blk-mq-sched: allow setting of default IO scheduler

Add Kconfig entries to manage what devices get assigned an MQ
scheduler, and add a blk-mq flag for drivers to opt out of scheduling.
The latter is useful for admin type queues that still allocate a blk-mq
queue and tag set, but aren't use for normal IO.

Signed-off-by: Jens Axboe <axboe@fb.com>

diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index 490ef2850faee1f6682e112a7876c35340794502..96216cf185604cfb7f2e94b2d4525c89415532a5 100644 (file)
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -32,12 +32,6 @@ config IOSCHED_CFQ
 
          This is the default I/O scheduler.
 
-config MQ_IOSCHED_DEADLINE
-       tristate "MQ deadline I/O scheduler"
-       default y
-       ---help---
-         MQ version of the deadline IO scheduler.
-
 config CFQ_GROUP_IOSCHED
        bool "CFQ Group Scheduling support"
        depends on IOSCHED_CFQ && BLK_CGROUP
@@ -69,6 +63,43 @@ config DEFAULT_IOSCHED
        default "cfq" if DEFAULT_CFQ
        default "noop" if DEFAULT_NOOP
 
+config MQ_IOSCHED_DEADLINE
+       tristate "MQ deadline I/O scheduler"
+       default y
+       ---help---
+         MQ version of the deadline IO scheduler.
+
+config MQ_IOSCHED_NONE
+       bool
+       default y
+
+choice
+       prompt "Default MQ I/O scheduler"
+       default MQ_IOSCHED_NONE
+       help
+         Select the I/O scheduler which will be used by default for all
+         blk-mq managed block devices.
+
+       config DEFAULT_MQ_DEADLINE
+               bool "MQ Deadline" if MQ_IOSCHED_DEADLINE=y
+
+       config DEFAULT_MQ_NONE
+               bool "None"
+
+endchoice
+
+config DEFAULT_MQ_IOSCHED
+       string
+       default "mq-deadline" if DEFAULT_MQ_DEADLINE
+       default "none" if DEFAULT_MQ_NONE
+
+config MQ_IOSCHED_ONLY_SQ
+       bool "Enable blk-mq IO scheduler only for single queue devices"
+       default y
+       help
+         Say Y here, if you only want to enable IO scheduling on block
+         devices that have a single queue registered.
+
 endmenu
 
 endif

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index b7e1839d4785a707254c1a81f5d047472f355c39..1f06efcdaa2dbced01feb39edc7ebf43bf0a4539 100644 (file)
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -432,3 +432,22 @@ void blk_mq_sched_request_inserted(struct request *rq)
        trace_block_rq_insert(rq->q, rq);
 }
 EXPORT_SYMBOL_GPL(blk_mq_sched_request_inserted);
+
+int blk_mq_sched_init(struct request_queue *q)
+{
+       int ret;
+
+#if defined(CONFIG_DEFAULT_MQ_NONE)
+       return 0;
+#endif
+#if defined(CONFIG_MQ_IOSCHED_ONLY_SQ)
+       if (q->nr_hw_queues > 1)
+               return 0;
+#endif
+
+       mutex_lock(&q->sysfs_lock);
+       ret = elevator_init(q, NULL);
+       mutex_unlock(&q->sysfs_lock);
+
+       return ret;
+}

diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index 1d1a4e9ce6cac41a26b67964e5e9eddb41a9d9ec..826f3e6991e3e1d2b818ba91709f9f37813366db 100644 (file)
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -37,6 +37,8 @@ bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq);
 
 void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
 
+int blk_mq_sched_init(struct request_queue *q);
+
 static inline bool
 blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
 {

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 30e3906f30c4d903890e1533f322bb0a1d5fc066..3a19834211b211e6eb1204cb25a6ba4eddb1e317 100644 (file)
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2121,6 +2121,9 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
        INIT_LIST_HEAD(&q->requeue_list);
        spin_lock_init(&q->requeue_lock);
 
+       if (!(set->flags & BLK_MQ_F_NO_SCHED))
+               blk_mq_sched_init(q);
+
        if (q->nr_hw_queues > 1)
                blk_queue_make_request(q, blk_mq_make_request);
        else

diff --git a/block/elevator.c b/block/elevator.c
index e6b52336023118c62c6be692580d515e18c336a9..eb34c26f675fc28a235771131b9258f82821972c 100644 (file)
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -219,7 +219,10 @@ int elevator_init(struct request_queue *q, char *name)
        }
 
        if (!e) {
-               e = elevator_get(CONFIG_DEFAULT_IOSCHED, false);
+               if (q->mq_ops)
+                       e = elevator_get(CONFIG_DEFAULT_MQ_IOSCHED, false);
+               else
+                       e = elevator_get(CONFIG_DEFAULT_IOSCHED, false);
                if (!e) {
                        printk(KERN_ERR
                                "Default I/O scheduler not found. " \

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 2fd7dc2e8fc4b742f505b7c54961f1be4dc927de..f2b252ff6855bdf351497aebe9e2623751161d87 100644 (file)
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1188,6 +1188,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev)
                dev->admin_tagset.timeout = ADMIN_TIMEOUT;
                dev->admin_tagset.numa_node = dev_to_node(dev->dev);
                dev->admin_tagset.cmd_size = nvme_cmd_size(dev);
+               dev->admin_tagset.flags = BLK_MQ_F_NO_SCHED;
                dev->admin_tagset.driver_data = dev;
 
                if (blk_mq_alloc_tag_set(&dev->admin_tagset))

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index e3159be841ffb1b3580415d6c9f81c9bc6ac68d9..9255ccb043f27abf85fd109900f8dc7818f42470 100644 (file)
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -152,6 +152,7 @@ enum {
        BLK_MQ_F_SG_MERGE       = 1 << 2,
        BLK_MQ_F_DEFER_ISSUE    = 1 << 4,
        BLK_MQ_F_BLOCKING       = 1 << 5,
+       BLK_MQ_F_NO_SCHED       = 1 << 6,
        BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
        BLK_MQ_F_ALLOC_POLICY_BITS = 1,