#include <linux/delay.h>
#include <linux/stop_machine.h>
+#define RCU_KTHREAD_PRIO 1
+
+#ifdef CONFIG_RCU_BOOST
+#define RCU_BOOST_PRIO CONFIG_RCU_BOOST_PRIO
+#else
+#define RCU_BOOST_PRIO RCU_KTHREAD_PRIO
+#endif
+
/*
* Check the RCU kernel configuration parameters and print informative
* messages about anything out of the ordinary. If you like #ifdef, you
#ifdef CONFIG_TREE_PREEMPT_RCU
-struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state);
+struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt);
DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data);
static struct rcu_state *rcu_state = &rcu_preempt_state;
+static void rcu_read_unlock_special(struct task_struct *t);
static int rcu_preempted_readers_exp(struct rcu_node *rnp);
/*
{
struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
- rdp->passed_quiesc_completed = rdp->gpnum - 1;
+ rdp->passed_quiesce_gpnum = rdp->gpnum;
barrier();
- rdp->passed_quiesc = 1;
+ if (rdp->passed_quiesce == 0)
+ trace_rcu_grace_period("rcu_preempt", rdp->gpnum, "cpuqs");
+ rdp->passed_quiesce = 1;
current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
}
struct rcu_data *rdp;
struct rcu_node *rnp;
- if (t->rcu_read_lock_nesting &&
+ if (t->rcu_read_lock_nesting > 0 &&
(t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
/* Possibly blocking in an RCU read-side critical section. */
if (rnp->qsmask & rdp->grpmask)
rnp->gp_tasks = &t->rcu_node_entry;
}
+ trace_rcu_preempt_task(rdp->rsp->name,
+ t->pid,
+ (rnp->qsmask & rdp->grpmask)
+ ? rnp->gpnum
+ : rnp->gpnum + 1);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
+ } else if (t->rcu_read_lock_nesting < 0 &&
+ t->rcu_read_unlock_special) {
+
+ /*
+ * Complete exit from RCU read-side critical section on
+ * behalf of preempted instance of __rcu_read_unlock().
+ */
+ rcu_read_unlock_special(t);
}
/*
* notify RCU core processing or task having blocked during the RCU
* read-side critical section.
*/
-static void rcu_read_unlock_special(struct task_struct *t)
+static noinline void rcu_read_unlock_special(struct task_struct *t)
{
int empty;
int empty_exp;
+ int empty_exp_now;
unsigned long flags;
struct list_head *np;
+#ifdef CONFIG_RCU_BOOST
+ struct rt_mutex *rbmp = NULL;
+#endif /* #ifdef CONFIG_RCU_BOOST */
struct rcu_node *rnp;
int special;
}
/* Hardware IRQ handlers cannot block. */
- if (in_irq()) {
+ if (in_irq() || in_serving_softirq()) {
local_irq_restore(flags);
return;
}
smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
np = rcu_next_node_entry(t, rnp);
list_del_init(&t->rcu_node_entry);
+ t->rcu_blocked_node = NULL;
+ trace_rcu_unlock_preempted_task("rcu_preempt",
+ rnp->gpnum, t->pid);
if (&t->rcu_node_entry == rnp->gp_tasks)
rnp->gp_tasks = np;
if (&t->rcu_node_entry == rnp->exp_tasks)
#ifdef CONFIG_RCU_BOOST
if (&t->rcu_node_entry == rnp->boost_tasks)
rnp->boost_tasks = np;
- /* Snapshot and clear ->rcu_boosted with rcu_node lock held. */
- if (t->rcu_boosted) {
- special |= RCU_READ_UNLOCK_BOOSTED;
- t->rcu_boosted = 0;
+ /* Snapshot/clear ->rcu_boost_mutex with rcu_node lock held. */
+ if (t->rcu_boost_mutex) {
+ rbmp = t->rcu_boost_mutex;
+ t->rcu_boost_mutex = NULL;
}
#endif /* #ifdef CONFIG_RCU_BOOST */
- t->rcu_blocked_node = NULL;
/*
* If this was the last task on the current list, and if
* we aren't waiting on any CPUs, report the quiescent state.
- * Note that rcu_report_unblock_qs_rnp() releases rnp->lock.
