1 files changed, 92 insertions, 58 deletions

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 338f1d1c1c66..32618b3fe4e6 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -54,6 +54,7 @@
 #include <linux/stop_machine.h>
 #include <linux/random.h>
 #include <linux/ftrace_event.h>
+#include <linux/suspend.h>
 
 #include "rcutree.h"
 #include <trace/events/rcu.h>
@@ -224,6 +225,10 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 	.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
 	.dynticks = ATOMIC_INIT(1),
+#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
+	.dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE,
+	.dynticks_idle = ATOMIC_INIT(1),
+#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
 };
 
 static long blimit = 10;	/* Maximum callbacks per rcu_do_batch. */
@@ -242,7 +247,10 @@ module_param(jiffies_till_next_fqs, ulong, 0644);
 
 static void rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
 				  struct rcu_data *rdp);
-static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *));
+static void force_qs_rnp(struct rcu_state *rsp,
+			 int (*f)(struct rcu_data *rsp, bool *isidle,
+				  unsigned long *maxj),
+			 bool *isidle, unsigned long *maxj);
 static void force_quiescent_state(struct rcu_state *rsp);
 static int rcu_pending(int cpu);
 
@@ -427,6 +435,7 @@ void rcu_idle_enter(void)
 
 	local_irq_save(flags);
 	rcu_eqs_enter(false);
+	rcu_sysidle_enter(&__get_cpu_var(rcu_dynticks), 0);
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(rcu_idle_enter);
@@ -444,27 +453,6 @@ void rcu_user_enter(void)
 {
 	rcu_eqs_enter(1);
 }
-
-/**
- * rcu_user_enter_after_irq - inform RCU that we are going to resume userspace
- * after the current irq returns.
- *
- * This is similar to rcu_user_enter() but in the context of a non-nesting
- * irq. After this call, RCU enters into idle mode when the interrupt
- * returns.
- */
-void rcu_user_enter_after_irq(void)
-{
-	unsigned long flags;
-	struct rcu_dynticks *rdtp;
-
-	local_irq_save(flags);
-	rdtp = &__get_cpu_var(rcu_dynticks);
-	/* Ensure this irq is interrupting a non-idle RCU state.  */
-	WARN_ON_ONCE(!(rdtp->dynticks_nesting & DYNTICK_TASK_MASK));
-	rdtp->dynticks_nesting = 1;
-	local_irq_restore(flags);
-}
 #endif /* CONFIG_RCU_USER_QS */
 
 /**
@@ -498,6 +486,7 @@ void rcu_irq_exit(void)
 		trace_rcu_dyntick(TPS("--="), oldval, rdtp->dynticks_nesting);
 	else
 		rcu_eqs_enter_common(rdtp, oldval, true);
+	rcu_sysidle_enter(rdtp, 1);
 	local_irq_restore(flags);
 }
 
@@ -566,6 +555,7 @@ void rcu_idle_exit(void)
 
 	local_irq_save(flags);
 	rcu_eqs_exit(false);
+	rcu_sysidle_exit(&__get_cpu_var(rcu_dynticks), 0);
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(rcu_idle_exit);
@@ -581,28 +571,6 @@ void rcu_user_exit(void)
 {
 	rcu_eqs_exit(1);
 }
-
-/**
- * rcu_user_exit_after_irq - inform RCU that we won't resume to userspace
- * idle mode after the current non-nesting irq returns.
- *
- * This is similar to rcu_user_exit() but in the context of an irq.
- * This is called when the irq has interrupted a userspace RCU idle mode
- * context. When the current non-nesting interrupt returns after this call,
- * the CPU won't restore the RCU idle mode.
- */
-void rcu_user_exit_after_irq(void)
-{
-	unsigned long flags;
-	struct rcu_dynticks *rdtp;
-
-	local_irq_save(flags);
-	rdtp = &__get_cpu_var(rcu_dynticks);
-	/* Ensure we are interrupting an RCU idle mode. */
-	WARN_ON_ONCE(rdtp->dynticks_nesting & DYNTICK_TASK_NEST_MASK);
-	rdtp->dynticks_nesting += DYNTICK_TASK_EXIT_IDLE;
-	local_irq_restore(flags);
-}
 #endif /* CONFIG_RCU_USER_QS */
 
