dm: allow remove to be deferred

This patch allows the removal of an open device to be deferred until
it is closed.  (Previously such a removal attempt would fail.)

The deferred remove functionality is enabled by setting the flag
DM_DEFERRED_REMOVE in the ioctl structure on DM_DEV_REMOVE or
DM_REMOVE_ALL ioctl.

On return from DM_DEV_REMOVE, the flag DM_DEFERRED_REMOVE indicates if
the device was removed immediately or flagged to be removed on close -
if the flag is clear, the device was removed.

On return from DM_DEV_STATUS and other ioctls, the flag
DM_DEFERRED_REMOVE is set if the device is scheduled to be removed on
closure.

A device that is scheduled to be deleted can be revived using the
message "@cancel_deferred_remove". This message clears the
DMF_DEFERRED_REMOVE flag so that the device won't be deleted on close.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

3 files changed, 86 insertions, 10 deletions

diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index afe08146f73..51521429fb5 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -57,7 +57,7 @@ struct vers_iter {
 static struct list_head _name_buckets[NUM_BUCKETS];
 static struct list_head _uuid_buckets[NUM_BUCKETS];
 
-static void dm_hash_remove_all(int keep_open_devices);
+static void dm_hash_remove_all(bool keep_open_devices, bool mark_deferred, bool only_deferred);
 
 /*
  * Guards access to both hash tables.
@@ -86,7 +86,7 @@ static int dm_hash_init(void)
 
 static void dm_hash_exit(void)
 {
-	dm_hash_remove_all(0);
+	dm_hash_remove_all(false, false, false);
 }
 
 /*-----------------------------------------------------------------
@@ -276,7 +276,7 @@ static struct dm_table *__hash_remove(struct hash_cell *hc)
 	return table;
 }
 
-static void dm_hash_remove_all(int keep_open_devices)
+static void dm_hash_remove_all(bool keep_open_devices, bool mark_deferred, bool only_deferred)
 {
 	int i, dev_skipped;
 	struct hash_cell *hc;
@@ -293,7 +293,8 @@ retry:
 			md = hc->md;
 			dm_get(md);
 
-			if (keep_open_devices && dm_lock_for_deletion(md)) {
+			if (keep_open_devices &&
+			    dm_lock_for_deletion(md, mark_deferred, only_deferred)) {
 				dm_put(md);
 				dev_skipped++;
 				continue;
@@ -450,6 +451,11 @@ static struct mapped_device *dm_hash_rename(struct dm_ioctl *param,
 	return md;
 }
 
+void dm_deferred_remove(void)
+{
+	dm_hash_remove_all(true, false, true);
+}
+
 /*-----------------------------------------------------------------
  * Implementation of the ioctl commands
  *---------------------------------------------------------------*/
@@ -461,7 +467,7 @@ typedef int (*ioctl_fn)(struct dm_ioctl *param, size_t param_size);
 
 static int remove_all(struct dm_ioctl *param, size_t param_size)
 {
-	dm_hash_remove_all(1);
+	dm_hash_remove_all(true, !!(param->flags & DM_DEFERRED_REMOVE), false);
 	param->data_size = 0;
 	return 0;
 }
@@ -683,6 +689,9 @@ static void __dev_status(struct mapped_device *md, struct dm_ioctl *param)
 	if (dm_suspended_md(md))
 		param->flags |= DM_SUSPEND_FLAG;
 
+	if (dm_test_deferred_remove_flag(md))
+		param->flags |= DM_DEFERRED_REMOVE;
+
 	param->dev = huge_encode_dev(disk_devt(disk));
 
 	/*
@@ -832,8 +841,13 @@ static int dev_remove(struct dm_ioctl *param, size_t param_size)
 	/*
 	 * Ensure the device is not open and nothing further can open it.
 	 */
-	r = dm_lock_for_deletion(md);
+	r = dm_lock_for_deletion(md, !!(param->flags & DM_DEFERRED_REMOVE), false);
 	if (r) {
+		if (r == -EBUSY && param->flags & DM_DEFERRED_REMOVE) {
+			up_write(&_hash_lock);
+			dm_put(md);
+			return 0;
+		}
 		DMDEBUG_LIMIT("unable to remove open device %s", hc->name);
 		up_write(&_hash_lock);
 		dm_put(md);
@@ -848,6 +862,8 @@ static int dev_remove(struct dm_ioctl *param, size_t param_size)
 		dm_table_destroy(t);
 	}
 
+	param->flags &= ~DM_DEFERRED_REMOVE;
+
 	if (!dm_kobject_uevent(md, KOBJ_REMOVE, param->event_nr))
 		param->flags |= DM_UEVENT_GENERATED_FLAG;
 
@@ -1469,6 +1485,14 @@ static int message_for_md(struct mapped_device *md, unsigned argc, char **argv,
 	if (**argv != '@')
 		return 2; /* no '@' prefix, deliver to target */
 
