/* SPDX-License-Identifier: GPL-2.0+ *//* * Read-Copy Update mechanism for mutual exclusion (tree-based version) * Internal non-public definitions that provide either classic * or preemptible semantics. * * Copyright Red Hat, 2009 * Copyright IBM Corporation, 2009 * * Author: Ingo Molnar <mingo@elte.hu> * Paul E. McKenney <paulmck@linux.ibm.com> */ #include "../locking/rtmutex_common.h" 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_NOCB_LOCKDEP_WARN( !(lockdep_is_held(&rcu_state.barrier_mutex) || (IS_ENABLED(CONFIG_HOTPLUG_CPU) && lockdep_is_cpus_held()) || lockdep_is_held(&rdp->nocb_lock) || lockdep_is_held(&rcu_state.nocb_mutex) || (!(IS_ENABLED(CONFIG_PREEMPT_COUNT) && preemptible()) && rdp == this_cpu_ptr(&rcu_data)) || 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 * messages about anything out of the ordinary. */static void __init rcu_bootup_announce_oddness(void){ if (IS_ENABLED(CONFIG_RCU_TRACE)) 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", RCU_FANOUT); if (rcu_fanout_exact) pr_info("\tHierarchical RCU autobalancing is disabled.\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) pr_info("\tBuild-time adjustment of leaf fanout to %d.\n", RCU_FANOUT_LEAF); if (rcu_fanout_leaf != RCU_FANOUT_LEAF) 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=%u.\n", NR_CPUS, nr_cpu_ids);#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 (qovld != DEFAULT_RCU_QOVLD) pr_info("\tBoot-time adjustment of callback overload level to %ld.\n", qovld); 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 (jiffies_till_sched_qs != ULONG_MAX) pr_info("\tBoot-time adjustment of scheduler-enlistment delay to %ld jiffies.\n", jiffies_till_sched_qs); 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 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 cleanup slowdown %d jiffies.\n", gp_cleanup_delay); if (nohz_full_patience_delay < 0) { pr_info("\tRCU NOCB CPU patience negative (%d), resetting to zero.\n", nohz_full_patience_delay); nohz_full_patience_delay = 0; } else if (nohz_full_patience_delay > 5 * MSEC_PER_SEC) { pr_info("\tRCU NOCB CPU patience too large (%d), resetting to %ld.\n", nohz_full_patience_delay, 5 * MSEC_PER_SEC); nohz_full_patience_delay = 5 * MSEC_PER_SEC; } else if (nohz_full_patience_delay) { pr_info("\tRCU NOCB CPU patience set to %d milliseconds.\n", nohz_full_patience_delay); } nohz_full_patience_delay_jiffies = msecs_to_jiffies(nohz_full_patience_delay); if (!use_softirq) pr_info("\tRCU_SOFTIRQ processing moved to rcuc kthreads.\n"); if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG)) pr_info("\tRCU debug extended QS entry/exit.\n"); rcupdate_announce_bootup_oddness();} #ifdef CONFIG_PREEMPT_RCU static void rcu_report_exp_rnp(struct rcu_node *rnp, bool wake);static void rcu_read_unlock_special(struct task_struct *t); /* * Tell them what RCU they are running. */static void __init rcu_bootup_announce(void){ pr_info("Preemptible hierarchical RCU implementation.\n"); rcu_bootup_announce_oddness();} /* Flags for rcu_preempt_ctxt_queue() decision table. */#define RCU_GP_TASKS 0x8#define RCU_EXP_TASKS 0x4#define RCU_GP_BLKD 0x2#define RCU_EXP_BLKD 0x1 /* * Queues a task preempted within an RCU-preempt read-side critical * section into the appropriate location within the ->blkd_tasks list, * depending on the states of any ongoing normal and expedited grace * periods. The ->gp_tasks pointer indicates which element the normal * grace period is waiting on (NULL if none), and the ->exp_tasks pointer * indicates which element the expedited grace period is waiting on (again, * NULL if none). If a grace period is waiting on a given element in the * ->blkd_tasks list, it also waits on all subsequent elements. Thus, * adding a task to the tail of the list blocks any grace period that is * already waiting on one of the elements. In contrast, adding a task * to the head of the list won't block any grace period that