Merge remote-tracking branch 'remotes/stable/linux-4.4.y' into karo-tx6-mainline

[karo-tx-linux.git] / kernel / cgroup.c

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 470f6536b9e8cfb029eedb5ecdb3c3e8c3c341be..1c9d701f7a72916155759c56561b084f0fc4900d 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -57,7 +57,7 @@
 #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
 #include <linux/kthread.h>
 #include <linux/delay.h>
-
+#include <linux/cpuset.h>
 #include <linux/atomic.h>
 
 /*
@@ -2498,6 +2498,14 @@ static void cgroup_migrate_add_src(struct css_set *src_cset,
        lockdep_assert_held(&cgroup_mutex);
        lockdep_assert_held(&css_set_lock);
 
+       /*
+        * If ->dead, @src_set is associated with one or more dead cgroups
+        * and doesn't contain any migratable tasks.  Ignore it early so
+        * that the rest of migration path doesn't get confused by it.
+        */
+       if (src_cset->dead)
+               return;
+
        src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
 
        if (!list_empty(&src_cset->mg_preload_node))
@@ -2713,9 +2721,10 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
                                    size_t nbytes, loff_t off, bool threadgroup)
 {
        struct task_struct *tsk;
+       struct cgroup_subsys *ss;
        struct cgroup *cgrp;
        pid_t pid;
-       int ret;
+       int ssid, ret;
 
        if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
                return -EINVAL;
@@ -2763,6 +2772,9 @@ out_unlock_rcu:
        rcu_read_unlock();
 out_unlock_threadgroup:
        percpu_up_write(&cgroup_threadgroup_rwsem);
+       for_each_subsys(ss, ssid)
+               if (ss->post_attach)
+                       ss->post_attach();
        cgroup_kn_unlock(of->kn);
        return ret ?: nbytes;
 }
@@ -4680,14 +4692,15 @@ static void css_free_work_fn(struct work_struct *work)
 
        if (ss) {
                /* css free path */
+               struct cgroup_subsys_state *parent = css->parent;
                int id = css->id;
 
-               if (css->parent)
-                       css_put(css->parent);
-
                ss->css_free(css);
                cgroup_idr_remove(&ss->css_idr, id);
                cgroup_put(cgrp);
+
+               if (parent)
+                       css_put(parent);
        } else {
                /* cgroup free path */
                atomic_dec(&cgrp->root->nr_cgrps);
@@ -4783,6 +4796,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
        INIT_LIST_HEAD(&css->sibling);
        INIT_LIST_HEAD(&css->children);
        css->serial_nr = css_serial_nr_next++;
+       atomic_set(&css->online_cnt, 0);
 
        if (cgroup_parent(cgrp)) {
                css->parent = cgroup_css(cgroup_parent(cgrp), ss);
@@ -4805,6 +4819,10 @@ static int online_css(struct cgroup_subsys_state *css)
        if (!ret) {
                css->flags |= CSS_ONLINE;
                rcu_assign_pointer(css->cgroup->subsys[ss->id], css);
+
+               atomic_inc(&css->online_cnt);
+               if (css->parent)
+                       atomic_inc(&css->parent->online_cnt);
        }
        return ret;
 }
@@ -5036,10 +5054,15 @@ static void css_killed_work_fn(struct work_struct *work)
                container_of(work, struct cgroup_subsys_state, destroy_work);
 
        mutex_lock(&cgroup_mutex);
-       offline_css(css);
-       mutex_unlock(&cgroup_mutex);
 
-       css_put(css);
+       do {
+               offline_css(css);
+               css_put(css);
+               /* @css can't go away while we're holding cgroup_mutex */
+               css = css->parent;
+       } while (css && atomic_dec_and_test(&css->online_cnt));
+
+       mutex_unlock(&cgroup_mutex);
 }
 
 /* css kill confirmation processing requires process context, bounce */
@@ -5048,8 +5071,10 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
        struct cgroup_subsys_state *css =
                container_of(ref, struct cgroup_subsys_state, refcnt);
 
-       INIT_WORK(&css->destroy_work, css_killed_work_fn);
-       queue_work(cgroup_destroy_wq, &css->destroy_work);
+       if (atomic_dec_and_test(&css->online_cnt)) {
+               INIT_WORK(&css->destroy_work, css_killed_work_fn);
+               queue_work(cgroup_destroy_wq, &css->destroy_work);
+       }
 }
 
 /**
@@ -5118,6 +5143,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
        __releases(&cgroup_mutex) __acquires(&cgroup_mutex)
 {
        struct cgroup_subsys_state *css;
+       struct cgrp_cset_link *link;
        int ssid;
 
        lockdep_assert_held(&cgroup_mutex);
@@ -5138,11 +5164,18 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
                return -EBUSY;
 
        /*
-        * Mark @cgrp dead.  This prevents further task migration and child
-        * creation by disabling cgroup_lock_live_group().
+        * Mark @cgrp and the associated csets dead.  The former prevents
+        * further task migration and child creation by disabling
+        * cgroup_lock_live_group().  The latter makes the csets ignored by
+        * the migration path.
         */
        cgrp->self.flags &= ~CSS_ONLINE;
 
+       spin_lock_bh(&css_set_lock);
+       list_for_each_entry(link, &cgrp->cset_links, cset_link)
+               link->cset->dead = true;
+       spin_unlock_bh(&css_set_lock);
+
        /* initiate massacre of all css's */
        for_each_css(css, ssid, cgrp)
                kill_css(css);