+ * Note that rcu_report_unblock_qs_rnp() releases rnp->lock,
+ * so we must take a snapshot of the expedited state.
*/
- if (empty)
- raw_spin_unlock_irqrestore(&rnp->lock, flags);
- else
+ empty_exp_now = !rcu_preempted_readers_exp(rnp);
+ if (!empty && !rcu_preempt_blocked_readers_cgp(rnp)) {
+ trace_rcu_quiescent_state_report("preempt_rcu",
+ rnp->gpnum,
+ 0, rnp->qsmask,
+ rnp->level,
+ rnp->grplo,
+ rnp->grphi,
+ !!rnp->gp_tasks);
rcu_report_unblock_qs_rnp(rnp, flags);
+ } else
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
#ifdef CONFIG_RCU_BOOST
/* Unboost if we were boosted. */
- if (special & RCU_READ_UNLOCK_BOOSTED) {
- rt_mutex_unlock(t->rcu_boost_mutex);
- t->rcu_boost_mutex = NULL;
- }
+ if (rbmp)
+ rt_mutex_unlock(rbmp);
#endif /* #ifdef CONFIG_RCU_BOOST */
/*
* If this was the last task on the expedited lists,
* then we need to report up the rcu_node hierarchy.
*/
- if (!empty_exp && !rcu_preempted_readers_exp(rnp))
- rcu_report_exp_rnp(&rcu_preempt_state, rnp);
+ if (!empty_exp && empty_exp_now)
+ rcu_report_exp_rnp(&rcu_preempt_state, rnp, true);
} else {
local_irq_restore(flags);
}
{
struct task_struct *t = current;
- barrier(); /* needed if we ever invoke rcu_read_unlock in rcutree.c */
- --t->rcu_read_lock_nesting;
- barrier(); /* decrement before load of ->rcu_read_unlock_special */
- if (t->rcu_read_lock_nesting == 0 &&
- unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
- rcu_read_unlock_special(t);
+ if (t->rcu_read_lock_nesting != 1)
+ --t->rcu_read_lock_nesting;
+ else {
+ barrier(); /* critical section before exit code. */
+ t->rcu_read_lock_nesting = INT_MIN;
+ barrier(); /* assign before ->rcu_read_unlock_special load */
+ if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
+ rcu_read_unlock_special(t);
+ barrier(); /* ->rcu_read_unlock_special load before assign */
+ t->rcu_read_lock_nesting = 0;
+ }
#ifdef CONFIG_PROVE_LOCKING
- WARN_ON_ONCE(ACCESS_ONCE(t->rcu_read_lock_nesting) < 0);
+ {
+ int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting);
+
+ WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2);
+ }
#endif /* #ifdef CONFIG_PROVE_LOCKING */
}
EXPORT_SYMBOL_GPL(__rcu_read_unlock);
* Scan the current list of tasks blocked within RCU read-side critical
* sections, printing out the tid of each.
*/
-static void rcu_print_task_stall(struct rcu_node *rnp)
+static int rcu_print_task_stall(struct rcu_node *rnp)
{
struct task_struct *t;
+ int ndetected = 0;
if (!rcu_preempt_blocked_readers_cgp(rnp))
- return;
+ return 0;
t = list_entry(rnp->gp_tasks,
struct task_struct, rcu_node_entry);
- list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry)
+ list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
printk(" P%d", t->pid);
+ ndetected++;
+ }
+ return ndetected;
}
/*
rcu_preempt_qs(cpu);
return;
}
- if (per_cpu(rcu_preempt_data, cpu).qs_pending)
+ if (t->rcu_read_lock_nesting > 0 &&
+ per_cpu(rcu_preempt_data, cpu).qs_pending)
t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS;
}
*/
void synchronize_rcu(void)
{
- struct rcu_synchronize rcu;
-
if (!rcu_scheduler_active)
return;
-
- init_rcu_head_on_stack(&rcu.head);
- init_completion(&rcu.completion);
- /* Will wake me after RCU finished. */
- call_rcu(&rcu.head, wakeme_after_rcu);
- /* Wait for it. */
- wait_for_completion(&rcu.completion);
- destroy_rcu_head_on_stack(&rcu.head);
+ wait_rcu_gp(call_rcu);
}
EXPORT_SYMBOL_GPL(synchronize_rcu);
* recursively up the tree. (Calm down, calm down, we do the recursion
* iteratively!)
