1 files changed, 157 insertions, 39 deletions

diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 05d3e1375e4c..af7c19439f4e 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -28,6 +28,8 @@ typedef void (*postgp_func_t)(struct rcu_tasks *rtp);
  * @kthread_ptr: This flavor's grace-period/callback-invocation kthread.
  * @gp_func: This flavor's grace-period-wait function.
  * @gp_state: Grace period's most recent state transition (debugging).
+ * @gp_sleep: Per-grace-period sleep to prevent CPU-bound looping.
+ * @init_fract: Initial backoff sleep interval.
  * @gp_jiffies: Time of last @gp_state transition.
  * @gp_start: Most recent grace-period start in jiffies.
  * @n_gps: Number of grace periods completed since boot.
@@ -48,6 +50,8 @@ struct rcu_tasks {
 	struct wait_queue_head cbs_wq;
 	raw_spinlock_t cbs_lock;
 	int gp_state;
+	int gp_sleep;
+	int init_fract;
 	unsigned long gp_jiffies;
 	unsigned long gp_start;
 	unsigned long n_gps;
@@ -81,7 +85,7 @@ static struct rcu_tasks rt_name =					\
 DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu);
 
 /* Avoid IPIing CPUs early in the grace period. */
-#define RCU_TASK_IPI_DELAY (HZ / 2)
+#define RCU_TASK_IPI_DELAY (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) ? HZ / 2 : 0)
 static int rcu_task_ipi_delay __read_mostly = RCU_TASK_IPI_DELAY;
 module_param(rcu_task_ipi_delay, int, 0644);
 
@@ -231,13 +235,13 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 			cond_resched();
 		}
 		/* Paranoid sleep to keep this from entering a tight loop */
-		schedule_timeout_idle(HZ/10);
+		schedule_timeout_idle(rtp->gp_sleep);
 
 		set_tasks_gp_state(rtp, RTGS_WAIT_CBS);
 	}
 }
 
-/* Spawn RCU-tasks grace-period kthread, e.g., at core_initcall() time. */
+/* Spawn RCU-tasks grace-period kthread. */
 static void __init rcu_spawn_tasks_kthread_generic(struct rcu_tasks *rtp)
 {
 	struct task_struct *t;
@@ -286,7 +290,7 @@ static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s)
 		".C"[!!data_race(rtp->cbs_head)],
 		s);
 }
-#endif /* #ifndef CONFIG_TINY_RCU */
+#endif // #ifndef CONFIG_TINY_RCU
 
 static void exit_tasks_rcu_finish_trace(struct task_struct *t);
 
@@ -329,23 +333,20 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
 	 */
 	lastreport = jiffies;
 
-	/* Start off with HZ/10 wait and slowly back off to 1 HZ wait. */
-	fract = 10;
+	// Start off with initial wait and slowly back off to 1 HZ wait.
+	fract = rtp->init_fract;
 
-	for (;;) {
+	while (!list_empty(&holdouts)) {
 		bool firstreport;
 		bool needreport;
 		int rtst;
 
-		if (list_empty(&holdouts))
-			break;
-
 		/* Slowly back off waiting for holdouts */
 		set_tasks_gp_state(rtp, RTGS_WAIT_SCAN_HOLDOUTS);
-		schedule_timeout_idle(HZ/fract);
+		schedule_timeout_idle(fract);
 
-		if (fract > 1)
-			fract--;
+		if (fract < HZ)
+			fract++;
 
 		rtst = READ_ONCE(rcu_task_stall_timeout);
 		needreport = rtst > 0 && time_after(jiffies, lastreport + rtst);
@@ -553,6 +554,8 @@ EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
 
 static int __init rcu_spawn_tasks_kthread(void)
 {
+	rcu_tasks.gp_sleep = HZ / 10;
+	rcu_tasks.init_fract = HZ / 10;
 	rcu_tasks.pregp_func = rcu_tasks_pregp_step;
 	rcu_tasks.pertask_func = rcu_tasks_pertask;
 	rcu_tasks.postscan_func = rcu_tasks_postscan;
@@ -561,14 +564,14 @@ static int __init rcu_spawn_tasks_kthread(void)
 	rcu_spawn_tasks_kthread_generic(&rcu_tasks);
 	return 0;
 }
-core_initcall(rcu_spawn_tasks_kthread);
 
