1 files changed, 72 insertions, 99 deletions

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index c5b45c2f68a1..e3142ee35fc6 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -330,7 +330,7 @@ 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,
@@ -460,7 +460,7 @@ 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;
@@ -486,6 +486,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 	t->rcu_read_unlock_special.s = 0;
 	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 {
@@ -556,16 +557,16 @@ 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.rtmutex);
-
 		/*
 		 * 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);
 	}
@@ -580,7 +581,7 @@ 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.cpu_no_qs.b.exp) ||
 		READ_ONCE(t->rcu_read_unlock_special.s)) &&
@@ -594,7 +595,7 @@ 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;
 
@@ -640,7 +641,8 @@ static void rcu_read_unlock_special(struct task_struct *t)
 
 		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) ||
+			   (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.
@@ -660,7 +662,13 @@ static void rcu_read_unlock_special(struct task_struct *t)
 			    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);
 			}
@@ -711,9 +719,6 @@ static void rcu_flavor_sched_clock_irq(int user)
 	struct task_struct *t = current;
 
 	lockdep_assert_irqs_disabled();
-	if (user || rcu_is_cpu_rrupt_from_idle()) {
-		rcu_note_voluntary_context_switch(current);
-	}
 	if (rcu_preempt_depth() > 0 ||
 	    (preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK))) {
 		/* No QS, force context switch if deferred. */
@@ -773,7 +778,6 @@ 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;
 
@@ -797,9 +801,8 @@ 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);
 	}
@@ -819,6 +822,7 @@ void rcu_read_unlock_strict(void)
 	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);
 }
@@ -864,7 +868,7 @@ 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();
@@ -894,8 +898,8 @@ 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);
@@ -921,16 +925,19 @@ 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;
 }
 
-// Except that we do need to respond to a request by an expedited grace
-// period for a quiescent state from this CPU.  Note that requests from
-// tasks are handled when removing the task from the blocked-tasks list
-// below.
-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);
 
@@ -967,7 +974,6 @@ static void rcu_flavor_sched_clock_irq(int user)
 		 * neither access nor modify, at least not while the
 		 * corresponding CPU is online.
 		 */
-
 		rcu_qs();
 	}
 }
@@ -996,12 +1002,34 @@ 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
@@ -1123,7 +1151,8 @@ 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;
 	}
@@ -1131,7 +1160,8 @@ 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);
@@ -1142,15 +1172,6 @@ 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)
 
 /*
@@ -1172,15 +1193,14 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
 	struct sched_param sp;
 	struct task_struct *t;
 
+	mutex_lock(&rnp->boost_kthread_mutex);
 	if (rnp->boost_kthread_task || !rcu_scheduler_fully_active)
-		return;
-
-	rcu_state.boost = 1;
+		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;
@@ -1188,6 +1208,9 @@ 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);
 }
 
 /*
@@ -1210,29 +1233,22 @@ 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);
 	for_each_leaf_node_possible_cpu(rnp, cpu)
 		if ((mask & leaf_node_cpu_bit(rnp, cpu)) &&
 		    cpu != outgoingcpu)
 			cpumask_set_cpu(cpu, cm);
-	cpumask_and(cm, cm, housekeeping_cpumask(HK_FLAG_RCU));
-	if (cpumask_weight(cm) == 0)
-		cpumask_copy(cm, housekeeping_cpumask(HK_FLAG_RCU));
+	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)
-		if (rcu_rnp_online_cpus(rnp))
-			rcu_spawn_one_boost_kthread(rnp);
-}
-
 #else /* #ifdef CONFIG_RCU_BOOST */
 
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
@@ -1241,11 +1257,6 @@ 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)
 {
 }
@@ -1258,10 +1269,6 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
 {
 }
 
-static void __init rcu_spawn_boost_kthreads(void)
-{
-}
-
 #endif /* #else #ifdef CONFIG_RCU_BOOST */
 
 /*
@@ -1291,39 +1298,5 @@ 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 __always_inline void 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 __always_inline void 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 __always_inline void rcu_dynticks_task_trace_enter(void)
-{
-#ifdef CONFIG_TASKS_TRACE_RCU
-	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
-		current->trc_reader_special.b.need_mb = true;
-#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
-}
-
-/* Turn off heavyweight RCU tasks trace readers on idle/user exit. */
-static __always_inline void rcu_dynticks_task_trace_exit(void)
-{
-#ifdef CONFIG_TASKS_TRACE_RCU
-	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
-		current->trc_reader_special.b.need_mb = false;
-#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
+	housekeeping_affine(current, HK_TYPE_RCU);
 }