From 070b57fcacc9dfc23a180290079078373fb697e1 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Sun, 9 Jun 2013 17:15:22 +0800 Subject: [PATCH] cpuset: introduce effective_{cpumask|nodemask}_cpuset() effective_cpumask_cpuset() returns an ancestor cpuset which has non-empty cpumask. If a cpuset is empty and the tasks in it need to update their cpus_allowed, they take on the ancestor cpuset's cpumask. This currently won't change any behavior, but it will later allow us to keep tasks in empty cpusets. Signed-off-by: Li Zefan Signed-off-by: Tejun Heo --- kernel/cpuset.c | 76 ++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 65 insertions(+), 11 deletions(-) diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 2b4554588a04..82ac1f862cbc 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -791,6 +791,45 @@ void rebuild_sched_domains(void) mutex_unlock(&cpuset_mutex); } +/* + * effective_cpumask_cpuset - return nearest ancestor with non-empty cpus + * @cs: the cpuset in interest + * + * A cpuset's effective cpumask is the cpumask of the nearest ancestor + * with non-empty cpus. We use effective cpumask whenever: + * - we update tasks' cpus_allowed. (they take on the ancestor's cpumask + * if the cpuset they reside in has no cpus) + * - we want to retrieve task_cs(tsk)'s cpus_allowed. + * + * Called with cpuset_mutex held. cpuset_cpus_allowed_fallback() is an + * exception. See comments there. + */ +static struct cpuset *effective_cpumask_cpuset(struct cpuset *cs) +{ + while (cpumask_empty(cs->cpus_allowed)) + cs = parent_cs(cs); + return cs; +} + +/* + * effective_nodemask_cpuset - return nearest ancestor with non-empty mems + * @cs: the cpuset in interest + * + * A cpuset's effective nodemask is the nodemask of the nearest ancestor + * with non-empty memss. We use effective nodemask whenever: + * - we update tasks' mems_allowed. (they take on the ancestor's nodemask + * if the cpuset they reside in has no mems) + * - we want to retrieve task_cs(tsk)'s mems_allowed. + * + * Called with cpuset_mutex held. + */ +static struct cpuset *effective_nodemask_cpuset(struct cpuset *cs) +{ + while (nodes_empty(cs->mems_allowed)) + cs = parent_cs(cs); + return cs; +} + /** * cpuset_change_cpumask - make a task's cpus_allowed the same as its cpuset's * @tsk: task to test @@ -805,7 +844,10 @@ void rebuild_sched_domains(void) static void cpuset_change_cpumask(struct task_struct *tsk, struct cgroup_scanner *scan) { - set_cpus_allowed_ptr(tsk, ((cgroup_cs(scan->cg))->cpus_allowed)); + struct cpuset *cpus_cs; + + cpus_cs = effective_cpumask_cpuset(cgroup_cs(scan->cg)); + set_cpus_allowed_ptr(tsk, cpus_cs->cpus_allowed); } /** @@ -920,12 +962,14 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to) { struct task_struct *tsk = current; + struct cpuset *mems_cs; tsk->mems_allowed = *to; do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL); - guarantee_online_mems(task_cs(tsk),&tsk->mems_allowed); + mems_cs = effective_nodemask_cpuset(task_cs(tsk)); + guarantee_online_mems(mems_cs, &tsk->mems_allowed); } /* @@ -1018,10 +1062,11 @@ static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap) { static nodemask_t newmems; /* protected by cpuset_mutex */ struct cgroup_scanner scan; + struct cpuset *mems_cs = effective_nodemask_cpuset(cs); cpuset_being_rebound = cs; /* causes mpol_dup() rebind */ - guarantee_online_mems(cs, &newmems); + guarantee_online_mems(mems_cs, &newmems); scan.cg = cs->css.cgroup; scan.test_task = NULL; @@ -1405,6 +1450,8 @@ static void cpuset_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) struct cgroup *oldcgrp = cgroup_taskset_cur_cgroup(tset); struct cpuset *cs = cgroup_cs(cgrp); struct cpuset *oldcs = cgroup_cs(oldcgrp); + struct cpuset *cpus_cs = effective_cpumask_cpuset(cs); + struct cpuset *mems_cs = effective_nodemask_cpuset(cs); mutex_lock(&cpuset_mutex); @@ -1412,9 +1459,9 @@ static void cpuset_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) if (cs == &top_cpuset) cpumask_copy(cpus_attach, cpu_possible_mask); else - guarantee_online_cpus(cs, cpus_attach); + guarantee_online_cpus(cpus_cs, cpus_attach); - guarantee_online_mems(cs, &cpuset_attach_nodemask_to); + guarantee_online_mems(mems_cs, &cpuset_attach_nodemask_to); cgroup_taskset_for_each(task, cgrp, tset) { /* @@ -1434,9 +1481,11 @@ static void cpuset_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) cpuset_attach_nodemask_to = cs->mems_allowed; mm = get_task_mm(leader); if (mm) { + struct cpuset *mems_oldcs = effective_nodemask_cpuset(oldcs); + mpol_rebind_mm(mm, &cpuset_attach_nodemask_to); if (is_memory_migrate(cs)) - cpuset_migrate_mm(mm, &oldcs->mems_allowed, + cpuset_migrate_mm(mm, &mems_oldcs->mems_allowed, &cpuset_attach_nodemask_to); mmput(mm); } @@ -2186,20 +2235,23 @@ void __init cpuset_init_smp(void) void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) { + struct cpuset *cpus_cs; + mutex_lock(&callback_mutex); task_lock(tsk); - guarantee_online_cpus(task_cs(tsk), pmask); + cpus_cs = effective_cpumask_cpuset(task_cs(tsk)); + guarantee_online_cpus(cpus_cs, pmask); task_unlock(tsk); mutex_unlock(&callback_mutex); } void cpuset_cpus_allowed_fallback(struct task_struct *tsk) { - const struct cpuset *cs; + const struct cpuset *cpus_cs; rcu_read_lock(); - cs = task_cs(tsk); - do_set_cpus_allowed(tsk, cs->cpus_allowed); + cpus_cs = effective_cpumask_cpuset(task_cs(tsk)); + do_set_cpus_allowed(tsk, cpus_cs->cpus_allowed); rcu_read_unlock(); /* @@ -2238,11 +2290,13 @@ void cpuset_init_current_mems_allowed(void) nodemask_t cpuset_mems_allowed(struct task_struct *tsk) { + struct cpuset *mems_cs; nodemask_t mask; mutex_lock(&callback_mutex); task_lock(tsk); - guarantee_online_mems(task_cs(tsk), &mask); + mems_cs = effective_nodemask_cpuset(task_cs(tsk)); + guarantee_online_mems(mems_cs, &mask); task_unlock(tsk); mutex_unlock(&callback_mutex);