blk_mq_queue_exit(q);
}
-void blk_mq_free_request(struct request *rq)
+void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
{
struct blk_mq_ctx *ctx = rq->mq_ctx;
- struct blk_mq_hw_ctx *hctx;
- struct request_queue *q = rq->q;
ctx->rq_completed[rq_is_sync(rq)]++;
-
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
__blk_mq_free_request(hctx, ctx, rq);
+
+}
+EXPORT_SYMBOL_GPL(blk_mq_free_hctx_request);
+
+void blk_mq_free_request(struct request *rq)
+{
+ struct blk_mq_hw_ctx *hctx;
+ struct request_queue *q = rq->q;
+
+ hctx = q->mq_ops->map_queue(q, rq->mq_ctx->cpu);
+ blk_mq_free_hctx_request(hctx, rq);
}
+EXPORT_SYMBOL_GPL(blk_mq_free_request);
inline void __blk_mq_end_request(struct request *rq, int error)
{
* If not software queues are currently mapped to this
* hardware queue, there's nothing to check
*/
- if (!hctx->nr_ctx || !hctx->tags)
+ if (!blk_mq_hw_queue_mapped(hctx))
continue;
blk_mq_tag_busy_iter(hctx, blk_mq_check_expired, &data);
struct request_queue *q = hctx->queue;
struct request *rq;
LIST_HEAD(rq_list);
+ LIST_HEAD(driver_list);
+ struct list_head *dptr;
int queued;
WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask));
spin_unlock(&hctx->lock);
}
+ /*
+ * Start off with dptr being NULL, so we start the first request
+ * immediately, even if we have more pending.
+ */
+ dptr = NULL;
+
/*
* Now process all the entries, sending them to the driver.
*/
queued = 0;
while (!list_empty(&rq_list)) {
+ struct blk_mq_queue_data bd;
int ret;
rq = list_first_entry(&rq_list, struct request, queuelist);
list_del_init(&rq->queuelist);
- ret = q->mq_ops->queue_rq(hctx, rq, list_empty(&rq_list));
+ bd.rq = rq;
+ bd.list = dptr;
+ bd.last = list_empty(&rq_list);
+
+ ret = q->mq_ops->queue_rq(hctx, &bd);
switch (ret) {
case BLK_MQ_RQ_QUEUE_OK:
queued++;
if (ret == BLK_MQ_RQ_QUEUE_BUSY)
break;
+
+ /*
+ * We've done the first request. If we have more than 1
+ * left in the list, set dptr to defer issue.
+ */
+ if (!dptr && rq_list.next != rq_list.prev)
+ dptr = &driver_list;
}
if (!queued)
*/
static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
{
- int cpu = hctx->next_cpu;
+ if (hctx->queue->nr_hw_queues == 1)
+ return WORK_CPU_UNBOUND;
if (--hctx->next_cpu_batch <= 0) {
- int next_cpu;
+ int cpu = hctx->next_cpu, next_cpu;
next_cpu = cpumask_next(hctx->next_cpu, hctx->cpumask);
if (next_cpu >= nr_cpu_ids)
hctx->next_cpu = next_cpu;
hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
+
+ return cpu;
}
- return cpu;
+ return hctx->next_cpu;
}
void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
{
- if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
+ if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state) ||
+ !blk_mq_hw_queue_mapped(hctx)))
return;
- if (!async && cpumask_test_cpu(smp_processor_id(), hctx->cpumask))
- __blk_mq_run_hw_queue(hctx);
- else if (hctx->queue->nr_hw_queues == 1)
- kblockd_schedule_delayed_work(&hctx->run_work, 0);
- else {
- unsigned int cpu;
+ if (!async) {
+ int cpu = get_cpu();
+ if (cpumask_test_cpu(cpu, hctx->cpumask)) {
+ __blk_mq_run_hw_queue(hctx);
+ put_cpu();
+ return;
+ }
- cpu = blk_mq_hctx_next_cpu(hctx);
- kblockd_schedule_delayed_work_on(cpu, &hctx->run_work, 0);
+ put_cpu();
}
+
+ kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
+ &hctx->run_work, 0);
}
void blk_mq_run_queues(struct request_queue *q, bool async)
test_bit(BLK_MQ_S_STOPPED, &hctx->state))
continue;
- preempt_disable();
blk_mq_run_hw_queue(hctx, async);
- preempt_enable();
}
}
EXPORT_SYMBOL(blk_mq_run_queues);
{
clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
- preempt_disable();
blk_mq_run_hw_queue(hctx, false);
- preempt_enable();
}
EXPORT_SYMBOL(blk_mq_start_hw_queue);
continue;
clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
- preempt_disable();
blk_mq_run_hw_queue(hctx, async);
- preempt_enable();
}
}
EXPORT_SYMBOL(blk_mq_start_stopped_hw_queues);
void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
{
- unsigned long tmo = msecs_to_jiffies(msecs);
-
- if (hctx->queue->nr_hw_queues == 1)
- kblockd_schedule_delayed_work(&hctx->delay_work, tmo);
- else {
- unsigned int cpu;
+ if (unlikely(!blk_mq_hw_queue_mapped(hctx)))
+ return;
- cpu = blk_mq_hctx_next_cpu(hctx);
- kblockd_schedule_delayed_work_on(cpu, &hctx->delay_work, tmo);
- }
+ kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
+ &hctx->delay_work, msecs_to_jiffies(msecs));
}
EXPORT_SYMBOL(blk_mq_delay_queue);
goto run_queue;
}
- if (is_sync) {
+ /*
+ * If the driver supports defer issued based on 'last', then
+ * queue it up like normal since we can potentially save some
+ * CPU this way.
+ */
+ if (is_sync && !(data.hctx->flags & BLK_MQ_F_DEFER_ISSUE)) {
+ struct blk_mq_queue_data bd = {
+ .rq = rq,
+ .list = NULL,
+ .last = 1
+ };
int ret;
blk_mq_bio_to_request(rq, bio);
* error (busy), just add it to our list as we previously
* would have done
*/
- ret = q->mq_ops->queue_rq(data.hctx, rq, true);
+ ret = q->mq_ops->queue_rq(data.hctx, &bd);
if (ret == BLK_MQ_RQ_QUEUE_OK)
goto done;
else {
if (!ctx)
return ERR_PTR(-ENOMEM);
- /*
- * If a crashdump is active, then we are potentially in a very
- * memory constrained environment. Limit us to 1 queue and
- * 64 tags to prevent using too much memory.
- */
- if (is_kdump_kernel()) {
- set->nr_hw_queues = 1;
- set->queue_depth = min(64U, set->queue_depth);
- }
-
hctxs = kmalloc_node(set->nr_hw_queues * sizeof(*hctxs), GFP_KERNEL,
set->numa_node);
set->queue_depth = BLK_MQ_MAX_DEPTH;
}
+ /*
+ * If a crashdump is active, then we are potentially in a very
+ * memory constrained environment. Limit us to 1 queue and
+ * 64 tags to prevent using too much memory.
+ */
+ if (is_kdump_kernel()) {
+ set->nr_hw_queues = 1;
+ set->queue_depth = min(64U, set->queue_depth);
+ }
+
set->tags = kmalloc_node(set->nr_hw_queues *
sizeof(struct blk_mq_tags *),
GFP_KERNEL, set->numa_node);