Merge remote-tracking branch 'rcu/rcu/next'

4 files changed, 186 insertions, 222 deletions

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index dd4aea806f8e..0ac1cc03f935 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -128,7 +128,7 @@ void rcu_note_context_switch(int cpu)
 #ifdef CONFIG_NO_HZ
 DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 	.dynticks_nesting = 1,
-	.dynticks = 1,
+	.dynticks = ATOMIC_INIT(1),
 };
 #endif /* #ifdef CONFIG_NO_HZ */
 
@@ -140,10 +140,8 @@ module_param(blimit, int, 0);
 module_param(qhimark, int, 0);
 module_param(qlowmark, int, 0);
 
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-int rcu_cpu_stall_suppress __read_mostly = RCU_CPU_STALL_SUPPRESS_INIT;
+int rcu_cpu_stall_suppress __read_mostly;
 module_param(rcu_cpu_stall_suppress, int, 0644);
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
 static void force_quiescent_state(struct rcu_state *rsp, int relaxed);
 static int rcu_pending(int cpu);
@@ -264,13 +262,25 @@ void rcu_enter_nohz(void)
 	unsigned long flags;
 	struct rcu_dynticks *rdtp;
 
-	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
 	local_irq_save(flags);
 	rdtp = &__get_cpu_var(rcu_dynticks);
-	rdtp->dynticks++;
-	rdtp->dynticks_nesting--;
-	WARN_ON_ONCE(rdtp->dynticks & 0x1);
+	if (--rdtp->dynticks_nesting) {
+		local_irq_restore(flags);
+		return;
+	}
+	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
+	smp_mb__before_atomic_inc();  /* See above. */
+	atomic_inc(&rdtp->dynticks);
+	smp_mb__after_atomic_inc();  /* Force ordering with next sojourn. */
+	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
 	local_irq_restore(flags);
+
+	/* If the interrupt queued a callback, get out of dyntick mode. */
+	if (in_irq() &&
+	    (__get_cpu_var(rcu_sched_data).nxtlist ||
+	     __get_cpu_var(rcu_bh_data).nxtlist ||
+	     rcu_preempt_needs_cpu(smp_processor_id())))
+		set_need_resched();
 }
 
 /*
@@ -286,11 +296,16 @@ void rcu_exit_nohz(void)
 
 	local_irq_save(flags);
 	rdtp = &__get_cpu_var(rcu_dynticks);
-	rdtp->dynticks++;
-	rdtp->dynticks_nesting++;
-	WARN_ON_ONCE(!(rdtp->dynticks & 0x1));
+	if (rdtp->dynticks_nesting++) {
+		local_irq_restore(flags);
+		return;
+	}
+	smp_mb__before_atomic_inc();  /* Force ordering w/previous sojourn. */
+	atomic_inc(&rdtp->dynticks);
+	/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
+	smp_mb__after_atomic_inc();  /* See above. */
+	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
 	local_irq_restore(flags);
-	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
 }
 
 /**
@@ -304,11 +319,15 @@ void rcu_nmi_enter(void)
 {
 	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
 
-	if (rdtp->dynticks & 0x1)
+	if (rdtp->dynticks_nmi_nesting == 0 &&
+	    (atomic_read(&rdtp->dynticks) & 0x1))
 		return;
-	rdtp->dynticks_nmi++;
-	WARN_ON_ONCE(!(rdtp->dynticks_nmi & 0x1));
-	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
+	rdtp->dynticks_nmi_nesting++;
+	smp_mb__before_atomic_inc();  /* Force delay from prior write. */
+	atomic_inc(&rdtp->dynticks);
+	/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
+	smp_mb__after_atomic_inc();  /* See above. */
+	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
 }
 
 /**
@@ -322,11 +341,14 @@ void rcu_nmi_exit(void)
 {
 	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
 
-	if (rdtp->dynticks & 0x1)
+	if (rdtp->dynticks_nmi_nesting == 0 ||
+	    --rdtp->dynticks_nmi_nesting != 0)
 		return;
-	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
-	rdtp->dynticks_nmi++;
-	WARN_ON_ONCE(rdtp->dynticks_nmi & 0x1);
+	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
+	smp_mb__before_atomic_inc();  /* See above. */
+	atomic_inc(&rdtp->dynticks);
+	smp_mb__after_atomic_inc();  /* Force delay to next write. */
+	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
 }
 
