aboutsummaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/cgroup/cgroup.c2
-rw-r--r--kernel/cgroup/cpuset.c163
-rw-r--r--kernel/events/core.c9
-rw-r--r--kernel/irq/manage.c3
-rw-r--r--kernel/kprobes.c2
-rw-r--r--kernel/locking/rtmutex.c6
-rw-r--r--kernel/rcu/Kconfig8
-rw-r--r--kernel/rcu/tree.c12
-rw-r--r--kernel/rcu/tree_stall.h6
-rw-r--r--kernel/sched/core.c561
-rw-r--r--kernel/sched/cpufreq_schedutil.c6
-rw-r--r--kernel/sched/deadline.c134
-rw-r--r--kernel/sched/fair.c409
-rw-r--r--kernel/sched/idle.c31
-rw-r--r--kernel/sched/isolation.c12
-rw-r--r--kernel/sched/psi.c2
-rw-r--r--kernel/sched/rt.c74
-rw-r--r--kernel/sched/sched.h63
-rw-r--r--kernel/sched/stats.h7
-rw-r--r--kernel/sched/stop_task.c22
-rw-r--r--kernel/sched/topology.c53
-rw-r--r--kernel/stop_machine.c2
-rw-r--r--kernel/trace/Kconfig6
-rw-r--r--kernel/trace/ftrace.c2
-rw-r--r--kernel/trace/ring_buffer_benchmark.c2
-rw-r--r--kernel/trace/trace_events.c4
-rw-r--r--kernel/trace/trace_sched_wakeup.c3
27 files changed, 1058 insertions, 546 deletions
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 8be1da1ebd9a..a7ce73a2c401 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1891,7 +1891,7 @@ static int cgroup_reconfigure(struct fs_context *fc)
*/
static bool use_task_css_set_links __read_mostly;
-static void cgroup_enable_task_cg_lists(void)
+void cgroup_enable_task_cg_lists(void)
{
struct task_struct *p, *g;
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 5aa37531ce76..c52bc91f882b 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -45,6 +45,7 @@
#include <linux/proc_fs.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
+#include <linux/sched/deadline.h>
#include <linux/sched/mm.h>
#include <linux/sched/task.h>
#include <linux/seq_file.h>
@@ -332,7 +333,18 @@ static struct cpuset top_cpuset = {
* guidelines for accessing subsystem state in kernel/cgroup.c
*/
-static DEFINE_MUTEX(cpuset_mutex);
+DEFINE_STATIC_PERCPU_RWSEM(cpuset_rwsem);
+
+void cpuset_read_lock(void)
+{
+ percpu_down_read(&cpuset_rwsem);
+}
+
+void cpuset_read_unlock(void)
+{
+ percpu_up_read(&cpuset_rwsem);
+}
+
static DEFINE_SPINLOCK(callback_lock);
static struct workqueue_struct *cpuset_migrate_mm_wq;
@@ -894,6 +906,67 @@ done:
return ndoms;
}
+static void update_tasks_root_domain(struct cpuset *cs)
+{
+ struct css_task_iter it;
+ struct task_struct *task;
+
+ css_task_iter_start(&cs->css, 0, &it);
+
+ while ((task = css_task_iter_next(&it)))
+ dl_add_task_root_domain(task);
+
+ css_task_iter_end(&it);
+}
+
+static void rebuild_root_domains(void)
+{
+ struct cpuset *cs = NULL;
+ struct cgroup_subsys_state *pos_css;
+
+ percpu_rwsem_assert_held(&cpuset_rwsem);
+ lockdep_assert_cpus_held();
+ lockdep_assert_held(&sched_domains_mutex);
+
+ cgroup_enable_task_cg_lists();
+
+ rcu_read_lock();
+
+ /*
+ * Clear default root domain DL accounting, it will be computed again
+ * if a task belongs to it.
+ */
+ dl_clear_root_domain(&def_root_domain);
+
+ cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {
+
+ if (cpumask_empty(cs->effective_cpus)) {
+ pos_css = css_rightmost_descendant(pos_css);
+ continue;
+ }
+
+ css_get(&cs->css);
+
+ rcu_read_unlock();
+
+ update_tasks_root_domain(cs);
+
+ rcu_read_lock();
+ css_put(&cs->css);
+ }
+ rcu_read_unlock();
+}
+
+static void
+partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
+ struct sched_domain_attr *dattr_new)
+{
+ mutex_lock(&sched_domains_mutex);
+ partition_sched_domains_locked(ndoms_new, doms_new, dattr_new);
+ rebuild_root_domains();
+ mutex_unlock(&sched_domains_mutex);
+}
+
/*
* Rebuild scheduler domains.
*
@@ -911,8 +984,8 @@ static void rebuild_sched_domains_locked(void)
cpumask_var_t *doms;
int ndoms;
- lockdep_assert_held(&cpuset_mutex);
- get_online_cpus();
+ lockdep_assert_cpus_held();
+ percpu_rwsem_assert_held(&cpuset_rwsem);
/*
* We have raced with CPU hotplug. Don't do anything to avoid
@@ -921,19 +994,17 @@ static void rebuild_sched_domains_locked(void)
*/
if (!top_cpuset.nr_subparts_cpus &&
!cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask))
- goto out;
+ return;
if (top_cpuset.nr_subparts_cpus &&
!cpumask_subset(top_cpuset.effective_cpus, cpu_active_mask))
- goto out;
+ return;
/* Generate domain masks and attrs */
ndoms = generate_sched_domains(&doms, &attr);
/* Have scheduler rebuild the domains */
- partition_sched_domains(ndoms, doms, attr);
-out:
- put_online_cpus();
+ partition_and_rebuild_sched_domains(ndoms, doms, attr);
}
#else /* !CONFIG_SMP */
static void rebuild_sched_domains_locked(void)
@@ -943,9 +1014,11 @@ static void rebuild_sched_domains_locked(void)
void rebuild_sched_domains(void)
{
- mutex_lock(&cpuset_mutex);
+ get_online_cpus();
+ percpu_down_write(&cpuset_rwsem);
rebuild_sched_domains_locked();
- mutex_unlock(&cpuset_mutex);
+ percpu_up_write(&cpuset_rwsem);
+ put_online_cpus();
}
/**
@@ -1051,7 +1124,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
int deleting; /* Moving cpus from subparts_cpus to effective_cpus */
bool part_error = false; /* Partition error? */
- lockdep_assert_held(&cpuset_mutex);
+ percpu_rwsem_assert_held(&cpuset_rwsem);
/*
* The parent must be a partition root.
@@ -2039,7 +2112,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css));
cs = css_cs(css);
- mutex_lock(&cpuset_mutex);
+ percpu_down_write(&cpuset_rwsem);
/* allow moving tasks into an empty cpuset if on default hierarchy */
ret = -ENOSPC;
@@ -2063,7 +2136,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
cs->attach_in_progress++;
ret = 0;
out_unlock:
- mutex_unlock(&cpuset_mutex);
+ percpu_up_write(&cpuset_rwsem);
return ret;
}
@@ -2073,9 +2146,9 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset)
cgroup_taskset_first(tset, &css);
- mutex_lock(&cpuset_mutex);
+ percpu_down_write(&cpuset_rwsem);
css_cs(css)->attach_in_progress--;
- mutex_unlock(&cpuset_mutex);
+ percpu_up_write(&cpuset_rwsem);
}
/*
@@ -2098,7 +2171,7 @@ static void cpuset_attach(struct cgroup_taskset *tset)
cgroup_taskset_first(tset, &css);
cs = css_cs(css);
- mutex_lock(&cpuset_mutex);
+ percpu_down_write(&cpuset_rwsem);
/* prepare for attach */
if (cs == &top_cpuset)
@@ -2152,7 +2225,7 @@ static void cpuset_attach(struct cgroup_taskset *tset)
if (!cs->attach_in_progress)
wake_up(&cpuset_attach_wq);
- mutex_unlock(&cpuset_mutex);
+ percpu_up_write(&cpuset_rwsem);
}
/* The various types of files and directories in a cpuset file system */
@@ -2183,7 +2256,8 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
cpuset_filetype_t type = cft->private;
int retval = 0;
- mutex_lock(&cpuset_mutex);
+ get_online_cpus();
+ percpu_down_write(&cpuset_rwsem);
if (!is_cpuset_online(cs)) {
retval = -ENODEV;
goto out_unlock;
@@ -2219,7 +2293,8 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
break;
}
out_unlock:
- mutex_unlock(&cpuset_mutex);
+ percpu_up_write(&cpuset_rwsem);
+ put_online_cpus();
return retval;
}
@@ -2230,7 +2305,8 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft,
cpuset_filetype_t type = cft->private;
int retval = -ENODEV;
- mutex_lock(&cpuset_mutex);
+ get_online_cpus();
+ percpu_down_write(&cpuset_rwsem);
if (!is_cpuset_online(cs))
goto out_unlock;
@@ -2243,7 +2319,8 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft,
break;
}
out_unlock:
- mutex_unlock(&cpuset_mutex);
+ percpu_up_write(&cpuset_rwsem);
+ put_online_cpus();
return retval;
}
@@ -2282,7 +2359,8 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
kernfs_break_active_protection(of->kn);
flush_work(&cpuset_hotplug_work);
- mutex_lock(&cpuset_mutex);
+ get_online_cpus();
+ percpu_down_write(&cpuset_rwsem);
if (!is_cpuset_online(cs))
goto out_unlock;
@@ -2306,7 +2384,8 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
free_cpuset(trialcs);
out_unlock:
- mutex_unlock(&cpuset_mutex);
+ percpu_up_write(&cpuset_rwsem);
+ put_online_cpus();
kernfs_unbreak_active_protection(of->kn);
css_put(&cs->css);
flush_workqueue(cpuset_migrate_mm_wq);
@@ -2437,13 +2516,15 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf,
return -EINVAL;
css_get(&cs->css);
- mutex_lock(&cpuset_mutex);
+ get_online_cpus();
+ percpu_down_write(&cpuset_rwsem);
if (!is_cpuset_online(cs))
goto out_unlock;
retval = update_prstate(cs, val);
out_unlock:
- mutex_unlock(&cpuset_mutex);
+ percpu_up_write(&cpuset_rwsem);
+ put_online_cpus();
css_put(&cs->css);
return retval ?: nbytes;
}
@@ -2649,7 +2730,8 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
if (!parent)
return 0;
- mutex_lock(&cpuset_mutex);
+ get_online_cpus();
+ percpu_down_write(&cpuset_rwsem);
set_bit(CS_ONLINE, &cs->flags);
if (is_spread_page(parent))
@@ -2700,7 +2782,8 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
cpumask_copy(cs->effective_cpus, parent->cpus_allowed);
spin_unlock_irq(&callback_lock);
out_unlock:
- mutex_unlock(&cpuset_mutex);
+ percpu_up_write(&cpuset_rwsem);
+ put_online_cpus();
return 0;
}
@@ -2719,7 +2802,8 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
{
struct cpuset *cs = css_cs(css);
- mutex_lock(&cpuset_mutex);
+ get_online_cpus();
+ percpu_down_write(&cpuset_rwsem);
if (is_partition_root(cs))
update_prstate(cs, 0);
@@ -2738,7 +2822,8 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
cpuset_dec();
clear_bit(CS_ONLINE, &cs->flags);
- mutex_unlock(&cpuset_mutex);
+ percpu_up_write(&cpuset_rwsem);
+ put_online_cpus();
}
static void cpuset_css_free(struct cgroup_subsys_state *css)
@@ -2750,7 +2835,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css)
static void cpuset_bind(struct cgroup_subsys_state *root_css)
{
- mutex_lock(&cpuset_mutex);
+ percpu_down_write(&cpuset_rwsem);
spin_lock_irq(&callback_lock);
if (is_in_v2_mode()) {
@@ -2763,7 +2848,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
}
spin_unlock_irq(&callback_lock);
- mutex_unlock(&cpuset_mutex);
+ percpu_up_write(&cpuset_rwsem);
}
/*
@@ -2805,6 +2890,8 @@ struct cgroup_subsys cpuset_cgrp_subsys = {
int __init cpuset_init(void)
{
+ BUG_ON(percpu_init_rwsem(&cpuset_rwsem));
+
BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL));
BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL));
BUG_ON(!zalloc_cpumask_var(&top_cpuset.subparts_cpus, GFP_KERNEL));
@@ -2876,7 +2963,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs,
is_empty = cpumask_empty(cs->cpus_allowed) ||
nodes_empty(cs->mems_allowed);
- mutex_unlock(&cpuset_mutex);
+ percpu_up_write(&cpuset_rwsem);
/*
* Move tasks to the nearest ancestor with execution resources,
@@ -2886,7 +2973,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs,
if (is_empty)
remove_tasks_in_empty_cpuset(cs);
- mutex_lock(&cpuset_mutex);
+ percpu_down_write(&cpuset_rwsem);
}
static void
@@ -2936,14 +3023,14 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
retry:
wait_event(cpuset_attach_wq, cs->attach_in_progress == 0);
- mutex_lock(&cpuset_mutex);
+ percpu_down_write(&cpuset_rwsem);
/*
* We have raced with task attaching. We wait until attaching
* is finished, so we won't attach a task to an empty cpuset.
*/
if (cs->attach_in_progress) {
- mutex_unlock(&cpuset_mutex);
+ percpu_up_write(&cpuset_rwsem);
goto retry;
}
@@ -3011,7 +3098,7 @@ update_tasks:
hotplug_update_tasks_legacy(cs, &new_cpus, &new_mems,
cpus_updated, mems_updated);
- mutex_unlock(&cpuset_mutex);
+ percpu_up_write(&cpuset_rwsem);
}
/**
@@ -3041,7 +3128,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
if (on_dfl && !alloc_cpumasks(NULL, &tmp))
ptmp = &tmp;
- mutex_lock(&cpuset_mutex);
+ percpu_down_write(&cpuset_rwsem);
/* fetch the available cpus/mems and find out which changed how */
cpumask_copy(&new_cpus, cpu_active_mask);
@@ -3091,7 +3178,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
update_tasks_nodemask(&top_cpuset);
}
- mutex_unlock(&cpuset_mutex);
+ percpu_up_write(&cpuset_rwsem);
/* if cpus or mems changed, we need to propagate to descendants */
if (cpus_updated || mems_updated) {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2aad959e6def..1c414b8866b4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4174,10 +4174,8 @@ alloc_perf_context(struct pmu *pmu, struct task_struct *task)
return NULL;
__perf_event_init_context(ctx);
- if (task) {
- ctx->task = task;
- get_task_struct(task);
- }
+ if (task)
+ ctx->task = get_task_struct(task);
ctx->pmu = pmu;
return ctx;
@@ -10440,8 +10438,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
* and we cannot use the ctx information because we need the
* pmu before we get a ctx.
