ehca_irq.c

linux内核源码

	return;
}

irqreturn_t ehca_interrupt_eq(int irq, void *dev_id)
{
	struct ehca_shca *shca = (struct ehca_shca*)dev_id;

	tasklet_hi_schedule(&shca->eq.interrupt_task);

	return IRQ_HANDLED;
}


static inline void process_eqe(struct ehca_shca *shca, struct ehca_eqe *eqe)
{
	u64 eqe_value;
	u32 token;
	struct ehca_cq *cq;

	eqe_value = eqe->entry;
	ehca_dbg(&shca->ib_device, "eqe_value=%lx", eqe_value);
	if (EHCA_BMASK_GET(EQE_COMPLETION_EVENT, eqe_value)) {
		ehca_dbg(&shca->ib_device, "Got completion event");
		token = EHCA_BMASK_GET(EQE_CQ_TOKEN, eqe_value);
		read_lock(&ehca_cq_idr_lock);
		cq = idr_find(&ehca_cq_idr, token);
		if (cq)
			atomic_inc(&cq->nr_events);
		read_unlock(&ehca_cq_idr_lock);
		if (cq == NULL) {
			ehca_err(&shca->ib_device,
				 "Invalid eqe for non-existing cq token=%x",
				 token);
			return;
		}
		reset_eq_pending(cq);
		if (ehca_scaling_code)
			queue_comp_task(cq);
		else {
			comp_event_callback(cq);
			if (atomic_dec_and_test(&cq->nr_events))
				wake_up(&cq->wait_completion);
		}
	} else {
		ehca_dbg(&shca->ib_device, "Got non completion event");
		parse_identifier(shca, eqe_value);
	}
}

void ehca_process_eq(struct ehca_shca *shca, int is_irq)
{
	struct ehca_eq *eq = &shca->eq;
	struct ehca_eqe_cache_entry *eqe_cache = eq->eqe_cache;
	u64 eqe_value;
	unsigned long flags;
	int eqe_cnt, i;
	int eq_empty = 0;

	spin_lock_irqsave(&eq->irq_spinlock, flags);
	if (is_irq) {
		const int max_query_cnt = 100;
		int query_cnt = 0;
		int int_state = 1;
		do {
			int_state = hipz_h_query_int_state(
				shca->ipz_hca_handle, eq->ist);
			query_cnt++;
			iosync();
		} while (int_state && query_cnt < max_query_cnt);
		if (unlikely((query_cnt == max_query_cnt)))
			ehca_dbg(&shca->ib_device, "int_state=%x query_cnt=%x",
				 int_state, query_cnt);
	}

	/* read out all eqes */
	eqe_cnt = 0;
	do {
		u32 token;
		eqe_cache[eqe_cnt].eqe =
			(struct ehca_eqe *)ehca_poll_eq(shca, eq);
		if (!eqe_cache[eqe_cnt].eqe)
			break;
		eqe_value = eqe_cache[eqe_cnt].eqe->entry;
		if (EHCA_BMASK_GET(EQE_COMPLETION_EVENT, eqe_value)) {
			token = EHCA_BMASK_GET(EQE_CQ_TOKEN, eqe_value);
			read_lock(&ehca_cq_idr_lock);
			eqe_cache[eqe_cnt].cq = idr_find(&ehca_cq_idr, token);
			if (eqe_cache[eqe_cnt].cq)
				atomic_inc(&eqe_cache[eqe_cnt].cq->nr_events);
			read_unlock(&ehca_cq_idr_lock);
			if (!eqe_cache[eqe_cnt].cq) {
				ehca_err(&shca->ib_device,
					 "Invalid eqe for non-existing cq "
					 "token=%x", token);
				continue;
			}
		} else
			eqe_cache[eqe_cnt].cq = NULL;
		eqe_cnt++;
	} while (eqe_cnt < EHCA_EQE_CACHE_SIZE);
	if (!eqe_cnt) {
		if (is_irq)
			ehca_dbg(&shca->ib_device,
				 "No eqe found for irq event");
		goto unlock_irq_spinlock;
	} else if (!is_irq)
		ehca_dbg(&shca->ib_device, "deadman found %x eqe", eqe_cnt);
	if (unlikely(eqe_cnt == EHCA_EQE_CACHE_SIZE))
		ehca_dbg(&shca->ib_device, "too many eqes for one irq event");
	/* enable irq for new packets */
	for (i = 0; i < eqe_cnt; i++) {
		if (eq->eqe_cache[i].cq)
			reset_eq_pending(eq->eqe_cache[i].cq);
	}
	/* check eq */
	spin_lock(&eq->spinlock);
	eq_empty = (!ipz_eqit_eq_peek_valid(&shca->eq.ipz_queue));
	spin_unlock(&eq->spinlock);
	/* call completion handler for cached eqes */
	for (i = 0; i < eqe_cnt; i++)
		if (eq->eqe_cache[i].cq) {
			if (ehca_scaling_code)
				queue_comp_task(eq->eqe_cache[i].cq);
			else {
				struct ehca_cq *cq = eq->eqe_cache[i].cq;
				comp_event_callback(cq);
				if (atomic_dec_and_test(&cq->nr_events))
					wake_up(&cq->wait_completion);
			}
		} else {
			ehca_dbg(&shca->ib_device, "Got non completion event");
			parse_identifier(shca, eq->eqe_cache[i].eqe->entry);
		}
	/* poll eq if not empty */
	if (eq_empty)
		goto unlock_irq_spinlock;
	do {
		struct ehca_eqe *eqe;
		eqe = (struct ehca_eqe *)ehca_poll_eq(shca, &shca->eq);
		if (!eqe)
			break;
		process_eqe(shca, eqe);
	} while (1);

