@@ -215,17 +215,6 @@ config BLK_DEV_DM
If unsure, say N.
-config DM_MQ_DEFAULT
- bool "request-based DM: use blk-mq I/O path by default"
- depends on BLK_DEV_DM
- ---help---
- This option enables the blk-mq based I/O path for request-based
- DM devices by default. With the option the dm_mod.use_blk_mq
- module/boot option defaults to Y, without it to N, but it can
- still be overriden either way.
-
- If unsure say N.
-
config DM_DEBUG
bool "Device mapper debugging support"
depends on BLK_DEV_DM
@@ -112,18 +112,8 @@ struct mapped_device {
struct dm_stats stats;
- struct kthread_worker kworker;
- struct task_struct *kworker_task;
-
- /* for request-based merge heuristic in dm_request_fn() */
- unsigned seq_rq_merge_deadline_usecs;
- int last_rq_rw;
- sector_t last_rq_pos;
- ktime_t last_rq_start_time;
-
/* for blk-mq request-based DM support */
struct blk_mq_tag_set *tag_set;
- bool use_blk_mq:1;
bool init_tio_pdu:1;
struct srcu_struct io_barrier;
@@ -203,14 +203,7 @@ static struct multipath *alloc_multipath(struct dm_target *ti)
static int alloc_multipath_stage2(struct dm_target *ti, struct multipath *m)
{
if (m->queue_mode == DM_TYPE_NONE) {
- /*
- * Default to request-based.
- */
- if (dm_use_blk_mq(dm_table_get_md(ti->table)))
- m->queue_mode = DM_TYPE_MQ_REQUEST_BASED;
- else
- m->queue_mode = DM_TYPE_REQUEST_BASED;
-
+ m->queue_mode = DM_TYPE_MQ_REQUEST_BASED;
} else if (m->queue_mode == DM_TYPE_BIO_BASED) {
INIT_WORK(&m->process_queued_bios, process_queued_bios);
/*
@@ -537,10 +530,7 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
* get the queue busy feedback (via BLK_STS_RESOURCE),
* otherwise I/O merging can suffer.
*/
- if (q->mq_ops)
- return DM_MAPIO_REQUEUE;
- else
- return DM_MAPIO_DELAY_REQUEUE;
+ return DM_MAPIO_REQUEUE;
}
clone->bio = clone->biotail = NULL;
clone->rq_disk = bdev->bd_disk;
@@ -23,19 +23,6 @@ static unsigned dm_mq_queue_depth = DM_MQ_QUEUE_DEPTH;
#define RESERVED_REQUEST_BASED_IOS 256
static unsigned reserved_rq_based_ios = RESERVED_REQUEST_BASED_IOS;
-static bool use_blk_mq = IS_ENABLED(CONFIG_DM_MQ_DEFAULT);
-
-bool dm_use_blk_mq_default(void)
-{
- return use_blk_mq;
-}
-
-bool dm_use_blk_mq(struct mapped_device *md)
-{
- return md->use_blk_mq;
-}
-EXPORT_SYMBOL_GPL(dm_use_blk_mq);
-
unsigned dm_get_reserved_rq_based_ios(void)
{
return __dm_get_module_param(&reserved_rq_based_ios,
@@ -59,16 +46,6 @@ int dm_request_based(struct mapped_device *md)
return queue_is_rq_based(md->queue);
}
-static void dm_old_start_queue(struct request_queue *q)
-{
- unsigned long flags;
-
- spin_lock_irqsave(q->queue_lock, flags);
- if (blk_queue_stopped(q))
- blk_start_queue(q);
- spin_unlock_irqrestore(q->queue_lock, flags);
-}
-
static void dm_mq_start_queue(struct request_queue *q)
{
blk_mq_unquiesce_queue(q);
@@ -77,20 +54,7 @@ static void dm_mq_start_queue(struct request_queue *q)
void dm_start_queue(struct request_queue *q)
{
- if (!q->mq_ops)
- dm_old_start_queue(q);
- else
- dm_mq_start_queue(q);
-}
-
-static void dm_old_stop_queue(struct request_queue *q)
-{
- unsigned long flags;
-
- spin_lock_irqsave(q->queue_lock, flags);
- if (!blk_queue_stopped(q))
- blk_stop_queue(q);
- spin_unlock_irqrestore(q->queue_lock, flags);
+ dm_mq_start_queue(q);