*/
- get_task_struct(task);
- event->hw.target = task;
+ event->hw.target = get_task_struct(task);
}
event->clock = &local_clock;
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index e8f7f179bf77..9d50fbe5531a 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1255,8 +1255,7 @@ setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary)
* the thread dies to avoid that the interrupt code
* references an already freed task_struct.
*/
- get_task_struct(t);
- new->thread = t;
+ new->thread = get_task_struct(t);
/*
* Tell the thread to set its affinity. This is
* important for shared interrupt handlers as we do
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ebe8315a756a..1b66ccbb744a 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1907,7 +1907,7 @@ int register_kretprobe(struct kretprobe *rp)
/* Pre-allocate memory for max kretprobe instances */
if (rp->maxactive <= 0) {
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
rp->maxactive = max_t(unsigned int, 10, 2*num_possible_cpus());
#else
rp->maxactive = num_possible_cpus();
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index fa83d36e30c6..2874bf556162 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -628,8 +628,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
}
/* [10] Grab the next task, i.e. owner of @lock */
- task = rt_mutex_owner(lock);
- get_task_struct(task);
+ task = get_task_struct(rt_mutex_owner(lock));
raw_spin_lock(&task->pi_lock);
/*
@@ -709,8 +708,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
}
/* [10] Grab the next task, i.e. the owner of @lock */
- task = rt_mutex_owner(lock);
- get_task_struct(task);
+ task = get_task_struct(rt_mutex_owner(lock));
raw_spin_lock(&task->pi_lock);
/* [11] requeue the pi waiters if necessary */
diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index 480edf328b51..7644eda17d62 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -7,7 +7,7 @@ menu "RCU Subsystem"
config TREE_RCU
bool
- default y if !PREEMPT && SMP
+ default y if !PREEMPTION && SMP
help
This option selects the RCU implementation that is
designed for very large SMP system with hundreds or
@@ -16,7 +16,7 @@ config TREE_RCU
config PREEMPT_RCU
bool
- default y if PREEMPT
+ default y if PREEMPTION
help
This option selects the RCU implementation that is
designed for very large SMP systems with hundreds or
@@ -28,7 +28,7 @@ config PREEMPT_RCU
config TINY_RCU
bool
- default y if !PREEMPT && !SMP
+ default y if !PREEMPTION && !SMP
help
This option selects the RCU implementation that is
designed for UP systems from which real-time response
@@ -70,7 +70,7 @@ config TREE_SRCU
This option selects the full-fledged version of SRCU.
config TASKS_RCU
- def_bool PREEMPT
+ def_bool PREEMPTION
select SRCU
help
This option enables a task-based RCU implementation that uses
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 71395e91b876..81105141b6a8 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1912,7 +1912,7 @@ rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
struct rcu_node *rnp_p;
raw_lockdep_assert_held_rcu_node(rnp);
- if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT)) ||
+ if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPTION)) ||
WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)) ||
rnp->qsmask != 0) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -2266,7 +2266,7 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
mask = 0;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if (rnp->qsmask == 0) {
- if (!IS_ENABLED(CONFIG_PREEMPT) ||
+ if (!IS_ENABLED(CONFIG_PREEMPTION) ||
rcu_preempt_blocked_readers_cgp(rnp)) {
/*
* No point in scanning bits because they
@@ -2681,7 +2681,7 @@ static int rcu_blocking_is_gp(void)
{
int ret;
- if (IS_ENABLED(CONFIG_PREEMPT))
+ if (IS_ENABLED(CONFIG_PREEMPTION))
return rcu_scheduler_active == RCU_SCHEDULER_INACTIVE;
might_sleep(); /* Check for RCU read-side critical section. */
preempt_disable();
@@ -3297,13 +3297,13 @@ static int __init rcu_spawn_gp_kthread(void)
t = kthread_create(rcu_gp_kthread, NULL, "%s", rcu_state.name);
if (WARN_ONCE(IS_ERR(t), "%s: Could not start grace-period kthread, OOM is now expected behavior\n", __func__))
return 0;
- rnp = rcu_get_root();
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- rcu_state.gp_kthread = t;
if (kthread_prio) {
sp.sched_priority = kthread_prio;
sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
}
+ rnp = rcu_get_root();
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ rcu_state.gp_kthread = t;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
wake_up_process(t);
rcu_spawn_nocb_kthreads();
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 841ab43f3e60..c0b8c458d8a6 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -163,7 +163,7 @@ static void rcu_iw_handler(struct irq_work *iwp)
//
// Printing RCU CPU stall warnings
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
/*
* Dump detailed information for all tasks blocking the current RCU
@@ -215,7 +215,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp)
return ndetected;
}
-#else /* #ifdef CONFIG_PREEMPT */
+#else /* #ifdef CONFIG_PREEMPTION */
/*
* Because preemptible RCU does not exist, we never have to check for
@@ -233,7 +233,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp)
{
return 0;
}
-#endif /* #else #ifdef CONFIG_PREEMPT */
+#endif /* #else #ifdef CONFIG_PREEMPTION */
/*
* Dump stacks of all tasks running on stalled CPUs. First try using
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7fa8e74ad2ab..06961b997ed6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -773,6 +773,18 @@ static void set_load_weight(struct task_struct *p, bool update_load)
}
#ifdef CONFIG_UCLAMP_TASK
+/*
+ * Serializes updates of utilization clamp values
+ *
+ * The (slow-path) user-space triggers utilization clamp value updates which
+ * can require updates on (fast-path) scheduler's data structures used to
+ * support enqueue/dequeue operations.
+ * While the per-CPU rq lock protects fast-path update operations, user-space
+ * requests are serialized using a mutex to reduce the risk of conflicting
+ * updates or API abuses.
+ */
+static DEFINE_MUTEX(uclamp_mutex);
+
/* Max allowed minimum utilization */
unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE;
@@ -798,7 +810,7 @@ static inline unsigned int uclamp_bucket_base_value(unsigned int clamp_value)
return UCLAMP_BUCKET_DELTA * uclamp_bucket_id(clamp_value);
}
-static inline unsigned int uclamp_none(int clamp_id)
+static inline enum uclamp_id uclamp_none(enum uclamp_id clamp_id)
{
if (clamp_id == UCLAMP_MIN)
return 0;
@@ -814,7 +826,7 @@ static inline void uclamp_se_set(struct uclamp_se *uc_se,
}
static inline unsigned int
-uclamp_idle_value(struct rq *rq, unsigned int clamp_id,
+uclamp_idle_value(struct rq *rq, enum uclamp_id clamp_id,
unsigned int clamp_value)
{
/*
@@ -830,7 +842,7 @@ uclamp_idle_value(struct rq *rq, unsigned int clamp_id,
return uclamp_none(UCLAMP_MIN);
}
-static inline void uclamp_idle_reset(struct rq *rq, unsigned int clamp_id,
+static inline void uclamp_idle_reset(struct rq *rq, enum uclamp_id clamp_id,
unsigned int clamp_value)
{
/* Reset max-clamp retention only on idle exit */
@@ -841,8 +853,8 @@ static inline void uclamp_idle_reset(struct rq *rq, unsigned int clamp_id,
}
static inline
-unsigned int uclamp_rq_max_value(struct rq *rq, unsigned int clamp_id,
- unsigned int clamp_value)
+enum uclamp_id uclamp_rq_max_value(struct rq *rq, enum uclamp_id clamp_id,
+ unsigned int clamp_value)
{
struct uclamp_bucket *bucket = rq->uclamp[clamp_id].bucket;
int bucket_id = UCLAMP_BUCKETS - 1;
@@ -861,16 +873,42 @@ unsigned int uclamp_rq_max_value(struct rq *rq, unsigned int clamp_id,
return uclamp_idle_value(rq, clamp_id, clamp_value);
}
+static inline struct uclamp_se
+uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id)
+{
+ struct uclamp_se uc_req = p->uclamp_req[clamp_id];
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+ struct uclamp_se uc_max;
+
+ /*
+ * Tasks in autogroups or root task group will be
+ * restricted by system defaults.
+ */
+ if (task_group_is_autogroup(task_group(p)))
+ return uc_req;
+ if (task_group(p) == &root_task_group)
+ return uc_req;
+
+ uc_max = task_group(p)->uclamp[clamp_id];
+ if (uc_req.value > uc_max.value || !uc_req.user_defined)
+ return uc_max;
+#endif
+
+ return uc_req;
+}
+
/*
* The effective clamp bucket index of a task depends on, by increasing
* priority:
* - the task specific clamp value, when explicitly requested from userspace
+ * - the task group effective clamp value, for tasks not either in the root
+ * group or in an autogroup
* - the system default clamp value, defined by the sysadmin
*/
static inline struct uclamp_se
-uclamp_eff_get(struct task_struct *p, unsigned int clamp_id)
+uclamp_eff_get(struct task_struct *p, enum uclamp_id clamp_id)
{
- struct uclamp_se uc_req = p->uclamp_req[clamp_id];
+ struct uclamp_se uc_req = uclamp_tg_restrict(p, clamp_id);
struct uclamp_se uc_max = uclamp_default[clamp_id];
/* System default restrictions always apply */
@@ -880,7 +918,7 @@ uclamp_eff_get(struct task_struct *p, unsigned int clamp_id)
return uc_req;
}
-unsigned int uclamp_eff_value(struct task_struct *p, unsigned int clamp_id)
+enum uclamp_id uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id)
{
struct uclamp_se uc_eff;
@@ -904,7 +942,7 @@ unsigned int uclamp_eff_value(struct task_struct *p, unsigned int clamp_id)
* for each bucket when all its RUNNABLE tasks require the same clamp.
*/
static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p,
- unsigned int clamp_id)
+ enum uclamp_id clamp_id)
{
struct uclamp_rq *uc_rq = &rq->uclamp[clamp_id];
struct uclamp_se *uc_se = &p->uclamp[clamp_id];
@@ -942,7 +980,7 @@ static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p,
* enforce the expected state and warn.
*/
static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
- unsigned int clamp_id)
+ enum uclamp_id clamp_id)
{
struct uclamp_rq *uc_rq = &rq->uclamp[clamp_id];
struct uclamp_se *uc_se = &p->uclamp[clamp_id];
@@ -981,7 +1019,7 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
{
- unsigned int clamp_id;
+ enum uclamp_id clamp_id;
if (unlikely(!p->sched_class->uclamp_enabled))
return;
@@ -996,7 +1034,7 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
{
- unsigned int clamp_id;
+ enum uclamp_id clamp_id;
if (unlikely(!p->sched_class->uclamp_enabled))
return;
@@ -1005,15 +1043,82 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
uclamp_rq_dec_id(rq, p, clamp_id);
}
+static inline void
+uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id)
+{
+ struct rq_flags rf;
+ struct rq *rq;
+
+ /*
+ * Lock the task and the rq where the task is (or was) queued.
+ *
+ * We might lock the (previous) rq of a !RUNNABLE task, but that's the
+ * price to pay to safely serialize util_{min,max} updates with
+ * enqueues, dequeues and migration operations.
+ * This is the same locking schema used by __set_cpus_allowed_ptr().
+ */
+ rq = task_rq_lock(p, &rf);
+
+ /*
+ * Setting the clamp bucket is serialized by task_rq_lock().
+ * If the task is not yet RUNNABLE and its task_struct is not
+ * affecting a valid clamp bucket, the next time it's enqueued,
+ * it will already see the updated clamp bucket value.
+ */
+ if (!p->uclamp[clamp_id].active) {
+ uclamp_rq_dec_id(rq, p, clamp_id);
+ uclamp_rq_inc_id(rq, p, clamp_id);
+ }
+
+ task_rq_unlock(rq, p, &rf);
+}
+
+static inline void
+uclamp_update_active_tasks(struct cgroup_subsys_state *css,
+ unsigned int clamps)
+{
+ enum uclamp_id clamp_id;
+ struct css_task_iter it;
+ struct task_struct *p;
+
+ css_task_iter_start(css, 0, &it);
+ while ((p = css_task_iter_next(&it))) {
+ for_each_clamp_id(clamp_id) {
+ if ((0x1 << clamp_id) & clamps)
+ uclamp_update_active(p, clamp_id);
+ }
+ }
+ css_task_iter_end(&it);
+}
+
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+static void cpu_util_update_eff(struct cgroup_subsys_state *css);
+static void uclamp_update_root_tg(void)
+{
+ struct task_group *tg = &root_task_group;
+
+ uclamp_se_set(&tg->uclamp_req[UCLAMP_MIN],
+ sysctl_sched_uclamp_util_min, false);
+ uclamp_se_set(&tg->uclamp_req[UCLAMP_MAX],
+ sysctl_sched_uclamp_util_max, false);
+
+ rcu_read_lock();
+ cpu_util_update_eff(&root_task_group.css);
+ rcu_read_unlock();
+}
+#else
+static void uclamp_update_root_tg(void) { }
+#endif
+
int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
+ bool update_root_tg = false;
int old_min, old_max;
- static DEFINE_MUTEX(mutex);
int result;
- mutex_lock(&mutex);
+ mutex_lock(&uclamp_mutex);
old_min = sysctl_sched_uclamp_util_min;
old_max = sysctl_sched_uclamp_util_max;
@@ -1032,23 +1137,30 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
if (old_min != sysctl_sched_uclamp_util_min) {
uclamp_se_set(&uclamp_default[UCLAMP_MIN],
sysctl_sched_uclamp_util_min, false);
+ update_root_tg = true;
}
if (old_max != sysctl_sched_uclamp_util_max) {
uclamp_se_set(&uclamp_default[UCLAMP_MAX],
sysctl_sched_uclamp_util_max, false);
+ update_root_tg = true;
}
+ if (update_root_tg)
+ uclamp_update_root_tg();
+
/*
- * Updating all the RUNNABLE task is expensive, keep it simple and do
- * just a lazy update at each next enqueue time.
