Merge branch 'sched-wq' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq into sched/core
This commit is contained in:
Ingo Molnar
commit
95ae3c59fa
|
|
@ -48,6 +48,31 @@ extern ssize_t arch_cpu_release(const char *, size_t);
|
|||
#endif
|
||||
struct notifier_block;
|
||||
|
||||
/*
|
||||
* CPU notifier priorities.
|
||||
*/
|
||||
enum {
|
||||
/*
|
||||
* SCHED_ACTIVE marks a cpu which is coming up active during
|
||||
* CPU_ONLINE and CPU_DOWN_FAILED and must be the first
|
||||
* notifier. CPUSET_ACTIVE adjusts cpuset according to
|
||||
* cpu_active mask right after SCHED_ACTIVE. During
|
||||
* CPU_DOWN_PREPARE, SCHED_INACTIVE and CPUSET_INACTIVE are
|
||||
* ordered in the similar way.
|
||||
*
|
||||
* This ordering guarantees consistent cpu_active mask and
|
||||
* migration behavior to all cpu notifiers.
|
||||
*/
|
||||
CPU_PRI_SCHED_ACTIVE = INT_MAX,
|
||||
CPU_PRI_CPUSET_ACTIVE = INT_MAX - 1,
|
||||
CPU_PRI_SCHED_INACTIVE = INT_MIN + 1,
|
||||
CPU_PRI_CPUSET_INACTIVE = INT_MIN,
|
||||
|
||||
/* migration should happen before other stuff but after perf */
|
||||
CPU_PRI_PERF = 20,
|
||||
CPU_PRI_MIGRATION = 10,
|
||||
};
|
||||
|
||||
#ifdef CONFIG_SMP
|
||||
/* Need to know about CPUs going up/down? */
|
||||
#if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE)
|
||||
|
|
|
|||
|
|
@ -20,6 +20,7 @@ extern int number_of_cpusets; /* How many cpusets are defined in system? */
|
|||
|
||||
extern int cpuset_init(void);
|
||||
extern void cpuset_init_smp(void);
|
||||
extern void cpuset_update_active_cpus(void);
|
||||
extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
|
||||
extern int cpuset_cpus_allowed_fallback(struct task_struct *p);
|
||||
extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
|
||||
|
|
@ -132,6 +133,11 @@ static inline void set_mems_allowed(nodemask_t nodemask)
|
|||
static inline int cpuset_init(void) { return 0; }
|
||||
static inline void cpuset_init_smp(void) {}
|
||||
|
||||
static inline void cpuset_update_active_cpus(void)
|
||||
{
|
||||
partition_sched_domains(1, NULL, NULL);
|
||||
}
|
||||
|
||||
static inline void cpuset_cpus_allowed(struct task_struct *p,
|
||||
struct cpumask *mask)
|
||||
{
|
||||
|
|
|
|||
|
|
@ -1068,7 +1068,7 @@ static inline void perf_event_disable(struct perf_event *event) { }
|
|||
#define perf_cpu_notifier(fn) \
|
||||
do { \
|
||||
static struct notifier_block fn##_nb __cpuinitdata = \
|
||||
{ .notifier_call = fn, .priority = 20 }; \
|
||||
{ .notifier_call = fn, .priority = CPU_PRI_PERF }; \
|
||||
fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE, \
|
||||
(void *)(unsigned long)smp_processor_id()); \
|
||||
fn(&fn##_nb, (unsigned long)CPU_STARTING, \
|
||||
|
|
|
|||
|
|
@ -1696,6 +1696,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
|
|||
#define PF_EXITING 0x00000004 /* getting shut down */
|
||||
#define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */
|
||||
#define PF_VCPU 0x00000010 /* I'm a virtual CPU */
|
||||
#define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */
|
||||
#define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */
|
||||
#define PF_MCE_PROCESS 0x00000080 /* process policy on mce errors */
|
||||
#define PF_SUPERPRIV 0x00000100 /* used super-user privileges */
|
||||
|
|
|
|||
|
|
@ -235,11 +235,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
|
|||
return -EINVAL;
|
||||
|
||||
cpu_hotplug_begin();
|
||||
set_cpu_active(cpu, false);
|
||||
err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls);
|
||||
if (err) {
|
||||
set_cpu_active(cpu, true);
|
||||
|
||||
nr_calls--;
|
||||
__cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL);
|
||||
printk("%s: attempt to take down CPU %u failed\n",
|
||||
|
|
@ -249,7 +246,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
|
|||
|
||||
err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
|
||||
if (err) {
|
||||
set_cpu_active(cpu, true);
|
||||
/* CPU didn't die: tell everyone. Can't complain. */
|
||||
cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);
|
||||
|
||||
|
|
@ -321,8 +317,6 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
|
|||
goto out_notify;
|
||||
BUG_ON(!cpu_online(cpu));
|
||||
|
||||
set_cpu_active(cpu, true);
|
||||
|
||||
/* Now call notifier in preparation. */
|
||||
cpu_notify(CPU_ONLINE | mod, hcpu);
|
||||
|
||||
|
|
|
|||
|
|
@ -2113,31 +2113,17 @@ static void scan_for_empty_cpusets(struct cpuset *root)
|
|||
* but making no active use of cpusets.
