/* for custom sched domain */
int relax_domain_level;
- /* used for walking a cpuset heirarchy */
+ /* used for walking a cpuset hierarchy */
struct list_head stack_list;
};
* users. If someone tries to mount the "cpuset" filesystem, we
* silently switch it to mount "cgroup" instead
*/
-static int cpuset_get_sb(struct file_system_type *fs_type,
- int flags, const char *unused_dev_name,
- void *data, struct vfsmount *mnt)
+static struct dentry *cpuset_mount(struct file_system_type *fs_type,
+ int flags, const char *unused_dev_name, void *data)
{
struct file_system_type *cgroup_fs = get_fs_type("cgroup");
- int ret = -ENODEV;
+ struct dentry *ret = ERR_PTR(-ENODEV);
if (cgroup_fs) {
char mountopts[] =
"cpuset,noprefix,"
"release_agent=/sbin/cpuset_release_agent";
- ret = cgroup_fs->get_sb(cgroup_fs, flags,
- unused_dev_name, mountopts, mnt);
+ ret = cgroup_fs->mount(cgroup_fs, flags,
+ unused_dev_name, mountopts);
put_filesystem(cgroup_fs);
}
return ret;
static struct file_system_type cpuset_fs_type = {
.name = "cpuset",
- .get_sb = cpuset_get_sb,
+ .mount = cpuset_mount,
};
/*
* In order to avoid seeing no nodes if the old and new nodes are disjoint,
* we structure updates as setting all new allowed nodes, then clearing newly
* disallowed ones.
- *
- * Called with task's alloc_lock held
*/
static void cpuset_change_task_nodemask(struct task_struct *tsk,
nodemask_t *newmems)
{
+repeat:
+ /*
+ * Allow tasks that have access to memory reserves because they have
+ * been OOM killed to get memory anywhere.
+ */
+ if (unlikely(test_thread_flag(TIF_MEMDIE)))
+ return;
+ if (current->flags & PF_EXITING) /* Let dying task have memory */
+ return;
+
+ task_lock(tsk);
nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
- mpol_rebind_task(tsk, &tsk->mems_allowed);
- mpol_rebind_task(tsk, newmems);
+ mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
+
+
+ /*
+ * ensure checking ->mems_allowed_change_disable after setting all new
+ * allowed nodes.
+ *
+ * the read-side task can see an nodemask with new allowed nodes and
+ * old allowed nodes. and if it allocates page when cpuset clears newly
+ * disallowed ones continuous, it can see the new allowed bits.
+ *
+ * And if setting all new allowed nodes is after the checking, setting
+ * all new allowed nodes and clearing newly disallowed ones will be done
+ * continuous, and the read-side task may find no node to alloc page.
+ */
+ smp_mb();
+
+ /*
+ * Allocation of memory is very fast, we needn't sleep when waiting
+ * for the read-side.
+ */
+ while (ACCESS_ONCE(tsk->mems_allowed_change_disable)) {
+ task_unlock(tsk);
+ if (!task_curr(tsk))
+ yield();
+ goto repeat;
+ }
+
+ /*
+ * ensure checking ->mems_allowed_change_disable before clearing all new
+ * disallowed nodes.
+ *
+ * if clearing newly disallowed bits before the checking, the read-side
+ * task may find no node to alloc page.
