dm: optimize use SRCU and RCU

This patch removes "io_lock" and "map_lock" in struct mapped_device and
"holders" in struct dm_table and replaces these mechanisms with
sleepable-rcu.

Previously, the code would call "dm_get_live_table" and "dm_table_put" to
get and release table. Now, the code is changed to call "dm_get_live_table"
and "dm_put_live_table". dm_get_live_table locks sleepable-rcu and
dm_put_live_table unlocks it.

dm_get_live_table_fast/dm_put_live_table_fast can be used instead of
dm_get_live_table/dm_put_live_table. These *_fast functions use
non-sleepable RCU, so the caller must not block between them.

If the code changes active or inactive dm table, it must call
dm_sync_table before destroying the old table.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>

drivers/md/dm-ioctl.c

@@ -36,6 +36,14 @@ struct hash_cell {
 	struct dm_table *new_map;
 };
 
+/*
+ * A dummy definition to make RCU happy.
+ * struct dm_table should never be dereferenced in this file.
+ */
+struct dm_table {
+	int undefined__;
+};
+
 struct vers_iter {
     size_t param_size;
     struct dm_target_versions *vers, *old_vers;
@@ -242,9 +250,10 @@ static int dm_hash_insert(const char *name, const char *uuid, struct mapped_devi
 	return -EBUSY;
 }
 
-static void __hash_remove(struct hash_cell *hc)
+static struct dm_table *__hash_remove(struct hash_cell *hc)
 {
 	struct dm_table *table;
+	int srcu_idx;
 
 	/* remove from the dev hash */
 	list_del(&hc->uuid_list);
@@ -253,16 +262,18 @@ static void __hash_remove(struct hash_cell *hc)
 	dm_set_mdptr(hc->md, NULL);
 	mutex_unlock(&dm_hash_cells_mutex);
 
-	table = dm_get_live_table(hc->md);
-	if (table) {
+	table = dm_get_live_table(hc->md, &srcu_idx);
+	if (table)
 		dm_table_event(table);
-		dm_table_put(table);
-	}
+	dm_put_live_table(hc->md, srcu_idx);
 
+	table = NULL;
 	if (hc->new_map)
-		dm_table_destroy(hc->new_map);
+		table = hc->new_map;
 	dm_put(hc->md);
 	free_cell(hc);
+
+	return table;
 }
 
 static void dm_hash_remove_all(int keep_open_devices)
@@ -270,6 +281,7 @@ static void dm_hash_remove_all(int keep_open_devices)
 	int i, dev_skipped;
 	struct hash_cell *hc;
 	struct mapped_device *md;
+	struct dm_table *t;
 
 retry:
 	dev_skipped = 0;
@@ -287,10 +299,14 @@ static void dm_hash_remove_all(int keep_open_devices)
 				continue;
 			}
 
-			__hash_remove(hc);
+			t = __hash_remove(hc);
 
 			up_write(&_hash_lock);
 
+			if (t) {
+				dm_sync_table(md);
+				dm_table_destroy(t);
+			}
 			dm_put(md);
 			if (likely(keep_open_devices))
 				dm_destroy(md);
@@ -356,6 +372,7 @@ static struct mapped_device *dm_hash_rename(struct dm_ioctl *param,
 	struct dm_table *table;
 	struct mapped_device *md;
 	unsigned change_uuid = (param->flags & DM_UUID_FLAG) ? 1 : 0;
+	int srcu_idx;
 
 	/*
 	 * duplicate new.
@@ -418,11 +435,10 @@ static struct mapped_device *dm_hash_rename(struct dm_ioctl *param,
 	/*
 	 * Wake up any dm event waiters.
 	 */
-	table = dm_get_live_table(hc->md);
-	if (table) {
+	table = dm_get_live_table(hc->md, &srcu_idx);
+	if (table)
 		dm_table_event(table);
-		dm_table_put(table);
-	}
+	dm_put_live_table(hc->md, srcu_idx);
 
 	if (!dm_kobject_uevent(hc->md, KOBJ_CHANGE, param->event_nr))
 		param->flags |= DM_UEVENT_GENERATED_FLAG;
@@ -620,11 +636,14 @@ static int check_name(const char *name)
  * _hash_lock without first calling dm_table_put, because dm_table_destroy
  * waits for this dm_table_put and could be called under this lock.
  */
-static struct dm_table *dm_get_inactive_table(struct mapped_device *md)
+static struct dm_table *dm_get_inactive_table(struct mapped_device *md, int *srcu_idx)
 {
 	struct hash_cell *hc;
 	struct dm_table *table = NULL;
 
