c4f3466c894 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -236,7 +236,8 @@ containing the following files describing that cgroup:
  - cgroup.procs: list of tgids in the cgroup.  This list is not
    guaranteed to be sorted or free of duplicate tgids, and userspace
    should sort/uniquify the list if this property is required.
-   This is a read-only file, for now.
+   Writing a thread group id into this file moves all threads in that
+   group into this cgroup.
  - notify_on_release flag: run the release agent on exit?
  - release_agent: the path to use for release notifications (this file
    exists in the top cgroup only)
@@ -430,6 +431,12 @@ You can attach the current shell task by echoing 0:
 
 # echo 0 > tasks
 
+You can use the cgroup.procs file instead of the tasks file to move all
+threads in a threadgroup at once. Echoing the pid of any task in a
+threadgroup to cgroup.procs causes all tasks in that threadgroup to be
+be attached to the cgroup. Writing 0 to cgroup.procs moves all tasks
+in the writing task's threadgroup.
+
 Note: Since every task is always a member of exactly one cgroup in each
 mounted hierarchy, to remove a task from its current cgroup you must
 move it into a new cgroup (possibly the root cgroup) by writing to the
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 38fb0ad1cb46..5e6a9745f0e7 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1735,6 +1735,76 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 }
 EXPORT_SYMBOL_GPL(cgroup_path);
 
+/*
+ * cgroup_task_migrate - move a task from one cgroup to another.
+ *
+ * 'guarantee' is set if the caller promises that a new css_set for the task
+ * will already exist. If not set, this function might sleep, and can fail with
+ * -ENOMEM. Otherwise, it can only fail with -ESRCH.
+ */
+static int cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp,
+                               struct task_struct *tsk, bool guarantee)
+{
+        struct css_set *oldcg;
+        struct css_set *newcg;
+
+        /*
+         * get old css_set. we need to take task_lock and refcount it, because
+         * an exiting task can change its css_set to init_css_set and drop its
+         * old one without taking cgroup_mutex.
+         */
+        task_lock(tsk);
+        oldcg = tsk->cgroups;
+        get_css_set(oldcg);
+        task_unlock(tsk);
+
+        /* locate or allocate a new css_set for this task. */
+        if (guarantee) {
+                /* we know the css_set we want already exists. */
+                struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT];
+                read_lock(&css_set_lock);
+                newcg = find_existing_css_set(oldcg, cgrp, template);
+                BUG_ON(!newcg);
+                get_css_set(newcg);
+                read_unlock(&css_set_lock);
+        } else {
+                might_sleep();
+                /* find_css_set will give us newcg already referenced. */
+                newcg = find_css_set(oldcg, cgrp);
+                if (!newcg) {
+                        put_css_set(oldcg);
+                        return -ENOMEM;
+                }
+        }
+        put_css_set(oldcg);
+
+        /* if PF_EXITING is set, the tsk->cgroups pointer is no longer safe. */
+        task_lock(tsk);
+        if (tsk->flags & PF_EXITING) {
+                task_unlock(tsk);
+                put_css_set(newcg);
+                return -ESRCH;
+        }
+        rcu_assign_pointer(tsk->cgroups, newcg);
+        task_unlock(tsk);
+
+        /* Update the css_set linked lists if we're using them */
+        write_lock(&css_set_lock);
+        if (!list_empty(&tsk->cg_list))
+                list_move(&tsk->cg_list, &newcg->tasks);
+        write_unlock(&css_set_lock);
+
+        /*
+         * We just gained a reference on oldcg by taking it from the task. As
+         * trading it for newcg is protected by cgroup_mutex, we're safe to drop
+         * it here; it will be freed under RCU.
+         */
+        put_css_set(oldcg);
+
+        set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
+        return 0;
+}
+
 /**
  * cgroup_attach_task - attach task 'tsk' to cgroup 'cgrp'
  * @cgrp: the cgroup the task is attaching to
@@ -1745,11 +1815,9 @@ EXPORT_SYMBOL_GPL(cgroup_path);
  */
 int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 {
-        int retval = 0;
+        int retval;
         struct cgroup_subsys *ss, *failed_ss = NULL;
         struct cgroup *oldcgrp;
-        struct css_set *cg;
-        struct css_set *newcg;
         struct cgroupfs_root *root = cgrp->root;
 
         /* Nothing to do if the task is already in that cgroup */
@@ -1780,36 +1848,9 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
                 }
         }
 
-        task_lock(tsk);
-        cg = tsk->cgroups;
-        get_css_set(cg);
-        task_unlock(tsk);
-        /*
-         * Locate or allocate a new css_set for this task,
-         * based on its final set of cgroups
-         */
-        newcg = find_css_set(cg, cgrp);
-        put_css_set(cg);
-        if (!newcg) {
-                retval = -ENOMEM;
-                goto out;
-        }
-
-        task_lock(tsk);
-        if (tsk->flags & PF_EXITING) {
-                task_unlock(tsk);
-                put_css_set(newcg);
-                retval = -ESRCH;
+        retval = cgroup_task_migrate(cgrp, oldcgrp, tsk, false);
+        if (retval)
                 goto out;
-        }
-        rcu_assign_pointer(tsk->cgroups, newcg);
-        task_unlock(tsk);
-
-        /* Update the css_set linked lists if we're using them */
-        write_lock(&css_set_lock);
-        if (!list_empty(&tsk->cg_list))
-                list_move(&tsk->cg_list, &newcg->tasks);
-        write_unlock(&css_set_lock);
 
         for_each_subsys(root, ss) {
                 if (ss->pre_attach)
@@ -1819,9 +1860,8 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
                 if (ss->attach)
                         ss->attach(ss, cgrp, oldcgrp, tsk);
         }
-        set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
+
         synchronize_rcu();
-        put_css_set(cg);
 
         /*
          * wake up rmdir() waiter. the rmdir should fail since the cgroup
@@ -1871,49 +1911,356 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 EXPORT_SYMBOL_GPL(cgroup_attach_task_all);
 
 /*
- * Attach task with pid 'pid' to cgroup 'cgrp'. Call with cgroup_mutex
- * held. May take task_lock of task
+ * cgroup_attach_proc works in two stages, the first of which prefetches all
+ * new css_sets needed (to make sure we have enough memory before committing
+ * to the move) and stores them in a list of entries of the following type.
+ * TODO: possible optimization: use css_set->rcu_head for chaining instead
+ */
+struct cg_list_entry {