 /**
@@ -337,13 +359,7 @@ void rcu_nmi_exit(void)
  */
 void rcu_irq_enter(void)
 {
-	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
-
-	if (rdtp->dynticks_nesting++)
-		return;
-	rdtp->dynticks++;
-	WARN_ON_ONCE(!(rdtp->dynticks & 0x1));
-	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
+	rcu_exit_nohz();
 }
 
 /**
@@ -355,18 +371,7 @@ void rcu_irq_enter(void)
  */
 void rcu_irq_exit(void)
 {
-	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
-
-	if (--rdtp->dynticks_nesting)
-		return;
-	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
-	rdtp->dynticks++;
-	WARN_ON_ONCE(rdtp->dynticks & 0x1);
-
-	/* If the interrupt queued a callback, get out of dyntick mode. */
-	if (__this_cpu_read(rcu_sched_data.nxtlist) ||
-	    __this_cpu_read(rcu_bh_data.nxtlist))
-		set_need_resched();
+	rcu_enter_nohz();
 }
 
 #ifdef CONFIG_SMP
@@ -378,19 +383,8 @@ void rcu_irq_exit(void)
  */
 static int dyntick_save_progress_counter(struct rcu_data *rdp)
 {
-	int ret;
-	int snap;
-	int snap_nmi;
-
-	snap = rdp->dynticks->dynticks;
-	snap_nmi = rdp->dynticks->dynticks_nmi;
-	smp_mb();	/* Order sampling of snap with end of grace period. */
-	rdp->dynticks_snap = snap;
-	rdp->dynticks_nmi_snap = snap_nmi;
-	ret = ((snap & 0x1) == 0) && ((snap_nmi & 0x1) == 0);
-	if (ret)
-		rdp->dynticks_fqs++;
-	return ret;
+	rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks);
+	return 0;
 }
 
 /*
@@ -401,16 +395,11 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
  */
 static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 {
-	long curr;
-	long curr_nmi;
-	long snap;
-	long snap_nmi;
+	unsigned long curr;
+	unsigned long snap;
 
-	curr = rdp->dynticks->dynticks;
-	snap = rdp->dynticks_snap;
-	curr_nmi = rdp->dynticks->dynticks_nmi;
-	snap_nmi = rdp->dynticks_nmi_snap;
-	smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
+	curr = (unsigned long)atomic_add_return(0, &rdp->dynticks->dynticks);
+	snap = (unsigned long)rdp->dynticks_snap;
 
 	/*
 	 * If the CPU passed through or entered a dynticks idle phase with
@@ -420,8 +409,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	 * read-side critical section that started before the beginning
 	 * of the current RCU grace period.
 	 */
-	if ((curr != snap || (curr & 0x1) == 0) &&
-	    (curr_nmi != snap_nmi || (curr_nmi & 0x1) == 0)) {
+	if ((curr & 0x1) == 0 || ULONG_CMP_GE(curr, snap + 2)) {
 		rdp->dynticks_fqs++;
 		return 1;
 	}
@@ -450,8 +438,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 
 #endif /* #else #ifdef CONFIG_NO_HZ */
 
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-
 int rcu_cpu_stall_suppress __read_mostly;
 
 static void record_gp_stall_check_time(struct rcu_state *rsp)
@@ -587,26 +573,6 @@ static void __init check_cpu_stall_init(void)
 	atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block);
 }
 
