Merge branch 'core-urgent-for-linus' of...

Merge branch 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  rcu: Start RCU kthreads in TASK_INTERRUPTIBLE state
  rcu: Remove waitqueue usage for cpu, node, and boost kthreads
  rcu: Avoid acquiring rcu_node locks in timer functions
  atomic: Add atomic_or()
  Documentation: Add statistics about nested locks
  rcu: Decrease memory-barrier usage based on semi-formal proof
  rcu: Make rcu_enter_nohz() pay attention to nesting
  rcu: Don't do reschedule unless in irq
  rcu: Remove old memory barriers from rcu_process_callbacks()
  rcu: Add memory barriers
  rcu: Fix unpaired rcu_irq_enter() from locking selftests

Documentation/RCU/trace.txt

@@ -99,18 +99,11 @@ o	"qp" indicates that RCU still expects a quiescent state from
 
 o	"dt" is the current value of the dyntick counter that is incremented
 	when entering or leaving dynticks idle state, either by the
-	scheduler or by irq.  The number after the "/" is the interrupt
-	nesting depth when in dyntick-idle state, or one greater than
-	the interrupt-nesting depth otherwise.
-
-	This field is displayed only for CONFIG_NO_HZ kernels.
-
-o	"dn" is the current value of the dyntick counter that is incremented
-	when entering or leaving dynticks idle state via NMI.  If both
-	the "dt" and "dn" values are even, then this CPU is in dynticks
-	idle mode and may be ignored by RCU.  If either of these two
-	counters is odd, then RCU must be alert to the possibility of
-	an RCU read-side critical section running on this CPU.
+	scheduler or by irq.  This number is even if the CPU is in
+	dyntick idle mode and odd otherwise.  The number after the first
+	"/" is the interrupt nesting depth when in dyntick-idle state,
+	or one greater than the interrupt-nesting depth otherwise.
+	The number after the second "/" is the NMI nesting depth.
 
 	This field is displayed only for CONFIG_NO_HZ kernels.
 

Documentation/lockstat.txt

@@ -12,8 +12,9 @@ Because things like lock contention can severely impact performance.
 - HOW
 
 Lockdep already has hooks in the lock functions and maps lock instances to
-lock classes. We build on that. The graph below shows the relation between
-the lock functions and the various hooks therein.
+lock classes. We build on that (see Documentation/lockdep-design.txt).
+The graph below shows the relation between the lock functions and the various
+hooks therein.
 
         __acquire
             |
@@ -128,6 +129,37 @@ points are the points we're contending with.
 
 The integer part of the time values is in us.
 
+Dealing with nested locks, subclasses may appear:
+
+32...............................................................................................................................................................................................
+33
+34                               &rq->lock:         13128          13128           0.43         190.53      103881.26          97454        3453404           0.00         401.11    13224683.11
+35                               ---------
+36                               &rq->lock            645          [<ffffffff8103bfc4>] task_rq_lock+0x43/0x75
+37                               &rq->lock            297          [<ffffffff8104ba65>] try_to_wake_up+0x127/0x25a
+38                               &rq->lock            360          [<ffffffff8103c4c5>] select_task_rq_fair+0x1f0/0x74a
+39                               &rq->lock            428          [<ffffffff81045f98>] scheduler_tick+0x46/0x1fb
+40                               ---------
+41                               &rq->lock             77          [<ffffffff8103bfc4>] task_rq_lock+0x43/0x75
+42                               &rq->lock            174          [<ffffffff8104ba65>] try_to_wake_up+0x127/0x25a
+43                               &rq->lock           4715          [<ffffffff8103ed4b>] double_rq_lock+0x42/0x54
+44                               &rq->lock            893          [<ffffffff81340524>] schedule+0x157/0x7b8
+45
+46...............................................................................................................................................................................................
+47
+48                             &rq->lock/1:         11526          11488           0.33         388.73      136294.31          21461          38404           0.00          37.93      109388.53
+49                             -----------
+50                             &rq->lock/1          11526          [<ffffffff8103ed58>] double_rq_lock+0x4f/0x54
+51                             -----------
+52                             &rq->lock/1           5645          [<ffffffff8103ed4b>] double_rq_lock+0x42/0x54
+53                             &rq->lock/1           1224          [<ffffffff81340524>] schedule+0x157/0x7b8
+54                             &rq->lock/1           4336          [<ffffffff8103ed58>] double_rq_lock+0x4f/0x54
+55                             &rq->lock/1            181          [<ffffffff8104ba65>] try_to_wake_up+0x127/0x25a
+
+Line 48 shows statistics for the second subclass (/1) of &rq->lock class
+(subclass starts from 0), since in this case, as line 50 suggests,
+double_rq_lock actually acquires a nested lock of two spinlocks.
+
 View the top contending locks:
 
 # grep : /proc/lock_stat | head

include/linux/atomic.h

@@ -34,4 +34,17 @@ static inline int atomic_inc_not_zero_hint(atomic_t *v, int hint)
 }
 #endif
 