}
static void dm_mq_stop_queue(struct request_queue *q)
@@ -103,10 +67,7 @@ static void dm_mq_stop_queue(struct request_queue *q)
void dm_stop_queue(struct request_queue *q)
{
- if (!q->mq_ops)
- dm_old_stop_queue(q);
- else
- dm_mq_stop_queue(q);
+ dm_mq_stop_queue(q);
}
/*
@@ -179,27 +140,12 @@ static void rq_end_stats(struct mapped_device *md, struct request *orig)
*/
static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
{
- struct request_queue *q = md->queue;
- unsigned long flags;
-
atomic_dec(&md->pending[rw]);
/* nudge anyone waiting on suspend queue */
if (!md_in_flight(md))
wake_up(&md->wait);
- /*
- * Run this off this callpath, as drivers could invoke end_io while
- * inside their request_fn (and holding the queue lock). Calling
- * back into ->request_fn() could deadlock attempting to grab the
- * queue lock again.
- */
- if (!q->mq_ops && run_queue) {
- spin_lock_irqsave(q->queue_lock, flags);
- blk_run_queue_async(q);
- spin_unlock_irqrestore(q->queue_lock, flags);
- }
-
/*
* dm_put() must be at the end of this function. See the comment above
*/
@@ -222,27 +168,10 @@ static void dm_end_request(struct request *clone, blk_status_t error)
tio->ti->type->release_clone_rq(clone);
rq_end_stats(md, rq);
- if (!rq->q->mq_ops)
- blk_end_request_all(rq, error);
- else
- blk_mq_end_request(rq, error);
+ blk_mq_end_request(rq, error);
rq_completed(md, rw, true);
}
-/*
- * Requeue the original request of a clone.
- */
-static void dm_old_requeue_request(struct request *rq, unsigned long delay_ms)
-{
- struct request_queue *q = rq->q;
- unsigned long flags;
-
- spin_lock_irqsave(q->queue_lock, flags);
- blk_requeue_request(q, rq);
- blk_delay_queue(q, delay_ms);
- spin_unlock_irqrestore(q->queue_lock, flags);
-}
-
static void __dm_mq_kick_requeue_list(struct request_queue *q, unsigned long msecs)
{
blk_mq_delay_kick_requeue_list(q, msecs);
@@ -273,11 +202,7 @@ static void dm_requeue_original_request(struct dm_rq_target_io *tio, bool delay_
tio->ti->type->release_clone_rq(tio->clone);
}
- if (!rq->q->mq_ops)
- dm_old_requeue_request(rq, delay_ms);
- else
- dm_mq_delay_requeue_request(rq, delay_ms);
-
+ dm_mq_delay_requeue_request(rq, delay_ms);
rq_completed(md, rw, false);
}
@@ -340,10 +265,7 @@ static void dm_softirq_done(struct request *rq)
rq_end_stats(md, rq);
rw = rq_data_dir(rq);
- if (!rq->q->mq_ops)
- blk_end_request_all(rq, tio->error);
- else
- blk_mq_end_request(rq, tio->error);
+ blk_mq_end_request(rq, tio->error);
rq_completed(md, rw, false);
return;
}
@@ -363,10 +285,7 @@ static void dm_complete_request(struct request *rq, blk_status_t error)
struct dm_rq_target_io *tio = tio_from_request(rq);
tio->error = error;
- if (!rq->q->mq_ops)
- blk_complete_request(rq);
- else
- blk_mq_complete_request(rq);
+ blk_mq_complete_request(rq);
}
/*
@@ -446,8 +365,6 @@ static int setup_clone(struct request *clone, struct request *rq,
return 0;
}
-static void map_tio_request(struct kthread_work *work);
-
static void init_tio(struct dm_rq_target_io *tio, struct request *rq,
struct mapped_device *md)
{
@@ -464,8 +381,6 @@ static void init_tio(struct dm_rq_target_io *tio, struct request *rq,
*/
if (!md->init_tio_pdu)
memset(&tio->info, 0, sizeof(tio->info));
