1 files changed, 388 insertions, 138 deletions

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index e441b77b614..16ea6792501 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -64,7 +64,7 @@
 static struct lock_class_key rcu_node_class[RCU_NUM_LVLS];
 static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
 
-#define RCU_STATE_INITIALIZER(sname, cr) { \
+#define RCU_STATE_INITIALIZER(sname, sabbr, cr) { \
 	.level = { &sname##_state.node[0] }, \
 	.call = cr, \
 	.fqs_state = RCU_GP_IDLE, \
@@ -76,13 +76,14 @@ static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
 	.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
 	.onoff_mutex = __MUTEX_INITIALIZER(sname##_state.onoff_mutex), \
 	.name = #sname, \
+	.abbr = sabbr, \
 }
 
 struct rcu_state rcu_sched_state =
-	RCU_STATE_INITIALIZER(rcu_sched, call_rcu_sched);
+	RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
 DEFINE_PER_CPU(struct rcu_data, rcu_sched_data);
 
-struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh, call_rcu_bh);
+struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh);
 DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
 
 static struct rcu_state *rcu_state;
@@ -105,7 +106,7 @@ int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */
  * The rcu_scheduler_active variable transitions from zero to one just
  * before the first task is spawned.  So when this variable is zero, RCU
  * can assume that there is but one task, allowing RCU to (for example)
- * optimized synchronize_sched() to a simple barrier().  When this variable
+ * optimize synchronize_sched() to a simple barrier().  When this variable
  * is one, RCU must actually do all the hard work required to detect real
  * grace periods.  This variable is also used to suppress boot-time false
  * positives from lockdep-RCU error checking.
@@ -217,18 +218,14 @@ module_param(blimit, long, 0444);
 module_param(qhimark, long, 0444);
 module_param(qlowmark, long, 0444);
 
-int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
-int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
-
-module_param(rcu_cpu_stall_suppress, int, 0644);
-module_param(rcu_cpu_stall_timeout, int, 0644);
-
 static ulong jiffies_till_first_fqs = RCU_JIFFIES_TILL_FORCE_QS;
 static ulong jiffies_till_next_fqs = RCU_JIFFIES_TILL_FORCE_QS;
 
 module_param(jiffies_till_first_fqs, ulong, 0644);
 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_quiescent_state(struct rcu_state *rsp);
 static int rcu_pending(int cpu);
@@ -305,17 +302,29 @@ cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp)
 }
 
 /*
- * Does the current CPU require a yet-as-unscheduled grace period?
+ * Does the current CPU require a not-yet-started grace period?
+ * The caller must have disabled interrupts to prevent races with
+ * normal callback registry.
  */
 static int
 cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
 {
-	struct rcu_head **ntp;
+	int i;
 
-	ntp = rdp->nxttail[RCU_DONE_TAIL +
-			   (ACCESS_ONCE(rsp->completed) != rdp->completed)];
-	return rdp->nxttail[RCU_DONE_TAIL] && ntp && *ntp &&
-	       !rcu_gp_in_progress(rsp);
+	if (rcu_gp_in_progress(rsp))
+		return 0;  /* No, a grace period is already in progress. */
+	if (rcu_nocb_needs_gp(rsp))
+		return 1;  /* Yes, a no-CBs CPU needs one. */
+	if (!rdp->nxttail[RCU_NEXT_TAIL])
+		return 0;  /* No, this is a no-CBs (or offline) CPU. */
+	if (*rdp->nxttail[RCU_NEXT_READY_TAIL])
+		return 1;  /* Yes, this CPU has newly registered callbacks. */
+	for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++)
+		if (rdp->nxttail[i - 1] != rdp->nxttail[i] &&
+		    ULONG_CMP_LT(ACCESS_ONCE(rsp->completed),
+				 rdp->nxtcompleted[i]))
+			return 1;  /* Yes, CBs for future grace period. */
+	return 0; /* No grace period needed. */
 }
 
 /*
@@ -336,7 +345,7 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
 static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
 				bool user)
 {
-	trace_rcu_dyntick("Start", oldval, 0);
+	trace_rcu_dyntick("Start", oldval, rdtp->dynticks_nesting);
 	if (!user && !is_idle_task(current)) {
 		struct task_struct *idle = idle_task(smp_processor_id());
 