is already * waiting on one of the elements. * * This queuing is imprecise, and can sometimes make an ongoing grace * period wait for a task that is not strictly speaking blocking it. * Given the choice, we needlessly block a normal grace period rather than * blocking an expedited grace period. * * Note that an endless sequence of expedited grace periods still cannot * indefinitely postpone a normal grace period. Eventually, all of the * fixed number of preempted tasks blocking the normal grace period that are * not also blocking the expedited grace period will resume and complete * their RCU read-side critical sections. At that point, the ->gp_tasks * pointer will equal the ->exp_tasks pointer, at which point the end of * the corresponding expedited grace period will also be the end of the * normal grace period. */static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) __releases(rnp->lock) /* But leaves rrupts disabled. */{ int blkd_state = (rnp->gp_tasks ? RCU_GP_TASKS : 0) + (rnp->exp_tasks ? RCU_EXP_TASKS : 0) + (rnp->qsmask & rdp->grpmask ? RCU_GP_BLKD : 0) + (rnp->expmask & rdp->grpmask ? RCU_EXP_BLKD : 0); struct task_struct *t = current; raw_lockdep_assert_held_rcu_node(rnp); WARN_ON_ONCE(rdp->mynode != rnp); WARN_ON_ONCE(!rcu_is_leaf_node(rnp)); /* RCU better not be waiting on newly onlined CPUs! */ WARN_ON_ONCE(rnp->qsmaskinitnext & ~rnp->qsmaskinit & rnp->qsmask & rdp->grpmask); /* * Decide where to queue the newly blocked task. In theory, * this could be an if-statement. In practice, when I tried * that, it was quite messy. */ switch (blkd_state) { case 0: case RCU_EXP_TASKS: case RCU_EXP_TASKS | RCU_GP_BLKD: case RCU_GP_TASKS: case RCU_GP_TASKS | RCU_EXP_TASKS: /* * Blocking neither GP, or first task blocking the normal * GP but not blocking the already-waiting expedited GP. * Queue at the head of the list to avoid unnecessarily * blocking the already-waiting GPs. */ list_add(&t->rcu_node_entry, &rnp->blkd_tasks); break; case RCU_EXP_BLKD: case RCU_GP_BLKD: case RCU_GP_BLKD | RCU_EXP_BLKD: case RCU_GP_TASKS | RCU_EXP_BLKD: case RCU_GP_TASKS | RCU_GP_BLKD | RCU_EXP_BLKD: case RCU_GP_TASKS | RCU_EXP_TASKS | RCU_GP_BLKD | RCU_EXP_BLKD: /* * First task arriving that blocks either GP, or first task * arriving that blocks the expedited GP (with the normal * GP already waiting), or a task arriving that blocks * both GPs with both GPs already waiting. Queue at the * tail of the list to avoid any GP waiting on any of the * already queued tasks that are not blocking it. */ list_add_tail(&t->rcu_node_entry, &rnp->blkd_tasks); break; case RCU_EXP_TASKS | RCU_EXP_BLKD: case RCU_EXP_TASKS | RCU_GP_BLKD | RCU_EXP_BLKD: case RCU_GP_TASKS | RCU_EXP_TASKS | RCU_EXP_BLKD: /* * Second or subsequent task blocking the expedited GP. * The task either does not block the normal GP, or is the * first task blocking the normal GP. Queue just after * the first task blocking the expedited GP. */ list_add(&t->rcu_node_entry, rnp->exp_tasks); break; case RCU_GP_TASKS | RCU_GP_BLKD: case RCU_GP_TASKS | RCU_EXP_TASKS | RCU_GP_BLKD: /* * Second or subsequent task blocking the normal GP. * The task does not block the expedited GP. Queue just * after the first task blocking the normal GP. */ list_add(&t->rcu_node_entry, rnp->gp_tasks); break; default: /* Yet another exercise in excessive paranoia. */ WARN_ON_ONCE(1); break; } /* * We have now queued the task. If it was the first one to * block either grace period, update the ->gp_tasks and/or * ->exp_tasks pointers, respectively, to reference the newly * blocked tasks. */ if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) { WRITE_ONCE(rnp->gp_tasks, &t->rcu_node_entry); WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq); } if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD)) WRITE_ONCE(rnp->exp_tasks, &t->rcu_node_entry); WARN_ON_ONCE(!(blkd_state & RCU_GP_BLKD) != !(rnp->qsmask & rdp->grpmask)); WARN_ON_ONCE(!