1 files changed, 104 insertions, 103 deletions

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 3c90dad00d3c..334eaf4d561f 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -33,10 +33,6 @@ static inline bool rcu_current_is_nocb_kthread(struct rcu_data *rdp)
 	return false;
 }
 
-static inline bool rcu_running_nocb_timer(struct rcu_data *rdp)
-{
-	return (timer_curr_running(&rdp->nocb_timer) && !in_irq());
-}
 #else
 static inline int rcu_lockdep_is_held_nocb(struct rcu_data *rdp)
 {
@@ -48,11 +44,6 @@ static inline bool rcu_current_is_nocb_kthread(struct rcu_data *rdp)
 	return false;
 }
 
-static inline bool rcu_running_nocb_timer(struct rcu_data *rdp)
-{
-	return false;
-}
-
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
 static bool rcu_rdp_is_offloaded(struct rcu_data *rdp)
@@ -72,8 +63,7 @@ static bool rcu_rdp_is_offloaded(struct rcu_data *rdp)
 		  rcu_lockdep_is_held_nocb(rdp) ||
 		  (rdp == this_cpu_ptr(&rcu_data) &&
 		   !(IS_ENABLED(CONFIG_PREEMPT_COUNT) && preemptible())) ||
-		  rcu_current_is_nocb_kthread(rdp) ||
-		  rcu_running_nocb_timer(rdp)),
+		  rcu_current_is_nocb_kthread(rdp)),
 		"Unsafe read of RCU_NOCB offloaded state"
 	);
 
@@ -1521,13 +1511,10 @@ static void rcu_cleanup_after_idle(void)
 static int __init rcu_nocb_setup(char *str)
 {
 	alloc_bootmem_cpumask_var(&rcu_nocb_mask);
-	if (!strcasecmp(str, "all"))		/* legacy: use "0-N" instead */
+	if (cpulist_parse(str, rcu_nocb_mask)) {
+		pr_warn("rcu_nocbs= bad CPU range, all CPUs set\n");
 		cpumask_setall(rcu_nocb_mask);
-	else
-		if (cpulist_parse(str, rcu_nocb_mask)) {
-			pr_warn("rcu_nocbs= bad CPU range, all CPUs set\n");
-			cpumask_setall(rcu_nocb_mask);
-		}
+	}
 	return 1;
 }
 __setup("rcu_nocbs=", rcu_nocb_setup);
@@ -1678,56 +1665,78 @@ bool rcu_is_nocb_cpu(int cpu)
 	return false;
 }
 
-/*
- * Kick the GP kthread for this NOCB group.  Caller holds ->nocb_lock
- * and this function releases it.
- */
-static bool wake_nocb_gp(struct rcu_data *rdp, bool force,
-			 unsigned long flags)
-	__releases(rdp->nocb_lock)
+static bool __wake_nocb_gp(struct rcu_data *rdp_gp,
+			   struct rcu_data *rdp,
+			   bool force, unsigned long flags)
+	__releases(rdp_gp->nocb_gp_lock)
 {
 	bool needwake = false;
-	struct rcu_data *rdp_gp = rdp->nocb_gp_rdp;
 
-	lockdep_assert_held(&rdp->nocb_lock);
 	if (!READ_ONCE(rdp_gp->nocb_gp_kthread)) {
-		rcu_nocb_unlock_irqrestore(rdp, flags);
+		raw_spin_unlock_irqrestore(&rdp_gp->nocb_gp_lock, flags);
 		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
 				    TPS("AlreadyAwake"));
 		return false;
 	}
 
