diff options
Diffstat (limited to 'kernel/rcu/tree_plugin.h')
| -rw-r--r-- | kernel/rcu/tree_plugin.h | 653 |
1 files changed, 153 insertions, 500 deletions
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index c9a48657512a..47d9b1c329ed 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -70,7 +70,7 @@ static bool __read_mostly rcu_nocb_poll; /* Offload kthread are to poll. */ static void __init rcu_bootup_announce_oddness(void) { if (IS_ENABLED(CONFIG_RCU_TRACE)) - pr_info("\tRCU debugfs-based tracing is enabled.\n"); + pr_info("\tRCU event tracing is enabled.\n"); if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) || (!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32)) pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n", @@ -90,8 +90,32 @@ static void __init rcu_bootup_announce_oddness(void) pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf); if (nr_cpu_ids != NR_CPUS) pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids); - if (IS_ENABLED(CONFIG_RCU_BOOST)) - pr_info("\tRCU kthread priority: %d.\n", kthread_prio); +#ifdef CONFIG_RCU_BOOST + pr_info("\tRCU priority boosting: priority %d delay %d ms.\n", kthread_prio, CONFIG_RCU_BOOST_DELAY); +#endif + if (blimit != DEFAULT_RCU_BLIMIT) + pr_info("\tBoot-time adjustment of callback invocation limit to %ld.\n", blimit); + if (qhimark != DEFAULT_RCU_QHIMARK) + pr_info("\tBoot-time adjustment of callback high-water mark to %ld.\n", qhimark); + if (qlowmark != DEFAULT_RCU_QLOMARK) + pr_info("\tBoot-time adjustment of callback low-water mark to %ld.\n", qlowmark); + if (jiffies_till_first_fqs != ULONG_MAX) + pr_info("\tBoot-time adjustment of first FQS scan delay to %ld jiffies.\n", jiffies_till_first_fqs); + if (jiffies_till_next_fqs != ULONG_MAX) + pr_info("\tBoot-time adjustment of subsequent FQS scan delay to %ld jiffies.\n", jiffies_till_next_fqs); + if (rcu_kick_kthreads) + pr_info("\tKick kthreads if too-long grace period.\n"); + if (IS_ENABLED(CONFIG_DEBUG_OBJECTS_RCU_HEAD)) + pr_info("\tRCU callback double-/use-after-free debug enabled.\n"); + if (gp_preinit_delay) + pr_info("\tRCU debug GP pre-init slowdown %d jiffies.\n", gp_preinit_delay); + if (gp_init_delay) + pr_info("\tRCU debug GP init slowdown %d jiffies.\n", gp_init_delay); + if (gp_cleanup_delay) + pr_info("\tRCU debug GP init slowdown %d jiffies.\n", gp_cleanup_delay); + if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG)) + pr_info("\tRCU debug extended QS entry/exit.\n"); + rcupdate_announce_bootup_oddness(); } #ifdef CONFIG_PREEMPT_RCU @@ -155,6 +179,8 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) (rnp->expmask & rdp->grpmask ? RCU_EXP_BLKD : 0); struct task_struct *t = current; + lockdep_assert_held(&rnp->lock); + /* * Decide where to queue the newly blocked task. In theory, * this could be an if-statement. In practice, when I tried @@ -263,6 +289,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) */ static void rcu_preempt_qs(void) { + RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_qs() invoked with preemption enabled!!!\n"); if (__this_cpu_read(rcu_data_p->cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_preempt"), __this_cpu_read(rcu_data_p->gpnum), @@ -286,12 +313,14 @@ static void rcu_preempt_qs(void) * * Caller must disable interrupts. */ -static void rcu_preempt_note_context_switch(void) +static void rcu_preempt_note_context_switch(bool preempt) { struct task_struct *t = current; struct rcu_data *rdp; struct rcu_node *rnp; + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_preempt_note_context_switch() invoked with interrupts enabled!!!