|
||||
*
|
||||
* This routine ensures that top_cpuset.cpus_allowed tracks
|
||||
* cpu_online_map on each CPU hotplug (cpuhp) event.
|
||||
* cpu_active_mask on each CPU hotplug (cpuhp) event.
|
||||
*
|
||||
* Called within get_online_cpus(). Needs to call cgroup_lock()
|
||||
* before calling generate_sched_domains().
|
||||
*/
|
||||
static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
|
||||
unsigned long phase, void *unused_cpu)
|
||||
void __cpuexit cpuset_update_active_cpus(void)
|
||||
{
|
||||
struct sched_domain_attr *attr;
|
||||
cpumask_var_t *doms;
|
||||
int ndoms;
|
||||
|
||||
switch (phase) {
|
||||
case CPU_ONLINE:
|
||||
case CPU_ONLINE_FROZEN:
|
||||
case CPU_DOWN_PREPARE:
|
||||
case CPU_DOWN_PREPARE_FROZEN:
|
||||
case CPU_DOWN_FAILED:
|
||||
case CPU_DOWN_FAILED_FROZEN:
|
||||
break;
|
||||
|
||||
default:
|
||||
return NOTIFY_DONE;
|
||||
}
|
||||
|
||||
cgroup_lock();
|
||||
mutex_lock(&callback_mutex);
|
||||
cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
|
||||
|
|
@ -2148,8 +2134,6 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
|
|||
|
||||
/* Have scheduler rebuild the domains */
|
||||
partition_sched_domains(ndoms, doms, attr);
|
||||
|
||||
return NOTIFY_OK;
|
||||
}
|
||||
|
||||
#ifdef CONFIG_MEMORY_HOTPLUG
|
||||
|
|
@ -2203,7 +2187,6 @@ void __init cpuset_init_smp(void)
|
|||
cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
|
||||
top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
|
||||
|
||||
hotcpu_notifier(cpuset_track_online_cpus, 0);
|
||||
hotplug_memory_notifier(cpuset_track_online_nodes, 10);
|
||||
|
||||
cpuset_wq = create_singlethread_workqueue("cpuset");
|
||||
|
|
|
|||
|
|
@ -907,7 +907,7 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p)
|
|||
{
|
||||
unsigned long new_flags = p->flags;
|
||||
|
||||
new_flags &= ~PF_SUPERPRIV;
|
||||
new_flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
|
||||
new_flags |= PF_FORKNOEXEC;
|
||||
new_flags |= PF_STARTING;
|
||||
p->flags = new_flags;
|
||||
|
|
|
|||
207
kernel/sched.c
207
kernel/sched.c
|
|
@ -77,6 +77,7 @@
|
|||
#include <asm/irq_regs.h>
|
||||
|
||||
#include "sched_cpupri.h"
|
||||
#include "workqueue_sched.h"
|
||||
|
||||
#define CREATE_TRACE_POINTS
|
||||
#include <trace/events/sched.h>
|
||||
|
|
@ -2264,11 +2265,55 @@ static void update_avg(u64 *avg, u64 sample)
|
|||
}
|
||||
#endif
|
||||
|
||||
/***
|
||||
static inline void ttwu_activate(struct task_struct *p, struct rq *rq,
|
||||
bool is_sync, bool is_migrate, bool is_local,
|
||||
unsigned long en_flags)
|
||||
{
|
||||
schedstat_inc(p, se.statistics.nr_wakeups);
|
||||
if (is_sync)
|
||||
schedstat_inc(p, se.statistics.nr_wakeups_sync);
|
||||
if (is_migrate)
|
||||
schedstat_inc(p, se.statistics.nr_wakeups_migrate);
|
||||
if (is_local)
|
||||
schedstat_inc(p, se.statistics.nr_wakeups_local);
|
||||
else
|
||||
schedstat_inc(p, se.statistics.nr_wakeups_remote);
|
||||
|
||||
activate_task(rq, p, en_flags);
|
||||
}
|
||||
|
||||
static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq,
|
||||
int wake_flags, bool success)
|
||||
{
|
||||
trace_sched_wakeup(p, success);
|
||||
check_preempt_curr(rq, p, wake_flags);
|
||||
|
||||
p->state = TASK_RUNNING;
|
||||
#ifdef CONFIG_SMP
|
||||