(blkd_state & RCU_EXP_BLKD) != !(rnp->expmask & rdp->grpmask)); raw_spin_unlock_rcu_node(rnp); /* interrupts remain disabled. */ /* * Report the quiescent state for the expedited GP. This expedited * 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->cpu_no_qs.b.exp) rcu_report_exp_rdp(rdp); else WARN_ON_ONCE(rdp->cpu_no_qs.b.exp);} /* * Record a preemptible-RCU quiescent state for the specified CPU. * Note that this does not necessarily mean that the task currently running * on the CPU is in a quiescent state: Instead, it means that the current * grace period need not wait on any RCU read-side critical section that * starts later on this CPU. It also means that if the current task is * in an RCU read-side critical section, it has already added itself to * some leaf rcu_node structure's ->blkd_tasks list. In addition to the * 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.b.norm)) { trace_rcu_grace_period(TPS("rcu_preempt"), __this_cpu_read(rcu_data.gp_seq), TPS("cpuqs")); __this_cpu_write(rcu_data.cpu_no_qs.b.norm, false); barrier(); /* Coordinate with rcu_flavor_sched_clock_irq(). */ WRITE_ONCE(current->rcu_read_unlock_special.b.need_qs, false); }} /* * We have entered the scheduler, and the current task might soon be * context-switched away from. If this task is in an RCU read-side * critical section, we will no longer be able to rely on the CPU to * record that fact, so we enqueue the task on the blkd_tasks list. * The task will dequeue itself when it exits the outermost enclosing * RCU read-side critical section. Therefore, the current grace period * cannot be permitted to complete until the blkd_tasks list entries * predating the current grace period drain, in other words, until * rnp->gp_tasks becomes NULL. * * Caller must disable interrupts. */void rcu_note_context_switch(bool preempt){ struct task_struct *t = current; struct rcu_data *rdp = this_cpu_ptr(&rcu_data); struct rcu_node *rnp; trace_rcu_utilization(TPS("Start context switch")); lockdep_assert_irqs_disabled(); 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) { /* Possibly blocking in an RCU read-side critical section. */ rnp = rdp->mynode; raw_spin_lock_rcu_node(rnp); t->rcu_read_unlock_special.b.blocked = true; t->rcu_blocked_node = rnp; /* * Verify the CPU's sanity, trace the preemption, and * then queue the task as required based on the states * of any ongoing and expedited grace periods. */ 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, (rnp->qsmask & rdp->grpmask) ? rnp->gp_seq : rcu_seq_snap(&rnp->gp_seq)); rcu_preempt_ctxt_queue(rnp, rdp); } else { rcu_preempt_deferred_qs(t); } /* * Either we were not in an RCU read-side critical section to * begin with, or we have now recorded that critical section * globally. Either way, we can now note a quiescent state * for this CPU. Again, if we were in an RCU read-side critical * section, and if that critical section was blocking the current * grace period, then the fact that the task has been enqueued * means that we continue to block the current grace period. */ rcu_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"));}EXPORT_SYMBOL_GPL(rcu_note_context_switch); /* * Check for preempted RCU readers blocking the current grace period * for the specified rcu_node structure. If the caller needs a reliable * answer, it must hold the rcu_node's ->lock. */static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp){ return READ_ONCE(rnp->gp_tasks) != NULL;} /* limit value for ->rcu_read_lock_nesting. */#define RCU_NEST_PMAX (INT_MAX / 2) static void rcu_preempt_read_enter(void){ WRITE_ONCE(current->rcu_read_lock_nesting, READ_ONCE(current->rcu_read_lock_nesting) + 1);} static int rcu_preempt_read_exit(void){ 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){ WRITE_ONCE(current->rcu_read_lock_nesting, val);} /* * Preemptible RCU implementation for rcu_read_lock(). * Just increment ->rcu_read_lock_nesting, shared