Merge branch 'rcu/next' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/rcu

Pull the v3.18 RCU changes from Paul E. McKenney:

"
  * Update RCU documentation.  These were posted to LKML at
    https://lkml.org/lkml/2014/8/28/378.

  * Miscellaneous fixes.  These were posted to LKML at
    https://lkml.org/lkml/2014/8/28/386.  An additional fix that
    eliminates a documented (but now inconvenient) deadlock between
    RCU hotplug and expedited grace periods was posted at
    https://lkml.org/lkml/2014/8/28/573.

  * Changes related to No-CBs CPUs and NO_HZ_FULL.  These were posted
    to LKML at https://lkml.org/lkml/2014/8/28/412.

  * Torture-test updates.  These were posted to LKML at
    https://lkml.org/lkml/2014/8/28/546 and at
    https://lkml.org/lkml/2014/9/11/1114.

  * RCU-tasks implementation.  These were posted to LKML at
    https://lkml.org/lkml/2014/8/28/540.
"

Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 69 insertions, 46 deletions

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 1b70cb6fbe3c..133e47223095 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -79,9 +79,18 @@ static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
  * the tracing userspace tools to be able to decipher the string
  * address to the matching string.
  */
-#define RCU_STATE_INITIALIZER(sname, sabbr, cr) \
+#ifdef CONFIG_TRACING
+# define DEFINE_RCU_TPS(sname) \
 static char sname##_varname[] = #sname; \
-static const char *tp_##sname##_varname __used __tracepoint_string = sname##_varname; \
+static const char *tp_##sname##_varname __used __tracepoint_string = sname##_varname;
+# define RCU_STATE_NAME(sname) sname##_varname
+#else
+# define DEFINE_RCU_TPS(sname)
+# define RCU_STATE_NAME(sname) __stringify(sname)
+#endif
+
+#define RCU_STATE_INITIALIZER(sname, sabbr, cr) \
+DEFINE_RCU_TPS(sname) \
 struct rcu_state sname##_state = { \
 	.level = { &sname##_state.node[0] }, \
 	.call = cr, \
@@ -93,7 +102,7 @@ struct rcu_state sname##_state = { \
 	.orphan_donetail = &sname##_state.orphan_donelist, \
 	.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
 	.onoff_mutex = __MUTEX_INITIALIZER(sname##_state.onoff_mutex), \
-	.name = sname##_varname, \
+	.name = RCU_STATE_NAME(sname), \
 	.abbr = sabbr, \
 }; \
 DEFINE_PER_CPU(struct rcu_data, sname##_data)
@@ -188,22 +197,24 @@ static int rcu_gp_in_progress(struct rcu_state *rsp)
  * one since the start of the grace period, this just sets a flag.
  * The caller must have disabled preemption.
  */
-void rcu_sched_qs(int cpu)
+void rcu_sched_qs(void)
 {
-	struct rcu_data *rdp = &per_cpu(rcu_sched_data, cpu);
-
-	if (rdp->passed_quiesce == 0)
-		trace_rcu_grace_period(TPS("rcu_sched"), rdp->gpnum, TPS("cpuqs"));
-	rdp->passed_quiesce = 1;
+	if (!__this_cpu_read(rcu_sched_data.passed_quiesce)) {
+		trace_rcu_grace_period(TPS("rcu_sched"),
+				       __this_cpu_read(rcu_sched_data.gpnum),
+				       TPS("cpuqs"));
+		__this_cpu_write(rcu_sched_data.passed_quiesce, 1);
+	}
 }
 
-void rcu_bh_qs(int cpu)
+void rcu_bh_qs(void)
 {
-	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
-
-	if (rdp->passed_quiesce == 0)
-		trace_rcu_grace_period(TPS("rcu_bh"), rdp->gpnum, TPS("cpuqs"));
-	rdp->passed_quiesce = 1;
+	if (!__this_cpu_read(rcu_bh_data.passed_quiesce)) {
+		trace_rcu_grace_period(TPS("rcu_bh"),
+				       __this_cpu_read(rcu_bh_data.gpnum),
+				       TPS("cpuqs"));
+		__this_cpu_write(rcu_bh_data.passed_quiesce, 1);
+	}
 }
 
 static DEFINE_PER_CPU(int, rcu_sched_qs_mask);
@@ -278,7 +289,7 @@ static void rcu_momentary_dyntick_idle(void)
 void rcu_note_context_switch(int cpu)
 {
 	trace_rcu_utilization(TPS("Start context switch"));
-	rcu_sched_qs(cpu);
+	rcu_sched_qs();
 	rcu_preempt_note_context_switch(cpu);
 	if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
 		rcu_momentary_dyntick_idle();
@@ -526,6 +537,7 @@ static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
 	atomic_inc(&rdtp->dynticks);
 	smp_mb__after_atomic();  /* Force ordering with next sojourn. */
 	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
+	rcu_dynticks_task_enter();
 
