diff options
Diffstat (limited to 'kernel/rcu')
| -rw-r--r-- | kernel/rcu/sync.c | 25 | ||||
| -rw-r--r-- | kernel/rcu/tree.c | 50 | ||||
| -rw-r--r-- | kernel/rcu/tree.h | 15 | ||||
| -rw-r--r-- | kernel/rcu/tree_exp.h | 10 | ||||
| -rw-r--r-- | kernel/rcu/tree_plugin.h | 46 | ||||
| -rw-r--r-- | kernel/rcu/update.c | 9 |
6 files changed, 83 insertions, 72 deletions
diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c index 3f943efcf61c..be10036fa621 100644 --- a/kernel/rcu/sync.c +++ b/kernel/rcu/sync.c @@ -44,15 +44,15 @@ static const struct { __INIT_HELD(rcu_read_lock_held) }, [RCU_SCHED_SYNC] = { - .sync = synchronize_sched, - .call = call_rcu_sched, - .wait = rcu_barrier_sched, + .sync = synchronize_rcu, + .call = call_rcu, + .wait = rcu_barrier, __INIT_HELD(rcu_read_lock_sched_held) }, [RCU_BH_SYNC] = { - .sync = synchronize_rcu_bh, - .call = call_rcu_bh, - .wait = rcu_barrier_bh, + .sync = synchronize_rcu, + .call = call_rcu, + .wait = rcu_barrier, __INIT_HELD(rcu_read_lock_bh_held) }, }; @@ -125,8 +125,7 @@ void rcu_sync_enter(struct rcu_sync *rsp) rsp->gp_state = GP_PENDING; spin_unlock_irq(&rsp->rss_lock); - BUG_ON(need_wait && need_sync); - + WARN_ON_ONCE(need_wait && need_sync); if (need_sync) { gp_ops[rsp->gp_type].sync(); rsp->gp_state = GP_PASSED; @@ -139,7 +138,7 @@ void rcu_sync_enter(struct rcu_sync *rsp) * Nobody has yet been allowed the 'fast' path and thus we can * avoid doing any sync(). The callback will get 'dropped'. */ - BUG_ON(rsp->gp_state != GP_PASSED); + WARN_ON_ONCE(rsp->gp_state != GP_PASSED); } } @@ -166,8 +165,8 @@ static void rcu_sync_func(struct rcu_head *rhp) struct rcu_sync *rsp = container_of(rhp, struct rcu_sync, cb_head); unsigned long flags; - BUG_ON(rsp->gp_state != GP_PASSED); - BUG_ON(rsp->cb_state == CB_IDLE); + WARN_ON_ONCE(rsp->gp_state != GP_PASSED); + WARN_ON_ONCE(rsp->cb_state == CB_IDLE); spin_lock_irqsave(&rsp->rss_lock, flags); if (rsp->gp_count) { @@ -225,7 +224,7 @@ void rcu_sync_dtor(struct rcu_sync *rsp) { int cb_state; - BUG_ON(rsp->gp_count); + WARN_ON_ONCE(rsp->gp_count); spin_lock_irq(&rsp->rss_lock); if (rsp->cb_state == CB_REPLAY) @@ -235,6 +234,6 @@ void rcu_sync_dtor(struct rcu_sync *rsp) if (cb_state != CB_IDLE) { gp_ops[rsp->gp_type].wait(); - BUG_ON(rsp->cb_state != CB_IDLE); + WARN_ON_ONCE(rsp->cb_state != CB_IDLE); } } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 121f833acd04..6ec3abbe90e2 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -500,16 +500,29 @@ void rcu_force_quiescent_state(void) EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); /* + * Convert a ->gp_state value to a character string. + */ +static const char *gp_state_getname(short gs) +{ + if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names)) + return "???"; + return gp_state_names[gs]; +} + +/* * Show the state of the grace-period kthreads. */ void show_rcu_gp_kthreads(void) { int cpu; + unsigned long j; struct rcu_data *rdp; struct rcu_node *rnp; - pr_info("%s: wait state: %d ->state: %#lx\n", rcu_state.name, - rcu_state.gp_state, rcu_state.gp_kthread->state); + j = jiffies - READ_ONCE(rcu_state.gp_activity); + pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %ld\n", + rcu_state.name, gp_state_getname(rcu_state.gp_state), + rcu_state.gp_state, rcu_state.gp_kthread->state, j); rcu_for_each_node_breadth_first(rnp) { if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed)) continue; @@ -891,12 +904,12 @@ void rcu_irq_enter_irqson(void) } /** - * rcu_is_watching - see if RCU thinks that the current CPU is idle + * rcu_is_watching - see if RCU thinks that