aboutsummaryrefslogtreecommitdiff
path: root/kernel/sched/core.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sched/core.c')
-rw-r--r--kernel/sched/core.c716
1 files changed, 476 insertions, 240 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9745613d531c..da0bf6fe9ecd 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6,26 +6,93 @@
*
* Copyright (C) 1991-2002 Linus Torvalds
*/
-#define CREATE_TRACE_POINTS
-#include <trace/events/sched.h>
-#undef CREATE_TRACE_POINTS
+#include <linux/highmem.h>
+#include <linux/hrtimer_api.h>
+#include <linux/ktime_api.h>
+#include <linux/sched/signal.h>
+#include <linux/syscalls_api.h>
+#include <linux/debug_locks.h>
+#include <linux/prefetch.h>
+#include <linux/capability.h>
+#include <linux/pgtable_api.h>
+#include <linux/wait_bit.h>
+#include <linux/jiffies.h>
+#include <linux/spinlock_api.h>
+#include <linux/cpumask_api.h>
+#include <linux/lockdep_api.h>
+#include <linux/hardirq.h>
+#include <linux/softirq.h>
+#include <linux/refcount_api.h>
+#include <linux/topology.h>
+#include <linux/sched/clock.h>
+#include <linux/sched/cond_resched.h>
+#include <linux/sched/cputime.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/hotplug.h>
+#include <linux/sched/init.h>
+#include <linux/sched/isolation.h>
+#include <linux/sched/loadavg.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/nohz.h>
+#include <linux/sched/rseq_api.h>
+#include <linux/sched/rt.h>
-#include "sched.h"
-
-#include <linux/nospec.h>
#include <linux/blkdev.h>
+#include <linux/context_tracking.h>
+#include <linux/cpuset.h>
+#include <linux/delayacct.h>
+#include <linux/init_task.h>
+#include <linux/interrupt.h>
+#include <linux/ioprio.h>
+#include <linux/kallsyms.h>
#include <linux/kcov.h>
+#include <linux/kprobes.h>
+#include <linux/llist_api.h>
+#include <linux/mmu_context.h>
+#include <linux/mmzone.h>
+#include <linux/mutex_api.h>
+#include <linux/nmi.h>
+#include <linux/nospec.h>
+#include <linux/perf_event_api.h>
+#include <linux/profile.h>
+#include <linux/psi.h>
+#include <linux/rcuwait_api.h>
+#include <linux/sched/wake_q.h>
#include <linux/scs.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/vtime.h>
+#include <linux/wait_api.h>
+#include <linux/workqueue_api.h>
+
+#ifdef CONFIG_PREEMPT_DYNAMIC
+# ifdef CONFIG_GENERIC_ENTRY
+# include <linux/entry-common.h>
+# endif
+#endif
+
+#include <uapi/linux/sched/types.h>
#include <asm/switch_to.h>
#include <asm/tlb.h>
-#include "../workqueue_internal.h"
-#include "../../fs/io-wq.h"
-#include "../smpboot.h"
+#define CREATE_TRACE_POINTS
+#include <linux/sched/rseq_api.h>
+#include <trace/events/sched.h>
+#undef CREATE_TRACE_POINTS
+#include "sched.h"
+#include "stats.h"
+#include "autogroup.h"
+
+#include "autogroup.h"
#include "pelt.h"
#include "smp.h"
+#include "stats.h"
+
+#include "../workqueue_internal.h"
+#include "../../fs/io-wq.h"
+#include "../smpboot.h"
/*
* Export tracepoints that act as a bare tracehook (ie: have no trace event
@@ -36,6 +103,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_rt_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_thermal_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_cpu_capacity_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
@@ -80,12 +148,6 @@ const_debug unsigned int sysctl_sched_nr_migrate = 8;
const_debug unsigned int sysctl_sched_nr_migrate = 32;
#endif
-/*
- * period over which we measure -rt task CPU usage in us.
- * default: 1s
- */
-unsigned int sysctl_sched_rt_period = 1000000;
-
__read_mostly int scheduler_running;
#ifdef CONFIG_SCHED_CORE
@@ -380,13 +442,6 @@ sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { }
#endif /* CONFIG_SCHED_CORE */
/*
- * part of the period that we allow rt tasks to run in us.