-	if (READ_ONCE(rdp->nocb_defer_wakeup) > RCU_NOCB_WAKE_NOT) {
-		WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT);
-		del_timer(&rdp->nocb_timer);
+	if (rdp_gp->nocb_defer_wakeup > RCU_NOCB_WAKE_NOT) {
+		WRITE_ONCE(rdp_gp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT);
+		del_timer(&rdp_gp->nocb_timer);
 	}
-	rcu_nocb_unlock_irqrestore(rdp, flags);
-	raw_spin_lock_irqsave(&rdp_gp->nocb_gp_lock, flags);
+
 	if (force || READ_ONCE(rdp_gp->nocb_gp_sleep)) {
 		WRITE_ONCE(rdp_gp->nocb_gp_sleep, false);
 		needwake = true;
-		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("DoWake"));
 	}
 	raw_spin_unlock_irqrestore(&rdp_gp->nocb_gp_lock, flags);
-	if (needwake)
+	if (needwake) {
+		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("DoWake"));
 		wake_up_process(rdp_gp->nocb_gp_kthread);
+	}
 
 	return needwake;
 }
 
 /*
+ * Kick the GP kthread for this NOCB group.
+ */
+static bool wake_nocb_gp(struct rcu_data *rdp, bool force)
+{
+	unsigned long flags;
+	struct rcu_data *rdp_gp = rdp->nocb_gp_rdp;
+
+	raw_spin_lock_irqsave(&rdp_gp->nocb_gp_lock, flags);
+	return __wake_nocb_gp(rdp_gp, rdp, force, flags);
+}
+
+/*
  * Arrange to wake the GP kthread for this NOCB group at some future
  * time when it is safe to do so.
  */
 static void wake_nocb_gp_defer(struct rcu_data *rdp, int waketype,
 			       const char *reason)
 {
-	if (rdp->nocb_defer_wakeup == RCU_NOCB_WAKE_OFF)
-		return;
-	if (rdp->nocb_defer_wakeup == RCU_NOCB_WAKE_NOT)
-		mod_timer(&rdp->nocb_timer, jiffies + 1);
-	if (rdp->nocb_defer_wakeup < waketype)
-		WRITE_ONCE(rdp->nocb_defer_wakeup, waketype);
+	unsigned long flags;
+	struct rcu_data *rdp_gp = rdp->nocb_gp_rdp;
+
+	raw_spin_lock_irqsave(&rdp_gp->nocb_gp_lock, flags);
+
+	/*
+	 * Bypass wakeup overrides previous deferments. In case
+	 * of callback storm, no need to wake up too early.
+	 */
+	if (waketype == RCU_NOCB_WAKE_BYPASS) {
+		mod_timer(&rdp_gp->nocb_timer, jiffies + 2);
+		WRITE_ONCE(rdp_gp->nocb_defer_wakeup, waketype);
+	} else {
+		if (rdp_gp->nocb_defer_wakeup < RCU_NOCB_WAKE)
+			mod_timer(&rdp_gp->nocb_timer, jiffies + 1);
+		if (rdp_gp->nocb_defer_wakeup < waketype)
+			WRITE_ONCE(rdp_gp->nocb_defer_wakeup, waketype);
+	}
+
+	raw_spin_unlock_irqrestore(&rdp_gp->nocb_gp_lock, flags);
+
 	trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, reason);
 }
 
@@ -1954,13 +1963,14 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
 		rdp->qlen_last_fqs_check = len;
 		if (!irqs_disabled_flags(flags)) {
 			/* ... if queue was empty ... */
-			wake_nocb_gp(rdp, false, flags);
+			rcu_nocb_unlock_irqrestore(rdp, flags);
+			wake_nocb_gp(rdp, false);
 			trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
 					    TPS("WakeEmpty"));
 		} else {
+			rcu_nocb_unlock_irqrestore(rdp, flags);
 			wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE,
 					   TPS("WakeEmptyIsDeferred"));
-			rcu_nocb_unlock_irqrestore(rdp, flags);
 		}
 	} else if (len > rdp->qlen_last_fqs_check + qhimark) {
 		/* ... or if many callbacks queued. */
@@ -1975,10 +1985,14 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
 		smp_mb(); /* Enqueue before timer_pending(). */
 		if ((rdp->nocb_cb_sleep ||
 		     !rcu_segcblist_ready_cbs(&rdp->cblist)) &&
-		    !timer_pending(&rdp->nocb_bypass_timer))
+		    !timer_pending(&rdp->nocb_timer)) {
+			rcu_nocb_unlock_irqrestore(rdp, flags);
 			wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE_FORCE,
 					   TPS("WakeOvfIsDeferred"));
-		rcu_nocb_unlock_irqrestore(rdp, flags);
+		} else {
+			rcu_nocb_unlock_irqrestore(rdp, flags);
+			trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNot"));
+		}
 	} else {
 		rcu_nocb_unlock_irqrestore(rdp, flags);
 		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNot"));
@@ -1986,18 +2000,6 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
 	return;
 }
 