@@ -727,7 +736,7 @@ EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);
  * interrupt from idle, return true.  The caller must have at least
  * disabled preemption.
  */
-int rcu_is_cpu_rrupt_from_idle(void)
+static int rcu_is_cpu_rrupt_from_idle(void)
 {
 	return __get_cpu_var(rcu_dynticks).dynticks_nesting <= 1;
 }
@@ -790,31 +799,23 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 		rdp->offline_fqs++;
 		return 1;
 	}
-	return 0;
-}
-
-static int jiffies_till_stall_check(void)
-{
-	int till_stall_check = ACCESS_ONCE(rcu_cpu_stall_timeout);
 
 	/*
-	 * Limit check must be consistent with the Kconfig limits
-	 * for CONFIG_RCU_CPU_STALL_TIMEOUT.
+	 * There is a possibility that a CPU in adaptive-ticks state
+	 * might run in the kernel with the scheduling-clock tick disabled
+	 * for an extended time period.  Invoke rcu_kick_nohz_cpu() to
+	 * force the CPU to restart the scheduling-clock tick in this
+	 * CPU is in this state.
 	 */
-	if (till_stall_check < 3) {
-		ACCESS_ONCE(rcu_cpu_stall_timeout) = 3;
-		till_stall_check = 3;
-	} else if (till_stall_check > 300) {
-		ACCESS_ONCE(rcu_cpu_stall_timeout) = 300;
-		till_stall_check = 300;
-	}
-	return till_stall_check * HZ + RCU_STALL_DELAY_DELTA;
+	rcu_kick_nohz_cpu(rdp->cpu);
+
+	return 0;
 }
 
 static void record_gp_stall_check_time(struct rcu_state *rsp)
 {
 	rsp->gp_start = jiffies;
-	rsp->jiffies_stall = jiffies + jiffies_till_stall_check();
+	rsp->jiffies_stall = jiffies + rcu_jiffies_till_stall_check();
 }
 
 /*
@@ -857,7 +858,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
 	}
-	rsp->jiffies_stall = jiffies + 3 * jiffies_till_stall_check() + 3;
+	rsp->jiffies_stall = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
 	/*
@@ -935,7 +936,7 @@ static void print_cpu_stall(struct rcu_state *rsp)
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	if (ULONG_CMP_GE(jiffies, rsp->jiffies_stall))
 		rsp->jiffies_stall = jiffies +
-				     3 * jiffies_till_stall_check() + 3;
+				     3 * rcu_jiffies_till_stall_check() + 3;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
 	set_need_resched();  /* kick ourselves to get things going. */
@@ -966,12 +967,6 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 	}
 }
 
-static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr)
-{
-	rcu_cpu_stall_suppress = 1;
-	return NOTIFY_DONE;
-}
-
 /**
  * rcu_cpu_stall_reset - prevent further stall warnings in current grace period
  *
@@ -989,15 +984,6 @@ void rcu_cpu_stall_reset(void)
 		rsp->jiffies_stall = jiffies + ULONG_MAX / 2;
 }
 
-static struct notifier_block rcu_panic_block = {
-	.notifier_call = rcu_panic,
-};
-
-static void __init check_cpu_stall_init(void)
-{
-	atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block);
-}
-
 /*
  * Update CPU-local rcu_data state to record the newly noticed grace period.
  * This is used both when we started the grace period and when we notice
@@ -1064,10 +1050,266 @@ static void init_callback_list(struct rcu_data *rdp)
 {
 	int i;
 