- * default: 0.95s
- */
-int sysctl_sched_rt_runtime = 950000;
-
-
-/*
* Serialization rules:
*
* Lock order:
@@ -545,10 +600,10 @@ void double_rq_lock(struct rq *rq1, struct rq *rq2)
swap(rq1, rq2);
raw_spin_rq_lock(rq1);
- if (__rq_lockp(rq1) == __rq_lockp(rq2))
- return;
+ if (__rq_lockp(rq1) != __rq_lockp(rq2))
+ raw_spin_rq_lock_nested(rq2, SINGLE_DEPTH_NESTING);
- raw_spin_rq_lock_nested(rq2, SINGLE_DEPTH_NESTING);
+ double_rq_clock_clear_update(rq1, rq2);
}
#endif
@@ -1024,13 +1079,13 @@ int get_nohz_timer_target(void)
struct sched_domain *sd;
const struct cpumask *hk_mask;
- if (housekeeping_cpu(cpu, HK_FLAG_TIMER)) {
+ if (housekeeping_cpu(cpu, HK_TYPE_TIMER)) {
if (!idle_cpu(cpu))
return cpu;
default_cpu = cpu;
}
- hk_mask = housekeeping_cpumask(HK_FLAG_TIMER);
+ hk_mask = housekeeping_cpumask(HK_TYPE_TIMER);
rcu_read_lock();
for_each_domain(cpu, sd) {
@@ -1046,7 +1101,7 @@ int get_nohz_timer_target(void)
}
if (default_cpu == -1)
- default_cpu = housekeeping_any_cpu(HK_FLAG_TIMER);
+ default_cpu = housekeeping_any_cpu(HK_TYPE_TIMER);
cpu = default_cpu;
unlock:
rcu_read_unlock();
@@ -1254,10 +1309,10 @@ static void set_load_weight(struct task_struct *p, bool update_load)
static DEFINE_MUTEX(uclamp_mutex);
/* Max allowed minimum utilization */
-unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE;
+static unsigned int __maybe_unused sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE;
/* Max allowed maximum utilization */
-unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
+static unsigned int __maybe_unused sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
/*
* By default RT tasks run at the maximum performance point/capacity of the
@@ -1274,7 +1329,7 @@ unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
* This knob will not override the system default sched_util_clamp_min defined
* above.
*/
-unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE;
+static unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE;
/* All clamps are required to be less or equal than these values */
static struct uclamp_se uclamp_default[UCLAMP_CNT];
@@ -1404,33 +1459,6 @@ static void uclamp_update_util_min_rt_default(struct task_struct *p)
task_rq_unlock(rq, p, &rf);
}
-static void uclamp_sync_util_min_rt_default(void)
-{
- struct task_struct *g, *p;
-
- /*
- * copy_process() sysctl_uclamp
- * uclamp_min_rt = X;
- * write_lock(&tasklist_lock) read_lock(&tasklist_lock)
- * // link thread smp_mb__after_spinlock()
- * write_unlock(&tasklist_lock) read_unlock(&tasklist_lock);
- * sched_post_fork() for_each_process_thread()
- * __uclamp_sync_rt() __uclamp_sync_rt()
- *
- * Ensures that either sched_post_fork() will observe the new
- * uclamp_min_rt or for_each_process_thread() will observe the new
- * task.
- */
- read_lock(&tasklist_lock);
- smp_mb__after_spinlock();
- read_unlock(&tasklist_lock);
-
- rcu_read_lock();
- for_each_process_thread(g, p)
- uclamp_update_util_min_rt_default(p);
- rcu_read_unlock();
-}
-
static inline struct uclamp_se
uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id)
{
@@ -1710,6 +1738,11 @@ uclamp_update_active_tasks(struct cgroup_subsys_state *css)
}
static void cpu_util_update_eff(struct cgroup_subsys_state *css);
+#endif
+
+#ifdef CONFIG_SYSCTL
+#ifdef CONFIG_UCLAMP_TASK
+#ifdef CONFIG_UCLAMP_TASK_GROUP
static void uclamp_update_root_tg(void)
{
struct task_group *tg = &root_task_group;
@@ -1727,7 +1760,34 @@ static void uclamp_update_root_tg(void)
static void uclamp_update_root_tg(void) { }
#endif
-int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
+static void uclamp_sync_util_min_rt_default(void)
+{
+ struct task_struct *g, *p;
+
+ /*
+ * copy_process() sysctl_uclamp
+ * uclamp_min_rt = X;
+ * write_lock(&tasklist_lock) read_lock(&tasklist_lock)
+ * // link thread smp_mb__after_spinlock()
+ * write_unlock(&tasklist_lock) read_unlock(&tasklist_lock);
+ * sched_post_fork() for_each_process_thread()
+ * __uclamp_sync_rt() __uclamp_sync_rt()
+ *
+ * Ensures that either sched_post_fork() will observe the new
+ * uclamp_min_rt or for_each_process_thread() will observe the new
+ * task.