-/* Wake up the no-CBs GP kthread to flush ->nocb_bypass. */
-static void do_nocb_bypass_wakeup_timer(struct timer_list *t)
-{
-	unsigned long flags;
-	struct rcu_data *rdp = from_timer(rdp, t, nocb_bypass_timer);
-
-	trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("Timer"));
-	rcu_nocb_lock_irqsave(rdp, flags);
-	smp_mb__after_spinlock(); /* Timer expire before wakeup. */
-	__call_rcu_nocb_wake(rdp, true, flags);
-}
-
 /*
  * Check if we ignore this rdp.
  *
@@ -2104,11 +2106,7 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 			bypass = true;
 		}
 		rnp = rdp->mynode;
-		if (bypass) {  // Avoid race with first bypass CB.
-			WRITE_ONCE(my_rdp->nocb_defer_wakeup,
-				   RCU_NOCB_WAKE_NOT);
-			del_timer(&my_rdp->nocb_timer);
-		}
+
 		// Advance callbacks if helpful and low contention.
 		needwake_gp = false;
 		if (!rcu_segcblist_restempty(&rdp->cblist,
@@ -2154,12 +2152,12 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 	my_rdp->nocb_gp_bypass = bypass;
 	my_rdp->nocb_gp_gp = needwait_gp;
 	my_rdp->nocb_gp_seq = needwait_gp ? wait_gp_seq : 0;
+
 	if (bypass && !rcu_nocb_poll) {
 		// At least one child with non-empty ->nocb_bypass, so set
 		// timer in order to avoid stranding its callbacks.
-		raw_spin_lock_irqsave(&my_rdp->nocb_gp_lock, flags);
-		mod_timer(&my_rdp->nocb_bypass_timer, j + 2);
-		raw_spin_unlock_irqrestore(&my_rdp->nocb_gp_lock, flags);
+		wake_nocb_gp_defer(my_rdp, RCU_NOCB_WAKE_BYPASS,
+				   TPS("WakeBypassIsDeferred"));
 	}
 	if (rcu_nocb_poll) {
 		/* Polling, so trace if first poll in the series. */
@@ -2183,8 +2181,10 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 	}
 	if (!rcu_nocb_poll) {
 		raw_spin_lock_irqsave(&my_rdp->nocb_gp_lock, flags);
-		if (bypass)
-			del_timer(&my_rdp->nocb_bypass_timer);
+		if (my_rdp->nocb_defer_wakeup > RCU_NOCB_WAKE_NOT) {
+			WRITE_ONCE(my_rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT);
+			del_timer(&my_rdp->nocb_timer);
+		}
 		WRITE_ONCE(my_rdp->nocb_gp_sleep, true);
 		raw_spin_unlock_irqrestore(&my_rdp->nocb_gp_lock, flags);
 	}
@@ -2320,25 +2320,27 @@ static int rcu_nocb_cb_kthread(void *arg)
 }
 
 /* Is a deferred wakeup of rcu_nocb_kthread() required? */
-static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
+static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp, int level)
 {
-	return READ_ONCE(rdp->nocb_defer_wakeup) > RCU_NOCB_WAKE_NOT;
+	return READ_ONCE(rdp->nocb_defer_wakeup) >= level;
 }
 
 /* Do a deferred wakeup of rcu_nocb_kthread(). */
-static bool do_nocb_deferred_wakeup_common(struct rcu_data *rdp)
+static bool do_nocb_deferred_wakeup_common(struct rcu_data *rdp_gp,
+					   struct rcu_data *rdp, int level,
+					   unsigned long flags)
+	__releases(rdp_gp->nocb_gp_lock)
 {
-	unsigned long flags;
 	int ndw;
 	int ret;
 