+	if (init_nocb_callback_list(rdp))
+		return;
 	rdp->nxtlist = NULL;
 	for (i = 0; i < RCU_NEXT_SIZE; i++)
 		rdp->nxttail[i] = &rdp->nxtlist;
-	init_nocb_callback_list(rdp);
+}
+
+/*
+ * Determine the value that ->completed will have at the end of the
+ * next subsequent grace period.  This is used to tag callbacks so that
+ * a CPU can invoke callbacks in a timely fashion even if that CPU has
+ * been dyntick-idle for an extended period with callbacks under the
+ * influence of RCU_FAST_NO_HZ.
+ *
+ * The caller must hold rnp->lock with interrupts disabled.
+ */
+static unsigned long rcu_cbs_completed(struct rcu_state *rsp,
+				       struct rcu_node *rnp)
+{
+	/*
+	 * If RCU is idle, we just wait for the next grace period.
+	 * But we can only be sure that RCU is idle if we are looking
+	 * at the root rcu_node structure -- otherwise, a new grace
+	 * period might have started, but just not yet gotten around
+	 * to initializing the current non-root rcu_node structure.
+	 */
+	if (rcu_get_root(rsp) == rnp && rnp->gpnum == rnp->completed)
+		return rnp->completed + 1;
+
+	/*
+	 * Otherwise, wait for a possible partial grace period and
+	 * then the subsequent full grace period.
+	 */
+	return rnp->completed + 2;
+}
+
+/*
+ * Trace-event helper function for rcu_start_future_gp() and
+ * rcu_nocb_wait_gp().
+ */
+static void trace_rcu_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
+				unsigned long c, char *s)
+{
+	trace_rcu_future_grace_period(rdp->rsp->name, rnp->gpnum,
+				      rnp->completed, c, rnp->level,
+				      rnp->grplo, rnp->grphi, s);
+}
+
+/*
+ * Start some future grace period, as needed to handle newly arrived
+ * callbacks.  The required future grace periods are recorded in each
+ * rcu_node structure's ->need_future_gp field.
+ *
+ * The caller must hold the specified rcu_node structure's ->lock.
+ */
+static unsigned long __maybe_unused
+rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp)
+{
+	unsigned long c;
+	int i;
+	struct rcu_node *rnp_root = rcu_get_root(rdp->rsp);
+
+	/*
+	 * Pick up grace-period number for new callbacks.  If this
+	 * grace period is already marked as needed, return to the caller.
+	 */
+	c = rcu_cbs_completed(rdp->rsp, rnp);
+	trace_rcu_future_gp(rnp, rdp, c, "Startleaf");
+	if (rnp->need_future_gp[c & 0x1]) {
+		trace_rcu_future_gp(rnp, rdp, c, "Prestartleaf");
+		return c;
+	}
+
+	/*
+	 * If either this rcu_node structure or the root rcu_node structure
+	 * believe that a grace period is in progress, then we must wait
+	 * for the one following, which is in "c".  Because our request
+	 * will be noticed at the end of the current grace period, we don't
+	 * need to explicitly start one.
+	 */
+	if (rnp->gpnum != rnp->completed ||
+	    ACCESS_ONCE(rnp->gpnum) != ACCESS_ONCE(rnp->completed)) {
+		rnp->need_future_gp[c & 0x1]++;
+		trace_rcu_future_gp(rnp, rdp, c, "Startedleaf");
+		return c;
+	}
+
+	/*
+	 * There might be no grace period in progress.  If we don't already
+	 * hold it, acquire the root rcu_node structure's lock in order to
+	 * start one (if needed).
+	 */
+	if (rnp != rnp_root)
+		raw_spin_lock(&rnp_root->lock);
+
+	/*
+	 * Get a new grace-period number.  If there really is no grace
+	 * period in progress, it will be smaller than the one we obtained
+	 * earlier.  Adjust callbacks as needed.  Note that even no-CBs
+	 * CPUs have a ->nxtcompleted[] array, so no no-CBs checks needed.
+	 */
+	c = rcu_cbs_completed(rdp->rsp, rnp_root);
+	for (i = RCU_DONE_TAIL; i < RCU_NEXT_TAIL; i++)
+		if (ULONG_CMP_LT(c, rdp->nxtcompleted[i]))
+			rdp->nxtcompleted[i] = c;
+
+	/*
+	 * If the needed for the required grace period is already
+	 * recorded, trace and leave.
+	 */
+	if (rnp_root->need_future_gp[c & 0x1]) {
+		trace_rcu_future_gp(rnp, rdp, c, "Prestartedroot");
+		goto unlock_out;
+	}
+
+	/* Record the need for the future grace period. */
+	rnp_root->need_future_gp[c & 0x1]++;
+
+	/* If a grace period is not already in progress, start one. */
+	if (rnp_root->gpnum != rnp_root->completed) {
+		trace_rcu_future_gp(rnp, rdp, c, "Startedleafroot");
+	} else {
+		trace_rcu_future_gp(rnp, rdp, c, "Startedroot");
+		rcu_start_gp_advanced(rdp->rsp, rnp_root, rdp);
+	}
+unlock_out:
+	if (rnp != rnp_root)
+		raw_spin_unlock(&rnp_root->lock);
+	return c;
+}
+
+/*
+ * Clean up any old requests for the just-ended grace period.  Also return
+ * whether any additional grace periods have been requested.  Also invoke
+ * rcu_nocb_gp_cleanup() in order to wake up any no-callbacks kthreads
+ * waiting for this grace period to complete.
