/*
 * Generic helpers for smp ipi calls
 *
 * (C) Jens Axboe <jens.axboe@oracle.com> 2008
 */
#include <linux/rcupdate.h>
#include <linux/rculist.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/smp.h>
#include <linux/cpu.h>

static DEFINE_PER_CPU(struct call_single_queue, call_single_queue);

static struct {
	struct list_head	queue;
	spinlock_t		lock;
} call_function __cacheline_aligned_in_smp =
	{
		.queue		= LIST_HEAD_INIT(call_function.queue),
		.lock		= __SPIN_LOCK_UNLOCKED(call_function.lock),
	};

enum {
	CSD_FLAG_LOCK		= 0x01,
};

struct call_function_data {
	struct call_single_data	csd;
	spinlock_t		lock;
	unsigned int		refs;
	cpumask_var_t		cpumask;
};

struct call_single_queue {
	struct list_head	list;
	spinlock_t		lock;
};

static DEFINE_PER_CPU(struct call_function_data, cfd_data) = {
	.lock			= __SPIN_LOCK_UNLOCKED(cfd_data.lock),
};

static int
hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
{
	long cpu = (long)hcpu;
	struct call_function_data *cfd = &per_cpu(cfd_data, cpu);

	switch (action) {
	case CPU_UP_PREPARE:
	case CPU_UP_PREPARE_FROZEN:
		if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL,
				cpu_to_node(cpu)))
			return NOTIFY_BAD;
		break;

#ifdef CONFIG_HOTPLUG_CPU
	case CPU_UP_CANCELED:
	case CPU_UP_CANCELED_FROZEN:

	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		free_cpumask_var(cfd->cpumask);
		break;
#endif
	};

	return NOTIFY_OK;
}

static struct notifier_block __cpuinitdata hotplug_cfd_notifier = {
	.notifier_call		= hotplug_cfd,
};

static int __cpuinit init_call_single_data(void)
{
	void *cpu = (void *)(long)smp_processor_id();
	int i;

	for_each_possible_cpu(i) {
		struct call_single_queue *q = &per_cpu(call_single_queue, i);

		spin_lock_init(&q->lock);
		INIT_LIST_HEAD(&q->list);
	}

	hotplug_cfd(&hotplug_cfd_notifier, CPU_UP_PREPARE, cpu);
	register_cpu_notifier(&hotplug_cfd_notifier);

	return 0;
}
early_initcall(init_call_single_data);

/*
 * csd_lock/csd_unlock used to serialize access to per-cpu csd resources
 *
 * For non-synchronous ipi calls the csd can still be in use by the
 * previous function call. For multi-cpu calls its even more interesting
 * as we'll have to ensure no other cpu is observing our csd.
 */
static void csd_lock_wait(struct call_single_data *data)
{
	while (data->flags & CSD_FLAG_LOCK)
		cpu_relax();
}

static void csd_lock(struct call_single_data *data)
{
	csd_lock_wait(data);
	data->flags = CSD_FLAG_LOCK;

	/*
	 * prevent CPU from reordering the above assignment
	 * to ->flags with any subsequent assignments to other
	 * fields of the specified call_single_data structure:
	 */
	smp_mb();
}

static void csd_unlock(struct call_single_data *data)
{
	WARN_ON(!(data->flags & CSD_FLAG_LOCK));

	/*
	 * ensure we're all done before releasing data:
	 */
	smp_mb();

	data->flags &= ~CSD_FLAG_LOCK;
}

/*
 * Insert a previously allocated call_single_data element
 * for execution on the given CPU. data must already have
 * ->func, ->info, and ->flags set.
 */
static
void generic_exec_single(int cpu, struct call_single_data *data, int wait)
{
	struct call_single_queue *dst = &per_cpu(call_single_queue, cpu);
	unsigned long flags;
	int ipi;

	spin_lock_irqsave(&dst->lock, flags);
	ipi = list_empty(&dst->list);
	list_add_tail(&data->list, &dst->list);
	spin_unlock_irqrestore(&dst->lock, flags);

	/*
	 * The list addition should be visible before sending the IPI
	 * handler locks the list to pull the entry off it because of
	 * normal cache coherency rules implied by spinlocks.
	 *
	 * If IPIs can go out of order to the cache coherency protocol
	 * in an architecture, sufficient synchronisation should be added
	 * to arch code to make it appear to obey cache coherency WRT
	 * locking and barrier primitives. Generic code isn't really
	 * equipped to do the right thing...
	 */
	if (ipi)
		arch_send_call_function_single_ipi(cpu);

	if (wait)
		csd_lock_wait(data);
}

/*
 * Invoked by arch to handle an IPI for call function. Must be called with
 * interrupts disabled.
 */
void generic_smp_call_function_interrupt(void)
{
	struct call_function_data *data;
	int cpu = get_cpu();

	/*
	 * Shouldn't receive this interrupt on a cpu that is not yet online.
	 */
	WARN_ON_ONCE(!cpu_online(cpu));

	/*
	 * Ensure entry is visible on call_function_queue after we have
	 * entered the IPI. See comment in smp_call_function_many.
	 * If we don't have this, then we may miss an entry on the list
	 * and never get another IPI to process it.
	 */
	smp_mb();

	/*
	 * It's ok to use list_for_each_rcu() here even though we may
	 * delete 'pos', since list_del_rcu() doesn't clear ->next
	 */
	list_for_each_entry_rcu(data, &call_function.queue, csd.list) {
		int refs;

		spin_lock(&data->lock);
		if (!cpumask_test_cpu(cpu, data->cpumask)) {
			spin_unlock(&data->lock);
			continue;
		}
		cpumask_clear_cpu(cpu, data->cpumask);
		spin_unlock(&data->lock);

		data->csd.func(data->csd.info);

		spin_lock(&data->lock);
		WARN_ON(data->refs == 0);
		refs = --data->refs;
		if (!refs) {
			spin_lock(&call_function.lock);
			list_del_rcu(&data->csd.list);
			spin_unlock(&call_function.lock);
		}
		spin_unlock(&data->lock);

		if (refs)
			continue;

		csd_unlock(&data->csd);
	}