+ * We update all RUNNABLE tasks only when task groups are in use.
+ * Otherwise, keep it simple and do just a lazy update at each next
+ * task enqueue time.
*/
+
goto done;
undo:
sysctl_sched_uclamp_util_min = old_min;
sysctl_sched_uclamp_util_max = old_max;
done:
- mutex_unlock(&mutex);
+ mutex_unlock(&uclamp_mutex);
return result;
}
@@ -1075,7 +1187,7 @@ static int uclamp_validate(struct task_struct *p,
static void __setscheduler_uclamp(struct task_struct *p,
const struct sched_attr *attr)
{
- unsigned int clamp_id;
+ enum uclamp_id clamp_id;
/*
* On scheduling class change, reset to default clamps for tasks
@@ -1112,7 +1224,7 @@ static void __setscheduler_uclamp(struct task_struct *p,
static void uclamp_fork(struct task_struct *p)
{
- unsigned int clamp_id;
+ enum uclamp_id clamp_id;
for_each_clamp_id(clamp_id)
p->uclamp[clamp_id].active = false;
@@ -1134,9 +1246,11 @@ static void uclamp_fork(struct task_struct *p)
static void __init init_uclamp(void)
{
struct uclamp_se uc_max = {};
- unsigned int clamp_id;
+ enum uclamp_id clamp_id;
int cpu;
+ mutex_init(&uclamp_mutex);
+
for_each_possible_cpu(cpu) {
memset(&cpu_rq(cpu)->uclamp, 0, sizeof(struct uclamp_rq));
cpu_rq(cpu)->uclamp_flags = 0;
@@ -1149,8 +1263,13 @@ static void __init init_uclamp(void)
/* System defaults allow max clamp values for both indexes */
uclamp_se_set(&uc_max, uclamp_none(UCLAMP_MAX), false);
- for_each_clamp_id(clamp_id)
+ for_each_clamp_id(clamp_id) {
uclamp_default[clamp_id] = uc_max;
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+ root_task_group.uclamp_req[clamp_id] = uc_max;
+ root_task_group.uclamp[clamp_id] = uc_max;
+#endif
+ }
}
#else /* CONFIG_UCLAMP_TASK */
@@ -1494,7 +1613,7 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
if (queued)
enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
if (running)
- set_curr_task(rq, p);
+ set_next_task(rq, p);
}
/*
@@ -3214,12 +3333,8 @@ static __always_inline struct rq *
context_switch(struct rq *rq, struct task_struct *prev,
struct task_struct *next, struct rq_flags *rf)
{
- struct mm_struct *mm, *oldmm;
-
prepare_task_switch(rq, prev, next);
- mm = next->mm;
- oldmm = prev->active_mm;
/*
* For paravirt, this is coupled with an exit in switch_to to
* combine the page table reload and the switch backend into
@@ -3228,22 +3343,37 @@ context_switch(struct rq *rq, struct task_struct *prev,
arch_start_context_switch(prev);
/*
- * If mm is non-NULL, we pass through switch_mm(). If mm is
- * NULL, we will pass through mmdrop() in finish_task_switch().
- * Both of these contain the full memory barrier required by
- * membarrier after storing to rq->curr, before returning to
- * user-space.
+ * kernel -> kernel lazy + transfer active
+ * user -> kernel lazy + mmgrab() active
+ *
+ * kernel -> user switch + mmdrop() active
+ * user -> user switch
*/
- if (!mm) {
- next->active_mm = oldmm;
- mmgrab(oldmm);
- enter_lazy_tlb(oldmm, next);
- } else
- switch_mm_irqs_off(oldmm, mm, next);
+ if (!next->mm) { // to kernel
+ enter_lazy_tlb(prev->active_mm, next);
+
+ next->active_mm = prev->active_mm;
+ if (prev->mm) // from user
+ mmgrab(prev->active_mm);
+ else
+ prev->active_mm = NULL;
+ } else { // to user
+ /*
+ * sys_membarrier() requires an smp_mb() between setting
+ * rq->curr and returning to userspace.
+ *
+ * The below provides this either through switch_mm(), or in
+ * case 'prev->active_mm == next->mm' through
+ * finish_task_switch()'s mmdrop().
+ */
+
+ switch_mm_irqs_off(prev->active_mm, next->mm, next);
- if (!prev->mm) {
- prev->active_mm = NULL;
- rq->prev_mm = oldmm;
+ if (!prev->mm) { // from kernel
+ /* will mmdrop() in finish_task_switch(). */
+ rq->prev_mm = prev->active_mm;
+ prev->active_mm = NULL;
+ }
}
rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
@@ -3622,7 +3752,7 @@ static inline void sched_tick_start(int cpu) { }
static inline void sched_tick_stop(int cpu) { }
#endif
-#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
+#if defined(CONFIG_PREEMPTION) && (defined(CONFIG_DEBUG_PREEMPT) || \
defined(CONFIG_TRACE_PREEMPT_TOGGLE))
/*
* If the value passed in is equal to the current preempt count
@@ -3780,7 +3910,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
p = fair_sched_class.pick_next_task(rq, prev, rf);
if (unlikely(p == RETRY_TASK))
- goto again;
+ goto restart;
/* Assumes fair_sched_class->next == idle_sched_class */
if (unlikely(!p))
@@ -3789,14 +3919,19 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
return p;
}
-again:
+restart:
+ /*
+ * Ensure that we put DL/RT tasks before the pick loop, such that they
+ * can PULL higher prio tasks when we lower the RQ 'priority'.
+ */
+ prev->sched_class->put_prev_task(rq, prev, rf);
+ if (!rq->nr_running)
+ newidle_balance(rq, rf);
+
for_each_class(class) {
- p = class->pick_next_task(rq, prev, rf);
- if (p) {
- if (unlikely(p == RETRY_TASK))
- goto again;
+ p = class->pick_next_task(rq, NULL, NULL);
+ if (p)
return p;
- }
}
/* The idle class should always have a runnable task: */
@@ -3823,7 +3958,7 @@ again:
* task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets
* called on the nearest possible occasion:
*
- * - If the kernel is preemptible (CONFIG_PREEMPT=y):
+ * - If the kernel is preemptible (CONFIG_PREEMPTION=y):
*
* - in syscall or exception context, at the next outmost
* preempt_enable(). (this might be as soon as the wake_up()'s
@@ -3832,7 +3967,7 @@ again:
* - in IRQ context, return from interrupt-handler to
* preemptible context
*
- * - If the kernel is not preemptible (CONFIG_PREEMPT is not set)
+ * - If the kernel is not preemptible (CONFIG_PREEMPTION is not set)
* then at the next:
*
* - cond_resched() call
@@ -4077,7 +4212,7 @@ static void __sched notrace preempt_schedule_common(void)
} while (need_resched());
}
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
/*
* this is the entry point to schedule() from in-kernel preemption
* off of preempt_enable. Kernel preemptions off return from interrupt
@@ -4149,7 +4284,7 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
}
EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
/*
* this is the entry point to schedule() from kernel preemption
@@ -4317,7 +4452,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
if (queued)
enqueue_task(rq, p, queue_flag);
if (running)
- set_curr_task(rq, p);
+ set_next_task(rq, p);
check_class_changed(rq, p, prev_class, oldprio);
out_unlock:
@@ -4384,7 +4519,7 @@ void set_user_nice(struct task_struct *p, long nice)
resched_curr(rq);
}
if (running)
- set_curr_task(rq, p);
+ set_next_task(rq, p);
out_unlock:
task_rq_unlock(rq, p, &rf);
}
@@ -4701,6 +4836,9 @@ recheck:
return retval;
}
+ if (pi)
+ cpuset_read_lock();
+
/*
* Make sure no PI-waiters arrive (or leave) while we are
* changing the priority of the task:
@@ -4715,8 +4853,8 @@ recheck:
* Changing the policy of the stop threads its a very bad idea:
*/
if (p == rq->stop) {
- task_rq_unlock(rq, p, &rf);
- return -EINVAL;
+ retval = -EINVAL;
+ goto unlock;
}
/*
@@ -4734,8 +4872,8 @@ recheck:
goto change;
p->sched_reset_on_fork = reset_on_fork;
- task_rq_unlock(rq, p, &rf);
- return 0;
+ retval = 0;
+ goto unlock;
}
change:
@@ -4748,8 +4886,8 @@ change:
if (rt_bandwidth_enabled() && rt_policy(policy) &&
task_group(p)->rt_bandwidth.rt_runtime == 0 &&
!task_group_is_autogroup(task_group(p))) {
- task_rq_unlock(rq, p, &rf);
- return -EPERM;
+ retval = -EPERM;
+ goto unlock;
}
#endif
#ifdef CONFIG_SMP
@@ -4764,8 +4902,8 @@ change:
*/
if (!cpumask_subset(span, p->cpus_ptr) ||
rq->rd->dl_bw.bw == 0) {
- task_rq_unlock(rq, p, &rf);
- return -EPERM;
+ retval = -EPERM;
+ goto unlock;
}
}
#endif
@@ -4775,6 +4913,8 @@ change:
if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
policy = oldpolicy = -1;
task_rq_unlock(rq, p, &rf);
+ if (pi)
+ cpuset_read_unlock();
goto recheck;
}
@@ -4784,8 +4924,8 @@ change:
* is available.
*/
if ((dl_policy(policy) || dl_task(p)) && sched_dl_overflow(p, policy, attr)) {
- task_rq_unlock(rq, p, &rf);
- return -EBUSY;
+ retval = -EBUSY;
+ goto unlock;
}
p->sched_reset_on_fork = reset_on_fork;
@@ -4827,7 +4967,7 @@ change:
enqueue_task(rq, p, queue_flags);
}
if (running)
- set_curr_task(rq, p);
+ set_next_task(rq, p);
check_class_changed(rq, p, prev_class, oldprio);
@@ -4835,14 +4975,22 @@ change:
preempt_disable();
task_rq_unlock(rq, p, &rf);
- if (pi)
+ if (pi) {
+ cpuset_read_unlock();
rt_mutex_adjust_pi(p);
+ }
/* Run balance callbacks after we've adjusted the PI chain: */
balance_callback(rq);
preempt_enable();
return 0;
+
+unlock:
+ task_rq_unlock(rq, p, &rf);
+ if (pi)
+ cpuset_read_unlock();
+ return retval;
}
static int _sched_setscheduler(struct task_struct *p, int policy,
@@ -4926,10 +5074,15 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
rcu_read_lock();
retval = -ESRCH;
p = find_process_by_pid(pid);
- if (p != NULL)
- retval = sched_setscheduler(p, policy, &lparam);
+ if (likely(p))
+ get_task_struct(p);
rcu_read_unlock();
+ if (likely(p)) {
+ retval = sched_setscheduler(p, policy, &lparam);
+ put_task_struct(p);
+ }
+
return retval;
}
@@ -5460,7 +5613,7 @@ SYSCALL_DEFINE0(sched_yield)
return 0;
}
-#ifndef CONFIG_PREEMPT
+#ifndef CONFIG_PREEMPTION
int __sched _cond_resched(void)
{
if (should_resched(0)) {
@@ -5477,7 +5630,7 @@ EXPORT_SYMBOL(_cond_resched);
* __cond_resched_lock() - if a reschedule is pending, drop the given lock,
* call schedule, and on return reacquire the lock.
*
- * This works OK both with and without CONFIG_PREEMPT. We do strange low-level
+ * This works OK both with and without CONFIG_PREEMPTION. We do strange low-level
* operations here to prevent schedule() from being called twice (once via
* spin_unlock(), once by hand).
*/
@@ -6016,7 +6169,7 @@ void sched_setnuma(struct task_struct *p, int nid)
if (queued)
enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
if (running)
- set_curr_task(rq, p);
+ set_next_task(rq, p);
task_rq_unlock(rq, p, &rf);
}
#endif /* CONFIG_NUMA_BALANCING */
@@ -6056,21 +6209,22 @@ static void calc_load_migrate(struct rq *rq)
atomic_long_add(delta, &calc_load_tasks);
}
-static void put_prev_task_fake(struct rq *rq, struct task_struct *prev)
+static struct task_struct *__pick_migrate_task(struct rq *rq)
{
-}
+ const struct sched_class *class;
+ struct task_struct *next;
-static const struct sched_class fake_sched_class = {
- .put_prev_task = put_prev_task_fake,
-};
+ for_each_class(class) {
+ next = class->pick_next_task(rq, NULL, NULL);
+ if (next) {
+ next->sched_class->put_prev_task(rq, next, NULL);
+ return next;
+ }
+ }
-static struct task_struct fake_task = {
- /*
- * Avoid pull_{rt,dl}_task()
- */
- .prio = MAX_PRIO + 1,
- .sched_class = &fake_sched_class,
-};
+ /* The idle class should always have a runnable task */
+ BUG();
+}
/*
* Migrate all tasks from the rq, sleeping tasks will be migrated by
@@ -6113,12 +6267,7 @@ static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf)
if (rq->nr_running == 1)
break;
- /*
- * pick_next_task() assumes pinned rq->lock:
- */
- next = pick_next_task(rq, &fake_task, rf);
- BUG_ON(!next);
- put_prev_task(rq, next);
+ next = __pick_migrate_task(rq);
/*
* Rules for changing task_struct::cpus_mask are holding
@@ -6415,19 +6564,19 @@ DECLARE_PER_CPU(cpumask_var_t, select_idle_mask);
void __init sched_init(void)
{
- unsigned long alloc_size = 0, ptr;
+ unsigned long ptr = 0;
int i;
wait_bit_init();
#ifdef CONFIG_FAIR_GROUP_SCHED
- alloc_size += 2 * nr_cpu_ids * sizeof(void **);
+ ptr += 2 * nr_cpu_ids * sizeof(void **);
#endif
#ifdef CONFIG_RT_GROUP_SCHED
- alloc_size += 2 * nr_cpu_ids * sizeof(void **);
+ ptr += 2 * nr_cpu_ids * sizeof(void **);
#endif
- if (alloc_size) {
- ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
+ if (ptr) {
+ ptr = (unsigned long)kzalloc(ptr, GFP_NOWAIT);
#ifdef CONFIG_FAIR_GROUP_SCHED
root_task_group.se = (struct sched_entity **)ptr;
@@ -6746,7 +6895,7 @@ struct task_struct *curr_task(int cpu)
#ifdef CONFIG_IA64
/**
- * set_curr_task - set the current task for a given CPU.