+ */
+ read_lock(&tasklist_lock);
+ smp_mb__after_spinlock();
+ read_unlock(&tasklist_lock);
+
+ rcu_read_lock();
+ for_each_process_thread(g, p)
+ uclamp_update_util_min_rt_default(p);
+ rcu_read_unlock();
+}
+
+static int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
bool update_root_tg = false;
@@ -1791,6 +1851,8 @@ done:
return result;
}
+#endif
+#endif
static int uclamp_validate(struct task_struct *p,
const struct sched_attr *attr)
@@ -2125,7 +2187,7 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
{
if (p->sched_class == rq->curr->sched_class)
rq->curr->sched_class->check_preempt_curr(rq, p, flags);
- else if (p->sched_class > rq->curr->sched_class)
+ else if (sched_class_above(p->sched_class, rq->curr->sched_class))
resched_curr(rq);
/*
@@ -2343,7 +2405,7 @@ static int migration_cpu_stop(void *data)
* __migrate_task() such that we will not miss enforcing cpus_ptr
* during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test.
*/
- flush_smp_call_function_from_idle();
+ flush_smp_call_function_queue();
raw_spin_lock(&p->pi_lock);
rq_lock(rq, &rf);
@@ -4279,7 +4341,9 @@ DEFINE_STATIC_KEY_FALSE(sched_numa_balancing);
#ifdef CONFIG_NUMA_BALANCING
-void set_numabalancing_state(bool enabled)
+int sysctl_numa_balancing_mode;
+
+static void __set_numabalancing_state(bool enabled)
{
if (enabled)
static_branch_enable(&sched_numa_balancing);
@@ -4287,13 +4351,22 @@ void set_numabalancing_state(bool enabled)
static_branch_disable(&sched_numa_balancing);
}
+void set_numabalancing_state(bool enabled)
+{
+ if (enabled)
+ sysctl_numa_balancing_mode = NUMA_BALANCING_NORMAL;
+ else
+ sysctl_numa_balancing_mode = NUMA_BALANCING_DISABLED;
+ __set_numabalancing_state(enabled);
+}
+
#ifdef CONFIG_PROC_SYSCTL
int sysctl_numa_balancing(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table t;
int err;
- int state = static_branch_likely(&sched_numa_balancing);
+ int state = sysctl_numa_balancing_mode;
if (write && !capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -4303,8 +4376,10 @@ int sysctl_numa_balancing(struct ctl_table *table, int write,
err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
if (err < 0)
return err;
- if (write)
- set_numabalancing_state(state);
+ if (write) {
+ sysctl_numa_balancing_mode = state;
+ __set_numabalancing_state(state);
+ }
return err;
}
#endif
@@ -4352,7 +4427,7 @@ out:
__setup("schedstats=", setup_schedstats);
#ifdef CONFIG_PROC_SYSCTL
-int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
+static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
size_t *lenp, loff_t *ppos)
{
struct ctl_table t;
@@ -4374,6 +4449,52 @@ int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
#endif /* CONFIG_PROC_SYSCTL */
#endif /* CONFIG_SCHEDSTATS */
+#ifdef CONFIG_SYSCTL
+static struct ctl_table sched_core_sysctls[] = {
+#ifdef CONFIG_SCHEDSTATS
+ {
+ .procname = "sched_schedstats",
+ .data = NULL,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = sysctl_schedstats,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
+ },
+#endif /* CONFIG_SCHEDSTATS */
+#ifdef CONFIG_UCLAMP_TASK
+ {
+ .procname = "sched_util_clamp_min",
+ .data = &sysctl_sched_uclamp_util_min,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = sysctl_sched_uclamp_handler,
+ },
+ {
+ .procname = "sched_util_clamp_max",
+ .data = &sysctl_sched_uclamp_util_max,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = sysctl_sched_uclamp_handler,
+ },
+ {
+ .procname = "sched_util_clamp_min_rt_default",
+ .data = &sysctl_sched_uclamp_util_min_rt_default,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = sysctl_sched_uclamp_handler,
+ },
+#endif /* CONFIG_UCLAMP_TASK */
+ {}
+};
+static int __init sched_core_sysctl_init(void)
+{
+ register_sysctl_init("kernel", sched_core_sysctls);
+ return 0;
+}
+late_initcall(sched_core_sysctl_init);
+#endif /* CONFIG_SYSCTL */
+
/*
* fork()/clone()-time setup:
*/
@@ -4677,25 +4798,55 @@ static void do_balance_callbacks(struct rq *rq, struct callback_head *head)
static void balance_push(struct rq *rq);
+/*
+ * balance_push_callback is a right abuse of the callback interface and plays
+ * by significantly different rules.
+ *
+ * Where the normal balance_callback's purpose is to be ran in the same context
+ * that queued it (only later, when it's safe to drop rq->lock again),
+ * balance_push_callback is specifically targeted at __schedule().
+ *
+ * This abuse is tolerated because it places all the unlikely/odd cases behind
+ * a single test, namely: rq->balance_callback == NULL.
