5 files changed, 85 insertions, 31 deletions

diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt
index e8d25e784214..ff49cf901148 100644
--- a/Documentation/cgroup-v2.txt
+++ b/Documentation/cgroup-v2.txt
@@ -7,7 +7,7 @@ This is the authoritative documentation on the design, interface and
 conventions of cgroup v2.  It describes all userland-visible aspects
 of cgroup including core and specific controller behaviors.  All
 future changes must be reflected in this document.  Documentation for
-v1 is available under Documentation/cgroup-legacy/.
+v1 is available under Documentation/cgroup-v1/.
 
 CONTENTS
 
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 7f540f7f588d..789471dba6fb 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -127,6 +127,12 @@ struct cgroup_subsys_state {
          */
         u64 serial_nr;
 
+        /*
+         * Incremented by online self and children.  Used to guarantee that
+         * parents are not offlined before their children.
+         */
+        atomic_t online_cnt;
+
         /* percpu_ref killing and RCU release */
         struct rcu_head rcu_head;
         struct work_struct destroy_work;
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 85a868ccb493..fea160ee5803 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -137,6 +137,8 @@ static inline void set_mems_allowed(nodemask_t nodemask)
         task_unlock(current);
 }
 
+extern void cpuset_post_attach_flush(void);
+
 #else /* !CONFIG_CPUSETS */
 
 static inline bool cpusets_enabled(void) { return false; }
@@ -243,6 +245,10 @@ static inline bool read_mems_allowed_retry(unsigned int seq)
         return false;
 }
 
+static inline void cpuset_post_attach_flush(void)
+{
+}
+
 #endif /* !CONFIG_CPUSETS */
 
 #endif /* _LINUX_CPUSET_H */
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c03a640ef6da..d27904c193da 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -58,6 +58,7 @@
 #include <linux/kthread.h>
 #include <linux/delay.h>
 #include <linux/atomic.h>
+#include <linux/cpuset.h>
 #include <net/sock.h>
 
 /*
@@ -2739,6 +2740,7 @@ out_unlock_rcu:
 out_unlock_threadgroup:
         percpu_up_write(&cgroup_threadgroup_rwsem);
         cgroup_kn_unlock(of->kn);
+        cpuset_post_attach_flush();
         return ret ?: nbytes;
 }
 
@@ -4655,14 +4657,15 @@ 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);
@@ -4758,6 +4761,7 @@ 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);
@@ -4780,6 +4784,10 @@ 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;
 }
@@ -5017,10 +5025,15 @@ 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 */
@@ -5029,8 +5042,10 @@ 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);
+        }
 }
 
 /**
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 3e945fcd8179..41989ab4db57 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -287,6 +287,8 @@ static struct cpuset top_cpuset = {
 static DEFINE_MUTEX(cpuset_mutex);
 static DEFINE_SPINLOCK(callback_lock);
 
+static struct workqueue_struct *cpuset_migrate_mm_wq;
+
 /*
  * CPU / memory hotplug is handled asynchronously.
  */
@@ -972,31 +974,51 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 }
 
 /*
- * cpuset_migrate_mm
- *
- *    Migrate memory region from one set of nodes to another.
- *
- *    Temporarilly set tasks mems_allowed to target nodes of migration,
- *    so that the migration code can allocate pages on these nodes.
- *
- *    While the mm_struct we are migrating is typically from some
- *    other task, the task_struct mems_allowed that we are hacking
- *    is for our current task, which must allocate new pages for that
- *    migrating memory region.
+ * Migrate memory region from one set of nodes to another.  This is
+ * performed asynchronously as it can be called from process migration path
+ * holding locks involved in process management.  All mm migrations are
+ * performed in the queued order and can be waited for by flushing
+ * cpuset_migrate_mm_wq.
  */
 
+struct cpuset_migrate_mm_work {
+        struct work_struct      work;
+        struct mm_struct        *mm;
+        nodemask_t              from;
+        nodemask_t              to;
+};
+
+static void cpuset_migrate_mm_workfn(struct work_struct *work)
+{
+        struct cpuset_migrate_mm_work *mwork =
+                container_of(work, struct cpuset_migrate_mm_work, work);
+
+        /* on a wq worker, no need to worry about %current's mems_allowed */
+        do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL);
+        mmput(mwork->mm);
+        kfree(mwork);
+}
+
 static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
                                                         const nodemask_t *to)
 {
-        struct task_struct *tsk = current;
-
-        tsk->mems_allowed = *to;
+        struct cpuset_migrate_mm_work *mwork;
 
-        do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
+        mwork = kzalloc(sizeof(*mwork), GFP_KERNEL);
+        if (mwork) {
+                mwork->mm = mm;
+                mwork->from = *from;
+                mwork->to = *to;
+                INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn);
+                queue_work(cpuset_migrate_mm_wq, &mwork->work);
+        } else {
+                mmput(mm);
+        }
+}
 
-        rcu_read_lock();
-        guarantee_online_mems(task_cs(tsk), &tsk->mems_allowed);
-        rcu_read_unlock();
+void cpuset_post_attach_flush(void)
+{
+        flush_workqueue(cpuset_migrate_mm_wq);
 }
 
 /*
@@ -1097,7 +1119,8 @@ static void update_tasks_nodemask(struct cpuset *cs)
                 mpol_rebind_mm(mm, &cs->mems_allowed);
                 if (migrate)
                         cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems);
-                mmput(mm);
+                else
+                        mmput(mm);
         }
         css_task_iter_end(&it);
 
@@ -1545,11 +1568,11 @@ static void cpuset_attach(struct cgroup_taskset *tset)
                          * @old_mems_allowed is the right nodesets that we
                          * migrate mm from.
                          */
-                        if (is_memory_migrate(cs)) {
+                        if (is_memory_migrate(cs))
                                 cpuset_migrate_mm(mm, &oldcs->old_mems_allowed,
                                                   &cpuset_attach_nodemask_to);
-                        }
-                        mmput(mm);
+                        else
+                                mmput(mm);
                 }
         }
 
@@ -1714,6 +1737,7 @@ out_unlock:
         mutex_unlock(&cpuset_mutex);
         kernfs_unbreak_active_protection(of->kn);
         css_put(&cs->css);
+        flush_workqueue(cpuset_migrate_mm_wq);
         return retval ?: nbytes;
 }
 
@@ -2359,6 +2383,9 @@ void __init cpuset_init_smp(void)
         top_cpuset.effective_mems = node_states[N_MEMORY];
 
         register_hotmemory_notifier(&cpuset_track_online_nodes_nb);
+
+        cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0);
+        BUG_ON(!cpuset_migrate_mm_wq);
 }
 
 /**