state will be updated * if we block. */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); /* * Preemptible RCU implementation for rcu_read_unlock(). * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then * invoke rcu_read_unlock_special() to clean up after a context switch * in an RCU read-side critical section and other special cases. */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 exit before .s check. if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s))) rcu_read_unlock_special(t); } if (IS_ENABLED(CONFIG_PROVE_LOCKING)) { int rrln = rcu_preempt_depth(); WARN_ON_ONCE(rrln < 0 || rrln > RCU_NEST_PMAX); }}EXPORT_SYMBOL_GPL(__rcu_read_unlock); /* * Advance a ->blkd_tasks-list pointer to the next entry, instead * returning NULL if at the end of the list. */static struct list_head *rcu_next_node_entry(struct task_struct *t, struct rcu_node *rnp){ struct list_head *np; np = t->rcu_node_entry.next; if (np == &rnp->blkd_tasks) np = NULL; return np;} /* * Return true if the specified rcu_node structure has tasks that were * preempted within an RCU read-side critical section. */static bool rcu_preempt_has_tasks(struct rcu_node *rnp){ return !list_empty(&rnp->blkd_tasks);} /* * Report deferred quiescent states. The deferral time can * be quite short, for example, in the case of the call from * rcu_read_unlock_special(). */static notrace voidrcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags){ bool empty_exp; bool empty_norm; bool empty_exp_now; struct list_head *np; bool drop_boost_mutex = false; struct rcu_data *rdp; struct rcu_node *rnp; union rcu_special special; /* * If RCU core is waiting for this CPU to exit its critical section, * report the fact that it has exited. Because irqs are disabled, * t->rcu_read_unlock_special cannot change. */ special = t->rcu_read_unlock_special; rdp = this_cpu_ptr(&rcu_data); 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) {Lines 1–500 of 1280. Load more
/* SPDX-License-Identifier: GPL-2.0+ */ /* * Read-Copy Update mechanism for mutual exclusion (tree-based version) * Internal non-public definitions that provide either classic * or preemptible semantics. * * Copyright Red Hat, 2009 * Copyright IBM Corporation, 2009 * * Author: Ingo Molnar <mingo@elte.hu> * Paul E. McKenney <paulmck@linux.ibm.com> */ #include "../locking/rtmutex_common.h" 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_NOCB_LOCKDEP_WARN( !(lockdep_is_held(&rcu_state.barrier_mutex) || (IS_ENABLED(CONFIG_HOTPLUG_CPU) && lockdep_is_cpus_held()) || lockdep_is_held(&rdp->nocb_lock) || lockdep_is_held(&rcu_state.nocb_mutex) || (!(IS_ENABLED(CONFIG_PREEMPT_COUNT) && preemptible()) && rdp == this_cpu_ptr(&rcu_data)) || 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 * messages about anything out of the ordinary. */ static void __init rcu_bootup_announce_oddness(void) { if (IS_ENABLED(CONFIG_RCU_TRACE)) 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", RCU_FANOUT); if (rcu_fanout_exact) pr_info("\tHierarchical RCU autobalancing is disabled.\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) pr_info("\tBuild-time adjustment of leaf fanout to %d.\n", RCU_FANOUT_LEAF); if (rcu_fanout_leaf != RCU_FANOUT_LEAF) 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=%u.\n", NR_CPUS, nr_cpu_ids); #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 (qovld != DEFAULT_RCU_QOVLD) pr_info("\tBoot-time adjustment of callback overload level to %ld.\n", qovld); 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 (jiffies_till_sched_qs != ULONG_MAX) pr_info("\tBoot-time adjustment of scheduler-enlistment delay to %ld jiffies.\n", jiffies_till_sched_qs); 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 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 cleanup slowdown %d jiffies.\n", gp_cleanup_delay); if (nohz_full_patience_delay < 0) { pr_info("\tRCU NOCB CPU patience negative (%d), resetting to zero.