*
+ * Most callers will set the "wake" flag, but the task initiating the
+ * expedited grace period need not wake itself.
+ *
* Caller must hold sync_rcu_preempt_exp_mutex.
*/
-static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
+static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
+ bool wake)
{
unsigned long flags;
unsigned long mask;
}
if (rnp->parent == NULL) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
- wake_up(&sync_rcu_preempt_exp_wq);
+ if (wake)
+ wake_up(&sync_rcu_preempt_exp_wq);
break;
}
mask = rnp->grpmask;
must_wait = 1;
}
if (!must_wait)
- rcu_report_exp_rnp(rsp, rnp);
+ rcu_report_exp_rnp(rsp, rnp, false); /* Don't wake self. */
}
/*
* Because preemptible RCU does not exist, we never have to check for
* tasks blocked within RCU read-side critical sections.
*/
-static void rcu_print_task_stall(struct rcu_node *rnp)
+static int rcu_print_task_stall(struct rcu_node *rnp)
{
+ return 0;
}
/*
* report on tasks preempted in RCU read-side critical sections during
* expedited RCU grace periods.
*/
-static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
+static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
+ bool wake)
{
- return;
}
#endif /* #ifdef CONFIG_HOTPLUG_CPU */
t = container_of(tb, struct task_struct, rcu_node_entry);
rt_mutex_init_proxy_locked(&mtx, t);
t->rcu_boost_mutex = &mtx;
- t->rcu_boosted = 1;
raw_spin_unlock_irqrestore(&rnp->lock, flags);
rt_mutex_lock(&mtx); /* Side effect: boosts task t's priority. */
rt_mutex_unlock(&mtx); /* Keep lockdep happy. */
- return rnp->exp_tasks != NULL || rnp->boost_tasks != NULL;
+ return ACCESS_ONCE(rnp->exp_tasks) != NULL ||
+ ACCESS_ONCE(rnp->boost_tasks) != NULL;
}
/*
int spincnt = 0;
int more2boost;
+ trace_rcu_utilization("Start boost kthread@init");
for (;;) {
rnp->boost_kthread_status = RCU_KTHREAD_WAITING;
+ trace_rcu_utilization("End boost kthread@rcu_wait");
rcu_wait(rnp->boost_tasks || rnp->exp_tasks);
+ trace_rcu_utilization("Start boost kthread@rcu_wait");
rnp->boost_kthread_status = RCU_KTHREAD_RUNNING;
more2boost = rcu_boost(rnp);
if (more2boost)
else
spincnt = 0;
if (spincnt > 10) {
+ trace_rcu_utilization("End boost kthread@rcu_yield");
rcu_yield(rcu_boost_kthread_timer, (unsigned long)rnp);
+ trace_rcu_utilization("Start boost kthread@rcu_yield");
spincnt = 0;
}
}
/* NOTREACHED */
+ trace_rcu_utilization("End boost kthread@notreached");
return 0;
}
local_irq_save(flags);
__this_cpu_write(rcu_cpu_has_work, 1);
- if (__this_cpu_read(rcu_cpu_kthread_task) == NULL) {
- local_irq_restore(flags);
- return;
- }
- wake_up_process(__this_cpu_read(rcu_cpu_kthread_task));
+ if (__this_cpu_read(rcu_cpu_kthread_task) != NULL &&
+ current != __this_cpu_read(rcu_cpu_kthread_task))
+ wake_up_process(__this_cpu_read(rcu_cpu_kthread_task));
local_irq_restore(flags);
}
/*
+ * Is the current CPU running the RCU-callbacks kthread?
+ * Caller must have preemption disabled.
