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 <[e-mail]>
Signed-off-by: Mike Snitzer <[e-mail]>

drivers/md/dm-mpath.c

···
 	struct multipath *m = (struct multipath *) ti->private;
 	int r = DM_MAPIO_REQUEUE;
 	size_t nr_bytes = blk_rq_bytes(clone);
-	unsigned long flags;
 	struct pgpath *pgpath;
 	struct block_device *bdev;
 	struct dm_mpath_io *mpio;
 
-	spin_lock_irqsave(&m->lock, flags);
+	spin_lock_irq(&m->lock);
 
 	/* Do we need to select a new pgpath? */
 	if (!m->current_pgpath ||
···
 		/* ENOMEM, requeue */
 		goto out_unlock;
 
-	bdev = pgpath->path.dev->bdev;
-	clone->q = bdev_get_queue(bdev);
-	clone->rq_disk = bdev->bd_disk;
-	clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
 	mpio = map_context->ptr;
 	mpio->pgpath = pgpath;
 	mpio->nr_bytes = nr_bytes;
+
+	bdev = pgpath->path.dev->bdev;
+
+	clone->q = bdev_get_queue(bdev);
+	clone->rq_disk = bdev->bd_disk;
+	clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
+
+	spin_unlock_irq(&m->lock);
+
 	if (pgpath->pg->ps.type->start_io)
 		pgpath->pg->ps.type->start_io(&pgpath->pg->ps,
 					      &pgpath->path,
 					      nr_bytes);
-	r = DM_MAPIO_REMAPPED;
+	return DM_MAPIO_REMAPPED;
 
 out_unlock:
-	spin_unlock_irqrestore(&m->lock, flags);
+	spin_unlock_irq(&m->lock);
 
 	return r;
 }

drivers/md/dm.c

···
 #include <linux/hdreg.h>
 #include <linux/delay.h>
 #include <linux/wait.h>
+#include <linux/kthread.h>
 
 #include <trace/events/block.h>
 
···
 	struct mapped_device *md;
 	struct dm_target *ti;
 	struct request *orig, *clone;
+	struct kthread_work work;
 	int error;
 	union map_info info;
 };
···
 	struct bio flush_bio;
 
 	struct dm_stats stats;
+
+	struct kthread_worker kworker;
+	struct task_struct *kworker_task;
 };
 
 /*
···
 	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)
 {
···
 	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) {
···
 	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:
···
 	}
 
 	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 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;
 
 	/*
···
 
 		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);
···
 	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;
···
 	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)
···
 	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;
···
 	idr_replace(&_minor_idr, MINOR_ALLOCED, MINOR(disk_devt(dm_disk(md))));
 	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);
···
 	 * 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);