-#else /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-
-static void record_gp_stall_check_time(struct rcu_state *rsp)
-{
-}
-
-static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
-{
-}
-
-void rcu_cpu_stall_reset(void)
-{
-}
-
-static void __init check_cpu_stall_init(void)
-{
-}
-
-#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-
 /*
  * 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
@@ -865,6 +831,12 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
 	__releases(rcu_get_root(rsp)->lock)
 {
 	WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
+
+	/*
+	 * Ensure that all grace-period and pre-grace-period activity
+	 * is seen before the assignment to rsp->completed.
+	 */
+	smp_mb(); /* See above block comment. */
 	rsp->completed = rsp->gpnum;
 	rsp->signaled = RCU_GP_IDLE;
 	rcu_start_gp(rsp, flags);  /* releases root node's rnp->lock. */
@@ -1391,25 +1363,11 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
  */
 static void rcu_process_callbacks(struct softirq_action *unused)
 {
-	/*
-	 * Memory references from any prior RCU read-side critical sections
-	 * executed by the interrupted code must be seen before any RCU
-	 * grace-period manipulations below.
-	 */
-	smp_mb(); /* See above block comment. */
-
 	__rcu_process_callbacks(&rcu_sched_state,
 				&__get_cpu_var(rcu_sched_data));
 	__rcu_process_callbacks(&rcu_bh_state, &__get_cpu_var(rcu_bh_data));
 	rcu_preempt_process_callbacks();
 
-	/*
-	 * Memory references from any later RCU read-side critical sections
-	 * executed by the interrupted code must be seen after any RCU
-	 * grace-period manipulations above.
-	 */
-	smp_mb(); /* See above block comment. */
-
 	/* If we are last CPU on way to dyntick-idle mode, accelerate it. */
 	rcu_needs_cpu_flush();
 }
@@ -1943,10 +1901,7 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 					      j / rsp->levelspread[i - 1];
 			}
 			rnp->level = i;
-			INIT_LIST_HEAD(&rnp->blocked_tasks[0]);
-			INIT_LIST_HEAD(&rnp->blocked_tasks[1]);
-			INIT_LIST_HEAD(&rnp->blocked_tasks[2]);
-			INIT_LIST_HEAD(&rnp->blocked_tasks[3]);
+			INIT_LIST_HEAD(&rnp->blkd_tasks);
 		}
 	}
 
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index e8f057e44e3e..5a439c180e69 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -84,11 +84,9 @@
  * Dynticks per-CPU state.
  */
 struct rcu_dynticks {
-	int dynticks_nesting;	/* Track nesting level, sort of. */
-	int dynticks;		/* Even value for dynticks-idle, else odd. */
-	int dynticks_nmi;	/* Even value for either dynticks-idle or */
-				/*  not in nmi handler, else odd.  So this */
-				/*  remains even for nmi from irq handler. */
+	int dynticks_nesting;	/* Track irq/process nesting level. */
+	int dynticks_nmi_nesting; /* Track NMI nesting level. */
+	atomic_t dynticks;	/* Even value for dynticks-idle, else odd. */
 };
 
 /*
@@ -109,7 +107,7 @@ struct rcu_node {
 				/*  an rcu_data structure, otherwise, each */
 				/*  bit corresponds to a child rcu_node */
 				/*  structure. */
-	unsigned long expmask;	/* Groups that have ->blocked_tasks[] */
+	unsigned long expmask;	/* Groups that have ->blkd_tasks */
 				/*  elements that need to drain to allow the */
 				/*  current expedited grace period to */
 				/*  complete (only for TREE_PREEMPT_RCU). */
@@ -122,11 +120,20 @@ struct rcu_node {
 	u8	grpnum;		/* CPU/group number for next level up. */
 	u8	level;		/* root is at level 0. */
 	struct rcu_node *parent;
-	struct list_head blocked_tasks[4];
-				/* Tasks blocked in RCU read-side critsect. */
-				/*  Grace period number (->gpnum) x blocked */
-				/*  by tasks on the (x & 0x1) element of the */
-				/*  blocked_tasks[] array. */
+	struct list_head blkd_tasks;
+				/* Tasks blocked in RCU read-side critical */
+				/*  section.  Tasks are placed at the head */
+				/*  of this list and age towards the tail. */
+	struct list_head *gp_tasks;
+				/* Pointer to the first task blocking the */
+				/*  current grace period, or NULL if there */
+				/*  is no such task. */
+	struct list_head *exp_tasks;
+				/* Pointer to the first task blocking the */
+				/*  current expedited grace period, or NULL */
+				/*  if there is no such task.  If there */
+				/*  is no current expedited grace period, */
+				/*  then there can cannot be any such task. */
 } ____cacheline_internodealigned_in_smp;
 