+ */
+static bool rcu_is_callbacks_kthread(void)
+{
+ return __get_cpu_var(rcu_cpu_kthread_task) == current;
+}
+
+/*
* Set the affinity of the boost kthread. The CPU-hotplug locks are
* held, so no one should be messing with the existence of the boost
* kthread.
if (rnp->boost_kthread_task != NULL)
return 0;
t = kthread_create(rcu_boost_kthread, (void *)rnp,
- "rcub%d", rnp_index);
+ "rcub/%d", rnp_index);
if (IS_ERR(t))
return PTR_ERR(t);
raw_spin_lock_irqsave(&rnp->lock, flags);
rnp->boost_kthread_task = t;
raw_spin_unlock_irqrestore(&rnp->lock, flags);
- sp.sched_priority = RCU_KTHREAD_PRIO;
+ sp.sched_priority = RCU_BOOST_PRIO;
sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
return 0;
{
struct sched_param sp;
struct timer_list yield_timer;
+ int prio = current->rt_priority;
setup_timer_on_stack(&yield_timer, f, arg);
mod_timer(&yield_timer, jiffies + 2);
sched_setscheduler_nocheck(current, SCHED_NORMAL, &sp);
set_user_nice(current, 19);
schedule();
- sp.sched_priority = RCU_KTHREAD_PRIO;
+ set_user_nice(current, 0);
+ sp.sched_priority = prio;
sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
del_timer(&yield_timer);
}
/*
* Per-CPU kernel thread that invokes RCU callbacks. This replaces the
- * earlier RCU softirq.
+ * RCU softirq used in flavors and configurations of RCU that do not
+ * support RCU priority boosting.
*/
static int rcu_cpu_kthread(void *arg)
{
char work;
char *workp = &per_cpu(rcu_cpu_has_work, cpu);
+ trace_rcu_utilization("Start CPU kthread@init");
for (;;) {
*statusp = RCU_KTHREAD_WAITING;
+ trace_rcu_utilization("End CPU kthread@rcu_wait");
rcu_wait(*workp != 0 || kthread_should_stop());
+ trace_rcu_utilization("Start CPU kthread@rcu_wait");
local_bh_disable();
if (rcu_cpu_kthread_should_stop(cpu)) {
local_bh_enable();
spincnt = 0;
if (spincnt > 10) {
*statusp = RCU_KTHREAD_YIELDING;
+ trace_rcu_utilization("End CPU kthread@rcu_yield");
rcu_yield(rcu_cpu_kthread_timer, (unsigned long)cpu);
+ trace_rcu_utilization("Start CPU kthread@rcu_yield");
spincnt = 0;
}
}
*statusp = RCU_KTHREAD_STOPPED;
+ trace_rcu_utilization("End CPU kthread@term");
return 0;
}
if (!rcu_scheduler_fully_active ||
per_cpu(rcu_cpu_kthread_task, cpu) != NULL)
return 0;
- t = kthread_create(rcu_cpu_kthread, (void *)(long)cpu, "rcuc%d", cpu);
+ t = kthread_create_on_node(rcu_cpu_kthread,
+ (void *)(long)cpu,
+ cpu_to_node(cpu),
+ "rcuc/%d", cpu);
if (IS_ERR(t))
return PTR_ERR(t);
if (cpu_online(cpu))
return 0;
if (rnp->node_kthread_task == NULL) {
t = kthread_create(rcu_node_kthread, (void *)rnp,
- "rcun%d", rnp_index);
+ "rcun/%d", rnp_index);
if (IS_ERR(t))
return PTR_ERR(t);
raw_spin_lock_irqsave(&rnp->lock, flags);
WARN_ON_ONCE(1);
}
+static bool rcu_is_callbacks_kthread(void)
+{
+ return false;
+}
+
static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
{
}
* grace period works for us.
*/
get_online_cpus();
- snap = atomic_read(&sync_sched_expedited_started) - 1;
+ snap = atomic_read(&sync_sched_expedited_started);
smp_mb(); /* ensure read is before try_stop_cpus(). */
}
* 1 if so. This function is part of the RCU implementation; it is -not-
* an exported member of the RCU API.
*
- * Because we have preemptible RCU, just check whether this CPU needs
- * any flavor of RCU. Do not chew up lots of CPU cycles with preemption
- * disabled in a most-likely vain attempt to cause RCU not to need this CPU.
+ * Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs
+ * any flavor of RCU.
