blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
}
+static void blk_mq_check_inflight_rw(struct blk_mq_hw_ctx *hctx,
+ struct request *rq, void *priv,
+ bool reserved)
+{
+ struct mq_inflight *mi = priv;
+
+ if (rq->part == mi->part)
+ mi->inflight[rq_data_dir(rq)]++;
+}
+
+void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
+ unsigned int inflight[2])
+{
+ struct mq_inflight mi = { .part = part, .inflight = inflight, };
+
+ inflight[0] = inflight[1] = 0;
+ blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight_rw, &mi);
+}
+
void blk_freeze_queue_start(struct request_queue *q)
{
int freeze_depth;
rq->tag = -1;
rq->internal_tag = tag;
} else {
- if (blk_mq_tag_busy(data->hctx)) {
+ if (data->hctx->flags & BLK_MQ_F_TAG_SHARED) {
rq->rq_flags = RQF_MQ_INFLIGHT;
atomic_inc(&data->hctx->nr_active);
}
*/
if (!op_is_flush(op) && e->type->ops.mq.limit_depth)
e->type->ops.mq.limit_depth(op, data);
+ } else {
+ blk_mq_tag_busy(data->hctx);
}
tag = blk_mq_get_tag(data);
void blk_mq_kick_requeue_list(struct request_queue *q)
{
- kblockd_schedule_delayed_work(&q->requeue_work, 0);
+ kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, 0);
}
EXPORT_SYMBOL(blk_mq_kick_requeue_list);
.hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu),
.flags = wait ? 0 : BLK_MQ_REQ_NOWAIT,
};
+ bool shared;
might_sleep_if(wait);
if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
data.flags |= BLK_MQ_REQ_RESERVED;
+ shared = blk_mq_tag_busy(data.hctx);
rq->tag = blk_mq_get_tag(&data);
if (rq->tag >= 0) {
- if (blk_mq_tag_busy(data.hctx)) {
+ if (shared) {
rq->rq_flags |= RQF_MQ_INFLIGHT;
atomic_inc(&data.hctx->nr_active);
}
}
}
+static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx)
+{
+ int cpu = cpumask_first_and(hctx->cpumask, cpu_online_mask);
+
+ if (cpu >= nr_cpu_ids)
+ cpu = cpumask_first(hctx->cpumask);
+ return cpu;
+}
+
/*
* It'd be great if the workqueue API had a way to pass
* in a mask and had some smarts for more clever placement.
*/
static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
{
+ bool tried = false;
+ int next_cpu = hctx->next_cpu;
+
if (hctx->queue->nr_hw_queues == 1)
return WORK_CPU_UNBOUND;
if (--hctx->next_cpu_batch <= 0) {
- int next_cpu;
-
- next_cpu = cpumask_next_and(hctx->next_cpu, hctx->cpumask,
+select_cpu:
+ next_cpu = cpumask_next_and(next_cpu, hctx->cpumask,
cpu_online_mask);
if (next_cpu >= nr_cpu_ids)
- next_cpu = cpumask_first_and(hctx->cpumask,cpu_online_mask);
+ next_cpu = blk_mq_first_mapped_cpu(hctx);
+ hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
+ }
+
+ /*
+ * Do unbound schedule if we can't find a online CPU for this hctx,
+ * and it should only happen in the path of handling CPU DEAD.
+ */
+ if (!cpu_online(next_cpu)) {
+ if (!tried) {
+ tried = true;
+ goto select_cpu;
+ }
+ /*
+ * Make sure to re-select CPU next time once after CPUs
+ * in hctx->cpumask become online again.
+ */
hctx->next_cpu = next_cpu;
- hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
+ hctx->next_cpu_batch = 1;
+ return WORK_CPU_UNBOUND;
}
- return hctx->next_cpu;
+ hctx->next_cpu = next_cpu;
+ return next_cpu;
}
static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
unsigned long msecs)
{
- if (WARN_ON_ONCE(!blk_mq_hw_queue_mapped(hctx)))
- return;
-
if (unlikely(blk_mq_hctx_stopped(hctx)))
return;
put_cpu();
}
- kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
- &hctx->run_work,
- msecs_to_jiffies(msecs));
+ kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work,
+ msecs_to_jiffies(msecs));
}
void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
BUG_ON(!rq->q);
if (rq->mq_ctx != this_ctx) {
if (this_ctx) {
- trace_block_unplug(this_q, depth, from_schedule);
+ trace_block_unplug(this_q, depth, !from_schedule);
blk_mq_sched_insert_requests(this_q, this_ctx,
&ctx_list,
from_schedule);
* on 'ctx_list'. Do those.
*/
if (this_ctx) {
- trace_block_unplug(this_q, depth, from_schedule);
+ trace_block_unplug(this_q, depth, !from_schedule);
blk_mq_sched_insert_requests(this_q, this_ctx, &ctx_list,
from_schedule);
}
/*
* Initialize batch roundrobin counts
*/
- hctx->next_cpu = cpumask_first_and(hctx->cpumask,
- cpu_online_mask);
+ hctx->next_cpu = blk_mq_first_mapped_cpu(hctx);
hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
}
}
mutex_lock(&set->tag_list_lock);
list_del_rcu(&q->tag_set_list);
- INIT_LIST_HEAD(&q->tag_set_list);
if (list_is_singular(&set->tag_list)) {
/* just transitioned to unshared */
set->flags &= ~BLK_MQ_F_TAG_SHARED;
blk_mq_update_tag_set_depth(set, false);
}
mutex_unlock(&set->tag_list_lock);
-
synchronize_rcu();
+ INIT_LIST_HEAD(&q->tag_set_list);
}
static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
if (!set)
return -EINVAL;
+ if (q->nr_requests == nr)
+ return 0;
+
blk_mq_freeze_queue(q);
ret = 0;