the current CPU is not idle * * 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. + * if the current CPU is not in its idle loop or is in an interrupt or + * NMI handler, return true. */ bool notrace rcu_is_watching(void) { @@ -1143,16 +1156,6 @@ static void record_gp_stall_check_time(void) } /* - * Convert a ->gp_state value to a character string. - */ -static const char *gp_state_getname(short gs) -{ - if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names)) - return "???"; - return gp_state_names[gs]; -} - -/* * Complain about starvation of grace-period kthread. */ static void rcu_check_gp_kthread_starvation(void) @@ -2032,9 +2035,9 @@ static void rcu_gp_cleanup(void) rnp = rcu_get_root(); raw_spin_lock_irq_rcu_node(rnp); /* GP before ->gp_seq update. */ - /* Declare grace period done. */ - rcu_seq_end(&rcu_state.gp_seq); + /* Declare grace period done, trace first to use old GP number. */ trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("end")); + rcu_seq_end(&rcu_state.gp_seq); rcu_state.gp_state = RCU_GP_IDLE; /* Check for GP requests since above loop. */ rdp = this_cpu_ptr(&rcu_data); @@ -2600,10 +2603,10 @@ static void force_quiescent_state(void) * This function checks for grace-period requests that fail to motivate * RCU to come out of its idle mode. */ -static void -rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp) +void +rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp, + const unsigned long gpssdelay) { - const unsigned long gpssdelay = rcu_jiffies_till_stall_check() * HZ; unsigned long flags; unsigned long j; struct rcu_node *rnp_root = rcu_get_root(); @@ -2690,7 +2693,7 @@ static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused local_irq_restore(flags); } - rcu_check_gp_start_stall(rnp, rdp); + rcu_check_gp_start_stall(rnp, rdp, rcu_jiffies_till_stall_check()); /* If there are callbacks ready, invoke them. */ if (rcu_segcblist_ready_cbs(&rdp->cblist)) @@ -2826,7 +2829,7 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, int cpu, bool lazy) * Very early boot, before rcu_init(). Initialize if needed * and then drop through to queue the callback. */ - BUG_ON(cpu != -1); + WARN_ON_ONCE(cpu != -1); WARN_ON_ONCE(!rcu_is_watching()); if (rcu_segcblist_empty(&rdp->cblist)) rcu_segcblist_init(&rdp->cblist); @@ -3485,7 +3488,8 @@ static int __init rcu_spawn_gp_kthread(void) rcu_scheduler_fully_active = 1; t = kthread_create(rcu_gp_kthread, NULL, "%s", rcu_state.name); - BUG_ON(IS_ERR(t)); + if (WARN_ONCE(IS_ERR(t), "%s: Could not start grace-period kthread, OOM is now expected behavior\n", __func__)) + return 0; rnp = rcu_get_root(); raw_spin_lock_irqsave_rcu_node(rnp, flags); rcu_state.gp_kthread = t; diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 703e19ff532d..c3e2807a834a 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -57,7 +57,7 @@ struct rcu_node { /* some rcu_state fields as well as */ /* following. */ unsigned long gp_seq; /* Track rsp->rcu_gp_seq. */ - unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed. */ + unsigned long gp_seq_needed; /* Track furthest future GP request. */ unsigned long completedqs; /* All QSes done for this node. */ unsigned long qsmask; /* CPUs or groups that need to switch in */ /* order for current grace period to proceed.