1 files changed, 63 insertions, 54 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index f0acff0f6..02a8ea5c9 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -473,7 +473,8 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 
 	/* On legacy hiearchy, we must be a subset of our parent cpuset. */
 	ret = -EACCES;
-	if (!cgroup_on_dfl(cur->css.cgroup) && !is_cpuset_subset(trial, par))
+	if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
+	    !is_cpuset_subset(trial, par))
 		goto out;
 
 	/*
@@ -497,7 +498,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 	 * be changed to have empty cpus_allowed or mems_allowed.
 	 */
 	ret = -ENOSPC;
-	if ((cgroup_has_tasks(cur->css.cgroup) || cur->attach_in_progress)) {
+	if ((cgroup_is_populated(cur->css.cgroup) || cur->attach_in_progress)) {
 		if (!cpumask_empty(cur->cpus_allowed) &&
 		    cpumask_empty(trial->cpus_allowed))
 			goto out;
@@ -879,7 +880,8 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
 		 * If it becomes empty, inherit the effective mask of the
 		 * parent, which is guaranteed to have some CPUs.
 		 */
-		if (cgroup_on_dfl(cp->css.cgroup) && cpumask_empty(new_cpus))
+		if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
+		    cpumask_empty(new_cpus))
 			cpumask_copy(new_cpus, parent->effective_cpus);
 
 		/* Skip the whole subtree if the cpumask remains the same. */
@@ -896,7 +898,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
 		cpumask_copy(cp->effective_cpus, new_cpus);
 		spin_unlock_irq(&callback_lock);
 
-		WARN_ON(!cgroup_on_dfl(cp->css.cgroup) &&
+		WARN_ON(!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
 			!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
 
 		update_tasks_cpumask(cp);
@@ -1135,7 +1137,8 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
 		 * If it becomes empty, inherit the effective mask of the
 		 * parent, which is guaranteed to have some MEMs.
 		 */
-		if (cgroup_on_dfl(cp->css.cgroup) && nodes_empty(*new_mems))
+		if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
+		    nodes_empty(*new_mems))
 			*new_mems = parent->effective_mems;
 
 		/* Skip the whole subtree if the nodemask remains the same. */
@@ -1152,7 +1155,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
 		cp->effective_mems = *new_mems;
 		spin_unlock_irq(&callback_lock);
 
-		WARN_ON(!cgroup_on_dfl(cp->css.cgroup) &&
+		WARN_ON(!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
 			!nodes_equal(cp->mems_allowed, cp->effective_mems));
 
 		update_tasks_nodemask(cp);
@@ -1426,25 +1429,26 @@ static int fmeter_getrate(struct fmeter *fmp)
 static struct cpuset *cpuset_attach_old_cs;
 
 /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */
-static int cpuset_can_attach(struct cgroup_subsys_state *css,
-			     struct cgroup_taskset *tset)
+static int cpuset_can_attach(struct cgroup_taskset *tset)
 {
-	struct cpuset *cs = css_cs(css);
+	struct cgroup_subsys_state *css;
+	struct cpuset *cs;
 	struct task_struct *task;
 	int ret;
 
 	/* used later by cpuset_attach() */
-	cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset));
+	cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css));
+	cs = css_cs(css);
 
 	mutex_lock(&cpuset_mutex);
 
 	/* allow moving tasks into an empty cpuset if on default hierarchy */
 	ret = -ENOSPC;
-	if (!cgroup_on_dfl(css->cgroup) &&
+	if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
 	    (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)))
 		goto out_unlock;
 
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, css, tset) {
 		ret = task_can_attach(task, cs->cpus_allowed);
 		if (ret)
 			goto out_unlock;
@@ -1464,9 +1468,14 @@ out_unlock:
 	return ret;
 }
 
-static void cpuset_cancel_attach(struct cgroup_subsys_state *css,
-				 struct cgroup_taskset *tset)
+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);
+
 	mutex_lock(&cpuset_mutex);
 	css_cs(css)->attach_in_progress--;
 	mutex_unlock(&cpuset_mutex);
@@ -1479,17 +1488,19 @@ static void cpuset_cancel_attach(struct cgroup_subsys_state *css,
  */
 static cpumask_var_t cpus_attach;
 
-static void cpuset_attach(struct cgroup_subsys_state *css,
-			  struct cgroup_taskset *tset)
+static void cpuset_attach(struct cgroup_taskset *tset)
 {
 	/* static buf protected by cpuset_mutex */
 	static nodemask_t cpuset_attach_nodemask_to;
-	struct mm_struct *mm;
 	struct task_struct *task;
-	struct task_struct *leader = cgroup_taskset_first(tset);
-	struct cpuset *cs = css_cs(css);
+	struct task_struct *leader;
+	struct cgroup_subsys_state *css;
+	struct cpuset *cs;
 	struct cpuset *oldcs = cpuset_attach_old_cs;
 
+	cgroup_taskset_first(tset, &css);
+	cs = css_cs(css);
+
 	mutex_lock(&cpuset_mutex);
 
 	/* prepare for attach */
@@ -1500,7 +1511,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 
 	guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
 
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, css, tset) {
 		/*
 		 * can_attach beforehand should guarantee that this doesn't
 		 * fail.  TODO: have a better way to handle failure here
@@ -1512,26 +1523,30 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 	}
 