\n"); + WARN_ON_ONCE(!preempt && t->rcu_read_lock_nesting > 0); if (t->rcu_read_lock_nesting > 0 && !t->rcu_read_unlock_special.b.blocked) { @@ -607,6 +636,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) */ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) { + RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n"); WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)); if (rcu_preempt_has_tasks(rnp)) rnp->gp_tasks = rnp->blkd_tasks.next; @@ -643,8 +673,37 @@ static void rcu_preempt_do_callbacks(void) #endif /* #ifdef CONFIG_RCU_BOOST */ -/* - * Queue a preemptible-RCU callback for invocation after a grace period. +/** + * call_rcu() - Queue an RCU callback for invocation after a grace period. + * @head: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all pre-existing RCU read-side + * critical sections have completed. However, the callback function + * might well execute concurrently with RCU read-side critical sections + * that started after call_rcu() was invoked. RCU read-side critical + * sections are delimited by rcu_read_lock() and rcu_read_unlock(), + * and may be nested. + * + * Note that all CPUs must agree that the grace period extended beyond + * all pre-existing RCU read-side critical section. On systems with more + * than one CPU, this means that when "func()" is invoked, each CPU is + * guaranteed to have executed a full memory barrier since the end of its + * last RCU read-side critical section whose beginning preceded the call + * to call_rcu(). It also means that each CPU executing an RCU read-side + * critical section that continues beyond the start of "func()" must have + * executed a memory barrier after the call_rcu() but before the beginning + * of that RCU read-side critical section. Note that these guarantees + * include CPUs that are offline, idle, or executing in user mode, as + * well as CPUs that are executing in the kernel. + * + * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the + * resulting RCU callback function "func()", then both CPU A and CPU B are + * guaranteed to execute a full memory barrier during the time interval + * between the call to call_rcu() and the invocation of "func()" -- even + * if CPU A and CPU B are the same CPU (but again only if the system has + * more than one CPU). */ void call_rcu(struct rcu_head *head, rcu_callback_t func) { @@ -663,8 +722,13 @@ EXPORT_SYMBOL_GPL(call_rcu); * synchronize_rcu() was waiting. RCU read-side critical sections are * delimited by rcu_read_lock() and rcu_read_unlock(), and may be nested. * - * See the description of synchronize_sched() for more detailed information - * on memory ordering guarantees. + * See the description of synchronize_sched() for more detailed + * information on memory-ordering guarantees. However, please note + * that -only- the memory-ordering guarantees apply. For example, + * synchronize_rcu() is -not- guaranteed to wait on things like code + * protected by preempt_disable(), instead, synchronize_rcu() is -only- + * guaranteed to wait on RCU read-side critical sections, that is, sections + * of code protected by rcu_read_lock(). */ void synchronize_rcu(void) { @@ -738,7 +802,7 @@ static void __init rcu_bootup_announce(void) * Because preemptible RCU does not exist, we never have to check for * CPUs being in quiescent states. */ -static void rcu_preempt_note_context_switch(void) +static void rcu_preempt_note_context_switch(bool preempt) { } @@ -835,33 +899,6 @@ void exit_rcu(void) #include "../locking/rtmutex_common.h" -#ifdef CONFIG_RCU_TRACE - -static void rcu_initiate_boost_trace(struct rcu_node *rnp) -{ - if (!rcu_preempt_has_tasks(rnp)) - rnp->n_balk_blkd_tasks++; - else if (rnp->exp_tasks == NULL && rnp->gp_tasks == NULL) - rnp->n_balk_exp_gp_tasks++; - else if (rnp->gp_tasks != NULL && rnp->boost_tasks != NULL) - rnp->n_balk_boost_tasks++; - else if (rnp->gp_tasks != NULL && rnp->qsmask != 0) - rnp->n_balk_notblocked++; - else if (rnp->gp_tasks != NULL && - ULONG_CMP_LT(jiffies, rnp->boost_time)) - rnp->n_balk_notyet++; - else - rnp->n_balk_nos++; -} - -#else /* #ifdef CONFIG_RCU_TRACE */ - -static void rcu_initiate_boost_trace(struct rcu_node *rnp) -{ -} - -#endif /* #else #ifdef CONFIG_RCU_TRACE */ - static void rcu_wake_cond(struct task_struct *t, int status) { /* @@ -992,8 +1029,8 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) { struct task_struct *t; + lockdep_assert_held(&rnp->lock); if (!rcu_preempt_blocked_readers_cgp(rnp) && rnp->exp_tasks == NULL) { - rnp->n_balk_exp_gp_tasks++; raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } @@ -1009,7 +1046,6 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) if (t) rcu_wake_cond(t, rnp->boost_kthread_status); } else { - rcu_initiate_boost_trace(rnp); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } } @@ -1260,8 +1296,7 @@ static void rcu_prepare_kthreads(int cpu) int rcu_needs_cpu(u64 basemono, u64 *nextevt) { *nextevt = KTIME_MAX; - return IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) - ? 0 : rcu_cpu_has_callbacks(NULL); + return rcu_cpu_has_callbacks(NULL); } /* @@ -1372,10 +1407,7 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt) struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); unsigned long dj; - if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)) { - *nextevt = KTIME_MAX; - return 0; - } + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_needs_cpu() invoked with irqs enabled!!!"); /* Snapshot to detect later posting of non-lazy callback. */ rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted; @@ -1424,8 +1456,8 @@ static void rcu_prepare_for_idle(void) struct rcu_state *rsp; int tne; - if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) || - rcu_is_nocb_cpu(smp_processor_id())) + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_prepare_for_idle() invoked with irqs enabled!!!"); + if (rcu_is_nocb_cpu(smp_processor_id())) return; /* Handle nohz enablement switches conservatively. */ @@ -1479,8 +1511,8 @@ static void rcu_prepare_for_idle(void) */ static void rcu_cleanup_after_idle(void) { - if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) || - rcu_is_nocb_cpu(smp_processor_id())) + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_cleanup_after_idle() invoked with irqs enabled!!!"); + if (rcu_is_nocb_cpu(smp_processor_id())) return; if (rcu_try_advance_all_cbs()) invoke_rcu_core(); @@ -1747,7 +1779,6 @@ static void rcu_init_one_nocb(struct rcu_node *rnp) init_swait_queue_head(&rnp->nocb_gp_wq[1]); } -#ifndef CONFIG_RCU_NOCB_CPU_ALL /* Is the specified CPU a no-CBs CPU? */ bool rcu_is_nocb_cpu(int cpu) { @@ -1755,25 +1786,59 @@ bool rcu_is_nocb_cpu(int cpu) return cpumask_test_cpu(cpu, rcu_nocb_mask); return false; } -#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ /* - * Kick the leader kthread for this NOCB group. + * Kick the leader kthread for this NOCB group. Caller holds lock. */ -static void wake_nocb_leader(struct rcu_data *rdp, bool force) +static void __wake_nocb_leader(struct rcu_data *rdp, bool force) { struct rcu_data *rdp_leader = rdp->nocb_leader; + lockdep_assert_held(&rdp->nocb_lock); if (!READ_ONCE(rdp_leader->nocb_kthread)) return; - if (READ_ONCE(rdp_leader->nocb_leader_sleep) || force) { + if (rdp_leader->nocb_leader_sleep || force) { /* Prior smp_mb__after_atomic() orders against prior enqueue. */ WRITE_ONCE(rdp_leader->nocb_leader_sleep, false); + smp_mb(); /* ->nocb_leader_sleep