-	rcu_nocb_lock_irqsave(rdp, flags);
-	if (!rcu_nocb_need_deferred_wakeup(rdp)) {
-		rcu_nocb_unlock_irqrestore(rdp, flags);
+	if (!rcu_nocb_need_deferred_wakeup(rdp_gp, level)) {
+		raw_spin_unlock_irqrestore(&rdp_gp->nocb_gp_lock, flags);
 		return false;
 	}
-	ndw = READ_ONCE(rdp->nocb_defer_wakeup);
-	ret = wake_nocb_gp(rdp, ndw == RCU_NOCB_WAKE_FORCE, flags);
+
+	ndw = rdp_gp->nocb_defer_wakeup;
+	ret = __wake_nocb_gp(rdp_gp, rdp, ndw == RCU_NOCB_WAKE_FORCE, flags);
 	trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("DeferredWake"));
 
 	return ret;
@@ -2347,9 +2349,15 @@ static bool do_nocb_deferred_wakeup_common(struct rcu_data *rdp)
 /* Do a deferred wakeup of rcu_nocb_kthread() from a timer handler. */
 static void do_nocb_deferred_wakeup_timer(struct timer_list *t)
 {
+	unsigned long flags;
 	struct rcu_data *rdp = from_timer(rdp, t, nocb_timer);
 
-	do_nocb_deferred_wakeup_common(rdp);
+	WARN_ON_ONCE(rdp->nocb_gp_rdp != rdp);
+	trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("Timer"));
+
+	raw_spin_lock_irqsave(&rdp->nocb_gp_lock, flags);
+	smp_mb__after_spinlock(); /* Timer expire before wakeup. */
+	do_nocb_deferred_wakeup_common(rdp, rdp, RCU_NOCB_WAKE_BYPASS, flags);
 }
 
 /*
@@ -2359,9 +2367,14 @@ static void do_nocb_deferred_wakeup_timer(struct timer_list *t)
  */
 static bool do_nocb_deferred_wakeup(struct rcu_data *rdp)
 {
-	if (rcu_nocb_need_deferred_wakeup(rdp))
-		return do_nocb_deferred_wakeup_common(rdp);
-	return false;
+	unsigned long flags;
+	struct rcu_data *rdp_gp = rdp->nocb_gp_rdp;
+
+	if (!rdp_gp || !rcu_nocb_need_deferred_wakeup(rdp_gp, RCU_NOCB_WAKE))
+		return false;
+
+	raw_spin_lock_irqsave(&rdp_gp->nocb_gp_lock, flags);
+	return do_nocb_deferred_wakeup_common(rdp_gp, rdp, RCU_NOCB_WAKE, flags);
 }
 
 void rcu_nocb_flush_deferred_wakeup(void)
@@ -2429,17 +2442,15 @@ static long rcu_nocb_rdp_deoffload(void *arg)
 	swait_event_exclusive(rdp->nocb_state_wq,
 			      !rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB |
 							SEGCBLIST_KTHREAD_GP));
-	rcu_nocb_lock_irqsave(rdp, flags);
-	/* Make sure nocb timer won't stay around */
-	WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_OFF);
-	rcu_nocb_unlock_irqrestore(rdp, flags);
-	del_timer_sync(&rdp->nocb_timer);
-
 	/*
-	 * Theoretically we could set SEGCBLIST_SOFTIRQ_ONLY with CB unlocked
-	 * and IRQs disabled but let's be paranoid.
+	 * Lock one last time to acquire latest callback updates from kthreads
+	 * so we can later handle callbacks locally without locking.
 	 */
 	rcu_nocb_lock_irqsave(rdp, flags);
+	/*
+	 * Theoretically we could set SEGCBLIST_SOFTIRQ_ONLY after the nocb
+	 * lock is released but how about being paranoid for once?
+	 */
 	rcu_segcblist_set_flags(cblist, SEGCBLIST_SOFTIRQ_ONLY);
 	/*
 	 * With SEGCBLIST_SOFTIRQ_ONLY, we can't use
@@ -2459,10 +2470,6 @@ int rcu_nocb_cpu_deoffload(int cpu)
 	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 	int ret = 0;
 
