#include <linux/init.h>
#include <linux/uaccess.h>
#include <linux/highmem.h>
-#include <asm/mmu_context.h>
+#include <linux/mmu_context.h>
#include <linux/interrupt.h>
#include <linux/capability.h>
#include <linux/completion.h>
/*
* Return the group to which this tasks belongs.
*
- * We use task_subsys_state_check() and extend the RCU verification with
- * pi->lock and rq->lock because cpu_cgroup_attach() holds those locks for each
- * task it moves into the cgroup. Therefore by holding either of those locks,
- * we pin the task to the current cgroup.
+ * We cannot use task_subsys_state() and friends because the cgroup
+ * subsystem changes that value before the cgroup_subsys::attach() method
+ * is called, therefore we cannot pin it and might observe the wrong value.
+ *
+ * The same is true for autogroup's p->signal->autogroup->tg, the autogroup
+ * core changes this before calling sched_move_task().
+ *
+ * Instead we use a 'copy' which is updated from sched_move_task() while
+ * holding both task_struct::pi_lock and rq::lock.
*/
static inline struct task_group *task_group(struct task_struct *p)
{
- struct task_group *tg;
- struct cgroup_subsys_state *css;
-
- css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
- lockdep_is_held(&p->pi_lock) ||
- lockdep_is_held(&task_rq(p)->lock));
- tg = container_of(css, struct task_group, css);
-
- return autogroup_task_group(p, tg);
+ return p->sched_task_group;
}
/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
* After ->on_cpu is cleared, the task can be moved to a different CPU.
* We must ensure this doesn't happen until the switch is completely
* finished.
+ *
+ * Pairs with the control dependency and rmb in try_to_wake_up().
*/
- smp_wmb();
+ smp_mb();
prev->on_cpu = 0;
#endif
#ifdef CONFIG_DEBUG_SPINLOCK
#endif
+#ifdef CONFIG_SMP
+static void unthrottle_offline_cfs_rqs(struct rq *rq);
+#endif
+
#include "sched_idletask.c"
#include "sched_fair.c"
#include "sched_rt.c"
* a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
*
* sched_move_task() holds both and thus holding either pins the cgroup,
- * see set_task_rq().
+ * see task_group().
*
* Furthermore, all task_rq users should acquire both locks, see
* task_rq_lock().
success = 1; /* we're going to change ->state */
cpu = task_cpu(p);
+ /*
+ * Ensure we load p->on_rq _after_ p->state, otherwise it would
+ * be possible to, falsely, observe p->on_rq == 0 and get stuck
+ * in smp_cond_load_acquire() below.
+ *
+ * sched_ttwu_pending() try_to_wake_up()
+ * [S] p->on_rq = 1; [L] P->state
+ * UNLOCK rq->lock -----.
+ * \
+ * +--- RMB
+ * schedule() /
+ * LOCK rq->lock -----'
+ * UNLOCK rq->lock
+ *
+ * [task p]
+ * [S] p->state = UNINTERRUPTIBLE [L] p->on_rq
+ *
+ * Pairs with the UNLOCK+LOCK on rq->lock from the
+ * last wakeup of our task and the schedule that got our task
+ * current.
+ */
+ smp_rmb();
if (p->on_rq && ttwu_remote(p, wake_flags))
goto stat;
{
struct rq *rq = task_rq(p);
- BUG_ON(rq != this_rq());
- BUG_ON(p == current);
+ if (WARN_ON_ONCE(rq != this_rq()) ||
+ WARN_ON_ONCE(p == current))
+ return;
+
lockdep_assert_held(&rq->lock);
if (!raw_spin_trylock(&p->pi_lock)) {
*/
int wake_up_process(struct task_struct *p)
{
- return try_to_wake_up(p, TASK_ALL, 0);
+ return try_to_wake_up(p, TASK_NORMAL, 0);
}
EXPORT_SYMBOL(wake_up_process);
* If a task dies, then it sets TASK_DEAD in tsk->state and calls
* schedule one last time. The schedule call will never return, and
* the scheduled task must drop that reference.
- * The test for TASK_DEAD must occur while the runqueue locks are
- * still held, otherwise prev could be scheduled on another cpu, die
- * there before we look at prev->state, and then the reference would
- * be dropped twice.
- * Manfred Spraul <manfred@colorfullife.com>
+ *
+ * We must observe prev->state before clearing prev->on_cpu (in
+ * finish_lock_switch), otherwise a concurrent wakeup can get prev
+ * running on another CPU and we could rave with its RUNNING -> DEAD
+ * transition, resulting in a double drop.