*/
int rcu_needs_cpu(int cpu)
{
- return rcu_needs_cpu_quick_check(cpu);
+ return rcu_cpu_has_callbacks(cpu);
+}
+
+/*
+ * Because we do not have RCU_FAST_NO_HZ, don't bother initializing for it.
+ */
+static void rcu_prepare_for_idle_init(int cpu)
+{
+}
+
+/*
+ * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up
+ * after it.
+ */
+static void rcu_cleanup_after_idle(int cpu)
+{
}
/*
- * Check to see if we need to continue a callback-flush operations to
- * allow the last CPU to enter dyntick-idle mode. But fast dyntick-idle
- * entry is not configured, so we never do need to.
+ * Do the idle-entry grace-period work, which, because CONFIG_RCU_FAST_NO_HZ=y,
+ * is nothing.
*/
-static void rcu_needs_cpu_flush(void)
+static void rcu_prepare_for_idle(int cpu)
{
}
#else /* #if !defined(CONFIG_RCU_FAST_NO_HZ) */
-#define RCU_NEEDS_CPU_FLUSHES 5
+/*
+ * This code is invoked when a CPU goes idle, at which point we want
+ * to have the CPU do everything required for RCU so that it can enter
+ * the energy-efficient dyntick-idle mode. This is handled by a
+ * state machine implemented by rcu_prepare_for_idle() below.
+ *
+ * The following three proprocessor symbols control this state machine:
+ *
+ * RCU_IDLE_FLUSHES gives the maximum number of times that we will attempt
+ * to satisfy RCU. Beyond this point, it is better to incur a periodic
+ * scheduling-clock interrupt than to loop through the state machine
+ * at full power.
+ * RCU_IDLE_OPT_FLUSHES gives the number of RCU_IDLE_FLUSHES that are
+ * optional if RCU does not need anything immediately from this
+ * CPU, even if this CPU still has RCU callbacks queued. The first
+ * times through the state machine are mandatory: we need to give
+ * the state machine a chance to communicate a quiescent state
+ * to the RCU core.
+ * RCU_IDLE_GP_DELAY gives the number of jiffies that a CPU is permitted
+ * to sleep in dyntick-idle mode with RCU callbacks pending. This
+ * is sized to be roughly one RCU grace period. Those energy-efficiency
+ * benchmarkers who might otherwise be tempted to set this to a large
+ * number, be warned: Setting RCU_IDLE_GP_DELAY too high can hang your
+ * system. And if you are -that- concerned about energy efficiency,
+ * just power the system down and be done with it!
+ *
+ * The values below work well in practice. If future workloads require
+ * adjustment, they can be converted into kernel config parameters, though
+ * making the state machine smarter might be a better option.
+ */
+#define RCU_IDLE_FLUSHES 5 /* Number of dyntick-idle tries. */
+#define RCU_IDLE_OPT_FLUSHES 3 /* Optional dyntick-idle tries. */
+#define RCU_IDLE_GP_DELAY 6 /* Roughly one grace period. */
+
static DEFINE_PER_CPU(int, rcu_dyntick_drain);
static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff);
+static DEFINE_PER_CPU(struct hrtimer, rcu_idle_gp_timer);
+static ktime_t rcu_idle_gp_wait;
/*
- * Check to see if any future RCU-related work will need to be done
- * by the current CPU, even if none need be done immediately, returning
- * 1 if so. This function is part of the RCU implementation; it is -not-
- * an exported member of the RCU API.
+ * Allow the CPU to enter dyntick-idle mode if either: (1) There are no
+ * callbacks on this CPU, (2) this CPU has not yet attempted to enter
+ * dyntick-idle mode, or (3) this CPU is in the process of attempting to
+ * enter dyntick-idle mode. Otherwise, if we have recently tried and failed
+ * to enter dyntick-idle mode, we refuse to try to enter it. After all,
+ * it is better to incur scheduling-clock interrupts than to spin
+ * continuously for the same time duration!