+ */
+ smp_mb();
+
+ mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2);
tsk->mems_allowed = *newmems;
+ task_unlock(tsk);
}
/*
struct cpuset *cs;
int migrate;
const nodemask_t *oldmem = scan->data;
- NODEMASK_ALLOC(nodemask_t, newmems, GFP_KERNEL);
-
- if (!newmems)
- return;
+ static nodemask_t newmems; /* protected by cgroup_mutex */
cs = cgroup_cs(scan->cg);
- guarantee_online_mems(cs, newmems);
-
- task_lock(p);
- cpuset_change_task_nodemask(p, newmems);
- task_unlock(p);
+ guarantee_online_mems(cs, &newmems);
- NODEMASK_FREE(newmems);
+ cpuset_change_task_nodemask(p, &newmems);
mm = get_task_mm(p);
if (!mm)
static int update_relax_domain_level(struct cpuset *cs, s64 val)
{
#ifdef CONFIG_SMP
- if (val < -1 || val >= SD_LV_MAX)
+ if (val < -1 || val >= sched_domain_level_max)
return -EINVAL;
#endif
return val;
}
-/* Protected by cgroup_lock */
-static cpumask_var_t cpus_attach;
-
/* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */
static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont,
- struct task_struct *tsk, bool threadgroup)
+ struct task_struct *tsk)
{
- int ret;
struct cpuset *cs = cgroup_cs(cont);
if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
if (tsk->flags & PF_THREAD_BOUND)
return -EINVAL;
- ret = security_task_setscheduler(tsk, 0, NULL);
- if (ret)
- return ret;
- if (threadgroup) {
- struct task_struct *c;
-
- rcu_read_lock();
- list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
- ret = security_task_setscheduler(c, 0, NULL);
- if (ret) {
- rcu_read_unlock();
- return ret;
- }
- }
- rcu_read_unlock();
- }
return 0;
}
-static void cpuset_attach_task(struct task_struct *tsk, nodemask_t *to,
- struct cpuset *cs)
+static int cpuset_can_attach_task(struct cgroup *cgrp, struct task_struct *task)
+{
+ return security_task_setscheduler(task);
+}
+
+/*
+ * Protected by cgroup_lock. The nodemasks must be stored globally because
+ * dynamically allocating them is not allowed in pre_attach, and they must
+ * persist among pre_attach, attach_task, and attach.
+ */
+static cpumask_var_t cpus_attach;
+static nodemask_t cpuset_attach_nodemask_from;
+static nodemask_t cpuset_attach_nodemask_to;
+
+/* Set-up work for before attaching each task. */
+static void cpuset_pre_attach(struct cgroup *cont)
+{
+ struct cpuset *cs = cgroup_cs(cont);
+
+ if (cs == &top_cpuset)
+ cpumask_copy(cpus_attach, cpu_possible_mask);
+ else
+ guarantee_online_cpus(cs, cpus_attach);
+
+ guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
+}
+
+/* Per-thread attachment work. */
+static void cpuset_attach_task(struct cgroup *cont, struct task_struct *tsk)
{
int err;
+ struct cpuset *cs = cgroup_cs(cont);
+
/*
* can_attach beforehand should guarantee that this doesn't fail.
* TODO: have a better way to handle failure here
err = set_cpus_allowed_ptr(tsk, cpus_attach);
WARN_ON_ONCE(err);
- task_lock(tsk);
- cpuset_change_task_nodemask(tsk, to);
- task_unlock(tsk);
+ cpuset_change_task_nodemask(tsk, &cpuset_attach_nodemask_to);
cpuset_update_task_spread_flag(cs, tsk);
-
}
static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont,
- struct cgroup *oldcont, struct task_struct *tsk,
- bool threadgroup)
+ struct cgroup *oldcont, struct task_struct *tsk)
{
struct mm_struct *mm;
struct cpuset *cs = cgroup_cs(cont);
struct cpuset *oldcs = cgroup_cs(oldcont);
- NODEMASK_ALLOC(nodemask_t, from, GFP_KERNEL);
- NODEMASK_ALLOC(nodemask_t, to, GFP_KERNEL);
-
- if (from == NULL || to == NULL)
- goto alloc_fail;
-
- if (cs == &top_cpuset) {
- cpumask_copy(cpus_attach, cpu_possible_mask);
- } else {
- guarantee_online_cpus(cs, cpus_attach);
- }
- guarantee_online_mems(cs, to);
-
- /* do per-task migration stuff possibly for each in the threadgroup */
- cpuset_attach_task(tsk, to, cs);
- if (threadgroup) {
- struct task_struct *c;
- rcu_read_lock();
- list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
- cpuset_attach_task(c, to, cs);
- }
- rcu_read_unlock();
- }
- /* change mm; only needs to be done once even if threadgroup */
- *from = oldcs->mems_allowed;
- *to = cs->mems_allowed;
+ /*
+ * Change mm, possibly for multiple threads in a threadgroup. This is
+ * expensive and may sleep.
+ */
+ cpuset_attach_nodemask_from = oldcs->mems_allowed;
+ cpuset_attach_nodemask_to = cs->mems_allowed;
mm = get_task_mm(tsk);
if (mm) {
- mpol_rebind_mm(mm, to);
+ mpol_rebind_mm(mm, &cpuset_attach_nodemask_to);
if (is_memory_migrate(cs))
- cpuset_migrate_mm(mm, from, to);
+ cpuset_migrate_mm(mm, &cpuset_attach_nodemask_from,
+ &cpuset_attach_nodemask_to);
mmput(mm);
}
-
-alloc_fail:
- NODEMASK_FREE(from);
- NODEMASK_FREE(to);
}
/* The various types of files and directories in a cpuset file system */
return -ENODEV;
trialcs = alloc_trial_cpuset(cs);
- if (!trialcs)
- return -ENOMEM;
+ if (!trialcs) {
+ retval = -ENOMEM;
+ goto out;
+ }
switch (cft->private) {
case FILE_CPULIST:
}
free_trial_cpuset(trialcs);
+out:
cgroup_unlock();
return retval;
}
* across a page fault.
