/*
   * Read-Copy Update mechanism for mutual exclusion
   *
   * This program is free software; you can redistribute it and/or modify
   * it under the terms of the GNU General Public License as published by
   * the Free Software Foundation; either version 2 of the License, or
   * (at your option) any later version.
   *
   * This program is distributed in the hope that it will be useful,
   * but WITHOUT ANY WARRANTY; without even the implied warranty of
   * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
   * GNU General Public License for more details.
   *
   * You should have received a copy of the GNU General Public License
   * along with this program; if not, write to the Free Software
   * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
   *
   * Copyright IBM Corporation, 2008
   *
   * Authors: Dipankar Sarma <dipankar@in.ibm.com>
   *	    Manfred Spraul <manfred@colorfullife.com>
   *	    Paul E. McKenney <paulmck@linux.vnet.ibm.com> Hierarchical version
   *
   * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
   * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
   *
   * For detailed explanation of Read-Copy Update mechanism see -

   *	Documentation/RCU

   */
  #include <linux/types.h>
  #include <linux/kernel.h>
  #include <linux/init.h>
  #include <linux/spinlock.h>
  #include <linux/smp.h>
  #include <linux/rcupdate.h>
  #include <linux/interrupt.h>
  #include <linux/sched.h>

  #include <linux/nmi.h>

  #include <linux/atomic.h>

  #include <linux/bitops.h>

  #include <linux/export.h>

  #include <linux/completion.h>
  #include <linux/moduleparam.h>
  #include <linux/percpu.h>
  #include <linux/notifier.h>
  #include <linux/cpu.h>
  #include <linux/mutex.h>
  #include <linux/time.h>

  #include <linux/kernel_stat.h>

  #include <linux/wait.h>
  #include <linux/kthread.h>

  #include <linux/prefetch.h>

  #include <linux/delay.h>
  #include <linux/stop_machine.h>

  #include <linux/random.h>

  #include "rcutree.h"

  #include <trace/events/rcu.h>
  
  #include "rcu.h"

  /* Data structures. */

  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) { \

  	.level = { &sname##_state.node[0] }, \

  	.call = cr, \

  	.fqs_state = RCU_GP_IDLE, \

  	.gpnum = 0UL - 300UL, \
  	.completed = 0UL - 300UL, \

  	.orphan_lock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.orphan_lock), \

  	.orphan_nxttail = &sname##_state.orphan_nxtlist, \
  	.orphan_donetail = &sname##_state.orphan_donelist, \

  	.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \

  	.onoff_mutex = __MUTEX_INITIALIZER(sname##_state.onoff_mutex), \

  	.name = #sname, \

  }

  struct rcu_state rcu_sched_state =
  	RCU_STATE_INITIALIZER(rcu_sched, 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);

  DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);

  static struct rcu_state *rcu_state;

  LIST_HEAD(rcu_struct_flavors);

  /* Increase (but not decrease) the CONFIG_RCU_FANOUT_LEAF at boot time. */
  static int rcu_fanout_leaf = CONFIG_RCU_FANOUT_LEAF;

  module_param(rcu_fanout_leaf, int, 0444);

  int rcu_num_lvls __read_mostly = RCU_NUM_LVLS;
  static int num_rcu_lvl[] = {  /* Number of rcu_nodes at specified level. */
  	NUM_RCU_LVL_0,
  	NUM_RCU_LVL_1,
  	NUM_RCU_LVL_2,
  	NUM_RCU_LVL_3,
  	NUM_RCU_LVL_4,
  };
  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)

   * 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.
   */

  int rcu_scheduler_active __read_mostly;
  EXPORT_SYMBOL_GPL(rcu_scheduler_active);

  /*
   * The rcu_scheduler_fully_active variable transitions from zero to one
   * during the early_initcall() processing, which is after the scheduler
   * is capable of creating new tasks.  So RCU processing (for example,
   * creating tasks for RCU priority boosting) must be delayed until after
   * rcu_scheduler_fully_active transitions from zero to one.  We also
   * currently delay invocation of any RCU callbacks until after this point.
   *
   * It might later prove better for people registering RCU callbacks during
   * early boot to take responsibility for these callbacks, but one step at
   * a time.
   */
  static int rcu_scheduler_fully_active __read_mostly;

  #ifdef CONFIG_RCU_BOOST

  /*

   * Control variables for per-CPU and per-rcu_node kthreads.  These
   * handle all flavors of RCU.
   */
  static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);

  DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);

  DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);

  DEFINE_PER_CPU(char, rcu_cpu_has_work);

  #endif /* #ifdef CONFIG_RCU_BOOST */

  static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);

  static void invoke_rcu_core(void);
  static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);

  /*

   * Track the rcutorture test sequence number and the update version
   * number within a given test.  The rcutorture_testseq is incremented
   * on every rcutorture module load and unload, so has an odd value
   * when a test is running.  The rcutorture_vernum is set to zero
   * when rcutorture starts and is incremented on each rcutorture update.
   * These variables enable correlating rcutorture output with the
   * RCU tracing information.
   */
  unsigned long rcutorture_testseq;
  unsigned long rcutorture_vernum;
  
  /*

   * Return true if an RCU grace period is in progress.  The ACCESS_ONCE()s
   * permit this function to be invoked without holding the root rcu_node
   * structure's ->lock, but of course results can be subject to change.
   */
  static int rcu_gp_in_progress(struct rcu_state *rsp)
  {
  	return ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum);
  }
  
  /*

   * Note a quiescent state.  Because we do not need to know

   * how many quiescent states passed, just if there was at least

   * 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)

  {

  	struct rcu_data *rdp = &per_cpu(rcu_sched_data, cpu);

  	if (rdp->passed_quiesce == 0)

  		trace_rcu_grace_period("rcu_sched", rdp->gpnum, "cpuqs");

  	rdp->passed_quiesce = 1;

  }

  void rcu_bh_qs(int cpu)

  {

  	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);

  	if (rdp->passed_quiesce == 0)

  		trace_rcu_grace_period("rcu_bh", rdp->gpnum, "cpuqs");

  	rdp->passed_quiesce = 1;

  }

  /*
   * Note a context switch.  This is a quiescent state for RCU-sched,
   * and requires special handling for preemptible RCU.

   * The caller must have disabled preemption.

   */
  void rcu_note_context_switch(int cpu)
  {

  	trace_rcu_utilization("Start context switch");

  	rcu_sched_qs(cpu);

  	rcu_preempt_note_context_switch(cpu);

  	trace_rcu_utilization("End context switch");

  }

  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),

  };

  static long blimit = 10;	/* Maximum callbacks per rcu_do_batch. */
  static long qhimark = 10000;	/* If this many pending, ignore blimit. */
  static long qlowmark = 100;	/* Once only this many pending, use blimit. */

  module_param(blimit, long, 0444);
  module_param(qhimark, long, 0444);
  module_param(qlowmark, long, 0444);

  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 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);

  
  /*

   * Return the number of RCU-sched batches processed thus far for debug & stats.