+ */
+int rcu_needs_cpu(int cpu)
+{
+ /* If no callbacks, RCU doesn't need the CPU. */
+ if (!rcu_cpu_has_callbacks(cpu))
+ return 0;
+ /* Otherwise, RCU needs the CPU only if it recently tried and failed. */
+ return per_cpu(rcu_dyntick_holdoff, cpu) == jiffies;
+}
+
+/*
+ * Timer handler used to force CPU to start pushing its remaining RCU
+ * callbacks in the case where it entered dyntick-idle mode with callbacks
+ * pending. The hander doesn't really need to do anything because the
+ * real work is done upon re-entry to idle, or by the next scheduling-clock
+ * interrupt should idle not be re-entered.
+ */
+static enum hrtimer_restart rcu_idle_gp_timer_func(struct hrtimer *hrtp)
+{
+ trace_rcu_prep_idle("Timer");
+ return HRTIMER_NORESTART;
+}
+
+/*
+ * Initialize the timer used to pull CPUs out of dyntick-idle mode.
+ */
+static void rcu_prepare_for_idle_init(int cpu)
+{
+ static int firsttime = 1;
+ struct hrtimer *hrtp = &per_cpu(rcu_idle_gp_timer, cpu);
+
+ hrtimer_init(hrtp, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtp->function = rcu_idle_gp_timer_func;
+ if (firsttime) {
+ unsigned int upj = jiffies_to_usecs(RCU_IDLE_GP_DELAY);
+
+ rcu_idle_gp_wait = ns_to_ktime(upj * (u64)1000);
+ firsttime = 0;
+ }
+}
+
+/*
+ * Clean up for exit from idle. Because we are exiting from idle, there
+ * is no longer any point to rcu_idle_gp_timer, so cancel it. This will
+ * do nothing if this timer is not active, so just cancel it unconditionally.
+ */
+static void rcu_cleanup_after_idle(int cpu)
+{
+ hrtimer_cancel(&per_cpu(rcu_idle_gp_timer, cpu));
+}
+
+/*
+ * Check to see if any RCU-related work can be done by the current CPU,
+ * and if so, schedule a softirq to get it done. This function is part
+ * of the RCU implementation; it is -not- an exported member of the RCU API.
*
- * Because we are not supporting preemptible RCU, attempt to accelerate
- * any current grace periods so that RCU no longer needs this CPU, but
- * only if all other CPUs are already in dynticks-idle mode. This will
- * allow the CPU cores to be powered down immediately, as opposed to after
- * waiting many milliseconds for grace periods to elapse.
+ * The idea is for the current CPU to clear out all work required by the
+ * RCU core for the current grace period, so that this CPU can be permitted
+ * to enter dyntick-idle mode. In some cases, it will need to be awakened
+ * at the end of the grace period by whatever CPU ends the grace period.
+ * This allows CPUs to go dyntick-idle more quickly, and to reduce the
+ * number of wakeups by a modest integer factor.
*
* Because it is not legal to invoke rcu_process_callbacks() with irqs
* disabled, we do one pass of force_quiescent_state(), then do a
* invoke_rcu_core() to cause rcu_process_callbacks() to be invoked
* later. The per-cpu rcu_dyntick_drain variable controls the sequencing.
+ *
+ * The caller must have disabled interrupts.
*/
-int rcu_needs_cpu(int cpu)
+static void rcu_prepare_for_idle(int cpu)
{
- int c = 0;
- int snap;
- int thatcpu;
-
- /* Check for being in the holdoff period. */
- if (per_cpu(rcu_dyntick_holdoff, cpu) == jiffies)
- return rcu_needs_cpu_quick_check(cpu);
-
- /* Don't bother unless we are the last non-dyntick-idle CPU. */
- for_each_online_cpu(thatcpu) {
- if (thatcpu == cpu)
- continue;
- snap = atomic_add_return(0, &per_cpu(rcu_dynticks,
- thatcpu).dynticks);
- smp_mb(); /* Order sampling of snap with end of grace period. */
- if ((snap & 0x1) != 0) {
- per_cpu(rcu_dyntick_drain, cpu) = 0;
- per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
- return rcu_needs_cpu_quick_check(cpu);
- }
+ unsigned long flags;
+
+ local_irq_save(flags);
+
+ /*
+ * If there are no callbacks on this CPU, enter dyntick-idle mode.
+ * Also reset state to avoid prejudicing later attempts.