+ */
struct callback_head balance_push_callback = {
.next = NULL,
.func = (void (*)(struct callback_head *))balance_push,
};
-static inline struct callback_head *splice_balance_callbacks(struct rq *rq)
+static inline struct callback_head *
+__splice_balance_callbacks(struct rq *rq, bool split)
{
struct callback_head *head = rq->balance_callback;
+ if (likely(!head))
+ return NULL;
+
lockdep_assert_rq_held(rq);
- if (head)
+ /*
+ * Must not take balance_push_callback off the list when
+ * splice_balance_callbacks() and balance_callbacks() are not
+ * in the same rq->lock section.
+ *
+ * In that case it would be possible for __schedule() to interleave
+ * and observe the list empty.
+ */
+ if (split && head == &balance_push_callback)
+ head = NULL;
+ else
rq->balance_callback = NULL;
return head;
}
+static inline struct callback_head *splice_balance_callbacks(struct rq *rq)
+{
+ return __splice_balance_callbacks(rq, true);
+}
+
static void __balance_callbacks(struct rq *rq)
{
- do_balance_callbacks(rq, splice_balance_callbacks(rq));
+ do_balance_callbacks(rq, __splice_balance_callbacks(rq, false));
}
static inline void balance_callbacks(struct rq *rq, struct callback_head *head)
@@ -4834,7 +4985,7 @@ static struct rq *finish_task_switch(struct task_struct *prev)
{
struct rq *rq = this_rq();
struct mm_struct *mm = rq->prev_mm;
- long prev_state;
+ unsigned int prev_state;
/*
* The previous task will have left us with a preempt_count of 2
@@ -5379,7 +5530,7 @@ static void sched_tick_start(int cpu)
int os;
struct tick_work *twork;
- if (housekeeping_cpu(cpu, HK_FLAG_TICK))
+ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
return;
WARN_ON_ONCE(!tick_work_cpu);
@@ -5400,7 +5551,7 @@ static void sched_tick_stop(int cpu)
struct tick_work *twork;
int os;
- if (housekeeping_cpu(cpu, HK_FLAG_TICK))
+ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
return;
WARN_ON_ONCE(!tick_work_cpu);
@@ -5611,7 +5762,7 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
* higher scheduling class, because otherwise those lose the
* opportunity to pull in more work from other CPUs.
*/
- if (likely(prev->sched_class <= &fair_sched_class &&
+ if (likely(!sched_class_above(prev->sched_class, &fair_sched_class) &&
rq->nr_running == rq->cfs.h_nr_running)) {
p = pick_next_task_fair(rq, prev, rf);
@@ -5674,6 +5825,8 @@ static inline struct task_struct *pick_task(struct rq *rq)
extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi);
+static void queue_core_balance(struct rq *rq);
+
static struct task_struct *
pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
@@ -5723,7 +5876,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
}
rq->core_pick = NULL;
- return next;
+ goto out;
}
put_prev_task_balance(rq, prev, rf);
@@ -5773,7 +5926,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
*/
WARN_ON_ONCE(fi_before);
task_vruntime_update(rq, next, false);
- goto done;
+ goto out_set_next;
}
}
@@ -5892,8 +6045,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
resched_curr(rq_i);
}
-done:
+out_set_next:
set_next_task(rq, next);
+out:
+ if (rq->core->core_forceidle_count && next == rq->idle)
+ queue_core_balance(rq);
+
return next;
}
@@ -5922,7 +6079,7 @@ static bool try_steal_cookie(int this, int that)
if (p == src->core_pick || p == src->curr)
goto next;
- if (!cpumask_test_cpu(this, &p->cpus_mask))
+ if (!is_cpu_allowed(p, this))
goto next;
if (p->core_occupation > dst->idle->core_occupation)
@@ -5988,7 +6145,7 @@ static void sched_core_balance(struct rq *rq)
static DEFINE_PER_CPU(struct callback_head, core_balance_head);
-void queue_core_balance(struct rq *rq)
+static void queue_core_balance(struct rq *rq)
{
if (!sched_core_enabled(rq))
return;
@@ -6226,10 +6383,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
/*
* We must load prev->state once (task_struct::state is volatile), such
- * that:
- *
- * - we form a control dependency vs deactivate_task() below.
- * - ptrace_{,un}freeze_traced() can change ->state underneath us.
+ * that we form a control dependency vs deactivate_task() below.
*/
prev_state = READ_ONCE(prev->__state);
if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) {
@@ -6298,7 +6452,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
migrate_disable_switch(rq, prev);
psi_sched_switch(prev, next, !task_on_rq_queued(prev));
- trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next);
+ trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next, prev_state);
/* Also unlocks the rq: */
rq = context_switch(rq, prev, next, &rf);
@@ -6353,8 +6507,7 @@ static inline void sched_submit_work(struct task_struct *tsk)
* If we are going to sleep and we have plugged IO queued,
* make sure to submit it to avoid deadlocks.