-#ifndef CONFIG_TINY_RCU
-static void show_rcu_tasks_classic_gp_kthread(void)
+#if !defined(CONFIG_TINY_RCU)
+void show_rcu_tasks_classic_gp_kthread(void)
 {
 	show_rcu_tasks_generic_gp_kthread(&rcu_tasks, "");
 }
-#endif /* #ifndef CONFIG_TINY_RCU */
+EXPORT_SYMBOL_GPL(show_rcu_tasks_classic_gp_kthread);
+#endif // !defined(CONFIG_TINY_RCU)
 
 /* Do the srcu_read_lock() for the above synchronize_srcu().  */
 void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu)
@@ -590,7 +593,6 @@ void exit_tasks_rcu_finish(void) __releases(&tasks_rcu_exit_srcu)
 }
 
 #else /* #ifdef CONFIG_TASKS_RCU */
-static inline void show_rcu_tasks_classic_gp_kthread(void) { }
 void exit_tasks_rcu_start(void) { }
 void exit_tasks_rcu_finish(void) { exit_tasks_rcu_finish_trace(current); }
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
@@ -685,21 +687,19 @@ EXPORT_SYMBOL_GPL(rcu_barrier_tasks_rude);
 
 static int __init rcu_spawn_tasks_rude_kthread(void)
 {
+	rcu_tasks_rude.gp_sleep = HZ / 10;
 	rcu_spawn_tasks_kthread_generic(&rcu_tasks_rude);
 	return 0;
 }
-core_initcall(rcu_spawn_tasks_rude_kthread);
 
-#ifndef CONFIG_TINY_RCU
-static void show_rcu_tasks_rude_gp_kthread(void)
+#if !defined(CONFIG_TINY_RCU)
+void show_rcu_tasks_rude_gp_kthread(void)
 {
 	show_rcu_tasks_generic_gp_kthread(&rcu_tasks_rude, "");
 }
-#endif /* #ifndef CONFIG_TINY_RCU */
-
-#else /* #ifdef CONFIG_TASKS_RUDE_RCU */
-static void show_rcu_tasks_rude_gp_kthread(void) {}
-#endif /* #else #ifdef CONFIG_TASKS_RUDE_RCU */
+EXPORT_SYMBOL_GPL(show_rcu_tasks_rude_gp_kthread);
+#endif // !defined(CONFIG_TINY_RCU)
+#endif /* #ifdef CONFIG_TASKS_RUDE_RCU */
 
 ////////////////////////////////////////////////////////////////////////
 //
@@ -745,9 +745,9 @@ static DEFINE_PER_CPU(bool, trc_ipi_to_cpu);
 
 // The number of detections of task quiescent state relying on
 // heavyweight readers executing explicit memory barriers.
-unsigned long n_heavy_reader_attempts;
-unsigned long n_heavy_reader_updates;
-unsigned long n_heavy_reader_ofl_updates;
+static unsigned long n_heavy_reader_attempts;
+static unsigned long n_heavy_reader_updates;
+static unsigned long n_heavy_reader_ofl_updates;
 
 void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func);
 DEFINE_RCU_TASKS(rcu_tasks_trace, rcu_tasks_wait_gp, call_rcu_tasks_trace,
@@ -821,6 +821,12 @@ static void trc_read_check_handler(void *t_in)
 		WRITE_ONCE(t->trc_reader_checked, true);
 		goto reset_ipi;
 	}
+	// If we are racing with an rcu_read_unlock_trace(), try again later.
+	if (unlikely(t->trc_reader_nesting < 0)) {
+		if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end)))
+			wake_up(&trc_wait);
+		goto reset_ipi;
+	}
 	WRITE_ONCE(t->trc_reader_checked, true);
 
 	// Get here if the task is in a read-side critical section.  Set
@@ -911,7 +917,8 @@ static void trc_wait_for_one_reader(struct task_struct *t,
 