+ * ia64_set_curr_task - set the current task for a given CPU.
* @cpu: the processor in question.
* @p: the task pointer to set.
*
@@ -6771,6 +6920,20 @@ void ia64_set_curr_task(int cpu, struct task_struct *p)
/* task_group_lock serializes the addition/removal of task groups */
static DEFINE_SPINLOCK(task_group_lock);
+static inline void alloc_uclamp_sched_group(struct task_group *tg,
+ struct task_group *parent)
+{
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+ enum uclamp_id clamp_id;
+
+ for_each_clamp_id(clamp_id) {
+ uclamp_se_set(&tg->uclamp_req[clamp_id],
+ uclamp_none(clamp_id), false);
+ tg->uclamp[clamp_id] = parent->uclamp[clamp_id];
+ }
+#endif
+}
+
static void sched_free_group(struct task_group *tg)
{
free_fair_sched_group(tg);
@@ -6794,6 +6957,8 @@ struct task_group *sched_create_group(struct task_group *parent)
if (!alloc_rt_sched_group(tg, parent))
goto err;
+ alloc_uclamp_sched_group(tg, parent);
+
return tg;
err:
@@ -6897,7 +7062,7 @@ void sched_move_task(struct task_struct *tsk)
if (queued)
enqueue_task(rq, tsk, queue_flags);
if (running)
- set_curr_task(rq, tsk);
+ set_next_task(rq, tsk);
task_rq_unlock(rq, tsk, &rf);
}
@@ -6980,10 +7145,6 @@ static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
#ifdef CONFIG_RT_GROUP_SCHED
if (!sched_rt_can_attach(css_tg(css), task))
return -EINVAL;
-#else
- /* We don't support RT-tasks being in separate groups */
- if (task->sched_class != &fair_sched_class)
- return -EINVAL;
#endif
/*
* Serialize against wake_up_new_task() such that if its
@@ -7014,6 +7175,178 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset)
sched_move_task(task);
}
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+static void cpu_util_update_eff(struct cgroup_subsys_state *css)
+{
+ struct cgroup_subsys_state *top_css = css;
+ struct uclamp_se *uc_parent = NULL;
+ struct uclamp_se *uc_se = NULL;
+ unsigned int eff[UCLAMP_CNT];
+ enum uclamp_id clamp_id;
+ unsigned int clamps;
+
+ css_for_each_descendant_pre(css, top_css) {
+ uc_parent = css_tg(css)->parent
+ ? css_tg(css)->parent->uclamp : NULL;
+
+ for_each_clamp_id(clamp_id) {
+ /* Assume effective clamps matches requested clamps */
+ eff[clamp_id] = css_tg(css)->uclamp_req[clamp_id].value;
+ /* Cap effective clamps with parent's effective clamps */
+ if (uc_parent &&
+ eff[clamp_id] > uc_parent[clamp_id].value) {
+ eff[clamp_id] = uc_parent[clamp_id].value;
+ }
+ }
+ /* Ensure protection is always capped by limit */
+ eff[UCLAMP_MIN] = min(eff[UCLAMP_MIN], eff[UCLAMP_MAX]);
+
+ /* Propagate most restrictive effective clamps */
+ clamps = 0x0;
+ uc_se = css_tg(css)->uclamp;
+ for_each_clamp_id(clamp_id) {
+ if (eff[clamp_id] == uc_se[clamp_id].value)
+ continue;
+ uc_se[clamp_id].value = eff[clamp_id];
+ uc_se[clamp_id].bucket_id = uclamp_bucket_id(eff[clamp_id]);
+ clamps |= (0x1 << clamp_id);
+ }
+ if (!clamps) {
+ css = css_rightmost_descendant(css);
+ continue;
+ }
+
+ /* Immediately update descendants RUNNABLE tasks */
+ uclamp_update_active_tasks(css, clamps);
+ }
+}
+
+/*
+ * Integer 10^N with a given N exponent by casting to integer the literal "1eN"
+ * C expression. Since there is no way to convert a macro argument (N) into a
+ * character constant, use two levels of macros.
+ */
+#define _POW10(exp) ((unsigned int)1e##exp)
+#define POW10(exp) _POW10(exp)
+
+struct uclamp_request {
+#define UCLAMP_PERCENT_SHIFT 2
+#define UCLAMP_PERCENT_SCALE (100 * POW10(UCLAMP_PERCENT_SHIFT))
+ s64 percent;
+ u64 util;
+ int ret;
+};
+
+static inline struct uclamp_request
+capacity_from_percent(char *buf)
+{
+ struct uclamp_request req = {
+ .percent = UCLAMP_PERCENT_SCALE,
+ .util = SCHED_CAPACITY_SCALE,
+ .ret = 0,
+ };
+
+ buf = strim(buf);
+ if (strcmp(buf, "max")) {
+ req.ret = cgroup_parse_float(buf, UCLAMP_PERCENT_SHIFT,
+ &req.percent);
+ if (req.ret)
+ return req;
+ if (req.percent > UCLAMP_PERCENT_SCALE) {
+ req.ret = -ERANGE;
+ return req;
+ }
+
+ req.util = req.percent << SCHED_CAPACITY_SHIFT;
+ req.util = DIV_ROUND_CLOSEST_ULL(req.util, UCLAMP_PERCENT_SCALE);
+ }
+
+ return req;
+}
+
+static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf,
+ size_t nbytes, loff_t off,
+ enum uclamp_id clamp_id)
+{
+ struct uclamp_request req;
+ struct task_group *tg;
+
+ req = capacity_from_percent(buf);
+ if (req.ret)
+ return req.ret;
+
+ mutex_lock(&uclamp_mutex);
+ rcu_read_lock();
+
+ tg = css_tg(of_css(of));
+ if (tg->uclamp_req[clamp_id].value != req.util)
+ uclamp_se_set(&tg->uclamp_req[clamp_id], req.util, false);
+
+ /*
+ * Because of not recoverable conversion rounding we keep track of the
+ * exact requested value
+ */
+ tg->uclamp_pct[clamp_id] = req.percent;
+
+ /* Update effective clamps to track the most restrictive value */
+ cpu_util_update_eff(of_css(of));
+
+ rcu_read_unlock();
+ mutex_unlock(&uclamp_mutex);
+
+ return nbytes;
+}
+
+static ssize_t cpu_uclamp_min_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes,
+ loff_t off)
+{
+ return cpu_uclamp_write(of, buf, nbytes, off, UCLAMP_MIN);
+}
+
+static ssize_t cpu_uclamp_max_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes,
+ loff_t off)
+{
+ return cpu_uclamp_write(of, buf, nbytes, off, UCLAMP_MAX);
+}
+
+static inline void cpu_uclamp_print(struct seq_file *sf,
+ enum uclamp_id clamp_id)
+{
+ struct task_group *tg;
+ u64 util_clamp;
+ u64 percent;
+ u32 rem;
+
+ rcu_read_lock();
+ tg = css_tg(seq_css(sf));
+ util_clamp = tg->uclamp_req[clamp_id].value;
+ rcu_read_unlock();
+
+ if (util_clamp == SCHED_CAPACITY_SCALE) {
+ seq_puts(sf, "max\n");
+ return;
+ }
+
+ percent = tg->uclamp_pct[clamp_id];
+ percent = div_u64_rem(percent, POW10(UCLAMP_PERCENT_SHIFT), &rem);
+ seq_printf(sf, "%llu.%0*u\n", percent, UCLAMP_PERCENT_SHIFT, rem);
+}
+
+static int cpu_uclamp_min_show(struct seq_file *sf, void *v)
+{
+ cpu_uclamp_print(sf, UCLAMP_MIN);
+ return 0;
+}
+
+static int cpu_uclamp_max_show(struct seq_file *sf, void *v)
+{
+ cpu_uclamp_print(sf, UCLAMP_MAX);
+ return 0;
+}
+#endif /* CONFIG_UCLAMP_TASK_GROUP */
+
#ifdef CONFIG_FAIR_GROUP_SCHED
static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
struct cftype *cftype, u64 shareval)
@@ -7359,6 +7692,20 @@ static struct cftype cpu_legacy_files[] = {
.write_u64 = cpu_rt_period_write_uint,
},
#endif
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+ {
+ .name = "uclamp.min",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = cpu_uclamp_min_show,
+ .write = cpu_uclamp_min_write,
+ },
+ {
+ .name = "uclamp.max",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = cpu_uclamp_max_show,
+ .write = cpu_uclamp_max_write,
+ },
+#endif
{ } /* Terminate */
};
@@ -7526,6 +7873,20 @@ static struct cftype cpu_files[] = {
.write = cpu_max_write,
},
#endif
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+ {
+ .name = "uclamp.min",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = cpu_uclamp_min_show,
+ .write = cpu_uclamp_min_write,
+ },
+ {
+ .name = "uclamp.max",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = cpu_uclamp_max_show,
+ .write = cpu_uclamp_max_write,
+ },
+#endif
{ } /* terminate */
};
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 867b4bb6d4be..fdce9cfaca05 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -263,9 +263,9 @@ unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs,
* irq metric. Because IRQ/steal time is hidden from the task clock we
* need to scale the task numbers:
*
- * 1 - irq
- * U' = irq + ------- * U
- * max
+ * max - irq
+ * U' = irq + --------- * U
+ * max
*/
util = scale_irq_capacity(util, irq, max);
util += irq;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 46122edd8552..39dc9f74f289 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -529,6 +529,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq);
static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p)
{
struct rq *later_rq = NULL;
+ struct dl_bw *dl_b;
later_rq = find_lock_later_rq(p, rq);
if (!later_rq) {
@@ -557,6 +558,38 @@ static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p
double_lock_balance(rq, later_rq);
}
+ if (p->dl.dl_non_contending || p->dl.dl_throttled) {
+ /*
+ * Inactive timer is armed (or callback is running, but
+ * waiting for us to release rq locks). In any case, when it
+ * will fire (or continue), it will see running_bw of this
+ * task migrated to later_rq (and correctly handle it).
+ */
+ sub_running_bw(&p->dl, &rq->dl);
+ sub_rq_bw(&p->dl, &rq->dl);
+
+ add_rq_bw(&p->dl, &later_rq->dl);
+ add_running_bw(&p->dl, &later_rq->dl);
+ } else {
+ sub_rq_bw(&p->dl, &rq->dl);
+ add_rq_bw(&p->dl, &later_rq->dl);
+ }
+
+ /*
+ * And we finally need to fixup root_domain(s) bandwidth accounting,
+ * since p is still hanging out in the old (now moved to default) root
+ * domain.
+ */
+ dl_b = &rq->rd->dl_bw;
+ raw_spin_lock(&dl_b->lock);
+ __dl_sub(dl_b, p->dl.dl_bw, cpumask_weight(rq->rd->span));
+ raw_spin_unlock(&dl_b->lock);
+
+ dl_b = &later_rq->rd->dl_bw;
+ raw_spin_lock(&dl_b->lock);
+ __dl_add(dl_b, p->dl.dl_bw, cpumask_weight(later_rq->rd->span));
+ raw_spin_unlock(&dl_b->lock);
+
set_task_cpu(p, later_rq->cpu);
double_unlock_balance(later_rq, rq);
@@ -1694,12 +1727,20 @@ static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
}
#endif
-static inline void set_next_task(struct rq *rq, struct task_struct *p)
+static void set_next_task_dl(struct rq *rq, struct task_struct *p)
{
p->se.exec_start = rq_clock_task(rq);
/* You can't push away the running task */
dequeue_pushable_dl_task(rq, p);
+
+ if (hrtick_enabled(rq))
+ start_hrtick_dl(rq, p);
+
+ if (rq->curr->sched_class != &dl_sched_class)
+ update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0);
+
+ deadline_queue_push_tasks(rq);
}
static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
@@ -1720,64 +1761,42 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
struct task_struct *p;
struct dl_rq *dl_rq;
- dl_rq = &rq->dl;
+ WARN_ON_ONCE(prev || rf);
- if (need_pull_dl_task(rq, prev)) {
- /*
- * This is OK, because current is on_cpu, which avoids it being
- * picked for load-balance and preemption/IRQs are still
- * disabled avoiding further scheduler activity on it and we're
- * being very careful to re-start the picking loop.
- */
- rq_unpin_lock(rq, rf);
- pull_dl_task(rq);
- rq_repin_lock(rq, rf);
- /*
- * pull_dl_task() can drop (and re-acquire) rq->lock; this
- * means a stop task can slip in, in which case we need to
- * re-start task selection.
- */
- if (rq->stop && task_on_rq_queued(rq->stop))
- return RETRY_TASK;
- }
-
- /*
- * When prev is DL, we may throttle it in put_prev_task().
- * So, we update time before we check for dl_nr_running.
- */
- if (prev->sched_class == &dl_sched_class)
- update_curr_dl(rq);
+ dl_rq = &rq->dl;
if (unlikely(!dl_rq->dl_nr_running))
return NULL;
- put_prev_task(rq, prev);
-
dl_se = pick_next_dl_entity(rq, dl_rq);
BUG_ON(!dl_se);
p = dl_task_of(dl_se);
- set_next_task(rq, p);
-
- if (hrtick_enabled(rq))
- start_hrtick_dl(rq, p);
-
- deadline_queue_push_tasks(rq);
-
- if (rq->curr->sched_class != &dl_sched_class)
- update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0);
+ set_next_task_dl(rq, p);
return p;
}
-static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
+static void put_prev_task_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
{
update_curr_dl(rq);
update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1);
if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
enqueue_pushable_dl_task(rq, p);
+
+ if (rf && !on_dl_rq(&p->dl) && need_pull_dl_task(rq, p)) {
+ /*
+ * This is OK, because current is on_cpu, which avoids it being
+ * picked for load-balance and preemption/IRQs are still
+ * disabled avoiding further scheduler activity on it and we've
+ * not yet started the picking loop.
