Merge branch 'rtt-speedup.2020.09.16a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into bpf-next

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Author: Alexei Starovoitov

include/linux/rcupdate_trace.h

@@ -50,6 +50,7 @@ static inline void rcu_read_lock_trace(void)
 	struct task_struct *t = current;
 
 	WRITE_ONCE(t->trc_reader_nesting, READ_ONCE(t->trc_reader_nesting) + 1);
+	barrier();
 	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) &&
 	    t->trc_reader_special.b.need_mb)
 		smp_mb(); // Pairs with update-side barriers
@@ -72,6 +73,9 @@ static inline void rcu_read_unlock_trace(void)
 
 	rcu_lock_release(&rcu_trace_lock_map);
 	nesting = READ_ONCE(t->trc_reader_nesting) - 1;
+	barrier(); // Critical section before disabling.
+	// Disable IPI-based setting of .need_qs.
+	WRITE_ONCE(t->trc_reader_nesting, INT_MIN);
 	if (likely(!READ_ONCE(t->trc_reader_special.s)) || nesting) {
 		WRITE_ONCE(t->trc_reader_nesting, nesting);
 		return;  // We assume shallow reader nesting.

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);
 
@@ -231,7 +235,7 @@ 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);
 	}
@@ -329,8 +333,10 @@ 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;
+	if (fract > HZ)
+		fract = HZ;
 
 	for (;;) {
 		bool firstreport;
@@ -553,6 +559,8 @@ EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
 
 static int __init rcu_spawn_tasks_kthread(void)
 {
+	rcu_tasks.gp_sleep = HZ / 10;
+	rcu_tasks.init_fract = 10;
 	rcu_tasks.pregp_func = rcu_tasks_pregp_step;
 	rcu_tasks.pertask_func = rcu_tasks_pertask;
 	rcu_tasks.postscan_func = rcu_tasks_postscan;
@@ -685,6 +693,7 @@ 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;
 }
@@ -745,9 +754,9 @@ 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 +830,12 @@ 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 +926,8 @@ 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);
 
@@ -1072,15 +1088,17 @@ 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 +1181,17 @@ 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 = 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 / 5;
+		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;