*/
- if (blk_needs_flush_plug(tsk))
- blk_flush_plug(tsk->plug, true);
+ blk_flush_plug(tsk->plug, true);
}
static void sched_update_worker(struct task_struct *tsk)
@@ -6491,17 +6644,31 @@ asmlinkage __visible void __sched notrace preempt_schedule(void)
*/
if (likely(!preemptible()))
return;
-
preempt_schedule_common();
}
NOKPROBE_SYMBOL(preempt_schedule);
EXPORT_SYMBOL(preempt_schedule);
#ifdef CONFIG_PREEMPT_DYNAMIC
-DEFINE_STATIC_CALL(preempt_schedule, __preempt_schedule_func);
+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
+#ifndef preempt_schedule_dynamic_enabled
+#define preempt_schedule_dynamic_enabled preempt_schedule
+#define preempt_schedule_dynamic_disabled NULL
+#endif
+DEFINE_STATIC_CALL(preempt_schedule, preempt_schedule_dynamic_enabled);
EXPORT_STATIC_CALL_TRAMP(preempt_schedule);
+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule);
+void __sched notrace dynamic_preempt_schedule(void)
+{
+ if (!static_branch_unlikely(&sk_dynamic_preempt_schedule))
+ return;
+ preempt_schedule();
+}
+NOKPROBE_SYMBOL(dynamic_preempt_schedule);
+EXPORT_SYMBOL(dynamic_preempt_schedule);
+#endif
#endif
-
/**
* preempt_schedule_notrace - preempt_schedule called by tracing
@@ -6556,147 +6723,27 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
#ifdef CONFIG_PREEMPT_DYNAMIC
-DEFINE_STATIC_CALL(preempt_schedule_notrace, __preempt_schedule_notrace_func);
-EXPORT_STATIC_CALL_TRAMP(preempt_schedule_notrace);
+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
+#ifndef preempt_schedule_notrace_dynamic_enabled
+#define preempt_schedule_notrace_dynamic_enabled preempt_schedule_notrace
+#define preempt_schedule_notrace_dynamic_disabled NULL
#endif
-
-#endif /* CONFIG_PREEMPTION */
-
-#ifdef CONFIG_PREEMPT_DYNAMIC
-
-#include <linux/entry-common.h>
-
-/*
- * SC:cond_resched
- * SC:might_resched
- * SC:preempt_schedule
- * SC:preempt_schedule_notrace
- * SC:irqentry_exit_cond_resched
- *
- *
- * NONE:
- * cond_resched <- __cond_resched
- * might_resched <- RET0
- * preempt_schedule <- NOP
- * preempt_schedule_notrace <- NOP
- * irqentry_exit_cond_resched <- NOP
- *
- * VOLUNTARY:
- * cond_resched <- __cond_resched
- * might_resched <- __cond_resched
- * preempt_schedule <- NOP
- * preempt_schedule_notrace <- NOP
- * irqentry_exit_cond_resched <- NOP
- *
- * FULL:
- * cond_resched <- RET0
- * might_resched <- RET0
- * preempt_schedule <- preempt_schedule
- * preempt_schedule_notrace <- preempt_schedule_notrace
- * irqentry_exit_cond_resched <- irqentry_exit_cond_resched
- */
-
-enum {
- preempt_dynamic_undefined = -1,
- preempt_dynamic_none,
- preempt_dynamic_voluntary,
- preempt_dynamic_full,
-};
-
-int preempt_dynamic_mode = preempt_dynamic_undefined;
-
-int sched_dynamic_mode(const char *str)
-{
- if (!strcmp(str, "none"))
- return preempt_dynamic_none;
-
- if (!strcmp(str, "voluntary"))
- return preempt_dynamic_voluntary;
-
- if (!strcmp(str, "full"))
- return preempt_dynamic_full;
-
- return -EINVAL;
-}
-
-void sched_dynamic_update(int mode)
-{
- /*
- * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in
- * the ZERO state, which is invalid.