+ */
+ rq_unpin_lock(rq, rf);
+ pull_dl_task(rq);
+ rq_repin_lock(rq, rf);
+ }
}
/*
@@ -1811,11 +1830,6 @@ static void task_fork_dl(struct task_struct *p)
*/
}
-static void set_curr_task_dl(struct rq *rq)
-{
- set_next_task(rq, rq->curr);
-}
-
#ifdef CONFIG_SMP
/* Only try algorithms three times */
@@ -2275,6 +2289,36 @@ void __init init_sched_dl_class(void)
GFP_KERNEL, cpu_to_node(i));
}
+void dl_add_task_root_domain(struct task_struct *p)
+{
+ struct rq_flags rf;
+ struct rq *rq;
+ struct dl_bw *dl_b;
+
+ rq = task_rq_lock(p, &rf);
+ if (!dl_task(p))
+ goto unlock;
+
+ dl_b = &rq->rd->dl_bw;
+ raw_spin_lock(&dl_b->lock);
+
+ __dl_add(dl_b, p->dl.dl_bw, cpumask_weight(rq->rd->span));
+
+ raw_spin_unlock(&dl_b->lock);
+
+unlock:
+ task_rq_unlock(rq, p, &rf);
+}
+
+void dl_clear_root_domain(struct root_domain *rd)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&rd->dl_bw.lock, flags);
+ rd->dl_bw.total_bw = 0;
+ raw_spin_unlock_irqrestore(&rd->dl_bw.lock, flags);
+}
+
#endif /* CONFIG_SMP */
static void switched_from_dl(struct rq *rq, struct task_struct *p)
@@ -2395,6 +2439,7 @@ const struct sched_class dl_sched_class = {
.pick_next_task = pick_next_task_dl,
.put_prev_task = put_prev_task_dl,
+ .set_next_task = set_next_task_dl,
#ifdef CONFIG_SMP
.select_task_rq = select_task_rq_dl,
@@ -2405,7 +2450,6 @@ const struct sched_class dl_sched_class = {
.task_woken = task_woken_dl,
#endif
- .set_curr_task = set_curr_task_dl,
.task_tick = task_tick_dl,
.task_fork = task_fork_dl,
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 500f5db0de0b..d4bbf68c3161 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -96,12 +96,12 @@ int __weak arch_asym_cpu_priority(int cpu)
}
/*
- * The margin used when comparing utilization with CPU capacity:
- * util * margin < capacity * 1024
+ * The margin used when comparing utilization with CPU capacity.
*
* (default: ~20%)
*/
-static unsigned int capacity_margin = 1280;
+#define fits_capacity(cap, max) ((cap) * 1280 < (max) * 1024)
+
#endif
#ifdef CONFIG_CFS_BANDWIDTH
@@ -1188,47 +1188,6 @@ static unsigned int task_scan_max(struct task_struct *p)
return max(smin, smax);
}
-void init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
-{
- int mm_users = 0;
- struct mm_struct *mm = p->mm;
-
- if (mm) {
- mm_users = atomic_read(&mm->mm_users);
- if (mm_users == 1) {
- mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
- mm->numa_scan_seq = 0;
- }
- }
- p->node_stamp = 0;
- p->numa_scan_seq = mm ? mm->numa_scan_seq : 0;
- p->numa_scan_period = sysctl_numa_balancing_scan_delay;
- p->numa_work.next = &p->numa_work;
- p->numa_faults = NULL;
- RCU_INIT_POINTER(p->numa_group, NULL);
- p->last_task_numa_placement = 0;
- p->last_sum_exec_runtime = 0;
-
- /* New address space, reset the preferred nid */
- if (!(clone_flags & CLONE_VM)) {
- p->numa_preferred_nid = NUMA_NO_NODE;
- return;
- }
-
- /*
- * New thread, keep existing numa_preferred_nid which should be copied
- * already by arch_dup_task_struct but stagger when scans start.
- */
- if (mm) {
- unsigned int delay;
-
- delay = min_t(unsigned int, task_scan_max(current),
- current->numa_scan_period * mm_users * NSEC_PER_MSEC);
- delay += 2 * TICK_NSEC;
- p->node_stamp = delay;
- }
-}
-
static void account_numa_enqueue(struct rq *rq, struct task_struct *p)
{
rq->nr_numa_running += (p->numa_preferred_nid != NUMA_NO_NODE);
@@ -2523,7 +2482,7 @@ static void reset_ptenuma_scan(struct task_struct *p)
* The expensive part of numa migration is done from task_work context.
* Triggered from task_tick_numa().
*/
-void task_numa_work(struct callback_head *work)
+static void task_numa_work(struct callback_head *work)
{
unsigned long migrate, next_scan, now = jiffies;
struct task_struct *p = current;
@@ -2536,7 +2495,7 @@ void task_numa_work(struct callback_head *work)
SCHED_WARN_ON(p != container_of(work, struct task_struct, numa_work));
- work->next = work; /* protect against double add */
+ work->next = work;
/*
* Who cares about NUMA placement when they're dying.
*
@@ -2665,6 +2624,50 @@ out:
}
}
+void init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
+{
+ int mm_users = 0;
+ struct mm_struct *mm = p->mm;
+
+ if (mm) {
+ mm_users = atomic_read(&mm->mm_users);
+ if (mm_users == 1) {
+ mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
+ mm->numa_scan_seq = 0;
+ }
+ }
+ p->node_stamp = 0;
+ p->numa_scan_seq = mm ? mm->numa_scan_seq : 0;
+ p->numa_scan_period = sysctl_numa_balancing_scan_delay;
+ /* Protect against double add, see task_tick_numa and task_numa_work */
+ p->numa_work.next = &p->numa_work;
+ p->numa_faults = NULL;
+ RCU_INIT_POINTER(p->numa_group, NULL);
+ p->last_task_numa_placement = 0;
+ p->last_sum_exec_runtime = 0;
+
+ init_task_work(&p->numa_work, task_numa_work);
+
+ /* New address space, reset the preferred nid */
+ if (!(clone_flags & CLONE_VM)) {
+ p->numa_preferred_nid = NUMA_NO_NODE;
+ return;
+ }
+
+ /*
+ * New thread, keep existing numa_preferred_nid which should be copied
+ * already by arch_dup_task_struct but stagger when scans start.
+ */
+ if (mm) {
+ unsigned int delay;
+
+ delay = min_t(unsigned int, task_scan_max(current),
+ current->numa_scan_period * mm_users * NSEC_PER_MSEC);
+ delay += 2 * TICK_NSEC;
+ p->node_stamp = delay;
+ }
+}
+
/*
* Drive the periodic memory faults..
*/
@@ -2693,10 +2696,8 @@ static void task_tick_numa(struct rq *rq, struct task_struct *curr)
curr->numa_scan_period = task_scan_start(curr);
curr->node_stamp += period;
- if (!time_before(jiffies, curr->mm->numa_next_scan)) {
- init_task_work(work, task_numa_work); /* TODO: move this into sched_fork() */
+ if (!time_before(jiffies, curr->mm->numa_next_scan))
task_work_add(curr, work, true);
- }
}
}
@@ -3689,8 +3690,6 @@ static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq)
return cfs_rq->avg.load_avg;
}
-static int idle_balance(struct rq *this_rq, struct rq_flags *rf);
-
static inline unsigned long task_util(struct task_struct *p)
{
return READ_ONCE(p->se.avg.util_avg);
@@ -3807,7 +3806,7 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
static inline int task_fits_capacity(struct task_struct *p, long capacity)
{
- return capacity * 1024 > task_util_est(p) * capacity_margin;
+ return fits_capacity(task_util_est(p), capacity);
}
static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
@@ -4370,8 +4369,6 @@ void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)
now = sched_clock_cpu(smp_processor_id());
cfs_b->runtime = cfs_b->quota;
- cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period);
- cfs_b->expires_seq++;
}
static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
@@ -4393,8 +4390,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
{
struct task_group *tg = cfs_rq->tg;
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
- u64 amount = 0, min_amount, expires;
- int expires_seq;
+ u64 amount = 0, min_amount;
/* note: this is a positive sum as runtime_remaining <= 0 */
min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining;
@@ -4411,61 +4407,17 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
cfs_b->idle = 0;
}
}
- expires_seq = cfs_b->expires_seq;
- expires = cfs_b->runtime_expires;
raw_spin_unlock(&cfs_b->lock);
cfs_rq->runtime_remaining += amount;
- /*
- * we may have advanced our local expiration to account for allowed
- * spread between our sched_clock and the one on which runtime was
- * issued.
- */
- if (cfs_rq->expires_seq != expires_seq) {
- cfs_rq->expires_seq = expires_seq;
- cfs_rq->runtime_expires = expires;
- }
return cfs_rq->runtime_remaining > 0;
}
-/*
- * Note: This depends on the synchronization provided by sched_clock and the
- * fact that rq->clock snapshots this value.
- */
-static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
-{
- struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
-
- /* if the deadline is ahead of our clock, nothing to do */
- if (likely((s64)(rq_clock(rq_of(cfs_rq)) - cfs_rq->runtime_expires) < 0))
- return;
-
- if (cfs_rq->runtime_remaining < 0)
- return;
-
- /*
- * If the local deadline has passed we have to consider the
- * possibility that our sched_clock is 'fast' and the global deadline
- * has not truly expired.
- *
- * Fortunately we can check determine whether this the case by checking
- * whether the global deadline(cfs_b->expires_seq) has advanced.
- */
- if (cfs_rq->expires_seq == cfs_b->expires_seq) {
- /* extend local deadline, drift is bounded above by 2 ticks */
- cfs_rq->runtime_expires += TICK_NSEC;
- } else {
- /* global deadline is ahead, expiration has passed */
- cfs_rq->runtime_remaining = 0;
- }
-}
-
static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
{
/* dock delta_exec before expiring quota (as it could span periods) */
cfs_rq->runtime_remaining -= delta_exec;
- expire_cfs_rq_runtime(cfs_rq);
if (likely(cfs_rq->runtime_remaining > 0))
return;
@@ -4556,7 +4508,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
struct rq *rq = rq_of(cfs_rq);
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
struct sched_entity *se;
- long task_delta, dequeue = 1;
+ long task_delta, idle_task_delta, dequeue = 1;
bool empty;
se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
@@ -4567,6 +4519,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
rcu_read_unlock();
task_delta = cfs_rq->h_nr_running;
+ idle_task_delta = cfs_rq->idle_h_nr_running;
for_each_sched_entity(se) {
struct cfs_rq *qcfs_rq = cfs_rq_of(se);
/* throttled entity or throttle-on-deactivate */
@@ -4576,6 +4529,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
if (dequeue)
dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
qcfs_rq->h_nr_running -= task_delta;
+ qcfs_rq->idle_h_nr_running -= idle_task_delta;
if (qcfs_rq->load.weight)
dequeue = 0;
@@ -4615,7 +4569,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
struct sched_entity *se;
int enqueue = 1;
- long task_delta;
+ long task_delta, idle_task_delta;
se = cfs_rq->tg->se[cpu_of(rq)];
@@ -4635,6 +4589,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
return;
task_delta = cfs_rq->h_nr_running;
+ idle_task_delta = cfs_rq->idle_h_nr_running;
for_each_sched_entity(se) {
if (se->on_rq)
enqueue = 0;
@@ -4643,6 +4598,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
if (enqueue)
enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
cfs_rq->h_nr_running += task_delta;
+ cfs_rq->idle_h_nr_running += idle_task_delta;
if (cfs_rq_throttled(cfs_rq))
break;
@@ -4658,8 +4614,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
resched_curr(rq);
}
-static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b,
- u64 remaining, u64 expires)
+static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining)
{
struct cfs_rq *cfs_rq;
u64 runtime;
@@ -4684,7 +4639,6 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b,
remaining -= runtime;
cfs_rq->runtime_remaining += runtime;
- cfs_rq->runtime_expires = expires;
/* we check whether we're throttled above */
if (cfs_rq->runtime_remaining > 0)
@@ -4709,7 +4663,7 @@ next:
*/
static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, unsigned long flags)
{
- u64 runtime, runtime_expires;
+ u64 runtime;
int throttled;
/* no need to continue the timer with no bandwidth constraint */
@@ -4737,8 +4691,6 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u
/* account preceding periods in which throttling occurred */
cfs_b->nr_throttled += overrun;
- runtime_expires = cfs_b->runtime_expires;
-
/*
* This check is repeated as we are holding onto the new bandwidth while
* we unthrottle. This can potentially race with an unthrottled group
@@ -4751,8 +4703,7 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u
cfs_b->distribute_running = 1;
raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
/* we can't nest cfs_b->lock while distributing bandwidth */
- runtime = distribute_cfs_runtime(cfs_b, runtime,
- runtime_expires);
+ runtime = distribute_cfs_runtime(cfs_b, runtime);
raw_spin_lock_irqsave(&cfs_b->lock, flags);
cfs_b->distribute_running = 0;
@@ -4834,8 +4785,7 @@ static void __return_cfs_rq_runtime(struct cfs_rq *cfs_rq)
return;
raw_spin_lock(&cfs_b->lock);
- if (cfs_b->quota != RUNTIME_INF &&
- cfs_rq->runtime_expires == cfs_b->runtime_expires) {
+ if (cfs_b->quota != RUNTIME_INF) {
cfs_b->runtime += slack_runtime;
/* we are under rq->lock, defer unthrottling using a timer */
@@ -4868,7 +4818,6 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
{
u64 runtime = 0, slice = sched_cfs_bandwidth_slice();
unsigned long flags;
- u64 expires;
/* confirm we're still not at a refresh boundary */
raw_spin_lock_irqsave(&cfs_b->lock, flags);
@@ -4886,7 +4835,6 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice)
runtime = cfs_b->runtime;
- expires = cfs_b->runtime_expires;
if (runtime)
cfs_b->distribute_running = 1;
@@ -4895,11 +4843,10 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
if (!runtime)
return;
- runtime = distribute_cfs_runtime(cfs_b, runtime, expires);
+ runtime = distribute_cfs_runtime(cfs_b, runtime);
raw_spin_lock_irqsave(&cfs_b->lock, flags);
