1 files changed, 163 insertions, 45 deletions

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 636f1c682ac0..e4ca2dd2b764 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1209,7 +1209,9 @@ void rebuild_sched_domains(void)
  *
  * Iterate through each task of @cs updating its cpus_allowed to the
  * effective cpuset's.  As this function is called with cpuset_rwsem held,
- * cpuset membership stays stable.
+ * cpuset membership stays stable. For top_cpuset, task_cpu_possible_mask()
+ * is used instead of effective_cpus to make sure all offline CPUs are also
+ * included as hotplug code won't update cpumasks for tasks in top_cpuset.
  */
 static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
 {
@@ -1219,15 +1221,18 @@ static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
 
 	css_task_iter_start(&cs->css, 0, &it);
 	while ((task = css_task_iter_next(&it))) {
-		/*
-		 * Percpu kthreads in top_cpuset are ignored
-		 */
-		if (top_cs && (task->flags & PF_KTHREAD) &&
-		    kthread_is_per_cpu(task))
-			continue;
+		const struct cpumask *possible_mask = task_cpu_possible_mask(task);
 
-		cpumask_and(new_cpus, cs->effective_cpus,
-			    task_cpu_possible_mask(task));
+		if (top_cs) {
+			/*
+			 * Percpu kthreads in top_cpuset are ignored
+			 */
+			if ((task->flags & PF_KTHREAD) && kthread_is_per_cpu(task))
+				continue;
+			cpumask_andnot(new_cpus, possible_mask, cs->subparts_cpus);
+		} else {
+			cpumask_and(new_cpus, possible_mask, cs->effective_cpus);
+		}
 		set_cpus_allowed_ptr(task, new_cpus);
 	}
 	css_task_iter_end(&it);
@@ -1513,7 +1518,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
 	spin_unlock_irq(&callback_lock);
 
 	if (adding || deleting)
-		update_tasks_cpumask(parent, tmp->new_cpus);
+		update_tasks_cpumask(parent, tmp->addmask);
 
 	/*
 	 * Set or clear CS_SCHED_LOAD_BALANCE when partcmd_update, if necessary.
@@ -1770,10 +1775,13 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	/*
 	 * Use the cpumasks in trialcs for tmpmasks when they are pointers
 	 * to allocated cpumasks.
+	 *
+	 * Note that update_parent_subparts_cpumask() uses only addmask &
+	 * delmask, but not new_cpus.
 	 */
 	tmp.addmask  = trialcs->subparts_cpus;
 	tmp.delmask  = trialcs->effective_cpus;
-	tmp.new_cpus = trialcs->cpus_allowed;
+	tmp.new_cpus = NULL;
 #endif
 
 	retval = validate_change(cs, trialcs);
@@ -1838,6 +1846,11 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	}
 	spin_unlock_irq(&callback_lock);
 
+#ifdef CONFIG_CPUMASK_OFFSTACK
+	/* Now trialcs->cpus_allowed is available */
+	tmp.new_cpus = trialcs->cpus_allowed;
+#endif
+
 	/* effective_cpus will be updated here */
 	update_cpumasks_hier(cs, &tmp, false);
 
@@ -2445,6 +2458,20 @@ static int fmeter_getrate(struct fmeter *fmp)
 
 static struct cpuset *cpuset_attach_old_cs;
 
+/*
+ * Check to see if a cpuset can accept a new task
+ * For v1, cpus_allowed and mems_allowed can't be empty.
+ * For v2, effective_cpus can't be empty.
+ * Note that in v1, effective_cpus = cpus_allowed.
+ */
+static int cpuset_can_attach_check(struct cpuset *cs)
+{
+	if (cpumask_empty(cs->effective_cpus) ||
+	   (!is_in_v2_mode() && nodes_empty(cs->mems_allowed)))
+		return -ENOSPC;
+	return 0;
+}
+
 /* Called by cgroups to determine if a cpuset is usable; cpuset_rwsem held */
 static int cpuset_can_attach(struct cgroup_taskset *tset)
 {
@@ -2459,16 +2486,9 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
 
 	percpu_down_write(&cpuset_rwsem);
 