unlock_irq_spinlock:
	spin_unlock_irqrestore(&eq->irq_spinlock, flags);
}

void ehca_tasklet_eq(unsigned long data)
{
	ehca_process_eq((struct ehca_shca*)data, 1);
}

static inline int find_next_online_cpu(struct ehca_comp_pool *pool)
{
	int cpu;
	unsigned long flags;

	WARN_ON_ONCE(!in_interrupt());
	if (ehca_debug_level)
		ehca_dmp(&cpu_online_map, sizeof(cpumask_t), "");

	spin_lock_irqsave(&pool->last_cpu_lock, flags);
	cpu = next_cpu(pool->last_cpu, cpu_online_map);
	if (cpu == NR_CPUS)
		cpu = first_cpu(cpu_online_map);
	pool->last_cpu = cpu;
	spin_unlock_irqrestore(&pool->last_cpu_lock, flags);

	return cpu;
}

static void __queue_comp_task(struct ehca_cq *__cq,
			      struct ehca_cpu_comp_task *cct)
{
	unsigned long flags;

	spin_lock_irqsave(&cct->task_lock, flags);
	spin_lock(&__cq->task_lock);

	if (__cq->nr_callbacks == 0) {
		__cq->nr_callbacks++;
		list_add_tail(&__cq->entry, &cct->cq_list);
		cct->cq_jobs++;
		wake_up(&cct->wait_queue);
	} else
		__cq->nr_callbacks++;

	spin_unlock(&__cq->task_lock);
	spin_unlock_irqrestore(&cct->task_lock, flags);
}

static void queue_comp_task(struct ehca_cq *__cq)
{
	int cpu_id;
	struct ehca_cpu_comp_task *cct;
	int cq_jobs;
	unsigned long flags;

	cpu_id = find_next_online_cpu(pool);
	BUG_ON(!cpu_online(cpu_id));

	cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu_id);
	BUG_ON(!cct);

	spin_lock_irqsave(&cct->task_lock, flags);
	cq_jobs = cct->cq_jobs;
	spin_unlock_irqrestore(&cct->task_lock, flags);
	if (cq_jobs > 0) {
		cpu_id = find_next_online_cpu(pool);
		cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu_id);
		BUG_ON(!cct);
	}

	__queue_comp_task(__cq, cct);
}

static void run_comp_task(struct ehca_cpu_comp_task *cct)
{
	struct ehca_cq *cq;
	unsigned long flags;

	spin_lock_irqsave(&cct->task_lock, flags);

	while (!list_empty(&cct->cq_list)) {
		cq = list_entry(cct->cq_list.next, struct ehca_cq, entry);
		spin_unlock_irqrestore(&cct->task_lock, flags);

		comp_event_callback(cq);
		if (atomic_dec_and_test(&cq->nr_events))
			wake_up(&cq->wait_completion);

		spin_lock_irqsave(&cct->task_lock, flags);
		spin_lock(&cq->task_lock);
		cq->nr_callbacks--;
		if (!cq->nr_callbacks) {
			list_del_init(cct->cq_list.next);
			cct->cq_jobs--;
		}
		spin_unlock(&cq->task_lock);
	}

	spin_unlock_irqrestore(&cct->task_lock, flags);
}

static int comp_task(void *__cct)
{
	struct ehca_cpu_comp_task *cct = __cct;
	int cql_empty;
	DECLARE_WAITQUEUE(wait, current);

	set_current_state(TASK_INTERRUPTIBLE);
	while (!kthread_should_stop()) {
		add_wait_queue(&cct->wait_queue, &wait);

		spin_lock_irq(&cct->task_lock);
		cql_empty = list_empty(&cct->cq_list);
		spin_unlock_irq(&cct->task_lock);
		if (cql_empty)
			schedule();
		else
			__set_current_state(TASK_RUNNING);

		remove_wait_queue(&cct->wait_queue, &wait);

		spin_lock_irq(&cct->task_lock);
		cql_empty = list_empty(&cct->cq_list);
		spin_unlock_irq(&cct->task_lock);
		if (!cql_empty)
			run_comp_task(__cct);

		set_current_state(TASK_INTERRUPTIBLE);
	}
	__set_current_state(TASK_RUNNING);