+	/* increment rcu count, we don't care about the table pointer */
+	dm_get_live_table(md, srcu_idx);
+
 	down_read(&_hash_lock);
 	hc = dm_get_mdptr(md);
 	if (!hc || hc->md != md) {
@@ -633,8 +652,6 @@ static struct dm_table *dm_get_inactive_table(struct mapped_device *md)
 	}
 
 	table = hc->new_map;
-	if (table)
-		dm_table_get(table);
 
 out:
 	up_read(&_hash_lock);
@@ -643,10 +660,11 @@ static struct dm_table *dm_get_inactive_table(struct mapped_device *md)
 }
 
 static struct dm_table *dm_get_live_or_inactive_table(struct mapped_device *md,
-						      struct dm_ioctl *param)
+						      struct dm_ioctl *param,
+						      int *srcu_idx)
 {
 	return (param->flags & DM_QUERY_INACTIVE_TABLE_FLAG) ?
-		dm_get_inactive_table(md) : dm_get_live_table(md);
+		dm_get_inactive_table(md, srcu_idx) : dm_get_live_table(md, srcu_idx);
 }
 
 /*
@@ -657,6 +675,7 @@ static void __dev_status(struct mapped_device *md, struct dm_ioctl *param)
 {
 	struct gendisk *disk = dm_disk(md);
 	struct dm_table *table;
+	int srcu_idx;
 
 	param->flags &= ~(DM_SUSPEND_FLAG | DM_READONLY_FLAG |
 			  DM_ACTIVE_PRESENT_FLAG);
@@ -676,26 +695,27 @@ static void __dev_status(struct mapped_device *md, struct dm_ioctl *param)
 	param->event_nr = dm_get_event_nr(md);
 	param->target_count = 0;
 
-	table = dm_get_live_table(md);
+	table = dm_get_live_table(md, &srcu_idx);
 	if (table) {
 		if (!(param->flags & DM_QUERY_INACTIVE_TABLE_FLAG)) {
 			if (get_disk_ro(disk))
 				param->flags |= DM_READONLY_FLAG;
 			param->target_count = dm_table_get_num_targets(table);
 		}
-		dm_table_put(table);
 
 		param->flags |= DM_ACTIVE_PRESENT_FLAG;
 	}
+	dm_put_live_table(md, srcu_idx);
 
 	if (param->flags & DM_QUERY_INACTIVE_TABLE_FLAG) {
-		table = dm_get_inactive_table(md);
+		int srcu_idx;
+		table = dm_get_inactive_table(md, &srcu_idx);
 		if (table) {
 			if (!(dm_table_get_mode(table) & FMODE_WRITE))
 				param->flags |= DM_READONLY_FLAG;
 			param->target_count = dm_table_get_num_targets(table);
-			dm_table_put(table);
 		}
+		dm_put_live_table(md, srcu_idx);
 	}
 }
 
@@ -796,6 +816,7 @@ static int dev_remove(struct dm_ioctl *param, size_t param_size)
 	struct hash_cell *hc;
 	struct mapped_device *md;
 	int r;
+	struct dm_table *t;
 
 	down_write(&_hash_lock);
 	hc = __find_device_hash_cell(param);
@@ -819,9 +840,14 @@ static int dev_remove(struct dm_ioctl *param, size_t param_size)
 		return r;
 	}
 
-	__hash_remove(hc);
+	t = __hash_remove(hc);
 	up_write(&_hash_lock);
 
+	if (t) {
+		dm_sync_table(md);
+		dm_table_destroy(t);
+	}
+
 	if (!dm_kobject_uevent(md, KOBJ_REMOVE, param->event_nr))
 		param->flags |= DM_UEVENT_GENERATED_FLAG;
 
@@ -986,6 +1012,7 @@ static int do_resume(struct dm_ioctl *param)
 
 		old_map = dm_swap_table(md, new_map);
 		if (IS_ERR(old_map)) {
+			dm_sync_table(md);
 			dm_table_destroy(new_map);
 			dm_put(md);
 			return PTR_ERR(old_map);
@@ -1003,6 +1030,10 @@ static int do_resume(struct dm_ioctl *param)
 			param->flags |= DM_UEVENT_GENERATED_FLAG;
 	}
 
+	/*
+	 * Since dm_swap_table synchronizes RCU, nobody should be in
+	 * read-side critical section already.
+	 */
 	if (old_map)
 		dm_table_destroy(old_map);
 
