diff options
Diffstat (limited to 'kernel/rcu/tree.c')
| -rw-r--r-- | kernel/rcu/tree.c | 412 |
1 files changed, 197 insertions, 215 deletions
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index e354e475e645..3e3650e94ae6 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -97,9 +97,6 @@ struct rcu_state sname##_state = { \ .gp_state = RCU_GP_IDLE, \ .gpnum = 0UL - 300UL, \ .completed = 0UL - 300UL, \ - .orphan_lock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.orphan_lock), \ - .orphan_pend = RCU_CBLIST_INITIALIZER(sname##_state.orphan_pend), \ - .orphan_done = RCU_CBLIST_INITIALIZER(sname##_state.orphan_done), \ .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \ .name = RCU_STATE_NAME(sname), \ .abbr = sabbr, \ @@ -168,35 +165,17 @@ static void rcu_report_exp_rdp(struct rcu_state *rsp, static void sync_sched_exp_online_cleanup(int cpu); /* rcuc/rcub kthread realtime priority */ -#ifdef CONFIG_RCU_KTHREAD_PRIO -static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO; -#else /* #ifdef CONFIG_RCU_KTHREAD_PRIO */ static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0; -#endif /* #else #ifdef CONFIG_RCU_KTHREAD_PRIO */ module_param(kthread_prio, int, 0644); /* Delay in jiffies for grace-period initialization delays, debug only. */ -#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT -static int gp_preinit_delay = CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT_DELAY; -module_param(gp_preinit_delay, int, 0644); -#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT */ -static const int gp_preinit_delay; -#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT */ - -#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT -static int gp_init_delay = CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY; -module_param(gp_init_delay, int, 0644); -#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */ -static const int gp_init_delay; -#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */ - -#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP -static int gp_cleanup_delay = CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY; -module_param(gp_cleanup_delay, int, 0644); -#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP */ -static const int gp_cleanup_delay; -#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP */ +static int gp_preinit_delay; +module_param(gp_preinit_delay, int, 0444); +static int gp_init_delay; +module_param(gp_init_delay, int, 0444); +static int gp_cleanup_delay; +module_param(gp_cleanup_delay, int, 0444); /* * Number of grace periods between delays, normalized by the duration of @@ -250,6 +229,7 @@ static int rcu_gp_in_progress(struct rcu_state *rsp) */ void rcu_sched_qs(void) { + RCU_LOCKDEP_WARN(preemptible(), "rcu_sched_qs() invoked with preemption enabled!!!"); if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) return; trace_rcu_grace_period(TPS("rcu_sched"), @@ -265,6 +245,7 @@ void rcu_sched_qs(void) void rcu_bh_qs(void) { + RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!"); if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_bh"), __this_cpu_read(rcu_bh_data.gpnum), @@ -286,10 +267,6 @@ void rcu_bh_qs(void) static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { .dynticks_nesting = DYNTICK_TASK_EXIT_IDLE, .dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR), -#ifdef CONFIG_NO_HZ_FULL_SYSIDLE - .dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE, - .dynticks_idle = ATOMIC_INIT(1), -#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ }; /* @@ -478,7 +455,7 @@ void rcu_note_context_switch(bool preempt) barrier(); /* Avoid RCU read-side critical sections leaking down. */ trace_rcu_utilization(TPS("Start context switch")); rcu_sched_qs(); - rcu_preempt_note_context_switch(); + rcu_preempt_note_context_switch(preempt); /* Load rcu_urgent_qs before other flags. */ if (!smp_load_acquire(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs))) goto out; @@ -534,9 +511,12 @@ void rcu_all_qs(void) } EXPORT_SYMBOL_GPL(rcu_all_qs); -static