+ */
+static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
+{
+	int c = rnp->completed;
+	int needmore;
+	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
+
+	rcu_nocb_gp_cleanup(rsp, rnp);
+	rnp->need_future_gp[c & 0x1] = 0;
+	needmore = rnp->need_future_gp[(c + 1) & 0x1];
+	trace_rcu_future_gp(rnp, rdp, c, needmore ? "CleanupMore" : "Cleanup");
+	return needmore;
+}
+
+/*
+ * If there is room, assign a ->completed number to any callbacks on
+ * this CPU that have not already been assigned.  Also accelerate any
+ * callbacks that were previously assigned a ->completed number that has
+ * since proven to be too conservative, which can happen if callbacks get
+ * assigned a ->completed number while RCU is idle, but with reference to
+ * a non-root rcu_node structure.  This function is idempotent, so it does
+ * not hurt to call it repeatedly.
+ *
+ * The caller must hold rnp->lock with interrupts disabled.
+ */
+static void rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
+			       struct rcu_data *rdp)
+{
+	unsigned long c;
+	int i;
+
+	/* If the CPU has no callbacks, nothing to do. */
+	if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL])
+		return;
+
+	/*
+	 * Starting from the sublist containing the callbacks most
+	 * recently assigned a ->completed number and working down, find the
+	 * first sublist that is not assignable to an upcoming grace period.
+	 * Such a sublist has something in it (first two tests) and has
+	 * a ->completed number assigned that will complete sooner than
+	 * the ->completed number for newly arrived callbacks (last test).
+	 *
+	 * The key point is that any later sublist can be assigned the
+	 * same ->completed number as the newly arrived callbacks, which
+	 * means that the callbacks in any of these later sublist can be
+	 * grouped into a single sublist, whether or not they have already
+	 * been assigned a ->completed number.
+	 */
+	c = rcu_cbs_completed(rsp, rnp);
+	for (i = RCU_NEXT_TAIL - 1; i > RCU_DONE_TAIL; i--)
+		if (rdp->nxttail[i] != rdp->nxttail[i - 1] &&
+		    !ULONG_CMP_GE(rdp->nxtcompleted[i], c))
+			break;
+
+	/*
+	 * If there are no sublist for unassigned callbacks, leave.
+	 * At the same time, advance "i" one sublist, so that "i" will
+	 * index into the sublist where all the remaining callbacks should
+	 * be grouped into.
+	 */
+	if (++i >= RCU_NEXT_TAIL)
+		return;
+
+	/*
+	 * Assign all subsequent callbacks' ->completed number to the next
+	 * full grace period and group them all in the sublist initially
+	 * indexed by "i".
+	 */
+	for (; i <= RCU_NEXT_TAIL; i++) {
+		rdp->nxttail[i] = rdp->nxttail[RCU_NEXT_TAIL];
+		rdp->nxtcompleted[i] = c;
+	}
+	/* Record any needed additional grace periods. */
+	rcu_start_future_gp(rnp, rdp);
+
+	/* Trace depending on how much we were able to accelerate. */
+	if (!*rdp->nxttail[RCU_WAIT_TAIL])
+		trace_rcu_grace_period(rsp->name, rdp->gpnum, "AccWaitCB");
+	else
+		trace_rcu_grace_period(rsp->name, rdp->gpnum, "AccReadyCB");
+}
+
+/*
+ * Move any callbacks whose grace period has completed to the
+ * RCU_DONE_TAIL sublist, then compact the remaining sublists and
+ * assign ->completed numbers to any callbacks in the RCU_NEXT_TAIL
+ * sublist.  This function is idempotent, so it does not hurt to
+ * invoke it repeatedly.  As long as it is not invoked -too- often...
+ *
+ * The caller must hold rnp->lock with interrupts disabled.
+ */
+static void rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
+			    struct rcu_data *rdp)
+{
+	int i, j;
+
+	/* If the CPU has no callbacks, nothing to do. */
+	if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL])
+		return;
+
+	/*
+	 * Find all callbacks whose ->completed numbers indicate that they
+	 * are ready to invoke, and put them into the RCU_DONE_TAIL sublist.
+	 */
+	for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++) {
+		if (ULONG_CMP_LT(rnp->completed, rdp->nxtcompleted[i]))
+			break;
+		rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[i];
+	}
+	/* Clean up any sublist tail pointers that were misordered above. */
+	for (j = RCU_WAIT_TAIL; j < i; j++)
+		rdp->nxttail[j] = rdp->nxttail[RCU_DONE_TAIL];
+
+	/* Copy down callbacks to fill in empty sublists. */
+	for (j = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++, j++) {
+		if (rdp->nxttail[j] == rdp->nxttail[RCU_NEXT_TAIL])
+			break;
+		rdp->nxttail[j] = rdp->nxttail[i];
+		rdp->nxtcompleted[j] = rdp->nxtcompleted[i];
+	}
+
+	/* Classify any remaining callbacks. */
+	rcu_accelerate_cbs(rsp, rnp, rdp);
 }
 
