Merge branch 'quilt/device-mapper'

11 files changed, 140 insertions, 70 deletions

diff --git a/Documentation/device-mapper/snapshot.txt b/Documentation/device-mapper/snapshot.txt
index e3a77b215135..0d5bc46dc167 100644
--- a/Documentation/device-mapper/snapshot.txt
+++ b/Documentation/device-mapper/snapshot.txt
@@ -122,3 +122,47 @@ volumeGroup-base: 0 2097152 snapshot-merge 254:11 254:12 P 16
 brw-------  1 root root 254, 11 29 ago 18:15 /dev/mapper/volumeGroup-base-real
 brw-------  1 root root 254, 12 29 ago 18:16 /dev/mapper/volumeGroup-base-cow
 brw-------  1 root root 254, 10 29 ago 18:16 /dev/mapper/volumeGroup-base
+
+
+How to determine when a merging is complete
+===========================================
+The snapshot-merge and snapshot status lines end with:
+  <sectors_allocated>/<total_sectors> <metadata_sectors>
+
+Both <sectors_allocated> and <total_sectors> include both data and metadata.
+During merging, the number of sectors allocated gets smaller and
+smaller.  Merging has finished when the number of sectors holding data
+is zero, in other words <sectors_allocated> == <metadata_sectors>.
+
+Here is a practical example (using a hybrid of lvm and dmsetup commands):
+
+# lvs
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup owi-a- 4.00g
+  snap    volumeGroup swi-a- 1.00g base  18.97
+
+# dmsetup status volumeGroup-snap
+0 8388608 snapshot 397896/2097152 1560
+                                  ^^^^ metadata sectors
+
+# lvconvert --merge -b volumeGroup/snap
+  Merging of volume snap started.
+
+# lvs volumeGroup/snap
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup Owi-a- 4.00g          17.23
+
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 281688/2097152 1104
+
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 180480/2097152 712
+
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 16/2097152 16
+
+Merging has finished.
+
+# lvs
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup owi-a- 4.00g
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 1d669322b27c..e3cf5686d0aa 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -897,16 +897,17 @@ static int do_resume(struct dm_ioctl *param)
 			set_disk_ro(dm_disk(md), 1);
 	}
 
-	if (dm_suspended_md(md))
+	if (dm_suspended_md(md)) {
 		r = dm_resume(md);
+		if (!r)
+			dm_kobject_uevent(md, KOBJ_CHANGE, param->event_nr);
+	}
 
 	if (old_map)
 		dm_table_destroy(old_map);
 
-	if (!r) {
-		dm_kobject_uevent(md, KOBJ_CHANGE, param->event_nr);
+	if (!r)
 		r = __dev_status(md, param);
-	}
 
 	dm_put(md);
 	return r;
diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c
index 54abf9e303b7..f1c8cae70b4b 100644
--- a/drivers/md/dm-log-userspace-transfer.c
+++ b/drivers/md/dm-log-userspace-transfer.c
@@ -172,11 +172,15 @@ int dm_consult_userspace(const char *uuid, uint64_t luid, int request_type,
 {
 	int r = 0;
 	size_t dummy = 0;
-	int overhead_size =
-		sizeof(struct dm_ulog_request *) + sizeof(struct cn_msg);
+	int overhead_size = sizeof(struct dm_ulog_request) + sizeof(struct cn_msg);
 	struct dm_ulog_request *tfr = prealloced_ulog_tfr;
 	struct receiving_pkg pkg;
 
+	/*
+	 * Given the space needed to hold the 'struct cn_msg' and
+	 * 'struct dm_ulog_request' - do we have enough payload
+	 * space remaining?
+	 */
 	if (data_size > (DM_ULOG_PREALLOCED_SIZE - overhead_size)) {
 		DMINFO("Size of tfr exceeds preallocated size");
 		return -EINVAL;
@@ -191,7 +195,7 @@ resend:
 	 */
 	mutex_lock(&dm_ulog_lock);
 