long blimit = 10; /* Maximum callbacks per rcu_do_batch. */ -static long qhimark = 10000; /* If this many pending, ignore blimit. */ -static long qlowmark = 100; /* Once only this many pending, use blimit. */ +#define DEFAULT_RCU_BLIMIT 10 /* Maximum callbacks per rcu_do_batch. */ +static long blimit = DEFAULT_RCU_BLIMIT; +#define DEFAULT_RCU_QHIMARK 10000 /* If this many pending, ignore blimit. */ +static long qhimark = DEFAULT_RCU_QHIMARK; +#define DEFAULT_RCU_QLOMARK 100 /* Once only this many pending, use blimit. */ +static long qlowmark = DEFAULT_RCU_QLOMARK; module_param(blimit, long, 0444); module_param(qhimark, long, 0444); @@ -559,10 +539,7 @@ module_param(jiffies_till_sched_qs, ulong, 0644); static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp); -static void force_qs_rnp(struct rcu_state *rsp, - int (*f)(struct rcu_data *rsp, bool *isidle, - unsigned long *maxj), - bool *isidle, unsigned long *maxj); +static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)); static void force_quiescent_state(struct rcu_state *rsp); static int rcu_pending(void); @@ -757,6 +734,7 @@ static int rcu_future_needs_gp(struct rcu_state *rsp) int idx = (READ_ONCE(rnp->completed) + 1) & 0x1; int *fp = &rnp->need_future_gp[idx]; + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_future_needs_gp() invoked with irqs enabled!!!"); return READ_ONCE(*fp); } @@ -768,6 +746,7 @@ static int rcu_future_needs_gp(struct rcu_state *rsp) static bool cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp) { + RCU_LOCKDEP_WARN(!irqs_disabled(), "cpu_needs_another_gp() invoked with irqs enabled!!!"); if (rcu_gp_in_progress(rsp)) return false; /* No, a grace period is already in progress. */ if (rcu_future_needs_gp(rsp)) @@ -794,6 +773,7 @@ static void rcu_eqs_enter_common(bool user) struct rcu_data *rdp; struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_eqs_enter_common() invoked with irqs enabled!!!"); trace_rcu_dyntick(TPS("Start"), rdtp->dynticks_nesting, 0); if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)) { @@ -860,14 +840,9 @@ static void rcu_eqs_enter(bool user) */ void rcu_idle_enter(void) { - unsigned long flags; - - local_irq_save(flags); + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_idle_enter() invoked with irqs enabled!!!"); rcu_eqs_enter(false); - rcu_sysidle_enter(0); - local_irq_restore(flags); } -EXPORT_SYMBOL_GPL(rcu_idle_enter); #ifdef CONFIG_NO_HZ_FULL /** @@ -880,7 +855,8 @@ EXPORT_SYMBOL_GPL(rcu_idle_enter); */ void rcu_user_enter(void) { - rcu_eqs_enter(1); + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_user_enter() invoked with irqs enabled!!!"); + rcu_eqs_enter(true); } #endif /* CONFIG_NO_HZ_FULL */ @@ -906,6 +882,11 @@ void rcu_irq_exit(void) RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); + + /* Page faults can happen in NMI handlers, so check... */ + if (rdtp->dynticks_nmi_nesting) + return; + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && rdtp->dynticks_nesting < 1); if (rdtp->dynticks_nesting <= 1) { @@ -914,7 +895,6 @@ void rcu_irq_exit(void) trace_rcu_dyntick(TPS("--="), rdtp->dynticks_nesting, rdtp->dynticks_nesting - 1); rdtp->dynticks_nesting--; } - rcu_sysidle_enter(1); } /* @@ -967,14 +947,17 @@ static void rcu_eqs_exit(bool user) struct rcu_dynticks *rdtp; long long oldval; + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_eqs_exit() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); oldval = rdtp->dynticks_nesting; WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0); if (oldval & DYNTICK_TASK_NEST_MASK) { rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE; } else { + __this_cpu_inc(disable_rcu_irq_enter); rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; rcu_eqs_exit_common(oldval, user); + __this_cpu_dec(disable_rcu_irq_enter); } } @@ -995,10 +978,8 @@ void rcu_idle_exit(void) local_irq_save(flags); rcu_eqs_exit(false); - rcu_sysidle_exit(0); local_irq_restore(flags); } -EXPORT_SYMBOL_GPL(rcu_idle_exit); #ifdef