 /*
@@ -1080,12 +1322,15 @@ static void
 __rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
 {
 	/* Did another grace period end? */
-	if (rdp->completed != rnp->completed) {
+	if (rdp->completed == rnp->completed) {
+
+		/* No, so just accelerate recent callbacks. */
+		rcu_accelerate_cbs(rsp, rnp, rdp);
+
+	} else {
 
-		/* Advance callbacks.  No harm if list empty. */
-		rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[RCU_WAIT_TAIL];
-		rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_READY_TAIL];
-		rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+		/* Advance callbacks. */
+		rcu_advance_cbs(rsp, rnp, rdp);
 
 		/* Remember that we saw this grace-period completion. */
 		rdp->completed = rnp->completed;
@@ -1195,9 +1440,9 @@ static int rcu_gp_init(struct rcu_state *rsp)
 		rdp = this_cpu_ptr(rsp->rda);
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
-		rnp->gpnum = rsp->gpnum;
+		ACCESS_ONCE(rnp->gpnum) = rsp->gpnum;
 		WARN_ON_ONCE(rnp->completed != rsp->completed);
-		rnp->completed = rsp->completed;
+		ACCESS_ONCE(rnp->completed) = rsp->completed;
 		if (rnp == rdp->mynode)
 			rcu_start_gp_per_cpu(rsp, rnp, rdp);
 		rcu_preempt_boost_start_gp(rnp);
@@ -1206,7 +1451,8 @@ static int rcu_gp_init(struct rcu_state *rsp)
 					    rnp->grphi, rnp->qsmask);
 		raw_spin_unlock_irq(&rnp->lock);
 #ifdef CONFIG_PROVE_RCU_DELAY
-		if ((random32() % (rcu_num_nodes * 8)) == 0)
+		if ((prandom_u32() % (rcu_num_nodes * 8)) == 0 &&
+		    system_state == SYSTEM_RUNNING)
 			schedule_timeout_uninterruptible(2);
 #endif /* #ifdef CONFIG_PROVE_RCU_DELAY */
 		cond_resched();
@@ -1248,6 +1494,7 @@ int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 static void rcu_gp_cleanup(struct rcu_state *rsp)
 {
 	unsigned long gp_duration;
+	int nocb = 0;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
@@ -1277,17 +1524,23 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq(&rnp->lock);
-		rnp->completed = rsp->gpnum;
+		ACCESS_ONCE(rnp->completed) = rsp->gpnum;
+		rdp = this_cpu_ptr(rsp->rda);
+		if (rnp == rdp->mynode)
+			__rcu_process_gp_end(rsp, rnp, rdp);
+		nocb += rcu_future_gp_cleanup(rsp, rnp);
 		raw_spin_unlock_irq(&rnp->lock);
 		cond_resched();
 	}
 	rnp = rcu_get_root(rsp);
 	raw_spin_lock_irq(&rnp->lock);
+	rcu_nocb_gp_set(rnp, nocb);
 