 /*
@@ -218,7 +225,6 @@ struct rcu_data {
 	/* 3) dynticks interface. */
 	struct rcu_dynticks *dynticks;	/* Shared per-CPU dynticks state. */
 	int dynticks_snap;		/* Per-GP tracking for dynticks. */
-	int dynticks_nmi_snap;		/* Per-GP tracking for dynticks_nmi. */
 #endif /* #ifdef CONFIG_NO_HZ */
 
 	/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
@@ -254,7 +260,6 @@ struct rcu_data {
 #endif /* #else #ifdef CONFIG_NO_HZ */
 
 #define RCU_JIFFIES_TILL_FORCE_QS	 3	/* for rsp->jiffies_force_qs */
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 
 #ifdef CONFIG_PROVE_RCU
 #define RCU_STALL_DELAY_DELTA	       (5 * HZ)
@@ -272,13 +277,6 @@ struct rcu_data {
 						/*  scheduling clock irq */
 						/*  before ratting on them. */
 
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR_RUNNABLE
-#define RCU_CPU_STALL_SUPPRESS_INIT 0
-#else
-#define RCU_CPU_STALL_SUPPRESS_INIT 1
-#endif
-
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
 /*
  * RCU global state, including node hierarchy.  This hierarchy is
@@ -325,12 +323,10 @@ struct rcu_state {
 						/*  due to lock unavailable. */
 	unsigned long n_force_qs_ngp;		/* Number of calls leaving */
 						/*  due to no GP active. */
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 	unsigned long gp_start;			/* Time at which GP started, */
 						/*  but in jiffies. */
 	unsigned long jiffies_stall;		/* Time at which to check */
 						/*  for CPU stalls. */
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 	char *name;				/* Name of structure. */
 };
 
@@ -366,11 +362,9 @@ static int rcu_preempted_readers(struct rcu_node *rnp);
 static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,
 				      unsigned long flags);
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 static void rcu_print_detail_task_stall(struct rcu_state *rsp);
 static void rcu_print_task_stall(struct rcu_node *rnp);
 static void rcu_preempt_stall_reset(void);
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
 static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index a3638710dc67..774f010a4619 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -54,10 +54,6 @@ static void __init rcu_bootup_announce_oddness(void)
 #ifdef CONFIG_RCU_TORTURE_TEST_RUNNABLE
 	printk(KERN_INFO "\tRCU torture testing starts during boot.\n");
 #endif
-#ifndef CONFIG_RCU_CPU_STALL_DETECTOR
-	printk(KERN_INFO
-	       "\tRCU-based detection of stalled CPUs is disabled.\n");
-#endif
 #if defined(CONFIG_TREE_PREEMPT_RCU) && !defined(CONFIG_RCU_CPU_STALL_VERBOSE)
 	printk(KERN_INFO "\tVerbose stalled-CPUs detection is disabled.\n");
 #endif
@@ -134,12 +130,12 @@ static void rcu_preempt_qs(int cpu)
  * We have entered the scheduler, and the current task might soon be
  * context-switched away from.  If this task is in an RCU read-side
  * critical section, we will no longer be able to rely on the CPU to
- * record that fact, so we enqueue the task on the appropriate entry
- * of the blocked_tasks[] array.  The task will dequeue itself when
- * it exits the outermost enclosing RCU read-side critical section.
- * Therefore, the current grace period cannot be permitted to complete
- * until the blocked_tasks[] entry indexed by the low-order bit of
- * rnp->gpnum empties.
+ * record that fact, so we enqueue the task on the blkd_tasks list.
+ * The task will dequeue itself when it exits the outermost enclosing
+ * RCU read-side critical section.  Therefore, the current grace period
+ * cannot be permitted to complete until the blkd_tasks list entries
+ * predating the current grace period drain, in other words, until
+ * rnp->gp_tasks becomes NULL.
  *
  * Caller must disable preemption.
  */
@@ -147,7 +143,6 @@ static void rcu_preempt_note_context_switch(int cpu)
 {
 	struct task_struct *t = current;
 	unsigned long flags;
-	int phase;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 
@@ -169,15 +164,26 @@ static void rcu_preempt_note_context_switch(int cpu)
 		 * (i.e., this CPU has not yet passed through a quiescent
 		 * state for the current grace period), then as long
 		 * as that task remains queued, the current grace period
-		 * cannot end.
+		 * cannot end.  Note that there is some uncertainty as
+		 * to exactly when the current grace period started.
+		 * We take a conservative approach, which can result
+		 * in unnecessarily waiting on tasks that started very
+		 * slightly after the current grace period began.  C'est
+		 * la vie!!!
 		 *
 		 * But first, note that the current CPU must still be
 		 * on line!
 		 */
 		WARN_ON_ONCE((rdp->grpmask & rnp->qsmaskinit) == 0);
 		WARN_ON_ONCE(!list_empty(&t->rcu_node_entry));
-		phase = (rnp->gpnum + !(rnp->qsmask & rdp->grpmask)) & 0x1;
-		list_add(&t->rcu_node_entry, &rnp->blocked_tasks[phase]);
+		if ((rnp->qsmask & rdp->grpmask) && rnp->gp_tasks != NULL) {
+			list_add(&t->rcu_node_entry, rnp->gp_tasks->prev);
+			rnp->gp_tasks = &t->rcu_node_entry;
+		} else {
+			list_add(&t->rcu_node_entry, &rnp->blkd_tasks);
+			if (rnp->qsmask & rdp->grpmask)
+				rnp->gp_tasks = &t->rcu_node_entry;
+		}
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	}
 
