4 files changed, 33 insertions, 20 deletions

diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 8da7a017b4e..54d0588fc1f 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -233,7 +233,7 @@ static void __hash_remove(struct hash_cell *hc)
 	}
 
 	if (hc->new_map)
-		dm_table_put(hc->new_map);
+		dm_table_destroy(hc->new_map);
 	dm_put(hc->md);
 	free_cell(hc);
 }
@@ -827,8 +827,8 @@ static int do_resume(struct dm_ioctl *param)
 
 		r = dm_swap_table(md, new_map);
 		if (r) {
+			dm_table_destroy(new_map);
 			dm_put(md);
-			dm_table_put(new_map);
 			return r;
 		}
 
@@ -836,8 +836,6 @@ static int do_resume(struct dm_ioctl *param)
 			set_disk_ro(dm_disk(md), 0);
 		else
 			set_disk_ro(dm_disk(md), 1);
-
-		dm_table_put(new_map);
 	}
 
 	if (dm_suspended(md))
@@ -1080,7 +1078,7 @@ static int table_load(struct dm_ioctl *param, size_t param_size)
 	}
 
 	if (hc->new_map)
-		dm_table_put(hc->new_map);
+		dm_table_destroy(hc->new_map);
 	hc->new_map = t;
 	up_write(&_hash_lock);
 
@@ -1109,7 +1107,7 @@ static int table_clear(struct dm_ioctl *param, size_t param_size)
 	}
 
 	if (hc->new_map) {
-		dm_table_put(hc->new_map);
+		dm_table_destroy(hc->new_map);
 		hc->new_map = NULL;
 	}
 
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index ebaaf72cd82..2fd66c30f7f 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2001 Sistina Software (UK) Limited.
- * Copyright (C) 2004 Red Hat, Inc. All rights reserved.
+ * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved.
  *
  * This file is released under the GPL.
  */
@@ -15,6 +15,7 @@
 #include <linux/slab.h>
 #include <linux/interrupt.h>
 #include <linux/mutex.h>
+#include <linux/delay.h>
 #include <asm/atomic.h>
 
 #define DM_MSG_PREFIX "table"
@@ -24,6 +25,19 @@
 #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;
@@ -228,7 +242,7 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&t->devices);
-	atomic_set(&t->holders, 1);
+	atomic_set(&t->holders, 0);
 	t->barriers_supported = 1;
 
 	if (!num_targets)
@@ -259,10 +273,14 @@ static void free_devices(struct list_head *devices)
 	}
 }
 
-static void table_destroy(struct dm_table *t)
+void dm_table_destroy(struct dm_table *t)
 {
 	unsigned int i;
 
+	while (atomic_read(&t->holders))
+		msleep(1);
+	smp_mb();
+
 	/* free the indexes (see dm_table_complete) */
 	if (t->depth >= 2)
 		vfree(t->index[t->depth - 2]);
@@ -300,8 +318,8 @@ void dm_table_put(struct dm_table *t)
 	if (!t)
 		return;
 
-	if (atomic_dec_and_test(&t->holders))
-		table_destroy(t);
+	smp_mb__before_atomic_dec();
+	atomic_dec(&t->holders);
 }
 
 /*
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index dd953b189f4..9f9aa64f733 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -977,8 +977,6 @@ static int dm_any_congested(void *congested_data, int bdi_bits)
 	struct mapped_device *md = congested_data;
 	struct dm_table *map;
 
-	atomic_inc(&md->pending);
-
 	if (!test_bit(DMF_BLOCK_IO, &md->flags)) {
 		map = dm_get_table(md);
 		if (map) {
@@ -987,10 +985,6 @@ static int dm_any_congested(void *congested_data, int bdi_bits)
 		}
 	}
 
-	if (!atomic_dec_return(&md->pending))
-		/* nudge anyone waiting on suspend queue */
-		wake_up(&md->wait);
-
 	return r;
 }
 
@@ -1250,10 +1244,12 @@ static int __bind(struct mapped_device *md, struct dm_table *t)
 
 	if (md->suspended_bdev)
 		__set_size(md, size);
-	if (size == 0)
+
+	if (!size) {
+		dm_table_destroy(t);
 		return 0;
+	}
 
-	dm_table_get(t);
 	dm_table_event_callback(t, event_callback, md);
 
 	write_lock(&md->map_lock);
@@ -1275,7 +1271,7 @@ static void __unbind(struct mapped_device *md)
 	write_lock(&md->map_lock);
 	md->map = NULL;
 	write_unlock(&md->map_lock);
-	dm_table_put(map);
+	dm_table_destroy(map);
 }
 
 /*
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 5b5d08ba9e9..bbbe9110f3b 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -36,6 +36,7 @@ struct dm_table;
 /*-----------------------------------------------------------------
  * Internal table functions.
  *---------------------------------------------------------------*/
+void dm_table_destroy(struct dm_table *t);
 void dm_table_event_callback(struct dm_table *t,
 			     void (*fn)(void *), void *context);
 struct dm_target *dm_table_get_target(struct dm_table *t, unsigned int index);