- */
- static_call_update(cond_resched, __cond_resched);
- static_call_update(might_resched, __cond_resched);
- static_call_update(preempt_schedule, __preempt_schedule_func);
- static_call_update(preempt_schedule_notrace, __preempt_schedule_notrace_func);
- static_call_update(irqentry_exit_cond_resched, irqentry_exit_cond_resched);
-
- switch (mode) {
- case preempt_dynamic_none:
- static_call_update(cond_resched, __cond_resched);
- static_call_update(might_resched, (void *)&__static_call_return0);
- static_call_update(preempt_schedule, NULL);
- static_call_update(preempt_schedule_notrace, NULL);
- static_call_update(irqentry_exit_cond_resched, NULL);
- pr_info("Dynamic Preempt: none\n");
- break;
-
- case preempt_dynamic_voluntary:
- static_call_update(cond_resched, __cond_resched);
- static_call_update(might_resched, __cond_resched);
- static_call_update(preempt_schedule, NULL);
- static_call_update(preempt_schedule_notrace, NULL);
- static_call_update(irqentry_exit_cond_resched, NULL);
- pr_info("Dynamic Preempt: voluntary\n");
- break;
-
- case preempt_dynamic_full:
- static_call_update(cond_resched, (void *)&__static_call_return0);
- static_call_update(might_resched, (void *)&__static_call_return0);
- static_call_update(preempt_schedule, __preempt_schedule_func);
- static_call_update(preempt_schedule_notrace, __preempt_schedule_notrace_func);
- static_call_update(irqentry_exit_cond_resched, irqentry_exit_cond_resched);
- pr_info("Dynamic Preempt: full\n");
- break;
- }
-
- preempt_dynamic_mode = mode;
-}
-
-static int __init setup_preempt_mode(char *str)
-{
- int mode = sched_dynamic_mode(str);
- if (mode < 0) {
- pr_warn("Dynamic Preempt: unsupported mode: %s\n", str);
- return 0;
- }
-
- sched_dynamic_update(mode);
- return 1;
-}
-__setup("preempt=", setup_preempt_mode);
-
-static void __init preempt_dynamic_init(void)
+DEFINE_STATIC_CALL(preempt_schedule_notrace, preempt_schedule_notrace_dynamic_enabled);
+EXPORT_STATIC_CALL_TRAMP(preempt_schedule_notrace);
+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule_notrace);
+void __sched notrace dynamic_preempt_schedule_notrace(void)
{
- if (preempt_dynamic_mode == preempt_dynamic_undefined) {
- if (IS_ENABLED(CONFIG_PREEMPT_NONE)) {
- sched_dynamic_update(preempt_dynamic_none);
- } else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY)) {
- sched_dynamic_update(preempt_dynamic_voluntary);
- } else {
- /* Default static call setting, nothing to do */
- WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT));
- preempt_dynamic_mode = preempt_dynamic_full;
- pr_info("Dynamic Preempt: full\n");
- }
- }
+ if (!static_branch_unlikely(&sk_dynamic_preempt_schedule_notrace))
+ return;
+ preempt_schedule_notrace();
}
+NOKPROBE_SYMBOL(dynamic_preempt_schedule_notrace);
+EXPORT_SYMBOL(dynamic_preempt_schedule_notrace);
+#endif
+#endif
-#else /* !CONFIG_PREEMPT_DYNAMIC */
-
-static inline void preempt_dynamic_init(void) { }
-
-#endif /* #ifdef CONFIG_PREEMPT_DYNAMIC */
+#endif /* CONFIG_PREEMPTION */
/*
* This is the entry point to schedule() from kernel preemption
@@ -8203,11 +8250,35 @@ EXPORT_SYMBOL(__cond_resched);
#endif
#ifdef CONFIG_PREEMPT_DYNAMIC
+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
+#define cond_resched_dynamic_enabled __cond_resched
+#define cond_resched_dynamic_disabled ((void *)&__static_call_return0)
DEFINE_STATIC_CALL_RET0(cond_resched, __cond_resched);
EXPORT_STATIC_CALL_TRAMP(cond_resched);
+#define might_resched_dynamic_enabled __cond_resched
+#define might_resched_dynamic_disabled ((void *)&__static_call_return0)
DEFINE_STATIC_CALL_RET0(might_resched, __cond_resched);
EXPORT_STATIC_CALL_TRAMP(might_resched);
+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+static DEFINE_STATIC_KEY_FALSE(sk_dynamic_cond_resched);
+int __sched dynamic_cond_resched(void)
+{
+ if (!static_branch_unlikely(&sk_dynamic_cond_resched))
+ return 0;
+ return __cond_resched();
+}
+EXPORT_SYMBOL(dynamic_cond_resched);
+
+static DEFINE_STATIC_KEY_FALSE(sk_dynamic_might_resched);
+int __sched dynamic_might_resched(void)
+{
+ if (!static_branch_unlikely(&sk_dynamic_might_resched))
+ return 0;
+ return __cond_resched();
+}
+EXPORT_SYMBOL(dynamic_might_resched);
+#endif
#endif
/*
@@ -8272,6 +8343,166 @@ int __cond_resched_rwlock_write(rwlock_t *lock)
}
EXPORT_SYMBOL(__cond_resched_rwlock_write);
+#ifdef CONFIG_PREEMPT_DYNAMIC
+
+#ifdef CONFIG_GENERIC_ENTRY
+#include <linux/entry-common.h>