if (p->sched_class->task_woken)
|
||||
p->sched_class->task_woken(rq, p);
|
||||
|
||||
if (unlikely(rq->idle_stamp)) {
|
||||
u64 delta = rq->clock - rq->idle_stamp;
|
||||
u64 max = 2*sysctl_sched_migration_cost;
|
||||
|
||||
if (delta > max)
|
||||
rq->avg_idle = max;
|
||||
else
|
||||
update_avg(&rq->avg_idle, delta);
|
||||
rq->idle_stamp = 0;
|
||||
}
|
||||
#endif
|
||||
/* if a worker is waking up, notify workqueue */
|
||||
if ((p->flags & PF_WQ_WORKER) && success)
|
||||
wq_worker_waking_up(p, cpu_of(rq));
|
||||
}
|
||||
|
||||
/**
|
||||
* try_to_wake_up - wake up a thread
|
||||
* @p: the to-be-woken-up thread
|
||||
* @p: the thread to be awakened
|
||||
* @state: the mask of task states that can be woken
|
||||
* @sync: do a synchronous wakeup?
|
||||
* @wake_flags: wake modifier flags (WF_*)
|
||||
*
|
||||
* Put it on the run-queue if it's not already there. The "current"
|
||||
* thread is always on the run-queue (except when the actual
|
||||
|
|
@ -2276,7 +2321,8 @@ static void update_avg(u64 *avg, u64 sample)
|
|||
* the simpler "current->state = TASK_RUNNING" to mark yourself
|
||||
* runnable without the overhead of this.
|
||||
*
|
||||
* returns failure only if the task is already active.
|
||||
* Returns %true if @p was woken up, %false if it was already running
|
||||
* or @state didn't match @p's state.
|
||||
*/
|
||||
static int try_to_wake_up(struct task_struct *p, unsigned int state,
|
||||
int wake_flags)
|
||||
|
|
@ -2356,38 +2402,11 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
|
|||
|
||||
out_activate:
|
||||
#endif /* CONFIG_SMP */
|
||||
schedstat_inc(p, se.statistics.nr_wakeups);
|
||||
if (wake_flags & WF_SYNC)
|
||||
schedstat_inc(p, se.statistics.nr_wakeups_sync);
|
||||
if (orig_cpu != cpu)
|
||||
schedstat_inc(p, se.statistics.nr_wakeups_migrate);
|
||||
if (cpu == this_cpu)
|
||||
schedstat_inc(p, se.statistics.nr_wakeups_local);
|
||||
else
|
||||
schedstat_inc(p, se.statistics.nr_wakeups_remote);
|
||||
activate_task(rq, p, en_flags);
|
||||
ttwu_activate(p, rq, wake_flags & WF_SYNC, orig_cpu != cpu,
|
||||
cpu == this_cpu, en_flags);
|
||||
success = 1;
|
||||
|
||||
out_running:
|
||||
trace_sched_wakeup(p, success);
|
||||
check_preempt_curr(rq, p, wake_flags);
|
||||
|
||||
p->state = TASK_RUNNING;
|
||||
#ifdef CONFIG_SMP
|
||||
if (p->sched_class->task_woken)
|
||||
p->sched_class->task_woken(rq, p);
|
||||
|
||||
if (unlikely(rq->idle_stamp)) {
|
||||
u64 delta = rq->clock - rq->idle_stamp;
|
||||
u64 max = 2*sysctl_sched_migration_cost;
|
||||
|
||||
if (delta > max)
|
||||
rq->avg_idle = max;
|
||||
else
|
||||
update_avg(&rq->avg_idle, delta);
|
||||
rq->idle_stamp = 0;
|
||||
}
|
||||
#endif
|
||||
ttwu_post_activation(p, rq, wake_flags, success);
|
||||
out:
|
||||
task_rq_unlock(rq, &flags);
|
||||
put_cpu();
|
||||
|
|
@ -2395,6 +2414,37 @@ out:
|
|||
return success;
|
||||
}
|
||||
|
||||
/**
|
||||
* try_to_wake_up_local - try to wake up a local task with rq lock held
|
||||
* @p: the thread to be awakened
|
||||
*
|
||||
* Put @p on the run-queue if it's not alredy there. The caller must
|
||||
* ensure that this_rq() is locked, @p is bound to this_rq() and not
|
||||
* the current task. this_rq() stays locked over invocation.
