[PATCH 08/11] [dm-thin] Add support for external origins.

[Joe Thornber <ejt@redhat.com>]

---
 Documentation/device-mapper/thin-provisioning.txt |   38 ++++++++++-
 drivers/md/dm-thin.c                              |   81 +++++++++++++++++----
 2 files changed, 105 insertions(+), 14 deletions(-)

diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt
index 801d9d1..60fc5cf 100644
--- a/Documentation/device-mapper/thin-provisioning.txt
+++ b/Documentation/device-mapper/thin-provisioning.txt
@@ -167,6 +167,38 @@ ii) Using an internal snapshot.
 
     dmsetup create snap --table "0 2097152 thin /dev/mapper/pool 1"
 
+External snapshots
+------------------
+
+You can use an external, _read only_, device as an origin for a thin
+device.  Any read to an unprovisioned area of the thin device will be
+passed through to the origin.  Writes trigger allocation of new blocks
+as usual.
+
+One possible use case for this would be VM hosts who want to run
+guests on thinp volumes, but have the base image on another device
+(possibly shared between many VMs).
+
+You must not write to the origin device if you use this technique!  Of
+course you can write to the thin device, and take internal snapshots
+of the thin.
+
+i) Creating an external snapshot
+
+  Same as creating a thin device.  You don't need to mention the
+  origin at this stage.
+
+    dmsetup message /dev/mapper/pool 0 "create_thin 0"
+
+ii) Using an external snapshot.
+
+  Add an extra parameter to the thin target specifying the origin:
+
+    dmsetup create snap --table "0 2097152 thin /dev/mapper/pool 0 /dev/image"
+
+  All descendants (internal snapshots) of an external snapshot will
+  need the extra origin argument.
+
 Deactivation
 ------------
 
@@ -262,7 +294,7 @@ iii) Messages
 
 i) Constructor
 
-    thin <pool dev> <dev id>
+    thin <pool dev> <dev id> [external origin id]
 
     pool dev:
 	the thin-pool device, e.g. /dev/mapper/my_pool or 253:0
@@ -271,6 +303,10 @@ i) Constructor
 	the internal device identifier of the device to be
 	activated.
 
+    external origin dev:
+        a block device; reads to unprovisioned areas of the thin target
+        will be mapped to here.
+
 The pool doesn't store any size against the thin devices.  If you
 load a thin target that is smaller than you've been using previously,
 then you'll have no access to blocks mapped beyond the end.  If you
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 19de11a..922ebf2 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -537,6 +537,7 @@ struct pool_c {
  */
 struct thin_c {
 	struct dm_dev *pool_dev;
+	struct dm_dev *origin_dev;
 	dm_thin_id dev_id;
 
 	struct pool *pool;
@@ -654,14 +655,16 @@ static void remap(struct thin_c *tc, struct bio *bio, dm_block_t block)
 		(bio->bi_sector & pool->offset_mask);
 }
 
-static void remap_and_issue(struct thin_c *tc, struct bio *bio,
-			    dm_block_t block)
+static void remap_to_origin(struct thin_c *tc, struct bio *bio)
+{
+	bio->bi_bdev = tc->origin_dev->bdev;
+}
+
+static void issue(struct thin_c *tc, struct bio *bio)
 {
 	struct pool *pool = tc->pool;
 	unsigned long flags;
 
-	remap(tc, bio, block);
-
 	/*
 	 * Batch together any FUA/FLUSH bios we find and then issue
 	 * a single commit for them in process_deferred_bios().
@@ -676,6 +679,19 @@ static void remap_and_issue(struct thin_c *tc, struct bio *bio,
 	}
 }
 
+static void remap_to_origin_and_issue(struct thin_c *tc, struct bio *bio)
+{
+	remap_to_origin(tc, bio);
+	issue(tc, bio);
+}
+
+static void remap_and_issue(struct thin_c *tc, struct bio *bio,
+			    dm_block_t block)
+{
+	remap(tc, bio, block);
+	issue(tc, bio);
+}
+
 /*
  * wake_worker() is used when new work is queued and when pool_resume is
  * ready to continue deferred IO processing.
@@ -927,7 +943,8 @@ static struct new_mapping *get_next_mapping(struct pool *pool)
 }
 
 static void schedule_copy(struct thin_c *tc, dm_block_t virt_block,
-			  dm_block_t data_origin, dm_block_t data_dest,
+			  struct dm_dev *origin, dm_block_t data_origin,
+			  dm_block_t data_dest,
 			  struct cell *cell, struct bio *bio)
 {
 	int r;
@@ -959,7 +976,7 @@ static void schedule_copy(struct thin_c *tc, dm_block_t virt_block,
 	} else {
 		struct dm_io_region from, to;
 