+#endif
+
+/*
+ * SC:cond_resched
+ * SC:might_resched
+ * SC:preempt_schedule
+ * SC:preempt_schedule_notrace
+ * SC:irqentry_exit_cond_resched
+ *
+ *
+ * NONE:
+ * cond_resched <- __cond_resched
+ * might_resched <- RET0
+ * preempt_schedule <- NOP
+ * preempt_schedule_notrace <- NOP
+ * irqentry_exit_cond_resched <- NOP
+ *
+ * VOLUNTARY:
+ * cond_resched <- __cond_resched
+ * might_resched <- __cond_resched
+ * preempt_schedule <- NOP
+ * preempt_schedule_notrace <- NOP
+ * irqentry_exit_cond_resched <- NOP
+ *
+ * FULL:
+ * cond_resched <- RET0
+ * might_resched <- RET0
+ * preempt_schedule <- preempt_schedule
+ * preempt_schedule_notrace <- preempt_schedule_notrace
+ * irqentry_exit_cond_resched <- irqentry_exit_cond_resched
+ */
+
+enum {
+ preempt_dynamic_undefined = -1,
+ preempt_dynamic_none,
+ preempt_dynamic_voluntary,
+ preempt_dynamic_full,
+};
+
+int preempt_dynamic_mode = preempt_dynamic_undefined;
+
+int sched_dynamic_mode(const char *str)
+{
+ if (!strcmp(str, "none"))
+ return preempt_dynamic_none;
+
+ if (!strcmp(str, "voluntary"))
+ return preempt_dynamic_voluntary;
+
+ if (!strcmp(str, "full"))
+ return preempt_dynamic_full;
+
+ return -EINVAL;
+}
+
+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
+#define preempt_dynamic_enable(f) static_call_update(f, f##_dynamic_enabled)
+#define preempt_dynamic_disable(f) static_call_update(f, f##_dynamic_disabled)
+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+#define preempt_dynamic_enable(f) static_key_enable(&sk_dynamic_##f.key)
+#define preempt_dynamic_disable(f) static_key_disable(&sk_dynamic_##f.key)
+#else
+#error "Unsupported PREEMPT_DYNAMIC mechanism"
+#endif
+
+void sched_dynamic_update(int mode)
+{
+ /*
+ * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in
+ * the ZERO state, which is invalid.
+ */
+ preempt_dynamic_enable(cond_resched);
+ preempt_dynamic_enable(might_resched);
+ preempt_dynamic_enable(preempt_schedule);
+ preempt_dynamic_enable(preempt_schedule_notrace);
+ preempt_dynamic_enable(irqentry_exit_cond_resched);
+
+ switch (mode) {
+ case preempt_dynamic_none:
+ preempt_dynamic_enable(cond_resched);
+ preempt_dynamic_disable(might_resched);
+ preempt_dynamic_disable(preempt_schedule);
+ preempt_dynamic_disable(preempt_schedule_notrace);
+ preempt_dynamic_disable(irqentry_exit_cond_resched);
+ pr_info("Dynamic Preempt: none\n");
+ break;
+
+ case preempt_dynamic_voluntary:
+ preempt_dynamic_enable(cond_resched);
+ preempt_dynamic_enable(might_resched);
+ preempt_dynamic_disable(preempt_schedule);
+ preempt_dynamic_disable(preempt_schedule_notrace);
+ preempt_dynamic_disable(irqentry_exit_cond_resched);
+ pr_info("Dynamic Preempt: voluntary\n");
+ break;
+
+ case preempt_dynamic_full:
+ preempt_dynamic_disable(cond_resched);
+ preempt_dynamic_disable(might_resched);
+ preempt_dynamic_enable(preempt_schedule);
+ preempt_dynamic_enable(preempt_schedule_notrace);
+ preempt_dynamic_enable(irqentry_exit_cond_resched);
+ pr_info("Dynamic Preempt: full\n");
+ break;
+ }
+
+ preempt_dynamic_mode = mode;
+}
+
+static int __init setup_preempt_mode(char *str)
+{
+ int mode = sched_dynamic_mode(str);
+ if (mode < 0) {
+ pr_warn("Dynamic Preempt: unsupported mode: %s\n", str);
+ return 0;
+ }
+
+ sched_dynamic_update(mode);
+ return 1;
+}
+__setup("preempt=", setup_preempt_mode);
+
+static void __init preempt_dynamic_init(void)
+{
+ if (preempt_dynamic_mode == preempt_dynamic_undefined) {
+ if (IS_ENABLED(CONFIG_PREEMPT_NONE)) {
+ sched_dynamic_update(preempt_dynamic_none);
+ } else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY)) {
+ sched_dynamic_update(preempt_dynamic_voluntary);
+ } else {
+ /* Default static call setting, nothing to do */
+ WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT));
+ preempt_dynamic_mode = preempt_dynamic_full;
+ pr_info("Dynamic Preempt: full\n");
+ }
+ }
+}
+
+#define PREEMPT_MODEL_ACCESSOR(mode) \
+ bool preempt_model_##mode(void) \
+ { \
+ WARN_ON_ONCE(preempt_dynamic_mode == preempt_dynamic_undefined); \
+ return preempt_dynamic_mode == preempt_dynamic_##mode; \
+ } \
+ EXPORT_SYMBOL_GPL(preempt_model_##mode)
+
+PREEMPT_MODEL_ACCESSOR(none);
+PREEMPT_MODEL_ACCESSOR(voluntary);
+PREEMPT_MODEL_ACCESSOR(full);
+
+#else /* !CONFIG_PREEMPT_DYNAMIC */
+
+static inline void preempt_dynamic_init(void) { }
+
+#endif /* #ifdef CONFIG_PREEMPT_DYNAMIC */
+
/**
* yield - yield the current processor to other threads.