+#ifndef CONFIG_ARCH_HAS_ATOMIC_OR
+static inline void atomic_or(int i, atomic_t *v)
+{
+	int old;
+	int new;
+
+	do {
+		old = atomic_read(v);
+		new = old | i;
+	} while (atomic_cmpxchg(v, old, new) != old);
+}
+#endif /* #ifndef CONFIG_ARCH_HAS_ATOMIC_OR */
+
 #endif /* _LINUX_ATOMIC_H */

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. */
 };
 
 /* RCU's kthread states for tracing. */
@@ -121,7 +119,9 @@ struct rcu_node {
 				/*  elements that need to drain to allow the */
 				/*  current expedited grace period to */
 				/*  complete (only for TREE_PREEMPT_RCU). */
-	unsigned long wakemask; /* CPUs whose kthread needs to be awakened. */
+	atomic_t wakemask;	/* CPUs whose kthread needs to be awakened. */
+				/*  Since this has meaning only for leaf */
+				/*  rcu_node structures, 32 bits suffices. */
 	unsigned long qsmaskinit;
 				/* Per-GP initial value for qsmask & expmask. */
 	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
@@ -159,9 +159,6 @@ struct rcu_node {
 	struct task_struct *boost_kthread_task;
 				/* kthread that takes care of priority */
 				/*  boosting for this rcu_node structure. */
-	wait_queue_head_t boost_wq;
-				/* Wait queue on which to park the boost */
-				/*  kthread. */
 	unsigned int boost_kthread_status;
 				/* State of boost_kthread_task for tracing. */
 	unsigned long n_tasks_boosted;
@@ -188,9 +185,6 @@ struct rcu_node {
 				/* kthread that takes care of this rcu_node */
 				/*  structure, for example, awakening the */
 				/*  per-CPU kthreads as needed. */
-	wait_queue_head_t node_wq;
-				/* Wait queue on which to park the per-node */
-				/*  kthread. */
 	unsigned int node_kthread_status;
 				/* State of node_kthread_task for tracing. */
 } ____cacheline_internodealigned_in_smp;
@@ -284,7 +278,6 @@ 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 */
@@ -337,6 +330,16 @@ struct rcu_data {
 						/*  scheduling clock irq */
 						/*  before ratting on them. */
 
+#define rcu_wait(cond)							\
+do {									\
+	for (;;) {							\
+		set_current_state(TASK_INTERRUPTIBLE);			\
+		if (cond)						\
+			break;						\
+		schedule();						\
+	}								\
+	__set_current_state(TASK_RUNNING);				\
+} while (0)
 
 /*
  * RCU global state, including node hierarchy.  This hierarchy is
@@ -446,7 +449,6 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu);
 static void rcu_preempt_send_cbs_to_online(void);
 static void __init __rcu_init_preempt(void);
 static void rcu_needs_cpu_flush(void);
-static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
 static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp,
 					  cpumask_var_t cm);

kernel/rcutree_plugin.h

@@ -1196,8 +1196,7 @@ static int rcu_boost_kthread(void *arg)
 
 	for (;;) {
 		rnp->boost_kthread_status = RCU_KTHREAD_WAITING;
-		wait_event_interruptible(rnp->boost_wq, rnp->boost_tasks ||
-							rnp->exp_tasks);
+		rcu_wait(rnp->boost_tasks || rnp->exp_tasks);
 		rnp->boost_kthread_status = RCU_KTHREAD_RUNNING;
 		more2boost = rcu_boost(rnp);
 		if (more2boost)
@@ -1274,14 +1273,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
 	rnp->boost_time = jiffies + RCU_BOOST_DELAY_JIFFIES;
 }
 
-/*
- * Initialize the RCU-boost waitqueue.
- */
-static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp)
-{
-	init_waitqueue_head(&rnp->boost_wq);
-}
-
 /*
  * Create an RCU-boost kthread for the specified node if one does not
  * already exist.  We only create this kthread for preemptible RCU.
@@ -1304,9 +1295,9 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 	if (IS_ERR(t))
 		return PTR_ERR(t);
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	set_task_state(t, TASK_INTERRUPTIBLE);
 	rnp->boost_kthread_task = t;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
-	wake_up_process(t);
 	sp.sched_priority = RCU_KTHREAD_PRIO;
 	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
 	return 0;
@@ -1328,10 +1319,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
 {
 }
 
-static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp)
-{
-}
-
 static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 						 struct rcu_node *rnp,
 						 int rnp_index)
@@ -1520,7 +1507,6 @@ int rcu_needs_cpu(int cpu)
 {
 	int c = 0;
 	int snap;
-	int snap_nmi;
 	int thatcpu;
 
 	/* Check for being in the holdoff period. */
@@ -1531,10 +1517,10 @@ 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);

kernel/rcutree_trace.c

@@ -69,10 +69,10 @@ 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);
@@ -141,9 +141,9 @@ 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);
@@ -167,7 +167,7 @@ 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

lib/locking-selftest.c

@@ -144,7 +144,7 @@ static void init_shared_classes(void)
 
 #define HARDIRQ_ENTER()				\
 	local_irq_disable();			\
-	irq_enter();				\
+	__irq_enter();				\
 	WARN_ON(!in_irq());
 
 #define HARDIRQ_EXIT()				\