-	memset(tfr, 0, DM_ULOG_PREALLOCED_SIZE - overhead_size);
+	memset(tfr, 0, DM_ULOG_PREALLOCED_SIZE - sizeof(struct cn_msg));
 	memcpy(tfr->uuid, uuid, DM_UUID_LEN);
 	tfr->luid = luid;
 	tfr->seq = dm_ulog_seq++;
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index e81345a1d08f..c1335487cc72 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -69,6 +69,7 @@ struct multipath {
 	struct list_head priority_groups;
 	unsigned pg_init_required;	/* pg_init needs calling? */
 	unsigned pg_init_in_progress;	/* Only one pg_init allowed at once */
+	wait_queue_head_t pg_init_wait;	/* Wait for pg_init completion */
 
 	unsigned nr_valid_paths;	/* Total number of usable paths */
 	struct pgpath *current_pgpath;
@@ -95,8 +96,6 @@ struct multipath {
 	mempool_t *mpio_pool;
 
 	struct mutex work_mutex;
-
-	unsigned suspended;	/* Don't create new I/O internally when set. */
 };
 
 /*
@@ -202,6 +201,7 @@ static struct multipath *alloc_multipath(struct dm_target *ti)
 		m->queue_io = 1;
 		INIT_WORK(&m->process_queued_ios, process_queued_ios);
 		INIT_WORK(&m->trigger_event, trigger_event);
+		init_waitqueue_head(&m->pg_init_wait);
 		mutex_init(&m->work_mutex);
 		m->mpio_pool = mempool_create_slab_pool(MIN_IOS, _mpio_cache);
 		if (!m->mpio_pool) {
@@ -235,6 +235,21 @@ static void free_multipath(struct multipath *m)
  * Path selection
  *-----------------------------------------------*/
 
+static void __pg_init_all_paths(struct multipath *m)
+{
+	struct pgpath *pgpath;
+
+	m->pg_init_count++;
+	m->pg_init_required = 0;
+	list_for_each_entry(pgpath, &m->current_pg->pgpaths, list) {
+		/* Skip failed paths */
+		if (!pgpath->is_active)
+			continue;
+		if (queue_work(kmpath_handlerd, &pgpath->activate_path))
+			m->pg_init_in_progress++;
+	}
+}
+
 static void __switch_pg(struct multipath *m, struct pgpath *pgpath)
 {
 	m->current_pg = pgpath->pg;
@@ -439,7 +454,7 @@ static void process_queued_ios(struct work_struct *work)
 {
 	struct multipath *m =
 		container_of(work, struct multipath, process_queued_ios);
-	struct pgpath *pgpath = NULL, *tmp;
+	struct pgpath *pgpath = NULL;
 	unsigned must_queue = 1;
 	unsigned long flags;
 
@@ -457,14 +472,9 @@ static void process_queued_ios(struct work_struct *work)
 	    (!pgpath && !m->queue_if_no_path))
 		must_queue = 0;
 
-	if (m->pg_init_required && !m->pg_init_in_progress && pgpath) {
-		m->pg_init_count++;
-		m->pg_init_required = 0;
-		list_for_each_entry(tmp, &pgpath->pg->pgpaths, list) {
-			if (queue_work(kmpath_handlerd, &tmp->activate_path))
-				m->pg_init_in_progress++;
-		}
-	}
+	if (m->pg_init_required && !m->pg_init_in_progress && pgpath)
+		__pg_init_all_paths(m);
+
 out:
 	spin_unlock_irqrestore(&m->lock, flags);
 	if (!must_queue)
@@ -890,9 +900,34 @@ static int multipath_ctr(struct dm_target *ti, unsigned int argc,
 	return r;
 }
 
-static void flush_multipath_work(void)
+static void multipath_wait_for_pg_init_completion(struct multipath *m)
+{
+	DECLARE_WAITQUEUE(wait, current);
+	unsigned long flags;
+
+	add_wait_queue(&m->pg_init_wait, &wait);
+
+	while (1) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+
+		spin_lock_irqsave(&m->lock, flags);
+		if (!m->pg_init_in_progress) {
+			spin_unlock_irqrestore(&m->lock, flags);
+			break;
+		}
+		spin_unlock_irqrestore(&m->lock, flags);
+
+		io_schedule();
+	}
+	set_current_state(TASK_RUNNING);
+
+	remove_wait_queue(&m->pg_init_wait, &wait);
+}
+
+static void flush_multipath_work(struct multipath *m)
 {
 	flush_workqueue(kmpath_handlerd);
+	multipath_wait_for_pg_init_completion(m);
 	flush_workqueue(kmultipathd);
 	flush_scheduled_work();
 }
@@ -901,7 +936,7 @@ static void multipath_dtr(struct dm_target *ti)
 {
 	struct multipath *m = ti->private;
 
