/*
* Check if any of the ctx's have pending work in this hardware queue
*/
-bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
+static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
{
- return sbitmap_any_bit_set(&hctx->ctx_map) ||
- !list_empty_careful(&hctx->dispatch) ||
+ return !list_empty_careful(&hctx->dispatch) ||
+ sbitmap_any_bit_set(&hctx->ctx_map) ||
blk_mq_sched_has_work(hctx);
}
}
struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
- unsigned int flags)
+ blk_mq_req_flags_t flags)
{
struct blk_mq_alloc_data alloc_data = { .flags = flags };
struct request *rq;
int ret;
- ret = blk_queue_enter(q, flags & BLK_MQ_REQ_NOWAIT);
+ ret = blk_queue_enter(q, flags);
if (ret)
return ERR_PTR(ret);
EXPORT_SYMBOL(blk_mq_alloc_request);
struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
- unsigned int op, unsigned int flags, unsigned int hctx_idx)
+ unsigned int op, blk_mq_req_flags_t flags, unsigned int hctx_idx)
{
struct blk_mq_alloc_data alloc_data = { .flags = flags };
struct request *rq;
if (hctx_idx >= q->nr_hw_queues)
return ERR_PTR(-EIO);
- ret = blk_queue_enter(q, true);
+ ret = blk_queue_enter(q, flags);
if (ret)
return ERR_PTR(ret);
/*
* We abuse this flag that is otherwise used by the I/O scheduler to
- * request head insertation from the workqueue.
+ * request head insertion from the workqueue.
*/
BUG_ON(rq->rq_flags & RQF_SOFTBARRIER);
return 1;
}
-static bool blk_mq_dispatch_wait_add(struct blk_mq_hw_ctx **hctx,
- struct request *rq)
+/*
+ * Mark us waiting for a tag. For shared tags, this involves hooking us into
+ * the tag wakeups. For non-shared tags, we can simply mark us nedeing a
+ * restart. For both caes, take care to check the condition again after
+ * marking us as waiting.
+ */
+static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx **hctx,
+ struct request *rq)
{
struct blk_mq_hw_ctx *this_hctx = *hctx;
- wait_queue_entry_t *wait = &this_hctx->dispatch_wait;
+ bool shared_tags = (this_hctx->flags & BLK_MQ_F_TAG_SHARED) != 0;
struct sbq_wait_state *ws;
+ wait_queue_entry_t *wait;
+ bool ret;
- if (!list_empty_careful(&wait->entry))
- return false;
+ if (!shared_tags) {
+ if (!test_bit(BLK_MQ_S_SCHED_RESTART, &this_hctx->state))
+ set_bit(BLK_MQ_S_SCHED_RESTART, &this_hctx->state);
+ } else {
+ wait = &this_hctx->dispatch_wait;
+ if (!list_empty_careful(&wait->entry))
+ return false;
- spin_lock(&this_hctx->lock);
- if (!list_empty(&wait->entry)) {
- spin_unlock(&this_hctx->lock);
- return false;
- }
+ spin_lock(&this_hctx->lock);
+ if (!list_empty(&wait->entry)) {
+ spin_unlock(&this_hctx->lock);
+ return false;
+ }
- ws = bt_wait_ptr(&this_hctx->tags->bitmap_tags, this_hctx);
- add_wait_queue(&ws->wait, wait);
+ ws = bt_wait_ptr(&this_hctx->tags->bitmap_tags, this_hctx);
+ add_wait_queue(&ws->wait, wait);
+ }
/*
* It's possible that a tag was freed in the window between the
* allocation failure and adding the hardware queue to the wait
* queue.
*/
- if (!blk_mq_get_driver_tag(rq, hctx, false)) {
+ ret = blk_mq_get_driver_tag(rq, hctx, false);
+
+ if (!shared_tags) {
+ /*
+ * Don't clear RESTART here, someone else could have set it.
+ * At most this will cost an extra queue run.
+ */
+ return ret;
+ } else {
+ if (!ret) {
+ spin_unlock(&this_hctx->lock);
+ return false;
+ }
+
+ /*
+ * We got a tag, remove ourselves from the wait queue to ensure
+ * someone else gets the wakeup.
+ */
+ spin_lock_irq(&ws->wait.lock);
+ list_del_init(&wait->entry);
+ spin_unlock_irq(&ws->wait.lock);
spin_unlock(&this_hctx->lock);
- return false;
+ return true;
}
-
- /*
- * We got a tag, remove ourselves from the wait queue to ensure
- * someone else gets the wakeup.
- */
- spin_lock_irq(&ws->wait.lock);
- list_del_init(&wait->entry);
- spin_unlock_irq(&ws->wait.lock);
- spin_unlock(&this_hctx->lock);
- return true;
}
bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
* before we add this entry back on the dispatch list,
* we'll re-run it below.
*/
- if (!blk_mq_dispatch_wait_add(&hctx, rq)) {
+ if (!blk_mq_mark_tag_wait(&hctx, rq)) {
if (got_budget)
blk_mq_put_dispatch_budget(hctx);
- no_tag = true;
+ /*
+ * For non-shared tags, the RESTART check
+ * will suffice.
+ */
+ if (hctx->flags & BLK_MQ_F_TAG_SHARED)
+ no_tag = true;
break;
}
}
if (ret == BLK_STS_RESOURCE) {
/*
* If an I/O scheduler has been configured and we got a
- * driver tag for the next request already, free it again.
+ * driver tag for the next request already, free it
+ * again.
*/
if (!list_empty(list)) {
nxt = list_first_entry(list, struct request, queuelist);
}
EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
-void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
+bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
{
- __blk_mq_delay_run_hw_queue(hctx, async, 0);
+ if (blk_mq_hctx_has_pending(hctx)) {
+ __blk_mq_delay_run_hw_queue(hctx, async, 0);
+ return true;
+ }
+
+ return false;
}
EXPORT_SYMBOL(blk_mq_run_hw_queue);
int i;
queue_for_each_hw_ctx(q, hctx, i) {
- if (!blk_mq_hctx_has_pending(hctx) ||
- blk_mq_hctx_stopped(hctx))
+ if (blk_mq_hctx_stopped(hctx))
continue;
blk_mq_run_hw_queue(hctx, async);
* Allocate space for all possible cpus to avoid allocation at
* runtime
*/
- hctx->ctxs = kmalloc_node(nr_cpu_ids * sizeof(void *),
+ hctx->ctxs = kmalloc_array_node(nr_cpu_ids, sizeof(void *),
GFP_KERNEL, node);
if (!hctx->ctxs)
goto unregister_cpu_notifier;
mutex_lock(&set->tag_list_lock);
- /* Check to see if we're transitioning to shared (from 1 to 2 queues). */
- if (!list_empty(&set->tag_list) && !(set->flags & BLK_MQ_F_TAG_SHARED)) {
+ /*
+ * Check to see if we're transitioning to shared (from 1 to 2 queues).
+ */
+ if (!list_empty(&set->tag_list) &&
+ !(set->flags & BLK_MQ_F_TAG_SHARED)) {
set->flags |= BLK_MQ_F_TAG_SHARED;
/* update existing queue */
blk_mq_update_tag_set_depth(set, true);
/*
* redo blk_mq_init_cpu_queues and blk_mq_init_hw_queues. FIXME: maybe
- * we should change hctx numa_node according to new topology (this
- * involves free and re-allocate memory, worthy doing?)
+ * we should change hctx numa_node according to the new topology (this
+ * involves freeing and re-allocating memory, worth doing?)
*/
-
blk_mq_map_swqueue(q);
blk_mq_sysfs_register(q);