rcuclassic.c

Kernel code of linux kernel

		rcp->completed = rcp->cur;
		rcu_start_batch(rcp);
	}
}

/*
 * Check if the cpu has gone through a quiescent state (say context
 * switch). If so and if it already hasn't done so in this RCU
 * quiescent cycle, then indicate that it has done so.
 */
static void rcu_check_quiescent_state(struct rcu_ctrlblk *rcp,
					struct rcu_data *rdp)
{
	if (rdp->quiescbatch != rcp->cur) {
		/* start new grace period: */
		rdp->qs_pending = 1;
		rdp->passed_quiesc = 0;
		rdp->quiescbatch = rcp->cur;
		return;
	}

	/* Grace period already completed for this cpu?
	 * qs_pending is checked instead of the actual bitmap to avoid
	 * cacheline trashing.
	 */
	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_quiesc)
		return;
	rdp->qs_pending = 0;

	spin_lock(&rcp->lock);
	/*
	 * rdp->quiescbatch/rcp->cur and the cpu bitmap can come out of sync
	 * during cpu startup. Ignore the quiescent state.
	 */
	if (likely(rdp->quiescbatch == rcp->cur))
		cpu_quiet(rdp->cpu, rcp);

	spin_unlock(&rcp->lock);
}


#ifdef CONFIG_HOTPLUG_CPU

/* warning! helper for rcu_offline_cpu. do not use elsewhere without reviewing
 * locking requirements, the list it's pulling from has to belong to a cpu
 * which is dead and hence not processing interrupts.
 */
static void rcu_move_batch(struct rcu_data *this_rdp, struct rcu_head *list,
				struct rcu_head **tail)
{
	local_irq_disable();
	*this_rdp->nxttail = list;
	if (list)
		this_rdp->nxttail = tail;
	local_irq_enable();
}

static void __rcu_offline_cpu(struct rcu_data *this_rdp,
				struct rcu_ctrlblk *rcp, struct rcu_data *rdp)
{
	/* if the cpu going offline owns the grace period
	 * we can block indefinitely waiting for it, so flush
	 * it here
	 */
	spin_lock_bh(&rcp->lock);
	if (rcp->cur != rcp->completed)
		cpu_quiet(rdp->cpu, rcp);
	spin_unlock_bh(&rcp->lock);
	rcu_move_batch(this_rdp, rdp->donelist, rdp->donetail);
	rcu_move_batch(this_rdp, rdp->curlist, rdp->curtail);
	rcu_move_batch(this_rdp, rdp->nxtlist, rdp->nxttail);

	local_irq_disable();
	this_rdp->qlen += rdp->qlen;
	local_irq_enable();
}

static void rcu_offline_cpu(int cpu)
{
	struct rcu_data *this_rdp = &get_cpu_var(rcu_data);
	struct rcu_data *this_bh_rdp = &get_cpu_var(rcu_bh_data);

	__rcu_offline_cpu(this_rdp, &rcu_ctrlblk,
					&per_cpu(rcu_data, cpu));
	__rcu_offline_cpu(this_bh_rdp, &rcu_bh_ctrlblk,
					&per_cpu(rcu_bh_data, cpu));
	put_cpu_var(rcu_data);
	put_cpu_var(rcu_bh_data);
}

#else

static void rcu_offline_cpu(int cpu)
{
}

#endif

/*
 * This does the RCU processing work from softirq context.
 */
static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp,
					struct rcu_data *rdp)
{
	if (rdp->curlist && !rcu_batch_before(rcp->completed, rdp->batch)) {
		*rdp->donetail = rdp->curlist;
		rdp->donetail = rdp->curtail;
		rdp->curlist = NULL;
		rdp->curtail = &rdp->curlist;
	}

	if (rdp->nxtlist && !rdp->curlist) {
		local_irq_disable();
		rdp->curlist = rdp->nxtlist;
		rdp->curtail = rdp->nxttail;
		rdp->nxtlist = NULL;
		rdp->nxttail = &rdp->nxtlist;
		local_irq_enable();

		/*
		 * start the next batch of callbacks
		 */

		/* determine batch number */
		rdp->batch = rcp->cur + 1;
		/* see the comment and corresponding wmb() in
		 * the rcu_start_batch()
		 */
		smp_rmb();

		if (!rcp->next_pending) {
			/* and start it/schedule start if it's a new batch */
			spin_lock(&rcp->lock);
			rcp->next_pending = 1;
			rcu_start_batch(rcp);
			spin_unlock(&rcp->lock);
		}
	}

	rcu_check_quiescent_state(rcp, rdp);
	if (rdp->donelist)
		rcu_do_batch(rdp);
}

static void rcu_process_callbacks(struct softirq_action *unused)
{
	__rcu_process_callbacks(&rcu_ctrlblk, &__get_cpu_var(rcu_data));
	__rcu_process_callbacks(&rcu_bh_ctrlblk, &__get_cpu_var(rcu_bh_data));
}

static int __rcu_pending(struct rcu_ctrlblk *rcp, struct rcu_data *rdp)
{
	/* This cpu has pending rcu entries and the grace period
	 * for them has completed.
	 */
	if (rdp->curlist && !rcu_batch_before(rcp->completed, rdp->batch))
		return 1;