CONFIG_NO_HZ_FULL /** @@ -1039,6 +1020,11 @@ void rcu_irq_enter(void) RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_enter() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); + + /* Page faults can happen in NMI handlers, so check... */ + if (rdtp->dynticks_nmi_nesting) + return; + oldval = rdtp->dynticks_nesting; rdtp->dynticks_nesting++; WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && @@ -1047,7 +1033,6 @@ void rcu_irq_enter(void) trace_rcu_dyntick(TPS("++="), oldval, rdtp->dynticks_nesting); else rcu_eqs_exit_common(oldval, true); - rcu_sysidle_exit(1); } /* @@ -1130,22 +1115,11 @@ void rcu_nmi_exit(void) } /** - * __rcu_is_watching - are RCU read-side critical sections safe? - * - * Return true if RCU is watching the running CPU, which means that - * this CPU can safely enter RCU read-side critical sections. Unlike - * rcu_is_watching(), the caller of __rcu_is_watching() must have at - * least disabled preemption. - */ -bool notrace __rcu_is_watching(void) -{ - return !rcu_dynticks_curr_cpu_in_eqs(); -} - -/** * rcu_is_watching - see if RCU thinks that the current CPU is idle * - * If the current CPU is in its idle loop and is neither in an interrupt + * Return true if RCU is watching the running CPU, which means that this + * CPU can safely enter RCU read-side critical sections. In other words, + * if the current CPU is in its idle loop and is neither in an interrupt * or NMI handler, return true. */ bool notrace rcu_is_watching(void) @@ -1153,7 +1127,7 @@ bool notrace rcu_is_watching(void) bool ret; preempt_disable_notrace(); - ret = __rcu_is_watching(); + ret = !rcu_dynticks_curr_cpu_in_eqs(); preempt_enable_notrace(); return ret; } @@ -1237,11 +1211,9 @@ static int rcu_is_cpu_rrupt_from_idle(void) * credit them with an implicit quiescent state. Return 1 if this CPU * is in dynticks idle mode, which is an extended quiescent state. */ -static int dyntick_save_progress_counter(struct rcu_data *rdp, - bool *isidle, unsigned long *maxj) +static int dyntick_save_progress_counter(struct rcu_data *rdp) { rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks); - rcu_sysidle_check_cpu(rdp, isidle, maxj); if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) { trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, @@ -1258,8 +1230,7 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp, * idle state since the last call to dyntick_save_progress_counter() * for this same CPU, or by virtue of having been offline. */ -static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, - bool *isidle, unsigned long *maxj) +static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) { unsigned long jtsq; bool *rnhqp; @@ -1392,12 +1363,13 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp) j = jiffies; gpa = READ_ONCE(rsp->gp_activity); if (j - gpa > 2 * HZ) { - pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x %s(%d) ->state=%#lx\n", + pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x %s(%d) ->state=%#lx ->cpu=%d\n", rsp->name, j - gpa, rsp->gpnum, rsp->completed, rsp->gp_flags, gp_state_getname(rsp->gp_state), rsp->gp_state, - rsp->gp_kthread ? rsp->gp_kthread->state : ~0); + rsp->gp_kthread ? rsp->gp_kthread->state : ~0, + rsp->gp_kthread ? task_cpu(rsp->gp_kthread) : -1); if (rsp->gp_kthread) { sched_show_task(rsp->gp_kthread); wake_up_process(rsp->gp_kthread); @@ -1674,6 +1646,8 @@ void rcu_cpu_stall_reset(void) static unsigned long rcu_cbs_completed(struct rcu_state *rsp, struct rcu_node *rnp) { + lockdep_assert_held(&rnp->lock); + /* * If RCU is idle, we just wait for the next grace period. * But we can only be sure that RCU is idle if we are looking @@ -1719,6 +1693,8 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, bool ret = false; struct rcu_node *rnp_root = rcu_get_root(rdp->rsp); + lockdep_assert_held(&rnp->lock); + /* * Pick up grace-period number for new callbacks. If this * grace period is already marked as needed, return to the caller. @@ -1845,6 +1821,8 