*/
-static int cpuset_sprintf_cpulist(char *page, struct cpuset *cs)
+static size_t cpuset_sprintf_cpulist(char *page, struct cpuset *cs)
{
- int ret;
+ size_t count;
mutex_lock(&callback_mutex);
- ret = cpulist_scnprintf(page, PAGE_SIZE, cs->cpus_allowed);
+ count = cpulist_scnprintf(page, PAGE_SIZE, cs->cpus_allowed);
mutex_unlock(&callback_mutex);
- return ret;
+ return count;
}
-static int cpuset_sprintf_memlist(char *page, struct cpuset *cs)
+static size_t cpuset_sprintf_memlist(char *page, struct cpuset *cs)
{
- NODEMASK_ALLOC(nodemask_t, mask, GFP_KERNEL);
- int retval;
-
- if (mask == NULL)
- return -ENOMEM;
+ size_t count;
mutex_lock(&callback_mutex);
- *mask = cs->mems_allowed;
+ count = nodelist_scnprintf(page, PAGE_SIZE, cs->mems_allowed);
mutex_unlock(&callback_mutex);
- retval = nodelist_scnprintf(page, PAGE_SIZE, *mask);
-
- NODEMASK_FREE(mask);
-
- return retval;
+ return count;
}
static ssize_t cpuset_common_file_read(struct cgroup *cont,
}
/*
- * post_clone() is called at the end of cgroup_clone().
- * 'cgroup' was just created automatically as a result of
- * a cgroup_clone(), and the current task is about to
- * be moved into 'cgroup'.
+ * 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
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;
}
.create = cpuset_create,
.destroy = cpuset_destroy,
.can_attach = cpuset_can_attach,
+ .can_attach_task = cpuset_can_attach_task,
+ .pre_attach = cpuset_pre_attach,
+ .attach_task = cpuset_attach_task,
.attach = cpuset_attach,
.populate = cpuset_populate,
.post_clone = cpuset_post_clone,
struct cpuset *cp; /* scans cpusets being updated */
struct cpuset *child; /* scans child cpusets of cp */
struct cgroup *cont;
- NODEMASK_ALLOC(nodemask_t, oldmems, GFP_KERNEL);
-
- if (oldmems == NULL)
- return;
+ static nodemask_t oldmems; /* protected by cgroup_mutex */
list_add_tail((struct list_head *)&root->stack_list, &queue);
nodes_subset(cp->mems_allowed, node_states[N_HIGH_MEMORY]))
continue;
- *oldmems = cp->mems_allowed;
+ oldmems = cp->mems_allowed;
/* Remove offline cpus and mems from this cpuset. */
mutex_lock(&callback_mutex);
remove_tasks_in_empty_cpuset(cp);
else {
update_tasks_cpumask(cp, NULL);
- update_tasks_nodemask(cp, oldmems, NULL);
+ update_tasks_nodemask(cp, &oldmems, NULL);
}
}
- NODEMASK_FREE(oldmems);
}
/*
* but making no active use of cpusets.
*
* This routine ensures that top_cpuset.cpus_allowed tracks
- * cpu_online_map on each CPU hotplug (cpuhp) event.
+ * cpu_active_mask on each CPU hotplug (cpuhp) event.
*
* Called within get_online_cpus(). Needs to call cgroup_lock()
* before calling generate_sched_domains().