 	rsp->completed = rsp->gpnum; /* Declare grace period done. */
 	trace_rcu_grace_period(rsp->name, rsp->completed, "end");
 	rsp->fqs_state = RCU_GP_IDLE;
 	rdp = this_cpu_ptr(rsp->rda);
+	rcu_advance_cbs(rsp, rnp, rdp);  /* Reduce false positives below. */
 	if (cpu_needs_another_gp(rsp, rdp))
 		rsp->gp_flags = 1;
 	raw_spin_unlock_irq(&rnp->lock);
@@ -1363,64 +1616,62 @@ static int __noreturn rcu_gp_kthread(void *arg)
 /*
  * Start a new RCU grace period if warranted, re-initializing the hierarchy
  * in preparation for detecting the next grace period.  The caller must hold
- * the root node's ->lock, which is released before return.  Hard irqs must
- * be disabled.
+ * the root node's ->lock and hard irqs must be disabled.
  *
  * Note that it is legal for a dying CPU (which is marked as offline) to
  * invoke this function.  This can happen when the dying CPU reports its
  * quiescent state.
  */
 static void
-rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
-	__releases(rcu_get_root(rsp)->lock)
+rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
+		      struct rcu_data *rdp)
 {
-	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
-	struct rcu_node *rnp = rcu_get_root(rsp);
-
-	if (!rsp->gp_kthread ||
-	    !cpu_needs_another_gp(rsp, rdp)) {
+	if (!rsp->gp_kthread || !cpu_needs_another_gp(rsp, rdp)) {
 		/*
 		 * Either we have not yet spawned the grace-period
 		 * task, this CPU does not need another grace period,
 		 * or a grace period is already in progress.
 		 * Either way, don't start a new grace period.
 		 */
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
 	}
-
-	/*
-	 * Because there is no grace period in progress right now,
-	 * any callbacks we have up to this point will be satisfied
-	 * by the next grace period.  So promote all callbacks to be
-	 * handled after the end of the next grace period.  If the
-	 * CPU is not yet aware of the end of the previous grace period,
-	 * we need to allow for the callback advancement that will
-	 * occur when it does become aware.  Deadlock prevents us from
-	 * making it aware at this point: We cannot acquire a leaf
-	 * rcu_node ->lock while holding the root rcu_node ->lock.
-	 */
-	rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
-	if (rdp->completed == rsp->completed)
-		rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
-
 	rsp->gp_flags = RCU_GP_FLAG_INIT;
-	raw_spin_unlock(&rnp->lock); /* Interrupts remain disabled. */
-
-	/* Ensure that CPU is aware of completion of last grace period. */
-	rcu_process_gp_end(rsp, rdp);
-	local_irq_restore(flags);
 
 	/* Wake up rcu_gp_kthread() to start the grace period. */
 	wake_up(&rsp->gp_wq);
 }
 
 /*
+ * Similar to rcu_start_gp_advanced(), but also advance the calling CPU's
+ * callbacks.  Note that rcu_start_gp_advanced() cannot do this because it
+ * is invoked indirectly from rcu_advance_cbs(), which would result in
+ * endless recursion -- or would do so if it wasn't for the self-deadlock
+ * that is encountered beforehand.
+ */
+static void
+rcu_start_gp(struct rcu_state *rsp)
+{
+	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
+	struct rcu_node *rnp = rcu_get_root(rsp);
+
+	/*
+	 * If there is no grace period in progress right now, any
+	 * callbacks we have up to this point will be satisfied by the
+	 * next grace period.  Also, advancing the callbacks reduces the
+	 * probability of false positives from cpu_needs_another_gp()
+	 * resulting in pointless grace periods.  So, advance callbacks
+	 * then start the grace period!
+	 */
+	rcu_advance_cbs(rsp, rnp, rdp);
+	rcu_start_gp_advanced(rsp, rnp, rdp);
+}
+
+/*
  * Report a full set of quiescent states to the specified rcu_state
  * data structure.  This involves cleaning up after the prior grace
  * period and letting rcu_start_gp() start up the next grace period
- * if one is needed.  Note that the caller must hold rnp->lock, as
- * required by rcu_start_gp(), which will release it.
+ * if one is needed.  Note that the caller must hold rnp->lock, which
+ * is released before return.
  */
 static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
 	__releases(rcu_get_root(rsp)->lock)
@@ -1527,7 +1778,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 		 * This GP can't end until cpu checks in, so all of our
 		 * callbacks can be processed during the next GP.
 		 */
-		rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+		rcu_accelerate_cbs(rsp, rnp, rdp);
 
 		rcu_report_qs_rnp(mask, rsp, rnp, flags); /* rlses rnp->lock */
 	}
@@ -1579,7 +1830,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
 			  struct rcu_node *rnp, struct rcu_data *rdp)
 {
 	/* No-CBs CPUs do not have orphanable callbacks. */
-	if (is_nocb_cpu(rdp->cpu))
+	if (rcu_is_nocb_cpu(rdp->cpu))
 		return;
 
