static DEFINE_MUTEX(all_q_mutex);
static LIST_HEAD(all_q_list);
-static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx);
-
/*
* Check if any of the ctx's have pending work in this hardware queue
*/
return ERR_PTR(ret);
ctx = blk_mq_get_ctx(q);
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
+ hctx = blk_mq_map_queue(q, ctx->cpu);
blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
-
rq = __blk_mq_alloc_request(&alloc_data, rw, 0);
- if (!rq && !(flags & BLK_MQ_REQ_NOWAIT)) {
- __blk_mq_run_hw_queue(hctx);
- blk_mq_put_ctx(ctx);
-
- ctx = blk_mq_get_ctx(q);
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
- blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
- rq = __blk_mq_alloc_request(&alloc_data, rw, 0);
- ctx = alloc_data.ctx;
- }
blk_mq_put_ctx(ctx);
+
if (!rq) {
blk_queue_exit(q);
return ERR_PTR(-EWOULDBLOCK);
if (ret)
return ERR_PTR(ret);
+ /*
+ * Check if the hardware context is actually mapped to anything.
+ * If not tell the caller that it should skip this queue.
+ */
hctx = q->queue_hw_ctx[hctx_idx];
+ if (!blk_mq_hw_queue_mapped(hctx)) {
+ ret = -EXDEV;
+ goto out_queue_exit;
+ }
ctx = __blk_mq_get_ctx(q, cpumask_first(hctx->cpumask));
blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
rq = __blk_mq_alloc_request(&alloc_data, rw, 0);
if (!rq) {
- blk_queue_exit(q);
- return ERR_PTR(-EWOULDBLOCK);
+ ret = -EWOULDBLOCK;
+ goto out_queue_exit;
}
return rq;
+
+out_queue_exit:
+ blk_queue_exit(q);
+ return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
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);
+ blk_mq_free_hctx_request(blk_mq_map_queue(rq->q, rq->mq_ctx->cpu), rq);
}
EXPORT_SYMBOL_GPL(blk_mq_free_request);
!blk_mq_hw_queue_mapped(hctx)))
return;
- if (!async) {
+ if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) {
int cpu = get_cpu();
if (cpumask_test_cpu(cpu, hctx->cpumask)) {
__blk_mq_run_hw_queue(hctx);
{
struct blk_mq_ctx *ctx = rq->mq_ctx;
struct request_queue *q = rq->q;
- struct blk_mq_hw_ctx *hctx;
-
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
+ struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
spin_lock(&ctx->lock);
__blk_mq_insert_request(hctx, rq, at_head);
bool from_schedule)
{
- struct blk_mq_hw_ctx *hctx;
+ struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
trace_block_unplug(q, depth, !from_schedule);
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
-
/*
* preemption doesn't flush plug list, so it's possible ctx->cpu is
* offline now
blk_queue_enter_live(q);
ctx = blk_mq_get_ctx(q);
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
+ hctx = blk_mq_map_queue(q, ctx->cpu);
if (rw_is_sync(bio_op(bio), bio->bi_opf))
op_flags |= REQ_SYNC;
trace_block_getrq(q, bio, op);
- blk_mq_set_alloc_data(&alloc_data, q, BLK_MQ_REQ_NOWAIT, ctx, hctx);
+ blk_mq_set_alloc_data(&alloc_data, q, 0, ctx, hctx);
rq = __blk_mq_alloc_request(&alloc_data, op, op_flags);
- if (unlikely(!rq)) {
- __blk_mq_run_hw_queue(hctx);
- blk_mq_put_ctx(ctx);
- trace_block_sleeprq(q, bio, op);
-
- ctx = blk_mq_get_ctx(q);
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
- blk_mq_set_alloc_data(&alloc_data, q, 0, ctx, hctx);
- rq = __blk_mq_alloc_request(&alloc_data, op, op_flags);
- ctx = alloc_data.ctx;
- hctx = alloc_data.hctx;
- }
hctx->queued++;
data->hctx = hctx;
{
int ret;
struct request_queue *q = rq->q;
- struct blk_mq_hw_ctx *hctx = q->mq_ops->map_queue(q,
- rq->mq_ctx->cpu);
+ struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu);
struct blk_mq_queue_data bd = {
.rq = rq,
.list = NULL,
return cookie;
}
-/*
- * Default mapping to a software queue, since we use one per CPU.
- */
-struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q, const int cpu)
-{
- return q->queue_hw_ctx[q->mq_map[cpu]];
-}
-EXPORT_SYMBOL(blk_mq_map_queue);
-
static void blk_mq_free_rq_map(struct blk_mq_tag_set *set,
struct blk_mq_tags *tags, unsigned int hctx_idx)
{
* software queue to the hw queue dispatch list, and ensure that it
* gets run.
