1 files changed, 57 insertions, 65 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index f33c7153b6d7..7bb63eea6eb8 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -302,10 +302,10 @@ static void guarantee_online_cpus(const struct cpuset *cs,
  * are online, with memory.  If none are online with memory, walk
  * up the cpuset hierarchy until we find one that does have some
  * online mems.  If we get all the way to the top and still haven't
- * found any online mems, return node_states[N_HIGH_MEMORY].
+ * found any online mems, return node_states[N_MEMORY].
  *
  * One way or another, we guarantee to return some non-empty subset
- * of node_states[N_HIGH_MEMORY].
+ * of node_states[N_MEMORY].
  *
  * Call with callback_mutex held.
  */
@@ -313,14 +313,14 @@ static void guarantee_online_cpus(const struct cpuset *cs,
 static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask)
 {
         while (cs && !nodes_intersects(cs->mems_allowed,
-                                        node_states[N_HIGH_MEMORY]))
+                                        node_states[N_MEMORY]))
                 cs = cs->parent;
         if (cs)
                 nodes_and(*pmask, cs->mems_allowed,
-                                        node_states[N_HIGH_MEMORY]);
+                                        node_states[N_MEMORY]);
         else
-                *pmask = node_states[N_HIGH_MEMORY];
-        BUG_ON(!nodes_intersects(*pmask, node_states[N_HIGH_MEMORY]));
+                *pmask = node_states[N_MEMORY];
+        BUG_ON(!nodes_intersects(*pmask, node_states[N_MEMORY]));
 }
 
 /*
@@ -1100,7 +1100,7 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
                 return -ENOMEM;
 
         /*
-         * top_cpuset.mems_allowed tracks node_stats[N_HIGH_MEMORY];
+         * top_cpuset.mems_allowed tracks node_stats[N_MEMORY];
          * it's read-only
          */
         if (cs == &top_cpuset) {
@@ -1122,7 +1122,7 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
                         goto done;
 
                 if (!nodes_subset(trialcs->mems_allowed,
-                                node_states[N_HIGH_MEMORY])) {
+                                node_states[N_MEMORY])) {
                         retval =  -EINVAL;
                         goto done;
                 }
@@ -1784,56 +1784,20 @@ static struct cftype files[] = {
 };
 
 /*
- * post_clone() is called during cgroup_create() when the
- * clone_children mount argument was specified.  The cgroup
- * can not yet have any tasks.
- *
- * Currently we refuse to set up the cgroup - thereby
- * refusing the task to be entered, and as a result refusing
- * the sys_unshare() or clone() which initiated it - if any
- * sibling cpusets have exclusive cpus or mem.
- *
- * If this becomes a problem for some users who wish to
- * allow that scenario, then cpuset_post_clone() could be
- * changed to grant parent->cpus_allowed-sibling_cpus_exclusive
- * (and likewise for mems) to the new cgroup. Called with cgroup_mutex
- * held.
- */
-static void cpuset_post_clone(struct cgroup *cgroup)
-{
-        struct cgroup *parent, *child;
-        struct cpuset *cs, *parent_cs;
-
-        parent = cgroup->parent;
-        list_for_each_entry(child, &parent->children, sibling) {
-                cs = cgroup_cs(child);
-                if (is_mem_exclusive(cs) || is_cpu_exclusive(cs))
-                        return;
-        }
-        cs = cgroup_cs(cgroup);
-        parent_cs = cgroup_cs(parent);
-
-        mutex_lock(&callback_mutex);
-        cs->mems_allowed = parent_cs->mems_allowed;
-        cpumask_copy(cs->cpus_allowed, parent_cs->cpus_allowed);
-        mutex_unlock(&callback_mutex);
-        return;
-}
-
-/*
- *      cpuset_create - create a cpuset
+ *      cpuset_css_alloc - allocate a cpuset css
  *      cont:   control group that the new cpuset will be part of
  */
 
-static struct cgroup_subsys_state *cpuset_create(struct cgroup *cont)
+static struct cgroup_subsys_state *cpuset_css_alloc(struct cgroup *cont)
 {
-        struct cpuset *cs;
-        struct cpuset *parent;
+        struct cgroup *parent_cg = cont->parent;
+        struct cgroup *tmp_cg;
+        struct cpuset *parent, *cs;
 
-        if (!cont->parent) {
+        if (!parent_cg)
                 return &top_cpuset.css;
-        }
-        parent = cgroup_cs(cont->parent);
+        parent = cgroup_cs(parent_cg);
+
         cs = kmalloc(sizeof(*cs), GFP_KERNEL);
         if (!cs)
                 return ERR_PTR(-ENOMEM);
@@ -1855,7 +1819,36 @@ static struct cgroup_subsys_state *cpuset_create(struct cgroup *cont)
 