-	flush_multipath_work();
+	flush_multipath_work(m);
 	free_multipath(m);
 }
 
@@ -1128,8 +1163,7 @@ static int pg_init_limit_reached(struct multipath *m, struct pgpath *pgpath)
 
 static void pg_init_done(void *data, int errors)
 {
-	struct dm_path *path = data;
-	struct pgpath *pgpath = path_to_pgpath(path);
+	struct pgpath *pgpath = data;
 	struct priority_group *pg = pgpath->pg;
 	struct multipath *m = pg->m;
 	unsigned long flags;
@@ -1143,8 +1177,8 @@ static void pg_init_done(void *data, int errors)
 			errors = 0;
 			break;
 		}
-		DMERR("Cannot failover device because scsi_dh_%s was not "
-		      "loaded.", m->hw_handler_name);
+		DMERR("Could not failover the device: Handler scsi_dh_%s "
+		      "Error %d.", m->hw_handler_name, errors);
 		/*
 		 * Fail path for now, so we do not ping pong
 		 */
@@ -1181,14 +1215,24 @@ static void pg_init_done(void *data, int errors)
 			m->current_pgpath = NULL;
 			m->current_pg = NULL;
 		}
-	} else if (!m->pg_init_required) {
-		m->queue_io = 0;
+	} else if (!m->pg_init_required)
 		pg->bypassed = 0;
-	}
 
-	m->pg_init_in_progress--;
-	if (!m->pg_init_in_progress)
-		queue_work(kmultipathd, &m->process_queued_ios);
+	if (--m->pg_init_in_progress)
+		/* Activations of other paths are still on going */
+		goto out;
+
+	if (!m->pg_init_required)
+		m->queue_io = 0;
+
+	queue_work(kmultipathd, &m->process_queued_ios);
+
+	/*
+	 * Wake up any thread waiting to suspend.
+	 */
+	wake_up(&m->pg_init_wait);
+
+out:
 	spin_unlock_irqrestore(&m->lock, flags);
 }
 
@@ -1198,7 +1242,7 @@ static void activate_path(struct work_struct *work)
 		container_of(work, struct pgpath, activate_path);
 
 	scsi_dh_activate(bdev_get_queue(pgpath->path.dev->bdev),
-				pg_init_done, &pgpath->path);
+				pg_init_done, pgpath);
 }
 
 /*
@@ -1276,8 +1320,7 @@ static void multipath_postsuspend(struct dm_target *ti)
 	struct multipath *m = ti->private;
 
 	mutex_lock(&m->work_mutex);
-	m->suspended = 1;
-	flush_multipath_work();
+	flush_multipath_work(m);
 	mutex_unlock(&m->work_mutex);
 }
 
@@ -1289,10 +1332,6 @@ static void multipath_resume(struct dm_target *ti)
 	struct multipath *m = (struct multipath *) ti->private;
 	unsigned long flags;
 
-	mutex_lock(&m->work_mutex);
-	m->suspended = 0;
-	mutex_unlock(&m->work_mutex);
-
 	spin_lock_irqsave(&m->lock, flags);
 	m->queue_if_no_path = m->saved_queue_if_no_path;
 	spin_unlock_irqrestore(&m->lock, flags);
@@ -1428,11 +1467,6 @@ static int multipath_message(struct dm_target *ti, unsigned argc, char **argv)
 
 	mutex_lock(&m->work_mutex);
 
-	if (m->suspended) {
-		r = -EBUSY;
-		goto out;
-	}
-
 	if (dm_suspended(ti)) {
 		r = -EBUSY;
 		goto out;
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index ad779bd13aec..de26fde4098f 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -724,7 +724,7 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
 	/*
 	 * Dispatch io.
 	 */
-	if (unlikely(ms->log_failure)) {
+	if (unlikely(ms->log_failure) && errors_handled(ms)) {
 		spin_lock_irq(&ms->lock);
 		bio_list_merge(&ms->failures, &sync);
 		spin_unlock_irq(&ms->lock);
@@ -737,9 +737,12 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
 		dm_rh_delay(ms->rh, bio);
 