- if (md->kworker_task)
- kthread_init_work(&tio->work, map_tio_request);
}
/*
@@ -504,10 +419,7 @@ static int map_request(struct dm_rq_target_io *tio)
blk_rq_unprep_clone(clone);
tio->ti->type->release_clone_rq(clone);
tio->clone = NULL;
- if (!rq->q->mq_ops)
- r = DM_MAPIO_DELAY_REQUEUE;
- else
- r = DM_MAPIO_REQUEUE;
+ r = DM_MAPIO_REQUEUE;
goto check_again;
}
break;
@@ -530,20 +442,23 @@ static int map_request(struct dm_rq_target_io *tio)
return r;
}
+/* DEPRECATED: previously used for request-based merge heuristic in dm_request_fn() */
+ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf)
+{
+ return sprintf(buf, "%u\n", 0);
+}
+
+ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md,
+ const char *buf, size_t count)
+{
+ return count;
+}
+
static void dm_start_request(struct mapped_device *md, struct request *orig)
{
- if (!orig->q->mq_ops)
- blk_start_request(orig);
- else
- blk_mq_start_request(orig);
+ blk_mq_start_request(orig);
atomic_inc(&md->pending[rq_data_dir(orig)]);
- if (md->seq_rq_merge_deadline_usecs) {
- md->last_rq_pos = rq_end_sector(orig);
- md->last_rq_rw = rq_data_dir(orig);
- md->last_rq_start_time = ktime_get();
- }
-
if (unlikely(dm_stats_used(&md->stats))) {
struct dm_rq_target_io *tio = tio_from_request(orig);
tio->duration_jiffies = jiffies;
@@ -563,8 +478,10 @@ static void dm_start_request(struct mapped_device *md, struct request *orig)
dm_get(md);
}
-static int __dm_rq_init_rq(struct mapped_device *md, struct request *rq)
+static int dm_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,
+ unsigned int hctx_idx, unsigned int numa_node)
{
+ struct mapped_device *md = set->driver_data;
struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
/*
@@ -581,163 +498,6 @@ static int __dm_rq_init_rq(struct mapped_device *md, struct request *rq)
return 0;
}
-static int dm_rq_init_rq(struct request_queue *q, struct request *rq, gfp_t gfp)
-{
- return __dm_rq_init_rq(q->rq_alloc_data, rq);
-}
-
-static void map_tio_request(struct kthread_work *work)
-{
- struct dm_rq_target_io *tio = container_of(work, struct dm_rq_target_io, work);
-
- if (map_request(tio) == DM_MAPIO_REQUEUE)
- dm_requeue_original_request(tio, false);
-}
-
-ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf)
-{
- return sprintf(buf, "%u\n", md->seq_rq_merge_deadline_usecs);
-}
-
-#define MAX_SEQ_RQ_MERGE_DEADLINE_USECS 100000
-
-ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md,
- const char *buf, size_t count)
-{
- unsigned deadline;
-
- if (dm_get_md_type(md) != DM_TYPE_REQUEST_BASED)
- return count;
-
- if (kstrtouint(buf, 10, &deadline))
- return -EINVAL;
-
- if (deadline > MAX_SEQ_RQ_MERGE_DEADLINE_USECS)
- deadline = MAX_SEQ_RQ_MERGE_DEADLINE_USECS;
-
- md->seq_rq_merge_deadline_usecs = deadline;
-
- return count;
-}
-
-static bool dm_old_request_peeked_before_merge_deadline(struct mapped_device *md)
-{
- ktime_t kt_deadline;
-
- if (!md->seq_rq_merge_deadline_usecs)
- return false;
-
- kt_deadline = ns_to_ktime((u64)md->seq_rq_merge_deadline_usecs * NSEC_PER_USEC);
- kt_deadline = ktime_add_safe(md->last_rq_start_time, kt_deadline);
-
- return !ktime_after(ktime_get(), kt_deadline);
-}
-
-/*
- * q->request_fn for old request-based dm.