	return 0;
}

static struct task_struct *create_comp_task(struct ehca_comp_pool *pool,
					    int cpu)
{
	struct ehca_cpu_comp_task *cct;

	cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
	spin_lock_init(&cct->task_lock);
	INIT_LIST_HEAD(&cct->cq_list);
	init_waitqueue_head(&cct->wait_queue);
	cct->task = kthread_create(comp_task, cct, "ehca_comp/%d", cpu);

	return cct->task;
}

static void destroy_comp_task(struct ehca_comp_pool *pool,
			      int cpu)
{
	struct ehca_cpu_comp_task *cct;
	struct task_struct *task;
	unsigned long flags_cct;

	cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);

	spin_lock_irqsave(&cct->task_lock, flags_cct);

	task = cct->task;
	cct->task = NULL;
	cct->cq_jobs = 0;

	spin_unlock_irqrestore(&cct->task_lock, flags_cct);

	if (task)
		kthread_stop(task);
}

static void __cpuinit take_over_work(struct ehca_comp_pool *pool, int cpu)
{
	struct ehca_cpu_comp_task *cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
	LIST_HEAD(list);
	struct ehca_cq *cq;
	unsigned long flags_cct;

	spin_lock_irqsave(&cct->task_lock, flags_cct);

	list_splice_init(&cct->cq_list, &list);

	while (!list_empty(&list)) {
		cq = list_entry(cct->cq_list.next, struct ehca_cq, entry);

		list_del(&cq->entry);
		__queue_comp_task(cq, per_cpu_ptr(pool->cpu_comp_tasks,
						  smp_processor_id()));
	}

	spin_unlock_irqrestore(&cct->task_lock, flags_cct);

}

static int __cpuinit comp_pool_callback(struct notifier_block *nfb,
					unsigned long action,
					void *hcpu)
{
	unsigned int cpu = (unsigned long)hcpu;
	struct ehca_cpu_comp_task *cct;

	switch (action) {
	case CPU_UP_PREPARE:
	case CPU_UP_PREPARE_FROZEN:
		ehca_gen_dbg("CPU: %x (CPU_PREPARE)", cpu);
		if (!create_comp_task(pool, cpu)) {
			ehca_gen_err("Can't create comp_task for cpu: %x", cpu);
			return NOTIFY_BAD;
		}
		break;
	case CPU_UP_CANCELED:
	case CPU_UP_CANCELED_FROZEN:
		ehca_gen_dbg("CPU: %x (CPU_CANCELED)", cpu);
		cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
		kthread_bind(cct->task, any_online_cpu(cpu_online_map));
		destroy_comp_task(pool, cpu);
		break;
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
		ehca_gen_dbg("CPU: %x (CPU_ONLINE)", cpu);
		cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
		kthread_bind(cct->task, cpu);
		wake_up_process(cct->task);
		break;
	case CPU_DOWN_PREPARE:
	case CPU_DOWN_PREPARE_FROZEN:
		ehca_gen_dbg("CPU: %x (CPU_DOWN_PREPARE)", cpu);
		break;
	case CPU_DOWN_FAILED:
	case CPU_DOWN_FAILED_FROZEN:
		ehca_gen_dbg("CPU: %x (CPU_DOWN_FAILED)", cpu);
		break;
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		ehca_gen_dbg("CPU: %x (CPU_DEAD)", cpu);
		destroy_comp_task(pool, cpu);
		take_over_work(pool, cpu);
		break;
	}

	return NOTIFY_OK;
}

static struct notifier_block comp_pool_callback_nb __cpuinitdata = {
	.notifier_call	= comp_pool_callback,
	.priority	= 0,
};

int ehca_create_comp_pool(void)
{
	int cpu;
	struct task_struct *task;

	if (!ehca_scaling_code)
		return 0;

	pool = kzalloc(sizeof(struct ehca_comp_pool), GFP_KERNEL);
	if (pool == NULL)
		return -ENOMEM;

	spin_lock_init(&pool->last_cpu_lock);
	pool->last_cpu = any_online_cpu(cpu_online_map);

	pool->cpu_comp_tasks = alloc_percpu(struct ehca_cpu_comp_task);
	if (pool->cpu_comp_tasks == NULL) {
		kfree(pool);
		return -EINVAL;
	}

	for_each_online_cpu(cpu) {
		task = create_comp_task(pool, cpu);
		if (task) {
			kthread_bind(task, cpu);
			wake_up_process(task);
		}
	}

	register_hotcpu_notifier(&comp_pool_callback_nb);

	printk(KERN_INFO "eHCA scaling code enabled\n");

	return 0;
}

void ehca_destroy_comp_pool(void)
{
	int i;

	if (!ehca_scaling_code)
		return;

	unregister_hotcpu_notifier(&comp_pool_callback_nb);

	for (i = 0; i < NR_CPUS; i++) {
		if (cpu_online(i))
			destroy_comp_task(pool, i);
	}
	free_percpu(pool->cpu_comp_tasks);
	kfree(pool);
}