 	/*
-	 * Change mm, possibly for multiple threads in a threadgroup. This is
-	 * expensive and may sleep.
+	 * Change mm for all threadgroup leaders. This is expensive and may
+	 * sleep and should be moved outside migration path proper.
 	 */
 	cpuset_attach_nodemask_to = cs->effective_mems;
-	mm = get_task_mm(leader);
-	if (mm) {
-		mpol_rebind_mm(mm, &cpuset_attach_nodemask_to);
-
-		/*
-		 * old_mems_allowed is the same with mems_allowed here, except
-		 * if this task is being moved automatically due to hotplug.
-		 * In that case @mems_allowed has been updated and is empty,
-		 * so @old_mems_allowed is the right nodesets that we migrate
-		 * mm from.
-		 */
-		if (is_memory_migrate(cs)) {
-			cpuset_migrate_mm(mm, &oldcs->old_mems_allowed,
-					  &cpuset_attach_nodemask_to);
+	cgroup_taskset_for_each_leader(leader, css, tset) {
+		struct mm_struct *mm = get_task_mm(leader);
+
+		if (mm) {
+			mpol_rebind_mm(mm, &cpuset_attach_nodemask_to);
+
+			/*
+			 * old_mems_allowed is the same with mems_allowed
+			 * here, except if this task is being moved
+			 * automatically due to hotplug.  In that case
+			 * @mems_allowed has been updated and is empty, so
+			 * @old_mems_allowed is the right nodesets that we
+			 * migrate mm from.
+			 */
+			if (is_memory_migrate(cs)) {
+				cpuset_migrate_mm(mm, &oldcs->old_mems_allowed,
+						  &cpuset_attach_nodemask_to);
+			}
+			mmput(mm);
 		}
-		mmput(mm);
 	}
 
 	cs->old_mems_allowed = cpuset_attach_nodemask_to;
@@ -1594,9 +1609,6 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
 	case FILE_MEMORY_PRESSURE_ENABLED:
 		cpuset_memory_pressure_enabled = !!val;
 		break;
-	case FILE_MEMORY_PRESSURE:
-		retval = -EACCES;
-		break;
 	case FILE_SPREAD_PAGE:
 		retval = update_flag(CS_SPREAD_PAGE, cs, val);
 		break;
@@ -1863,9 +1875,6 @@ static struct cftype files[] = {
 	{
 		.name = "memory_pressure",
 		.read_u64 = cpuset_read_u64,
-		.write_u64 = cpuset_write_u64,
-		.private = FILE_MEMORY_PRESSURE,
-		.mode = S_IRUGO,
 	},
 
 	{
@@ -1952,7 +1961,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 	cpuset_inc();
 
 	spin_lock_irq(&callback_lock);
-	if (cgroup_on_dfl(cs->css.cgroup)) {
+	if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) {
 		cpumask_copy(cs->effective_cpus, parent->effective_cpus);
 		cs->effective_mems = parent->effective_mems;
 	}
@@ -2029,7 +2038,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
 	mutex_lock(&cpuset_mutex);
 	spin_lock_irq(&callback_lock);
 
-	if (cgroup_on_dfl(root_css->cgroup)) {
+	if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) {
 		cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask);
 		top_cpuset.mems_allowed = node_possible_map;
 	} else {
@@ -2210,7 +2219,7 @@ retry:
 	cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus);
 	mems_updated = !nodes_equal(new_mems, cs->effective_mems);
 
-	if (cgroup_on_dfl(cs->css.cgroup))
+	if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys))
 		hotplug_update_tasks(cs, &new_cpus, &new_mems,
 				     cpus_updated, mems_updated);
 	else
@@ -2241,7 +2250,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 	static cpumask_t new_cpus;
 	static nodemask_t new_mems;
 	bool cpus_updated, mems_updated;
-	bool on_dfl = cgroup_on_dfl(top_cpuset.css.cgroup);
+	bool on_dfl = cgroup_subsys_on_dfl(cpuset_cgrp_subsys);
 
 	mutex_lock(&cpuset_mutex);
 
@@ -2598,22 +2607,22 @@ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
 }
 
 /**
- * cpuset_print_task_mems_allowed - prints task's cpuset and mems_allowed
- * @tsk: pointer to task_struct of some task.
+ * cpuset_print_current_mems_allowed - prints current's cpuset and mems_allowed
  *
- * Description: Prints @task's name, cpuset name, and cached copy of its
+ * Description: Prints current's name, cpuset name, and cached copy of its
  * mems_allowed to the kernel log.
  */
-void cpuset_print_task_mems_allowed(struct task_struct *tsk)
+void cpuset_print_current_mems_allowed(void)
 {
 	struct cgroup *cgrp;
 
 	rcu_read_lock();
 
-	cgrp = task_cs(tsk)->css.cgroup;
-	pr_info("%s cpuset=", tsk->comm);
+	cgrp = task_cs(current)->css.cgroup;
+	pr_info("%s cpuset=", current->comm);
 	pr_cont_cgroup_name(cgrp);
-	pr_cont(" mems_allowed=%*pbl\n", nodemask_pr_args(&tsk->mems_allowed));
+	pr_cont(" mems_allowed=%*pbl\n",
+		nodemask_pr_args(&current->mems_allowed));
 
 	rcu_read_unlock();
 }