@@ -1125,6 +1156,7 @@ static int dev_wait(struct dm_ioctl *param, size_t param_size)
 	int r = 0;
 	struct mapped_device *md;
 	struct dm_table *table;
+	int srcu_idx;
 
 	md = find_device(param);
 	if (!md)
@@ -1145,11 +1177,10 @@ static int dev_wait(struct dm_ioctl *param, size_t param_size)
 	 */
 	__dev_status(md, param);
 
-	table = dm_get_live_or_inactive_table(md, param);
-	if (table) {
+	table = dm_get_live_or_inactive_table(md, param, &srcu_idx);
+	if (table)
 		retrieve_status(table, param, param_size);
-		dm_table_put(table);
-	}
+	dm_put_live_table(md, srcu_idx);
 
 out:
 	dm_put(md);
@@ -1221,7 +1252,7 @@ static int table_load(struct dm_ioctl *param, size_t param_size)
 {
 	int r;
 	struct hash_cell *hc;
-	struct dm_table *t;
+	struct dm_table *t, *old_map = NULL;
 	struct mapped_device *md;
 	struct target_type *immutable_target_type;
 
@@ -1277,14 +1308,14 @@ static int table_load(struct dm_ioctl *param, size_t param_size)
 	hc = dm_get_mdptr(md);
 	if (!hc || hc->md != md) {
 		DMWARN("device has been removed from the dev hash table.");
-		dm_table_destroy(t);
 		up_write(&_hash_lock);
+		dm_table_destroy(t);
 		r = -ENXIO;
 		goto out;
 	}
 
 	if (hc->new_map)
-		dm_table_destroy(hc->new_map);
+		old_map = hc->new_map;
 	hc->new_map = t;
 	up_write(&_hash_lock);
 
@@ -1292,6 +1323,11 @@ static int table_load(struct dm_ioctl *param, size_t param_size)
 	__dev_status(md, param);
 
 out:
+	if (old_map) {
+		dm_sync_table(md);
+		dm_table_destroy(old_map);
+	}
+
 	dm_put(md);
 
 	return r;
@@ -1301,6 +1337,7 @@ static int table_clear(struct dm_ioctl *param, size_t param_size)
 {
 	struct hash_cell *hc;
 	struct mapped_device *md;
+	struct dm_table *old_map = NULL;
 
 	down_write(&_hash_lock);
 
@@ -1312,7 +1349,7 @@ static int table_clear(struct dm_ioctl *param, size_t param_size)
 	}
 
 	if (hc->new_map) {
-		dm_table_destroy(hc->new_map);
+		old_map = hc->new_map;
 		hc->new_map = NULL;
 	}
 
@@ -1321,6 +1358,10 @@ static int table_clear(struct dm_ioctl *param, size_t param_size)
 	__dev_status(hc->md, param);
 	md = hc->md;
 	up_write(&_hash_lock);
+	if (old_map) {
+		dm_sync_table(md);
+		dm_table_destroy(old_map);
+	}
 	dm_put(md);
 
 	return 0;
@@ -1370,6 +1411,7 @@ static int table_deps(struct dm_ioctl *param, size_t param_size)
 {
 	struct mapped_device *md;
 	struct dm_table *table;
+	int srcu_idx;
 
 	md = find_device(param);
 	if (!md)
@@ -1377,11 +1419,10 @@ static int table_deps(struct dm_ioctl *param, size_t param_size)
 
 	__dev_status(md, param);
 
-	table = dm_get_live_or_inactive_table(md, param);
-	if (table) {
+	table = dm_get_live_or_inactive_table(md, param, &srcu_idx);
+	if (table)
 		retrieve_deps(table, param, param_size);
-		dm_table_put(table);
-	}
+	dm_put_live_table(md, srcu_idx);
 
 	dm_put(md);
 
@@ -1396,6 +1437,7 @@ static int table_status(struct dm_ioctl *param, size_t param_size)
 {
 	struct mapped_device *md;
 	struct dm_table *table;
+	int srcu_idx;
 
 	md = find_device(param);
 	if (!md)
@@ -1403,11 +1445,10 @@ static int table_status(struct dm_ioctl *param, size_t param_size)
 
 	__dev_status(md, param);
 
-	table = dm_get_live_or_inactive_table(md, param);
-	if (table) {
+	table = dm_get_live_or_inactive_table(md, param, &srcu_idx);
+	if (table)
 		retrieve_status(table, param, param_size);
-		dm_table_put(table);
-	}
+	dm_put_live_table(md, srcu_idx);
 
 	dm_put(md);
 