	/* This cpu has no pending entries, but there are new entries */
	if (!rdp->curlist && rdp->nxtlist)
		return 1;

	/* This cpu has finished callbacks to invoke */
	if (rdp->donelist)
		return 1;

	/* The rcu core waits for a quiescent state from the cpu */
	if (rdp->quiescbatch != rcp->cur || rdp->qs_pending)
		return 1;

	/* nothing to do */
	return 0;
}

/*
 * Check to see if there is any immediate RCU-related work to be done
 * by the current CPU, returning 1 if so.  This function is part of the
 * RCU implementation; it is -not- an exported member of the RCU API.
 */
int rcu_pending(int cpu)
{
	return __rcu_pending(&rcu_ctrlblk, &per_cpu(rcu_data, cpu)) ||
		__rcu_pending(&rcu_bh_ctrlblk, &per_cpu(rcu_bh_data, cpu));
}

/*
 * Check to see if any future RCU-related work will need to be done
 * by the current CPU, even if none need be done immediately, returning
 * 1 if so.  This function is part of the RCU implementation; it is -not-
 * an exported member of the RCU API.
 */
int rcu_needs_cpu(int cpu)
{
	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
	struct rcu_data *rdp_bh = &per_cpu(rcu_bh_data, cpu);

	return (!!rdp->curlist || !!rdp_bh->curlist || rcu_pending(cpu));
}

void rcu_check_callbacks(int cpu, int user)
{
	if (user ||
	    (idle_cpu(cpu) && !in_softirq() &&
				hardirq_count() <= (1 << HARDIRQ_SHIFT))) {

		/*
		 * Get here if this CPU took its interrupt from user
		 * mode or from the idle loop, and if this is not a
		 * nested interrupt.  In this case, the CPU is in
		 * a quiescent state, so count it.
		 *
		 * Also do a memory barrier.  This is needed to handle
		 * the case where writes from a preempt-disable section
		 * of code get reordered into schedule() by this CPU's
		 * write buffer.  The memory barrier makes sure that
		 * the rcu_qsctr_inc() and rcu_bh_qsctr_inc() are see
		 * by other CPUs to happen after any such write.
		 */

		smp_mb();  /* See above block comment. */
		rcu_qsctr_inc(cpu);
		rcu_bh_qsctr_inc(cpu);

	} else if (!in_softirq()) {

		/*
		 * Get here if this CPU did not take its interrupt from
		 * softirq, in other words, if it is not interrupting
		 * a rcu_bh read-side critical section.  This is an _bh
		 * critical section, so count it.  The memory barrier
		 * is needed for the same reason as is the above one.
		 */

		smp_mb();  /* See above block comment. */
		rcu_bh_qsctr_inc(cpu);
	}
	raise_rcu_softirq();
}

static void rcu_init_percpu_data(int cpu, struct rcu_ctrlblk *rcp,
						struct rcu_data *rdp)
{
	memset(rdp, 0, sizeof(*rdp));
	rdp->curtail = &rdp->curlist;
	rdp->nxttail = &rdp->nxtlist;
	rdp->donetail = &rdp->donelist;
	rdp->quiescbatch = rcp->completed;
	rdp->qs_pending = 0;
	rdp->cpu = cpu;
	rdp->blimit = blimit;
}

static void __cpuinit rcu_online_cpu(int cpu)
{
	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
	struct rcu_data *bh_rdp = &per_cpu(rcu_bh_data, cpu);

	rcu_init_percpu_data(cpu, &rcu_ctrlblk, rdp);
	rcu_init_percpu_data(cpu, &rcu_bh_ctrlblk, bh_rdp);
	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
}

static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
				unsigned long action, void *hcpu)
{
	long cpu = (long)hcpu;

	switch (action) {
	case CPU_UP_PREPARE:
	case CPU_UP_PREPARE_FROZEN:
		rcu_online_cpu(cpu);
		break;
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		rcu_offline_cpu(cpu);
		break;
	default:
		break;
	}
	return NOTIFY_OK;
}

static struct notifier_block __cpuinitdata rcu_nb = {
	.notifier_call	= rcu_cpu_notify,
};

/*
 * Initializes rcu mechanism.  Assumed to be called early.
 * That is before local timer(SMP) or jiffie timer (uniproc) is setup.
 * Note that rcu_qsctr and friends are implicitly
 * initialized due to the choice of ``0'' for RCU_CTR_INVALID.
 */
void __init __rcu_init(void)
{
	rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE,
			(void *)(long)smp_processor_id());
	/* Register notifier for non-boot CPUs */
	register_cpu_notifier(&rcu_nb);
}

module_param(blimit, int, 0);
module_param(qhimark, int, 0);
module_param(qlowmark, int, 0);