*/
-static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
- unsigned long phase, void *unused_cpu)
+void cpuset_update_active_cpus(void)
{
struct sched_domain_attr *attr;
cpumask_var_t *doms;
int ndoms;
- switch (phase) {
- case CPU_ONLINE:
- case CPU_ONLINE_FROZEN:
- case CPU_DOWN_PREPARE:
- case CPU_DOWN_PREPARE_FROZEN:
- case CPU_DOWN_FAILED:
- case CPU_DOWN_FAILED_FROZEN:
- break;
-
- default:
- return NOTIFY_DONE;
- }
-
cgroup_lock();
mutex_lock(&callback_mutex);
cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
/* Have scheduler rebuild the domains */
partition_sched_domains(ndoms, doms, attr);
-
- return NOTIFY_OK;
}
#ifdef CONFIG_MEMORY_HOTPLUG
static int cpuset_track_online_nodes(struct notifier_block *self,
unsigned long action, void *arg)
{
- NODEMASK_ALLOC(nodemask_t, oldmems, GFP_KERNEL);
-
- if (oldmems == NULL)
- return NOTIFY_DONE;
+ static nodemask_t oldmems; /* protected by cgroup_mutex */
cgroup_lock();
switch (action) {
case MEM_ONLINE:
- *oldmems = top_cpuset.mems_allowed;
+ oldmems = top_cpuset.mems_allowed;
mutex_lock(&callback_mutex);
top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
mutex_unlock(&callback_mutex);
- update_tasks_nodemask(&top_cpuset, oldmems, NULL);
+ update_tasks_nodemask(&top_cpuset, &oldmems, NULL);
break;
case MEM_OFFLINE:
/*
}
cgroup_unlock();
- NODEMASK_FREE(oldmems);
return NOTIFY_OK;
}
#endif
cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
- hotcpu_notifier(cpuset_track_online_cpus, 0);
hotplug_memory_notifier(cpuset_track_online_nodes, 10);
cpuset_wq = create_singlethread_workqueue("cpuset");
mutex_unlock(&callback_mutex);
}
+int cpuset_cpus_allowed_fallback(struct task_struct *tsk)
+{
+ const struct cpuset *cs;
+ int cpu;
+
+ rcu_read_lock();
+ cs = task_cs(tsk);
+ if (cs)
+ do_set_cpus_allowed(tsk, cs->cpus_allowed);
+ rcu_read_unlock();
+
+ /*
+ * We own tsk->cpus_allowed, nobody can change it under us.
+ *
+ * But we used cs && cs->cpus_allowed lockless and thus can
+ * race with cgroup_attach_task() or update_cpumask() and get
+ * the wrong tsk->cpus_allowed. However, both cases imply the
+ * subsequent cpuset_change_cpumask()->set_cpus_allowed_ptr()
+ * which takes task_rq_lock().
+ *
+ * If we are called after it dropped the lock we must see all
+ * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary
+ * set any mask even if it is not right from task_cs() pov,
+ * the pending set_cpus_allowed_ptr() will fix things.
+ */
+
+ cpu = cpumask_any_and(&tsk->cpus_allowed, cpu_active_mask);
+ if (cpu >= nr_cpu_ids) {
+ /*
+ * Either tsk->cpus_allowed is wrong (see above) or it
+ * is actually empty. The latter case is only possible
+ * if we are racing with remove_tasks_in_empty_cpuset().
+ * Like above we can temporary set any mask and rely on
+ * set_cpus_allowed_ptr() as synchronization point.
+ */
+ do_set_cpus_allowed(tsk, cpu_possible_mask);
+ cpu = cpumask_any(cpu_active_mask);
+ }
+
+ return cpu;
+}
+
void cpuset_init_current_mems_allowed(void)
{
nodes_setall(current->mems_allowed);
}
/**
- * cpuset_mem_spread_node() - On which node to begin search for a page
+ * cpuset_mem_spread_node() - On which node to begin search for a file page
+ * cpuset_slab_spread_node() - On which node to begin search for a slab page
*
* If a task is marked PF_SPREAD_PAGE or PF_SPREAD_SLAB (as for
* tasks in a cpuset with is_spread_page or is_spread_slab set),
* See kmem_cache_alloc_node().
*/
-int cpuset_mem_spread_node(void)
+static int cpuset_spread_node(int *rotor)
{
int node;
- node = next_node(current->cpuset_mem_spread_rotor, current->mems_allowed);
+ node = next_node(*rotor, current->mems_allowed);
if (node == MAX_NUMNODES)
node = first_node(current->mems_allowed);
- current->cpuset_mem_spread_rotor = node;
+ *rotor = node;
return node;
}
+
+int cpuset_mem_spread_node(void)
+{
+ return cpuset_spread_node(¤t->cpuset_mem_spread_rotor);
+}
+
+int cpuset_slab_spread_node(void)
+{
+ return cpuset_spread_node(¤t->cpuset_slab_spread_rotor);
+}
+
EXPORT_SYMBOL_GPL(cpuset_mem_spread_node);
/**