- if (expires == cfs_b->runtime_expires)
- lsub_positive(&cfs_b->runtime, runtime);
+ lsub_positive(&cfs_b->runtime, runtime);
cfs_b->distribute_running = 0;
raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
}
@@ -5056,8 +5003,6 @@ void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
cfs_b->period_active = 1;
overrun = hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
- cfs_b->runtime_expires += (overrun + 1) * ktime_to_ns(cfs_b->period);
- cfs_b->expires_seq++;
hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
}
@@ -5235,7 +5180,7 @@ static inline unsigned long cpu_util(int cpu);
static inline bool cpu_overutilized(int cpu)
{
- return (capacity_of(cpu) * 1024) < (cpu_util(cpu) * capacity_margin);
+ return !fits_capacity(cpu_util(cpu), capacity_of(cpu));
}
static inline void update_overutilized_status(struct rq *rq)
@@ -5259,6 +5204,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se;
+ int idle_h_nr_running = task_has_idle_policy(p);
/*
* The code below (indirectly) updates schedutil which looks at
@@ -5291,6 +5237,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
if (cfs_rq_throttled(cfs_rq))
break;
cfs_rq->h_nr_running++;
+ cfs_rq->idle_h_nr_running += idle_h_nr_running;
flags = ENQUEUE_WAKEUP;
}
@@ -5298,6 +5245,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
cfs_rq->h_nr_running++;
+ cfs_rq->idle_h_nr_running += idle_h_nr_running;
if (cfs_rq_throttled(cfs_rq))
break;
@@ -5359,6 +5307,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se;
int task_sleep = flags & DEQUEUE_SLEEP;
+ int idle_h_nr_running = task_has_idle_policy(p);
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
@@ -5373,6 +5322,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
if (cfs_rq_throttled(cfs_rq))
break;
cfs_rq->h_nr_running--;
+ cfs_rq->idle_h_nr_running -= idle_h_nr_running;
/* Don't dequeue parent if it has other entities besides us */
if (cfs_rq->load.weight) {
@@ -5392,6 +5342,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
cfs_rq->h_nr_running--;
+ cfs_rq->idle_h_nr_running -= idle_h_nr_running;
if (cfs_rq_throttled(cfs_rq))
break;
@@ -5425,6 +5376,15 @@ static struct {
#endif /* CONFIG_NO_HZ_COMMON */
+/* CPU only has SCHED_IDLE tasks enqueued */
+static int sched_idle_cpu(int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+
+ return unlikely(rq->nr_running == rq->cfs.idle_h_nr_running &&
+ rq->nr_running);
+}
+
static unsigned long cpu_runnable_load(struct rq *rq)
{
return cfs_rq_runnable_load_avg(&rq->cfs);
@@ -5747,7 +5707,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
unsigned int min_exit_latency = UINT_MAX;
u64 latest_idle_timestamp = 0;
int least_loaded_cpu = this_cpu;
- int shallowest_idle_cpu = -1;
+ int shallowest_idle_cpu = -1, si_cpu = -1;
int i;
/* Check if we have any choice: */
@@ -5778,7 +5738,12 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
latest_idle_timestamp = rq->idle_stamp;
shallowest_idle_cpu = i;
}
- } else if (shallowest_idle_cpu == -1) {
+ } else if (shallowest_idle_cpu == -1 && si_cpu == -1) {
+ if (sched_idle_cpu(i)) {
+ si_cpu = i;
+ continue;
+ }
+
load = cpu_runnable_load(cpu_rq(i));
if (load < min_load) {
min_load = load;
@@ -5787,7 +5752,11 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
}
}
- return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu;
+ if (shallowest_idle_cpu != -1)
+ return shallowest_idle_cpu;
+ if (si_cpu != -1)
+ return si_cpu;
+ return least_loaded_cpu;
}
static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p,
@@ -5940,7 +5909,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
*/
static int select_idle_smt(struct task_struct *p, int target)
{
- int cpu;
+ int cpu, si_cpu = -1;
if (!static_branch_likely(&sched_smt_present))
return -1;
@@ -5950,9 +5919,11 @@ static int select_idle_smt(struct task_struct *p, int target)
continue;
if (available_idle_cpu(cpu))
return cpu;
+ if (si_cpu == -1 && sched_idle_cpu(cpu))
+ si_cpu = cpu;
}
- return -1;
+ return si_cpu;
}
#else /* CONFIG_SCHED_SMT */
@@ -5980,8 +5951,8 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
u64 avg_cost, avg_idle;
u64 time, cost;
s64 delta;
- int cpu, nr = INT_MAX;
int this = smp_processor_id();
+ int cpu, nr = INT_MAX, si_cpu = -1;
this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
if (!this_sd)
@@ -6009,11 +5980,13 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
for_each_cpu_wrap(cpu, sched_domain_span(sd), target) {
if (!--nr)
- return -1;
+ return si_cpu;
if (!cpumask_test_cpu(cpu, p->cpus_ptr))
continue;
if (available_idle_cpu(cpu))
break;
+ if (si_cpu == -1 && sched_idle_cpu(cpu))
+ si_cpu = cpu;
}
time = cpu_clock(this) - time;
@@ -6032,13 +6005,14 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
struct sched_domain *sd;
int i, recent_used_cpu;
- if (available_idle_cpu(target))
+ if (available_idle_cpu(target) || sched_idle_cpu(target))
return target;
/*
* If the previous CPU is cache affine and idle, don't be stupid:
*/
- if (prev != target && cpus_share_cache(prev, target) && available_idle_cpu(prev))
+ if (prev != target && cpus_share_cache(prev, target) &&
+ (available_idle_cpu(prev) || sched_idle_cpu(prev)))
return prev;
/* Check a recently used CPU as a potential idle candidate: */
@@ -6046,7 +6020,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
if (recent_used_cpu != prev &&
recent_used_cpu != target &&
cpus_share_cache(recent_used_cpu, target) &&
- available_idle_cpu(recent_used_cpu) &&
+ (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) {
/*
* Replace recent_used_cpu with prev as it is a potential
@@ -6282,69 +6256,55 @@ static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu)
}
/*
- * compute_energy(): Estimates the energy that would be consumed if @p was
+ * compute_energy(): Estimates the energy that @pd would consume if @p was
* migrated to @dst_cpu. compute_energy() predicts what will be the utilization
- * landscape of the * CPUs after the task migration, and uses the Energy Model
+ * landscape of @pd's CPUs after the task migration, and uses the Energy Model
* to compute what would be the energy if we decided to actually migrate that
* task.
*/
static long
compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
{
- unsigned int max_util, util_cfs, cpu_util, cpu_cap;
- unsigned long sum_util, energy = 0;
- struct task_struct *tsk;
+ struct cpumask *pd_mask = perf_domain_span(pd);
+ unsigned long cpu_cap = arch_scale_cpu_capacity(cpumask_first(pd_mask));
+ unsigned long max_util = 0, sum_util = 0;
int cpu;
- for (; pd; pd = pd->next) {
- struct cpumask *pd_mask = perf_domain_span(pd);
+ /*
+ * The capacity state of CPUs of the current rd can be driven by CPUs
+ * of another rd if they belong to the same pd. So, account for the
+ * utilization of these CPUs too by masking pd with cpu_online_mask
+ * instead of the rd span.
+ *
+ * If an entire pd is outside of the current rd, it will not appear in
+ * its pd list and will not be accounted by compute_energy().
+ */
+ for_each_cpu_and(cpu, pd_mask, cpu_online_mask) {
+ unsigned long cpu_util, util_cfs = cpu_util_next(cpu, p, dst_cpu);
+ struct task_struct *tsk = cpu == dst_cpu ? p : NULL;
/*
- * The energy model mandates all the CPUs of a performance
- * domain have the same capacity.
+ * Busy time computation: utilization clamping is not
+ * required since the ratio (sum_util / cpu_capacity)
+ * is already enough to scale the EM reported power
+ * consumption at the (eventually clamped) cpu_capacity.
*/
- cpu_cap = arch_scale_cpu_capacity(cpumask_first(pd_mask));
- max_util = sum_util = 0;
+ sum_util += schedutil_cpu_util(cpu, util_cfs, cpu_cap,
+ ENERGY_UTIL, NULL);
/*
- * The capacity state of CPUs of the current rd can be driven by
- * CPUs of another rd if they belong to the same performance
- * domain. So, account for the utilization of these CPUs too
- * by masking pd with cpu_online_mask instead of the rd span.
- *
- * If an entire performance domain is outside of the current rd,
- * it will not appear in its pd list and will not be accounted
- * by compute_energy().
+ * Performance domain frequency: utilization clamping
+ * must be considered since it affects the selection
+ * of the performance domain frequency.
+ * NOTE: in case RT tasks are running, by default the
+ * FREQUENCY_UTIL's utilization can be max OPP.
*/
- for_each_cpu_and(cpu, pd_mask, cpu_online_mask) {
- util_cfs = cpu_util_next(cpu, p, dst_cpu);
-
- /*
- * Busy time computation: utilization clamping is not
- * required since the ratio (sum_util / cpu_capacity)
- * is already enough to scale the EM reported power
- * consumption at the (eventually clamped) cpu_capacity.
- */
- sum_util += schedutil_cpu_util(cpu, util_cfs, cpu_cap,
- ENERGY_UTIL, NULL);
-
- /*
- * Performance domain frequency: utilization clamping
- * must be considered since it affects the selection
- * of the performance domain frequency.
- * NOTE: in case RT tasks are running, by default the
- * FREQUENCY_UTIL's utilization can be max OPP.
- */
- tsk = cpu == dst_cpu ? p : NULL;
- cpu_util = schedutil_cpu_util(cpu, util_cfs, cpu_cap,
- FREQUENCY_UTIL, tsk);
- max_util = max(max_util, cpu_util);
- }
-
- energy += em_pd_energy(pd->em_pd, max_util, sum_util);
+ cpu_util = schedutil_cpu_util(cpu, util_cfs, cpu_cap,
+ FREQUENCY_UTIL, tsk);
+ max_util = max(max_util, cpu_util);
}
- return energy;
+ return em_pd_energy(pd->em_pd, max_util, sum_util);
}
/*
@@ -6386,21 +6346,19 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
* other use-cases too. So, until someone finds a better way to solve this,
* let's keep things simple by re-using the existing slow path.
*/
-
static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
{
- unsigned long prev_energy = ULONG_MAX, best_energy = ULONG_MAX;
+ unsigned long prev_delta = ULONG_MAX, best_delta = ULONG_MAX;
struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
+ unsigned long cpu_cap, util, base_energy = 0;
int cpu, best_energy_cpu = prev_cpu;
- struct perf_domain *head, *pd;
- unsigned long cpu_cap, util;
struct sched_domain *sd;
+ struct perf_domain *pd;
rcu_read_lock();
pd = rcu_dereference(rd->pd);
if (!pd || READ_ONCE(rd->overutilized))
goto fail;
- head = pd;
/*
* Energy-aware wake-up happens on the lowest sched_domain starting
@@ -6417,9 +6375,14 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
goto unlock;
for (; pd; pd = pd->next) {
- unsigned long cur_energy, spare_cap, max_spare_cap = 0;
+ unsigned long cur_delta, spare_cap, max_spare_cap = 0;
+ unsigned long base_energy_pd;
int max_spare_cap_cpu = -1;
+ /* Compute the 'base' energy of the pd, without @p */
+ base_energy_pd = compute_energy(p, -1, pd);
+ base_energy += base_energy_pd;
+
for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) {
if (!cpumask_test_cpu(cpu, p->cpus_ptr))
continue;
@@ -6427,14 +6390,14 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
/* Skip CPUs that will be overutilized. */
util = cpu_util_next(cpu, p, cpu);
cpu_cap = capacity_of(cpu);
- if (cpu_cap * 1024 < util * capacity_margin)
+ if (!fits_capacity(util, cpu_cap))
continue;
/* Always use prev_cpu as a candidate. */
if (cpu == prev_cpu) {
- prev_energy = compute_energy(p, prev_cpu, head);
- best_energy = min(best_energy, prev_energy);
- continue;
+ prev_delta = compute_energy(p, prev_cpu, pd);
+ prev_delta -= base_energy_pd;
+ best_delta = min(best_delta, prev_delta);
}
/*
@@ -6450,9 +6413,10 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
/* Evaluate the energy impact of using this CPU. */
if (max_spare_cap_cpu >= 0) {
- cur_energy = compute_energy(p, max_spare_cap_cpu, head);
- if (cur_energy < best_energy) {
- best_energy = cur_energy;
+ cur_delta = compute_energy(p, max_spare_cap_cpu, pd);
+ cur_delta -= base_energy_pd;
+ if (cur_delta < best_delta) {
+ best_delta = cur_delta;
best_energy_cpu = max_spare_cap_cpu;
}
}
@@ -6464,10 +6428,10 @@ unlock:
* Pick the best CPU if prev_cpu cannot be used, or if it saves at
* least 6% of the energy used by prev_cpu.
*/
- if (prev_energy == ULONG_MAX)
+ if (prev_delta == ULONG_MAX)
return best_energy_cpu;
- if ((prev_energy - best_energy) > (prev_energy >> 4))
+ if ((prev_delta - best_delta) > ((prev_delta + base_energy) >> 4))
return best_energy_cpu;
return prev_cpu;
@@ -6801,7 +6765,7 @@ again:
goto idle;
#ifdef CONFIG_FAIR_GROUP_SCHED
- if (prev->sched_class != &fair_sched_class)
+ if (!prev || prev->sched_class != &fair_sched_class)
goto simple;
/*
@@ -6878,8 +6842,8 @@ again:
goto done;
simple:
#endif
-
- put_prev_task(rq, prev);
+ if (prev)
+ put_prev_task(rq, prev);
do {
se = pick_next_entity(cfs_rq, NULL);
@@ -6907,11 +6871,13 @@ done: __maybe_unused;
return p;
idle:
- update_misfit_status(NULL, rq);
- new_tasks = idle_balance(rq, rf);
+ if (!rf)
+ return NULL;
+
+ new_tasks = newidle_balance(rq, rf);
/*
- * Because idle_balance() releases (and re-acquires) rq->lock, it is
+ * Because newidle_balance() releases (and re-acquires) rq->lock, it is
* possible for any higher priority task to appear. In that case we
* must re-start the pick_next_entity() loop.