   */

  long rcu_batches_completed_sched(void)

  {

  	return rcu_sched_state.completed;

  }

  EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);

  
  /*
   * Return the number of RCU BH batches processed thus far for debug & stats.
   */
  long rcu_batches_completed_bh(void)
  {
  	return rcu_bh_state.completed;
  }
  EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
  
  /*

   * Force a quiescent state for RCU BH.
   */
  void rcu_bh_force_quiescent_state(void)
  {

  	force_quiescent_state(&rcu_bh_state);

  }
  EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state);
  
  /*

   * Record the number of times rcutorture tests have been initiated and
   * terminated.  This information allows the debugfs tracing stats to be
   * correlated to the rcutorture messages, even when the rcutorture module
   * is being repeatedly loaded and unloaded.  In other words, we cannot
   * store this state in rcutorture itself.
   */
  void rcutorture_record_test_transition(void)
  {
  	rcutorture_testseq++;
  	rcutorture_vernum = 0;
  }
  EXPORT_SYMBOL_GPL(rcutorture_record_test_transition);
  
  /*
   * Record the number of writer passes through the current rcutorture test.
   * This is also used to correlate debugfs tracing stats with the rcutorture
   * messages.
   */
  void rcutorture_record_progress(unsigned long vernum)
  {
  	rcutorture_vernum++;
  }
  EXPORT_SYMBOL_GPL(rcutorture_record_progress);
  
  /*

   * Force a quiescent state for RCU-sched.
   */
  void rcu_sched_force_quiescent_state(void)
  {

  	force_quiescent_state(&rcu_sched_state);

  }
  EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state);
  
  /*

   * Does the CPU have callbacks ready to be invoked?
   */
  static int
  cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp)
  {

  	return &rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL] &&
  	       rdp->nxttail[RCU_DONE_TAIL] != NULL;

  }
  
  /*

   * 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)
  {

  	int i;

  	if (rcu_gp_in_progress(rsp))
  		return 0;  /* No, a grace period is already in progress. */
  	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. */

  }
  
  /*
   * Return the root node of the specified rcu_state structure.
   */
  static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
  {
  	return &rsp->node[0];
  }

  /*

   * rcu_eqs_enter_common - current CPU is moving towards extended quiescent state

   *
   * If the new value of the ->dynticks_nesting counter now is zero,
   * we really have entered idle, and must do the appropriate accounting.
   * The caller must have disabled interrupts.
   */

  static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
  				bool user)

  {

  	trace_rcu_dyntick("Start", oldval, rdtp->dynticks_nesting);

  	if (!user && !is_idle_task(current)) {

  		struct task_struct *idle = idle_task(smp_processor_id());

  		trace_rcu_dyntick("Error on entry: not idle task", oldval, 0);

  		ftrace_dump(DUMP_ORIG);

  		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
  			  current->pid, current->comm,
  			  idle->pid, idle->comm); /* must be idle task! */

  	}

  	rcu_prepare_for_idle(smp_processor_id());

  	/* 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);

  
  	/*

  	 * It is illegal to enter an extended quiescent state while

  	 * in an RCU read-side critical section.
  	 */
  	rcu_lockdep_assert(!lock_is_held(&rcu_lock_map),
  			   "Illegal idle entry in RCU read-side critical section.");
  	rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map),
  			   "Illegal idle entry in RCU-bh read-side critical section.");
  	rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map),
  			   "Illegal idle entry in RCU-sched read-side critical section.");

  }

  /*
   * Enter an RCU extended quiescent state, which can be either the
   * idle loop or adaptive-tickless usermode execution.

   */

  static void rcu_eqs_enter(bool user)

  {

  	long long oldval;

  	struct rcu_dynticks *rdtp;

  	rdtp = &__get_cpu_var(rcu_dynticks);

  	oldval = rdtp->dynticks_nesting;

  	WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
  	if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE)
  		rdtp->dynticks_nesting = 0;
  	else
  		rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;

  	rcu_eqs_enter_common(rdtp, oldval, user);

  }

  
  /**
   * rcu_idle_enter - inform RCU that current CPU is entering idle
   *
   * Enter idle mode, in other words, -leave- the mode in which RCU
   * read-side critical sections can occur.  (Though RCU read-side
   * critical sections can occur in irq handlers in idle, a possibility
   * handled by irq_enter() and irq_exit().)
   *
   * We crowbar the ->dynticks_nesting field to zero to allow for
   * the possibility of usermode upcalls having messed up our count
   * of interrupt nesting level during the prior busy period.
   */
  void rcu_idle_enter(void)
  {

  	unsigned long flags;
  
  	local_irq_save(flags);

  	rcu_eqs_enter(false);

  	local_irq_restore(flags);

  }

  EXPORT_SYMBOL_GPL(rcu_idle_enter);

  #ifdef CONFIG_RCU_USER_QS

  /**

   * rcu_user_enter - inform RCU that we are resuming userspace.
   *
   * Enter RCU idle mode right before resuming userspace.  No use of RCU
   * is permitted between this call and rcu_user_exit(). This way the
   * CPU doesn't need to maintain the tick for RCU maintenance purposes
   * when the CPU runs in userspace.
   */
  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 */

  
  /**

   * rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle
   *
   * Exit from an interrupt handler, which might possibly result in entering
   * idle mode, in other words, leaving the mode in which read-side critical
   * sections can occur.

   *

   * This code assumes that the idle loop never does anything that might
   * result in unbalanced calls to irq_enter() and irq_exit().  If your
   * architecture violates this assumption, RCU will give you what you
   * deserve, good and hard.  But very infrequently and irreproducibly.
   *
   * Use things like work queues to work around this limitation.
   *
   * You have been warned.

   */

  void rcu_irq_exit(void)

  {
  	unsigned long flags;

  	long long oldval;

  	struct rcu_dynticks *rdtp;
  
  	local_irq_save(flags);
  	rdtp = &__get_cpu_var(rcu_dynticks);

  	oldval = rdtp->dynticks_nesting;

  	rdtp->dynticks_nesting--;
  	WARN_ON_ONCE(rdtp->dynticks_nesting < 0);

  	if (rdtp->dynticks_nesting)
  		trace_rcu_dyntick("--=", oldval, rdtp->dynticks_nesting);
  	else

  		rcu_eqs_enter_common(rdtp, oldval, true);

  	local_irq_restore(flags);
  }
  
  /*

   * rcu_eqs_exit_common - current CPU moving away from extended quiescent state

   *
   * If the new value of the ->dynticks_nesting counter was previously zero,
   * we really have exited idle, and must do the appropriate accounting.
   * The caller must have disabled interrupts.
   */

  static void rcu_eqs_exit_common(struct rcu_dynticks *rdtp, long long oldval,
  			       int user)

  {

  	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));

  	rcu_cleanup_after_idle(smp_processor_id());

  	trace_rcu_dyntick("End", oldval, rdtp->dynticks_nesting);

  	if (!user && !is_idle_task(current)) {

  		struct task_struct *idle = idle_task(smp_processor_id());

  		trace_rcu_dyntick("Error on exit: not idle task",
  				  oldval, rdtp->dynticks_nesting);

  		ftrace_dump(DUMP_ORIG);

  		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
  			  current->pid, current->comm,
  			  idle->pid, idle->comm); /* must be idle task! */

  	}
  }

  /*
   * Exit an RCU extended quiescent state, which can be either the
   * idle loop or adaptive-tickless usermode execution.