*
@@ -8380,9 +8611,7 @@ int io_schedule_prepare(void)
int old_iowait = current->in_iowait;
current->in_iowait = 1;
- if (current->plug)
- blk_flush_plug(current->plug, true);
-
+ blk_flush_plug(current->plug, true);
return old_iowait;
}
@@ -8709,7 +8938,7 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur,
{
int ret = 1;
- if (!cpumask_weight(cur))
+ if (cpumask_empty(cur))
return ret;
ret = dl_cpuset_cpumask_can_shrink(cur, trial);
@@ -8737,8 +8966,11 @@ int task_can_attach(struct task_struct *p,
}
if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
- cs_cpus_allowed))
- ret = dl_task_can_attach(p, cs_cpus_allowed);
+ cs_cpus_allowed)) {
+ int cpu = cpumask_any_and(cpu_active_mask, cs_cpus_allowed);
+
+ ret = dl_cpu_busy(cpu, p);
+ }
out:
return ret;
@@ -9022,8 +9254,10 @@ static void cpuset_cpu_active(void)
static int cpuset_cpu_inactive(unsigned int cpu)
{
if (!cpuhp_tasks_frozen) {
- if (dl_cpu_busy(cpu))
- return -EBUSY;
+ int ret = dl_cpu_busy(cpu, NULL);
+
+ if (ret)
+ return ret;
cpuset_update_active_cpus();
} else {
num_cpus_frozen++;
@@ -9053,6 +9287,7 @@ int sched_cpu_activate(unsigned int cpu)
set_cpu_active(cpu, true);
if (sched_smp_initialized) {
+ sched_update_numa(cpu, true);
sched_domains_numa_masks_set(cpu);
cpuset_cpu_active();
}
@@ -9131,10 +9366,12 @@ int sched_cpu_deactivate(unsigned int cpu)
if (!sched_smp_initialized)
return 0;
+ sched_update_numa(cpu, false);
ret = cpuset_cpu_inactive(cpu);
if (ret) {
balance_push_set(cpu, false);
set_cpu_active(cpu, true);
+ sched_update_numa(cpu, true);
return ret;
}
sched_domains_numa_masks_clear(cpu);
@@ -9237,7 +9474,7 @@ int sched_cpu_dying(unsigned int cpu)
void __init sched_init_smp(void)
{
- sched_init_numa();
+ sched_init_numa(NUMA_NO_NODE);
/*
* There's no userspace yet to cause hotplug operations; hence all the
@@ -9249,7 +9486,7 @@ void __init sched_init_smp(void)
mutex_unlock(&sched_domains_mutex);
/* Move init over to a non-isolated CPU */
- if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0)
+ if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_TYPE_DOMAIN)) < 0)
BUG();
current->flags &= ~PF_NO_SETAFFINITY;
sched_init_granularity();
@@ -9302,11 +9539,11 @@ void __init sched_init(void)
int i;
/* Make sure the linker didn't screw up */
- BUG_ON(&idle_sched_class + 1 != &fair_sched_class ||
- &fair_sched_class + 1 != &rt_sched_class ||
- &rt_sched_class + 1 != &dl_sched_class);
+ BUG_ON(&idle_sched_class != &fair_sched_class + 1 ||
+ &fair_sched_class != &rt_sched_class + 1 ||
+ &rt_sched_class != &dl_sched_class + 1);
#ifdef CONFIG_SMP
- BUG_ON(&dl_sched_class + 1 != &stop_sched_class);
+ BUG_ON(&dl_sched_class != &stop_sched_class + 1);
#endif
wait_bit_init();
@@ -9349,7 +9586,6 @@ void __init sched_init(void)
#endif /* CONFIG_CPUMASK_OFFSTACK */
init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(), global_rt_runtime());
- init_dl_bandwidth(&def_dl_bandwidth, global_rt_period(), global_rt_runtime());
#ifdef CONFIG_SMP
init_defrootdomain();