-	if (rdp == rdp->nocb_gp_rdp) {
-		pr_info("Can't deoffload an rdp GP leader (yet)\n");
-		return -EINVAL;
-	}
 	mutex_lock(&rcu_state.barrier_mutex);
 	cpus_read_lock();
 	if (rcu_rdp_is_offloaded(rdp)) {
@@ -2503,8 +2510,7 @@ static long rcu_nocb_rdp_offload(void *arg)
 	 * SEGCBLIST_SOFTIRQ_ONLY mode.
 	 */
 	raw_spin_lock_irqsave(&rdp->nocb_lock, flags);
-	/* Re-enable nocb timer */
-	WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT);
+
 	/*
 	 * We didn't take the nocb lock while working on the
 	 * rdp->cblist in SEGCBLIST_SOFTIRQ_ONLY mode.
@@ -2612,7 +2618,6 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 	raw_spin_lock_init(&rdp->nocb_bypass_lock);
 	raw_spin_lock_init(&rdp->nocb_gp_lock);
 	timer_setup(&rdp->nocb_timer, do_nocb_deferred_wakeup_timer, 0);
-	timer_setup(&rdp->nocb_bypass_timer, do_nocb_bypass_wakeup_timer, 0);
 	rcu_cblist_init(&rdp->nocb_bypass);
 }
 
@@ -2771,13 +2776,12 @@ static void show_rcu_nocb_gp_state(struct rcu_data *rdp)
 {
 	struct rcu_node *rnp = rdp->mynode;
 
-	pr_info("nocb GP %d %c%c%c%c%c%c %c[%c%c] %c%c:%ld rnp %d:%d %lu %c CPU %d%s\n",
+	pr_info("nocb GP %d %c%c%c%c%c %c[%c%c] %c%c:%ld rnp %d:%d %lu %c CPU %d%s\n",
 		rdp->cpu,
 		"kK"[!!rdp->nocb_gp_kthread],
 		"lL"[raw_spin_is_locked(&rdp->nocb_gp_lock)],
 		"dD"[!!rdp->nocb_defer_wakeup],
 		"tT"[timer_pending(&rdp->nocb_timer)],
-		"bB"[timer_pending(&rdp->nocb_bypass_timer)],
 		"sS"[!!rdp->nocb_gp_sleep],
 		".W"[swait_active(&rdp->nocb_gp_wq)],
 		".W"[swait_active(&rnp->nocb_gp_wq[0])],
@@ -2798,7 +2802,6 @@ static void show_rcu_nocb_state(struct rcu_data *rdp)
 	char bufr[20];
 	struct rcu_segcblist *rsclp = &rdp->cblist;
 	bool waslocked;
-	bool wastimer;
 	bool wassleep;
 
 	if (rdp->nocb_gp_rdp == rdp)
@@ -2835,15 +2838,13 @@ static void show_rcu_nocb_state(struct rcu_data *rdp)
 		return;
 
 	waslocked = raw_spin_is_locked(&rdp->nocb_gp_lock);
-	wastimer = timer_pending(&rdp->nocb_bypass_timer);
 	wassleep = swait_active(&rdp->nocb_gp_wq);
-	if (!rdp->nocb_gp_sleep && !waslocked && !wastimer && !wassleep)
-		return;  /* Nothing untowards. */
+	if (!rdp->nocb_gp_sleep && !waslocked && !wassleep)
+		return;  /* Nothing untoward. */
 
-	pr_info("   nocb GP activity on CB-only CPU!!! %c%c%c%c %c\n",
+	pr_info("   nocb GP activity on CB-only CPU!!! %c%c%c %c\n",
 		"lL"[waslocked],
 		"dD"[!!rdp->nocb_defer_wakeup],
-		"tT"[wastimer],
 		"sS"[!!rdp->nocb_gp_sleep],
 		".W"[wassleep]);
 }
@@ -2908,7 +2909,7 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 {
 }
 
-static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
+static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp, int level)
 {
 	return false;
 }