*/
- static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu)
+ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
{
+ struct blk_mq_hw_ctx *hctx;
struct blk_mq_ctx *ctx;
LIST_HEAD(tmp);
+ hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_dead);
ctx = __blk_mq_get_ctx(hctx->queue, cpu);
spin_lock(&ctx->lock);
spin_unlock(&ctx->lock);
if (list_empty(&tmp))
- return NOTIFY_OK;
+ return 0;
spin_lock(&hctx->lock);
list_splice_tail_init(&tmp, &hctx->dispatch);
spin_unlock(&hctx->lock);
blk_mq_run_hw_queue(hctx, true);
- return NOTIFY_OK;
+ return 0;
}
- static int blk_mq_hctx_notify(void *data, unsigned long action,
- unsigned int cpu)
+ static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx)
{
- struct blk_mq_hw_ctx *hctx = data;
-
- if (action == CPU_DEAD || action == CPU_DEAD_FROZEN)
- return blk_mq_hctx_cpu_offline(hctx, cpu);
-
- /*
- * In case of CPU online, tags may be reallocated
- * in blk_mq_map_swqueue() after mapping is updated.
- */
-
- return NOTIFY_OK;
+ cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD,
+ &hctx->cpuhp_dead);
}
/* hctx->ctxs will be freed in queue's release handler */
if (set->ops->exit_hctx)
set->ops->exit_hctx(hctx, hctx_idx);
- blk_mq_unregister_cpu_notifier(&hctx->cpu_notifier);
+ blk_mq_remove_cpuhp(hctx);
blk_free_flush_queue(hctx->fq);
sbitmap_free(&hctx->ctx_map);
}
hctx->queue_num = hctx_idx;
hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED;
- blk_mq_init_cpu_notifier(&hctx->cpu_notifier,
- blk_mq_hctx_notify, hctx);
- blk_mq_register_cpu_notifier(&hctx->cpu_notifier);
+ cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);
hctx->tags = set->tags[hctx_idx];
free_ctxs:
kfree(hctx->ctxs);
unregister_cpu_notifier:
- blk_mq_unregister_cpu_notifier(&hctx->cpu_notifier);
-
+ blk_mq_remove_cpuhp(hctx);
return -1;
}
if (!cpu_online(i))
continue;
- hctx = q->mq_ops->map_queue(q, i);
+ hctx = blk_mq_map_queue(q, i);
/*
* Set local node, IFF we have more than one hw queue. If
continue;
ctx = per_cpu_ptr(q->queue_ctx, i);
- hctx = q->mq_ops->map_queue(q, i);
+ hctx = blk_mq_map_queue(q, i);
cpumask_set_cpu(i, hctx->cpumask);
ctx->index_hw = hctx->nr_ctx;
hctx->tags = set->tags[i];
WARN_ON(!hctx->tags);
- cpumask_copy(hctx->tags->cpumask, hctx->cpumask);
/*
* Set the map size to the number of mapped software queues.
* This is more accurate and more efficient than looping
kfree(hctx);
}
- kfree(q->mq_map);
q->mq_map = NULL;
kfree(q->queue_hw_ctx);
if (!q->queue_hw_ctx)
goto err_percpu;
- q->mq_map = blk_mq_make_queue_map(set);
- if (!q->mq_map)
- goto err_map;
+ q->mq_map = set->mq_map;
blk_mq_realloc_hw_ctxs(set, q);
if (!q->nr_hw_queues)
return q;
err_hctxs:
- kfree(q->mq_map);
-err_map:
kfree(q->queue_hw_ctx);
err_percpu:
free_percpu(q->queue_ctx);
blk_mq_sysfs_unregister(q);
- blk_mq_update_queue_map(q->mq_map, q->nr_hw_queues, online_mask);
-
/*
* 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
blk_mq_sysfs_register(q);
}
- static int blk_mq_queue_reinit_notify(struct notifier_block *nb,
- unsigned long action, void *hcpu)
+ /*
+ * New online cpumask which is going to be set in this hotplug event.
+ * Declare this cpumasks as global as cpu-hotplug operation is invoked
+ * one-by-one and dynamically allocating this could result in a failure.
+ */
+ static struct cpumask cpuhp_online_new;
+
+ static void blk_mq_queue_reinit_work(void)
{
struct request_queue *q;
- int cpu = (unsigned long)hcpu;
- /*
- * New online cpumask which is going to be set in this hotplug event.
- * Declare this cpumasks as global as cpu-hotplug operation is invoked
- * one-by-one and dynamically allocating this could result in a failure.
- */
- static struct cpumask online_new;
-
- /*
- * Before hotadded cpu starts handling requests, new mappings must
- * be established. Otherwise, these requests in hw queue might
- * never be dispatched.
- *
- * For example, there is a single hw queue (hctx) and two CPU queues
- * (ctx0 for CPU0, and ctx1 for CPU1).
- *
- * Now CPU1 is just onlined and a request is inserted into
- * ctx1->rq_list and set bit0 in pending bitmap as ctx1->index_hw is
- * still zero.
- *
- * And then while running hw queue, flush_busy_ctxs() finds bit0 is
- * set in pending bitmap and tries to retrieve requests in
- * hctx->ctxs[0]->rq_list. But htx->ctxs[0] is a pointer to ctx0,
- * so the request in ctx1->rq_list is ignored.
