summaryrefslogtreecommitdiff
path: root/kernel/cgroup
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-08-30 13:42:10 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-08-30 13:42:10 -0700
commit5d3c0db4598c5de511824649df2aa976259cf10a (patch)
tree6b2cd47c837f566287b9a8ff39731d2da38ffdfd /kernel/cgroup
parent230bda0873a6ce4d089afde22aa5e487888ddebb (diff)
parentb542e383d8c005f06a131e2b40d5889b812f19c6 (diff)
downloadlwn-5d3c0db4598c5de511824649df2aa976259cf10a.tar.gz
lwn-5d3c0db4598c5de511824649df2aa976259cf10a.zip
Merge tag 'sched-core-2021-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar: - The biggest change in this cycle is scheduler support for asymmetric scheduling affinity, to support the execution of legacy 32-bit tasks on AArch32 systems that also have 64-bit-only CPUs. Architectures can fill in this functionality by defining their own task_cpu_possible_mask(p). When this is done, the scheduler will make sure the task will only be scheduled on CPUs that support it. (The actual arm64 specific changes are not part of this tree.) For other architectures there will be no change in functionality. - Add cgroup SCHED_IDLE support - Increase node-distance flexibility & delay determining it until a CPU is brought online. (This enables platforms where node distance isn't final until the CPU is only.) - Deadline scheduler enhancements & fixes - Misc fixes & cleanups. * tag 'sched-core-2021-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (27 commits) eventfd: Make signal recursion protection a task bit sched/fair: Mark tg_is_idle() an inline in the !CONFIG_FAIR_GROUP_SCHED case sched: Introduce dl_task_check_affinity() to check proposed affinity sched: Allow task CPU affinity to be restricted on asymmetric systems sched: Split the guts of sched_setaffinity() into a helper function sched: Introduce task_struct::user_cpus_ptr to track requested affinity sched: Reject CPU affinity changes based on task_cpu_possible_mask() cpuset: Cleanup cpuset_cpus_allowed_fallback() use in select_fallback_rq() cpuset: Honour task_cpu_possible_mask() in guarantee_online_cpus() cpuset: Don't use the cpu_possible_mask as a last resort for cgroup v1 sched: Introduce task_cpu_possible_mask() to limit fallback rq selection sched: Cgroup SCHED_IDLE support sched/topology: Skip updating masks for non-online nodes sched: Replace deprecated CPU-hotplug functions. sched: Skip priority checks with SCHED_FLAG_KEEP_PARAMS sched: Fix UCLAMP_FLAG_IDLE setting sched/deadline: Fix missing clock update in migrate_task_rq_dl() sched/fair: Avoid a second scan of target in select_idle_cpu sched/fair: Use prev instead of new target as recent_used_cpu sched: Don't report SCHED_FLAG_SUGOV in sched_getattr() ...
Diffstat (limited to 'kernel/cgroup')
-rw-r--r--kernel/cgroup/cpuset.c59
1 files changed, 39 insertions, 20 deletions
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index adb5190c4429..6500cbe0ce16 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -372,18 +372,29 @@ static inline bool is_in_v2_mode(void)
}
/*
- * 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.
+ * Return in pmask the portion of a task's cpusets's cpus_allowed that
+ * are online and are capable of running the task. If none are found,
+ * walk up the cpuset hierarchy until we find one that does have some
+ * appropriate cpus.
*
* One way or another, we guarantee to return some non-empty subset
* of cpu_online_mask.
*
* Call with callback_lock or cpuset_mutex held.
*/
-static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)
+static void guarantee_online_cpus(struct task_struct *tsk,
+ struct cpumask *pmask)
{
- while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) {
+ const struct cpumask *possible_mask = task_cpu_possible_mask(tsk);
+ struct cpuset *cs;
+
+ if (WARN_ON(!cpumask_and(pmask, possible_mask, cpu_online_mask)))
+ cpumask_copy(pmask, cpu_online_mask);
+
+ rcu_read_lock();
+ cs = task_cs(tsk);
+
+ while (!cpumask_intersects(cs->effective_cpus, pmask)) {
cs = parent_cs(cs);
if (unlikely(!cs)) {
/*
@@ -393,11 +404,13 @@ static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)
* cpuset's effective_cpus is on its way to be
* identical to cpu_online_mask.
*/
- cpumask_copy(pmask, cpu_online_mask);
- return;
+ goto out_unlock;
}
}
- cpumask_and(pmask, cs->effective_cpus, cpu_online_mask);
+ cpumask_and(pmask, pmask, cs->effective_cpus);
+
+out_unlock:
+ rcu_read_unlock();
}
/*
@@ -2199,15 +2212,13 @@ static void cpuset_attach(struct cgroup_taskset *tset)
percpu_down_write(&cpuset_rwsem);
- /* prepare for attach */
- 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);
cgroup_taskset_for_each(task, css, tset) {
+ if (cs != &top_cpuset)
+ guarantee_online_cpus(task, cpus_attach);
+ else
+ cpumask_copy(cpus_attach, task_cpu_possible_mask(task));
/*
* can_attach beforehand should guarantee that this doesn't
* fail. TODO: have a better way to handle failure here
@@ -3302,9 +3313,7 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
unsigned long flags;
spin_lock_irqsave(&callback_lock, flags);
- rcu_read_lock();
- guarantee_online_cpus(task_cs(tsk), pmask);
- rcu_read_unlock();
+ guarantee_online_cpus(tsk, pmask);
spin_unlock_irqrestore(&callback_lock, flags);
}
@@ -3318,13 +3327,22 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
* which will not contain a sane cpumask during cases such as cpu hotplugging.
* This is the absolute last resort for the scheduler and it is only used if
* _every_ other avenue has been traveled.
+ *
+ * Returns true if the affinity of @tsk was changed, false otherwise.
**/
-void cpuset_cpus_allowed_fallback(struct task_struct *tsk)
+bool cpuset_cpus_allowed_fallback(struct task_struct *tsk)
{
+ const struct cpumask *possible_mask = task_cpu_possible_mask(tsk);
+ const struct cpumask *cs_mask;
+ bool changed = false;
+
rcu_read_lock();
- do_set_cpus_allowed(tsk, is_in_v2_mode() ?
- task_cs(tsk)->cpus_allowed : cpu_possible_mask);
+ cs_mask = task_cs(tsk)->cpus_allowed;
+ if (is_in_v2_mode() && cpumask_subset(cs_mask, possible_mask)) {
+ do_set_cpus_allowed(tsk, cs_mask);
+ changed = true;
+ }
rcu_read_unlock();
/*
@@ -3344,6 +3362,7 @@ void cpuset_cpus_allowed_fallback(struct task_struct *tsk)
* select_fallback_rq() will fix things ups and set cpu_possible_mask
* if required.
*/
+ return changed;
}
void __init cpuset_init_current_mems_allowed(void)