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, { bool ret = false; + lockdep_assert_held(&rnp->lock); + /* If no pending (not yet ready to invoke) callbacks, nothing to do. */ if (!rcu_segcblist_pend_cbs(&rdp->cblist)) return false; @@ -1883,6 +1861,8 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { + lockdep_assert_held(&rnp->lock); + /* If no pending (not yet ready to invoke) callbacks, nothing to do. */ if (!rcu_segcblist_pend_cbs(&rdp->cblist)) return false; @@ -1909,6 +1889,8 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, bool ret; bool need_gp; + lockdep_assert_held(&rnp->lock); + /* Handle the ends of any preceding grace periods first. */ if (rdp->completed == rnp->completed && !unlikely(READ_ONCE(rdp->gpwrap))) { @@ -2091,8 +2073,8 @@ static bool rcu_gp_init(struct rcu_state *rsp) } /* - * Helper function for wait_event_interruptible_timeout() wakeup - * at force-quiescent-state time. + * Helper function for swait_event_idle() wakeup at force-quiescent-state + * time. */ static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp) { @@ -2115,25 +2097,16 @@ static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp) */ static void rcu_gp_fqs(struct rcu_state *rsp, bool first_time) { - bool isidle = false; - unsigned long maxj; struct rcu_node *rnp = rcu_get_root(rsp); WRITE_ONCE(rsp->gp_activity, jiffies); rsp->n_force_qs++; if (first_time) { /* Collect dyntick-idle snapshots. */ - if (is_sysidle_rcu_state(rsp)) { - isidle = true; - maxj = jiffies - ULONG_MAX / 4; - } - force_qs_rnp(rsp, dyntick_save_progress_counter, - &isidle, &maxj); - rcu_sysidle_report_gp(rsp, isidle, maxj); + force_qs_rnp(rsp, dyntick_save_progress_counter); } else { /* Handle dyntick-idle and offline CPUs. */ - isidle = true; - force_qs_rnp(rsp, rcu_implicit_dynticks_qs, &isidle, &maxj); + force_qs_rnp(rsp, rcu_implicit_dynticks_qs); } /* Clear flag to prevent immediate re-entry. */ if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { @@ -2239,9 +2212,8 @@ static int __noreturn rcu_gp_kthread(void *arg) READ_ONCE(rsp->gpnum), TPS("reqwait")); rsp->gp_state = RCU_GP_WAIT_GPS; - swait_event_interruptible(rsp->gp_wq, - READ_ONCE(rsp->gp_flags) & - RCU_GP_FLAG_INIT); + swait_event_idle(rsp->gp_wq, READ_ONCE(rsp->gp_flags) & + RCU_GP_FLAG_INIT); rsp->gp_state = RCU_GP_DONE_GPS; /* Locking provides needed memory barrier. */ if (rcu_gp_init(rsp)) @@ -2272,7 +2244,7 @@ static int __noreturn rcu_gp_kthread(void *arg) READ_ONCE(rsp->gpnum), TPS("fqswait")); rsp->gp_state = RCU_GP_WAIT_FQS; - ret = swait_event_interruptible_timeout(rsp->gp_wq, + ret = swait_event_idle_timeout(rsp->gp_wq, rcu_gp_fqs_check_wake(rsp, &gf), j); rsp->gp_state = RCU_GP_DOING_FQS; /* Locking provides needed memory barriers. */ @@ -2341,6 +2313,7 @@ static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { + lockdep_assert_held(&rnp->lock); if (!rsp->gp_kthread || !cpu_needs_another_gp(rsp, rdp)) { /* * Either we have not yet spawned the grace-period @@ -2402,6 +2375,7 @@ static bool rcu_start_gp(struct rcu_state *rsp) static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) __releases(rcu_get_root(rsp)->lock) { + lockdep_assert_held(&rcu_get_root(rsp)->lock); WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS); raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(rsp), flags); @@ -2426,6 +2400,8 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, unsigned long oldmask = 0; struct rcu_node *rnp_c; + lockdep_assert_held(&rnp->lock); + /* Walk up the rcu_node hierarchy. */ for (;;) { if (!