|
||||
*/
|
||||
static void try_to_wake_up_local(struct task_struct *p)
|
||||
{
|
||||
struct rq *rq = task_rq(p);
|
||||
bool success = false;
|
||||
|
||||
BUG_ON(rq != this_rq());
|
||||
BUG_ON(p == current);
|
||||
lockdep_assert_held(&rq->lock);
|
||||
|
||||
if (!(p->state & TASK_NORMAL))
|
||||
return;
|
||||
|
||||
if (!p->se.on_rq) {
|
||||
if (likely(!task_running(rq, p))) {
|
||||
schedstat_inc(rq, ttwu_count);
|
||||
schedstat_inc(rq, ttwu_local);
|
||||
}
|
||||
ttwu_activate(p, rq, false, false, true, ENQUEUE_WAKEUP);
|
||||
success = true;
|
||||
}
|
||||
ttwu_post_activation(p, rq, 0, success);
|
||||
}
|
||||
|
||||
/**
|
||||
* wake_up_process - Wake up a specific process
|
||||
* @p: The process to be woken up.
|
||||
|
|
@ -3600,10 +3650,24 @@ need_resched_nonpreemptible:
|
|||
clear_tsk_need_resched(prev);
|
||||
|
||||
if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
|
||||
if (unlikely(signal_pending_state(prev->state, prev)))
|
||||
if (unlikely(signal_pending_state(prev->state, prev))) {
|
||||
prev->state = TASK_RUNNING;
|
||||
else
|
||||
} else {
|
||||
/*
|
||||
* If a worker is going to sleep, notify and
|
||||
* ask workqueue whether it wants to wake up a
|
||||
* task to maintain concurrency. If so, wake
|
||||
* up the task.
|
||||
*/
|
||||
if (prev->flags & PF_WQ_WORKER) {
|
||||
struct task_struct *to_wakeup;
|
||||
|
||||
to_wakeup = wq_worker_sleeping(prev, cpu);
|
||||
if (to_wakeup)
|
||||
try_to_wake_up_local(to_wakeup);
|
||||
}
|
||||
deactivate_task(rq, prev, DEQUEUE_SLEEP);
|
||||
}
|
||||
switch_count = &prev->nvcsw;
|
||||
}
|
||||
|
||||
|
|
@ -5804,20 +5868,49 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
|
|||
*/
|
||||
static struct notifier_block __cpuinitdata migration_notifier = {
|
||||
.notifier_call = migration_call,
|
||||
.priority = 10
|
||||
.priority = CPU_PRI_MIGRATION,
|
||||
};
|
||||
|
||||
static int __cpuinit sched_cpu_active(struct notifier_block *nfb,
|
||||
unsigned long action, void *hcpu)
|
||||
{
|
||||
switch (action & ~CPU_TASKS_FROZEN) {
|
||||
case CPU_ONLINE:
|
||||
case CPU_DOWN_FAILED:
|
||||
set_cpu_active((long)hcpu, true);
|
||||
return NOTIFY_OK;
|
||||
default:
|
||||
return NOTIFY_DONE;
|
||||
}
|
||||
}
|
||||
|
||||
static int __cpuinit sched_cpu_inactive(struct notifier_block *nfb,
|
||||
unsigned long action, void *hcpu)
|
||||
{
|
||||
switch (action & ~CPU_TASKS_FROZEN) {
|
||||
case CPU_DOWN_PREPARE:
|
||||
set_cpu_active((long)hcpu, false);
|
||||
return NOTIFY_OK;
|
||||
default:
|
||||
return NOTIFY_DONE;
|
||||
}
|
||||
}
|
||||
|
||||
static int __init migration_init(void)
|
||||
{
|
||||
void *cpu = (void *)(long)smp_processor_id();
|
||||
int err;
|
||||
|
||||
/* Start one for the boot CPU: */
|
||||
/* Initialize migration for the boot CPU */
|
||||
err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
|
||||
BUG_ON(err == NOTIFY_BAD);
|
||||
migration_call(&migration_notifier, CPU_ONLINE, cpu);
|
||||
register_cpu_notifier(&migration_notifier);
|
||||
|
||||
/* Register cpu active notifiers */
|
||||
cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE);
|
||||
cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE);
|
||||
|
||||
return 0;
|
||||
}
|
||||
early_initcall(migration_init);
|
||||
|
|
@ -7276,29 +7369,35 @@ int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls)
|
|||
}
|
||||
#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
|
||||
|
||||
#ifndef CONFIG_CPUSETS
|
||||
/*
|
||||
* Add online and remove offline CPUs from the scheduler domains.