         cs->parent = parent;
         number_of_cpusets++;
-        return &cs->css ;
+
+        if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &cont->flags))
+                goto skip_clone;
+
+        /*
+         * Clone @parent's configuration if CGRP_CPUSET_CLONE_CHILDREN is
+         * set.  This flag handling is implemented in cgroup core for
+         * histrical reasons - the flag may be specified during mount.
+         *
+         * Currently, if any sibling cpusets have exclusive cpus or mem, we
+         * refuse to clone the configuration - thereby refusing the task to
+         * be entered, and as a result refusing the sys_unshare() or
+         * clone() which initiated it.  If this becomes a problem for some
+         * users who wish to allow that scenario, then this could be
+         * changed to grant parent->cpus_allowed-sibling_cpus_exclusive
+         * (and likewise for mems) to the new cgroup.
+         */
+        list_for_each_entry(tmp_cg, &parent_cg->children, sibling) {
+                struct cpuset *tmp_cs = cgroup_cs(tmp_cg);
+
+                if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs))
+                        goto skip_clone;
+        }
+
+        mutex_lock(&callback_mutex);
+        cs->mems_allowed = parent->mems_allowed;
+        cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
+        mutex_unlock(&callback_mutex);
+skip_clone:
+        return &cs->css;
 }
 
 /*
@@ -1864,7 +1857,7 @@ static struct cgroup_subsys_state *cpuset_create(struct cgroup *cont)
  * will call async_rebuild_sched_domains().
  */
 
-static void cpuset_destroy(struct cgroup *cont)
+static void cpuset_css_free(struct cgroup *cont)
 {
         struct cpuset *cs = cgroup_cs(cont);
 
@@ -1878,11 +1871,10 @@ static void cpuset_destroy(struct cgroup *cont)
 
 struct cgroup_subsys cpuset_subsys = {
         .name = "cpuset",
-        .create = cpuset_create,
-        .destroy = cpuset_destroy,
+        .css_alloc = cpuset_css_alloc,
+        .css_free = cpuset_css_free,
         .can_attach = cpuset_can_attach,
         .attach = cpuset_attach,
-        .post_clone = cpuset_post_clone,
         .subsys_id = cpuset_subsys_id,
         .base_cftypes = files,
         .early_init = 1,
@@ -2034,7 +2026,7 @@ static struct cpuset *cpuset_next(struct list_head *queue)
  * before dropping down to the next.  It always processes a node before
  * any of its children.
  *
- * In the case of memory hot-unplug, it will remove nodes from N_HIGH_MEMORY
+ * In the case of memory hot-unplug, it will remove nodes from N_MEMORY
  * if all present pages from a node are offlined.
  */
 static void
@@ -2073,7 +2065,7 @@ scan_cpusets_upon_hotplug(struct cpuset *root, enum hotplug_event event)
 
                         /* Continue past cpusets with all mems online */
                         if (nodes_subset(cp->mems_allowed,
-                                        node_states[N_HIGH_MEMORY]))
+                                        node_states[N_MEMORY]))
                                 continue;
 
                         oldmems = cp->mems_allowed;
@@ -2081,7 +2073,7 @@ scan_cpusets_upon_hotplug(struct cpuset *root, enum hotplug_event event)
                         /* Remove offline mems from this cpuset. */
                         mutex_lock(&callback_mutex);
                         nodes_and(cp->mems_allowed, cp->mems_allowed,
-                                                node_states[N_HIGH_MEMORY]);
+                                                node_states[N_MEMORY]);
                         mutex_unlock(&callback_mutex);
 
                         /* Move tasks from the empty cpuset to a parent */
@@ -2134,8 +2126,8 @@ void cpuset_update_active_cpus(bool cpu_online)
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 /*
- * Keep top_cpuset.mems_allowed tracking node_states[N_HIGH_MEMORY].
- * Call this routine anytime after node_states[N_HIGH_MEMORY] changes.
+ * Keep top_cpuset.mems_allowed tracking node_states[N_MEMORY].
+ * Call this routine anytime after node_states[N_MEMORY] changes.
  * See cpuset_update_active_cpus() for CPU hotplug handling.
  */
 static int cpuset_track_online_nodes(struct notifier_block *self,
@@ -2148,7 +2140,7 @@ static int cpuset_track_online_nodes(struct notifier_block *self,
         case MEM_ONLINE:
                 oldmems = top_cpuset.mems_allowed;
                 mutex_lock(&callback_mutex);
-                top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
+                top_cpuset.mems_allowed = node_states[N_MEMORY];
                 mutex_unlock(&callback_mutex);
                 update_tasks_nodemask(&top_cpuset, &oldmems, NULL);
                 break;
@@ -2177,7 +2169,7 @@ static int cpuset_track_online_nodes(struct notifier_block *self,
 void __init cpuset_init_smp(void)
 {
         cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
-        top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
+        top_cpuset.mems_allowed = node_states[N_MEMORY];
 
         hotplug_memory_notifier(cpuset_track_online_nodes, 10);
 
@@ -2245,7 +2237,7 @@ void cpuset_init_current_mems_allowed(void)
  *
  * Description: Returns the nodemask_t mems_allowed of the cpuset
  * attached to the specified @tsk.  Guaranteed to return some non-empty
- * subset of node_states[N_HIGH_MEMORY], even if this means going outside the
+ * subset of node_states[N_MEMORY], even if this means going outside the
  * tasks cpuset.
  **/