 	/*
@@ -1779,7 +2030,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 	long bl, count, count_lazy;
 	int i;
 
-	/* If no callbacks are ready, just return.*/
+	/* If no callbacks are ready, just return. */
 	if (!cpu_has_callbacks_ready_to_invoke(rdp)) {
 		trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, 0);
 		trace_rcu_batch_end(rsp->name, 0, !!ACCESS_ONCE(rdp->nxtlist),
@@ -2008,19 +2259,20 @@ __rcu_process_callbacks(struct rcu_state *rsp)
 
 	WARN_ON_ONCE(rdp->beenonline == 0);
 
-	/*
-	 * Advance callbacks in response to end of earlier grace
-	 * period that some other CPU ended.
-	 */
+	/* Handle the end of a grace period that some other CPU ended.  */
 	rcu_process_gp_end(rsp, rdp);
 
 	/* Update RCU state based on any recent quiescent states. */
 	rcu_check_quiescent_state(rsp, rdp);
 
 	/* Does this CPU require a not-yet-started grace period? */
+	local_irq_save(flags);
 	if (cpu_needs_another_gp(rsp, rdp)) {
-		raw_spin_lock_irqsave(&rcu_get_root(rsp)->lock, flags);
-		rcu_start_gp(rsp, flags);  /* releases above lock */
+		raw_spin_lock(&rcu_get_root(rsp)->lock); /* irqs disabled. */
+		rcu_start_gp(rsp);
+		raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
+	} else {
+		local_irq_restore(flags);
 	}
 
 	/* If there are callbacks ready, invoke them. */
@@ -2063,7 +2315,8 @@ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
 
 static void invoke_rcu_core(void)
 {
-	raise_softirq(RCU_SOFTIRQ);
+	if (cpu_online(smp_processor_id()))
+		raise_softirq(RCU_SOFTIRQ);
 }
 
 /*
@@ -2098,11 +2351,11 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 
 		/* Start a new grace period if one not already started. */
 		if (!rcu_gp_in_progress(rsp)) {
-			unsigned long nestflag;
 			struct rcu_node *rnp_root = rcu_get_root(rsp);
 
-			raw_spin_lock_irqsave(&rnp_root->lock, nestflag);
-			rcu_start_gp(rsp, nestflag);  /* rlses rnp_root->lock */
+			raw_spin_lock(&rnp_root->lock);
+			rcu_start_gp(rsp);
+			raw_spin_unlock(&rnp_root->lock);
 		} else {
 			/* Give the grace period a kick. */
 			rdp->blimit = LONG_MAX;
@@ -2522,19 +2775,27 @@ static int rcu_pending(int cpu)
 }
 
 /*
- * Check to see if any future RCU-related work will need to be done
- * by the current CPU, even if none need be done immediately, returning
- * 1 if so.
+ * Return true if the specified CPU has any callback.  If all_lazy is
+ * non-NULL, store an indication of whether all callbacks are lazy.
+ * (If there are no callbacks, all of them are deemed to be lazy.)
  */
-static int rcu_cpu_has_callbacks(int cpu)
+static int rcu_cpu_has_callbacks(int cpu, bool *all_lazy)
 {
+	bool al = true;
+	bool hc = false;
+	struct rcu_data *rdp;
 	struct rcu_state *rsp;
 
-	/* RCU callbacks either ready or pending? */
-	for_each_rcu_flavor(rsp)
-		if (per_cpu_ptr(rsp->rda, cpu)->nxtlist)
-			return 1;
-	return 0;
+	for_each_rcu_flavor(rsp) {
+		rdp = per_cpu_ptr(rsp->rda, cpu);
+		if (rdp->qlen != rdp->qlen_lazy)
+			al = false;
+		if (rdp->nxtlist)
+			hc = true;
+	}
+	if (all_lazy)
+		*all_lazy = al;
+	return hc;
 }
 