- */
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_DEAD:
- case CPU_UP_CANCELED:
- cpumask_copy(&online_new, cpu_online_mask);
- break;
- case CPU_UP_PREPARE:
- cpumask_copy(&online_new, cpu_online_mask);
- cpumask_set_cpu(cpu, &online_new);
- break;
- default:
- return NOTIFY_OK;
- }
mutex_lock(&all_q_mutex);
-
/*
* We need to freeze and reinit all existing queues. Freezing
* involves synchronous wait for an RCU grace period and doing it
}
list_for_each_entry(q, &all_q_list, all_q_node)
- blk_mq_queue_reinit(q, &online_new);
+ blk_mq_queue_reinit(q, &cpuhp_online_new);
list_for_each_entry(q, &all_q_list, all_q_node)
blk_mq_unfreeze_queue(q);
mutex_unlock(&all_q_mutex);
- return NOTIFY_OK;
+ }
+
+ static int blk_mq_queue_reinit_dead(unsigned int cpu)
+ {
+ cpumask_copy(&cpuhp_online_new, cpu_online_mask);
+ blk_mq_queue_reinit_work();
+ return 0;
+ }
+
+ /*
+ * Before hotadded cpu starts handling requests, new mappings must be
+ * established. Otherwise, these requests in hw queue might never be
+ * dispatched.
+ *
+ * For example, there is a single hw queue (hctx) and two CPU queues (ctx0
+ * for CPU0, and ctx1 for CPU1).
+ *
+ * Now CPU1 is just onlined and a request is inserted into ctx1->rq_list
+ * and set bit0 in pending bitmap as ctx1->index_hw is still zero.
+ *
+ * And then while running hw queue, flush_busy_ctxs() finds bit0 is set in
+ * pending bitmap and tries to retrieve requests in hctx->ctxs[0]->rq_list.
+ * But htx->ctxs[0] is a pointer to ctx0, so the request in ctx1->rq_list
+ * is ignored.
+ */
+ static int blk_mq_queue_reinit_prepare(unsigned int cpu)
+ {
+ cpumask_copy(&cpuhp_online_new, cpu_online_mask);
+ cpumask_set_cpu(cpu, &cpuhp_online_new);
+ blk_mq_queue_reinit_work();
+ return 0;
}
static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
return 0;
}
-struct cpumask *blk_mq_tags_cpumask(struct blk_mq_tags *tags)
-{
- return tags->cpumask;
-}
-EXPORT_SYMBOL_GPL(blk_mq_tags_cpumask);
-
/*
* Alloc a tag set to be associated with one or more request queues.
* May fail with EINVAL for various error conditions. May adjust the
*/
int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
{
+ int ret;
+
BUILD_BUG_ON(BLK_MQ_MAX_DEPTH > 1 << BLK_MQ_UNIQUE_TAG_BITS);
if (!set->nr_hw_queues)
if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN)
return -EINVAL;
- if (!set->ops->queue_rq || !set->ops->map_queue)
+ if (!set->ops->queue_rq)
return -EINVAL;
if (set->queue_depth > BLK_MQ_MAX_DEPTH) {
if (!set->tags)
return -ENOMEM;
- if (blk_mq_alloc_rq_maps(set))
- goto enomem;
+ ret = -ENOMEM;
+ set->mq_map = kzalloc_node(sizeof(*set->mq_map) * nr_cpu_ids,
+ GFP_KERNEL, set->numa_node);
+ if (!set->mq_map)
+ goto out_free_tags;
+
+ if (set->ops->map_queues)
+ ret = set->ops->map_queues(set);
+ else
+ ret = blk_mq_map_queues(set);
+ if (ret)
+ goto out_free_mq_map;
+
+ ret = blk_mq_alloc_rq_maps(set);
+ if (ret)
+ goto out_free_mq_map;
mutex_init(&set->tag_list_lock);
INIT_LIST_HEAD(&set->tag_list);
return 0;
-enomem:
+
+out_free_mq_map:
+ kfree(set->mq_map);
+ set->mq_map = NULL;
+out_free_tags:
kfree(set->tags);
set->tags = NULL;
- return -ENOMEM;
+ return ret;
}
EXPORT_SYMBOL(blk_mq_alloc_tag_set);
blk_mq_free_rq_map(set, set->tags[i], i);
}
+ kfree(set->mq_map);
+ set->mq_map = NULL;
+
kfree(set->tags);
set->tags = NULL;
}
static int __init blk_mq_init(void)
{
- blk_mq_cpu_init();
-
- hotcpu_notifier(blk_mq_queue_reinit_notify, 0);
+ cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL,
+ blk_mq_hctx_notify_dead);
+ cpuhp_setup_state_nocalls(CPUHP_BLK_MQ_PREPARE, "block/mq:prepare",
+ blk_mq_queue_reinit_prepare,
+ blk_mq_queue_reinit_dead);
return 0;
}
subsys_initcall(blk_mq_init);