(rnp->qsmask & mask) || rnp->gpnum != gps) { @@ -2438,6 +2414,8 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, return; } WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */ + WARN_ON_ONCE(rnp->level != rcu_num_lvls - 1 && + rcu_preempt_blocked_readers_cgp(rnp)); rnp->qsmask &= ~mask; trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum, mask, rnp->qsmask, rnp->level, @@ -2486,6 +2464,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, unsigned long mask; struct rcu_node *rnp_p; + lockdep_assert_held(&rnp->lock); if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p || rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); @@ -2591,81 +2570,6 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) } /* - * Send the specified CPU's RCU callbacks to the orphanage. The - * specified CPU must be offline, and the caller must hold the - * ->orphan_lock. - */ -static void -rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, - struct rcu_node *rnp, struct rcu_data *rdp) -{ - /* No-CBs CPUs do not have orphanable callbacks. */ - if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || rcu_is_nocb_cpu(rdp->cpu)) - return; - - /* - * Orphan the callbacks. First adjust the counts. This is safe - * because _rcu_barrier() excludes CPU-hotplug operations, so it - * cannot be running now. Thus no memory barrier is required. - */ - rdp->n_cbs_orphaned += rcu_segcblist_n_cbs(&rdp->cblist); - rcu_segcblist_extract_count(&rdp->cblist, &rsp->orphan_done); - - /* - * Next, move those callbacks still needing a grace period to - * the orphanage, where some other CPU will pick them up. - * Some of the callbacks might have gone partway through a grace - * period, but that is too bad. They get to start over because we - * cannot assume that grace periods are synchronized across CPUs. - */ - rcu_segcblist_extract_pend_cbs(&rdp->cblist, &rsp->orphan_pend); - - /* - * Then move the ready-to-invoke callbacks to the orphanage, - * where some other CPU will pick them up. These will not be - * required to pass though another grace period: They are done. - */ - rcu_segcblist_extract_done_cbs(&rdp->cblist, &rsp->orphan_done); - - /* Finally, disallow further callbacks on this CPU. */ - rcu_segcblist_disable(&rdp->cblist); -} - -/* - * Adopt the RCU callbacks from the specified rcu_state structure's - * orphanage. The caller must hold the ->orphan_lock. - */ -static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags) -{ - struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); - - /* No-CBs CPUs are handled specially. */ - if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || - rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags)) - return; - - /* Do the accounting first. */ - rdp->n_cbs_adopted += rsp->orphan_done.len; - if (rsp->orphan_done.len_lazy != rsp->orphan_done.len) - rcu_idle_count_callbacks_posted(); - rcu_segcblist_insert_count(&rdp->cblist, &rsp->orphan_done); - - /* - * We do not need a memory barrier here because the only way we - * can get here if there is an rcu_barrier() in flight is if - * we are the task doing the rcu_barrier(). - */ - - /* First adopt the ready-to-invoke callbacks, then the done ones. */ - rcu_segcblist_insert_done_cbs(&rdp->cblist, &rsp->orphan_done); - WARN_ON_ONCE(rsp->orphan_done.head); - rcu_segcblist_insert_pend_cbs(&rdp->cblist, &rsp->orphan_pend); - WARN_ON_ONCE(rsp->orphan_pend.head); - WARN_ON_ONCE(rcu_segcblist_empty(&rdp->cblist) != - !rcu_segcblist_n_cbs(&rdp->cblist)); -} - -/* * Trace the fact that this CPU is going offline. */ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) @@ -2705,6 +2609,7 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) long mask; struct rcu_node *rnp = rnp_leaf; + lockdep_assert_held(&rnp->lock); if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || rnp->qsmaskinit || rcu_preempt_has_tasks(rnp)) return; @@ -2727,14 +2632,12 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) /* * The CPU has been completely removed, and some other CPU is reporting - * this fact from process context. Do the remainder of the cleanup, - * including orphaning the outgoing CPU's RCU callbacks, and also - * adopting them. There can only be one CPU hotplug operation at a time, - * so no other CPU can be attempting to update rcu_cpu_kthread_task. + * this fact from process context. Do the remainder of the cleanup. + * There can only be one CPU hotplug operation at a time, so no need for + * explicit