*/
@@ -6933,7 +6899,7 @@ idle:
/*
* Account for a descheduled task:
*/
-static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
+static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct sched_entity *se = &prev->se;
struct cfs_rq *cfs_rq;
@@ -7435,7 +7401,7 @@ static int detach_tasks(struct lb_env *env)
detached++;
env->imbalance -= load;
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
/*
* NEWIDLE balancing is a source of latency, so preemptible
* kernels will stop after the first task is detached to minimize
@@ -7982,8 +7948,7 @@ group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs)
static inline bool
group_smaller_min_cpu_capacity(struct sched_group *sg, struct sched_group *ref)
{
- return sg->sgc->min_capacity * capacity_margin <
- ref->sgc->min_capacity * 1024;
+ return fits_capacity(sg->sgc->min_capacity, ref->sgc->min_capacity);
}
/*
@@ -7993,8 +7958,7 @@ group_smaller_min_cpu_capacity(struct sched_group *sg, struct sched_group *ref)
static inline bool
group_smaller_max_cpu_capacity(struct sched_group *sg, struct sched_group *ref)
{
- return sg->sgc->max_capacity * capacity_margin <
- ref->sgc->max_capacity * 1024;
+ return fits_capacity(sg->sgc->max_capacity, ref->sgc->max_capacity);
}
static inline enum
@@ -9052,9 +9016,10 @@ more_balance:
out_balanced:
/*
* We reach balance although we may have faced some affinity
- * constraints. Clear the imbalance flag if it was set.
+ * constraints. Clear the imbalance flag only if other tasks got
+ * a chance to move and fix the imbalance.
*/
- if (sd_parent) {
+ if (sd_parent && !(env.flags & LBF_ALL_PINNED)) {
int *group_imbalance = &sd_parent->groups->sgc->imbalance;
if (*group_imbalance)
@@ -9075,10 +9040,10 @@ out_one_pinned:
ld_moved = 0;
/*
- * idle_balance() disregards balance intervals, so we could repeatedly
- * reach this code, which would lead to balance_interval skyrocketting
- * in a short amount of time. Skip the balance_interval increase logic
- * to avoid that.
+ * newidle_balance() disregards balance intervals, so we could
+ * repeatedly reach this code, which would lead to balance_interval
+ * skyrocketting in a short amount of time. Skip the balance_interval
+ * increase logic to avoid that.
*/
if (env.idle == CPU_NEWLY_IDLE)
goto out;
@@ -9788,7 +9753,7 @@ static inline void nohz_newidle_balance(struct rq *this_rq) { }
* idle_balance is called by schedule() if this_cpu is about to become
* idle. Attempts to pull tasks from other CPUs.
*/
-static int idle_balance(struct rq *this_rq, struct rq_flags *rf)
+int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
{
unsigned long next_balance = jiffies + HZ;
int this_cpu = this_rq->cpu;
@@ -9796,6 +9761,7 @@ static int idle_balance(struct rq *this_rq, struct rq_flags *rf)
int pulled_task = 0;
u64 curr_cost = 0;
+ update_misfit_status(NULL, this_rq);
/*
* We must set idle_stamp _before_ calling idle_balance(), such that we
* measure the duration of idle_balance() as idle time.
@@ -10180,9 +10146,19 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p)
* This routine is mostly called to set cfs_rq->curr field when a task
* migrates between groups/classes.
*/
-static void set_curr_task_fair(struct rq *rq)
+static void set_next_task_fair(struct rq *rq, struct task_struct *p)
{
- struct sched_entity *se = &rq->curr->se;
+ struct sched_entity *se = &p->se;
+
+#ifdef CONFIG_SMP
+ if (task_on_rq_queued(p)) {
+ /*
+ * Move the next running task to the front of the list, so our
+ * cfs_tasks list becomes MRU one.
+ */
+ list_move(&se->group_node, &rq->cfs_tasks);
+ }
+#endif
for_each_sched_entity(se) {
struct cfs_rq *cfs_rq = cfs_rq_of(se);
@@ -10300,18 +10276,18 @@ err:
void online_fair_sched_group(struct task_group *tg)
{
struct sched_entity *se;
+ struct rq_flags rf;
struct rq *rq;
int i;
for_each_possible_cpu(i) {
rq = cpu_rq(i);
se = tg->se[i];
-
- raw_spin_lock_irq(&rq->lock);
+ rq_lock_irq(rq, &rf);
update_rq_clock(rq);
attach_entity_cfs_rq(se);
sync_throttle(tg, i);
- raw_spin_unlock_irq(&rq->lock);
+ rq_unlock_irq(rq, &rf);
}
}
@@ -10453,7 +10429,9 @@ const struct sched_class fair_sched_class = {
.check_preempt_curr = check_preempt_wakeup,
.pick_next_task = pick_next_task_fair,
+
.put_prev_task = put_prev_task_fair,
+ .set_next_task = set_next_task_fair,
#ifdef CONFIG_SMP
.select_task_rq = select_task_rq_fair,
@@ -10466,7 +10444,6 @@ const struct sched_class fair_sched_class = {
.set_cpus_allowed = set_cpus_allowed_common,
#endif
- .set_curr_task = set_curr_task_fair,
.task_tick = task_tick_fair,
.task_fork = task_fork_fair,
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index e4bc4aa739b8..8bfeb6395bdd 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -375,14 +375,27 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
resched_curr(rq);
}
-static struct task_struct *
-pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+{
+}
+
+static void set_next_task_idle(struct rq *rq, struct task_struct *next)
{
- put_prev_task(rq, prev);
update_idle_core(rq);
schedstat_inc(rq->sched_goidle);
+}
+
+static struct task_struct *
+pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+{
+ struct task_struct *next = rq->idle;
+
+ if (prev)
+ put_prev_task(rq, prev);
+
+ set_next_task_idle(rq, next);
- return rq->idle;
+ return next;
}
/*
@@ -398,10 +411,6 @@ dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
raw_spin_lock_irq(&rq->lock);
}
-static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
-{
-}
-
/*
* scheduler tick hitting a task of our scheduling class.
*
@@ -414,10 +423,6 @@ static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued)
{
}
-static void set_curr_task_idle(struct rq *rq)
-{
-}
-
static void switched_to_idle(struct rq *rq, struct task_struct *p)
{
BUG();
@@ -452,13 +457,13 @@ const struct sched_class idle_sched_class = {
.pick_next_task = pick_next_task_idle,
.put_prev_task = put_prev_task_idle,
+ .set_next_task = set_next_task_idle,
#ifdef CONFIG_SMP
.select_task_rq = select_task_rq_idle,
.set_cpus_allowed = set_cpus_allowed_common,
#endif
- .set_curr_task = set_curr_task_idle,
.task_tick = task_tick_idle,
.get_rr_interval = get_rr_interval_idle,
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index ccb28085b114..9fcb2a695a41 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -22,9 +22,17 @@ EXPORT_SYMBOL_GPL(housekeeping_enabled);
int housekeeping_any_cpu(enum hk_flags flags)
{
- if (static_branch_unlikely(&housekeeping_overridden))
- if (housekeeping_flags & flags)
+ int cpu;
+
+ if (static_branch_unlikely(&housekeeping_overridden)) {
+ if (housekeeping_flags & flags) {
+ cpu = sched_numa_find_closest(housekeeping_mask, smp_processor_id());
+ if (cpu < nr_cpu_ids)
+ return cpu;
+
return cpumask_any_and(housekeeping_mask, cpu_online_mask);
+ }
+ }
return smp_processor_id();
}
EXPORT_SYMBOL_GPL(housekeeping_any_cpu);
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 6e52b67b420e..517e3719027e 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -1198,7 +1198,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf,
if (static_branch_likely(&psi_disabled))
return -EOPNOTSUPP;
- buf_size = min(nbytes, (sizeof(buf) - 1));
+ buf_size = min(nbytes, sizeof(buf));
if (copy_from_user(buf, user_buf, buf_size))
return -EFAULT;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index a532558a5176..858c4cc6f99b 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1498,12 +1498,22 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag
#endif
}
-static inline void set_next_task(struct rq *rq, struct task_struct *p)
+static inline void set_next_task_rt(struct rq *rq, struct task_struct *p)
{
p->se.exec_start = rq_clock_task(rq);
/* The running task is never eligible for pushing */
dequeue_pushable_task(rq, p);
+
+ /*
+ * If prev task was rt, put_prev_task() has already updated the
+ * utilization. We only care of the case where we start to schedule a
+ * rt task
+ */
+ if (rq->curr->sched_class != &rt_sched_class)
+ update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0);
+
+ rt_queue_push_tasks(rq);
}
static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
@@ -1543,56 +1553,19 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
struct task_struct *p;
struct rt_rq *rt_rq = &rq->rt;
- if (need_pull_rt_task(rq, prev)) {
- /*
- * This is OK, because current is on_cpu, which avoids it being
- * picked for load-balance and preemption/IRQs are still
- * disabled avoiding further scheduler activity on it and we're
- * being very careful to re-start the picking loop.
- */
- rq_unpin_lock(rq, rf);
- pull_rt_task(rq);
- rq_repin_lock(rq, rf);
- /*
- * pull_rt_task() can drop (and re-acquire) rq->lock; this
- * means a dl or stop task can slip in, in which case we need
- * to re-start task selection.
- */
- if (unlikely((rq->stop && task_on_rq_queued(rq->stop)) ||
- rq->dl.dl_nr_running))
- return RETRY_TASK;
- }
-
- /*
- * We may dequeue prev's rt_rq in put_prev_task().
- * So, we update time before rt_queued check.
- */
- if (prev->sched_class == &rt_sched_class)
- update_curr_rt(rq);
+ WARN_ON_ONCE(prev || rf);
if (!rt_rq->rt_queued)
return NULL;
- put_prev_task(rq, prev);
-
p = _pick_next_task_rt(rq);
- set_next_task(rq, p);
-
- rt_queue_push_tasks(rq);
-
- /*
- * If prev task was rt, put_prev_task() has already updated the
- * utilization. We only care of the case where we start to schedule a
- * rt task
- */
- if (rq->curr->sched_class != &rt_sched_class)
- update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0);
+ set_next_task_rt(rq, p);
return p;
}
-static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
+static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
{
update_curr_rt(rq);
@@ -1604,6 +1577,18 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
*/
if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
enqueue_pushable_task(rq, p);
+
+ if (rf && !on_rt_rq(&p->rt) && need_pull_rt_task(rq, p)) {
+ /*
+ * This is OK, because current is on_cpu, which avoids it being
+ * picked for load-balance and preemption/IRQs are still
+ * disabled avoiding further scheduler activity on it and we've
+ * not yet started the picking loop.
+ */
+ rq_unpin_lock(rq, rf);
+ pull_rt_task(rq);
+ rq_repin_lock(rq, rf);
+ }
}
#ifdef CONFIG_SMP
@@ -2354,11 +2339,6 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
}
}
-static void set_curr_task_rt(struct rq *rq)
-{
- set_next_task(rq, rq->curr);
-}
-
static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
{
/*
@@ -2380,6 +2360,7 @@ const struct sched_class rt_sched_class = {
.pick_next_task = pick_next_task_rt,
.put_prev_task = put_prev_task_rt,
+ .set_next_task = set_next_task_rt,
#ifdef CONFIG_SMP
.select_task_rq = select_task_rq_rt,
@@ -2391,7 +2372,6 @@ const struct sched_class rt_sched_class = {
.switched_from = switched_from_rt,
#endif
- .set_curr_task = set_curr_task_rt,
.task_tick = task_tick_rt,
.get_rr_interval = get_rr_interval_rt,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 802b1f3405f2..b3cb895d14a2 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -335,8 +335,6 @@ struct cfs_bandwidth {
u64 quota;
u64 runtime;
s64 hierarchical_quota;
- u64 runtime_expires;
- int expires_seq;
u8 idle;
u8 period_active;
@@ -393,6 +391,16 @@ struct task_group {
#endif
struct cfs_bandwidth cfs_bandwidth;
+
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+ /* The two decimal precision [%] value requested from user-space */
+ unsigned int uclamp_pct[UCLAMP_CNT];
+ /* Clamp values requested for a task group */
+ struct uclamp_se uclamp_req[UCLAMP_CNT];
+ /* Effective clamp values used for a task group */
+ struct uclamp_se uclamp[UCLAMP_CNT];
+#endif
+
};
#ifdef CONFIG_FAIR_GROUP_SCHED
@@ -483,7 +491,8 @@ struct cfs_rq {
struct load_weight load;
unsigned long runnable_weight;
unsigned int nr_running;
- unsigned int h_nr_running;
+ unsigned int h_nr_running; /* SCHED_{NORMAL,BATCH,IDLE} */
+ unsigned int idle_h_nr_running; /* SCHED_IDLE */
u64 exec_clock;
u64 min_vruntime;
@@ -556,8 +565,6 @@ struct cfs_rq {
#ifdef CONFIG_CFS_BANDWIDTH
int runtime_enabled;
- int expires_seq;
- u64 runtime_expires;
s64 runtime_remaining;
u64 throttled_clock;
@@ -777,9 +784,6 @@ struct root_domain {
struct perf_domain __rcu *pd;
};
-extern struct root_domain def_root_domain;
-extern struct mutex sched_domains_mutex;
-
extern void init_defrootdomain(void);
extern int sched_init_domains(const struct cpumask *cpu_map);
extern void rq_attach_root(struct rq *rq, struct root_domain *rd);
@@ -1261,16 +1265,18 @@ enum numa_topology_type {
extern enum numa_topology_type sched_numa_topology_type;
extern int sched_max_numa_distance;
extern bool find_numa_distance(int distance);
-#endif
-
-#ifdef CONFIG_NUMA
extern void sched_init_numa(void);
extern void sched_domains_numa_masks_set(unsigned int cpu);
extern void sched_domains_numa_masks_clear(unsigned int cpu);
+extern int sched_numa_find_closest(const struct cpumask *cpus, int cpu);
#else
static inline void sched_init_numa(void) { }
static inline void sched_domains_numa_masks_set(unsigned int cpu) { }
static inline void sched_domains_numa_masks_clear(unsigned int cpu) { }
+static inline int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
+{
+ return nr_cpu_ids;
+}
#endif
#ifdef CONFIG_NUMA_BALANCING
@@ -1449,10 +1455,14 @@ static inline void unregister_sched_domain_sysctl(void)
}
#endif
+extern int newidle_balance(struct rq *this_rq, struct rq_flags *rf);
+
#else
static inline void sched_ttwu_pending(void) { }
+static inline int newidle_balance(struct rq *this_rq, struct rq_flags *rf) { return 0; }
+
#endif /* CONFIG_SMP */
#include "stats.h"
@@ -1700,17 +1710,21 @@ struct sched_class {
void (*check_preempt_curr)(struct rq *rq, struct task_struct *p, int flags);
/*
- * It is the responsibility of the pick_next_task() method that will
- * return the next task to call put_prev_task() on the @prev task or
- * something equivalent.