 	// If currently running, send an IPI, either way, add to list.
 	trc_add_holdout(t, bhp);
-	if (task_curr(t) && time_after(jiffies, rcu_tasks_trace.gp_start + rcu_task_ipi_delay)) {
+	if (task_curr(t) &&
+	    time_after(jiffies + 1, rcu_tasks_trace.gp_start + rcu_task_ipi_delay)) {
 		// The task is currently running, so try IPIing it.
 		cpu = task_cpu(t);
 
@@ -959,6 +966,11 @@ static void rcu_tasks_trace_pregp_step(void)
 static void rcu_tasks_trace_pertask(struct task_struct *t,
 				    struct list_head *hop)
 {
+	// During early boot when there is only the one boot CPU, there
+	// is no idle task for the other CPUs. Just return.
+	if (unlikely(t == NULL))
+		return;
+
 	WRITE_ONCE(t->trc_reader_special.b.need_qs, false);
 	WRITE_ONCE(t->trc_reader_checked, false);
 	t->trc_ipi_to_cpu = -1;
@@ -1072,15 +1084,17 @@ static void rcu_tasks_trace_postgp(struct rcu_tasks *rtp)
 		if (ret)
 			break;  // Count reached zero.
 		// Stall warning time, so make a list of the offenders.
+		rcu_read_lock();
 		for_each_process_thread(g, t)
 			if (READ_ONCE(t->trc_reader_special.b.need_qs))
 				trc_add_holdout(t, &holdouts);
+		rcu_read_unlock();
 		firstreport = true;
-		list_for_each_entry_safe(t, g, &holdouts, trc_holdout_list)
-			if (READ_ONCE(t->trc_reader_special.b.need_qs)) {
+		list_for_each_entry_safe(t, g, &holdouts, trc_holdout_list) {
+			if (READ_ONCE(t->trc_reader_special.b.need_qs))
 				show_stalled_task_trace(t, &firstreport);
-				trc_del_holdout(t);
-			}
+			trc_del_holdout(t); // Release task_struct reference.
+		}
 		if (firstreport)
 			pr_err("INFO: rcu_tasks_trace detected stalls? (Counter/taskslist mismatch?)\n");
 		show_stalled_ipi_trace();
@@ -1163,6 +1177,17 @@ EXPORT_SYMBOL_GPL(rcu_barrier_tasks_trace);
 
 static int __init rcu_spawn_tasks_trace_kthread(void)
 {
+	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) {
+		rcu_tasks_trace.gp_sleep = HZ / 10;
+		rcu_tasks_trace.init_fract = HZ / 10;
+	} else {
+		rcu_tasks_trace.gp_sleep = HZ / 200;
+		if (rcu_tasks_trace.gp_sleep <= 0)
+			rcu_tasks_trace.gp_sleep = 1;
+		rcu_tasks_trace.init_fract = HZ / 200;
+		if (rcu_tasks_trace.init_fract <= 0)
+			rcu_tasks_trace.init_fract = 1;
+	}
 	rcu_tasks_trace.pregp_func = rcu_tasks_trace_pregp_step;
 	rcu_tasks_trace.pertask_func = rcu_tasks_trace_pertask;
 	rcu_tasks_trace.postscan_func = rcu_tasks_trace_postscan;
@@ -1171,10 +1196,9 @@ static int __init rcu_spawn_tasks_trace_kthread(void)
 	rcu_spawn_tasks_kthread_generic(&rcu_tasks_trace);
 	return 0;
 }
-core_initcall(rcu_spawn_tasks_trace_kthread);
 
-#ifndef CONFIG_TINY_RCU
-static void show_rcu_tasks_trace_gp_kthread(void)
+#if !defined(CONFIG_TINY_RCU)
+void show_rcu_tasks_trace_gp_kthread(void)
 {
 	char buf[64];
 