- * Called with the queue lock held.
- */
-static void dm_old_request_fn(struct request_queue *q)
-{
- struct mapped_device *md = q->queuedata;
- struct dm_target *ti = md->immutable_target;
- struct request *rq;
- struct dm_rq_target_io *tio;
- sector_t pos = 0;
-
- if (unlikely(!ti)) {
- int srcu_idx;
- struct dm_table *map = dm_get_live_table(md, &srcu_idx);
-
- if (unlikely(!map)) {
- dm_put_live_table(md, srcu_idx);
- return;
- }
- ti = dm_table_find_target(map, pos);
- dm_put_live_table(md, srcu_idx);
- }
-
- /*
- * For suspend, check blk_queue_stopped() and increment
- * ->pending within a single queue_lock not to increment the
- * number of in-flight I/Os after the queue is stopped in
- * dm_suspend().
- */
- while (!blk_queue_stopped(q)) {
- rq = blk_peek_request(q);
- if (!rq)
- return;
-
- /* always use block 0 to find the target for flushes for now */
- pos = 0;
- if (req_op(rq) != REQ_OP_FLUSH)
- pos = blk_rq_pos(rq);
-
- if ((dm_old_request_peeked_before_merge_deadline(md) &&
- md_in_flight(md) && rq->bio && !bio_multiple_segments(rq->bio) &&
- md->last_rq_pos == pos && md->last_rq_rw == rq_data_dir(rq)) ||
- (ti->type->busy && ti->type->busy(ti))) {
- blk_delay_queue(q, 10);
- return;
- }
-
- dm_start_request(md, rq);
-
- tio = tio_from_request(rq);
- init_tio(tio, rq, md);
- /* Establish tio->ti before queuing work (map_tio_request) */
- tio->ti = ti;
- kthread_queue_work(&md->kworker, &tio->work);
- BUG_ON(!irqs_disabled());
- }
-}
-
-/*
- * Fully initialize a .request_fn request-based queue.
- */
-int dm_old_init_request_queue(struct mapped_device *md, struct dm_table *t)
-{
- struct dm_target *immutable_tgt;
-
- /* Fully initialize the queue */
- md->queue->cmd_size = sizeof(struct dm_rq_target_io);
- md->queue->rq_alloc_data = md;
- md->queue->request_fn = dm_old_request_fn;
- md->queue->init_rq_fn = dm_rq_init_rq;
-
- immutable_tgt = dm_table_get_immutable_target(t);
- if (immutable_tgt && immutable_tgt->per_io_data_size) {
- /* any target-specific per-io data is immediately after the tio */
- md->queue->cmd_size += immutable_tgt->per_io_data_size;
- md->init_tio_pdu = true;
- }
- if (blk_init_allocated_queue(md->queue) < 0)
- return -EINVAL;
-
- /* disable dm_old_request_fn's merge heuristic by default */
- md->seq_rq_merge_deadline_usecs = 0;
-
- blk_queue_softirq_done(md->queue, dm_softirq_done);
-
- /* Initialize the request-based DM worker thread */
- kthread_init_worker(&md->kworker);
- md->kworker_task = kthread_run(kthread_worker_fn, &md->kworker,
- "kdmwork-%s", dm_device_name(md));
- if (IS_ERR(md->kworker_task)) {
- int error = PTR_ERR(md->kworker_task);
- md->kworker_task = NULL;
- return error;
- }
-
- return 0;
-}
-
-static int dm_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,
- unsigned int hctx_idx, unsigned int numa_node)
-{
- return __dm_rq_init_rq(set->driver_data, rq);
-}
-
static blk_status_t dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
@@ -790,11 +550,6 @@ int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t)
struct dm_target *immutable_tgt;
int err;
- if (!dm_table_all_blk_mq_devices(t)) {
- DMERR("request-based dm-mq may only be stacked on blk-mq device(s)");