@@ -214,10 +220,7 @@ EXPORT_SYMBOL_GPL(__rcu_read_lock);
  */
 static int rcu_preempted_readers(struct rcu_node *rnp)
 {
-	int phase = rnp->gpnum & 0x1;
-
-	return !list_empty(&rnp->blocked_tasks[phase]) ||
-	       !list_empty(&rnp->blocked_tasks[phase + 2]);
+	return rnp->gp_tasks != NULL;
 }
 
 /*
@@ -257,6 +260,21 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
 }
 
 /*
+ * Advance a ->blkd_tasks-list pointer to the next entry, instead
+ * returning NULL if at the end of the list.
+ */
+static struct list_head *rcu_next_node_entry(struct task_struct *t,
+					     struct rcu_node *rnp)
+{
+	struct list_head *np;
+
+	np = t->rcu_node_entry.next;
+	if (np == &rnp->blkd_tasks)
+		np = NULL;
+	return np;
+}
+
+/*
  * Handle special cases during rcu_read_unlock(), such as needing to
  * notify RCU core processing or task having blocked during the RCU
  * read-side critical section.
@@ -266,6 +284,7 @@ static void rcu_read_unlock_special(struct task_struct *t)
 	int empty;
 	int empty_exp;
 	unsigned long flags;
+	struct list_head *np;
 	struct rcu_node *rnp;
 	int special;
 
@@ -309,7 +328,12 @@ static void rcu_read_unlock_special(struct task_struct *t)
 		empty = !rcu_preempted_readers(rnp);
 		empty_exp = !rcu_preempted_readers_exp(rnp);
 		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
+		np = rcu_next_node_entry(t, rnp);
 		list_del_init(&t->rcu_node_entry);
+		if (&t->rcu_node_entry == rnp->gp_tasks)
+			rnp->gp_tasks = np;
+		if (&t->rcu_node_entry == rnp->exp_tasks)
+			rnp->exp_tasks = np;
 		t->rcu_blocked_node = NULL;
 
 		/*
@@ -356,8 +380,6 @@ void __rcu_read_unlock(void)
 }
 EXPORT_SYMBOL_GPL(__rcu_read_unlock);
 
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-
 #ifdef CONFIG_RCU_CPU_STALL_VERBOSE
 
 /*
@@ -367,18 +389,16 @@ EXPORT_SYMBOL_GPL(__rcu_read_unlock);
 static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
 {
 	unsigned long flags;
-	struct list_head *lp;
-	int phase;
 	struct task_struct *t;
 
-	if (rcu_preempted_readers(rnp)) {
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		phase = rnp->gpnum & 0x1;
-		lp = &rnp->blocked_tasks[phase];
-		list_for_each_entry(t, lp, rcu_node_entry)
-			sched_show_task(t);
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-	}
+	if (!rcu_preempted_readers(rnp))
+		return;
+	raw_spin_lock_irqsave(&rnp->lock, flags);
+	t = list_entry(rnp->gp_tasks,
+		       struct task_struct, rcu_node_entry);
+	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry)
+		sched_show_task(t);
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
 