+ * Both @prev and @rf are optional and may be NULL, in which case the
+ * caller must already have invoked put_prev_task(rq, prev, rf).
+ *
+ * Otherwise it is the responsibility of the pick_next_task() to call
+ * put_prev_task() on the @prev task or something equivalent, IFF it
+ * returns a next task.
*
- * May return RETRY_TASK when it finds a higher prio class has runnable
- * tasks.
+ * In that case (@rf != NULL) it may return RETRY_TASK when it finds a
+ * higher prio class has runnable tasks.
*/
struct task_struct * (*pick_next_task)(struct rq *rq,
struct task_struct *prev,
struct rq_flags *rf);
- void (*put_prev_task)(struct rq *rq, struct task_struct *p);
+ void (*put_prev_task)(struct rq *rq, struct task_struct *p, struct rq_flags *rf);
+ void (*set_next_task)(struct rq *rq, struct task_struct *p);
#ifdef CONFIG_SMP
int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
@@ -1725,7 +1739,6 @@ struct sched_class {
void (*rq_offline)(struct rq *rq);
#endif
- void (*set_curr_task)(struct rq *rq);
void (*task_tick)(struct rq *rq, struct task_struct *p, int queued);
void (*task_fork)(struct task_struct *p);
void (*task_dead)(struct task_struct *p);
@@ -1755,12 +1768,14 @@ struct sched_class {
static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
{
- prev->sched_class->put_prev_task(rq, prev);
+ WARN_ON_ONCE(rq->curr != prev);
+ prev->sched_class->put_prev_task(rq, prev, NULL);
}
-static inline void set_curr_task(struct rq *rq, struct task_struct *curr)
+static inline void set_next_task(struct rq *rq, struct task_struct *next)
{
- curr->sched_class->set_curr_task(rq);
+ WARN_ON_ONCE(rq->curr != next);
+ next->sched_class->set_next_task(rq, next);
}
#ifdef CONFIG_SMP
@@ -1943,7 +1958,7 @@ unsigned long arch_scale_freq_capacity(int cpu)
#endif
#ifdef CONFIG_SMP
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
static inline void double_rq_lock(struct rq *rq1, struct rq *rq2);
@@ -1995,7 +2010,7 @@ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
return ret;
}
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
/*
* double_lock_balance - lock the busiest runqueue, this_rq is locked already.
@@ -2266,7 +2281,7 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
#endif /* CONFIG_CPU_FREQ */
#ifdef CONFIG_UCLAMP_TASK
-unsigned int uclamp_eff_value(struct task_struct *p, unsigned int clamp_id);
+enum uclamp_id uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
static __always_inline
unsigned int uclamp_util_with(struct rq *rq, unsigned int util,
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index aa0de240fb41..ba683fe81a6e 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -157,9 +157,10 @@ static inline void sched_info_dequeued(struct rq *rq, struct task_struct *t)
{
unsigned long long now = rq_clock(rq), delta = 0;
- if (unlikely(sched_info_on()))
+ if (sched_info_on()) {
if (t->sched_info.last_queued)
delta = now - t->sched_info.last_queued;
+ }
sched_info_reset_dequeued(t);
t->sched_info.run_delay += delta;
@@ -192,7 +193,7 @@ static void sched_info_arrive(struct rq *rq, struct task_struct *t)
*/
static inline void sched_info_queued(struct rq *rq, struct task_struct *t)
{
- if (unlikely(sched_info_on())) {
+ if (sched_info_on()) {
if (!t->sched_info.last_queued)
t->sched_info.last_queued = rq_clock(rq);
}
@@ -239,7 +240,7 @@ __sched_info_switch(struct rq *rq, struct task_struct *prev, struct task_struct
static inline void
sched_info_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next)
{
- if (unlikely(sched_info_on()))
+ if (sched_info_on())
__sched_info_switch(rq, prev, next);
}
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index c183b790ca54..7e1cee4e65b2 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -23,17 +23,22 @@ check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
/* we're never preempted */
}
+static void set_next_task_stop(struct rq *rq, struct task_struct *stop)
+{
+ stop->se.exec_start = rq_clock_task(rq);
+}
+
static struct task_struct *
pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct task_struct *stop = rq->stop;
+ WARN_ON_ONCE(prev || rf);
+
if (!stop || !task_on_rq_queued(stop))
return NULL;
- put_prev_task(rq, prev);
-
- stop->se.exec_start = rq_clock_task(rq);
+ set_next_task_stop(rq, stop);
return stop;
}
@@ -55,7 +60,7 @@ static void yield_task_stop(struct rq *rq)
BUG(); /* the stop task should never yield, its pointless. */
}
-static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
+static void put_prev_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct task_struct *curr = rq->curr;
u64 delta_exec;
@@ -86,13 +91,6 @@ static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued)
{
}
-static void set_curr_task_stop(struct rq *rq)
-{
- struct task_struct *stop = rq->stop;
-
- stop->se.exec_start = rq_clock_task(rq);
-}
-
static void switched_to_stop(struct rq *rq, struct task_struct *p)
{
BUG(); /* its impossible to change to this class */
@@ -128,13 +126,13 @@ const struct sched_class stop_sched_class = {
.pick_next_task = pick_next_task_stop,
.put_prev_task = put_prev_task_stop,
+ .set_next_task = set_next_task_stop,
#ifdef CONFIG_SMP
.select_task_rq = select_task_rq_stop,
.set_cpus_allowed = set_cpus_allowed_common,
#endif
- .set_curr_task = set_curr_task_stop,
.task_tick = task_tick_stop,
.get_rr_interval = get_rr_interval_stop,
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index f751ce0b783e..b5667a273bf6 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1284,6 +1284,7 @@ static int sched_domains_curr_level;
int sched_max_numa_distance;
static int *sched_domains_numa_distance;
static struct cpumask ***sched_domains_numa_masks;
+int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE;
#endif
/*
@@ -1402,7 +1403,7 @@ sd_init(struct sched_domain_topology_level *tl,
sd->flags &= ~SD_PREFER_SIBLING;
sd->flags |= SD_SERIALIZE;
- if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) {
+ if (sched_domains_numa_distance[tl->numa_level] > node_reclaim_distance) {
sd->flags &= ~(SD_BALANCE_EXEC |
SD_BALANCE_FORK |
SD_WAKE_AFFINE);
@@ -1724,6 +1725,26 @@ void sched_domains_numa_masks_clear(unsigned int cpu)
}
}
+/*
+ * sched_numa_find_closest() - given the NUMA topology, find the cpu
+ * closest to @cpu from @cpumask.
+ * cpumask: cpumask to find a cpu from
+ * cpu: cpu to be close to
+ *
+ * returns: cpu, or nr_cpu_ids when nothing found.
+ */
+int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
+{
+ int i, j = cpu_to_node(cpu);
+
+ for (i = 0; i < sched_domains_numa_levels; i++) {
+ cpu = cpumask_any_and(cpus, sched_domains_numa_masks[i][j]);
+ if (cpu < nr_cpu_ids)
+ return cpu;
+ }
+ return nr_cpu_ids;
+}
+
#endif /* CONFIG_NUMA */
static int __sdt_alloc(const struct cpumask *cpu_map)
@@ -2149,16 +2170,16 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
* ndoms_new == 0 is a special case for destroying existing domains,
* and it will not create the default domain.
*
- * Call with hotplug lock held
+ * Call with hotplug lock and sched_domains_mutex held
*/
-void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
- struct sched_domain_attr *dattr_new)
+void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
+ struct sched_domain_attr *dattr_new)
{
bool __maybe_unused has_eas = false;
int i, j, n;
int new_topology;
- mutex_lock(&sched_domains_mutex);
+ lockdep_assert_held(&sched_domains_mutex);
/* Always unregister in case we don't destroy any domains: */
unregister_sched_domain_sysctl();
@@ -2183,8 +2204,19 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
for (i = 0; i < ndoms_cur; i++) {
for (j = 0; j < n && !new_topology; j++) {
if (cpumask_equal(doms_cur[i], doms_new[j]) &&
- dattrs_equal(dattr_cur, i, dattr_new, j))
+ dattrs_equal(dattr_cur, i, dattr_new, j)) {
+ struct root_domain *rd;
+
+ /*
+ * This domain won't be destroyed and as such
+ * its dl_bw->total_bw needs to be cleared. It
+ * will be recomputed in function
+ * update_tasks_root_domain().
+ */
+ rd = cpu_rq(cpumask_any(doms_cur[i]))->rd;
+ dl_clear_root_domain(rd);
goto match1;
+ }
}
/* No match - a current sched domain not in new doms_new[] */
detach_destroy_domains(doms_cur[i]);
@@ -2241,6 +2273,15 @@ match3:
ndoms_cur = ndoms_new;
register_sched_domain_sysctl();
+}
+/*
+ * Call with hotplug lock held
+ */
+void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
+ struct sched_domain_attr *dattr_new)
+{
+ mutex_lock(&sched_domains_mutex);
+ partition_sched_domains_locked(ndoms_new, doms_new, dattr_new);
mutex_unlock(&sched_domains_mutex);
}
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index b4f83f7bdf86..c7031a22aa7b 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -383,6 +383,7 @@ static bool queue_stop_cpus_work(const struct cpumask *cpumask,
*/
preempt_disable();
stop_cpus_in_progress = true;
+ barrier();
for_each_cpu(cpu, cpumask) {
work = &per_cpu(cpu_stopper.stop_work, cpu);
work->fn = fn;
@@ -391,6 +392,7 @@ static bool queue_stop_cpus_work(const struct cpumask *cpumask,
if (cpu_stop_queue_work(cpu, work))
queued = true;
}
+ barrier();
stop_cpus_in_progress = false;
preempt_enable();
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 98da8998c25c..6a64d7772870 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -146,7 +146,7 @@ config FUNCTION_TRACER
select GENERIC_TRACER
select CONTEXT_SWITCH_TRACER
select GLOB
- select TASKS_RCU if PREEMPT
+ select TASKS_RCU if PREEMPTION
help
Enable the kernel to trace every kernel function. This is done
by using a compiler feature to insert a small, 5-byte No-Operation
@@ -179,7 +179,7 @@ config TRACE_PREEMPT_TOGGLE
config PREEMPTIRQ_EVENTS
bool "Enable trace events for preempt and irq disable/enable"
select TRACE_IRQFLAGS
- select TRACE_PREEMPT_TOGGLE if PREEMPT
+ select TRACE_PREEMPT_TOGGLE if PREEMPTION
select GENERIC_TRACER
default n
help
@@ -214,7 +214,7 @@ config PREEMPT_TRACER
bool "Preemption-off Latency Tracer"
default n
depends on !ARCH_USES_GETTIMEOFFSET
- depends on PREEMPT
+ depends on PREEMPTION
select GENERIC_TRACER
select TRACER_MAX_TRACE
select RING_BUFFER_ALLOW_SWAP
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f9821a3374e9..356b848c697a 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2814,7 +2814,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
* synchornize_rcu_tasks() will wait for those tasks to
* execute and either schedule voluntarily or enter user space.
*/
- if (IS_ENABLED(CONFIG_PREEMPT))
+ if (IS_ENABLED(CONFIG_PREEMPTION))
synchronize_rcu_tasks();
free_ops:
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 0564f6db0561..09b0b49f346e 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -267,7 +267,7 @@ static void ring_buffer_producer(void)
if (consumer && !(cnt % wakeup_interval))
wake_up_process(consumer);
-#ifndef CONFIG_PREEMPT
+#ifndef CONFIG_PREEMPTION
/*
* If we are a non preempt kernel, the 10 second run will
* stop everything while it runs. Instead, we will call
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 648930823b57..b89cdfe20bc1 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -255,12 +255,12 @@ void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer,
local_save_flags(fbuffer->flags);
fbuffer->pc = preempt_count();
/*
- * If CONFIG_PREEMPT is enabled, then the tracepoint itself disables
+ * If CONFIG_PREEMPTION is enabled, then the tracepoint itself disables
* preemption (adding one to the preempt_count). Since we are
* interested in the preempt_count at the time the tracepoint was
* hit, we need to subtract one to offset the increment.
*/
- if (IS_ENABLED(CONFIG_PREEMPT))
+ if (IS_ENABLED(CONFIG_PREEMPTION))
fbuffer->pc--;
fbuffer->trace_file = trace_file;
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 743b2b520d34..5e43b9664eca 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -579,8 +579,7 @@ probe_wakeup(void *ignore, struct task_struct *p)
else
tracing_dl = 0;
- wakeup_task = p;
- get_task_struct(wakeup_task);
+ wakeup_task = get_task_struct(p);
local_save_flags(flags);
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.