before swake_up(). */ swake_up(&rdp_leader->nocb_wq); } } /* + * Kick the leader kthread for this NOCB group, but caller has not + * acquired locks. + */ +static void wake_nocb_leader(struct rcu_data *rdp, bool force) +{ + unsigned long flags; + + del_timer(&rdp->nocb_timer); + raw_spin_lock_irqsave(&rdp->nocb_lock, flags); + __wake_nocb_leader(rdp, force); + raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); +} + +/* + * Arrange to wake the leader kthread for this NOCB group at some + * future time when it is safe to do so. + */ +static void wake_nocb_leader_defer(struct rcu_data *rdp, int waketype, + const char *reason) +{ + unsigned long flags; + bool needtimer; + + raw_spin_lock_irqsave(&rdp->nocb_lock, flags); + needtimer = rdp->nocb_defer_wakeup == RCU_NOCB_WAKE_NOT; + WRITE_ONCE(rdp->nocb_defer_wakeup, waketype); + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, reason); + raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); + if (needtimer) + mod_timer(&rdp->nocb_timer, jiffies + 1); +} + +/* * Does the specified CPU need an RCU callback for the specified flavor * of rcu_barrier()? */ @@ -1860,11 +1925,8 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeEmpty")); } else { - WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOGP_WAKE); - /* Store ->nocb_defer_wakeup before ->rcu_urgent_qs. */ - smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true); - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, - TPS("WakeEmptyIsDeferred")); + wake_nocb_leader_defer(rdp, RCU_NOCB_WAKE, + TPS("WakeEmptyIsDeferred")); } rdp->qlen_last_fqs_check = 0; } else if (len > rdp->qlen_last_fqs_check + qhimark) { @@ -1874,11 +1936,8 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeOvf")); } else { - WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOGP_WAKE_FORCE); - /* Store ->nocb_defer_wakeup before ->rcu_urgent_qs. */ - smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true); - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, - TPS("WakeOvfIsDeferred")); + wake_nocb_leader_defer(rdp, RCU_NOCB_WAKE, + TPS("WakeOvfIsDeferred")); } rdp->qlen_last_fqs_check = LONG_MAX / 2; } else { @@ -2023,6 +2082,7 @@ wait_again: * nocb_gp_head, where they await a grace period. */ gotcbs = false; + smp_mb(); /* wakeup before ->nocb_head reads. */ for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) { rdp->nocb_gp_head = READ_ONCE(rdp->nocb_head); if (!rdp->nocb_gp_head) @@ -2194,16 +2254,39 @@ static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp) } /* Do a deferred wakeup of rcu_nocb_kthread(). */ -static void do_nocb_deferred_wakeup(struct rcu_data *rdp) +static void do_nocb_deferred_wakeup_common(struct rcu_data *rdp) { + unsigned long flags; int ndw; - if (!rcu_nocb_need_deferred_wakeup(rdp)) + raw_spin_lock_irqsave(&rdp->nocb_lock, flags); + if (!rcu_nocb_need_deferred_wakeup(rdp)) { + raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); return; + } ndw = READ_ONCE(rdp->nocb_defer_wakeup); - WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOGP_WAKE_NOT); - wake_nocb_leader(rdp, ndw == RCU_NOGP_WAKE_FORCE); + WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT); + __wake_nocb_leader(rdp, ndw == RCU_NOCB_WAKE_FORCE); trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWake")); + raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); +} + +/* Do a deferred wakeup of rcu_nocb_kthread() from a timer handler. */ +static void do_nocb_deferred_wakeup_timer(unsigned long x) +{ + do_nocb_deferred_wakeup_common((struct rcu_data *)x); +} + +/* + * Do a deferred wakeup of rcu_nocb_kthread() from fastpath. + * This means we do an inexact common-case