-	/* allow moving tasks into an empty cpuset if on default hierarchy */
-	ret = -ENOSPC;
-	if (!is_in_v2_mode() &&
-	    (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)))
-		goto out_unlock;
-
-	/*
-	 * Task cannot be moved to a cpuset with empty effective cpus.
-	 */
-	if (cpumask_empty(cs->effective_cpus))
+	/* Check to see if task is allowed in the cpuset */
+	ret = cpuset_can_attach_check(cs);
+	if (ret)
 		goto out_unlock;
 
 	cgroup_taskset_for_each(task, css, tset) {
@@ -2485,7 +2505,6 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
 	 * changes which zero cpus/mems_allowed.
 	 */
 	cs->attach_in_progress++;
-	ret = 0;
 out_unlock:
 	percpu_up_write(&cpuset_rwsem);
 	return ret;
@@ -2494,25 +2513,47 @@ out_unlock:
 static void cpuset_cancel_attach(struct cgroup_taskset *tset)
 {
 	struct cgroup_subsys_state *css;
+	struct cpuset *cs;
 
 	cgroup_taskset_first(tset, &css);
+	cs = css_cs(css);
 
 	percpu_down_write(&cpuset_rwsem);
-	css_cs(css)->attach_in_progress--;
+	cs->attach_in_progress--;
+	if (!cs->attach_in_progress)
+		wake_up(&cpuset_attach_wq);
 	percpu_up_write(&cpuset_rwsem);
 }
 
 /*
- * Protected by cpuset_rwsem.  cpus_attach is used only by cpuset_attach()
+ * Protected by cpuset_rwsem. cpus_attach is used only by cpuset_attach_task()
  * but we can't allocate it dynamically there.  Define it global and
  * allocate from cpuset_init().
  */
 static cpumask_var_t cpus_attach;
+static nodemask_t cpuset_attach_nodemask_to;
+
+static void cpuset_attach_task(struct cpuset *cs, struct task_struct *task)
+{
+	percpu_rwsem_assert_held(&cpuset_rwsem);
+
+	if (cs != &top_cpuset)
+		guarantee_online_cpus(task, cpus_attach);
+	else
+		cpumask_andnot(cpus_attach, task_cpu_possible_mask(task),
+			       cs->subparts_cpus);
+	/*
+	 * can_attach beforehand should guarantee that this doesn't
+	 * fail.  TODO: have a better way to handle failure here
+	 */
+	WARN_ON_ONCE(set_cpus_allowed_ptr(task, cpus_attach));
+
+	cpuset_change_task_nodemask(task, &cpuset_attach_nodemask_to);
+	cpuset_update_task_spread_flags(cs, task);
+}
 
 static void cpuset_attach(struct cgroup_taskset *tset)
 {
-	/* static buf protected by cpuset_rwsem */
-	static nodemask_t cpuset_attach_nodemask_to;
 	struct task_struct *task;
 	struct task_struct *leader;
 	struct cgroup_subsys_state *css;
@@ -2543,20 +2584,8 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 
 	guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
 
-	cgroup_taskset_for_each(task, css, tset) {
-		if (cs != &top_cpuset)
-			guarantee_online_cpus(task, cpus_attach);
-		else
-			cpumask_copy(cpus_attach, task_cpu_possible_mask(task));
-		/*
-		 * can_attach beforehand should guarantee that this doesn't
-		 * fail.  TODO: have a better way to handle failure here
-		 */
-		WARN_ON_ONCE(set_cpus_allowed_ptr(task, cpus_attach));
-
-		cpuset_change_task_nodemask(task, &cpuset_attach_nodemask_to);
-		cpuset_update_task_spread_flags(cs, task);
-	}
+	cgroup_taskset_for_each(task, css, tset)
+		cpuset_attach_task(cs, task);
 
 	/*
 	 * Change mm for all threadgroup leaders. This is expensive and may
@@ -3248,17 +3277,101 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
 }
 
