存储之Block-MultiQueue机制详解（三）

（1）bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)——启动硬件队列派发IO请求

//启动硬件队列派发IO请求，可以同步/异步执行；如果队列不在静默状态(quiesced)且有IO请求pending，则启动派发
bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
{
	int srcu_idx;
	bool need_run;

	/*
	 * When queue is quiesced, we may be switching io scheduler, or
	 * updating nr_hw_queues, or other things, and we can't run queue
	 * any more, even __blk_mq_hctx_has_pending() can't be called safely.
	 *
	 * And queue will be rerun in blk_mq_unquiesce_queue() if it is
	 * quiesced.
	 */
	hctx_lock(hctx, &srcu_idx);
	need_run = !blk_queue_quiesced(hctx->queue) &&
		blk_mq_hctx_has_pending(hctx);
	hctx_unlock(hctx, srcu_idx);

	if (need_run) {
		__blk_mq_delay_run_hw_queue(hctx, async, 0);
		return true;
	}

	return false;
}

2、static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)——派发IO请求

//派发IO请求
static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
{
	int srcu_idx;

	/*
	 * We should be running this queue from one of the CPUs that
	 * are mapped to it.
	 *
	 * There are at least two related races now between setting
	 * hctx->next_cpu from blk_mq_hctx_next_cpu() and running
	 * __blk_mq_run_hw_queue():
	 *
	 * - hctx->next_cpu is found offline in blk_mq_hctx_next_cpu(),
	 *   but later it becomes online, then this warning is harmless
	 *   at all
	 *
	 * - hctx->next_cpu is found online in blk_mq_hctx_next_cpu(),
	 *   but later it becomes offline, then the warning can't be
	 *   triggered, and we depend on blk-mq timeout handler to
	 *   handle dispatched requests to this hctx
	 */
	if (!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
		cpu_online(hctx->next_cpu)) {
		printk(KERN_WARNING "run queue from wrong CPU %d, hctx %s\n",
			raw_smp_processor_id(),
			cpumask_empty(hctx->cpumask) ? "inactive": "active");
		dump_stack();
	}

	/*
	 * We can't run the queue inline with ints disabled. Ensure that
	 * we catch bad users of this early.
	 */
	WARN_ON_ONCE(in_interrupt());

	might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);

	hctx_lock(hctx, &srcu_idx);
	blk_mq_sched_dispatch_requests(hctx);
	hctx_unlock(hctx, srcu_idx);
}

3、void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)——派发IO请求到块设备

//派发IO请求到块设备
void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
{
	struct request_queue *q = hctx->queue;
	struct elevator_queue *e = q->elevator;
	const bool has_sched_dispatch = e && e->type->ops.dispatch_request;
	LIST_HEAD(rq_list);

	/* RCU or SRCU read lock is needed before checking quiesced flag */
	if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)))
		return;

	hctx->run++;

	/*
	 * If we have previous entries on our dispatch list, grab them first for
	 * more fair dispatch.
	 */
	if (!list_empty_careful(&hctx->dispatch)) {
		spin_lock(&hctx->lock);
		if (!list_empty(&hctx->dispatch))
			list_splice_init(&hctx->dispatch, &rq_list);
		spin_unlock(&hctx->lock);
	}

	/*
	 * Only ask the scheduler for requests, if we didn't have residual
	 * requests from the dispatch list. This is to avoid the case where
	 * we only ever dispatch a fraction of the requests available because
	 * of low device queue depth. Once we pull requests out of the IO
	 * scheduler, we can no longer merge or sort them. So it's best to
	 * leave them there for as long as we can. Mark the hw queue as
	 * needing a restart in that case.
	 *
	 * We want to dispatch from the scheduler if there was nothing
	 * on the dispatch list or we were able to dispatch from the
	 * dispatch list.
	 */
	if (!list_empty(&rq_list)) {
		blk_mq_sched_mark_restart_hctx(hctx);
		if (blk_mq_dispatch_rq_list(q, &rq_list, false)) {             //如果硬件派发队列(hctx->dispatch)非空，则先调用blk_mq_dispatch_rq_list派发这个队列中的IO请求

			if (has_sched_dispatch)
				blk_mq_do_dispatch_sched(hctx);
			else
				blk_mq_do_dispatch_ctx(hctx);
		}
	} else if (has_sched_dispatch) {
		blk_mq_do_dispatch_sched(hctx);                   //如果配置了调度器，则调用该函数从调度队列中派发该IO请求
	} else if (hctx->dispatch_busy) {
		/* dequeue request one by one from sw queue if queue is busy */
		blk_mq_do_dispatch_ctx(hctx);                     //如果队列繁忙(dispatch_busy记录繁忙状态)，则调用该函数从软件队列中取1个IO请求派发
	} else {
		blk_mq_flush_busy_ctxs(hctx, &rq_list);
		blk_mq_dispatch_rq_list(q, &rq_list, false);      //否则取映射到这个硬件队列上的所有软件队列的IO请求来进行派发
	}
}