locking. */ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) { - unsigned long flags; struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ @@ -2743,18 +2646,6 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) /* Adjust any no-longer-needed kthreads. */ rcu_boost_kthread_setaffinity(rnp, -1); - - /* Orphan the dead CPU's callbacks, and adopt them if appropriate. */ - raw_spin_lock_irqsave(&rsp->orphan_lock, flags); - rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp); - rcu_adopt_orphan_cbs(rsp, flags); - raw_spin_unlock_irqrestore(&rsp->orphan_lock, flags); - - WARN_ONCE(rcu_segcblist_n_cbs(&rdp->cblist) != 0 || - !rcu_segcblist_empty(&rdp->cblist), - "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, 1stCB=%p\n", - cpu, rcu_segcblist_n_cbs(&rdp->cblist), - rcu_segcblist_first_cb(&rdp->cblist)); } /* @@ -2895,10 +2786,7 @@ void rcu_check_callbacks(int user) * * The caller must have suppressed start of new grace periods. */ -static void force_qs_rnp(struct rcu_state *rsp, - int (*f)(struct rcu_data *rsp, bool *isidle, - unsigned long *maxj), - bool *isidle, unsigned long *maxj) +static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)) { int cpu; unsigned long flags; @@ -2937,7 +2825,7 @@ static void force_qs_rnp(struct rcu_state *rsp, for_each_leaf_node_possible_cpu(rnp, cpu) { unsigned long bit = leaf_node_cpu_bit(rnp, cpu); if ((rnp->qsmask & bit) != 0) { - if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj)) + if (f(per_cpu_ptr(rsp->rda, cpu))) mask |= bit; } } @@ -3143,9 +3031,14 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, WARN_ON_ONCE((unsigned long)head & (sizeof(void *) - 1)); if (debug_rcu_head_queue(head)) { - /* Probable double call_rcu(), so leak the callback. */ + /* + * Probable double call_rcu(), so leak the callback. + * Use rcu:rcu_callback trace event to find the previous + * time callback was passed to __call_rcu(). + */ + WARN_ONCE(1, "__call_rcu(): Double-freed CB %p->%pF()!!!\n", + head, head->func); WRITE_ONCE(head->func, rcu_leak_callback); - WARN_ONCE(1, "__call_rcu(): Leaked duplicate callback\n"); return; } head->func = func; @@ -3194,8 +3087,25 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, local_irq_restore(flags); } -/* - * Queue an RCU-sched callback for invocation after a grace period. +/** + * call_rcu_sched() - Queue an RCU for invocation after sched grace period. + * @head: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all currently executing RCU + * read-side critical sections have completed. call_rcu_sched() assumes + * that the read-side critical sections end on enabling of preemption + * or on voluntary preemption. + * RCU read-side critical sections are delimited by: + * + * - rcu_read_lock_sched() and rcu_read_unlock_sched(), OR + * - anything that disables preemption. + * + * These may be nested. + * + * See the description of call_rcu() for more detailed information on + * memory ordering guarantees. */ void call_rcu_sched(struct rcu_head *head, rcu_callback_t func) { @@ -3203,8 +3113,27 @@ void call_rcu_sched(struct rcu_head *head, rcu_callback_t func) } EXPORT_SYMBOL_GPL(call_rcu_sched); -/* - * Queue an RCU callback for invocation after a quicker grace period. +/** + * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. + * @head: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all currently executing RCU + * read-side critical sections have completed. call_rcu_bh() assumes + * that the read-side critical sections end on completion of a softirq + * handler. This means that read-side critical sections in process + * context must not be interrupted by softirqs. This interface is to be + * used when most of the read-side critical sections are in softirq context. + * RCU read-side critical sections are delimited by: + * + * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context, OR + * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context. + * + * These may be nested. + * + * See the description of call_rcu() for more