 	while ((bio = bio_list_pop(&nosync))) {
-		if (unlikely(ms->leg_failure) && errors_handled(ms))
-			hold_bio(ms, bio);
-		else {
+		if (unlikely(ms->leg_failure) && errors_handled(ms)) {
+			spin_lock_irq(&ms->lock);
+			bio_list_add(&ms->failures, bio);
+			spin_unlock_irq(&ms->lock);
+			wakeup_mirrord(ms);
+		} else {
 			map_bio(get_default_mirror(ms), bio);
 			generic_make_request(bio);
 		}
diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c
index 5f19ceb6fe91..168bd38f5006 100644
--- a/drivers/md/dm-region-hash.c
+++ b/drivers/md/dm-region-hash.c
@@ -660,10 +660,9 @@ void dm_rh_recovery_end(struct dm_region *reg, int success)
 	spin_lock_irq(&rh->region_lock);
 	if (success)
 		list_add(&reg->list, &reg->rh->recovered_regions);
-	else {
-		reg->state = DM_RH_NOSYNC;
+	else
 		list_add(&reg->list, &reg->rh->failed_recovered_regions);
-	}
+
 	spin_unlock_irq(&rh->region_lock);
 
 	rh->wakeup_workers(rh->context);
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index 7d08879689ac..c097d8a4823d 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -254,7 +254,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw,
 	 * Issue the synchronous I/O from a different thread
 	 * to avoid generic_make_request recursion.
 	 */
-	INIT_WORK(&req.work, do_metadata);
+	INIT_WORK_ON_STACK(&req.work, do_metadata);
 	queue_work(ps->metadata_wq, &req.work);
 	flush_workqueue(ps->metadata_wq);
 
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index e0efc1adcaff..bd58703ee8f6 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -110,7 +110,7 @@ static int stripe_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	}
 
 	stripes = simple_strtoul(argv[0], &end, 10);
-	if (*end) {
+	if (!stripes || *end) {
 		ti->error = "Invalid stripe count";
 		return -EINVAL;
 	}
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 4b22feb01a0c..7d70cca585ac 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1231,8 +1231,6 @@ void dm_table_unplug_all(struct dm_table *t)
 
 struct mapped_device *dm_table_get_md(struct dm_table *t)
 {
-	dm_get(t->md);
-
 	return t->md;
 }
 
diff --git a/drivers/md/dm-uevent.c b/drivers/md/dm-uevent.c
index c7c555a8c7b2..6b1e3b61b25e 100644
--- a/drivers/md/dm-uevent.c
+++ b/drivers/md/dm-uevent.c
@@ -187,7 +187,7 @@ void dm_path_uevent(enum dm_uevent_type event_type, struct dm_target *ti,
 
 	if (event_type >= ARRAY_SIZE(_dm_uevent_type_names)) {
 		DMERR("%s: Invalid event_type %d", __func__, event_type);
-		goto out;
+		return;
 	}
 
 	event = dm_build_path_uevent(md, ti,
@@ -195,12 +195,9 @@ void dm_path_uevent(enum dm_uevent_type event_type, struct dm_target *ti,
 				     _dm_uevent_type_names[event_type].name,
 				     path, nr_valid_paths);
 	if (IS_ERR(event))
-		goto out;
+		return;
 
 	dm_uevent_add(md, &event->elist);
-
-out:
-	dm_put(md);
 }
 EXPORT_SYMBOL_GPL(dm_path_uevent);
 
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 3167480b532c..b03fa1ce67f8 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2686,23 +2686,13 @@ int dm_suspended_md(struct mapped_device *md)
 
 int dm_suspended(struct dm_target *ti)
 {
-	struct mapped_device *md = dm_table_get_md(ti->table);
-	int r = dm_suspended_md(md);
-
-	dm_put(md);
-
-	return r;
+	return dm_suspended_md(dm_table_get_md(ti->table));
 }
 EXPORT_SYMBOL_GPL(dm_suspended);
 
 int dm_noflush_suspending(struct dm_target *ti)
 {
-	struct mapped_device *md = dm_table_get_md(ti->table);
-	int r = __noflush_suspending(md);
-
-	dm_put(md);
-
-	return r;
+	return __noflush_suspending(dm_table_get_md(ti->table));
 }
 EXPORT_SYMBOL_GPL(dm_noflush_suspending);