 /*
@@ -408,16 +428,14 @@ static void rcu_print_detail_task_stall(struct rcu_state *rsp)
  */
 static void rcu_print_task_stall(struct rcu_node *rnp)
 {
-	struct list_head *lp;
-	int phase;
 	struct task_struct *t;
 
-	if (rcu_preempted_readers(rnp)) {
-		phase = rnp->gpnum & 0x1;
-		lp = &rnp->blocked_tasks[phase];
-		list_for_each_entry(t, lp, rcu_node_entry)
-			printk(" P%d", t->pid);
-	}
+	if (!rcu_preempted_readers(rnp))
+		return;
+	t = list_entry(rnp->gp_tasks,
+		       struct task_struct, rcu_node_entry);
+	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry)
+		printk(" P%d", t->pid);
 }
 
 /*
@@ -430,18 +448,21 @@ static void rcu_preempt_stall_reset(void)
 	rcu_preempt_state.jiffies_stall = jiffies + ULONG_MAX / 2;
 }
 
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-
 /*
  * Check that the list of blocked tasks for the newly completed grace
  * period is in fact empty.  It is a serious bug to complete a grace
  * period that still has RCU readers blocked!  This function must be
  * invoked -before- updating this rnp's ->gpnum, and the rnp's ->lock
  * must be held by the caller.
+ *
+ * Also, if there are blocked tasks on the list, they automatically
+ * block the newly created grace period, so set up ->gp_tasks accordingly.
  */
 static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
 {
 	WARN_ON_ONCE(rcu_preempted_readers(rnp));
+	if (!list_empty(&rnp->blkd_tasks))
+		rnp->gp_tasks = rnp->blkd_tasks.next;
 	WARN_ON_ONCE(rnp->qsmask);
 }
 
@@ -465,45 +486,49 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
 				     struct rcu_node *rnp,
 				     struct rcu_data *rdp)
 {
-	int i;
 	struct list_head *lp;
 	struct list_head *lp_root;
 	int retval = 0;
 	struct rcu_node *rnp_root = rcu_get_root(rsp);
-	struct task_struct *tp;
+	struct task_struct *t;
 
 	if (rnp == rnp_root) {
 		WARN_ONCE(1, "Last CPU thought to be offlined?");
 		return 0;  /* Shouldn't happen: at least one CPU online. */
 	}
-	WARN_ON_ONCE(rnp != rdp->mynode &&
-		     (!list_empty(&rnp->blocked_tasks[0]) ||
-		      !list_empty(&rnp->blocked_tasks[1]) ||
-		      !list_empty(&rnp->blocked_tasks[2]) ||
-		      !list_empty(&rnp->blocked_tasks[3])));
+
+	/* If we are on an internal node, complain bitterly. */
+	WARN_ON_ONCE(rnp != rdp->mynode);
 
 	/*
-	 * Move tasks up to root rcu_node.  Rely on the fact that the
-	 * root rcu_node can be at most one ahead of the rest of the
-	 * rcu_nodes in terms of gp_num value.  This fact allows us to
-	 * move the blocked_tasks[] array directly, element by element.
+	 * Move tasks up to root rcu_node.  Don't try to get fancy for
+	 * this corner-case operation -- just put this node's tasks
+	 * at the head of the root node's list, and update the root node's
+	 * ->gp_tasks and ->exp_tasks pointers to those of this node's,
+	 * if non-NULL.  This might result in waiting for more tasks than
+	 * absolutely necessary, but this is a good performance/complexity
+	 * tradeoff.
 	 */
 	if (rcu_preempted_readers(rnp))
 		retval |= RCU_OFL_TASKS_NORM_GP;
 	if (rcu_preempted_readers_exp(rnp))
 		retval |= RCU_OFL_TASKS_EXP_GP;
-	for (i = 0; i < 4; i++) {
-		lp = &rnp->blocked_tasks[i];
-		lp_root = &rnp_root->blocked_tasks[i];
-		while (!list_empty(lp)) {
-			tp = list_entry(lp->next, typeof(*tp), rcu_node_entry);
-			raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
-			list_del(&tp->rcu_node_entry);
-			tp->rcu_blocked_node = rnp_root;
-			list_add(&tp->rcu_node_entry, lp_root);
-			raw_spin_unlock(&rnp_root->lock); /* irqs remain disabled */
-		}
+	lp = &rnp->blkd_tasks;
+	lp_root = &rnp_root->blkd_tasks;
+	while (!list_empty(lp)) {
+		t = list_entry(lp->next, typeof(*t), rcu_node_entry);
+		raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+		list_del(&t->rcu_node_entry);
+		t->rcu_blocked_node = rnp_root;
+		list_add(&t->rcu_node_entry, lp_root);
+		if (&t->rcu_node_entry == rnp->gp_tasks)
+			rnp_root->gp_tasks = rnp->gp_tasks;
+		if (&t->rcu_node_entry == rnp->exp_tasks)
+			rnp_root->exp_tasks = rnp->exp_tasks;
+		raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */
 	}
+	rnp->gp_tasks = NULL;
+	rnp->exp_tasks = NULL;
 	return retval;
 }
 