detailed information on + * memory ordering guarantees. */ void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) { @@ -3280,12 +3209,6 @@ static inline int rcu_blocking_is_gp(void) * to have executed a full memory barrier during the execution of * synchronize_sched() -- even if CPU A and CPU B are the same CPU (but * again only if the system has more than one CPU). - * - * This primitive provides the guarantees made by the (now removed) - * synchronize_kernel() API. In contrast, synchronize_rcu() only - * guarantees that rcu_read_lock() sections will have completed. - * In "classic RCU", these two guarantees happen to be one and - * the same, but can differ in realtime RCU implementations. */ void synchronize_sched(void) { @@ -3562,10 +3485,11 @@ static void rcu_barrier_callback(struct rcu_head *rhp) struct rcu_state *rsp = rdp->rsp; if (atomic_dec_and_test(&rsp->barrier_cpu_count)) { - _rcu_barrier_trace(rsp, "LastCB", -1, rsp->barrier_sequence); + _rcu_barrier_trace(rsp, TPS("LastCB"), -1, + rsp->barrier_sequence); complete(&rsp->barrier_completion); } else { - _rcu_barrier_trace(rsp, "CB", -1, rsp->barrier_sequence); + _rcu_barrier_trace(rsp, TPS("CB"), -1, rsp->barrier_sequence); } } @@ -3577,9 +3501,16 @@ static void rcu_barrier_func(void *type) struct rcu_state *rsp = type; struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); - _rcu_barrier_trace(rsp, "IRQ", -1, rsp->barrier_sequence); - atomic_inc(&rsp->barrier_cpu_count); - rsp->call(&rdp->barrier_head, rcu_barrier_callback); + _rcu_barrier_trace(rsp, TPS("IRQ"), -1, rsp->barrier_sequence); + rdp->barrier_head.func = rcu_barrier_callback; + debug_rcu_head_queue(&rdp->barrier_head); + if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head, 0)) { + atomic_inc(&rsp->barrier_cpu_count); + } else { + debug_rcu_head_unqueue(&rdp->barrier_head); + _rcu_barrier_trace(rsp, TPS("IRQNQ"), -1, + rsp->barrier_sequence); + } } /* @@ -3592,14 +3523,15 @@ static void _rcu_barrier(struct rcu_state *rsp) struct rcu_data *rdp; unsigned long s = rcu_seq_snap(&rsp->barrier_sequence); - _rcu_barrier_trace(rsp, "Begin", -1, s); + _rcu_barrier_trace(rsp, TPS("Begin"), -1, s); /* Take mutex to serialize concurrent rcu_barrier() requests. */ mutex_lock(&rsp->barrier_mutex); /* Did someone else do our work for us? */ if (rcu_seq_done(&rsp->barrier_sequence, s)) { - _rcu_barrier_trace(rsp, "EarlyExit", -1, rsp->barrier_sequence); + _rcu_barrier_trace(rsp, TPS("EarlyExit"), -1, + rsp->barrier_sequence); smp_mb(); /* caller's subsequent code after above check. */ mutex_unlock(&rsp->barrier_mutex); return; @@ -3607,7 +3539,7 @@ static void _rcu_barrier(struct rcu_state *rsp) /* Mark the start of the barrier operation. */ rcu_seq_start(&rsp->barrier_sequence); - _rcu_barrier_trace(rsp, "Inc1", -1, rsp->barrier_sequence); + _rcu_barrier_trace(rsp, TPS("Inc1"), -1, rsp->barrier_sequence); /* * Initialize the count to one rather than to zero in order to @@ -3630,10 +3562,10 @@ static void _rcu_barrier(struct rcu_state *rsp) rdp = per_cpu_ptr(rsp->rda, cpu); if (rcu_is_nocb_cpu(cpu)) { if (!rcu_nocb_cpu_needs_barrier(rsp, cpu)) { - _rcu_barrier_trace(rsp, "OfflineNoCB", cpu, + _rcu_barrier_trace(rsp, TPS("OfflineNoCB"), cpu, rsp->barrier_sequence); } else { - _rcu_barrier_trace(rsp, "OnlineNoCB", cpu, + _rcu_barrier_trace(rsp, TPS("OnlineNoCB"), cpu, rsp->barrier_sequence); smp_mb__before_atomic(); atomic_inc(&rsp->barrier_cpu_count); @@ -3641,11 +3573,11 @@ static void _rcu_barrier(struct rcu_state *rsp) rcu_barrier_callback, rsp, cpu, 0); } } else if (rcu_segcblist_n_cbs(&rdp->cblist)) { - _rcu_barrier_trace(rsp, "OnlineQ", cpu, + _rcu_barrier_trace(rsp, TPS("OnlineQ"), cpu, rsp->barrier_sequence); smp_call_function_single(cpu, rcu_barrier_func, rsp, 1); } else { - _rcu_barrier_trace(rsp, "OnlineNQ", cpu, + _rcu_barrier_trace(rsp, TPS("OnlineNQ"), cpu, rsp->barrier_sequence); } } @@ -3662,7 +3594,7 @@ static void _rcu_barrier(struct rcu_state *rsp) wait_for_completion(&rsp->barrier_completion); /* Mark