   */

  static void rcu_eqs_exit(bool user)

  {

  	struct rcu_dynticks *rdtp;
  	long long oldval;

  	rdtp = &__get_cpu_var(rcu_dynticks);
  	oldval = rdtp->dynticks_nesting;

  	WARN_ON_ONCE(oldval < 0);
  	if (oldval & DYNTICK_TASK_NEST_MASK)
  		rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
  	else
  		rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;

  	rcu_eqs_exit_common(rdtp, oldval, user);

  }

  
  /**
   * rcu_idle_exit - inform RCU that current CPU is leaving idle
   *
   * Exit idle mode, in other words, -enter- the mode in which RCU
   * read-side critical sections can occur.
   *
   * We crowbar the ->dynticks_nesting field to DYNTICK_TASK_NEST to
   * allow for the possibility of usermode upcalls messing up our count
   * of interrupt nesting level during the busy period that is just
   * now starting.
   */
  void rcu_idle_exit(void)
  {

  	unsigned long flags;
  
  	local_irq_save(flags);

  	rcu_eqs_exit(false);

  	local_irq_restore(flags);

  }

  EXPORT_SYMBOL_GPL(rcu_idle_exit);

  #ifdef CONFIG_RCU_USER_QS

  /**

   * rcu_user_exit - inform RCU that we are exiting userspace.
   *
   * Exit RCU idle mode while entering the kernel because it can
   * run a RCU read side critical section anytime.
   */
  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 */

  
  /**

   * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle
   *
   * Enter an interrupt handler, which might possibly result in exiting
   * idle mode, in other words, entering the mode in which read-side critical
   * sections can occur.
   *
   * Note that the Linux kernel is fully capable of entering an interrupt
   * handler that it never exits, for example when doing upcalls to
   * user mode!  This code assumes that the idle loop never does upcalls to
   * user mode.  If your architecture does do upcalls from the idle loop (or
   * does anything else that results in unbalanced calls to the irq_enter()
   * and irq_exit() functions), RCU will give you what you deserve, good
   * and hard.  But very infrequently and irreproducibly.
   *
   * Use things like work queues to work around this limitation.
   *
   * You have been warned.
   */
  void rcu_irq_enter(void)
  {
  	unsigned long flags;
  	struct rcu_dynticks *rdtp;
  	long long oldval;
  
  	local_irq_save(flags);
  	rdtp = &__get_cpu_var(rcu_dynticks);
  	oldval = rdtp->dynticks_nesting;
  	rdtp->dynticks_nesting++;
  	WARN_ON_ONCE(rdtp->dynticks_nesting == 0);

  	if (oldval)
  		trace_rcu_dyntick("++=", oldval, rdtp->dynticks_nesting);
  	else

  		rcu_eqs_exit_common(rdtp, oldval, true);

  	local_irq_restore(flags);

  }
  
  /**
   * rcu_nmi_enter - inform RCU of entry to NMI context
   *
   * If the CPU was idle with dynamic ticks active, and there is no
   * irq handler running, this updates rdtp->dynticks_nmi to let the
   * RCU grace-period handling know that the CPU is active.
   */
  void rcu_nmi_enter(void)
  {
  	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);

  	if (rdtp->dynticks_nmi_nesting == 0 &&
  	    (atomic_read(&rdtp->dynticks) & 0x1))

  		return;

  	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));

  }
  
  /**
   * rcu_nmi_exit - inform RCU of exit from NMI context
   *
   * If the CPU was idle with dynamic ticks active, and there is no
   * irq handler running, this updates rdtp->dynticks_nmi to let the
   * RCU grace-period handling know that the CPU is no longer active.
   */
  void rcu_nmi_exit(void)
  {
  	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);

  	if (rdtp->dynticks_nmi_nesting == 0 ||
  	    --rdtp->dynticks_nmi_nesting != 0)

  		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 delay to next write. */
  	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);

  }
  
  /**

   * rcu_is_cpu_idle - see if RCU thinks that the current CPU is idle

   *

   * If the current CPU is in its idle loop and is neither in an interrupt

   * or NMI handler, return true.

   */

  int rcu_is_cpu_idle(void)

  {

  	int ret;
  
  	preempt_disable();
  	ret = (atomic_read(&__get_cpu_var(rcu_dynticks).dynticks) & 0x1) == 0;
  	preempt_enable();
  	return ret;

  }

  EXPORT_SYMBOL(rcu_is_cpu_idle);

  #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)

  
  /*
   * Is the current CPU online?  Disable preemption to avoid false positives
   * that could otherwise happen due to the current CPU number being sampled,
   * this task being preempted, its old CPU being taken offline, resuming
   * on some other CPU, then determining that its old CPU is now offline.
   * It is OK to use RCU on an offline processor during initial boot, hence

   * the check for rcu_scheduler_fully_active.  Note also that it is OK
   * for a CPU coming online to use RCU for one jiffy prior to marking itself
   * online in the cpu_online_mask.  Similarly, it is OK for a CPU going
   * offline to continue to use RCU for one jiffy after marking itself
   * offline in the cpu_online_mask.  This leniency is necessary given the
   * non-atomic nature of the online and offline processing, for example,
   * the fact that a CPU enters the scheduler after completing the CPU_DYING
   * notifiers.
   *
   * This is also why RCU internally marks CPUs online during the
   * CPU_UP_PREPARE phase and offline during the CPU_DEAD phase.

   *
   * Disable checking if in an NMI handler because we cannot safely report
   * errors from NMI handlers anyway.
   */
  bool rcu_lockdep_current_cpu_online(void)
  {

  	struct rcu_data *rdp;
  	struct rcu_node *rnp;

  	bool ret;
  
  	if (in_nmi())
  		return 1;
  	preempt_disable();

  	rdp = &__get_cpu_var(rcu_sched_data);
  	rnp = rdp->mynode;
  	ret = (rdp->grpmask & rnp->qsmaskinit) ||

  	      !rcu_scheduler_fully_active;
  	preempt_enable();
  	return ret;
  }
  EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);

  #endif /* #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) */

  /**

   * rcu_is_cpu_rrupt_from_idle - see if idle or immediately interrupted from idle

   *

   * If the current CPU is idle or running at a first-level (not nested)
   * interrupt from idle, return true.  The caller must have at least
   * disabled preemption.