 /**
@@ -639,6 +607,7 @@ void rcu_irq_enter(void)
 		trace_rcu_dyntick(TPS("++="), oldval, rdtp->dynticks_nesting);
 	else
 		rcu_eqs_exit_common(rdtp, oldval, true);
+	rcu_sysidle_exit(rdtp, 1);
 	local_irq_restore(flags);
 }
 
@@ -762,9 +731,11 @@ static int rcu_is_cpu_rrupt_from_idle(void)
  * credit them with an implicit quiescent state.  Return 1 if this CPU
  * is in dynticks idle mode, which is an extended quiescent state.
  */
-static int dyntick_save_progress_counter(struct rcu_data *rdp)
+static int dyntick_save_progress_counter(struct rcu_data *rdp,
+					 bool *isidle, unsigned long *maxj)
 {
 	rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks);
+	rcu_sysidle_check_cpu(rdp, isidle, maxj);
 	return (rdp->dynticks_snap & 0x1) == 0;
 }
 
@@ -774,7 +745,8 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
  * idle state since the last call to dyntick_save_progress_counter()
  * for this same CPU, or by virtue of having been offline.
  */
-static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
+static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
+				    bool *isidle, unsigned long *maxj)
 {
 	unsigned int curr;
 	unsigned int snap;
@@ -1332,6 +1304,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
+	rcu_bind_gp_kthread();
 	raw_spin_lock_irq(&rnp->lock);
 	rsp->gp_flags = 0; /* Clear all flags: New grace period. */
 
@@ -1396,16 +1369,25 @@ static int rcu_gp_init(struct rcu_state *rsp)
 int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 {
 	int fqs_state = fqs_state_in;
+	bool isidle = false;
+	unsigned long maxj;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	rsp->n_force_qs++;
 	if (fqs_state == RCU_SAVE_DYNTICK) {
 		/* Collect dyntick-idle snapshots. */
-		force_qs_rnp(rsp, dyntick_save_progress_counter);
+		if (is_sysidle_rcu_state(rsp)) {
+			isidle = 1;
+			maxj = jiffies - ULONG_MAX / 4;
+		}
+		force_qs_rnp(rsp, dyntick_save_progress_counter,
+			     &isidle, &maxj);
+		rcu_sysidle_report_gp(rsp, isidle, maxj);
 		fqs_state = RCU_FORCE_QS;
 	} else {
 		/* Handle dyntick-idle and offline CPUs. */
-		force_qs_rnp(rsp, rcu_implicit_dynticks_qs);
+		isidle = 0;
+		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) {
@@ -1575,10 +1557,12 @@ rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
 
 	/*
 	 * We can't do wakeups while holding the rnp->lock, as that
-	 * could cause possible deadlocks with the rq->lock. Deter
-	 * the wakeup to interrupt context.
+	 * could cause possible deadlocks with the rq->lock. Defer
+	 * the wakeup to interrupt context.  And don't bother waking
+	 * up the running kthread.
 	 */
-	irq_work_queue(&rsp->wakeup_work);
+	if (current != rsp->gp_kthread)
+		irq_work_queue(&rsp->wakeup_work);
 }
 
 /*
@@ -2104,7 +2088,10 @@ void rcu_check_callbacks(int cpu, int user)
  *
  * The caller must have suppressed start of new grace periods.
  */
-static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *))
+static void force_qs_rnp(struct rcu_state *rsp,
+			 int (*f)(struct rcu_data *rsp, bool *isidle,
+				  unsigned long *maxj),
+			 bool *isidle, unsigned long *maxj)
 {
 	unsigned long bit;
 	int cpu;
@@ -2127,9 +2114,12 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *))
 		cpu = rnp->grplo;
 		bit = 1;
 		for (; cpu <= rnp->grphi; cpu++, bit <<= 1) {
-			if ((rnp->qsmask & bit) != 0 &&
-			    f(per_cpu_ptr(rsp->rda, cpu)))
-				mask |= bit;
+			if ((rnp->qsmask & bit) != 0) {
+				if ((rnp->qsmaskinit & bit) != 0)
+					*isidle = 0;
+				if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj))
+					mask |= bit;
+			}
 		}
 		if (mask != 0) {
 