@@ -1443,6 +1484,7 @@ static int target_message(struct dm_ioctl *param, size_t param_size)
 	struct dm_target_msg *tmsg = (void *) param + param->data_start;
 	size_t maxlen;
 	char *result = get_result_buffer(param, param_size, &maxlen);
+	int srcu_idx;
 
 	md = find_device(param);
 	if (!md)
@@ -1470,9 +1512,9 @@ static int target_message(struct dm_ioctl *param, size_t param_size)
 	if (r <= 1)
 		goto out_argv;
 
-	table = dm_get_live_table(md);
+	table = dm_get_live_table(md, &srcu_idx);
 	if (!table)
-		goto out_argv;
+		goto out_table;
 
 	if (dm_deleting_md(md)) {
 		r = -ENXIO;
@@ -1491,7 +1533,7 @@ static int target_message(struct dm_ioctl *param, size_t param_size)
 	}
 
  out_table:
-	dm_table_put(table);
+	dm_put_live_table(md, srcu_idx);
  out_argv:
 	kfree(argv);
  out:

drivers/md/dm-table.c

@@ -26,22 +26,8 @@
 #define KEYS_PER_NODE (NODE_SIZE / sizeof(sector_t))
 #define CHILDREN_PER_NODE (KEYS_PER_NODE + 1)
 
-/*
- * The table has always exactly one reference from either mapped_device->map
- * or hash_cell->new_map. This reference is not counted in table->holders.
- * A pair of dm_create_table/dm_destroy_table functions is used for table
- * creation/destruction.
- *
- * Temporary references from the other code increase table->holders. A pair
- * of dm_table_get/dm_table_put functions is used to manipulate it.
- *
- * When the table is about to be destroyed, we wait for table->holders to
- * drop to zero.
- */
-
 struct dm_table {
 	struct mapped_device *md;
-	atomic_t holders;
 	unsigned type;
 
 	/* btree table */
@@ -208,7 +194,6 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
 
 	INIT_LIST_HEAD(&t->devices);
 	INIT_LIST_HEAD(&t->target_callbacks);
-	atomic_set(&t->holders, 0);
 
 	if (!num_targets)
 		num_targets = KEYS_PER_NODE;
@@ -246,10 +231,6 @@ void dm_table_destroy(struct dm_table *t)
 	if (!t)
 		return;
 
-	while (atomic_read(&t->holders))
-		msleep(1);
-	smp_mb();
-
 	/* free the indexes */
 	if (t->depth >= 2)
 		vfree(t->index[t->depth - 2]);
@@ -274,22 +255,6 @@ void dm_table_destroy(struct dm_table *t)
 	kfree(t);
 }
 
-void dm_table_get(struct dm_table *t)
-{
-	atomic_inc(&t->holders);
-}
-EXPORT_SYMBOL(dm_table_get);
-
-void dm_table_put(struct dm_table *t)
-{
-	if (!t)
-		return;
-
-	smp_mb__before_atomic_dec();
-	atomic_dec(&t->holders);
-}
-EXPORT_SYMBOL(dm_table_put);
-
 /*
  * Checks to see if we need to extend highs or targets.
  */

include/linux/device-mapper.h

@@ -446,9 +446,9 @@ int __must_check dm_set_target_max_io_len(struct dm_target *ti, sector_t len);
 /*
  * Table reference counting.
  */
-struct dm_table *dm_get_live_table(struct mapped_device *md);
-void dm_table_get(struct dm_table *t);
-void dm_table_put(struct dm_table *t);
+struct dm_table *dm_get_live_table(struct mapped_device *md, int *srcu_idx);
+void dm_put_live_table(struct mapped_device *md, int srcu_idx);
+void dm_sync_table(struct mapped_device *md);
 
 /*
  * Queries

include/uapi/linux/dm-ioctl.h

@@ -267,9 +267,9 @@ enum {
 #define DM_DEV_SET_GEOMETRY	_IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl)
 
 #define DM_VERSION_MAJOR	4
-#define DM_VERSION_MINOR	24
+#define DM_VERSION_MINOR	25
 #define DM_VERSION_PATCHLEVEL	0
-#define DM_VERSION_EXTRA	"-ioctl (2013-01-15)"
+#define DM_VERSION_EXTRA	"-ioctl (2013-06-26)"
 
 /* Status bits */
 #define DM_READONLY_FLAG	(1 << 0) /* In/Out */