\n", nohz_full_patience_delay); nohz_full_patience_delay = 0; } else if (nohz_full_patience_delay > 5 * MSEC_PER_SEC) { pr_info("\tRCU NOCB CPU patience too large (%d), resetting to %ld.\n", nohz_full_patience_delay, 5 * MSEC_PER_SEC); nohz_full_patience_delay = 5 * MSEC_PER_SEC; } else if (nohz_full_patience_delay) { pr_info("\tRCU NOCB CPU patience set to %d milliseconds.\n", nohz_full_patience_delay); } nohz_full_patience_delay_jiffies = msecs_to_jiffies(nohz_full_patience_delay); if (!use_softirq) pr_info("\tRCU_SOFTIRQ processing moved to rcuc kthreads.\n"); if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG)) pr_info("\tRCU debug extended QS entry/exit.\n"); rcupdate_announce_bootup_oddness(); } #ifdef CONFIG_PREEMPT_RCU static void rcu_report_exp_rnp(struct rcu_node *rnp, bool wake); static void rcu_read_unlock_special(struct task_struct *t); /* * Tell them what RCU they are running. */ static void __init rcu_bootup_announce(void) { pr_info("Preemptible hierarchical RCU implementation.\n"); rcu_bootup_announce_oddness(); } /* Flags for rcu_preempt_ctxt_queue() decision table. */ #define RCU_GP_TASKS 0x8 #define RCU_EXP_TASKS 0x4 #define RCU_GP_BLKD 0x2 #define RCU_EXP_BLKD 0x1 /* * Queues a task preempted within an RCU-preempt read-side critical * section into the appropriate location within the ->blkd_tasks list, * depending on the states of any ongoing normal and expedited grace * periods. The ->gp_tasks pointer indicates which element the normal * grace period is waiting on (NULL if none), and the ->exp_tasks pointer * indicates which element the expedited grace period is waiting on (again, * NULL if none). If a grace period is waiting on a given element in the * ->blkd_tasks list, it also waits on all subsequent elements. Thus, * adding a task to the tail of the list blocks any grace period that is * already waiting on one of the elements. In contrast, adding a task * to the head of the list won't block any grace period that is already * waiting on one of the elements. * * This queuing is imprecise, and can sometimes make an ongoing grace * period wait for a task that is not strictly speaking blocking it. * Given the choice, we needlessly block a normal grace period rather than * blocking an expedited grace period. * * Note that an endless sequence of expedited grace periods still cannot * indefinitely postpone a normal grace period. Eventually, all of the * fixed number of preempted tasks blocking the normal grace period that are * not also blocking the expedited grace period will resume and complete * their RCU read-side critical sections. At that point, the ->gp_tasks * pointer will equal the ->exp_tasks pointer, at which point the end of * the corresponding expedited grace period will also be the end of the * normal grace period. */ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) __releases(rnp->lock) /* But leaves rrupts disabled. */ { int blkd_state = (rnp->gp_tasks ? RCU_GP_TASKS : 0) + (rnp->exp_tasks ? RCU_EXP_TASKS : 0) + (rnp->qsmask & rdp->grpmask ? RCU_GP_BLKD : 0) + (rnp->expmask & rdp->grpmask ? RCU_EXP_BLKD : 0); struct task_struct *t = current; raw_lockdep_assert_held_rcu_node(rnp); WARN_ON_ONCE(rdp->mynode != rnp); WARN_ON_ONCE(!rcu_is_leaf_node(rnp)); /* RCU better not be waiting on newly onlined CPUs! */ WARN_ON_ONCE(rnp->qsmaskinitnext & ~rnp->qsmaskinit & rnp->qsmask & rdp->grpmask); /* * Decide where to queue the newly blocked task. In theory, * this could be an if-statement. In practice, when I tried * that, it was quite messy. */ switch (blkd_state) { case 0: case RCU_EXP_TASKS: case RCU_EXP_TASKS | RCU_GP_BLKD: case RCU_GP_TASKS: case RCU_GP_TASKS | RCU_EXP_TASKS: /* * Blocking neither GP, or first task blocking the normal * GP but not blocking the already-waiting expedited GP. * Queue at the head of the list to avoid unnecessarily * blocking the already-waiting GPs. */ list_add(&t->rcu_node_entry, &rnp->blkd_tasks); break; case