Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 33ad801d authored by Li Zefan's avatar Li Zefan Committed by Tejun Heo
Browse files

cpuset: record old_mems_allowed in struct cpuset 



When we update a cpuset's mems_allowed and thus update tasks'
mems_allowed, it's required to pass the old mems_allowed and new
mems_allowed to cpuset_migrate_mm().

Currently we save old mems_allowed in a temp local variable before
changing cpuset->mems_allowed. This patch changes it by saving
old mems_allowed in cpuset->old_mems_allowed.

This currently won't change any behavior, but it will later allow
us to keep tasks in empty cpusets.

v3: restored "cpuset_attach_nodemask_to = cs->mems_allowed"

Signed-off-by: default avatarLi Zefan <lizefan@huawei.com>
Signed-off-by: default avatarTejun Heo <tj@kernel.org>
parent 388afd85

kernel/cpuset.c

+36 −25
Original line number Original line Diff line number Diff line
@@ -88,6 +88,18 @@ struct cpuset { 
	cpumask_var_t cpus_allowed;	/* CPUs allowed to tasks in cpuset */

	cpumask_var_t cpus_allowed;	/* CPUs allowed to tasks in cpuset */

	nodemask_t mems_allowed;	/* Memory Nodes allowed to tasks */

	nodemask_t mems_allowed;	/* Memory Nodes allowed to tasks */





	/*

	 * This is old Memory Nodes tasks took on.

	 *

	 * - top_cpuset.old_mems_allowed is initialized to mems_allowed.

	 * - A new cpuset's old_mems_allowed is initialized when some

	 *   task is moved into it.

	 * - old_mems_allowed is used in cpuset_migrate_mm() when we change

	 *   cpuset.mems_allowed and have tasks' nodemask updated, and

	 *   then old_mems_allowed is updated to mems_allowed.

	 */

	nodemask_t old_mems_allowed;



	struct fmeter fmeter;		/* memory_pressure filter */

	struct fmeter fmeter;		/* memory_pressure filter */





	/*

	/*
@@ -972,16 +984,12 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk, 
static void cpuset_change_nodemask(struct task_struct *p,

static void cpuset_change_nodemask(struct task_struct *p,

				   struct cgroup_scanner *scan)

				   struct cgroup_scanner *scan)

{

{

	struct cpuset *cs = cgroup_cs(scan->cg);

	struct mm_struct *mm;

	struct mm_struct *mm;

	struct cpuset *cs;

	int migrate;

	int migrate;

	const nodemask_t *oldmem = scan->data;

	nodemask_t *newmems = scan->data;

	static nodemask_t newmems;	/* protected by cpuset_mutex */



	cs = cgroup_cs(scan->cg);

	guarantee_online_mems(cs, &newmems);





	cpuset_change_task_nodemask(p, &newmems);

	cpuset_change_task_nodemask(p, newmems);





	mm = get_task_mm(p);

	mm = get_task_mm(p);

	if (!mm)

	if (!mm)
@@ -991,7 +999,7 @@ static void cpuset_change_nodemask(struct task_struct *p, 




	mpol_rebind_mm(mm, &cs->mems_allowed);

	mpol_rebind_mm(mm, &cs->mems_allowed);

	if (migrate)

	if (migrate)

		cpuset_migrate_mm(mm, oldmem, &cs->mems_allowed);

		cpuset_migrate_mm(mm, &cs->old_mems_allowed, newmems);

	mmput(mm);

	mmput(mm);

}

}
@@ -1000,25 +1008,26 @@ static void *cpuset_being_rebound; 
/**

/**

 * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset.

 * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset.

 * @cs: the cpuset in which each task's mems_allowed mask needs to be changed

 * @cs: the cpuset in which each task's mems_allowed mask needs to be changed

 * @oldmem: old mems_allowed of cpuset cs

 * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks()

 * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks()

 *

 *

 * Called with cpuset_mutex held

 * Called with cpuset_mutex held

 * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0

 * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0

 * if @heap != NULL.

 * if @heap != NULL.

 */

 */

static void update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem,

static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap)

				 struct ptr_heap *heap)

{

{

	static nodemask_t newmems;	/* protected by cpuset_mutex */

	struct cgroup_scanner scan;

	struct cgroup_scanner scan;





	cpuset_being_rebound = cs;		/* causes mpol_dup() rebind */

	cpuset_being_rebound = cs;		/* causes mpol_dup() rebind */





	guarantee_online_mems(cs, &newmems);



	scan.cg = cs->css.cgroup;

	scan.cg = cs->css.cgroup;

	scan.test_task = NULL;

	scan.test_task = NULL;

	scan.process_task = cpuset_change_nodemask;

	scan.process_task = cpuset_change_nodemask;

	scan.heap = heap;

	scan.heap = heap;

	scan.data = (nodemask_t *)oldmem;

	scan.data = &newmems;





	/*

	/*

	 * The mpol_rebind_mm() call takes mmap_sem, which we couldn't

	 * The mpol_rebind_mm() call takes mmap_sem, which we couldn't
@@ -1032,6 +1041,12 @@ static void update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem, 
	 */

	 */

	cgroup_scan_tasks(&scan);

	cgroup_scan_tasks(&scan);





	/*

	 * All the tasks' nodemasks have been updated, update

	 * cs->old_mems_allowed.