 	/*
 	 * It is illegal to enter an extended quiescent state while
@@ -642,6 +654,7 @@ void rcu_irq_exit(void)
 static void rcu_eqs_exit_common(struct rcu_dynticks *rdtp, long long oldval,
 			       int user)
 {
+	rcu_dynticks_task_exit();
 	smp_mb__before_atomic();  /* Force ordering w/previous sojourn. */
 	atomic_inc(&rdtp->dynticks);
 	/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
@@ -819,7 +832,7 @@ bool notrace __rcu_is_watching(void)
  */
 bool notrace rcu_is_watching(void)
 {
-	int ret;
+	bool ret;
 
 	preempt_disable();
 	ret = __rcu_is_watching();
@@ -1647,7 +1660,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 					    rnp->level, rnp->grplo,
 					    rnp->grphi, rnp->qsmask);
 		raw_spin_unlock_irq(&rnp->lock);
-		cond_resched();
+		cond_resched_rcu_qs();
 	}
 
 	mutex_unlock(&rsp->onoff_mutex);
@@ -1668,7 +1681,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 	if (fqs_state == RCU_SAVE_DYNTICK) {
 		/* Collect dyntick-idle snapshots. */
 		if (is_sysidle_rcu_state(rsp)) {
-			isidle = 1;
+			isidle = true;
 			maxj = jiffies - ULONG_MAX / 4;
 		}
 		force_qs_rnp(rsp, dyntick_save_progress_counter,
@@ -1677,14 +1690,15 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 		fqs_state = RCU_FORCE_QS;
 	} else {
 		/* Handle dyntick-idle and offline CPUs. */
-		isidle = 0;
+		isidle = false;
 		force_qs_rnp(rsp, rcu_implicit_dynticks_qs, &isidle, &maxj);
 	}
 	/* Clear flag to prevent immediate re-entry. */
 	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		raw_spin_lock_irq(&rnp->lock);
 		smp_mb__after_unlock_lock();
-		ACCESS_ONCE(rsp->gp_flags) &= ~RCU_GP_FLAG_FQS;
+		ACCESS_ONCE(rsp->gp_flags) =
+			ACCESS_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS;
 		raw_spin_unlock_irq(&rnp->lock);
 	}
 	return fqs_state;
@@ -1736,7 +1750,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 		/* smp_mb() provided by prior unlock-lock pair. */
 		nocb += rcu_future_gp_cleanup(rsp, rnp);
 		raw_spin_unlock_irq(&rnp->lock);
-		cond_resched();
+		cond_resched_rcu_qs();
 	}
 	rnp = rcu_get_root(rsp);
 	raw_spin_lock_irq(&rnp->lock);
@@ -1785,8 +1799,8 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			/* Locking provides needed memory barrier. */
 			if (rcu_gp_init(rsp))
 				break;
-			cond_resched();
-			flush_signals(current);
+			cond_resched_rcu_qs();
+			WARN_ON(signal_pending(current));
 			trace_rcu_grace_period(rsp->name,
 					       ACCESS_ONCE(rsp->gpnum),
 					       TPS("reqwaitsig"));
@@ -1828,11 +1842,11 @@ static int __noreturn rcu_gp_kthread(void *arg)
 				trace_rcu_grace_period(rsp->name,
 						       ACCESS_ONCE(rsp->gpnum),
 						       TPS("fqsend"));
-				cond_resched();
+				cond_resched_rcu_qs();
 			} else {
 				/* Deal with stray signal. */
-				cond_resched();
-				flush_signals(current);
+				cond_resched_rcu_qs();
+				WARN_ON(signal_pending(current));
 				trace_rcu_grace_period(rsp->name,
 						       ACCESS_ONCE(rsp->gpnum),
 						       TPS("fqswaitsig"));
@@ -1928,7 +1942,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
 {
 	WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
 	raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
-	wake_up(&rsp->gp_wq);  /* Memory barrier implied by wake_up() path. */
+	rcu_gp_kthread_wake(rsp);
 }
 
 /*
@@ -2210,8 +2224,6 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 	/* Adjust any no-longer-needed kthreads. */
 	rcu_boost_kthread_setaffinity(rnp, -1);
 
-	/* Remove the dead CPU from the bitmasks in the rcu_node hierarchy. */
-
 	/* Exclude any attempts to start a new grace period. */
 	mutex_lock(&rsp->onoff_mutex);
 	raw_spin_lock_irqsave(&rsp->orphan_lock, flags);
@@ -2393,8 +2405,8 @@ void rcu_check_callbacks(int cpu, int user)
 		 * at least not while the corresponding CPU is online.
 		 */
 
-		rcu_sched_qs(cpu);
-		rcu_bh_qs(cpu);
+		rcu_sched_qs();
+		rcu_bh_qs();
 
 	} else if (!in_softirq()) {
 
@@ -2405,11 +2417,13 @@ void rcu_check_callbacks(int cpu, int user)
 		 * critical section, so note it.
 		 */
 
