dm mpath: requeue I/O during pg_init

When pg_init is running no I/O can be submitted to the underlying
devices, as the path priority etc might change.  When using queue_io for
this, requests will be piling up within multipath as the block I/O
scheduler just sees a _very fast_ device.  All of this queued I/O has to
be resubmitted from within multipathing once pg_init is done.

This approach has the problem that it's virtually impossible to
abort I/O when pg_init is running, and we're adding heavy load
to the devices after pg_init since all of the queued I/O needs to be
resubmitted _before_ any requests can be pulled off of the request queue
and normal operation continues.

This patch will requeue the I/O that triggers the pg_init call, and
return 'busy' when pg_init is in progress.  With these changes the block
I/O scheduler will stop submitting I/O during pg_init, resulting in a
quicker path switch and less I/O pressure (and memory consumption) after
pg_init.
Signed-off-by: Hannes Reinecke <hare@suse.de>
[patch header edited for clarity and typos by Mike Snitzer]
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

drivers/md/dm-mpath.c

@@ -391,13 +391,16 @@ static int map_io(struct multipath *m, struct request *clone,
 	if (was_queued)
 		m->queue_size--;
 
-	if ((pgpath && m->queue_io) ||
-	    (!pgpath && m->queue_if_no_path)) {
+	if (m->pg_init_required) {
+		if (!m->pg_init_in_progress)
+			queue_work(kmultipathd, &m->process_queued_ios);
+		r = DM_MAPIO_REQUEUE;
+	} else if ((pgpath && m->queue_io) ||
+		   (!pgpath && m->queue_if_no_path)) {
 		/* Queue for the daemon to resubmit */
 		list_add_tail(&clone->queuelist, &m->queued_ios);
 		m->queue_size++;
-		if ((m->pg_init_required && !m->pg_init_in_progress) ||
-		    !m->queue_io)
+		if (!m->queue_io)
 			queue_work(kmultipathd, &m->process_queued_ios);
 		pgpath = NULL;
 		r = DM_MAPIO_SUBMITTED;
@@ -1677,6 +1680,11 @@ static int multipath_busy(struct dm_target *ti)
 
 	spin_lock_irqsave(&m->lock, flags);
 
+	/* pg_init in progress, requeue until done */
+	if (m->pg_init_in_progress) {
+		busy = 1;
+		goto out;
+	}
 	/* Guess which priority_group will be used at next mapping time */
 	if (unlikely(!m->current_pgpath && m->next_pg))
 		pg = m->next_pg;