- return -EINVAL;
- }
-
md->tag_set = kzalloc_node(sizeof(struct blk_mq_tag_set), GFP_KERNEL, md->numa_node_id);
if (!md->tag_set)
return -ENOMEM;
@@ -845,6 +600,8 @@ void dm_mq_cleanup_mapped_device(struct mapped_device *md)
module_param(reserved_rq_based_ios, uint, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(reserved_rq_based_ios, "Reserved IOs in request-based mempools");
+/* Unused, but preserved for userspace compatibility */
+static bool use_blk_mq = true;
module_param(use_blk_mq, bool, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(use_blk_mq, "Use block multiqueue for request-based DM devices");
@@ -46,10 +46,6 @@ struct dm_rq_clone_bio_info {
struct bio clone;
};
-bool dm_use_blk_mq_default(void);
-bool dm_use_blk_mq(struct mapped_device *md);
-
-int dm_old_init_request_queue(struct mapped_device *md, struct dm_table *t);
int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t);
void dm_mq_cleanup_mapped_device(struct mapped_device *md);
@@ -92,7 +92,8 @@ static ssize_t dm_attr_suspended_show(struct mapped_device *md, char *buf)
static ssize_t dm_attr_use_blk_mq_show(struct mapped_device *md, char *buf)
{
- sprintf(buf, "%d\n", dm_use_blk_mq(md));
+ /* Purely for userspace compatibility */
+ sprintf(buf, "%d\n", true);
return strlen(buf);
}
@@ -47,7 +47,6 @@ struct dm_table {
bool integrity_supported:1;
bool singleton:1;
- bool all_blk_mq:1;
unsigned integrity_added:1;
/*
@@ -921,10 +920,7 @@ static int device_is_rq_based(struct dm_target *ti, struct dm_dev *dev,
struct request_queue *q = bdev_get_queue(dev->bdev);
struct verify_rq_based_data *v = data;
- if (q->mq_ops)
- v->mq_count++;
- else
- v->sq_count++;
+ v->mq_count++;
return queue_is_rq_based(q);
}
@@ -1022,11 +1018,9 @@ static int dm_table_determine_type(struct dm_table *t)
int srcu_idx;
struct dm_table *live_table = dm_get_live_table(t->md, &srcu_idx);
- /* inherit live table's type and all_blk_mq */
- if (live_table) {
+ /* inherit live table's type */
+ if (live_table)
t->type = live_table->type;
- t->all_blk_mq = live_table->all_blk_mq;
- }
dm_put_live_table(t->md, srcu_idx);
return 0;
}
@@ -1050,13 +1044,6 @@ static int dm_table_determine_type(struct dm_table *t)
DMERR("table load rejected: not all devices are blk-mq request-stackable");
return -EINVAL;
}
- t->all_blk_mq = v.mq_count > 0;
-
- if (!t->all_blk_mq &&
- (t->type == DM_TYPE_MQ_REQUEST_BASED || t->type == DM_TYPE_NVME_BIO_BASED)) {
- DMERR("table load rejected: all devices are not blk-mq request-stackable");
- return -EINVAL;
- }
return 0;
}
@@ -1105,11 +1092,6 @@ bool dm_table_request_based(struct dm_table *t)
return __table_type_request_based(dm_table_get_type(t));
}
-bool dm_table_all_blk_mq_devices(struct dm_table *t)
-{
- return t->all_blk_mq;
-}
-
static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *md)
{
enum dm_queue_mode type = dm_table_get_type(t);
@@ -2093,22 +2075,14 @@ void dm_table_run_md_queue_async(struct dm_table *t)
{
struct mapped_device *md;
struct request_queue *queue;
- unsigned long flags;
if (!dm_table_request_based(t))
return;
md = dm_table_get_md(t);
queue = dm_get_md_queue(md);
- if (queue) {
- if (queue->mq_ops)
- blk_mq_run_hw_queues(queue, true);