 /*
@@ -2641,10 +2902,10 @@ static void _rcu_barrier(struct rcu_state *rsp)
 	 * corresponding CPU's preceding callbacks have been invoked.
 	 */
 	for_each_possible_cpu(cpu) {
-		if (!cpu_online(cpu) && !is_nocb_cpu(cpu))
+		if (!cpu_online(cpu) && !rcu_is_nocb_cpu(cpu))
 			continue;
 		rdp = per_cpu_ptr(rsp->rda, cpu);
-		if (is_nocb_cpu(cpu)) {
+		if (rcu_is_nocb_cpu(cpu)) {
 			_rcu_barrier_trace(rsp, "OnlineNoCB", cpu,
 					   rsp->n_barrier_done);
 			atomic_inc(&rsp->barrier_cpu_count);
@@ -2719,9 +2980,6 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
 	WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE);
 	WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1);
-#ifdef CONFIG_RCU_USER_QS
-	WARN_ON_ONCE(rdp->dynticks->in_user);
-#endif
 	rdp->cpu = cpu;
 	rdp->rsp = rsp;
 	rcu_boot_init_nocb_percpu_data(rdp);
@@ -2756,7 +3014,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible)
 	rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
 	atomic_set(&rdp->dynticks->dynticks,
 		   (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1);
-	rcu_prepare_for_idle_init(cpu);
 	raw_spin_unlock(&rnp->lock);		/* irqs remain disabled. */
 
 	/* Add CPU to rcu_node bitmasks. */
@@ -2806,7 +3063,6 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;
 	struct rcu_state *rsp;
-	int ret = NOTIFY_OK;
 
 	trace_rcu_utilization("Start CPU hotplug");
 	switch (action) {
@@ -2820,21 +3076,12 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 		rcu_boost_kthread_setaffinity(rnp, -1);
 		break;
 	case CPU_DOWN_PREPARE:
-		if (nocb_cpu_expendable(cpu))
-			rcu_boost_kthread_setaffinity(rnp, cpu);
-		else
-			ret = NOTIFY_BAD;
+		rcu_boost_kthread_setaffinity(rnp, cpu);
 		break;
 	case CPU_DYING:
 	case CPU_DYING_FROZEN:
-		/*
-		 * The whole machine is "stopped" except this CPU, so we can
-		 * touch any data without introducing corruption. We send the
-		 * dying CPU's callbacks to an arbitrarily chosen online CPU.
-		 */
 		for_each_rcu_flavor(rsp)
 			rcu_cleanup_dying_cpu(rsp);
-		rcu_cleanup_after_idle(cpu);
 		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
@@ -2847,7 +3094,7 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 		break;
 	}
 	trace_rcu_utilization("End CPU hotplug");
-	return ret;
+	return NOTIFY_OK;
 }
 
 /*
@@ -2938,6 +3185,10 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 
 	BUILD_BUG_ON(MAX_RCU_LVLS > ARRAY_SIZE(buf));  /* Fix buf[] init! */
 
+	/* Silence gcc 4.8 warning about array index out of range. */
+	if (rcu_num_lvls > RCU_NUM_LVLS)
+		panic("rcu_init_one: rcu_num_lvls overflow");
+
 	/* Initialize the level-tracking arrays. */
 
 	for (i = 0; i < rcu_num_lvls; i++)
@@ -2978,6 +3229,7 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 			}
 			rnp->level = i;
 			INIT_LIST_HEAD(&rnp->blkd_tasks);
+			rcu_init_one_nocb(rnp);
 		}
 	}
 
@@ -3063,8 +3315,7 @@ void __init rcu_init(void)
 	rcu_init_one(&rcu_sched_state, &rcu_sched_data);
 	rcu_init_one(&rcu_bh_state, &rcu_bh_data);
 	__rcu_init_preempt();
-	rcu_init_nocb();
-	 open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 
 	/*
 	 * We don't need protection against CPU-hotplug here because
@@ -3074,7 +3325,6 @@ void __init rcu_init(void)
 	cpu_notifier(rcu_cpu_notify, 0);
 	for_each_online_cpu(cpu)
 		rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
-	check_cpu_stall_init();
 }
 
 #include "rcutree_plugin.h"