+	if (!strcasecmp(argv[0], "@cancel_deferred_remove")) {
+		if (argc != 1) {
+			DMERR("Invalid arguments for @cancel_deferred_remove");
+			return -EINVAL;
+		}
+		return dm_cancel_deferred_remove(md);
+	}
+
 	r = dm_stats_message(md, argc, argv, result, maxlen);
 	if (r < 2)
 		return r;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index b3e26c7d141..0704c523a76 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -49,6 +49,11 @@ static unsigned int _major = 0;
 static DEFINE_IDR(_minor_idr);
 
 static DEFINE_SPINLOCK(_minor_lock);
+
+static void do_deferred_remove(struct work_struct *w);
+
+static DECLARE_WORK(deferred_remove_work, do_deferred_remove);
+
 /*
  * For bio-based dm.
  * One of these is allocated per bio.
@@ -116,6 +121,7 @@ EXPORT_SYMBOL_GPL(dm_get_rq_mapinfo);
 #define DMF_DELETING 4
 #define DMF_NOFLUSH_SUSPENDING 5
 #define DMF_MERGE_IS_OPTIONAL 6
+#define DMF_DEFERRED_REMOVE 7
 
 /*
  * A dummy definition to make RCU happy.
@@ -299,6 +305,8 @@ out_free_io_cache:
 
 static void local_exit(void)
 {
+	flush_scheduled_work();
+
 	kmem_cache_destroy(_rq_tio_cache);
 	kmem_cache_destroy(_io_cache);
 	unregister_blkdev(_major, _name);
@@ -404,7 +412,10 @@ static void dm_blk_close(struct gendisk *disk, fmode_t mode)
 
 	spin_lock(&_minor_lock);
 
-	atomic_dec(&md->open_count);
+	if (atomic_dec_and_test(&md->open_count) &&
+	    (test_bit(DMF_DEFERRED_REMOVE, &md->flags)))
+		schedule_work(&deferred_remove_work);
+
 	dm_put(md);
 
 	spin_unlock(&_minor_lock);
@@ -418,14 +429,18 @@ int dm_open_count(struct mapped_device *md)
 /*
  * Guarantees nothing is using the device before it's deleted.
  */
-int dm_lock_for_deletion(struct mapped_device *md)
+int dm_lock_for_deletion(struct mapped_device *md, bool mark_deferred, bool only_deferred)
 {
 	int r = 0;
 
 	spin_lock(&_minor_lock);
 
-	if (dm_open_count(md))
+	if (dm_open_count(md)) {
 		r = -EBUSY;
+		if (mark_deferred)
+			set_bit(DMF_DEFERRED_REMOVE, &md->flags);
+	} else if (only_deferred && !test_bit(DMF_DEFERRED_REMOVE, &md->flags))
+		r = -EEXIST;
 	else
 		set_bit(DMF_DELETING, &md->flags);
 
@@ -434,6 +449,27 @@ int dm_lock_for_deletion(struct mapped_device *md)
 	return r;
 }
 
+int dm_cancel_deferred_remove(struct mapped_device *md)
+{
+	int r = 0;
+
+	spin_lock(&_minor_lock);
+
+	if (test_bit(DMF_DELETING, &md->flags))
+		r = -EBUSY;
+	else
+		clear_bit(DMF_DEFERRED_REMOVE, &md->flags);
+
+	spin_unlock(&_minor_lock);
+
+	return r;
+}
+
+static void do_deferred_remove(struct work_struct *w)
+{
+	dm_deferred_remove();
+}
+
 sector_t dm_get_size(struct mapped_device *md)
 {
 	return get_capacity(md->disk);
@@ -2894,6 +2930,11 @@ int dm_suspended_md(struct mapped_device *md)
 	return test_bit(DMF_SUSPENDED, &md->flags);
 }
 
+int dm_test_deferred_remove_flag(struct mapped_device *md)
+{
+	return test_bit(DMF_DEFERRED_REMOVE, &md->flags);
+}
+
 int dm_suspended(struct dm_target *ti)
 {
 	return dm_suspended_md(dm_table_get_md(ti->table));
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 1d1ad7b7e52..c57ba550f69 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -129,6 +129,16 @@ int dm_deleting_md(struct mapped_device *md);
 int dm_suspended_md(struct mapped_device *md);
 
 /*
+ * Test if the device is scheduled for deferred remove.
+ */
+int dm_test_deferred_remove_flag(struct mapped_device *md);
+
+/*
+ * Try to remove devices marked for deferred removal.
+ */
+void dm_deferred_remove(void);
+
+/*
  * The device-mapper can be driven through one of two interfaces;
  * ioctl or filesystem, depending which patch you have applied.
  */
@@ -158,7 +168,8 @@ void dm_stripe_exit(void);
 void dm_destroy(struct mapped_device *md);
 void dm_destroy_immediate(struct mapped_device *md);
 int dm_open_count(struct mapped_device *md);
-int dm_lock_for_deletion(struct mapped_device *md);
+int dm_lock_for_deletion(struct mapped_device *md, bool mark_deferred, bool only_deferred);
+int dm_cancel_deferred_remove(struct mapped_device *md);
 int dm_request_based(struct mapped_device *md);
 sector_t dm_get_size(struct mapped_device *md);
 struct dm_stats *dm_get_stats(struct mapped_device *md);