*/
prev_state = prev->state;
finish_arch_switch(prev);
atomic_inc(&oldmm->mm_count);
enter_lazy_tlb(oldmm, next);
} else
- switch_mm(oldmm, mm, next);
+ switch_mm_irqs_off(oldmm, mm, next);
if (!prev->mm) {
prev->active_mm = NULL;
static unsigned long
calc_load(unsigned long load, unsigned long exp, unsigned long active)
{
- load *= exp;
- load += active * (FIXED_1 - exp);
- load += 1UL << (FSHIFT - 1);
- return load >> FSHIFT;
+ unsigned long newload;
+
+ newload = load * exp + active * (FIXED_1 - exp);
+ if (active >= load)
+ newload += FIXED_1-1;
+
+ return newload / FIXED_1;
}
#ifdef CONFIG_NO_HZ
struct rq *this_rq = this_rq();
/*
- * If we're still before the sample window, we're done.
+ * If we're still before the pending sample window, we're done.
*/
+ this_rq->calc_load_update = calc_load_update;
if (time_before(jiffies, this_rq->calc_load_update))
return;
* accounted through the nohz accounting, so skip the entire deal and
* sync up for the next window.
*/
- this_rq->calc_load_update = calc_load_update;
if (time_before(jiffies, this_rq->calc_load_update + 10))
this_rq->calc_load_update += LOAD_FREQ;
}
# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs)
#endif
+static cputime_t scale_utime(cputime_t utime, cputime_t rtime, cputime_t total)
+{
+ u64 temp = (__force u64) rtime;
+
+ temp *= (__force u64) utime;
+
+ if (sizeof(cputime_t) == 4)
+ temp = div_u64(temp, (__force u32) total);
+ else
+ temp = div64_u64(temp, (__force u64) total);
+
+ return (__force cputime_t) temp;
+}
+
void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
cputime_t rtime, utime = p->utime, total = cputime_add(utime, p->stime);
*/
rtime = nsecs_to_cputime(p->se.sum_exec_runtime);
- if (total) {
- u64 temp = rtime;
-
- temp *= utime;
- do_div(temp, total);
- utime = (cputime_t)temp;
- } else
+ if (total)
+ utime = scale_utime(utime, rtime, total);
+ else
utime = rtime;
/*
total = cputime_add(cputime.utime, cputime.stime);
rtime = nsecs_to_cputime(cputime.sum_exec_runtime);
- if (total) {
- u64 temp = rtime;
-
- temp *= cputime.utime;
- do_div(temp, total);
- utime = (cputime_t)temp;
- } else
+ if (total)
+ utime = scale_utime(cputime.utime, rtime, total);
+ else
utime = rtime;
sig->prev_utime = max(sig->prev_utime, utime);
if (rt_prio(prio))
p->sched_class = &rt_sched_class;
- else
+ else {
+ if (rt_prio(oldprio))
+ p->rt.timeout = 0;
p->sched_class = &fair_sched_class;
+ }
p->prio = prio;
/*
* reset the NMI-timeout, listing all files on a slow
* console might take a lot of time:
+ * Also, reset softlockup watchdogs on all CPUs, because
+ * another CPU might be blocked waiting for us to process
+ * an IPI.
*/
touch_nmi_watchdog();
+ touch_all_softlockup_watchdogs();
if (!state_filter || (p->state & state_filter))
sched_show_task(p);
} while_each_thread(g, p);
- touch_all_softlockup_watchdogs();
-
#ifdef CONFIG_SCHED_DEBUG
sysrq_sched_debug_show();
#endif
unthrottle_cfs_rq(cfs_rq);
}
}
-#else
-static void unthrottle_offline_cfs_rqs(struct rq *rq) {}
#endif
/*
*/
rq->stop = NULL;
- /* Ensure any throttled groups are reachable by pick_next_task */
- unthrottle_offline_cfs_rqs(rq);
-
for ( ; ; ) {
/*
* There's this thread running, bail when that's the only
#endif /* CONFIG_HOTPLUG_CPU */
+#if !defined(CONFIG_HOTPLUG_CPU) || !defined(CONFIG_CFS_BANDWIDTH)
+static void unthrottle_offline_cfs_rqs(struct rq *rq) {}
+#endif
+
#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
static struct ctl_table sd_ctl_dir[] = {
*tablep = NULL;
}
+static int min_load_idx = 0;
+static int max_load_idx = CPU_LOAD_IDX_MAX-1;
+
static void
set_table_entry(struct ctl_table *entry,
const char *procname, void *data, int maxlen,
- mode_t mode, proc_handler *proc_handler)
+ mode_t mode, proc_handler *proc_handler,
+ bool load_idx)
{
entry->procname = procname;
entry->data = data;
entry->maxlen = maxlen;
entry->mode = mode;
entry->proc_handler = proc_handler;
+
+ if (load_idx) {
+ entry->extra1 = &min_load_idx;
+ entry->extra2 = &max_load_idx;
+ }
}
static struct ctl_table *
return NULL;
set_table_entry(&table[0], "min_interval", &sd->min_interval,
- sizeof(long), 0644, proc_doulongvec_minmax);
+ sizeof(long), 0644, proc_doulongvec_minmax, false);
set_table_entry(&table[1], "max_interval", &sd->max_interval,
- sizeof(long), 0644, proc_doulongvec_minmax);
+ sizeof(long), 0644, proc_doulongvec_minmax, false);
set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
- sizeof(int), 0644, proc_dointvec_minmax);