   */

  static int rcu_is_cpu_rrupt_from_idle(void)

  {

  	return __get_cpu_var(rcu_dynticks).dynticks_nesting <= 1;

  }

  /*

   * Snapshot the specified CPU's dynticks counter so that we can later
   * 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)
  {

  	rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks);

  	return (rdp->dynticks_snap & 0x1) == 0;

  }
  
  /*
   * Return true if the specified CPU has passed through a quiescent
   * state by virtue of being in or having passed through an dynticks
   * 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)
  {

  	unsigned int curr;
  	unsigned int snap;

  	curr = (unsigned int)atomic_add_return(0, &rdp->dynticks->dynticks);
  	snap = (unsigned int)rdp->dynticks_snap;

  
  	/*
  	 * If the CPU passed through or entered a dynticks idle phase with
  	 * no active irq/NMI handlers, then we can safely pretend that the CPU
  	 * already acknowledged the request to pass through a quiescent
  	 * state.  Either way, that CPU cannot possibly be in an RCU
  	 * read-side critical section that started before the beginning
  	 * of the current RCU grace period.
  	 */

  	if ((curr & 0x1) == 0 || UINT_CMP_GE(curr, snap + 2)) {

  		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, "dti");

  		rdp->dynticks_fqs++;
  		return 1;
  	}

  	/*
  	 * Check for the CPU being offline, but only if the grace period
  	 * is old enough.  We don't need to worry about the CPU changing
  	 * state: If we see it offline even once, it has been through a
  	 * quiescent state.
  	 *
  	 * The reason for insisting that the grace period be at least
  	 * one jiffy old is that CPUs that are not quite online and that
  	 * have just gone offline can still execute RCU read-side critical
  	 * sections.
  	 */
  	if (ULONG_CMP_GE(rdp->rsp->gp_start + 2, jiffies))
  		return 0;  /* Grace period is not old enough. */
  	barrier();
  	if (cpu_is_offline(rdp->cpu)) {
  		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, "ofl");
  		rdp->offline_fqs++;
  		return 1;
  	}
  	return 0;

  }

  static void record_gp_stall_check_time(struct rcu_state *rsp)
  {
  	rsp->gp_start = jiffies;

  	rsp->jiffies_stall = jiffies + rcu_jiffies_till_stall_check();

  }

  /*
   * Dump stacks of all tasks running on stalled CPUs.  This is a fallback
   * for architectures that do not implement trigger_all_cpu_backtrace().
   * The NMI-triggered stack traces are more accurate because they are
   * printed by the target CPU.
   */
  static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
  {
  	int cpu;
  	unsigned long flags;
  	struct rcu_node *rnp;
  
  	rcu_for_each_leaf_node(rsp, rnp) {
  		raw_spin_lock_irqsave(&rnp->lock, flags);
  		if (rnp->qsmask != 0) {
  			for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
  				if (rnp->qsmask & (1UL << cpu))
  					dump_cpu_task(rnp->grplo + cpu);
  		}
  		raw_spin_unlock_irqrestore(&rnp->lock, flags);
  	}
  }

  static void print_other_cpu_stall(struct rcu_state *rsp)
  {
  	int cpu;
  	long delta;
  	unsigned long flags;

  	int ndetected = 0;

  	struct rcu_node *rnp = rcu_get_root(rsp);

  	long totqlen = 0;

  
  	/* Only let one CPU complain about others per time interval. */

  	raw_spin_lock_irqsave(&rnp->lock, flags);

  	delta = jiffies - rsp->jiffies_stall;

  	if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {

  		raw_spin_unlock_irqrestore(&rnp->lock, flags);

  		return;
  	}

  	rsp->jiffies_stall = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;

  	raw_spin_unlock_irqrestore(&rnp->lock, flags);

  	/*
  	 * OK, time to rat on our buddy...
  	 * See Documentation/RCU/stallwarn.txt for info on how to debug
  	 * RCU CPU stall warnings.
  	 */

  	printk(KERN_ERR "INFO: %s detected stalls on CPUs/tasks:",

  	       rsp->name);

  	print_cpu_stall_info_begin();

  	rcu_for_each_leaf_node(rsp, rnp) {

  		raw_spin_lock_irqsave(&rnp->lock, flags);

  		ndetected += rcu_print_task_stall(rnp);

  		if (rnp->qsmask != 0) {
  			for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
  				if (rnp->qsmask & (1UL << cpu)) {
  					print_cpu_stall_info(rsp,
  							     rnp->grplo + cpu);
  					ndetected++;
  				}
  		}

  		raw_spin_unlock_irqrestore(&rnp->lock, flags);

  	}

  
  	/*
  	 * Now rat on any tasks that got kicked up to the root rcu_node
  	 * due to CPU offlining.
  	 */
  	rnp = rcu_get_root(rsp);
  	raw_spin_lock_irqsave(&rnp->lock, flags);

  	ndetected += rcu_print_task_stall(rnp);

  	raw_spin_unlock_irqrestore(&rnp->lock, flags);
  
  	print_cpu_stall_info_end();

  	for_each_possible_cpu(cpu)
  		totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen;
  	pr_cont("(detected by %d, t=%ld jiffies, g=%lu, c=%lu, q=%lu)
  ",

  	       smp_processor_id(), (long)(jiffies - rsp->gp_start),

  	       rsp->gpnum, rsp->completed, totqlen);

  	if (ndetected == 0)
  		printk(KERN_ERR "INFO: Stall ended before state dump start
  ");
  	else if (!trigger_all_cpu_backtrace())

  		rcu_dump_cpu_stacks(rsp);

  	/* Complain about tasks blocking the grace period. */

  
  	rcu_print_detail_task_stall(rsp);

  	force_quiescent_state(rsp);  /* Kick them all. */

  }
  
  static void print_cpu_stall(struct rcu_state *rsp)
  {

  	int cpu;

  	unsigned long flags;
  	struct rcu_node *rnp = rcu_get_root(rsp);

  	long totqlen = 0;

  	/*
  	 * OK, time to rat on ourselves...
  	 * See Documentation/RCU/stallwarn.txt for info on how to debug
  	 * RCU CPU stall warnings.
  	 */

  	printk(KERN_ERR "INFO: %s self-detected stall on CPU", rsp->name);
  	print_cpu_stall_info_begin();
  	print_cpu_stall_info(rsp, smp_processor_id());
  	print_cpu_stall_info_end();

  	for_each_possible_cpu(cpu)
  		totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen;
  	pr_cont(" (t=%lu jiffies g=%lu c=%lu q=%lu)
  ",
  		jiffies - rsp->gp_start, rsp->gpnum, rsp->completed, totqlen);

  	if (!trigger_all_cpu_backtrace())
  		dump_stack();

  	raw_spin_lock_irqsave(&rnp->lock, flags);

  	if (ULONG_CMP_GE(jiffies, rsp->jiffies_stall))

  		rsp->jiffies_stall = jiffies +

  				     3 * rcu_jiffies_till_stall_check() + 3;

  	raw_spin_unlock_irqrestore(&rnp->lock, flags);

  	set_need_resched();  /* kick ourselves to get things going. */
  }
  
  static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
  {

  	unsigned long j;
  	unsigned long js;

  	struct rcu_node *rnp;

  	if (rcu_cpu_stall_suppress)

  		return;

  	j = ACCESS_ONCE(jiffies);
  	js = ACCESS_ONCE(rsp->jiffies_stall);

  	rnp = rdp->mynode;

  	if (rcu_gp_in_progress(rsp) &&
  	    (ACCESS_ONCE(rnp->qsmask) & rdp->grpmask) && ULONG_CMP_GE(j, js)) {

  
  		/* We haven't checked in, so go dump stack. */
  		print_cpu_stall(rsp);

  	} else if (rcu_gp_in_progress(rsp) &&
  		   ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) {

  		/* They had a few time units to dump stack, so complain. */

  		print_other_cpu_stall(rsp);
  	}
  }

  /**
   * rcu_cpu_stall_reset - prevent further stall warnings in current grace period
   *
   * Set the stall-warning timeout way off into the future, thus preventing
   * any RCU CPU stall-warning messages from appearing in the current set of
   * RCU grace periods.
   *
   * The caller must disable hard irqs.
   */
  void rcu_cpu_stall_reset(void)
  {

  	struct rcu_state *rsp;
  
  	for_each_rcu_flavor(rsp)
  		rsp->jiffies_stall = jiffies + ULONG_MAX / 2;

  }

  /*
   * 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

   * that someone else started the grace period.  The caller must hold the
   * ->lock of the leaf rcu_node structure corresponding to the current CPU,
   *  and must have irqs disabled.