check. Note that if + * we miss, ->nocb_timer will eventually clean things up. + */ +static void do_nocb_deferred_wakeup(struct rcu_data *rdp) +{ + del_timer(&rdp->nocb_timer); + if (rcu_nocb_need_deferred_wakeup(rdp)) + do_nocb_deferred_wakeup_common(rdp); } void __init rcu_init_nohz(void) @@ -2212,10 +2295,6 @@ void __init rcu_init_nohz(void) bool need_rcu_nocb_mask = true; struct rcu_state *rsp; -#ifdef CONFIG_RCU_NOCB_CPU_NONE - need_rcu_nocb_mask = false; -#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */ - #if defined(CONFIG_NO_HZ_FULL) if (tick_nohz_full_running && cpumask_weight(tick_nohz_full_mask)) need_rcu_nocb_mask = true; @@ -2231,14 +2310,6 @@ void __init rcu_init_nohz(void) if (!have_rcu_nocb_mask) return; -#ifdef CONFIG_RCU_NOCB_CPU_ZERO - pr_info("\tOffload RCU callbacks from CPU 0\n"); - cpumask_set_cpu(0, rcu_nocb_mask); -#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */ -#ifdef CONFIG_RCU_NOCB_CPU_ALL - pr_info("\tOffload RCU callbacks from all CPUs\n"); - cpumask_copy(rcu_nocb_mask, cpu_possible_mask); -#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */ #if defined(CONFIG_NO_HZ_FULL) if (tick_nohz_full_running) cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask); @@ -2267,6 +2338,9 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) rdp->nocb_tail = &rdp->nocb_head; init_swait_queue_head(&rdp->nocb_wq); rdp->nocb_follower_tail = &rdp->nocb_follower_head; + raw_spin_lock_init(&rdp->nocb_lock); + setup_timer(&rdp->nocb_timer, do_nocb_deferred_wakeup_timer, + (unsigned long)rdp); } /* @@ -2491,421 +2565,6 @@ static void __maybe_unused rcu_kick_nohz_cpu(int cpu) #endif /* #ifdef CONFIG_NO_HZ_FULL */ } - -#ifdef CONFIG_NO_HZ_FULL_SYSIDLE - -static int full_sysidle_state; /* Current system-idle state. */ -#define RCU_SYSIDLE_NOT 0 /* Some CPU is not idle. */ -#define RCU_SYSIDLE_SHORT 1 /* All CPUs idle for brief period. */ -#define RCU_SYSIDLE_LONG 2 /* All CPUs idle for long enough. */ -#define RCU_SYSIDLE_FULL 3 /* All CPUs idle, ready for sysidle. */ -#define RCU_SYSIDLE_FULL_NOTED 4 /* Actually entered sysidle state. */ - -/* - * Invoked to note exit from irq or task transition to idle. Note that - * usermode execution does -not- count as idle here! After all, we want - * to detect full-system idle states, not RCU quiescent states and grace - * periods. The caller must have disabled interrupts. - */ -static void rcu_sysidle_enter(int irq) -{ - unsigned long j; - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - - /* If there are no nohz_full= CPUs, no need to track this. */ - if (!tick_nohz_full_enabled()) - return; - - /* Adjust nesting, check for fully idle. */ - if (irq) { - rdtp->dynticks_idle_nesting--; - WARN_ON_ONCE(rdtp->dynticks_idle_nesting < 0); - if (rdtp->dynticks_idle_nesting != 0) - return; /* Still not fully idle. */ - } else { - if ((rdtp->dynticks_idle_nesting & DYNTICK_TASK_NEST_MASK) == - DYNTICK_TASK_NEST_VALUE) { - rdtp->dynticks_idle_nesting = 0; - } else { - rdtp->dynticks_idle_nesting -= DYNTICK_TASK_NEST_VALUE; - WARN_ON_ONCE(rdtp->dynticks_idle_nesting < 0); - return; /* Still not fully idle. */ - } - } - - /* Record start of fully idle period. */ - j = jiffies; - WRITE_ONCE(rdtp->dynticks_idle_jiffies, j); - smp_mb__before_atomic(); - atomic_inc(&rdtp->dynticks_idle); - smp_mb__after_atomic(); - WARN_ON_ONCE(atomic_read(&rdtp->dynticks_idle) & 0x1); -} - -/* - * Unconditionally force exit from full system-idle state. This is - * invoked when a normal CPU exits idle, but must be called separately - * for the timekeeping CPU (tick_do_timer_cpu). The reason for this - * is that the timekeeping CPU is permitted to take scheduling-clock - * interrupts while the system is in system-idle state, and of course - * rcu_sysidle_exit() has no way of distinguishing a scheduling-clock - * interrupt from any other type of interrupt. - */ -void rcu_sysidle_force_exit(void) -{ - int oldstate = READ_ONCE(full_sysidle_state); - int newoldstate; - - /* - * Each pass through the following loop attempts to exit full - * system-idle state. If contention proves to be a problem, - * a trylock-based contention tree could be used here. - */ - while (oldstate > RCU_SYSIDLE_SHORT) { - newoldstate = cmpxchg(&full_sysidle_state, - oldstate, RCU_SYSIDLE_NOT); - if (oldstate == newoldstate && - oldstate == RCU_SYSIDLE_FULL_NOTED) { - rcu_kick_nohz_cpu(tick_do_timer_cpu); - return; /* We cleared it, done! */ - } - oldstate = newoldstate; - } - smp_mb(); /* Order initial oldstate fetch vs. later non-idle work. */ -} - -/* - * Invoked to note entry to irq or task transition from idle. Note that - * usermode execution does -not- count as idle here! The caller must - * have disabled interrupts. - */ -static void rcu_sysidle_exit(int irq) -{ - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - - /* If there are no nohz_full= CPUs, no need to track this. */ - if (!tick_nohz_full_enabled()) - return; - - /* Adjust nesting, check for already non-idle. */ - if (irq) { - rdtp->dynticks_idle_nesting++; - WARN_ON_ONCE(rdtp->dynticks_idle_nesting <= 0); - if (rdtp->dynticks_idle_nesting != 1) - return; /* Already non-idle. */ - } else { - /* - * Allow for irq misnesting. Yes, it really is possible - * to enter an irq handler then never leave it, and maybe - * also vice versa. Handle both possibilities. - */ - if (rdtp->dynticks_idle_nesting & DYNTICK_TASK_NEST_MASK) { - rdtp->dynticks_idle_nesting += DYNTICK_TASK_NEST_VALUE; - WARN_ON_ONCE(rdtp->dynticks_idle_nesting <= 0); - return; /* Already non-idle. */ - } else { - rdtp->dynticks_idle_nesting = DYNTICK_TASK_EXIT_IDLE; - } - } - - /* Record end of idle period. */ - smp_mb__before_atomic(); - atomic_inc(&rdtp->dynticks_idle); - smp_mb__after_atomic(); - WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks_idle) & 0x1)); - - /* - * If we are the timekeeping CPU, we are permitted to be non-idle - * during a system-idle state. This must be the case, because - * the timekeeping CPU has to take scheduling-clock interrupts - * during the time that the system is transitioning to full - * system-idle state. This means that the timekeeping CPU must - * invoke rcu_sysidle_force_exit() directly if it does anything - * more than take a scheduling-clock interrupt. - */ - if (smp_processor_id() == tick_do_timer_cpu) - return; - - /* Update system-idle state: We are clearly no longer fully idle! */ - rcu_sysidle_force_exit(); -} - -/* - * Check to see if the current CPU is idle. Note that usermode execution - * does not count as idle. The caller must have disabled interrupts, - * and must be running on tick_do_timer_cpu. - */ -static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, - unsigned long *maxj) -{ - int cur; - unsigned long j; - struct rcu_dynticks *rdtp = rdp->dynticks; - - /* If there are no nohz_full= CPUs, don't check system-wide idleness. */ - if (!tick_nohz_full_enabled()) - return; - - /* - * If some other CPU has already reported non-idle, if this is - * not the flavor of RCU that tracks sysidle state, or if this - * is an offline or the timekeeping CPU, nothing to do. - */ - if (!*isidle || rdp->rsp != rcu_state_p || - cpu_is_offline(rdp->cpu) || rdp->cpu == tick_do_timer_cpu) - return; - /* Verify affinity of current kthread. */ - WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu); - - /* Pick up current idle and NMI-nesting counter and check. */ - cur = atomic_read(&rdtp->dynticks_idle); - if (cur & 0x1) { - *isidle = false; /* We are not idle! */ - return; - } - smp_mb(); /* Read counters before timestamps. */ - - /* Pick up timestamps. */ - j = READ_ONCE(rdtp->dynticks_idle_jiffies); - /* If this CPU entered idle more recently, update maxj timestamp. */ - if (ULONG_CMP_LT(*maxj, j)) - *maxj = j; -} - -/* - * Is this the flavor of RCU that is handling full-system idle? - */ -static bool is_sysidle_rcu_state(struct rcu_state *rsp) -{ - return rsp == rcu_state_p; -} - -/* - * Return a delay in jiffies based on the number of CPUs, rcu_node - * leaf fanout, and jiffies tick rate. The idea is to allow larger - * systems more time to transition to full-idle state in order to - * avoid the cache thrashing that otherwise occur on the state variable. - * Really small systems (less than a couple of tens of CPUs) should - * instead use a single global atomically incremented counter, and later - * versions of this will automatically reconfigure themselves accordingly. - */ -static unsigned long rcu_sysidle_delay(void) -{ - if (nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL) - return 0; - return DIV_ROUND_UP(nr_cpu_ids * HZ, rcu_fanout_leaf * 1000); -} - -/* - * Advance the full-system-idle state. This is invoked when all of - * the non-timekeeping CPUs are idle. - */ -static void rcu_sysidle(unsigned long j) -{ - /* Check the current state. */ - switch (READ_ONCE(full_sysidle_state)) { - case RCU_SYSIDLE_NOT: - - /* First time all are idle, so note a short idle period. */ - WRITE_ONCE(full_sysidle_state, RCU_SYSIDLE_SHORT); - break; - - case RCU_SYSIDLE_SHORT: - - /* - * Idle for a bit, time to advance to next state? - * cmpxchg failure means race with non-idle, let them win. - */ - if (ULONG_CMP_GE(jiffies, j + rcu_sysidle_delay())) - (void)cmpxchg(&full_sysidle_state, - RCU_SYSIDLE_SHORT, RCU_SYSIDLE_LONG); - break; - - case RCU_SYSIDLE_LONG: - - /* - * Do an additional check pass before advancing to full. - * cmpxchg failure means race with non-idle, let them win. - */ - if (ULONG_CMP_GE(jiffies, j + rcu_sysidle_delay())) - (void)cmpxchg(&full_sysidle_state, - RCU_SYSIDLE_LONG, RCU_SYSIDLE_FULL); - break; - - default: - break; - } -} - -/* - * Found a non-idle non-timekeeping CPU, so kick the system-idle state - * back to the beginning. - */ -static void rcu_sysidle_cancel(void) -{ - smp_mb(); - if (full_sysidle_state > RCU_SYSIDLE_SHORT) - WRITE_ONCE(full_sysidle_state, RCU_SYSIDLE_NOT); -} - -/* - * Update the sysidle state based on the results of a force-quiescent-state - * scan of the CPUs' dyntick-idle state. - */ -static void rcu_sysidle_report(struct rcu_state *rsp, int isidle, - unsigned long maxj, bool gpkt) -{ - if (rsp != rcu_state_p) - return; /* Wrong flavor, ignore. */ - if (gpkt && nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL) - return; /* Running state machine from timekeeping CPU. */ - if (isidle) - rcu_sysidle(maxj); /* More idle! */ - else - rcu_sysidle_cancel(); /* Idle is over. */ -} - -/* - * Wrapper for rcu_sysidle_report() when called from the grace-period - * kthread's context. - */ -static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, - unsigned long maxj) -{ - /* If there are no nohz_full= CPUs, no need to track this. */ - if (!tick_nohz_full_enabled()) - return; - - rcu_sysidle_report(rsp, isidle, maxj, true); -} - -/* Callback and function for forcing an RCU grace period. */ -struct rcu_sysidle_head { - struct rcu_head rh; - int inuse; -}; - -static void rcu_sysidle_cb(struct rcu_head *rhp) -{ - struct rcu_sysidle_head *rshp; - - /* - * The