-		from.bdev = tc->pool_dev->bdev;
+		from.bdev = origin->bdev;
 		from.sector = data_origin * pool->sectors_per_block;
 		from.count = pool->sectors_per_block;
 
@@ -977,6 +994,22 @@ static void schedule_copy(struct thin_c *tc, dm_block_t virt_block,
 	}
 }
 
+static void schedule_internal_copy(struct thin_c *tc, dm_block_t virt_block,
+				   dm_block_t data_origin, dm_block_t data_dest,
+				   struct cell *cell, struct bio *bio)
+{
+	schedule_copy(tc, virt_block, tc->pool_dev,
+		      data_origin, data_dest, cell, bio);
+}
+
+static void schedule_external_copy(struct thin_c *tc, dm_block_t virt_block,
+				   dm_block_t data_dest,
+				   struct cell *cell, struct bio *bio)
+{
+	schedule_copy(tc, virt_block, tc->origin_dev,
+		      virt_block, data_dest, cell, bio);
+}
+
 static void schedule_zero(struct thin_c *tc, dm_block_t virt_block,
 			  dm_block_t data_block, struct cell *cell,
 			  struct bio *bio)
@@ -1123,8 +1156,8 @@ static void break_sharing(struct thin_c *tc, struct bio *bio, dm_block_t block,
 	r = alloc_data_block(tc, &data_block);
 	switch (r) {
 	case 0:
-		schedule_copy(tc, block, lookup_result->block,
-			      data_block, cell, bio);
+		schedule_internal_copy(tc, block, lookup_result->block,
+				       data_block, cell, bio);
 		break;
 
 	case -ENOSPC:
@@ -1198,7 +1231,10 @@ static void provision_block(struct thin_c *tc, struct bio *bio, dm_block_t block
 	r = alloc_data_block(tc, &data_block);
 	switch (r) {
 	case 0:
-		schedule_zero(tc, block, data_block, cell, bio);
+		if (tc->origin_dev)
+			schedule_external_copy(tc, block, data_block, cell, bio);
+		else
+			schedule_zero(tc, block, data_block, cell, bio);
 		break;
 
 	case -ENOSPC:
@@ -1249,7 +1285,11 @@ static void process_bio(struct thin_c *tc, struct bio *bio)
 		break;
 
 	case -ENODATA:
-		provision_block(tc, bio, block, cell);
+		if (bio_data_dir(bio) == READ && tc->origin_dev) {
+			cell_release_singleton(cell, bio);
+			remap_to_origin_and_issue(tc, bio);
+		} else
+			provision_block(tc, bio, block, cell);
 		break;
 
 	default:
@@ -2235,6 +2275,8 @@ static void thin_dtr(struct dm_target *ti)
 	__pool_dec(tc->pool);
 	dm_pool_close_thin_device(tc->td);
 	dm_put_device(ti, tc->pool_dev);
+	if (tc->origin_dev)
+		dm_put_device(ti, tc->origin_dev);
 	kfree(tc);
 
 	mutex_unlock(&dm_thin_pool_table.mutex);
@@ -2243,21 +2285,22 @@ static void thin_dtr(struct dm_target *ti)
 /*
  * Thin target parameters:
  *
- * <pool_dev> <dev_id>
+ * <pool_dev> <dev_id> [origin_dev]
  *
  * pool_dev: the path to the pool (eg, /dev/mapper/my_pool)
  * dev_id: the internal device identifier
+ * origin_dev: a device external to the pool that should act as the origin
  */
 static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 {
 	int r;
 	struct thin_c *tc;
-	struct dm_dev *pool_dev;
+	struct dm_dev *pool_dev, *origin_dev;
 	struct mapped_device *pool_md;
 
 	mutex_lock(&dm_thin_pool_table.mutex);
 
-	if (argc != 2) {
+	if (argc != 2 && argc != 3) {
 		ti->error = "Invalid argument count";
 		r = -EINVAL;
 		goto out_unlock;
@@ -2270,6 +2313,15 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		goto out_unlock;
 	}
 
+	if (argc == 3) {
+		r = dm_get_device(ti, argv[2], FMODE_READ, &origin_dev);
+		if (r) {
+			ti->error = "Error opening origin device";
+			goto bad_origin_dev;
+		}
+		tc->origin_dev = origin_dev;
+	}
+
 	r = dm_get_device(ti, argv[0], dm_table_get_mode(ti->table), &pool_dev);
 	if (r) {
 		ti->error = "Error opening pool device";
@@ -2322,6 +2374,9 @@ bad_pool_lookup:
 bad_common:
 	dm_put_device(ti, tc->pool_dev);
 bad_pool_dev:
+	if (tc->origin_dev)
+		dm_put_device(ti, tc->origin_dev);
+bad_origin_dev:
 	kfree(tc);
 out_unlock:
 	mutex_unlock(&dm_thin_pool_table.mutex);
-- 
1.7.5.4