   */

  static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
  {
  	if (rdp->gpnum != rnp->gpnum) {

  		/*
  		 * If the current grace period is waiting for this CPU,
  		 * set up to detect a quiescent state, otherwise don't
  		 * go looking for one.
  		 */

  		rdp->gpnum = rnp->gpnum;

  		trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpustart");

  		rdp->passed_quiesce = 0;
  		rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask);

  		zero_cpu_stall_ticks(rdp);

  	}
  }

  static void note_new_gpnum(struct rcu_state *rsp, struct rcu_data *rdp)
  {

  	unsigned long flags;
  	struct rcu_node *rnp;
  
  	local_irq_save(flags);
  	rnp = rdp->mynode;
  	if (rdp->gpnum == ACCESS_ONCE(rnp->gpnum) || /* outside lock. */

  	    !raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */

  		local_irq_restore(flags);
  		return;
  	}
  	__note_new_gpnum(rsp, rnp, rdp);

  	raw_spin_unlock_irqrestore(&rnp->lock, flags);

  }
  
  /*
   * Did someone else start a new RCU grace period start since we last
   * checked?  Update local state appropriately if so.  Must be called
   * on the CPU corresponding to rdp.
   */
  static int
  check_for_new_grace_period(struct rcu_state *rsp, struct rcu_data *rdp)
  {
  	unsigned long flags;
  	int ret = 0;
  
  	local_irq_save(flags);
  	if (rdp->gpnum != rsp->gpnum) {
  		note_new_gpnum(rsp, rdp);
  		ret = 1;
  	}
  	local_irq_restore(flags);
  	return ret;
  }
  
  /*

   * Initialize the specified rcu_data structure's callback list to empty.
   */
  static void init_callback_list(struct rcu_data *rdp)
  {
  	int i;
  
  	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;
  }
  
  /*
   * 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;
  	}

  
  	/* 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);
  }
  
  /*

   * Advance this CPU's callbacks, but only if the current grace period
   * has ended.  This may be called only from the CPU to whom the rdp
   * belongs.  In addition, the corresponding leaf rcu_node structure's
   * ->lock must be held by the caller, with irqs disabled.
   */
  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) {

  		/* No, so just accelerate recent callbacks. */
  		rcu_accelerate_cbs(rsp, rnp, rdp);

  	} else {
  
  		/* Advance callbacks. */
  		rcu_advance_cbs(rsp, rnp, rdp);

  
  		/* Remember that we saw this grace-period completion. */
  		rdp->completed = rnp->completed;

  		trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpuend");

  
  		/*

  		 * If we were in an extended quiescent state, we may have

  		 * missed some grace periods that others CPUs handled on

  		 * our behalf. Catch up with this state to avoid noting

  		 * spurious new grace periods.  If another grace period
  		 * has started, then rnp->gpnum will have advanced, so

  		 * we will detect this later on.  Of course, any quiescent
  		 * states we found for the old GP are now invalid.

  		 */

  		if (ULONG_CMP_LT(rdp->gpnum, rdp->completed)) {

  			rdp->gpnum = rdp->completed;

  			rdp->passed_quiesce = 0;
  		}

  
  		/*

  		 * If RCU does not need a quiescent state from this CPU,
  		 * then make sure that this CPU doesn't go looking for one.

  		 */

  		if ((rnp->qsmask & rdp->grpmask) == 0)

  			rdp->qs_pending = 0;

  	}
  }
  
  /*
   * Advance this CPU's callbacks, but only if the current grace period
   * has ended.  This may be called only from the CPU to whom the rdp
   * belongs.
   */
  static void
  rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp)
  {
  	unsigned long flags;
  	struct rcu_node *rnp;
  
  	local_irq_save(flags);
  	rnp = rdp->mynode;
  	if (rdp->completed == ACCESS_ONCE(rnp->completed) || /* outside lock. */

  	    !raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */

  		local_irq_restore(flags);
  		return;
  	}
  	__rcu_process_gp_end(rsp, rnp, rdp);

  	raw_spin_unlock_irqrestore(&rnp->lock, flags);

  }
  
  /*
   * Do per-CPU grace-period initialization for running CPU.  The caller
   * must hold the lock of the leaf rcu_node structure corresponding to
   * this CPU.
   */
  static void
  rcu_start_gp_per_cpu(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
  {
  	/* Prior grace period ended, so advance callbacks for current CPU. */
  	__rcu_process_gp_end(rsp, rnp, rdp);

  	/* Set state so that this CPU will detect the next quiescent state. */
  	__note_new_gpnum(rsp, rnp, rdp);

  }
  
  /*

   * Initialize a new grace period.

   */

  static int rcu_gp_init(struct rcu_state *rsp)

  {
  	struct rcu_data *rdp;

  	struct rcu_node *rnp = rcu_get_root(rsp);

  	raw_spin_lock_irq(&rnp->lock);

  	rsp->gp_flags = 0; /* Clear all flags: New grace period. */

  	if (rcu_gp_in_progress(rsp)) {
  		/* Grace period already in progress, don't start another.  */
  		raw_spin_unlock_irq(&rnp->lock);
  		return 0;
  	}

  	/* Advance to a new grace period and initialize state. */
  	rsp->gpnum++;
  	trace_rcu_grace_period(rsp->name, rsp->gpnum, "start");

  	record_gp_stall_check_time(rsp);
  	raw_spin_unlock_irq(&rnp->lock);
  
  	/* Exclude any concurrent CPU-hotplug operations. */

  	mutex_lock(&rsp->onoff_mutex);

  
  	/*
  	 * Set the quiescent-state-needed bits in all the rcu_node
  	 * structures for all currently online CPUs in breadth-first order,
  	 * starting from the root rcu_node structure, relying on the layout
  	 * of the tree within the rsp->node[] array.  Note that other CPUs
  	 * will access only the leaves of the hierarchy, thus seeing that no
  	 * grace period is in progress, at least until the corresponding
  	 * leaf node has been initialized.  In addition, we have excluded
  	 * CPU-hotplug operations.
  	 *
  	 * The grace period cannot complete until the initialization
  	 * process finishes, because this kthread handles both.
  	 */
  	rcu_for_each_node_breadth_first(rsp, rnp) {

  		raw_spin_lock_irq(&rnp->lock);

  		rdp = this_cpu_ptr(rsp->rda);

  		rcu_preempt_check_blocked_tasks(rnp);
  		rnp->qsmask = rnp->qsmaskinit;
  		rnp->gpnum = rsp->gpnum;