RCU_EXP_BLKD: case RCU_GP_BLKD: case RCU_GP_BLKD | RCU_EXP_BLKD: case RCU_GP_TASKS | RCU_EXP_BLKD: case RCU_GP_TASKS | RCU_GP_BLKD | RCU_EXP_BLKD: case RCU_GP_TASKS | RCU_EXP_TASKS | RCU_GP_BLKD | RCU_EXP_BLKD: /* * First task arriving that blocks either GP, or first task * arriving that blocks the expedited GP (with the normal * GP already waiting), or a task arriving that blocks * both GPs with both GPs already waiting. Queue at the * tail of the list to avoid any GP waiting on any of the * already queued tasks that are not blocking it. */ list_add_tail(&t->rcu_node_entry, &rnp->blkd_tasks); break; case RCU_EXP_TASKS | RCU_EXP_BLKD: case RCU_EXP_TASKS | RCU_GP_BLKD | RCU_EXP_BLKD: case RCU_GP_TASKS | RCU_EXP_TASKS | RCU_EXP_BLKD: /* * Second or subsequent task blocking the expedited GP. * The task either does not block the normal GP, or is the * first task blocking the normal GP. Queue just after * the first task blocking the expedited GP. */ list_add(&t->rcu_node_entry, rnp->exp_tasks); break; case RCU_GP_TASKS | RCU_GP_BLKD: case RCU_GP_TASKS | RCU_EXP_TASKS | RCU_GP_BLKD: /* * Second or subsequent task blocking the normal GP. * The task does not block the expedited GP. Queue just * after the first task blocking the normal GP. */ list_add(&t->rcu_node_entry, rnp->gp_tasks); break; default: /* Yet another exercise in excessive paranoia. */ WARN_ON_ONCE(1); break; } /* * We have now queued the task. If it was the first one to * block either grace period, update the ->gp_tasks and/or * ->exp_tasks pointers, respectively, to reference the newly * blocked tasks. */ if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) { WRITE_ONCE(rnp->gp_tasks, &t->rcu_node_entry); WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq); } if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD)) WRITE_ONCE(rnp->exp_tasks, &t->rcu_node_entry); WARN_ON_ONCE(!(blkd_state & RCU_GP_BLKD) != !(rnp->qsmask & rdp->grpmask)); WARN_ON_ONCE(!(blkd_state & RCU_EXP_BLKD) != !(rnp->expmask & rdp->grpmask)); raw_spin_unlock_rcu_node(rnp); /* interrupts remain disabled. */ /* * Report the quiescent state for the expedited GP. This expedited * 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->cpu_no_qs.b.exp) rcu_report_exp_rdp(rdp); else WARN_ON_ONCE(rdp->cpu_no_qs.b.exp); } /* * Record a preemptible-RCU quiescent state for the specified CPU. * Note that this does not necessarily mean that the task currently running * on the CPU is in a quiescent state: Instead, it means that the current * grace period need not wait on any RCU read-side critical section that * starts later on this CPU. It also means that if the current task is * in an RCU read-side critical section, it has already added itself to * some leaf rcu_node structure's ->blkd_tasks list. In addition to the * 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.b.norm)) { trace_rcu_grace_period(TPS("rcu_preempt"), __this_cpu_read(rcu_data.gp_seq), TPS("cpuqs")); __this_cpu_write(rcu_data.cpu_no_qs.b.norm, false); barrier(); /* Coordinate with rcu_flavor_sched_clock_irq(). */ WRITE_ONCE(current->rcu_read_unlock_special.b.need_qs, false); } } /* * We have entered the scheduler, and the current task might soon be * context-switched away from. If this task is in an RCU read-side * critical section, we will no longer be able to rely on the CPU to * record that fact, so we enqueue the task on the blkd_tasks list. * The task will dequeue itself when it exits the outermost enclosing * RCU read-side critical section. Therefore, the current grace period * cannot be permitted to complete until the blkd_tasks list entries * predating the current grace period drain, in other words, until * rnp->gp_tasks becomes NULL. * * Caller must disable interrupts. */ void rcu_note_context_switch(bool preempt) { struct task_struct *t = current; struct rcu_data *rdp = this_cpu_ptr(&rcu_data); struct rcu_node *rnp; trace_rcu_utilization(TPS("Start context switch")); lockdep_assert_irqs_disabled(); 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) { /* Possibly blocking in an RCU read-side critical section. */ rnp = rdp->mynode; raw_spin_lock_rcu_node(rnp); t->rcu_read_unlock_special.b.blocked = true; t->rcu_blocked_node = rnp; /* * Verify the CPU's sanity, trace the preemption, and * then queue the task as required based on the states * of any ongoing and expedited grace periods. */ 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, (rnp->qsmask & rdp->grpmask) ? rnp->gp_seq : rcu_seq_snap(&rnp->gp_seq)); rcu_preempt_ctxt_queue(rnp, rdp); } else { rcu_preempt_deferred_qs(t); } /* * Either we were not in an RCU read-side critical section to * begin with, or we have now recorded that critical section * globally. Either way, we can now note a quiescent state * for this CPU. Again, if we were in an RCU read-side critical * section, and if that critical section was blocking the current * grace period, then the fact that the task has been enqueued * means that we continue to block the current grace period. */ rcu_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")); } EXPORT_SYMBOL_GPL(rcu_note_context_switch); /* * Check for preempted RCU readers blocking the current grace period * for the specified rcu_node structure. If the caller needs a reliable * answer, it must hold the rcu_node's ->lock. */ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) { return READ_ONCE(rnp->gp_tasks) != NULL; } /* limit value for ->rcu_read_lock_nesting. */ #define RCU_NEST_PMAX (INT_MAX / 2) static void rcu_preempt_read_enter(void) { WRITE_ONCE(current->rcu_read_lock_nesting, READ_ONCE(current->rcu_read_lock_nesting) + 1); } static int rcu_preempt_read_exit(void) { 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) { WRITE_ONCE(current->rcu_read_lock_nesting, val); } /* * Preemptible RCU implementation for rcu_read_lock(). * Just increment ->rcu_read_lock_nesting, shared state will be updated * if we block. */ 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); /* * Preemptible RCU implementation for rcu_read_unlock(). * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then * invoke rcu_read_unlock_special() to clean up after a context switch * in an RCU read-side critical section and other special cases. */ 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 exit before .s check. if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s))) rcu_read_unlock_special(t); } if (IS_ENABLED(CONFIG_PROVE_LOCKING)) { int rrln = rcu_preempt_depth(); WARN_ON_ONCE(rrln < 0 || rrln > RCU_NEST_PMAX); } } EXPORT_SYMBOL_GPL(__rcu_read_unlock); /* * Advance a ->blkd_tasks-list pointer to the next entry, instead * returning NULL if at the end of the list. */ static struct list_head *rcu_next_node_entry(struct task_struct *t, struct rcu_node *rnp) { struct list_head *np; np = t->rcu_node_entry.next; if (np == &rnp->blkd_tasks) np = NULL; return np; } /* * Return true if the specified rcu_node structure has tasks that were * preempted within an RCU read-side critical section. */ static bool rcu_preempt_has_tasks(struct rcu_node *rnp) { return !list_empty(&rnp->blkd_tasks); } /* * Report deferred quiescent states. The deferral time can * be quite short, for example, in the case of the call from * rcu_read_unlock_special(). */ static notrace void rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) { bool empty_exp; bool empty_norm; bool empty_exp_now; struct list_head *np; bool drop_boost_mutex = false; struct rcu_data *rdp; struct rcu_node *rnp; union rcu_special special; /* * If RCU core is waiting for this CPU to exit its critical section, * report the fact that it has exited. Because irqs are disabled, * t->rcu_read_unlock_special cannot change. */ special = t->rcu_read_unlock_special; rdp = this_cpu_ptr(&rcu_data); 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) {