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>

2 files changed, 46 insertions, 18 deletions

diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 7b6b0f0f831a..2552b88f8953 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -384,12 +384,11 @@ static int multipath_map(struct dm_target *ti, struct request *clone,
         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 ||
@@ -411,21 +410,26 @@ static int multipath_map(struct dm_target *ti, struct request *clone,
                 /* ENOMEM, requeue */
                 goto out_unlock;
 
+        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;
-        mpio = map_context->ptr;
-        mpio->pgpath = pgpath;
-        mpio->nr_bytes = nr_bytes;
+
+        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;
 }
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 9a857e337902..f0e34070c11d 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 dm_rq_target_io {
         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 mapped_device {
         struct bio flush_bio;
 
         struct dm_stats stats;
+
+        struct kthread_worker kworker;
+        struct task_struct *kworker_task;
 };
 
 /*
@@ -1773,6 +1778,8 @@ static struct request *__clone_rq(struct request *rq, struct mapped_device *md,
         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 @@ static struct request *clone_rq(struct request *rq, struct mapped_device *md,
         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 @@ static int map_request(struct dm_target *ti, struct request *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:
@@ -1864,6 +1871,13 @@ static int map_request(struct dm_target *ti, struct request *clone,
         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 @@ static void dm_request_fn(struct request_queue *q)
         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 @@ static void dm_request_fn(struct request_queue *q)
 
                 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 @@ 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;
@@ -2189,6 +2200,9 @@ static void free_dev(struct mapped_device *md)
         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 @@ static int dm_init_request_based_queue(struct mapped_device *md)
         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));