  		WARN_ON_ONCE(rnp->completed != rsp->completed);

  		rnp->completed = rsp->completed;
  		if (rnp == rdp->mynode)
  			rcu_start_gp_per_cpu(rsp, rnp, rdp);
  		rcu_preempt_boost_start_gp(rnp);
  		trace_rcu_grace_period_init(rsp->name, rnp->gpnum,
  					    rnp->level, rnp->grplo,
  					    rnp->grphi, rnp->qsmask);
  		raw_spin_unlock_irq(&rnp->lock);

  #ifdef CONFIG_PROVE_RCU_DELAY
  		if ((random32() % (rcu_num_nodes * 8)) == 0)
  			schedule_timeout_uninterruptible(2);
  #endif /* #ifdef CONFIG_PROVE_RCU_DELAY */

  		cond_resched();
  	}

  	mutex_unlock(&rsp->onoff_mutex);

  	return 1;
  }

  /*

   * Do one round of quiescent-state forcing.
   */
  int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
  {
  	int fqs_state = fqs_state_in;
  	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);
  		fqs_state = RCU_FORCE_QS;
  	} else {
  		/* Handle dyntick-idle and offline CPUs. */
  		force_qs_rnp(rsp, rcu_implicit_dynticks_qs);
  	}
  	/* Clear flag to prevent immediate re-entry. */
  	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
  		raw_spin_lock_irq(&rnp->lock);
  		rsp->gp_flags &= ~RCU_GP_FLAG_FQS;
  		raw_spin_unlock_irq(&rnp->lock);
  	}
  	return fqs_state;
  }
  
  /*

   * Clean up after the old grace period.
   */

  static void rcu_gp_cleanup(struct rcu_state *rsp)

  {
  	unsigned long gp_duration;
  	struct rcu_data *rdp;
  	struct rcu_node *rnp = rcu_get_root(rsp);

  	raw_spin_lock_irq(&rnp->lock);
  	gp_duration = jiffies - rsp->gp_start;
  	if (gp_duration > rsp->gp_max)
  		rsp->gp_max = gp_duration;

  	/*
  	 * We know the grace period is complete, but to everyone else
  	 * it appears to still be ongoing.  But it is also the case
  	 * that to everyone else it looks like there is nothing that
  	 * they can do to advance the grace period.  It is therefore
  	 * safe for us to drop the lock in order to mark the grace
  	 * period as completed in all of the rcu_node structures.

  	 */

  	raw_spin_unlock_irq(&rnp->lock);

  	/*
  	 * Propagate new ->completed value to rcu_node structures so
  	 * that other CPUs don't have to wait until the start of the next
  	 * grace period to process their callbacks.  This also avoids
  	 * some nasty RCU grace-period initialization races by forcing
  	 * the end of the current grace period to be completely recorded in
  	 * all of the rcu_node structures before the beginning of the next
  	 * grace period is recorded in any of the rcu_node structures.
  	 */
  	rcu_for_each_node_breadth_first(rsp, rnp) {

  		raw_spin_lock_irq(&rnp->lock);

  		rnp->completed = rsp->gpnum;
  		raw_spin_unlock_irq(&rnp->lock);
  		cond_resched();

  	}

  	rnp = rcu_get_root(rsp);
  	raw_spin_lock_irq(&rnp->lock);

  
  	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);

  	if (cpu_needs_another_gp(rsp, rdp))
  		rsp->gp_flags = 1;
  	raw_spin_unlock_irq(&rnp->lock);

  }
  
  /*
   * Body of kthread that handles grace periods.
   */
  static int __noreturn rcu_gp_kthread(void *arg)
  {

  	int fqs_state;

  	unsigned long j;

  	int ret;

  	struct rcu_state *rsp = arg;
  	struct rcu_node *rnp = rcu_get_root(rsp);
  
  	for (;;) {
  
  		/* Handle grace-period start. */
  		for (;;) {

  			wait_event_interruptible(rsp->gp_wq,
  						 rsp->gp_flags &
  						 RCU_GP_FLAG_INIT);
  			if ((rsp->gp_flags & RCU_GP_FLAG_INIT) &&
  			    rcu_gp_init(rsp))

  				break;
  			cond_resched();
  			flush_signals(current);
  		}

  		/* Handle quiescent-state forcing. */
  		fqs_state = RCU_SAVE_DYNTICK;

  		j = jiffies_till_first_fqs;
  		if (j > HZ) {
  			j = HZ;
  			jiffies_till_first_fqs = HZ;
  		}

  		for (;;) {

  			rsp->jiffies_force_qs = jiffies + j;

  			ret = wait_event_interruptible_timeout(rsp->gp_wq,
  					(rsp->gp_flags & RCU_GP_FLAG_FQS) ||
  					(!ACCESS_ONCE(rnp->qsmask) &&
  					 !rcu_preempt_blocked_readers_cgp(rnp)),

  					j);

  			/* If grace period done, leave loop. */

  			if (!ACCESS_ONCE(rnp->qsmask) &&

  			    !rcu_preempt_blocked_readers_cgp(rnp))

  				break;

  			/* If time for quiescent-state forcing, do it. */
  			if (ret == 0 || (rsp->gp_flags & RCU_GP_FLAG_FQS)) {
  				fqs_state = rcu_gp_fqs(rsp, fqs_state);
  				cond_resched();
  			} else {
  				/* Deal with stray signal. */
  				cond_resched();
  				flush_signals(current);
  			}

  			j = jiffies_till_next_fqs;
  			if (j > HZ) {
  				j = HZ;
  				jiffies_till_next_fqs = HZ;
  			} else if (j < 1) {
  				j = 1;
  				jiffies_till_next_fqs = 1;
  			}

  		}

  
  		/* Handle grace-period end. */
  		rcu_gp_cleanup(rsp);

  	}

  }
  
  /*

   * 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.

   *
   * 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)
  {

  	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)) {
  		/*

  		 * 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 this is a good place to
  	 * assign a grace period number to recently posted callbacks.

  	 */

  	rcu_accelerate_cbs(rsp, rnp, rdp);

  	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);

  }
  
  /*

   * 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.

   */

  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));

  	raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
  	wake_up(&rsp->gp_wq);  /* Memory barrier implied by wake_up() path. */

  }
  
  /*

   * Similar to rcu_report_qs_rdp(), for which it is a helper function.
   * Allows quiescent states for a group of CPUs to be reported at one go
   * to the specified rcu_node structure, though all the CPUs in the group
   * must be represented by the same rcu_node structure (which need not be
   * a leaf rcu_node structure, though it often will be).  That structure's
   * lock must be held upon entry, and it is released before return.