+ */
+ if (!rcu_cpu_has_callbacks(cpu)) {
+ per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
+ per_cpu(rcu_dyntick_drain, cpu) = 0;
+ local_irq_restore(flags);
+ trace_rcu_prep_idle("No callbacks");
+ return;
+ }
+
+ /*
+ * If in holdoff mode, just return. We will presumably have
+ * refrained from disabling the scheduling-clock tick.
+ */
+ if (per_cpu(rcu_dyntick_holdoff, cpu) == jiffies) {
+ local_irq_restore(flags);
+ trace_rcu_prep_idle("In holdoff");
+ return;
}
/* Check and update the rcu_dyntick_drain sequencing. */
if (per_cpu(rcu_dyntick_drain, cpu) <= 0) {
/* First time through, initialize the counter. */
- per_cpu(rcu_dyntick_drain, cpu) = RCU_NEEDS_CPU_FLUSHES;
+ per_cpu(rcu_dyntick_drain, cpu) = RCU_IDLE_FLUSHES;
+ } else if (per_cpu(rcu_dyntick_drain, cpu) <= RCU_IDLE_OPT_FLUSHES &&
+ !rcu_pending(cpu)) {
+ /* Can we go dyntick-idle despite still having callbacks? */
+ trace_rcu_prep_idle("Dyntick with callbacks");
+ per_cpu(rcu_dyntick_drain, cpu) = 0;
+ per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
+ hrtimer_start(&per_cpu(rcu_idle_gp_timer, cpu),
+ rcu_idle_gp_wait, HRTIMER_MODE_REL);
+ return; /* Nothing more to do immediately. */
} else if (--per_cpu(rcu_dyntick_drain, cpu) <= 0) {
/* We have hit the limit, so time to give up. */
per_cpu(rcu_dyntick_holdoff, cpu) = jiffies;
- return rcu_needs_cpu_quick_check(cpu);
+ local_irq_restore(flags);
+ trace_rcu_prep_idle("Begin holdoff");
+ invoke_rcu_core(); /* Force the CPU out of dyntick-idle. */
+ return;
}
- /* Do one step pushing remaining RCU callbacks through. */
+ /*
+ * Do one step of pushing the remaining RCU callbacks through
+ * the RCU core state machine.
+ */
+#ifdef CONFIG_TREE_PREEMPT_RCU
+ if (per_cpu(rcu_preempt_data, cpu).nxtlist) {
+ local_irq_restore(flags);
+ rcu_preempt_qs(cpu);
+ force_quiescent_state(&rcu_preempt_state, 0);
+ local_irq_save(flags);
+ }
+#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
if (per_cpu(rcu_sched_data, cpu).nxtlist) {
+ local_irq_restore(flags);
rcu_sched_qs(cpu);
force_quiescent_state(&rcu_sched_state, 0);
- c = c || per_cpu(rcu_sched_data, cpu).nxtlist;
+ local_irq_save(flags);
}
if (per_cpu(rcu_bh_data, cpu).nxtlist) {
+ local_irq_restore(flags);
rcu_bh_qs(cpu);
force_quiescent_state(&rcu_bh_state, 0);
- c = c || per_cpu(rcu_bh_data, cpu).nxtlist;
+ local_irq_save(flags);
}
- /* If RCU callbacks are still pending, RCU still needs this CPU. */
- if (c)
+ /*
+ * If RCU callbacks are still pending, RCU still needs this CPU.
+ * So try forcing the callbacks through the grace period.
+ */
+ if (rcu_cpu_has_callbacks(cpu)) {
+ local_irq_restore(flags);
+ trace_rcu_prep_idle("More callbacks");
invoke_rcu_core();
- return c;
-}
-
-/*
- * Check to see if we need to continue a callback-flush operations to
- * allow the last CPU to enter dyntick-idle mode.
- */
-static void rcu_needs_cpu_flush(void)
-{
- int cpu = smp_processor_id();
- unsigned long flags;
-
- if (per_cpu(rcu_dyntick_drain, cpu) <= 0)
- return;
- local_irq_save(flags);
- (void)rcu_needs_cpu(cpu);
- local_irq_restore(flags);
+ } else {
+ local_irq_restore(flags);
+ trace_rcu_prep_idle("Callbacks drained");
+ }
}
#endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */