diff options
Diffstat (limited to 'kernel/rcu/tree_plugin.h')
| -rw-r--r-- | kernel/rcu/tree_plugin.h | 1634 |
1 files changed, 184 insertions, 1450 deletions
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 352223664ebd..41021080ad25 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -13,10 +13,29 @@ #include "../locking/rtmutex_common.h" -#ifdef CONFIG_RCU_NOCB_CPU -static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */ -static bool __read_mostly rcu_nocb_poll; /* Offload kthread are to poll. */ -#endif /* #ifdef CONFIG_RCU_NOCB_CPU */ +static bool rcu_rdp_is_offloaded(struct rcu_data *rdp) +{ + /* + * In order to read the offloaded state of an rdp in a safe + * and stable way and prevent from its value to be changed + * under us, we must either hold the barrier mutex, the cpu + * hotplug lock (read or write) or the nocb lock. Local + * non-preemptible reads are also safe. NOCB kthreads and + * timers have their own means of synchronization against the + * offloaded state updaters. + */ + RCU_LOCKDEP_WARN( + !(lockdep_is_held(&rcu_state.barrier_mutex) || + (IS_ENABLED(CONFIG_HOTPLUG_CPU) && lockdep_is_cpus_held()) || + rcu_lockdep_is_held_nocb(rdp) || + (rdp == this_cpu_ptr(&rcu_data) && + !(IS_ENABLED(CONFIG_PREEMPT_COUNT) && preemptible())) || + rcu_current_is_nocb_kthread(rdp)), + "Unsafe read of RCU_NOCB offloaded state" + ); + + return rcu_segcblist_is_offloaded(&rdp->cblist); +} /* * Check the RCU kernel configuration parameters and print informative @@ -32,10 +51,10 @@ static void __init rcu_bootup_announce_oddness(void) RCU_FANOUT); if (rcu_fanout_exact) pr_info("\tHierarchical RCU autobalancing is disabled.\n"); - if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ)) - pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n"); if (IS_ENABLED(CONFIG_PROVE_RCU)) pr_info("\tRCU lockdep checking is enabled.\n"); + if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) + pr_info("\tRCU strict (and thus non-scalable) grace periods are enabled.\n"); if (RCU_NUM_LVLS >= 4) pr_info("\tFour(or more)-level hierarchy is enabled.\n"); if (RCU_FANOUT_LEAF != 16) @@ -67,13 +86,13 @@ static void __init rcu_bootup_announce_oddness(void) 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"); + pr_info("\tRCU callback double-/use-after-free debug is 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); + pr_info("\tRCU debug GP cleanup slowdown %d jiffies.\n", gp_cleanup_delay); if (!use_softirq) pr_info("\tRCU_SOFTIRQ processing moved to rcuc kthreads.\n"); if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG)) @@ -238,11 +257,13 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) * GP should not be able to end until we report, so there should be * no need to check for a subsequent expedited GP. (Though we are * still in a quiescent state in any case.) + * + * Interrupts are disabled, so ->cpu_no_qs.b.exp cannot change. */ - if (blkd_state & RCU_EXP_BLKD && rdp->exp_deferred_qs) + if (blkd_state & RCU_EXP_BLKD && rdp->cpu_no_qs.b.exp) rcu_report_exp_rdp(rdp); else - WARN_ON_ONCE(rdp->exp_deferred_qs); + WARN_ON_ONCE(rdp->cpu_no_qs.b.exp); } /* @@ -256,12 +277,16 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) * current task, there might be any number of other tasks blocked while * in an RCU read-side critical section. * + * Unlike non-preemptible-RCU, quiescent state reports for expedited + * grace periods are handled separately via deferred quiescent states + * and context switch events. + * * Callers to this function must disable preemption. */ static void rcu_qs(void) { RCU_LOCKDEP_WARN(preemptible(), "rcu_qs() invoked with preemption enabled!!!\n"); - if (__this_cpu_read(rcu_data.cpu_no_qs.s)) { + if (__this_cpu_read(rcu_data.cpu_no_qs.b.norm)) { trace_rcu_grace_period(TPS("rcu_preempt"), __this_cpu_read(rcu_data.gp_seq), TPS("cpuqs")); @@ -292,7 +317,7 @@ void rcu_note_context_switch(bool preempt) trace_rcu_utilization(TPS("Start context switch")); lockdep_assert_irqs_disabled(); - WARN_ON_ONCE(!preempt && rcu_preempt_depth() > 0); + WARN_ONCE(!preempt && rcu_preempt_depth() > 0, "Voluntary context switch within RCU read-side critical section!"); if (rcu_preempt_depth() > 0 && !t->rcu_read_unlock_special.b.blocked) { @@ -307,7 +332,7 @@ void rcu_note_context_switch(bool preempt) * then queue the task as required based on the states * of any ongoing and expedited grace periods. */ - WARN_ON_ONCE((rdp->grpmask & rcu_rnp_online_cpus(rnp)) == 0); + WARN_ON_ONCE(!rcu_rdp_cpu_online(rdp)); WARN_ON_ONCE(!list_empty(&t->rcu_node_entry)); trace_rcu_preempt_task(rcu_state.name, t->pid, @@ -329,7 +354,7 @@ void rcu_note_context_switch(bool preempt) * means that we continue to block the current grace period. */ rcu_qs(); - if (rdp->exp_deferred_qs) + if (rdp->cpu_no_qs.b.exp) rcu_report_exp_rdp(rdp); rcu_tasks_qs(current, preempt); trace_rcu_utilization(TPS("End context switch")); @@ -351,17 +376,20 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) static void rcu_preempt_read_enter(void) { - current->rcu_read_lock_nesting++; + WRITE_ONCE(current->rcu_read_lock_nesting, READ_ONCE(current->rcu_read_lock_nesting) + 1); } static int rcu_preempt_read_exit(void) { - return --current->rcu_read_lock_nesting; + int ret = READ_ONCE(current->rcu_read_lock_nesting) - 1; + + WRITE_ONCE(current->rcu_read_lock_nesting, ret); + return ret; } static void rcu_preempt_depth_set(int val) { - current->rcu_read_lock_nesting = val; + WRITE_ONCE(current->rcu_read_lock_nesting, val); } /* @@ -374,6 +402,8 @@ void __rcu_read_lock(void) rcu_preempt_read_enter(); if (IS_ENABLED(CONFIG_PROVE_LOCKING)) WARN_ON_ONCE(rcu_preempt_depth() > RCU_NEST_PMAX); + if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) && rcu_state.gp_kthread) + WRITE_ONCE(current->rcu_read_unlock_special.b.need_qs, true); barrier(); /* critical section after entry code. */ } EXPORT_SYMBOL_GPL(__rcu_read_lock); @@ -389,8 +419,9 @@ void __rcu_read_unlock(void) { struct task_struct *t = current; + barrier(); // critical section before exit code. if (rcu_preempt_read_exit() == 0) { - barrier(); /* critical section before exit code. */ + barrier(); // critical-section exit before .s check. if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s))) rcu_read_unlock_special(t); } @@ -431,7 +462,7 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp) * be quite short, for example, in the case of the call from * rcu_read_unlock_special(). */ -static void +static notrace void rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) { bool empty_exp; @@ -450,13 +481,20 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) */ special = t->rcu_read_unlock_special; rdp = this_cpu_ptr(&rcu_data); - if (!special.s && !rdp->exp_deferred_qs) { + if (!special.s && !rdp->cpu_no_qs.b.exp) { local_irq_restore(flags); return; } t->rcu_read_unlock_special.s = 0; - if (special.b.need_qs) - rcu_qs(); + if (special.b.need_qs) { + if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) { + rdp->cpu_no_qs.b.norm = false; + rcu_report_qs_rdp(rdp); + udelay(rcu_unlock_delay); + } else { + rcu_qs(); + } + } /* * Respond to a request by an expedited grace period for a @@ -464,7 +502,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) * tasks are handled when removing the task from the * blocked-tasks list below. */ - if (rdp->exp_deferred_qs) + if (rdp->cpu_no_qs.b.exp) rcu_report_exp_rdp(rdp); /* Clean up if blocked during RCU read-side critical section. */ @@ -496,7 +534,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) WRITE_ONCE(rnp->exp_tasks, np); if (IS_ENABLED(CONFIG_RCU_BOOST)) { /* Snapshot ->boost_mtx ownership w/rnp->lock held. */ - drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t; + drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx.rtmutex) == t; if (&t->rcu_node_entry == rnp->boost_tasks) WRITE_ONCE(rnp->boost_tasks, np); } @@ -521,16 +559,16 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } - /* Unboost if we were boosted. */ - if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex) - rt_mutex_futex_unlock(&rnp->boost_mtx); - /* * If this was the last task on the expedited lists, * then we need to report up the rcu_node hierarchy. */ if (!empty_exp && empty_exp_now) rcu_report_exp_rnp(rnp, true); + + /* Unboost if we were boosted. */ + if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex) + rt_mutex_futex_unlock(&rnp->boost_mtx.rtmutex); } else { local_irq_restore(flags); } @@ -545,9 +583,9 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) * is disabled. This function cannot be expected to understand these * nuances, so the caller must handle them. */ -static bool rcu_preempt_need_deferred_qs(struct task_struct *t) +static notrace bool rcu_preempt_need_deferred_qs(struct task_struct *t) { - return (__this_cpu_read(rcu_data.exp_deferred_qs) || + return (__this_cpu_read(rcu_data.cpu_no_qs.b.exp) || READ_ONCE(t->rcu_read_unlock_special.s)) && rcu_preempt_depth() == 0; } @@ -559,7 +597,7 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t) * evaluate safety in terms of interrupt, softirq, and preemption * disabling. */ -static void rcu_preempt_deferred_qs(struct task_struct *t) +notrace void rcu_preempt_deferred_qs(struct task_struct *t) { unsigned long flags; @@ -588,9 +626,9 @@ static void rcu_preempt_deferred_qs_handler(struct irq_work *iwp) static void rcu_read_unlock_special(struct task_struct *t) { unsigned long flags; + bool irqs_were_disabled; bool preempt_bh_were_disabled = !!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)); - bool irqs_were_disabled; /* NMI handlers cannot block and cannot safely manipulate state. */ if (in_nmi()) @@ -599,30 +637,40 @@ static void rcu_read_unlock_special(struct task_struct *t) local_irq_save(flags); irqs_were_disabled = irqs_disabled_flags(flags); if (preempt_bh_were_disabled || irqs_were_disabled) { - bool exp; + bool expboost; // Expedited GP in flight or possible boosting. struct rcu_data *rdp = this_cpu_ptr(&rcu_data); struct rcu_node *rnp = rdp->mynode; - exp = (t->rcu_blocked_node && - READ_ONCE(t->rcu_blocked_node->exp_tasks)) || - (rdp->grpmask & READ_ONCE(rnp->expmask)); + expboost = (t->rcu_blocked_node && READ_ONCE(t->rcu_blocked_node->exp_tasks)) || + (rdp->grpmask & READ_ONCE(rnp->expmask)) || + (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) && + ((rdp->grpmask & READ_ONCE(rnp->qsmask)) || t->rcu_blocked_node)) || + (IS_ENABLED(CONFIG_RCU_BOOST) && irqs_were_disabled && + t->rcu_blocked_node); // Need to defer quiescent state until everything is enabled. - if (use_softirq && (in_irq() || (exp && !irqs_were_disabled))) { + if (use_softirq && (in_hardirq() || (expboost && !irqs_were_disabled))) { // Using softirq, safe to awaken, and either the - // wakeup is free or there is an expedited GP. + // wakeup is free or there is either an expedited + // GP in flight or a potential need to deboost. raise_softirq_irqoff(RCU_SOFTIRQ); } else { // Enabling BH or preempt does reschedule, so... - // Also if no expediting, slow is OK. - // Plus nohz_full CPUs eventually get tick enabled. + // Also if no expediting and no possible deboosting, + // slow is OK. Plus nohz_full CPUs eventually get + // tick enabled. set_tsk_need_resched(current); set_preempt_need_resched(); if (IS_ENABLED(CONFIG_IRQ_WORK) && irqs_were_disabled && - !rdp->defer_qs_iw_pending && exp) { + expboost && !rdp->defer_qs_iw_pending && cpu_online(rdp->cpu)) { // Get scheduler to re-evaluate and call hooks. // If !IRQ_WORK, FQS scan will eventually IPI. - init_irq_work(&rdp->defer_qs_iw, - rcu_preempt_deferred_qs_handler); + if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) && + IS_ENABLED(CONFIG_PREEMPT_RT)) + rdp->defer_qs_iw = IRQ_WORK_INIT_HARD( + rcu_preempt_deferred_qs_handler); + else + init_irq_work(&rdp->defer_qs_iw, + rcu_preempt_deferred_qs_handler); rdp->defer_qs_iw_pending = true; irq_work_queue_on(&rdp->defer_qs_iw, rdp->cpu); } @@ -672,9 +720,7 @@ static void rcu_flavor_sched_clock_irq(int user) { struct task_struct *t = current; - if (user || rcu_is_cpu_rrupt_from_idle()) { - rcu_note_voluntary_context_switch(current); - } + lockdep_assert_irqs_disabled(); if (rcu_preempt_depth() > 0 || (preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK))) { /* No QS, force context switch if deferred. */ @@ -734,7 +780,6 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck) int cpu; int i; struct list_head *lhp; - bool onl; struct rcu_data *rdp; struct rcu_node *rnp1; @@ -758,9 +803,8 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck) pr_cont("\n"); for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) { rdp = per_cpu_ptr(&rcu_data, cpu); - onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp)); pr_info("\t%d: %c online: %ld(%d) offline: %ld(%d)\n", - cpu, ".o"[onl], + cpu, ".o"[rcu_rdp_cpu_online(rdp)], (long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags, (long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags); } @@ -769,6 +813,24 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck) #else /* #ifdef CONFIG_PREEMPT_RCU */ /* + * If strict grace periods are enabled, and if the calling + * __rcu_read_unlock() marks the beginning of a quiescent state, immediately + * report that quiescent state and, if requested, spin for a bit. + */ +void rcu_read_unlock_strict(void) +{ + struct rcu_data *rdp; + + if (irqs_disabled() || preempt_count() || !rcu_state.gp_kthread) + return; + rdp = this_cpu_ptr(&rcu_data); + rdp->cpu_no_qs.b.norm = false; + rcu_report_qs_rdp(rdp); + udelay(rcu_unlock_delay); +} +EXPORT_SYMBOL_GPL(rcu_read_unlock_strict); + +/* * Tell them what RCU they are running. */ static void __init rcu_bootup_announce(void) @@ -791,10 +853,8 @@ static void rcu_qs(void) trace_rcu_grace_period(TPS("rcu_sched"), __this_cpu_read(rcu_data.gp_seq), TPS("cpuqs")); __this_cpu_write(rcu_data.cpu_no_qs.b.norm, false); - if (!__this_cpu_read(rcu_data.cpu_no_qs.b.exp)) - return; - __this_cpu_write(rcu_data.cpu_no_qs.b.exp, false); - rcu_report_exp_rdp(this_cpu_ptr(&rcu_data)); + if (__this_cpu_read(rcu_data.cpu_no_qs.b.exp)) + rcu_report_exp_rdp(this_cpu_ptr(&rcu_data)); } /* @@ -810,7 +870,7 @@ void rcu_all_qs(void) if (!raw_cpu_read(rcu_data.rcu_urgent_qs)) return; - preempt_disable(); + preempt_disable(); // For CONFIG_PREEMPT_COUNT=y kernels /* Load rcu_urgent_qs before other flags. */ if (!smp_load_acquire(this_cpu_ptr(&rcu_data.rcu_urgent_qs))) { preempt_enable(); @@ -840,8 +900,8 @@ void rcu_note_context_switch(bool preempt) this_cpu_write(rcu_data.rcu_urgent_qs, false); if (unlikely(raw_cpu_read(rcu_data.rcu_need_heavy_qs))) rcu_momentary_dyntick_idle(); - rcu_tasks_qs(current, preempt); out: + rcu_tasks_qs(current, preempt); trace_rcu_utilization(TPS("End context switch")); } EXPORT_SYMBOL_GPL(rcu_note_context_switch); @@ -867,11 +927,25 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp) * Because there is no preemptible RCU, there can be no deferred quiescent * states. */ -static bool rcu_preempt_need_deferred_qs(struct task_struct *t) +static notrace bool rcu_preempt_need_deferred_qs(struct task_struct *t) { return false; } -static void rcu_preempt_deferred_qs(struct task_struct *t) { } + +// Except that we do need to respond to a request by an expedited +// grace period for a quiescent state from this CPU. Note that in +// non-preemptible kernels, there can be no context switches within RCU +// read-side critical sections, which in turn means that the leaf rcu_node +// structure's blocked-tasks list is always empty. is therefore no need to +// actually check it. Instead, a quiescent state from this CPU suffices, +// and this function is only called from such a quiescent state. +notrace void rcu_preempt_deferred_qs(struct task_struct *t) +{ + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); + + if (READ_ONCE(rdp->cpu_no_qs.b.exp)) + rcu_report_exp_rdp(rdp); +} /* * Because there is no preemptible RCU, there can be no readers blocked, @@ -902,7 +976,6 @@ static void rcu_flavor_sched_clock_irq(int user) * neither access nor modify, at least not while the * corresponding CPU is online. */ - rcu_qs(); } } @@ -931,12 +1004,34 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck) */ static void rcu_cpu_kthread_setup(unsigned int cpu) { + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); #ifdef CONFIG_RCU_BOOST struct sched_param sp; sp.sched_priority = kthread_prio; sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); #endif /* #ifdef CONFIG_RCU_BOOST */ + + WRITE_ONCE(rdp->rcuc_activity, jiffies); +} + +static bool rcu_is_callbacks_nocb_kthread(struct rcu_data *rdp) +{ +#ifdef CONFIG_RCU_NOCB_CPU + return rdp->nocb_cb_kthread == current; +#else + return false; +#endif +} + +/* + * Is the current CPU running the RCU-callbacks kthread? + * Caller must have preemption disabled. + */ +static bool rcu_is_callbacks_kthread(struct rcu_data *rdp) +{ + return rdp->rcu_cpu_kthread_task == current || + rcu_is_callbacks_nocb_kthread(rdp); } #ifdef CONFIG_RCU_BOOST @@ -998,11 +1093,12 @@ static int rcu_boost(struct rcu_node *rnp) * section. */ t = container_of(tb, struct task_struct, rcu_node_entry); - rt_mutex_init_proxy_locked(&rnp->boost_mtx, t); + rt_mutex_init_proxy_locked(&rnp->boost_mtx.rtmutex, t); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); /* Lock only for side effect: boosts task t's priority. */ rt_mutex_lock(&rnp->boost_mtx); rt_mutex_unlock(&rnp->boost_mtx); /* Then keep lockdep happy. */ + rnp->n_boosts++; return READ_ONCE(rnp->exp_tasks) != NULL || READ_ONCE(rnp->boost_tasks) != NULL; @@ -1033,7 +1129,7 @@ static int rcu_boost_kthread(void *arg) if (spincnt > 10) { WRITE_ONCE(rnp->boost_kthread_status, RCU_KTHREAD_YIELDING); trace_rcu_utilization(TPS("End boost kthread@rcu_yield")); - schedule_timeout_interruptible(2); + schedule_timeout_idle(2); trace_rcu_utilization(TPS("Start boost kthread@rcu_yield")); spincnt = 0; } @@ -1057,7 +1153,8 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) __releases(rnp->lock) { raw_lockdep_assert_held_rcu_node(rnp); - if (!rcu_preempt_blocked_readers_cgp(rnp) && rnp->exp_tasks == NULL) { + if (!rnp->boost_kthread_task || + (!rcu_preempt_blocked_readers_cgp(rnp) && !rnp->exp_tasks)) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } @@ -1065,7 +1162,8 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) (rnp->gp_tasks != NULL && rnp->boost_tasks == NULL && rnp->qsmask == 0 && - (!time_after(rnp->boost_time, jiffies) || rcu_state.cbovld))) { + (!time_after(rnp->boost_time, jiffies) || rcu_state.cbovld || + IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)))) { if (rnp->exp_tasks == NULL) WRITE_ONCE(rnp->boost_tasks, rnp->gp_tasks); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); @@ -1076,15 +1174,6 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) } } -/* - * Is the current CPU running the RCU-callbacks kthread? - * Caller must have preemption disabled. - */ -static bool rcu_is_callbacks_kthread(void) -{ - return __this_cpu_read(rcu_data.rcu_cpu_kthread_task) == current; -} - #define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000) /* @@ -1098,30 +1187,22 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp) /* * Create an RCU-boost kthread for the specified node if one does not * already exist. We only create this kthread for preemptible RCU. - * Returns zero if all is well, a negated errno otherwise. */ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp) { - int rnp_index = rnp - rcu_get_root(); unsigned long flags; + int rnp_index = rnp - rcu_get_root(); struct sched_param sp; struct task_struct *t; - if (!IS_ENABLED(CONFIG_PREEMPT_RCU)) - return; - - if (!rcu_scheduler_fully_active || rcu_rnp_online_cpus(rnp) == 0) - return; - - rcu_state.boost = 1; - - if (rnp->boost_kthread_task != NULL) - return; + mutex_lock(&rnp->boost_kthread_mutex); + if (rnp->boost_kthread_task || !rcu_scheduler_fully_active) + goto out; t = kthread_create(rcu_boost_kthread, (void *)rnp, "rcub/%d", rnp_index); if (WARN_ON_ONCE(IS_ERR(t))) - return; + goto out; raw_spin_lock_irqsave_rcu_node(rnp, flags); rnp->boost_kthread_task = t; @@ -1129,6 +1210,9 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp) sp.sched_priority = kthread_prio; sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */ + + out: + mutex_unlock(&rnp->boost_kthread_mutex); } /* @@ -1139,11 +1223,13 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp) * We don't include outgoingcpu in the affinity set, use -1 if there is * no outgoing CPU. If there are no CPUs left in the affinity set, * this function allows the kthread to execute on any CPU. + * + * Any future concurrent calls are serialized via ->boost_kthread_mutex. */ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) { struct task_struct *t = rnp->boost_kthread_task; - unsigned long mask = rcu_rnp_online_cpus(rnp); + unsigned long mask; cpumask_var_t cm; int cpu; @@ -1151,37 +1237,23 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) return; if (!zalloc_cpumask_var(&cm, GFP_KERNEL)) return; + mutex_lock(&rnp->boost_kthread_mutex); + mask = rcu_rnp_online_cpus(rnp); for_each_leaf_node_possible_cpu(rnp, cpu) if ((mask & leaf_node_cpu_bit(rnp, cpu)) && cpu != outgoingcpu) cpumask_set_cpu(cpu, cm); - if (cpumask_weight(cm) == 0) - cpumask_setall(cm); + cpumask_and(cm, cm, housekeeping_cpumask(HK_TYPE_RCU)); + if (cpumask_empty(cm)) { + cpumask_copy(cm, housekeeping_cpumask(HK_TYPE_RCU)); + if (outgoingcpu >= 0) + cpumask_clear_cpu(outgoingcpu, cm); + } set_cpus_allowed_ptr(t, cm); + mutex_unlock(&rnp->boost_kthread_mutex); free_cpumask_var(cm); } -/* - * Spawn boost kthreads -- called as soon as the scheduler is running. - */ -static void __init rcu_spawn_boost_kthreads(void) -{ - struct rcu_node *rnp; - - rcu_for_each_leaf_node(rnp) - rcu_spawn_one_boost_kthread(rnp); -} - -static void rcu_prepare_kthreads(int cpu) -{ - struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); - struct rcu_node *rnp = rdp->mynode; - - /* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */ - if (rcu_scheduler_fully_active) - rcu_spawn_one_boost_kthread(rnp); -} - #else /* #ifdef CONFIG_RCU_BOOST */ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) @@ -1190,1324 +1262,20 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } -static bool rcu_is_callbacks_kthread(void) -{ - return false; -} - static void rcu_preempt_boost_start_gp(struct rcu_node *rnp) { } -static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) -{ -} - -static void __init rcu_spawn_boost_kthreads(void) +static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp) { } -static void rcu_prepare_kthreads(int cpu) +static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) { } #endif /* #else #ifdef CONFIG_RCU_BOOST */ -#if !defined(CONFIG_RCU_FAST_NO_HZ) - -/* - * Check to see if any future non-offloaded 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. - * - * Because we not have RCU_FAST_NO_HZ, just check whether or not this - * CPU has RCU callbacks queued. - */ -int rcu_needs_cpu(u64 basemono, u64 *nextevt) -{ - *nextevt = KTIME_MAX; - return !rcu_segcblist_empty(&this_cpu_ptr(&rcu_data)->cblist) && - !rcu_segcblist_is_offloaded(&this_cpu_ptr(&rcu_data)->cblist); -} - -/* - * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up - * after it. - */ -static void rcu_cleanup_after_idle(void) -{ -} - -/* - * Do the idle-entry grace-period work, which, because CONFIG_RCU_FAST_NO_HZ=n, - * is nothing. - */ -static void rcu_prepare_for_idle(void) -{ -} - -#else /* #if !defined(CONFIG_RCU_FAST_NO_HZ) */ - -/* - * 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. - * - * The following preprocessor symbol controls this: - * - * 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 value below works 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_GP_DELAY 4 /* Roughly one grace period. */ - -static int rcu_idle_gp_delay = RCU_IDLE_GP_DELAY; -module_param(rcu_idle_gp_delay, int, 0644); - -/* - * Try to advance callbacks on the current CPU, but only if it has been - * awhile since the last time we did so. Afterwards, if there are any - * callbacks ready for immediate invocation, return true. - */ -static bool __maybe_unused rcu_try_advance_all_cbs(void) -{ - bool cbs_ready = false; - struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - struct rcu_node *rnp; - - /* Exit early if we advanced recently. */ - if (jiffies == rdp->last_advance_all) - return false; - rdp->last_advance_all = jiffies; - - rnp = rdp->mynode; - - /* - * Don't bother checking unless a grace period has - * completed since we last checked and there are - * callbacks not yet ready to invoke. - */ - if ((rcu_seq_completed_gp(rdp->gp_seq, - rcu_seq_current(&rnp->gp_seq)) || - unlikely(READ_ONCE(rdp->gpwrap))) && - rcu_segcblist_pend_cbs(&rdp->cblist)) - note_gp_changes(rdp); - - if (rcu_segcblist_ready_cbs(&rdp->cblist)) - cbs_ready = true; - return cbs_ready; -} - -/* - * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready - * to invoke. If the CPU has callbacks, try to advance them. Tell the - * caller about what to set the timeout. - * - * The caller must have disabled interrupts. - */ -int rcu_needs_cpu(u64 basemono, u64 *nextevt) -{ - struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - unsigned long dj; - - lockdep_assert_irqs_disabled(); - - /* If no non-offloaded callbacks, RCU doesn't need the CPU. */ - if (rcu_segcblist_empty(&rdp->cblist) || - rcu_segcblist_is_offloaded(&this_cpu_ptr(&rcu_data)->cblist)) { - *nextevt = KTIME_MAX; - return 0; - } - - /* Attempt to advance callbacks. */ - if (rcu_try_advance_all_cbs()) { - /* Some ready to invoke, so initiate later invocation. */ - invoke_rcu_core(); - return 1; - } - rdp->last_accelerate = jiffies; - - /* Request timer and round. */ - dj = round_up(rcu_idle_gp_delay + jiffies, rcu_idle_gp_delay) - jiffies; - - *nextevt = basemono + dj * TICK_NSEC; - return 0; -} - -/* - * Prepare a CPU for idle from an RCU perspective. The first major task is to - * sense whether nohz mode has been enabled or disabled via sysfs. The second - * major task is to accelerate (that is, assign grace-period numbers to) any - * recently arrived callbacks. - * - * The caller must have disabled interrupts. - */ -static void rcu_prepare_for_idle(void) -{ - bool needwake; - struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - struct rcu_node *rnp; - int tne; - - lockdep_assert_irqs_disabled(); - if (rcu_segcblist_is_offloaded(&rdp->cblist)) - return; - - /* Handle nohz enablement switches conservatively. */ - tne = READ_ONCE(tick_nohz_active); - if (tne != rdp->tick_nohz_enabled_snap) { - if (!rcu_segcblist_empty(&rdp->cblist)) - invoke_rcu_core(); /* force nohz to see update. */ - rdp->tick_nohz_enabled_snap = tne; - return; - } - if (!tne) - return; - - /* - * If we have not yet accelerated this jiffy, accelerate all - * callbacks on this CPU. - */ - if (rdp->last_accelerate == jiffies) - return; - rdp->last_accelerate = jiffies; - if (rcu_segcblist_pend_cbs(&rdp->cblist)) { - rnp = rdp->mynode; - raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ - needwake = rcu_accelerate_cbs(rnp, rdp); - raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ - if (needwake) - rcu_gp_kthread_wake(); - } -} - -/* - * Clean up for exit from idle. Attempt to advance callbacks based on - * any grace periods that elapsed while the CPU was idle, and if any - * callbacks are now ready to invoke, initiate invocation. - */ -static void rcu_cleanup_after_idle(void) -{ - struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - - lockdep_assert_irqs_disabled(); - if (rcu_segcblist_is_offloaded(&rdp->cblist)) - return; - if (rcu_try_advance_all_cbs()) - invoke_rcu_core(); -} - -#endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */ - -#ifdef CONFIG_RCU_NOCB_CPU - -/* - * Offload callback processing from the boot-time-specified set of CPUs - * specified by rcu_nocb_mask. For the CPUs in the set, there are kthreads - * created that pull the callbacks from the corresponding CPU, wait for - * a grace period to elapse, and invoke the callbacks. These kthreads - * are organized into GP kthreads, which manage incoming callbacks, wait for - * grace periods, and awaken CB kthreads, and the CB kthreads, which only - * invoke callbacks. Each GP kthread invokes its own CBs. The no-CBs CPUs - * do a wake_up() on their GP kthread when they insert a callback into any - * empty list, unless the rcu_nocb_poll boot parameter has been specified, - * in which case each kthread actively polls its CPU. (Which isn't so great - * for energy efficiency, but which does reduce RCU's overhead on that CPU.) - * - * This is intended to be used in conjunction with Frederic Weisbecker's - * adaptive-idle work, which would seriously reduce OS jitter on CPUs - * running CPU-bound user-mode computations. - * - * Offloading of callbacks can also be used as an energy-efficiency - * measure because CPUs with no RCU callbacks queued are more aggressive - * about entering dyntick-idle mode. - */ - - -/* - * Parse the boot-time rcu_nocb_mask CPU list from the kernel parameters. - * The string after the "rcu_nocbs=" is either "all" for all CPUs, or a - * comma-separated list of CPUs and/or CPU ranges. If an invalid list is - * given, a warning is emitted and all CPUs are offloaded. - */ -static int __init rcu_nocb_setup(char *str) -{ - alloc_bootmem_cpumask_var(&rcu_nocb_mask); - if (!strcasecmp(str, "all")) - cpumask_setall(rcu_nocb_mask); - else - if (cpulist_parse(str, rcu_nocb_mask)) { - pr_warn("rcu_nocbs= bad CPU range, all CPUs set\n"); - cpumask_setall(rcu_nocb_mask); - } - return 1; -} -__setup("rcu_nocbs=", rcu_nocb_setup); - -static int __init parse_rcu_nocb_poll(char *arg) -{ - rcu_nocb_poll = true; - return 0; -} -early_param("rcu_nocb_poll", parse_rcu_nocb_poll); - -/* - * Don't bother bypassing ->cblist if the call_rcu() rate is low. - * After all, the main point of bypassing is to avoid lock contention - * on ->nocb_lock, which only can happen at high call_rcu() rates. - */ -int nocb_nobypass_lim_per_jiffy = 16 * 1000 / HZ; -module_param(nocb_nobypass_lim_per_jiffy, int, 0); - -/* - * Acquire the specified rcu_data structure's ->nocb_bypass_lock. If the - * lock isn't immediately available, increment ->nocb_lock_contended to - * flag the contention. - */ -static void rcu_nocb_bypass_lock(struct rcu_data *rdp) - __acquires(&rdp->nocb_bypass_lock) -{ - lockdep_assert_irqs_disabled(); - if (raw_spin_trylock(&rdp->nocb_bypass_lock)) - return; - atomic_inc(&rdp->nocb_lock_contended); - WARN_ON_ONCE(smp_processor_id() != rdp->cpu); - smp_mb__after_atomic(); /* atomic_inc() before lock. */ - raw_spin_lock(&rdp->nocb_bypass_lock); - smp_mb__before_atomic(); /* atomic_dec() after lock. */ - atomic_dec(&rdp->nocb_lock_contended); -} - -/* - * Spinwait until the specified rcu_data structure's ->nocb_lock is - * not contended. Please note that this is extremely special-purpose, - * relying on the fact that at most two kthreads and one CPU contend for - * this lock, and also that the two kthreads are guaranteed to have frequent - * grace-period-duration time intervals between successive acquisitions - * of the lock. This allows us to use an extremely simple throttling - * mechanism, and further to apply it only to the CPU doing floods of - * call_rcu() invocations. Don't try this at home! - */ -static void rcu_nocb_wait_contended(struct rcu_data *rdp) -{ - WARN_ON_ONCE(smp_processor_id() != rdp->cpu); - while (WARN_ON_ONCE(atomic_read(&rdp->nocb_lock_contended))) - cpu_relax(); -} - -/* - * Conditionally acquire the specified rcu_data structure's - * ->nocb_bypass_lock. - */ -static bool rcu_nocb_bypass_trylock(struct rcu_data *rdp) -{ - lockdep_assert_irqs_disabled(); - return raw_spin_trylock(&rdp->nocb_bypass_lock); -} - -/* - * Release the specified rcu_data structure's ->nocb_bypass_lock. - */ -static void rcu_nocb_bypass_unlock(struct rcu_data *rdp) - __releases(&rdp->nocb_bypass_lock) -{ - lockdep_assert_irqs_disabled(); - raw_spin_unlock(&rdp->nocb_bypass_lock); -} - -/* - * Acquire the specified rcu_data structure's ->nocb_lock, but only - * if it corresponds to a no-CBs CPU. - */ -static void rcu_nocb_lock(struct rcu_data *rdp) -{ - lockdep_assert_irqs_disabled(); - if (!rcu_segcblist_is_offloaded(&rdp->cblist)) - return; - raw_spin_lock(&rdp->nocb_lock); -} - -/* - * Release the specified rcu_data structure's ->nocb_lock, but only - * if it corresponds to a no-CBs CPU. - */ -static void rcu_nocb_unlock(struct rcu_data *rdp) -{ - if (rcu_segcblist_is_offloaded(&rdp->cblist)) { - lockdep_assert_irqs_disabled(); - raw_spin_unlock(&rdp->nocb_lock); - } -} - -/* - * Release the specified rcu_data structure's ->nocb_lock and restore - * interrupts, but only if it corresponds to a no-CBs CPU. - */ -static void rcu_nocb_unlock_irqrestore(struct rcu_data *rdp, - unsigned long flags) -{ - if (rcu_segcblist_is_offloaded(&rdp->cblist)) { - lockdep_assert_irqs_disabled(); - raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); - } else { - local_irq_restore(flags); - } -} - -/* Lockdep check that ->cblist may be safely accessed. */ -static void rcu_lockdep_assert_cblist_protected(struct rcu_data *rdp) -{ - lockdep_assert_irqs_disabled(); - if (rcu_segcblist_is_offloaded(&rdp->cblist)) - lockdep_assert_held(&rdp->nocb_lock); -} - -/* - * Wake up any no-CBs CPUs' kthreads that were waiting on the just-ended - * grace period. - */ -static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq) -{ - swake_up_all(sq); -} - -static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp) -{ - return &rnp->nocb_gp_wq[rcu_seq_ctr(rnp->gp_seq) & 0x1]; -} - -static void rcu_init_one_nocb(struct rcu_node *rnp) -{ - init_swait_queue_head(&rnp->nocb_gp_wq[0]); - init_swait_queue_head(&rnp->nocb_gp_wq[1]); -} - -/* Is the specified CPU a no-CBs CPU? */ -bool rcu_is_nocb_cpu(int cpu) -{ - if (cpumask_available(rcu_nocb_mask)) - return cpumask_test_cpu(cpu, rcu_nocb_mask); - return false; -} - -/* - * Kick the GP kthread for this NOCB group. Caller holds ->nocb_lock - * and this function releases it. - */ -static void wake_nocb_gp(struct rcu_data *rdp, bool force, - unsigned long flags) - __releases(rdp->nocb_lock) -{ - bool needwake = false; - struct rcu_data *rdp_gp = rdp->nocb_gp_rdp; - - lockdep_assert_held(&rdp->nocb_lock); - if (!READ_ONCE(rdp_gp->nocb_gp_kthread)) { - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, - TPS("AlreadyAwake")); - rcu_nocb_unlock_irqrestore(rdp, flags); - return; - } - del_timer(&rdp->nocb_timer); - rcu_nocb_unlock_irqrestore(rdp, flags); - raw_spin_lock_irqsave(&rdp_gp->nocb_gp_lock, flags); - if (force || READ_ONCE(rdp_gp->nocb_gp_sleep)) { - WRITE_ONCE(rdp_gp->nocb_gp_sleep, false); - needwake = true; - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("DoWake")); - } - raw_spin_unlock_irqrestore(&rdp_gp->nocb_gp_lock, flags); - if (needwake) - wake_up_process(rdp_gp->nocb_gp_kthread); -} - -/* - * Arrange to wake the GP kthread for this NOCB group at some future - * time when it is safe to do so. - */ -static void wake_nocb_gp_defer(struct rcu_data *rdp, int waketype, - const char *reason) -{ - if (rdp->nocb_defer_wakeup == RCU_NOCB_WAKE_NOT) - mod_timer(&rdp->nocb_timer, jiffies + 1); - if (rdp->nocb_defer_wakeup < waketype) - WRITE_ONCE(rdp->nocb_defer_wakeup, waketype); - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, reason); -} - -/* - * Flush the ->nocb_bypass queue into ->cblist, enqueuing rhp if non-NULL. - * However, if there is a callback to be enqueued and if ->nocb_bypass - * proves to be initially empty, just return false because the no-CB GP - * kthread may need to be awakened in this case. - * - * Note that this function always returns true if rhp is NULL. - */ -static bool rcu_nocb_do_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp, - unsigned long j) -{ - struct rcu_cblist rcl; - - WARN_ON_ONCE(!rcu_segcblist_is_offloaded(&rdp->cblist)); - rcu_lockdep_assert_cblist_protected(rdp); - lockdep_assert_held(&rdp->nocb_bypass_lock); - if (rhp && !rcu_cblist_n_cbs(&rdp->nocb_bypass)) { - raw_spin_unlock(&rdp->nocb_bypass_lock); - return false; - } - /* Note: ->cblist.len already accounts for ->nocb_bypass contents. */ - if (rhp) - rcu_segcblist_inc_len(&rdp->cblist); /* Must precede enqueue. */ - rcu_cblist_flush_enqueue(&rcl, &rdp->nocb_bypass, rhp); - rcu_segcblist_insert_pend_cbs(&rdp->cblist, &rcl); - WRITE_ONCE(rdp->nocb_bypass_first, j); - rcu_nocb_bypass_unlock(rdp); - return true; -} - -/* - * Flush the ->nocb_bypass queue into ->cblist, enqueuing rhp if non-NULL. - * However, if there is a callback to be enqueued and if ->nocb_bypass - * proves to be initially empty, just return false because the no-CB GP - * kthread may need to be awakened in this case. - * - * Note that this function always returns true if rhp is NULL. - */ -static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp, - unsigned long j) -{ - if (!rcu_segcblist_is_offloaded(&rdp->cblist)) - return true; - rcu_lockdep_assert_cblist_protected(rdp); - rcu_nocb_bypass_lock(rdp); - return rcu_nocb_do_flush_bypass(rdp, rhp, j); -} - -/* - * If the ->nocb_bypass_lock is immediately available, flush the - * ->nocb_bypass queue into ->cblist. - */ -static void rcu_nocb_try_flush_bypass(struct rcu_data *rdp, unsigned long j) -{ - rcu_lockdep_assert_cblist_protected(rdp); - if (!rcu_segcblist_is_offloaded(&rdp->cblist) || - !rcu_nocb_bypass_trylock(rdp)) - return; - WARN_ON_ONCE(!rcu_nocb_do_flush_bypass(rdp, NULL, j)); -} - -/* - * See whether it is appropriate to use the ->nocb_bypass list in order - * to control contention on ->nocb_lock. A limited number of direct - * enqueues are permitted into ->cblist per jiffy. If ->nocb_bypass - * is non-empty, further callbacks must be placed into ->nocb_bypass, - * otherwise rcu_barrier() breaks. Use rcu_nocb_flush_bypass() to switch - * back to direct use of ->cblist. However, ->nocb_bypass should not be - * used if ->cblist is empty, because otherwise callbacks can be stranded - * on ->nocb_bypass because we cannot count on the current CPU ever again - * invoking call_rcu(). The general rule is that if ->nocb_bypass is - * non-empty, the corresponding no-CBs grace-period kthread must not be - * in an indefinite sleep state. - * - * Finally, it is not permitted to use the bypass during early boot, - * as doing so would confuse the auto-initialization code. Besides - * which, there is no point in worrying about lock contention while - * there is only one CPU in operation. - */ -static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp, - bool *was_alldone, unsigned long flags) -{ - unsigned long c; - unsigned long cur_gp_seq; - unsigned long j = jiffies; - long ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass); - - if (!rcu_segcblist_is_offloaded(&rdp->cblist)) { - *was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist); - return false; /* Not offloaded, no bypassing. */ - } - lockdep_assert_irqs_disabled(); - - // Don't use ->nocb_bypass during early boot. - if (rcu_scheduler_active != RCU_SCHEDULER_RUNNING) { - rcu_nocb_lock(rdp); - WARN_ON_ONCE(rcu_cblist_n_cbs(&rdp->nocb_bypass)); - *was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist); - return false; - } - - // If we have advanced to a new jiffy, reset counts to allow - // moving back from ->nocb_bypass to ->cblist. - if (j == rdp->nocb_nobypass_last) { - c = rdp->nocb_nobypass_count + 1; - } else { - WRITE_ONCE(rdp->nocb_nobypass_last, j); - c = rdp->nocb_nobypass_count - nocb_nobypass_lim_per_jiffy; - if (ULONG_CMP_LT(rdp->nocb_nobypass_count, - nocb_nobypass_lim_per_jiffy)) - c = 0; - else if (c > nocb_nobypass_lim_per_jiffy) - c = nocb_nobypass_lim_per_jiffy; - } - WRITE_ONCE(rdp->nocb_nobypass_count, c); - - // If there hasn't yet been all that many ->cblist enqueues - // this jiffy, tell the caller to enqueue onto ->cblist. But flush - // ->nocb_bypass first. - if (rdp->nocb_nobypass_count < nocb_nobypass_lim_per_jiffy) { - rcu_nocb_lock(rdp); - *was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist); - if (*was_alldone) - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, - TPS("FirstQ")); - WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, j)); - WARN_ON_ONCE(rcu_cblist_n_cbs(&rdp->nocb_bypass)); - return false; // Caller must enqueue the callback. - } - - // If ->nocb_bypass has been used too long or is too full, - // flush ->nocb_bypass to ->cblist. - if ((ncbs && j != READ_ONCE(rdp->nocb_bypass_first)) || - ncbs >= qhimark) { - rcu_nocb_lock(rdp); - if (!rcu_nocb_flush_bypass(rdp, rhp, j)) { - *was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist); - if (*was_alldone) - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, - TPS("FirstQ")); - WARN_ON_ONCE(rcu_cblist_n_cbs(&rdp->nocb_bypass)); - return false; // Caller must enqueue the callback. - } - if (j != rdp->nocb_gp_adv_time && - rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq) && - rcu_seq_done(&rdp->mynode->gp_seq, cur_gp_seq)) { - rcu_advance_cbs_nowake(rdp->mynode, rdp); - rdp->nocb_gp_adv_time = j; - } - rcu_nocb_unlock_irqrestore(rdp, flags); - return true; // Callback already enqueued. - } - - // We need to use the bypass. - rcu_nocb_wait_contended(rdp); - rcu_nocb_bypass_lock(rdp); - ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass); - rcu_segcblist_inc_len(&rdp->cblist); /* Must precede enqueue. */ - rcu_cblist_enqueue(&rdp->nocb_bypass, rhp); - if (!ncbs) { - WRITE_ONCE(rdp->nocb_bypass_first, j); - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("FirstBQ")); - } - rcu_nocb_bypass_unlock(rdp); - smp_mb(); /* Order enqueue before wake. */ - if (ncbs) { - local_irq_restore(flags); - } else { - // No-CBs GP kthread might be indefinitely asleep, if so, wake. - rcu_nocb_lock(rdp); // Rare during call_rcu() flood. - if (!rcu_segcblist_pend_cbs(&rdp->cblist)) { - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, - TPS("FirstBQwake")); - __call_rcu_nocb_wake(rdp, true, flags); - } else { - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, - TPS("FirstBQnoWake")); - rcu_nocb_unlock_irqrestore(rdp, flags); - } - } - return true; // Callback already enqueued. -} - -/* - * Awaken the no-CBs grace-period kthead if needed, either due to it - * legitimately being asleep or due to overload conditions. - * - * If warranted, also wake up the kthread servicing this CPUs queues. - */ -static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone, - unsigned long flags) - __releases(rdp->nocb_lock) -{ - unsigned long cur_gp_seq; - unsigned long j; - long len; - struct task_struct *t; - - // If we are being polled or there is no kthread, just leave. - t = READ_ONCE(rdp->nocb_gp_kthread); - if (rcu_nocb_poll || !t) { - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, - TPS("WakeNotPoll")); - rcu_nocb_unlock_irqrestore(rdp, flags); - return; - } - // Need to actually to a wakeup. - len = rcu_segcblist_n_cbs(&rdp->cblist); - if (was_alldone) { - rdp->qlen_last_fqs_check = len; - if (!irqs_disabled_flags(flags)) { - /* ... if queue was empty ... */ - wake_nocb_gp(rdp, false, flags); - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, - TPS("WakeEmpty")); - } else { - wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE, - TPS("WakeEmptyIsDeferred")); - rcu_nocb_unlock_irqrestore(rdp, flags); - } - } else if (len > rdp->qlen_last_fqs_check + qhimark) { - /* ... or if many callbacks queued. */ - rdp->qlen_last_fqs_check = len; - j = jiffies; - if (j != rdp->nocb_gp_adv_time && - rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq) && - rcu_seq_done(&rdp->mynode->gp_seq, cur_gp_seq)) { - rcu_advance_cbs_nowake(rdp->mynode, rdp); - rdp->nocb_gp_adv_time = j; - } - smp_mb(); /* Enqueue before timer_pending(). */ - if ((rdp->nocb_cb_sleep || - !rcu_segcblist_ready_cbs(&rdp->cblist)) && - !timer_pending(&rdp->nocb_bypass_timer)) - wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE_FORCE, - TPS("WakeOvfIsDeferred")); - rcu_nocb_unlock_irqrestore(rdp, flags); - } else { - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNot")); - rcu_nocb_unlock_irqrestore(rdp, flags); - } - return; -} - -/* Wake up the no-CBs GP kthread to flush ->nocb_bypass. */ -static void do_nocb_bypass_wakeup_timer(struct timer_list *t) -{ - unsigned long flags; - struct rcu_data *rdp = from_timer(rdp, t, nocb_bypass_timer); - - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("Timer")); - rcu_nocb_lock_irqsave(rdp, flags); - smp_mb__after_spinlock(); /* Timer expire before wakeup. */ - __call_rcu_nocb_wake(rdp, true, flags); -} - -/* - * No-CBs GP kthreads come here to wait for additional callbacks to show up - * or for grace periods to end. - */ -static void nocb_gp_wait(struct rcu_data *my_rdp) -{ - bool bypass = false; - long bypass_ncbs; - int __maybe_unused cpu = my_rdp->cpu; - unsigned long cur_gp_seq; - unsigned long flags; - bool gotcbs = false; - unsigned long j = jiffies; - bool needwait_gp = false; // This prevents actual uninitialized use. - bool needwake; - bool needwake_gp; - struct rcu_data *rdp; - struct rcu_node *rnp; - unsigned long wait_gp_seq = 0; // Suppress "use uninitialized" warning. - bool wasempty = false; - - /* - * Each pass through the following loop checks for CBs and for the - * nearest grace period (if any) to wait for next. The CB kthreads - * and the global grace-period kthread are awakened if needed. - */ - for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_cb_rdp) { - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("Check")); - rcu_nocb_lock_irqsave(rdp, flags); - bypass_ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass); - if (bypass_ncbs && - (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + 1) || - bypass_ncbs > 2 * qhimark)) { - // Bypass full or old, so flush it. - (void)rcu_nocb_try_flush_bypass(rdp, j); - bypass_ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass); - } else if (!bypass_ncbs && rcu_segcblist_empty(&rdp->cblist)) { - rcu_nocb_unlock_irqrestore(rdp, flags); - continue; /* No callbacks here, try next. */ - } - if (bypass_ncbs) { - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, - TPS("Bypass")); - bypass = true; - } - rnp = rdp->mynode; - if (bypass) { // Avoid race with first bypass CB. - WRITE_ONCE(my_rdp->nocb_defer_wakeup, - RCU_NOCB_WAKE_NOT); - del_timer(&my_rdp->nocb_timer); - } - // Advance callbacks if helpful and low contention. - needwake_gp = false; - if (!rcu_segcblist_restempty(&rdp->cblist, - RCU_NEXT_READY_TAIL) || - (rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq) && - rcu_seq_done(&rnp->gp_seq, cur_gp_seq))) { - raw_spin_lock_rcu_node(rnp); /* irqs disabled. */ - needwake_gp = rcu_advance_cbs(rnp, rdp); - wasempty = rcu_segcblist_restempty(&rdp->cblist, - RCU_NEXT_READY_TAIL); - raw_spin_unlock_rcu_node(rnp); /* irqs disabled. */ - } - // Need to wait on some grace period? - WARN_ON_ONCE(wasempty && - !rcu_segcblist_restempty(&rdp->cblist, - RCU_NEXT_READY_TAIL)); - if (rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq)) { - if (!needwait_gp || - ULONG_CMP_LT(cur_gp_seq, wait_gp_seq)) - wait_gp_seq = cur_gp_seq; - needwait_gp = true; - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, - TPS("NeedWaitGP")); - } - if (rcu_segcblist_ready_cbs(&rdp->cblist)) { - needwake = rdp->nocb_cb_sleep; - WRITE_ONCE(rdp->nocb_cb_sleep, false); - smp_mb(); /* CB invocation -after- GP end. */ - } else { - needwake = false; - } - rcu_nocb_unlock_irqrestore(rdp, flags); - if (needwake) { - swake_up_one(&rdp->nocb_cb_wq); - gotcbs = true; - } - if (needwake_gp) - rcu_gp_kthread_wake(); - } - - my_rdp->nocb_gp_bypass = bypass; - my_rdp->nocb_gp_gp = needwait_gp; - my_rdp->nocb_gp_seq = needwait_gp ? wait_gp_seq : 0; - if (bypass && !rcu_nocb_poll) { - // At least one child with non-empty ->nocb_bypass, so set - // timer in order to avoid stranding its callbacks. - raw_spin_lock_irqsave(&my_rdp->nocb_gp_lock, flags); - mod_timer(&my_rdp->nocb_bypass_timer, j + 2); - raw_spin_unlock_irqrestore(&my_rdp->nocb_gp_lock, flags); - } - if (rcu_nocb_poll) { - /* Polling, so trace if first poll in the series. */ - if (gotcbs) - trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Poll")); - schedule_timeout_interruptible(1); - } else if (!needwait_gp) { - /* Wait for callbacks to appear. */ - trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Sleep")); - swait_event_interruptible_exclusive(my_rdp->nocb_gp_wq, - !READ_ONCE(my_rdp->nocb_gp_sleep)); - trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("EndSleep")); - } else { - rnp = my_rdp->mynode; - trace_rcu_this_gp(rnp, my_rdp, wait_gp_seq, TPS("StartWait")); - swait_event_interruptible_exclusive( - rnp->nocb_gp_wq[rcu_seq_ctr(wait_gp_seq) & 0x1], - rcu_seq_done(&rnp->gp_seq, wait_gp_seq) || - !READ_ONCE(my_rdp->nocb_gp_sleep)); - trace_rcu_this_gp(rnp, my_rdp, wait_gp_seq, TPS("EndWait")); - } - if (!rcu_nocb_poll) { - raw_spin_lock_irqsave(&my_rdp->nocb_gp_lock, flags); - if (bypass) - del_timer(&my_rdp->nocb_bypass_timer); - WRITE_ONCE(my_rdp->nocb_gp_sleep, true); - raw_spin_unlock_irqrestore(&my_rdp->nocb_gp_lock, flags); - } - my_rdp->nocb_gp_seq = -1; - WARN_ON(signal_pending(current)); -} - -/* - * No-CBs grace-period-wait kthread. There is one of these per group - * of CPUs, but only once at least one CPU in that group has come online - * at least once since boot. This kthread checks for newly posted - * callbacks from any of the CPUs it is responsible for, waits for a - * grace period, then awakens all of the rcu_nocb_cb_kthread() instances - * that then have callback-invocation work to do. - */ -static int rcu_nocb_gp_kthread(void *arg) -{ - struct rcu_data *rdp = arg; - - for (;;) { - WRITE_ONCE(rdp->nocb_gp_loops, rdp->nocb_gp_loops + 1); - nocb_gp_wait(rdp); - cond_resched_tasks_rcu_qs(); - } - return 0; -} - -/* - * Invoke any ready callbacks from the corresponding no-CBs CPU, - * then, if there are no more, wait for more to appear. - */ -static void nocb_cb_wait(struct rcu_data *rdp) -{ - unsigned long cur_gp_seq; - unsigned long flags; - bool needwake_gp = false; - struct rcu_node *rnp = rdp->mynode; - - local_irq_save(flags); - rcu_momentary_dyntick_idle(); - local_irq_restore(flags); - local_bh_disable(); - rcu_do_batch(rdp); - local_bh_enable(); - lockdep_assert_irqs_enabled(); - rcu_nocb_lock_irqsave(rdp, flags); - if (rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq) && - rcu_seq_done(&rnp->gp_seq, cur_gp_seq) && - raw_spin_trylock_rcu_node(rnp)) { /* irqs already disabled. */ - needwake_gp = rcu_advance_cbs(rdp->mynode, rdp); - raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ - } - if (rcu_segcblist_ready_cbs(&rdp->cblist)) { - rcu_nocb_unlock_irqrestore(rdp, flags); - if (needwake_gp) - rcu_gp_kthread_wake(); - return; - } - - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("CBSleep")); - WRITE_ONCE(rdp->nocb_cb_sleep, true); - rcu_nocb_unlock_irqrestore(rdp, flags); - if (needwake_gp) - rcu_gp_kthread_wake(); - swait_event_interruptible_exclusive(rdp->nocb_cb_wq, - !READ_ONCE(rdp->nocb_cb_sleep)); - if (!smp_load_acquire(&rdp->nocb_cb_sleep)) { /* VVV */ - /* ^^^ Ensure CB invocation follows _sleep test. */ - return; - } - WARN_ON(signal_pending(current)); - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WokeEmpty")); -} - -/* - * Per-rcu_data kthread, but only for no-CBs CPUs. Repeatedly invoke - * nocb_cb_wait() to do the dirty work. - */ -static int rcu_nocb_cb_kthread(void *arg) -{ - struct rcu_data *rdp = arg; - - // Each pass through this loop does one callback batch, and, - // if there are no more ready callbacks, waits for them. - for (;;) { - nocb_cb_wait(rdp); - cond_resched_tasks_rcu_qs(); - } - return 0; -} - -/* Is a deferred wakeup of rcu_nocb_kthread() required? */ -static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp) -{ - return READ_ONCE(rdp->nocb_defer_wakeup); -} - -/* Do a deferred wakeup of rcu_nocb_kthread(). */ -static void do_nocb_deferred_wakeup_common(struct rcu_data *rdp) -{ - unsigned long flags; - int ndw; - - rcu_nocb_lock_irqsave(rdp, flags); - if (!rcu_nocb_need_deferred_wakeup(rdp)) { - rcu_nocb_unlock_irqrestore(rdp, flags); - return; - } - ndw = READ_ONCE(rdp->nocb_defer_wakeup); - WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT); - wake_nocb_gp(rdp, ndw == RCU_NOCB_WAKE_FORCE, flags); - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("DeferredWake")); -} - -/* Do a deferred wakeup of rcu_nocb_kthread() from a timer handler. */ -static void do_nocb_deferred_wakeup_timer(struct timer_list *t) -{ - struct rcu_data *rdp = from_timer(rdp, t, nocb_timer); - - do_nocb_deferred_wakeup_common(rdp); -} - -/* - * 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) -{ - if (rcu_nocb_need_deferred_wakeup(rdp)) - do_nocb_deferred_wakeup_common(rdp); -} - -void __init rcu_init_nohz(void) -{ - int cpu; - bool need_rcu_nocb_mask = false; - struct rcu_data *rdp; - -#if defined(CONFIG_NO_HZ_FULL) - if (tick_nohz_full_running && cpumask_weight(tick_nohz_full_mask)) - need_rcu_nocb_mask = true; -#endif /* #if defined(CONFIG_NO_HZ_FULL) */ - - if (!cpumask_available(rcu_nocb_mask) && need_rcu_nocb_mask) { - if (!zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL)) { - pr_info("rcu_nocb_mask allocation failed, callback offloading disabled.\n"); - return; - } - } - if (!cpumask_available(rcu_nocb_mask)) - return; - -#if defined(CONFIG_NO_HZ_FULL) - if (tick_nohz_full_running) - cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask); -#endif /* #if defined(CONFIG_NO_HZ_FULL) */ - - if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) { - pr_info("\tNote: kernel parameter 'rcu_nocbs=', 'nohz_full', or 'isolcpus=' contains nonexistent CPUs.\n"); - cpumask_and(rcu_nocb_mask, cpu_possible_mask, - rcu_nocb_mask); - } - if (cpumask_empty(rcu_nocb_mask)) - pr_info("\tOffload RCU callbacks from CPUs: (none).\n"); - else - pr_info("\tOffload RCU callbacks from CPUs: %*pbl.\n", - cpumask_pr_args(rcu_nocb_mask)); - if (rcu_nocb_poll) - pr_info("\tPoll for callbacks from no-CBs CPUs.\n"); - - for_each_cpu(cpu, rcu_nocb_mask) { - rdp = per_cpu_ptr(&rcu_data, cpu); - if (rcu_segcblist_empty(&rdp->cblist)) - rcu_segcblist_init(&rdp->cblist); - rcu_segcblist_offload(&rdp->cblist); - } - rcu_organize_nocb_kthreads(); -} - -/* Initialize per-rcu_data variables for no-CBs CPUs. */ -static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) -{ - init_swait_queue_head(&rdp->nocb_cb_wq); - init_swait_queue_head(&rdp->nocb_gp_wq); - raw_spin_lock_init(&rdp->nocb_lock); - raw_spin_lock_init(&rdp->nocb_bypass_lock); - raw_spin_lock_init(&rdp->nocb_gp_lock); - timer_setup(&rdp->nocb_timer, do_nocb_deferred_wakeup_timer, 0); - timer_setup(&rdp->nocb_bypass_timer, do_nocb_bypass_wakeup_timer, 0); - rcu_cblist_init(&rdp->nocb_bypass); -} - -/* - * If the specified CPU is a no-CBs CPU that does not already have its - * rcuo CB kthread, spawn it. Additionally, if the rcuo GP kthread - * for this CPU's group has not yet been created, spawn it as well. - */ -static void rcu_spawn_one_nocb_kthread(int cpu) -{ - struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); - struct rcu_data *rdp_gp; - struct task_struct *t; - - /* - * If this isn't a no-CBs CPU or if it already has an rcuo kthread, - * then nothing to do. - */ - if (!rcu_is_nocb_cpu(cpu) || rdp->nocb_cb_kthread) - return; - - /* If we didn't spawn the GP kthread first, reorganize! */ - rdp_gp = rdp->nocb_gp_rdp; - if (!rdp_gp->nocb_gp_kthread) { - t = kthread_run(rcu_nocb_gp_kthread, rdp_gp, - "rcuog/%d", rdp_gp->cpu); - if (WARN_ONCE(IS_ERR(t), "%s: Could not start rcuo GP kthread, OOM is now expected behavior\n", __func__)) - return; - WRITE_ONCE(rdp_gp->nocb_gp_kthread, t); - } - - /* Spawn the kthread for this CPU. */ - t = kthread_run(rcu_nocb_cb_kthread, rdp, - "rcuo%c/%d", rcu_state.abbr, cpu); - if (WARN_ONCE(IS_ERR(t), "%s: Could not start rcuo CB kthread, OOM is now expected behavior\n", __func__)) - return; - WRITE_ONCE(rdp->nocb_cb_kthread, t); - WRITE_ONCE(rdp->nocb_gp_kthread, rdp_gp->nocb_gp_kthread); -} - -/* - * If the specified CPU is a no-CBs CPU that does not already have its - * rcuo kthread, spawn it. - */ -static void rcu_spawn_cpu_nocb_kthread(int cpu) -{ - if (rcu_scheduler_fully_active) - rcu_spawn_one_nocb_kthread(cpu); -} - -/* - * Once the scheduler is running, spawn rcuo kthreads for all online - * no-CBs CPUs. This assumes that the early_initcall()s happen before - * non-boot CPUs come online -- if this changes, we will need to add - * some mutual exclusion. - */ -static void __init rcu_spawn_nocb_kthreads(void) -{ - int cpu; - - for_each_online_cpu(cpu) - rcu_spawn_cpu_nocb_kthread(cpu); -} - -/* How many CB CPU IDs per GP kthread? Default of -1 for sqrt(nr_cpu_ids). */ -static int rcu_nocb_gp_stride = -1; -module_param(rcu_nocb_gp_stride, int, 0444); - -/* - * Initialize GP-CB relationships for all no-CBs CPU. - */ -static void __init rcu_organize_nocb_kthreads(void) -{ - int cpu; - bool firsttime = true; - bool gotnocbs = false; - bool gotnocbscbs = true; - int ls = rcu_nocb_gp_stride; - int nl = 0; /* Next GP kthread. */ - struct rcu_data *rdp; - struct rcu_data *rdp_gp = NULL; /* Suppress misguided gcc warn. */ - struct rcu_data *rdp_prev = NULL; - - if (!cpumask_available(rcu_nocb_mask)) - return; - if (ls == -1) { - ls = nr_cpu_ids / int_sqrt(nr_cpu_ids); - rcu_nocb_gp_stride = ls; - } - - /* - * Each pass through this loop sets up one rcu_data structure. - * Should the corresponding CPU come online in the future, then - * we will spawn the needed set of rcu_nocb_kthread() kthreads. - */ - for_each_cpu(cpu, rcu_nocb_mask) { - rdp = per_cpu_ptr(&rcu_data, cpu); - if (rdp->cpu >= nl) { - /* New GP kthread, set up for CBs & next GP. */ - gotnocbs = true; - nl = DIV_ROUND_UP(rdp->cpu + 1, ls) * ls; - rdp->nocb_gp_rdp = rdp; - rdp_gp = rdp; - if (dump_tree) { - if (!firsttime) - pr_cont("%s\n", gotnocbscbs - ? "" : " (self only)"); - gotnocbscbs = false; - firsttime = false; - pr_alert("%s: No-CB GP kthread CPU %d:", - __func__, cpu); - } - } else { - /* Another CB kthread, link to previous GP kthread. */ - gotnocbscbs = true; - rdp->nocb_gp_rdp = rdp_gp; - rdp_prev->nocb_next_cb_rdp = rdp; - if (dump_tree) - pr_cont(" %d", cpu); - } - rdp_prev = rdp; - } - if (gotnocbs && dump_tree) - pr_cont("%s\n", gotnocbscbs ? "" : " (self only)"); -} - -/* - * Bind the current task to the offloaded CPUs. If there are no offloaded - * CPUs, leave the task unbound. Splat if the bind attempt fails. - */ -void rcu_bind_current_to_nocb(void) -{ - if (cpumask_available(rcu_nocb_mask) && cpumask_weight(rcu_nocb_mask)) - WARN_ON(sched_setaffinity(current->pid, rcu_nocb_mask)); -} -EXPORT_SYMBOL_GPL(rcu_bind_current_to_nocb); - -/* - * Dump out nocb grace-period kthread state for the specified rcu_data - * structure. - */ -static void show_rcu_nocb_gp_state(struct rcu_data *rdp) -{ - struct rcu_node *rnp = rdp->mynode; - - pr_info("nocb GP %d %c%c%c%c%c%c %c[%c%c] %c%c:%ld rnp %d:%d %lu\n", - rdp->cpu, - "kK"[!!rdp->nocb_gp_kthread], - "lL"[raw_spin_is_locked(&rdp->nocb_gp_lock)], - "dD"[!!rdp->nocb_defer_wakeup], - "tT"[timer_pending(&rdp->nocb_timer)], - "bB"[timer_pending(&rdp->nocb_bypass_timer)], - "sS"[!!rdp->nocb_gp_sleep], - ".W"[swait_active(&rdp->nocb_gp_wq)], - ".W"[swait_active(&rnp->nocb_gp_wq[0])], - ".W"[swait_active(&rnp->nocb_gp_wq[1])], - ".B"[!!rdp->nocb_gp_bypass], - ".G"[!!rdp->nocb_gp_gp], - (long)rdp->nocb_gp_seq, - rnp->grplo, rnp->grphi, READ_ONCE(rdp->nocb_gp_loops)); -} - -/* Dump out nocb kthread state for the specified rcu_data structure. */ -static void show_rcu_nocb_state(struct rcu_data *rdp) -{ - struct rcu_segcblist *rsclp = &rdp->cblist; - bool waslocked; - bool wastimer; - bool wassleep; - - if (rdp->nocb_gp_rdp == rdp) - show_rcu_nocb_gp_state(rdp); - - pr_info(" CB %d->%d %c%c%c%c%c%c F%ld L%ld C%d %c%c%c%c%c q%ld\n", - rdp->cpu, rdp->nocb_gp_rdp->cpu, - "kK"[!!rdp->nocb_cb_kthread], - "bB"[raw_spin_is_locked(&rdp->nocb_bypass_lock)], - "cC"[!!atomic_read(&rdp->nocb_lock_contended)], - "lL"[raw_spin_is_locked(&rdp->nocb_lock)], - "sS"[!!rdp->nocb_cb_sleep], - ".W"[swait_active(&rdp->nocb_cb_wq)], - jiffies - rdp->nocb_bypass_first, - jiffies - rdp->nocb_nobypass_last, - rdp->nocb_nobypass_count, - ".D"[rcu_segcblist_ready_cbs(rsclp)], - ".W"[!rcu_segcblist_restempty(rsclp, RCU_DONE_TAIL)], - ".R"[!rcu_segcblist_restempty(rsclp, RCU_WAIT_TAIL)], - ".N"[!rcu_segcblist_restempty(rsclp, RCU_NEXT_READY_TAIL)], - ".B"[!!rcu_cblist_n_cbs(&rdp->nocb_bypass)], - rcu_segcblist_n_cbs(&rdp->cblist)); - - /* It is OK for GP kthreads to have GP state. */ - if (rdp->nocb_gp_rdp == rdp) - return; - - waslocked = raw_spin_is_locked(&rdp->nocb_gp_lock); - wastimer = timer_pending(&rdp->nocb_timer); - wassleep = swait_active(&rdp->nocb_gp_wq); - if (!rdp->nocb_defer_wakeup && !rdp->nocb_gp_sleep && - !waslocked && !wastimer && !wassleep) - return; /* Nothing untowards. */ - - pr_info(" !!! %c%c%c%c %c\n", - "lL"[waslocked], - "dD"[!!rdp->nocb_defer_wakeup], - "tT"[wastimer], - "sS"[!!rdp->nocb_gp_sleep], - ".W"[wassleep]); -} - -#else /* #ifdef CONFIG_RCU_NOCB_CPU */ - -/* No ->nocb_lock to acquire. */ -static void rcu_nocb_lock(struct rcu_data *rdp) -{ -} - -/* No ->nocb_lock to release. */ -static void rcu_nocb_unlock(struct rcu_data *rdp) -{ -} - -/* No ->nocb_lock to release. */ -static void rcu_nocb_unlock_irqrestore(struct rcu_data *rdp, - unsigned long flags) -{ - local_irq_restore(flags); -} - -/* Lockdep check that ->cblist may be safely accessed. */ -static void rcu_lockdep_assert_cblist_protected(struct rcu_data *rdp) -{ - lockdep_assert_irqs_disabled(); -} - -static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq) -{ -} - -static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp) -{ - return NULL; -} - -static void rcu_init_one_nocb(struct rcu_node *rnp) -{ -} - -static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp, - unsigned long j) -{ - return true; -} - -static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp, - bool *was_alldone, unsigned long flags) -{ - return false; -} - -static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_empty, - unsigned long flags) -{ - WARN_ON_ONCE(1); /* Should be dead code! */ -} - -static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) -{ -} - -static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp) -{ - return false; -} - -static void do_nocb_deferred_wakeup(struct rcu_data *rdp) -{ -} - -static void rcu_spawn_cpu_nocb_kthread(int cpu) -{ -} - -static void __init rcu_spawn_nocb_kthreads(void) -{ -} - -static void show_rcu_nocb_state(struct rcu_data *rdp) -{ -} - -#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ - /* * Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the * grace-period kthread will do force_quiescent_state() processing? @@ -2515,7 +1283,7 @@ static void show_rcu_nocb_state(struct rcu_data *rdp) * CPU unless the grace period has extended for too long. * * This code relies on the fact that all NO_HZ_FULL CPUs are also - * CONFIG_RCU_NOCB_CPU CPUs. + * RCU_NOCB_CPU CPUs. */ static bool rcu_nohz_full_cpu(void) { @@ -2535,39 +1303,5 @@ static void rcu_bind_gp_kthread(void) { if (!tick_nohz_full_enabled()) return; - housekeeping_affine(current, HK_FLAG_RCU); -} - -/* Record the current task on dyntick-idle entry. */ -static void noinstr rcu_dynticks_task_enter(void) -{ -#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) - WRITE_ONCE(current->rcu_tasks_idle_cpu, smp_processor_id()); -#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */ -} - -/* Record no current task on dyntick-idle exit. */ -static void noinstr rcu_dynticks_task_exit(void) -{ -#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) - WRITE_ONCE(current->rcu_tasks_idle_cpu, -1); -#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */ -} - -/* Turn on heavyweight RCU tasks trace readers on idle/user entry. */ -static void rcu_dynticks_task_trace_enter(void) -{ -#ifdef CONFIG_TASKS_RCU_TRACE - if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) - current->trc_reader_special.b.need_mb = true; -#endif /* #ifdef CONFIG_TASKS_RCU_TRACE */ -} - -/* Turn off heavyweight RCU tasks trace readers on idle/user exit. */ -static void rcu_dynticks_task_trace_exit(void) -{ -#ifdef CONFIG_TASKS_RCU_TRACE - if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) - current->trc_reader_special.b.need_mb = false; -#endif /* #ifdef CONFIG_TASKS_RCU_TRACE */ + housekeeping_affine(current, HK_TYPE_RCU); } |