*/ @@ -163,7 +163,7 @@ union rcu_noqs { struct rcu_data { /* 1) quiescent-state and grace-period handling : */ unsigned long gp_seq; /* Track rsp->rcu_gp_seq counter. */ - unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed ctr. */ + unsigned long gp_seq_needed; /* Track furthest future GP request. */ union rcu_noqs cpu_no_qs; /* No QSes yet for this CPU. */ bool core_needs_qs; /* Core waits for quiesc state. */ bool beenonline; /* CPU online at least once. */ @@ -398,17 +398,6 @@ static const char *tp_rcu_varname __used __tracepoint_string = rcu_name; #define RCU_NAME rcu_name #endif /* #else #ifdef CONFIG_TRACING */ -/* - * RCU implementation internal declarations: - */ -extern struct rcu_state rcu_sched_state; - -extern struct rcu_state rcu_bh_state; - -#ifdef CONFIG_PREEMPT_RCU -extern struct rcu_state rcu_preempt_state; -#endif /* #ifdef CONFIG_PREEMPT_RCU */ - int rcu_dynticks_snap(struct rcu_data *rdp); #ifdef CONFIG_RCU_BOOST diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 8d18c1014e2b..928fe5893a57 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -450,10 +450,12 @@ static void sync_rcu_exp_select_cpus(smp_call_func_t func) } INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus); preempt_disable(); - cpu = cpumask_next(rnp->grplo - 1, cpu_online_mask); + cpu = find_next_bit(&rnp->ffmask, BITS_PER_LONG, -1); /* If all offline, queue the work on an unbound CPU. */ - if (unlikely(cpu > rnp->grphi)) + if (unlikely(cpu > rnp->grphi - rnp->grplo)) cpu = WORK_CPU_UNBOUND; + else + cpu += rnp->grplo; queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work); preempt_enable(); rnp->exp_need_flush = true; @@ -690,8 +692,10 @@ static void sync_rcu_exp_handler(void *unused) */ if (t->rcu_read_lock_nesting > 0) { raw_spin_lock_irqsave_rcu_node(rnp, flags); - if (rnp->expmask & rdp->grpmask) + if (rnp->expmask & rdp->grpmask) { rdp->deferred_qs = true; + WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, true); + } raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 05915e536336..605ff3b06098 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -397,6 +397,11 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) return rnp->gp_tasks != NULL; } +/* Bias and limit values for ->rcu_read_lock_nesting. */ +#define RCU_NEST_BIAS INT_MAX +#define RCU_NEST_NMAX (-INT_MAX / 2) +#define RCU_NEST_PMAX (INT_MAX / 2) + /* * Preemptible RCU implementation for rcu_read_lock(). * Just increment ->rcu_read_lock_nesting, shared state will be updated @@ -405,6 +410,8 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) void __rcu_read_lock(void) { current->rcu_read_lock_nesting++; + if (IS_ENABLED(CONFIG_PROVE_LOCKING)) + WARN_ON_ONCE(current->rcu_read_lock_nesting > RCU_NEST_PMAX); barrier(); /* critical section after entry code. */ } EXPORT_SYMBOL_GPL(__rcu_read_lock); @@ -424,20 +431,18 @@ void __rcu_read_unlock(void) --t->rcu_read_lock_nesting; } else { barrier(); /* critical section before exit code. */ - t->rcu_read_lock_nesting = INT_MIN; + t->rcu_read_lock_nesting = -RCU_NEST_BIAS; barrier(); /* assign before ->rcu_read_unlock_special load */ if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s))) rcu_read_unlock_special(t); barrier(); /* ->rcu_read_unlock_special load before assign */ t->rcu_read_lock_nesting = 0; } -#ifdef CONFIG_PROVE_LOCKING - { - int rrln = READ_ONCE(t->rcu_read_lock_nesting); + if (IS_ENABLED(CONFIG_PROVE_LOCKING)) { + int rrln = t->rcu_read_lock_nesting; - WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); + WARN_ON_ONCE(rrln < 0 && rrln > RCU_NEST_NMAX); } -#endif /* #ifdef CONFIG_PROVE_LOCKING */ } EXPORT_SYMBOL_GPL(__rcu_read_unlock); @@ -597,7 +602,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) */ static bool rcu_preempt_need_deferred_qs(struct task_struct *t) { - return (this_cpu_ptr(&rcu_data)->deferred_qs || + return (__this_cpu_read(rcu_data.deferred_qs) || READ_ONCE(t->rcu_read_unlock_special.s)) && t->rcu_read_lock_nesting <= 0; } @@ -617,11 +622,11 @@ static void rcu_preempt_deferred_qs(struct task_struct *t) if (!rcu_preempt_need_deferred_qs(t)) return; if (couldrecurse) - t->rcu_read_lock_nesting -= INT_MIN; + t->rcu_read_lock_nesting -= RCU_NEST_BIAS; local_irq_save(flags); rcu_preempt_deferred_qs_irqrestore(t, flags); if (couldrecurse) - t->rcu_read_lock_nesting += INT_MIN; + t->rcu_read_lock_nesting += RCU_NEST_BIAS; } /* @@ -642,13 +647,21 @@ 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) && - t->rcu_read_unlock_special.b.blocked) { + if (preempt_bh_were_disabled || irqs_were_disabled) { + WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, false); /* Need to defer quiescent state until everything is enabled. */ - raise_softirq_irqoff(RCU_SOFTIRQ); + if (irqs_were_disabled) { + /* Enabling irqs does not reschedule, so... */ + raise_softirq_irqoff(RCU_SOFTIRQ); + } else { + /* Enabling BH or preempt does reschedule, so... */ + set_tsk_need_resched(current); + set_preempt_need_resched(); + } local_irq_restore(flags); return; } + WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, false); rcu_preempt_deferred_qs_irqrestore(t, flags); } @@ -1464,7 +1477,8 @@ static void __init rcu_spawn_boost_kthreads(void) for_each_possible_cpu(cpu) per_cpu(rcu_cpu_has_work, cpu) = 0; - BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); + if (WARN_ONCE(smpboot_register_percpu_thread(&rcu_cpu_thread_spec), "%s: Could not start rcub kthread, OOM is now expected behavior\n", __func__)) + return; rcu_for_each_leaf_node(rnp) (void)rcu_spawn_one_boost_kthread(rnp); } @@ -2322,7 +2336,8 @@ static int rcu_nocb_kthread(void *arg) tail = rdp->nocb_follower_tail; rdp->nocb_follower_tail = &rdp->nocb_follower_head; raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); - BUG_ON(!list); + if (WARN_ON_ONCE(!list)) + continue; trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WokeNonEmpty")); /* Each pass through the following loop invokes a callback. */ @@ -2495,7 +2510,8 @@ static void rcu_spawn_one_nocb_kthread(int cpu) /* Spawn the kthread for this CPU. */ t = kthread_run(rcu_nocb_kthread, rdp_spawn, "rcuo%c/%d", rcu_state.abbr, cpu); - BUG_ON(IS_ERR(t)); + if (WARN_ONCE(IS_ERR(t), "%s: Could not start rcuo kthread, OOM is now expected behavior\n", __func__)) + return; WRITE_ONCE(rdp_spawn->nocb_kthread, t); } diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index f203b94f6b5b..1971869c4072 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -335,8 +335,7 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, /* Initialize and register callbacks for each crcu_array element. */ for (i = 0; i < n; i++) { if (checktiny && - (crcu_array[i] == call_rcu || - crcu_array[i] == call_rcu_bh)) { + (crcu_array[i] == call_rcu)) { might_sleep(); continue; } @@ -352,8 +351,7 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, /* Wait for all callbacks to be invoked. */ for (i = 0; i < n; i++) { if (checktiny && - (crcu_array[i] == call_rcu || - crcu_array[i] == call_rcu_bh)) + (crcu_array[i] == call_rcu)) continue; for (j = 0; j < i; j++) if (crcu_array[j] == crcu_array[i]) @@ -822,7 +820,8 @@ static int __init rcu_spawn_tasks_kthread(void) struct task_struct *t; t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread"); - BUG_ON(IS_ERR(t)); + if (WARN_ONCE(IS_ERR(t), "%s: Could not start Tasks-RCU grace-period kthread, OOM is now expected behavior\n", __func__)) + return 0; smp_mb(); /* Ensure others see full kthread. */ WRITE_ONCE(rcu_tasks_kthread_ptr, t); return 0; |