 /*
+ * In case the child is cloned into a cpuset different from its parent,
+ * additional checks are done to see if the move is allowed.
+ */
+static int cpuset_can_fork(struct task_struct *task, struct css_set *cset)
+{
+	struct cpuset *cs = css_cs(cset->subsys[cpuset_cgrp_id]);
+	bool same_cs;
+	int ret;
+
+	rcu_read_lock();
+	same_cs = (cs == task_cs(current));
+	rcu_read_unlock();
+
+	if (same_cs)
+		return 0;
+
+	lockdep_assert_held(&cgroup_mutex);
+	percpu_down_write(&cpuset_rwsem);
+
+	/* Check to see if task is allowed in the cpuset */
+	ret = cpuset_can_attach_check(cs);
+	if (ret)
+		goto out_unlock;
+
+	ret = task_can_attach(task, cs->effective_cpus);
+	if (ret)
+		goto out_unlock;
+
+	ret = security_task_setscheduler(task);
+	if (ret)
+		goto out_unlock;
+
+	/*
+	 * Mark attach is in progress.  This makes validate_change() fail
+	 * changes which zero cpus/mems_allowed.
+	 */
+	cs->attach_in_progress++;
+out_unlock:
+	percpu_up_write(&cpuset_rwsem);
+	return ret;
+}
+
+static void cpuset_cancel_fork(struct task_struct *task, struct css_set *cset)
+{
+	struct cpuset *cs = css_cs(cset->subsys[cpuset_cgrp_id]);
+	bool same_cs;
+
+	rcu_read_lock();
+	same_cs = (cs == task_cs(current));
+	rcu_read_unlock();
+
+	if (same_cs)
+		return;
+
+	percpu_down_write(&cpuset_rwsem);
+	cs->attach_in_progress--;
+	if (!cs->attach_in_progress)
+		wake_up(&cpuset_attach_wq);
+	percpu_up_write(&cpuset_rwsem);
+}
+
+/*
  * Make sure the new task conform to the current state of its parent,
  * which could have been changed by cpuset just after it inherits the
  * state from the parent and before it sits on the cgroup's task list.
  */
 static void cpuset_fork(struct task_struct *task)
 {
-	if (task_css_is_root(task, cpuset_cgrp_id))
+	struct cpuset *cs;
+	bool same_cs;
+
+	rcu_read_lock();
+	cs = task_cs(task);
+	same_cs = (cs == task_cs(current));
+	rcu_read_unlock();
+
+	if (same_cs) {
+		if (cs == &top_cpuset)
+			return;
+
+		set_cpus_allowed_ptr(task, current->cpus_ptr);
+		task->mems_allowed = current->mems_allowed;
 		return;
+	}
 
-	set_cpus_allowed_ptr(task, current->cpus_ptr);
-	task->mems_allowed = current->mems_allowed;
+	/* CLONE_INTO_CGROUP */
+	percpu_down_write(&cpuset_rwsem);
+	guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
+	cpuset_attach_task(cs, task);
+
+	cs->attach_in_progress--;
+	if (!cs->attach_in_progress)
+		wake_up(&cpuset_attach_wq);
+
+	percpu_up_write(&cpuset_rwsem);
 }
 
 struct cgroup_subsys cpuset_cgrp_subsys = {
@@ -3271,6 +3384,8 @@ struct cgroup_subsys cpuset_cgrp_subsys = {
 	.attach		= cpuset_attach,
 	.post_attach	= cpuset_post_attach,
 	.bind		= cpuset_bind,
+	.can_fork	= cpuset_can_fork,
+	.cancel_fork	= cpuset_cancel_fork,
 	.fork		= cpuset_fork,
 	.legacy_cftypes	= legacy_files,
 	.dfl_cftypes	= dfl_files,
@@ -3508,6 +3623,8 @@ retry:
 update_tasks:
 	cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus);
 	mems_updated = !nodes_equal(new_mems, cs->effective_mems);
+	if (!cpus_updated && !mems_updated)
+		goto unlock;	/* Hotplug doesn't affect this cpuset */
 
 	if (mems_updated)
 		check_insane_mems_config(&new_mems);
@@ -3519,6 +3636,7 @@ update_tasks:
 		hotplug_update_tasks_legacy(cs, &new_cpus, &new_mems,
 					    cpus_updated, mems_updated);
 
+unlock:
 	percpu_up_write(&cpuset_rwsem);
 }
 
@@ -3831,7 +3949,7 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
 }
 
 /*
- * __cpuset_node_allowed - Can we allocate on a memory node?
+ * cpuset_node_allowed - Can we allocate on a memory node?
  * @node: is this an allowed node?
  * @gfp_mask: memory allocation flags
  *
@@ -3870,7 +3988,7 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
  *	GFP_KERNEL   - any node in enclosing hardwalled cpuset ok
  *	GFP_USER     - only nodes in current tasks mems allowed ok.
  */
-bool __cpuset_node_allowed(int node, gfp_t gfp_mask)
+bool cpuset_node_allowed(int node, gfp_t gfp_mask)
 {
 	struct cpuset *cs;		/* current cpuset ancestors */
 	bool allowed;			/* is allocation in zone z allowed? */