|
||||
* When cpusets are enabled they take over this function.
|
||||
* Update cpusets according to cpu_active mask. If cpusets are
|
||||
* disabled, cpuset_update_active_cpus() becomes a simple wrapper
|
||||
* around partition_sched_domains().
|
||||
*/
|
||||
static int update_sched_domains(struct notifier_block *nfb,
|
||||
unsigned long action, void *hcpu)
|
||||
static int __cpuexit cpuset_cpu_active(struct notifier_block *nfb,
|
||||
unsigned long action, void *hcpu)
|
||||
{
|
||||
switch (action) {
|
||||
switch (action & ~CPU_TASKS_FROZEN) {
|
||||
case CPU_ONLINE:
|
||||
case CPU_ONLINE_FROZEN:
|
||||
case CPU_DOWN_PREPARE:
|
||||
case CPU_DOWN_PREPARE_FROZEN:
|
||||
case CPU_DOWN_FAILED:
|
||||
case CPU_DOWN_FAILED_FROZEN:
|
||||
partition_sched_domains(1, NULL, NULL);
|
||||
cpuset_update_active_cpus();
|
||||
return NOTIFY_OK;
|
||||
default:
|
||||
return NOTIFY_DONE;
|
||||
}
|
||||
}
|
||||
|
||||
static int __cpuexit cpuset_cpu_inactive(struct notifier_block *nfb,
|
||||
unsigned long action, void *hcpu)
|
||||
{
|
||||
switch (action & ~CPU_TASKS_FROZEN) {
|
||||
case CPU_DOWN_PREPARE:
|
||||
cpuset_update_active_cpus();
|
||||
return NOTIFY_OK;
|
||||
|
||||
default:
|
||||
return NOTIFY_DONE;
|
||||
}
|
||||
}
|
||||
#endif
|
||||
|
||||
static int update_runtime(struct notifier_block *nfb,
|
||||
unsigned long action, void *hcpu)
|
||||
|
|
@ -7344,10 +7443,8 @@ void __init sched_init_smp(void)
|
|||
mutex_unlock(&sched_domains_mutex);
|
||||
put_online_cpus();
|
||||
|
||||
#ifndef CONFIG_CPUSETS
|
||||
/* XXX: Theoretical race here - CPU may be hotplugged now */
|
||||
hotcpu_notifier(update_sched_domains, 0);
|
||||
#endif
|
||||
hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE);
|
||||
hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE);
|
||||
|
||||
/* RT runtime code needs to handle some hotplug events */
|
||||
hotcpu_notifier(update_runtime, 0);
|
||||
|
|
|
|||
|
|
@ -0,0 +1,16 @@
|
|||
/*
|
||||
* kernel/workqueue_sched.h
|
||||
*
|
||||
* Scheduler hooks for concurrency managed workqueue. Only to be
|
||||
* included from sched.c and workqueue.c.
|
||||
*/
|
||||
static inline void wq_worker_waking_up(struct task_struct *task,
|
||||
unsigned int cpu)
|
||||
{
|
||||
}
|
||||
|
||||
static inline struct task_struct *wq_worker_sleeping(struct task_struct *task,
|
||||
unsigned int cpu)
|
||||
{
|
||||
return NULL;
|
||||
}
|
||||
Loading…
Reference in New Issue