+ sizeof(int), 0644, proc_dointvec_minmax, true);
set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
- sizeof(int), 0644, proc_dointvec_minmax);
+ sizeof(int), 0644, proc_dointvec_minmax, true);
set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
- sizeof(int), 0644, proc_dointvec_minmax);
+ sizeof(int), 0644, proc_dointvec_minmax, true);
set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
- sizeof(int), 0644, proc_dointvec_minmax);
+ sizeof(int), 0644, proc_dointvec_minmax, true);
set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
- sizeof(int), 0644, proc_dointvec_minmax);
+ sizeof(int), 0644, proc_dointvec_minmax, true);
set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
- sizeof(int), 0644, proc_dointvec_minmax);
+ sizeof(int), 0644, proc_dointvec_minmax, false);
set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
- sizeof(int), 0644, proc_dointvec_minmax);
+ sizeof(int), 0644, proc_dointvec_minmax, false);
set_table_entry(&table[9], "cache_nice_tries",
&sd->cache_nice_tries,
- sizeof(int), 0644, proc_dointvec_minmax);
+ sizeof(int), 0644, proc_dointvec_minmax, false);
set_table_entry(&table[10], "flags", &sd->flags,
- sizeof(int), 0644, proc_dointvec_minmax);
+ sizeof(int), 0644, proc_dointvec_minmax, false);
set_table_entry(&table[11], "name", sd->name,
- CORENAME_MAX_SIZE, 0444, proc_dostring);
+ CORENAME_MAX_SIZE, 0444, proc_dostring, false);
/* &table[12] is terminator */
return table;
{
memset(rd, 0, sizeof(*rd));
- if (!alloc_cpumask_var(&rd->span, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL))
goto out;
- if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL))
goto free_span;
- if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
goto free_online;
if (cpupri_init(&rd->cpupri) != 0)
cpumask_clear(covered);
- for_each_cpu(i, span) {
+ for_each_cpu_wrap(i, span, cpu) {
struct cpumask *sg_span;
if (cpumask_test_cpu(i, covered))
}
#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
+static int num_cpus_frozen; /* used to mark begin/end of suspend/resume */
+
/*
* Update cpusets according to cpu_active mask. If cpusets are
* disabled, cpuset_update_active_cpus() becomes a simple wrapper
* around partition_sched_domains().
+ *
+ * If we come here as part of a suspend/resume, don't touch cpusets because we
+ * want to restore it back to its original state upon resume anyway.
*/
static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action,
void *hcpu)
{
- switch (action & ~CPU_TASKS_FROZEN) {
+ switch (action) {
+ case CPU_ONLINE_FROZEN:
+ case CPU_DOWN_FAILED_FROZEN:
+
+ /*
+ * num_cpus_frozen tracks how many CPUs are involved in suspend
+ * resume sequence. As long as this is not the last online
+ * operation in the resume sequence, just build a single sched
+ * domain, ignoring cpusets.
+ */
+ num_cpus_frozen--;
+ if (likely(num_cpus_frozen)) {
+ partition_sched_domains(1, NULL, NULL);
+ break;
+ }
+
+ /*
+ * This is the last CPU online operation. So fall through and
+ * restore the original sched domains by considering the
+ * cpuset configurations.
+ */
+
case CPU_ONLINE:
case CPU_DOWN_FAILED:
cpuset_update_active_cpus();
- return NOTIFY_OK;
+ break;
default:
return NOTIFY_DONE;
}
+ return NOTIFY_OK;
}
static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action,
void *hcpu)
{
- switch (action & ~CPU_TASKS_FROZEN) {
+ switch (action) {
case CPU_DOWN_PREPARE:
cpuset_update_active_cpus();
- return NOTIFY_OK;
+ break;
+ case CPU_DOWN_PREPARE_FROZEN:
+ num_cpus_frozen++;
+ partition_sched_domains(1, NULL, NULL);
+ break;
default:
return NOTIFY_DONE;
}
+ return NOTIFY_OK;
}
static int update_runtime(struct notifier_block *nfb,
*/
void sched_move_task(struct task_struct *tsk)
{
+ struct task_group *tg;
int on_rq, running;
unsigned long flags;
struct rq *rq;
if (unlikely(running))
tsk->sched_class->put_prev_task(rq, tsk);
+ tg = container_of(task_subsys_state_check(tsk, cpu_cgroup_subsys_id,
+ lockdep_is_held(&tsk->sighand->siglock)),
+ struct task_group, css);
+ tg = autogroup_task_group(tsk, tg);
+ tsk->sched_task_group = tg;
+
#ifdef CONFIG_FAIR_GROUP_SCHED
if (tsk->sched_class->task_move_group)
tsk->sched_class->task_move_group(tsk, on_rq);
{
struct task_struct *g, *p;
+ /*
+ * Autogroups do not have RT tasks; see autogroup_create().
+ */
+ if (task_group_is_autogroup(tg))
+ return 0;
+
do_each_thread(g, p) {
if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg)
return 1;