#include <asm/uaccess.h>
#include <linux/atomic.h>
#include <linux/mutex.h>
-#include <linux/workqueue.h>
#include <linux/cgroup.h>
#include <linux/wait.h>
/* user-configured CPUs and Memory Nodes allow to tasks */
cpumask_var_t cpus_allowed;
+ cpumask_var_t cpus_requested;
nodemask_t mems_allowed;
/* effective CPUs and Memory Nodes allow to tasks */
static DEFINE_MUTEX(cpuset_mutex);
static DEFINE_SPINLOCK(callback_lock);
+static struct workqueue_struct *cpuset_migrate_mm_wq;
+
/*
* CPU / memory hotplug is handled asynchronously.
*/
/*
* Return in pmask the portion of a cpusets's cpus_allowed that
* are online. If none are online, walk up the cpuset hierarchy
- * until we find one that does have some online cpus. The top
- * cpuset always has some cpus online.
+ * until we find one that does have some online cpus.
*
* One way or another, we guarantee to return some non-empty subset
* of cpu_online_mask.
*/
static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)
{
- while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask))
+ while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) {
cs = parent_cs(cs);
+ if (unlikely(!cs)) {
+ /*
+ * The top cpuset doesn't have any online cpu as a
+ * consequence of a race between cpuset_hotplug_work
+ * and cpu hotplug notifier. But we know the top
+ * cpuset's effective_cpus is on its way to to be
+ * identical to cpu_online_mask.
+ */
+ cpumask_copy(pmask, cpu_online_mask);
+ return;
+ }
+ }
cpumask_and(pmask, cs->effective_cpus, cpu_online_mask);
}
static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q)
{
- return cpumask_subset(p->cpus_allowed, q->cpus_allowed) &&
+ return cpumask_subset(p->cpus_requested, q->cpus_requested) &&
nodes_subset(p->mems_allowed, q->mems_allowed) &&
is_cpu_exclusive(p) <= is_cpu_exclusive(q) &&
is_mem_exclusive(p) <= is_mem_exclusive(q);
cpuset_for_each_child(c, css, par) {
if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) &&
c != cur &&
- cpumask_intersects(trial->cpus_allowed, c->cpus_allowed))
+ cpumask_intersects(trial->cpus_requested, c->cpus_requested))
goto out;
if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) &&
c != cur &&
if (!*buf) {
cpumask_clear(trialcs->cpus_allowed);
} else {
- retval = cpulist_parse(buf, trialcs->cpus_allowed);
+ retval = cpulist_parse(buf, trialcs->cpus_requested);
if (retval < 0)
return retval;
- if (!cpumask_subset(trialcs->cpus_allowed,
- top_cpuset.cpus_allowed))
+ if (!cpumask_subset(trialcs->cpus_requested, cpu_present_mask))
return -EINVAL;
+
+ cpumask_and(trialcs->cpus_allowed, trialcs->cpus_requested, cpu_active_mask);
}
/* Nothing to do if the cpus didn't change */
- if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed))
+ if (cpumask_equal(cs->cpus_requested, trialcs->cpus_requested))
return 0;
retval = validate_change(cs, trialcs);
spin_lock_irq(&callback_lock);
cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);
+ cpumask_copy(cs->cpus_requested, trialcs->cpus_requested);
spin_unlock_irq(&callback_lock);
/* use trialcs->cpus_allowed as a temp variable */
}
/*
- * 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();
+static void cpuset_post_attach(void)
+{
+ flush_workqueue(cpuset_migrate_mm_wq);
}
/*
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);
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);
(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;
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);
*/
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 task_struct *task;
struct task_struct *leader;
- struct cpuset *cs = css_cs(css);
+ 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 */
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
* sleep and should be moved outside migration path proper.
*/
cpuset_attach_nodemask_to = cs->effective_mems;
- cgroup_taskset_for_each_leader(leader, tset) {
+ cgroup_taskset_for_each_leader(leader, css, tset) {
struct mm_struct *mm = get_task_mm(leader);
if (mm) {
* @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);
}
}
mutex_unlock(&cpuset_mutex);
kernfs_unbreak_active_protection(of->kn);
css_put(&cs->css);
+ flush_workqueue(cpuset_migrate_mm_wq);
return retval ?: nbytes;
}
switch (type) {
case FILE_CPULIST:
- seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_allowed));
+ seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_requested));
break;
case FILE_MEMLIST:
seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->mems_allowed));
return ERR_PTR(-ENOMEM);
if (!alloc_cpumask_var(&cs->cpus_allowed, GFP_KERNEL))
goto free_cs;
+ if (!alloc_cpumask_var(&cs->cpus_requested, GFP_KERNEL))
+ goto free_allowed;
if (!alloc_cpumask_var(&cs->effective_cpus, GFP_KERNEL))
- goto free_cpus;
+ goto free_requested;
set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
cpumask_clear(cs->cpus_allowed);
+ cpumask_clear(cs->cpus_requested);
nodes_clear(cs->mems_allowed);
cpumask_clear(cs->effective_cpus);
nodes_clear(cs->effective_mems);
return &cs->css;
-free_cpus:
+free_requested:
+ free_cpumask_var(cs->cpus_requested);
+free_allowed:
free_cpumask_var(cs->cpus_allowed);
free_cs:
kfree(cs);
cs->mems_allowed = parent->mems_allowed;
cs->effective_mems = parent->mems_allowed;
cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
+ cpumask_copy(cs->cpus_requested, parent->cpus_requested);
cpumask_copy(cs->effective_cpus, parent->cpus_allowed);
spin_unlock_irq(&callback_lock);
out_unlock:
free_cpumask_var(cs->effective_cpus);
free_cpumask_var(cs->cpus_allowed);
+ free_cpumask_var(cs->cpus_requested);
kfree(cs);
}
mutex_unlock(&cpuset_mutex);
}
+/*
+ * 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.
+ */
+void cpuset_fork(struct task_struct *task, void *priv)
+{
+ if (task_css_is_root(task, cpuset_cgrp_id))
+ return;
+
+ set_cpus_allowed_ptr(task, ¤t->cpus_allowed);
+ task->mems_allowed = current->mems_allowed;
+}
+
struct cgroup_subsys cpuset_cgrp_subsys = {
.css_alloc = cpuset_css_alloc,
.css_online = cpuset_css_online,
.can_attach = cpuset_can_attach,
.cancel_attach = cpuset_cancel_attach,
.attach = cpuset_attach,
+ .post_attach = cpuset_post_attach,
.bind = cpuset_bind,
+ .fork = cpuset_fork,
.legacy_cftypes = files,
.early_init = 1,
};
BUG();
if (!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL))
BUG();
+ if (!alloc_cpumask_var(&top_cpuset.cpus_requested, GFP_KERNEL))
+ BUG();
cpumask_setall(top_cpuset.cpus_allowed);
+ cpumask_setall(top_cpuset.cpus_requested);
nodes_setall(top_cpuset.mems_allowed);
cpumask_setall(top_cpuset.effective_cpus);
nodes_setall(top_cpuset.effective_mems);
goto retry;
}
- cpumask_and(&new_cpus, cs->cpus_allowed, parent_cs(cs)->effective_cpus);
+ cpumask_and(&new_cpus, cs->cpus_requested, parent_cs(cs)->effective_cpus);
nodes_and(new_mems, cs->mems_allowed, parent_cs(cs)->effective_mems);
cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus);
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);
}
/**