the end of the barrier operation. */ - _rcu_barrier_trace(rsp, "Inc2", -1, rsp->barrier_sequence); + _rcu_barrier_trace(rsp, TPS("Inc2"), -1, rsp->barrier_sequence); rcu_seq_end(&rsp->barrier_sequence); /* Other rcu_barrier() invocations can now safely proceed. */ @@ -3698,6 +3630,7 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf) long mask; struct rcu_node *rnp = rnp_leaf; + lockdep_assert_held(&rnp->lock); for (;;) { mask = rnp->grpmask; rnp = rnp->parent; @@ -3753,7 +3686,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) !init_nocb_callback_list(rdp)) rcu_segcblist_init(&rdp->cblist); /* Re-enable callbacks. */ rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; - rcu_sysidle_init_percpu_data(rdp->dynticks); rcu_dynticks_eqs_online(); raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ @@ -3764,8 +3696,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) */ rnp = rdp->mynode; raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ - if (!rdp->beenonline) - WRITE_ONCE(rsp->ncpus, READ_ONCE(rsp->ncpus) + 1); rdp->beenonline = true; /* We have now been online. */ rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */ rdp->completed = rnp->completed; @@ -3869,6 +3799,8 @@ void rcu_cpu_starting(unsigned int cpu) { unsigned long flags; unsigned long mask; + int nbits; + unsigned long oldmask; struct rcu_data *rdp; struct rcu_node *rnp; struct rcu_state *rsp; @@ -3879,9 +3811,15 @@ void rcu_cpu_starting(unsigned int cpu) mask = rdp->grpmask; raw_spin_lock_irqsave_rcu_node(rnp, flags); rnp->qsmaskinitnext |= mask; + oldmask = rnp->expmaskinitnext; rnp->expmaskinitnext |= mask; + oldmask ^= rnp->expmaskinitnext; + nbits = bitmap_weight(&oldmask, BITS_PER_LONG); + /* Allow lockless access for expedited grace periods. */ + smp_store_release(&rsp->ncpus, rsp->ncpus + nbits); /* ^^^ */ raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } + smp_mb(); /* Ensure RCU read-side usage follows above initialization. */ } #ifdef CONFIG_HOTPLUG_CPU @@ -3924,6 +3862,50 @@ void rcu_report_dead(unsigned int cpu) for_each_rcu_flavor(rsp) rcu_cleanup_dying_idle_cpu(cpu, rsp); } + +/* Migrate the dead CPU's callbacks to the current CPU. */ +static void rcu_migrate_callbacks(int cpu, struct rcu_state *rsp) +{ + unsigned long flags; + struct rcu_data *my_rdp; + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_node *rnp_root = rcu_get_root(rdp->rsp); + + if (rcu_is_nocb_cpu(cpu) || rcu_segcblist_empty(&rdp->cblist)) + return; /* No callbacks to migrate. */ + + local_irq_save(flags); + my_rdp = this_cpu_ptr(rsp->rda); + if (rcu_nocb_adopt_orphan_cbs(my_rdp, rdp, flags)) { + local_irq_restore(flags); + return; + } + raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */ + rcu_advance_cbs(rsp, rnp_root, rdp); /* Leverage recent GPs. */ + rcu_advance_cbs(rsp, rnp_root, my_rdp); /* Assign GP to pending CBs. */ + rcu_segcblist_merge(&my_rdp->cblist, &rdp->cblist); + WARN_ON_ONCE(rcu_segcblist_empty(&my_rdp->cblist) != + !rcu_segcblist_n_cbs(&my_rdp->cblist)); + raw_spin_unlock_irqrestore_rcu_node(rnp_root, flags); + WARN_ONCE(rcu_segcblist_n_cbs(&rdp->cblist) != 0 || + !rcu_segcblist_empty(&rdp->cblist), + "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, 1stCB=%p\n", + cpu, rcu_segcblist_n_cbs(&rdp->cblist), + rcu_segcblist_first_cb(&rdp->cblist)); +} + +/* + * The outgoing CPU has just passed through the dying-idle state, + * and we are being invoked from the CPU that was IPIed to continue the + * offline operation. We need to migrate the outgoing CPU's callbacks. + */ +void rcutree_migrate_callbacks(int cpu) +{ + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + rcu_migrate_callbacks(cpu, rsp); +} #endif /* @@ -4121,7 +4103,7 @@ static void __init rcu_init_geometry(void) if (rcu_fanout_leaf == RCU_FANOUT_LEAF && nr_cpu_ids == NR_CPUS) return; - pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%d\n", + pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%u\n", rcu_fanout_leaf, nr_cpu_ids); /* |