@@ -2304,6 +2294,13 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 }
 
 /*
+ * RCU callback function to leak a callback.
+ */
+static void rcu_leak_callback(struct rcu_head *rhp)
+{
+}
+
+/*
  * Helper function for call_rcu() and friends.  The cpu argument will
  * normally be -1, indicating "currently running CPU".  It may specify
  * a CPU only if that CPU is a no-CBs CPU.  Currently, only _rcu_barrier()
@@ -2317,7 +2314,12 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 	struct rcu_data *rdp;
 
 	WARN_ON_ONCE((unsigned long)head & 0x3); /* Misaligned rcu_head! */
-	debug_rcu_head_queue(head);
+	if (debug_rcu_head_queue(head)) {
+		/* Probable double call_rcu(), so leak the callback. */
+		ACCESS_ONCE(head->func) = rcu_leak_callback;
+		WARN_ONCE(1, "__call_rcu(): Leaked duplicate callback\n");
+		return;
+	}
 	head->func = func;
 	head->next = NULL;
 
@@ -2802,9 +2804,20 @@ static void _rcu_barrier(struct rcu_state *rsp)
 	 * transition.  The "if" expression below therefore rounds the old
 	 * value up to the next even number and adds two before comparing.
 	 */
-	snap_done = ACCESS_ONCE(rsp->n_barrier_done);
+	snap_done = rsp->n_barrier_done;
 	_rcu_barrier_trace(rsp, "Check", -1, snap_done);
-	if (ULONG_CMP_GE(snap_done, ((snap + 1) & ~0x1) + 2)) {
+
+	/*
+	 * If the value in snap is odd, we needed to wait for the current
+	 * rcu_barrier() to complete, then wait for the next one, in other
+	 * words, we need the value of snap_done to be three larger than
+	 * the value of snap.  On the other hand, if the value in snap is
+	 * even, we only had to wait for the next rcu_barrier() to complete,
+	 * in other words, we need the value of snap_done to be only two
+	 * greater than the value of snap.  The "(snap + 3) & ~0x1" computes
+	 * this for us (thank you, Linus!).
+	 */
+	if (ULONG_CMP_GE(snap_done, (snap + 3) & ~0x1)) {
 		_rcu_barrier_trace(rsp, "EarlyExit", -1, snap_done);
 		smp_mb(); /* caller's subsequent code after above check. */
 		mutex_unlock(&rsp->barrier_mutex);
@@ -2947,6 +2960,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible)
 	rdp->blimit = blimit;
 	init_callback_list(rdp);  /* Re-enable callbacks on this CPU. */
 	rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
+	rcu_sysidle_init_percpu_data(rdp->dynticks);
 	atomic_set(&rdp->dynticks->dynticks,
 		   (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1);
 	raw_spin_unlock(&rnp->lock);		/* irqs remain disabled. */
@@ -3032,6 +3046,25 @@ static int rcu_cpu_notify(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
+static int rcu_pm_notify(struct notifier_block *self,
+			 unsigned long action, void *hcpu)
+{
+	switch (action) {
+	case PM_HIBERNATION_PREPARE:
+	case PM_SUSPEND_PREPARE:
+		if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */
+			rcu_expedited = 1;
+		break;
+	case PM_POST_HIBERNATION:
+	case PM_POST_SUSPEND:
+		rcu_expedited = 0;
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
 /*
  * Spawn the kthread that handles this RCU flavor's grace periods.
  */
@@ -3273,6 +3306,7 @@ void __init rcu_init(void)
 	 * or the scheduler are operational.
 	 */
 	cpu_notifier(rcu_cpu_notify, 0);
+	pm_notifier(rcu_pm_notify, 0);
 	for_each_online_cpu(cpu)
 		rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
 }