@@ -594,8 +619,7 @@ static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex);
  */
 static int rcu_preempted_readers_exp(struct rcu_node *rnp)
 {
-	return !list_empty(&rnp->blocked_tasks[2]) ||
-	       !list_empty(&rnp->blocked_tasks[3]);
+	return rnp->exp_tasks != NULL;
 }
 
 /*
@@ -655,12 +679,13 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
 static void
 sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
 {
-	int must_wait;
+	int must_wait = 0;
 
 	raw_spin_lock(&rnp->lock); /* irqs already disabled */
-	list_splice_init(&rnp->blocked_tasks[0], &rnp->blocked_tasks[2]);
-	list_splice_init(&rnp->blocked_tasks[1], &rnp->blocked_tasks[3]);
-	must_wait = rcu_preempted_readers_exp(rnp);
+	if (!list_empty(&rnp->blkd_tasks)) {
+		rnp->exp_tasks = rnp->blkd_tasks.next;
+		must_wait = 1;
+	}
 	raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
 	if (!must_wait)
 		rcu_report_exp_rnp(rsp, rnp);
@@ -669,9 +694,7 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
 /*
  * Wait for an rcu-preempt grace period, but expedite it.  The basic idea
  * is to invoke synchronize_sched_expedited() to push all the tasks to
- * the ->blocked_tasks[] lists, move all entries from the first set of
- * ->blocked_tasks[] lists to the second set, and finally wait for this
- * second set to drain.
+ * the ->blkd_tasks lists and wait for this list to drain.
  */
 void synchronize_rcu_expedited(void)
 {
@@ -703,7 +726,7 @@ void synchronize_rcu_expedited(void)
 	if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0)
 		goto unlock_mb_ret; /* Others did our work for us. */
 
-	/* force all RCU readers onto blocked_tasks[]. */
+	/* force all RCU readers onto ->blkd_tasks lists. */
 	synchronize_sched_expedited();
 
 	raw_spin_lock_irqsave(&rsp->onofflock, flags);
@@ -715,7 +738,7 @@ void synchronize_rcu_expedited(void)
 		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 	}
 
-	/* Snapshot current state of ->blocked_tasks[] lists. */
+	/* Snapshot current state of ->blkd_tasks lists. */
 	rcu_for_each_leaf_node(rsp, rnp)
 		sync_rcu_preempt_exp_init(rsp, rnp);
 	if (NUM_RCU_NODES > 1)
@@ -723,7 +746,7 @@ void synchronize_rcu_expedited(void)
 
 	raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
 
-	/* Wait for snapshotted ->blocked_tasks[] lists to drain. */
+	/* Wait for snapshotted ->blkd_tasks lists to drain. */
 	rnp = rcu_get_root(rsp);
 	wait_event(sync_rcu_preempt_exp_wq,
 		   sync_rcu_preempt_exp_done(rnp));
@@ -862,8 +885,6 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
 
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-
 /*
  * Because preemptable RCU does not exist, we never have to check for
  * tasks blocked within RCU read-side critical sections.
@@ -888,8 +909,6 @@ static void rcu_preempt_stall_reset(void)
 {
 }
 
