dm: submit stacked requests in irq enabled context
Switch to having request-based DM enqueue all prep'ed requests into work
processed by another thread. This allows request-based DM to invoke
block APIs that assume interrupt enabled context (e.g. blk_get_request)
and is a prerequisite for adding blk-mq support to request-based DM.
The new kernel thread is only initialized for request-based DM devices.
multipath_map() is now always in irq enabled context so change multipath
spinlock (m->lock) locking to always disable interrupts.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 9a857e3..f0e3407 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -20,6 +20,7 @@
#include <linux/hdreg.h>
#include <linux/delay.h>
#include <linux/wait.h>
+#include <linux/kthread.h>
#include <trace/events/block.h>
@@ -79,6 +80,7 @@
struct mapped_device *md;
struct dm_target *ti;
struct request *orig, *clone;
+ struct kthread_work work;
int error;
union map_info info;
};
@@ -208,6 +210,9 @@
struct bio flush_bio;
struct dm_stats stats;
+
+ struct kthread_worker kworker;
+ struct task_struct *kworker_task;
};
/*
@@ -1773,6 +1778,8 @@
return clone;
}
+static void map_tio_request(struct kthread_work *work);
+
static struct request *clone_rq(struct request *rq, struct mapped_device *md,
gfp_t gfp_mask)
{
@@ -1789,6 +1796,7 @@
tio->orig = rq;
tio->error = 0;
memset(&tio->info, 0, sizeof(tio->info));
+ init_kthread_work(&tio->work, map_tio_request);
clone = __clone_rq(rq, md, tio, GFP_ATOMIC);
if (!clone) {
@@ -1833,7 +1841,6 @@
int r, requeued = 0;
struct dm_rq_target_io *tio = clone->end_io_data;
- tio->ti = ti;
r = ti->type->map_rq(ti, clone, &tio->info);
switch (r) {
case DM_MAPIO_SUBMITTED:
@@ -1864,6 +1871,13 @@
return requeued;
}
+static void map_tio_request(struct kthread_work *work)
+{
+ struct dm_rq_target_io *tio = container_of(work, struct dm_rq_target_io, work);
+
+ map_request(tio->ti, tio->clone, tio->md);
+}
+
static struct request *dm_start_request(struct mapped_device *md, struct request *orig)
{
struct request *clone;
@@ -1895,6 +1909,7 @@
struct dm_table *map = dm_get_live_table(md, &srcu_idx);
struct dm_target *ti;
struct request *rq, *clone;
+ struct dm_rq_target_io *tio;
sector_t pos;
/*
@@ -1930,20 +1945,15 @@
clone = dm_start_request(md, rq);
- spin_unlock(q->queue_lock);
- if (map_request(ti, clone, md))
- goto requeued;
-
+ tio = rq->special;
+ /* Establish tio->ti before queuing work (map_tio_request) */
+ tio->ti = ti;
+ queue_kthread_work(&md->kworker, &tio->work);
BUG_ON(!irqs_disabled());
- spin_lock(q->queue_lock);
}
goto out;
-requeued:
- BUG_ON(!irqs_disabled());
- spin_lock(q->queue_lock);
-
delay_and_out:
blk_delay_queue(q, HZ / 10);
out:
@@ -2129,6 +2139,7 @@
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;
@@ -2189,6 +2200,9 @@
unlock_fs(md);
bdput(md->bdev);
destroy_workqueue(md->wq);
+
+ if (md->kworker_task)
+ kthread_stop(md->kworker_task);
if (md->io_pool)
mempool_destroy(md->io_pool);
if (md->rq_pool)
@@ -2484,6 +2498,11 @@
blk_queue_prep_rq(md->queue, dm_prep_fn);
blk_queue_lld_busy(md->queue, dm_lld_busy);
+ /* Also initialize the request-based DM worker thread */
+ init_kthread_worker(&md->kworker);
+ md->kworker_task = kthread_run(kthread_worker_fn, &md->kworker,
+ "kdmwork-%s", dm_device_name(md));
+
elv_register_queue(md->queue);
return 1;
@@ -2574,6 +2593,9 @@
set_bit(DMF_FREEING, &md->flags);
spin_unlock(&_minor_lock);
+ if (dm_request_based(md))
+ flush_kthread_worker(&md->kworker);
+
if (!dm_suspended_md(md)) {
dm_table_presuspend_targets(map);
dm_table_postsuspend_targets(map);
@@ -2817,8 +2839,10 @@
* 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)) {
stop_queue(md->queue);
+ flush_kthread_worker(&md->kworker);
+ }
flush_workqueue(md->wq);