following memory barrier is needed to replace the - * memory barriers that would normally be in the memory - * allocator. - */ - smp_mb(); /* grace period precedes setting inuse. */ - - rshp = container_of(rhp, struct rcu_sysidle_head, rh); - WRITE_ONCE(rshp->inuse, 0); -} - -/* - * Check to see if the system is fully idle, other than the timekeeping CPU. - * The caller must have disabled interrupts. This is not intended to be - * called unless tick_nohz_full_enabled(). - */ -bool rcu_sys_is_idle(void) -{ - static struct rcu_sysidle_head rsh; - int rss = READ_ONCE(full_sysidle_state); - - if (WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu)) - return false; - - /* Handle small-system case by doing a full scan of CPUs. */ - if (nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL) { - int oldrss = rss - 1; - - /* - * One pass to advance to each state up to _FULL. - * Give up if any pass fails to advance the state. - */ - while (rss < RCU_SYSIDLE_FULL && oldrss < rss) { - int cpu; - bool isidle = true; - unsigned long maxj = jiffies - ULONG_MAX / 4; - struct rcu_data *rdp; - - /* Scan all the CPUs looking for nonidle CPUs. */ - for_each_possible_cpu(cpu) { - rdp = per_cpu_ptr(rcu_state_p->rda, cpu); - rcu_sysidle_check_cpu(rdp, &isidle, &maxj); - if (!isidle) - break; - } - rcu_sysidle_report(rcu_state_p, isidle, maxj, false); - oldrss = rss; - rss = READ_ONCE(full_sysidle_state); - } - } - - /* If this is the first observation of an idle period, record it. */ - if (rss == RCU_SYSIDLE_FULL) { - rss = cmpxchg(&full_sysidle_state, - RCU_SYSIDLE_FULL, RCU_SYSIDLE_FULL_NOTED); - return rss == RCU_SYSIDLE_FULL; - } - - smp_mb(); /* ensure rss load happens before later caller actions. */ - - /* If already fully idle, tell the caller (in case of races). */ - if (rss == RCU_SYSIDLE_FULL_NOTED) - return true; - - /* - * If we aren't there yet, and a grace period is not in flight, - * initiate a grace period. Either way, tell the caller that - * we are not there yet. We use an xchg() rather than an assignment - * to make up for the memory barriers that would otherwise be - * provided by the memory allocator. - */ - if (nr_cpu_ids > CONFIG_NO_HZ_FULL_SYSIDLE_SMALL && - !rcu_gp_in_progress(rcu_state_p) && - !rsh.inuse && xchg(&rsh.inuse, 1) == 0) - call_rcu(&rsh.rh, rcu_sysidle_cb); - return false; -} - -/* - * Initialize dynticks sysidle state for CPUs coming online. - */ -static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp) -{ - rdtp->dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE; -} - -#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ - -static void rcu_sysidle_enter(int irq) -{ -} - -static void rcu_sysidle_exit(int irq) -{ -} - -static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, - unsigned long *maxj) -{ -} - -static bool is_sysidle_rcu_state(struct rcu_state *rsp) -{ - return false; -} - -static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, - unsigned long maxj) -{ -} - -static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp) -{ -} - -#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ - /* * Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the * grace-period kthread will do force_quiescent_state() processing? @@ -2936,13 +2595,7 @@ static void rcu_bind_gp_kthread(void) if (!tick_nohz_full_enabled()) return; -#ifdef CONFIG_NO_HZ_FULL_SYSIDLE - cpu = tick_do_timer_cpu; - if (cpu >= 0 && cpu < nr_cpu_ids) - set_cpus_allowed_ptr(current, cpumask_of(cpu)); -#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ housekeeping_affine(current); -#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ } /* Record the current task on dyntick-idle entry. */ |