@@ -1184,11 +1208,11 @@ static void show_rcu_tasks_trace_gp_kthread(void)
 		data_race(n_heavy_reader_attempts));
 	show_rcu_tasks_generic_gp_kthread(&rcu_tasks_trace, buf);
 }
-#endif /* #ifndef CONFIG_TINY_RCU */
+EXPORT_SYMBOL_GPL(show_rcu_tasks_trace_gp_kthread);
+#endif // !defined(CONFIG_TINY_RCU)
 
 #else /* #ifdef CONFIG_TASKS_TRACE_RCU */
 static void exit_tasks_rcu_finish_trace(struct task_struct *t) { }
-static inline void show_rcu_tasks_trace_gp_kthread(void) {}
 #endif /* #else #ifdef CONFIG_TASKS_TRACE_RCU */
 
 #ifndef CONFIG_TINY_RCU
@@ -1200,6 +1224,100 @@ void show_rcu_tasks_gp_kthreads(void)
 }
 #endif /* #ifndef CONFIG_TINY_RCU */
 
+#ifdef CONFIG_PROVE_RCU
+struct rcu_tasks_test_desc {
+	struct rcu_head rh;
+	const char *name;
+	bool notrun;
+};
+
+static struct rcu_tasks_test_desc tests[] = {
+	{
+		.name = "call_rcu_tasks()",
+		/* If not defined, the test is skipped. */
+		.notrun = !IS_ENABLED(CONFIG_TASKS_RCU),
+	},
+	{
+		.name = "call_rcu_tasks_rude()",
+		/* If not defined, the test is skipped. */
+		.notrun = !IS_ENABLED(CONFIG_TASKS_RUDE_RCU),
+	},
+	{
+		.name = "call_rcu_tasks_trace()",
+		/* If not defined, the test is skipped. */
+		.notrun = !IS_ENABLED(CONFIG_TASKS_TRACE_RCU)
+	}
+};
+
+static void test_rcu_tasks_callback(struct rcu_head *rhp)
+{
+	struct rcu_tasks_test_desc *rttd =
+		container_of(rhp, struct rcu_tasks_test_desc, rh);
+
+	pr_info("Callback from %s invoked.\n", rttd->name);
+
+	rttd->notrun = true;
+}
+
+static void rcu_tasks_initiate_self_tests(void)
+{
+	pr_info("Running RCU-tasks wait API self tests\n");
+#ifdef CONFIG_TASKS_RCU
+	synchronize_rcu_tasks();
+	call_rcu_tasks(&tests[0].rh, test_rcu_tasks_callback);
+#endif
+
+#ifdef CONFIG_TASKS_RUDE_RCU
+	synchronize_rcu_tasks_rude();
+	call_rcu_tasks_rude(&tests[1].rh, test_rcu_tasks_callback);
+#endif
+
+#ifdef CONFIG_TASKS_TRACE_RCU
+	synchronize_rcu_tasks_trace();
+	call_rcu_tasks_trace(&tests[2].rh, test_rcu_tasks_callback);
+#endif
+}
+
+static int rcu_tasks_verify_self_tests(void)
+{
+	int ret = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		if (!tests[i].notrun) {		// still hanging.
+			pr_err("%s has been failed.\n", tests[i].name);
+			ret = -1;
+		}
+	}
+
+	if (ret)
+		WARN_ON(1);
+
+	return ret;
+}
+late_initcall(rcu_tasks_verify_self_tests);
+#else /* #ifdef CONFIG_PROVE_RCU */
+static void rcu_tasks_initiate_self_tests(void) { }
+#endif /* #else #ifdef CONFIG_PROVE_RCU */
+
+void __init rcu_init_tasks_generic(void)
+{
+#ifdef CONFIG_TASKS_RCU
+	rcu_spawn_tasks_kthread();
+#endif
+
+#ifdef CONFIG_TASKS_RUDE_RCU
+	rcu_spawn_tasks_rude_kthread();
+#endif
+
+#ifdef CONFIG_TASKS_TRACE_RCU
+	rcu_spawn_tasks_trace_kthread();
+#endif
+
+	// Run the self-tests.
+	rcu_tasks_initiate_self_tests();
+}
+
 #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
 static inline void rcu_tasks_bootup_oddness(void) {}
 void show_rcu_tasks_gp_kthreads(void) {}