   */
  static void

  rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
  		  struct rcu_node *rnp, unsigned long flags)

  	__releases(rnp->lock)
  {

  	struct rcu_node *rnp_c;

  	/* Walk up the rcu_node hierarchy. */
  	for (;;) {
  		if (!(rnp->qsmask & mask)) {
  
  			/* Our bit has already been cleared, so done. */

  			raw_spin_unlock_irqrestore(&rnp->lock, flags);

  			return;
  		}
  		rnp->qsmask &= ~mask;

  		trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum,
  						 mask, rnp->qsmask, rnp->level,
  						 rnp->grplo, rnp->grphi,
  						 !!rnp->gp_tasks);

  		if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {

  
  			/* Other bits still set at this level, so done. */

  			raw_spin_unlock_irqrestore(&rnp->lock, flags);

  			return;
  		}
  		mask = rnp->grpmask;
  		if (rnp->parent == NULL) {
  
  			/* No more levels.  Exit loop holding root lock. */
  
  			break;
  		}

  		raw_spin_unlock_irqrestore(&rnp->lock, flags);

  		rnp_c = rnp;

  		rnp = rnp->parent;

  		raw_spin_lock_irqsave(&rnp->lock, flags);

  		WARN_ON_ONCE(rnp_c->qsmask);

  	}
  
  	/*
  	 * Get here if we are the last CPU to pass through a quiescent

  	 * state for this grace period.  Invoke rcu_report_qs_rsp()

  	 * to clean up and start the next grace period if one is needed.

  	 */

  	rcu_report_qs_rsp(rsp, flags); /* releases rnp->lock. */

  }
  
  /*

   * Record a quiescent state for the specified CPU to that CPU's rcu_data
   * structure.  This must be either called from the specified CPU, or
   * called when the specified CPU is known to be offline (and when it is
   * also known that no other CPU is concurrently trying to help the offline
   * CPU).  The lastcomp argument is used to make sure we are still in the
   * grace period of interest.  We don't want to end the current grace period
   * based on quiescent states detected in an earlier grace period!

   */
  static void

  rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)

  {
  	unsigned long flags;
  	unsigned long mask;
  	struct rcu_node *rnp;
  
  	rnp = rdp->mynode;

  	raw_spin_lock_irqsave(&rnp->lock, flags);

  	if (rdp->passed_quiesce == 0 || rdp->gpnum != rnp->gpnum ||
  	    rnp->completed == rnp->gpnum) {

  
  		/*

  		 * The grace period in which this quiescent state was
  		 * recorded has ended, so don't report it upwards.
  		 * We will instead need a new quiescent state that lies
  		 * within the current grace period.

  		 */

  		rdp->passed_quiesce = 0;	/* need qs for new gp. */

  		raw_spin_unlock_irqrestore(&rnp->lock, flags);

  		return;
  	}
  	mask = rdp->grpmask;
  	if ((rnp->qsmask & mask) == 0) {

  		raw_spin_unlock_irqrestore(&rnp->lock, flags);

  	} else {
  		rdp->qs_pending = 0;
  
  		/*
  		 * This GP can't end until cpu checks in, so all of our
  		 * callbacks can be processed during the next GP.
  		 */

  		rcu_accelerate_cbs(rsp, rnp, rdp);

  		rcu_report_qs_rnp(mask, rsp, rnp, flags); /* rlses rnp->lock */

  	}
  }
  
  /*
   * Check to see if there is a new grace period of which this CPU
   * is not yet aware, and if so, set up local rcu_data state for it.
   * Otherwise, see if this CPU has just passed through its first
   * quiescent state for this grace period, and record that fact if so.
   */
  static void
  rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
  {
  	/* If there is now a new grace period, record and return. */
  	if (check_for_new_grace_period(rsp, rdp))
  		return;
  
  	/*
  	 * Does this CPU still need to do its part for current grace period?
  	 * If no, return and let the other CPUs do their part as well.
  	 */
  	if (!rdp->qs_pending)
  		return;
  
  	/*
  	 * Was there a quiescent state since the beginning of the grace
  	 * period? If no, then exit and wait for the next call.
  	 */

  	if (!rdp->passed_quiesce)

  		return;

  	/*
  	 * Tell RCU we are done (but rcu_report_qs_rdp() will be the
  	 * judge of that).
  	 */

  	rcu_report_qs_rdp(rdp->cpu, rsp, rdp);

  }
  
  #ifdef CONFIG_HOTPLUG_CPU
  
  /*

   * Send the specified CPU's RCU callbacks to the orphanage.  The
   * specified CPU must be offline, and the caller must hold the

   * ->orphan_lock.

   */

  static void
  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))
  		return;

  	/*
  	 * Orphan the callbacks.  First adjust the counts.  This is safe

  	 * because _rcu_barrier() excludes CPU-hotplug operations, so it
  	 * cannot be running now.  Thus no memory barrier is required.

  	 */

  	if (rdp->nxtlist != NULL) {

  		rsp->qlen_lazy += rdp->qlen_lazy;
  		rsp->qlen += rdp->qlen;
  		rdp->n_cbs_orphaned += rdp->qlen;

  		rdp->qlen_lazy = 0;

  		ACCESS_ONCE(rdp->qlen) = 0;

  	}
  
  	/*

  	 * Next, move those callbacks still needing a grace period to
  	 * the orphanage, where some other CPU will pick them up.
  	 * Some of the callbacks might have gone partway through a grace
  	 * period, but that is too bad.  They get to start over because we
  	 * cannot assume that grace periods are synchronized across CPUs.
  	 * We don't bother updating the ->nxttail[] array yet, instead
  	 * we just reset the whole thing later on.

  	 */

  	if (*rdp->nxttail[RCU_DONE_TAIL] != NULL) {
  		*rsp->orphan_nxttail = *rdp->nxttail[RCU_DONE_TAIL];
  		rsp->orphan_nxttail = rdp->nxttail[RCU_NEXT_TAIL];
  		*rdp->nxttail[RCU_DONE_TAIL] = NULL;

  	}
  
  	/*

  	 * Then move the ready-to-invoke callbacks to the orphanage,
  	 * where some other CPU will pick them up.  These will not be
  	 * required to pass though another grace period: They are done.

  	 */

  	if (rdp->nxtlist != NULL) {

  		*rsp->orphan_donetail = rdp->nxtlist;
  		rsp->orphan_donetail = rdp->nxttail[RCU_DONE_TAIL];

  	}

  	/* Finally, initialize the rcu_data structure's list to empty.  */

  	init_callback_list(rdp);

  }
  
  /*
   * Adopt the RCU callbacks from the specified rcu_state structure's

   * orphanage.  The caller must hold the ->orphan_lock.

   */
  static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
  {
  	int i;
  	struct rcu_data *rdp = __this_cpu_ptr(rsp->rda);

  	/* No-CBs CPUs are handled specially. */
  	if (rcu_nocb_adopt_orphan_cbs(rsp, rdp))
  		return;

  	/* Do the accounting first. */
  	rdp->qlen_lazy += rsp->qlen_lazy;
  	rdp->qlen += rsp->qlen;
  	rdp->n_cbs_adopted += rsp->qlen;

  	if (rsp->qlen_lazy != rsp->qlen)
  		rcu_idle_count_callbacks_posted();

  	rsp->qlen_lazy = 0;
  	rsp->qlen = 0;
  
  	/*
  	 * We do not need a memory barrier here because the only way we
  	 * can get here if there is an rcu_barrier() in flight is if
  	 * we are the task doing the rcu_barrier().
  	 */
  