-		rcu_bh_qs(cpu);
+		rcu_bh_qs();
 	}
 	rcu_preempt_check_callbacks(cpu);
 	if (rcu_pending(cpu))
 		invoke_rcu_core();
+	if (user)
+		rcu_note_voluntary_context_switch(current);
 	trace_rcu_utilization(TPS("End scheduler-tick"));
 }
 
@@ -2432,7 +2446,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
 	struct rcu_node *rnp;
 
 	rcu_for_each_leaf_node(rsp, rnp) {
-		cond_resched();
+		cond_resched_rcu_qs();
 		mask = 0;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		smp_mb__after_unlock_lock();
@@ -2449,7 +2463,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
 		for (; cpu <= rnp->grphi; cpu++, bit <<= 1) {
 			if ((rnp->qsmask & bit) != 0) {
 				if ((rnp->qsmaskinit & bit) != 0)
-					*isidle = 0;
+					*isidle = false;
 				if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj))
 					mask |= bit;
 			}
@@ -2505,9 +2519,10 @@ static void force_quiescent_state(struct rcu_state *rsp)
 		raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
 		return;  /* Someone beat us to it. */
 	}
-	ACCESS_ONCE(rsp->gp_flags) |= RCU_GP_FLAG_FQS;
+	ACCESS_ONCE(rsp->gp_flags) =
+		ACCESS_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS;
 	raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
-	wake_up(&rsp->gp_wq);  /* Memory barrier implied by wake_up() path. */
+	rcu_gp_kthread_wake(rsp);
 }
 
 /*
@@ -2925,11 +2940,6 @@ static int synchronize_sched_expedited_cpu_stop(void *data)
  * restructure your code to batch your updates, and then use a single
  * synchronize_sched() instead.
  *
- * Note that it is illegal to call this function while holding any lock
- * that is acquired by a CPU-hotplug notifier.  And yes, it is also illegal
- * to call this function from a CPU-hotplug notifier.  Failing to observe
- * these restriction will result in deadlock.
- *
  * This implementation can be thought of as an application of ticket
  * locking to RCU, with sync_sched_expedited_started and
  * sync_sched_expedited_done taking on the roles of the halves
@@ -2979,7 +2989,12 @@ void synchronize_sched_expedited(void)
 	 */
 	snap = atomic_long_inc_return(&rsp->expedited_start);
 	firstsnap = snap;
-	get_online_cpus();
+	if (!try_get_online_cpus()) {
+		/* CPU hotplug operation in flight, fall back to normal GP. */
+		wait_rcu_gp(call_rcu_sched);
+		atomic_long_inc(&rsp->expedited_normal);
+		return;
+	}
 	WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id()));
 
 	/*
@@ -3026,7 +3041,12 @@ void synchronize_sched_expedited(void)
 		 * and they started after our first try, so their grace
 		 * period works for us.
 		 */
-		get_online_cpus();
+		if (!try_get_online_cpus()) {
+			/* CPU hotplug operation in flight, use normal GP. */
+			wait_rcu_gp(call_rcu_sched);
+			atomic_long_inc(&rsp->expedited_normal);
+			return;
+		}
 		snap = atomic_long_read(&rsp->expedited_start);
 		smp_mb(); /* ensure read is before try_stop_cpus(). */
 	}
@@ -3442,6 +3462,7 @@ static int rcu_cpu_notify(struct notifier_block *self,
 	case CPU_UP_PREPARE_FROZEN:
 		rcu_prepare_cpu(cpu);
 		rcu_prepare_kthreads(cpu);
+		rcu_spawn_all_nocb_kthreads(cpu);
 		break;
 	case CPU_ONLINE:
 	case CPU_DOWN_FAILED:
@@ -3489,7 +3510,7 @@ static int rcu_pm_notify(struct notifier_block *self,
 }
 
 /*
- * Spawn the kthread that handles this RCU flavor's grace periods.
+ * Spawn the kthreads that handle each RCU flavor's grace periods.
  */
 static int __init rcu_spawn_gp_kthread(void)
 {
@@ -3498,6 +3519,7 @@ static int __init rcu_spawn_gp_kthread(void)
 	struct rcu_state *rsp;
 	struct task_struct *t;
 
+	rcu_scheduler_fully_active = 1;
 	for_each_rcu_flavor(rsp) {
 		t = kthread_run(rcu_gp_kthread, rsp, "%s", rsp->name);
 		BUG_ON(IS_ERR(t));
@@ -3505,8 +3527,9 @@ static int __init rcu_spawn_gp_kthread(void)
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		rsp->gp_kthread = t;
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-		rcu_spawn_nocb_kthreads(rsp);
 	}
+	rcu_spawn_nocb_kthreads();
+	rcu_spawn_boost_kthreads();
 	return 0;
 }
 early_initcall(rcu_spawn_gp_kthread);