	 */

	cs->old_mems_allowed = newmems;



	/* We're done rebinding vmas to this cpuset's new mems_allowed. */

	/* We're done rebinding vmas to this cpuset's new mems_allowed. */

	cpuset_being_rebound = NULL;

	cpuset_being_rebound = NULL;

}

}
@@ -1052,13 +1067,9 @@ static void update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem, 
static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,

static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,

			   const char *buf)

			   const char *buf)

{

{

	NODEMASK_ALLOC(nodemask_t, oldmem, GFP_KERNEL);

	int retval;

	int retval;

	struct ptr_heap heap;

	struct ptr_heap heap;





	if (!oldmem)

		return -ENOMEM;



	/*

	/*

	 * top_cpuset.mems_allowed tracks node_stats[N_MEMORY];

	 * top_cpuset.mems_allowed tracks node_stats[N_MEMORY];

	 * it's read-only

	 * it's read-only
@@ -1087,8 +1098,8 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, 
			goto done;

			goto done;

		}

		}

	}

	}

	*oldmem = cs->mems_allowed;



	if (nodes_equal(*oldmem, trialcs->mems_allowed)) {

	if (nodes_equal(cs->mems_allowed, trialcs->mems_allowed)) {

		retval = 0;		/* Too easy - nothing to do */

		retval = 0;		/* Too easy - nothing to do */

		goto done;

		goto done;

	}

	}
@@ -1104,11 +1115,10 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, 
	cs->mems_allowed = trialcs->mems_allowed;

	cs->mems_allowed = trialcs->mems_allowed;

	mutex_unlock(&callback_mutex);

	mutex_unlock(&callback_mutex);





	update_tasks_nodemask(cs, oldmem, &heap);

	update_tasks_nodemask(cs, &heap);





	heap_free(&heap);

	heap_free(&heap);

done:

done:

	NODEMASK_FREE(oldmem);

	return retval;

	return retval;

}

}
@@ -1431,6 +1441,8 @@ static void cpuset_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) 
		mmput(mm);

		mmput(mm);

	}

	}





	cs->old_mems_allowed = cpuset_attach_nodemask_to;



	cs->attach_in_progress--;

	cs->attach_in_progress--;

	if (!cs->attach_in_progress)

	if (!cs->attach_in_progress)

		wake_up(&cpuset_attach_wq);

		wake_up(&cpuset_attach_wq);
@@ -1985,7 +1997,7 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs) 
static void cpuset_hotplug_update_tasks(struct cpuset *cs)

static void cpuset_hotplug_update_tasks(struct cpuset *cs)

{

{

	static cpumask_t off_cpus;

	static cpumask_t off_cpus;

	static nodemask_t off_mems, tmp_mems;

	static nodemask_t off_mems;

	bool is_empty;

	bool is_empty;





retry:

retry:
@@ -2015,11 +2027,10 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs) 




	/* remove offline mems from @cs */

	/* remove offline mems from @cs */

	if (!nodes_empty(off_mems)) {

	if (!nodes_empty(off_mems)) {

		tmp_mems = cs->mems_allowed;

		mutex_lock(&callback_mutex);

		mutex_lock(&callback_mutex);

		nodes_andnot(cs->mems_allowed, cs->mems_allowed, off_mems);

		nodes_andnot(cs->mems_allowed, cs->mems_allowed, off_mems);

		mutex_unlock(&callback_mutex);

		mutex_unlock(&callback_mutex);

		update_tasks_nodemask(cs, &tmp_mems, NULL);

		update_tasks_nodemask(cs, NULL);

	}

	}





	is_empty = cpumask_empty(cs->cpus_allowed) ||

	is_empty = cpumask_empty(cs->cpus_allowed) ||
@@ -2083,11 +2094,10 @@ static void cpuset_hotplug_workfn(struct work_struct *work) 




	/* synchronize mems_allowed to N_MEMORY */

	/* synchronize mems_allowed to N_MEMORY */

	if (mems_updated) {

	if (mems_updated) {

		tmp_mems = top_cpuset.mems_allowed;

		mutex_lock(&callback_mutex);

		mutex_lock(&callback_mutex);

		top_cpuset.mems_allowed = new_mems;

		top_cpuset.mems_allowed = new_mems;

		mutex_unlock(&callback_mutex);

		mutex_unlock(&callback_mutex);

		update_tasks_nodemask(&top_cpuset, &tmp_mems, NULL);

		update_tasks_nodemask(&top_cpuset, NULL);

	}

	}





	mutex_unlock(&cpuset_mutex);

	mutex_unlock(&cpuset_mutex);
@@ -2158,6 +2168,7 @@ void __init cpuset_init_smp(void) 
{

{

	cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);

	cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);

	top_cpuset.mems_allowed = node_states[N_MEMORY];

	top_cpuset.mems_allowed = node_states[N_MEMORY];

	top_cpuset.old_mems_allowed = top_cpuset.mems_allowed;





	register_hotmemory_notifier(&cpuset_track_online_nodes_nb);

	register_hotmemory_notifier(&cpuset_track_online_nodes_nb);

}

}