- else {
- spin_lock_irqsave(queue->queue_lock, flags);
- blk_run_queue_async(queue);
- spin_unlock_irqrestore(queue->queue_lock, flags);
- }
- }
+ if (queue)
+ blk_mq_run_hw_queues(queue, true);
}
EXPORT_SYMBOL(dm_table_run_md_queue_async);
@@ -1806,8 +1806,6 @@ static void dm_wq_work(struct work_struct *work);
static void dm_init_normal_md_queue(struct mapped_device *md)
{
- md->use_blk_mq = false;
-
/*
* Initialize aspects of queue that aren't relevant for blk-mq
*/
@@ -1818,8 +1816,6 @@ static void cleanup_mapped_device(struct mapped_device *md)
{
if (md->wq)
destroy_workqueue(md->wq);
- if (md->kworker_task)
- kthread_stop(md->kworker_task);
bioset_exit(&md->bs);
bioset_exit(&md->io_bs);
@@ -1886,7 +1882,6 @@ static struct mapped_device *alloc_dev(int minor)
goto bad_io_barrier;
md->numa_node_id = numa_node_id;
- md->use_blk_mq = dm_use_blk_mq_default();
md->init_tio_pdu = false;
md->type = DM_TYPE_NONE;
mutex_init(&md->suspend_lock);
@@ -1917,7 +1912,6 @@ static struct mapped_device *alloc_dev(int minor)
INIT_WORK(&md->work, dm_wq_work);
init_waitqueue_head(&md->eventq);
init_completion(&md->kobj_holder.completion);
- md->kworker_task = NULL;
md->disk->major = _major;
md->disk->first_minor = minor;
@@ -2217,13 +2211,6 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
switch (type) {
case DM_TYPE_REQUEST_BASED:
- dm_init_normal_md_queue(md);
- r = dm_old_init_request_queue(md, t);
- if (r) {
- DMERR("Cannot initialize queue for request-based mapped device");
- return r;
- }
- break;
case DM_TYPE_MQ_REQUEST_BASED:
r = dm_mq_init_request_queue(md, t);
if (r) {
@@ -2329,9 +2316,6 @@ static void __dm_destroy(struct mapped_device *md, bool wait)
blk_set_queue_dying(md->queue);
- if (dm_request_based(md) && md->kworker_task)
- kthread_flush_worker(&md->kworker);
-
/*
* Take suspend_lock so that presuspend and postsuspend methods
* do not race with internal suspend.
@@ -2584,11 +2568,8 @@ static int __dm_suspend(struct mapped_device *md, struct dm_table *map,
* Stop md->queue before flushing md->wq in case request-based
* dm defers requests to md->wq from md->queue.
*/
- if (dm_request_based(md)) {
+ if (dm_request_based(md))
dm_stop_queue(md->queue);
- if (md->kworker_task)
- kthread_flush_worker(&md->kworker);
- }
flush_workqueue(md->wq);
@@ -70,7 +70,6 @@ struct dm_target *dm_table_get_immutable_target(struct dm_table *t);
struct dm_target *dm_table_get_wildcard_target(struct dm_table *t);
bool dm_table_bio_based(struct dm_table *t);
bool dm_table_request_based(struct dm_table *t);
-bool dm_table_all_blk_mq_devices(struct dm_table *t);
void dm_table_free_md_mempools(struct dm_table *t);
struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t);
dm supports both, and since we're killing off the legacy path in general, get rid of it in dm as well. Signed-off-by: Jens Axboe <axboe@kernel.dk> --- drivers/md/Kconfig | 11 -- drivers/md/dm-core.h | 10 -- drivers/md/dm-mpath.c | 14 +- drivers/md/dm-rq.c | 293 ++++-------------------------------------- drivers/md/dm-rq.h | 4 - drivers/md/dm-sysfs.c | 3 +- drivers/md/dm-table.c | 36 +----- drivers/md/dm.c | 21 +-- drivers/md/dm.h | 1 - 9 files changed, 35 insertions(+), 358 deletions(-)