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-
 /*
  * Because there is no preemptable RCU, there can be no readers blocked,
  * so there is no need to check for blocked tasks.  So check only for
@@ -1194,7 +1213,6 @@ int rcu_needs_cpu(int cpu)
 {
 	int c = 0;
 	int snap;
-	int snap_nmi;
 	int thatcpu;
 
 	/* Check for being in the holdoff period. */
@@ -1205,10 +1223,10 @@ int rcu_needs_cpu(int cpu)
 	for_each_online_cpu(thatcpu) {
 		if (thatcpu == cpu)
 			continue;
-		snap = per_cpu(rcu_dynticks, thatcpu).dynticks;
-		snap_nmi = per_cpu(rcu_dynticks, thatcpu).dynticks_nmi;
+		snap = atomic_add_return(0, &per_cpu(rcu_dynticks,
+						     thatcpu).dynticks);
 		smp_mb(); /* Order sampling of snap with end of grace period. */
-		if (((snap & 0x1) != 0) || ((snap_nmi & 0x1) != 0)) {
+		if ((snap & 0x1) != 0) {
 			per_cpu(rcu_dyntick_drain, cpu) = 0;
 			per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
 			return rcu_needs_cpu_quick_check(cpu);
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index c8e97853b970..1cedf94e2c4f 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -57,10 +57,10 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->passed_quiesc, rdp->passed_quiesc_completed,
 		   rdp->qs_pending);
 #ifdef CONFIG_NO_HZ
-	seq_printf(m, " dt=%d/%d dn=%d df=%lu",
-		   rdp->dynticks->dynticks,
+	seq_printf(m, " dt=%d/%d/%d df=%lu",
+		   atomic_read(&rdp->dynticks->dynticks),
 		   rdp->dynticks->dynticks_nesting,
-		   rdp->dynticks->dynticks_nmi,
+		   rdp->dynticks->dynticks_nmi_nesting,
 		   rdp->dynticks_fqs);
 #endif /* #ifdef CONFIG_NO_HZ */
 	seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi);
@@ -115,9 +115,9 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->qs_pending);
 #ifdef CONFIG_NO_HZ
 	seq_printf(m, ",%d,%d,%d,%lu",
-		   rdp->dynticks->dynticks,
+		   atomic_read(&rdp->dynticks->dynticks),
 		   rdp->dynticks->dynticks_nesting,
-		   rdp->dynticks->dynticks_nmi,
+		   rdp->dynticks->dynticks_nmi_nesting,
 		   rdp->dynticks_fqs);
 #endif /* #ifdef CONFIG_NO_HZ */
 	seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi);
@@ -130,7 +130,7 @@ static int show_rcudata_csv(struct seq_file *m, void *unused)
 {
 	seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pqc\",\"pq\",");
 #ifdef CONFIG_NO_HZ
-	seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\",");
+	seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\",");
 #endif /* #ifdef CONFIG_NO_HZ */
 	seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\",\"ci\",\"co\",\"ca\"\n");
 #ifdef CONFIG_TREE_PREEMPT_RCU
@@ -161,7 +161,6 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 {
 	unsigned long gpnum;
 	int level = 0;
-	int phase;
 	struct rcu_node *rnp;
 
 	gpnum = rsp->gpnum;
@@ -178,13 +177,11 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 			seq_puts(m, "\n");
 			level = rnp->level;
 		}
-		phase = gpnum & 0x1;
-		seq_printf(m, "%lx/%lx %c%c>%c%c %d:%d ^%d    ",
+		seq_printf(m, "%lx/%lx %c%c>%c %d:%d ^%d    ",
 			   rnp->qsmask, rnp->qsmaskinit,
-			   "T."[list_empty(&rnp->blocked_tasks[phase])],
-			   "E."[list_empty(&rnp->blocked_tasks[phase + 2])],
-			   "T."[list_empty(&rnp->blocked_tasks[!phase])],
-			   "E."[list_empty(&rnp->blocked_tasks[!phase + 2])],
+			   ".G"[rnp->gp_tasks != NULL],
+			   ".E"[rnp->exp_tasks != NULL],
+			   ".T"[!list_empty(&rnp->blkd_tasks)],
 			   rnp->grplo, rnp->grphi, rnp->grpnum);
 	}
 	seq_puts(m, "\n");