  	/* First adopt the ready-to-invoke callbacks. */
  	if (rsp->orphan_donelist != NULL) {
  		*rsp->orphan_donetail = *rdp->nxttail[RCU_DONE_TAIL];
  		*rdp->nxttail[RCU_DONE_TAIL] = rsp->orphan_donelist;
  		for (i = RCU_NEXT_SIZE - 1; i >= RCU_DONE_TAIL; i--)
  			if (rdp->nxttail[i] == rdp->nxttail[RCU_DONE_TAIL])
  				rdp->nxttail[i] = rsp->orphan_donetail;
  		rsp->orphan_donelist = NULL;
  		rsp->orphan_donetail = &rsp->orphan_donelist;
  	}
  
  	/* And then adopt the callbacks that still need a grace period. */
  	if (rsp->orphan_nxtlist != NULL) {
  		*rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_nxtlist;
  		rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_nxttail;
  		rsp->orphan_nxtlist = NULL;
  		rsp->orphan_nxttail = &rsp->orphan_nxtlist;
  	}
  }
  
  /*
   * Trace the fact that this CPU is going offline.
   */
  static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
  {
  	RCU_TRACE(unsigned long mask);
  	RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda));
  	RCU_TRACE(struct rcu_node *rnp = rdp->mynode);
  
  	RCU_TRACE(mask = rdp->grpmask);

  	trace_rcu_grace_period(rsp->name,
  			       rnp->gpnum + 1 - !!(rnp->qsmask & mask),
  			       "cpuofl");

  }
  
  /*

   * The CPU has been completely removed, and some other CPU is reporting

   * this fact from process context.  Do the remainder of the cleanup,
   * including orphaning the outgoing CPU's RCU callbacks, and also

   * adopting them.  There can only be one CPU hotplug operation at a time,
   * so no other CPU can be attempting to update rcu_cpu_kthread_task.

   */

  static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)

  {

  	unsigned long flags;
  	unsigned long mask;
  	int need_report = 0;

  	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);

  	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */

  	/* 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);

  	/* Orphan the dead CPU's callbacks, and adopt them if appropriate. */
  	rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp);
  	rcu_adopt_orphan_cbs(rsp);

  	/* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */
  	mask = rdp->grpmask;	/* rnp->grplo is constant. */
  	do {
  		raw_spin_lock(&rnp->lock);	/* irqs already disabled. */
  		rnp->qsmaskinit &= ~mask;
  		if (rnp->qsmaskinit != 0) {
  			if (rnp != rdp->mynode)
  				raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
  			break;
  		}
  		if (rnp == rdp->mynode)
  			need_report = rcu_preempt_offline_tasks(rsp, rnp, rdp);
  		else
  			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
  		mask = rnp->grpmask;
  		rnp = rnp->parent;
  	} while (rnp != NULL);
  
  	/*
  	 * We still hold the leaf rcu_node structure lock here, and
  	 * irqs are still disabled.  The reason for this subterfuge is

  	 * because invoking rcu_report_unblock_qs_rnp() with ->orphan_lock

  	 * held leads to deadlock.
  	 */

  	raw_spin_unlock(&rsp->orphan_lock); /* irqs remain disabled. */

  	rnp = rdp->mynode;
  	if (need_report & RCU_OFL_TASKS_NORM_GP)
  		rcu_report_unblock_qs_rnp(rnp, flags);
  	else
  		raw_spin_unlock_irqrestore(&rnp->lock, flags);
  	if (need_report & RCU_OFL_TASKS_EXP_GP)
  		rcu_report_exp_rnp(rsp, rnp, true);

  	WARN_ONCE(rdp->qlen != 0 || rdp->nxtlist != NULL,
  		  "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, nxtlist=%p
  ",
  		  cpu, rdp->qlen, rdp->nxtlist);

  	init_callback_list(rdp);
  	/* Disallow further callbacks on this CPU. */
  	rdp->nxttail[RCU_NEXT_TAIL] = NULL;

  	mutex_unlock(&rsp->onoff_mutex);

  }
  
  #else /* #ifdef CONFIG_HOTPLUG_CPU */

  static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)

  {
  }

  static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)

  {
  }
  
  #endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
  
  /*
   * Invoke any RCU callbacks that have made it to the end of their grace
   * period.  Thottle as specified by rdp->blimit.
   */

  static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)

  {
  	unsigned long flags;
  	struct rcu_head *next, *list, **tail;

  	long bl, count, count_lazy;
  	int i;

  	/* 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),
  				    need_resched(), is_idle_task(current),
  				    rcu_is_callbacks_kthread());

  		return;

  	}

  
  	/*
  	 * Extract the list of ready callbacks, disabling to prevent
  	 * races with call_rcu() from interrupt handlers.
  	 */
  	local_irq_save(flags);

  	WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));

  	bl = rdp->blimit;

  	trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, bl);

  	list = rdp->nxtlist;
  	rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL];
  	*rdp->nxttail[RCU_DONE_TAIL] = NULL;
  	tail = rdp->nxttail[RCU_DONE_TAIL];

  	for (i = RCU_NEXT_SIZE - 1; i >= 0; i--)
  		if (rdp->nxttail[i] == rdp->nxttail[RCU_DONE_TAIL])
  			rdp->nxttail[i] = &rdp->nxtlist;

  	local_irq_restore(flags);
  
  	/* Invoke callbacks. */

  	count = count_lazy = 0;

  	while (list) {
  		next = list->next;
  		prefetch(next);

  		debug_rcu_head_unqueue(list);

  		if (__rcu_reclaim(rsp->name, list))
  			count_lazy++;

  		list = next;

  		/* Stop only if limit reached and CPU has something to do. */
  		if (++count >= bl &&
  		    (need_resched() ||
  		     (!is_idle_task(current) && !rcu_is_callbacks_kthread())))

  			break;
  	}
  
  	local_irq_save(flags);

  	trace_rcu_batch_end(rsp->name, count, !!list, need_resched(),
  			    is_idle_task(current),
  			    rcu_is_callbacks_kthread());

  
  	/* Update count, and requeue any remaining callbacks. */

  	if (list != NULL) {
  		*tail = rdp->nxtlist;
  		rdp->nxtlist = list;

  		for (i = 0; i < RCU_NEXT_SIZE; i++)
  			if (&rdp->nxtlist == rdp->nxttail[i])
  				rdp->nxttail[i] = tail;

  			else
  				break;
  	}

  	smp_mb(); /* List handling before counting for rcu_barrier(). */
  	rdp->qlen_lazy -= count_lazy;

  	ACCESS_ONCE(rdp->qlen) -= count;

  	rdp->n_cbs_invoked += count;

  
  	/* Reinstate batch limit if we have worked down the excess. */
  	if (rdp->blimit == LONG_MAX && rdp->qlen <= qlowmark)
  		rdp->blimit = blimit;

  	/* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */
  	if (rdp->qlen == 0 && rdp->qlen_last_fqs_check != 0) {
  		rdp->qlen_last_fqs_check = 0;
  		rdp->n_force_qs_snap = rsp->n_force_qs;
  	} else if (rdp->qlen < rdp->qlen_last_fqs_check - qhimark)
  		rdp->qlen_last_fqs_check = rdp->qlen;

  	WARN_ON_ONCE((rdp->nxtlist == NULL) != (rdp->qlen == 0));

  	local_irq_restore(flags);

  	/* Re-invoke RCU core processing if there are callbacks remaining. */