rbd: get parent spec for version 2 images

Add support for getting the the information identifying the parent
image for rbd images that have them.  The child image holds a
reference to its parent image specification structure.  Create a new
entry "parent" in /sys/bus/rbd/image/N/ to report the identifying
information for the parent image, if any.

Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

3 files changed, 137 insertions, 0 deletions

diff --git a/Documentation/ABI/testing/sysfs-bus-rbd b/Documentation/ABI/testing/sysfs-bus-rbd
index 1cf2adf46b11..cd9213ccf3dc 100644
--- a/Documentation/ABI/testing/sysfs-bus-rbd
+++ b/Documentation/ABI/testing/sysfs-bus-rbd
@@ -70,6 +70,10 @@ snap_*
 
 	A directory per each snapshot
 
+parent
+
+	Information identifying the pool, image, and snapshot id for
+	the parent image in a layered rbd image (format 2 only).
 
 Entries under /sys/bus/rbd/devices/<dev-id>/snap_<snap-name>
 -------------------------------------------------------------
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 28052ff679ca..bce1fcfb5185 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -217,6 +217,9 @@ struct rbd_device {
 	struct ceph_osd_event   *watch_event;
 	struct ceph_osd_request *watch_request;
 
+	struct rbd_spec		*parent_spec;
+	u64			parent_overlap;
+
 	/* protects updating the header */
 	struct rw_semaphore     header_rwsem;
 
@@ -2009,6 +2012,49 @@ static ssize_t rbd_snap_show(struct device *dev,
 	return sprintf(buf, "%s\n", rbd_dev->spec->snap_name);
 }
 
+/*
+ * For an rbd v2 image, shows the pool id, image id, and snapshot id
+ * for the parent image.  If there is no parent, simply shows
+ * "(no parent image)".
+ */
+static ssize_t rbd_parent_show(struct device *dev,
+			     struct device_attribute *attr,
+			     char *buf)
+{
+	struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
+	struct rbd_spec *spec = rbd_dev->parent_spec;
+	int count;
+	char *bufp = buf;
+
+	if (!spec)
+		return sprintf(buf, "(no parent image)\n");
+
+	count = sprintf(bufp, "pool_id %llu\npool_name %s\n",
+			(unsigned long long) spec->pool_id, spec->pool_name);
+	if (count < 0)
+		return count;
+	bufp += count;
+
+	count = sprintf(bufp, "image_id %s\nimage_name %s\n", spec->image_id,
+			spec->image_name ? spec->image_name : "(unknown)");
+	if (count < 0)
+		return count;
+	bufp += count;
+
+	count = sprintf(bufp, "snap_id %llu\nsnap_name %s\n",
+			(unsigned long long) spec->snap_id, spec->snap_name);
+	if (count < 0)
+		return count;
+	bufp += count;
+
+	count = sprintf(bufp, "overlap %llu\n", rbd_dev->parent_overlap);
+	if (count < 0)
+		return count;
+	bufp += count;
+
+	return (ssize_t) (bufp - buf);
+}
+
 static ssize_t rbd_image_refresh(struct device *dev,
 				 struct device_attribute *attr,
 				 const char *buf,
@@ -2032,6 +2078,7 @@ static DEVICE_ATTR(name, S_IRUGO, rbd_name_show, NULL);
 static DEVICE_ATTR(image_id, S_IRUGO, rbd_image_id_show, NULL);
 static DEVICE_ATTR(refresh, S_IWUSR, NULL, rbd_image_refresh);
 static DEVICE_ATTR(current_snap, S_IRUGO, rbd_snap_show, NULL);
+static DEVICE_ATTR(parent, S_IRUGO, rbd_parent_show, NULL);
 
 static struct attribute *rbd_attrs[] = {
 	&dev_attr_size.attr,
@@ -2043,6 +2090,7 @@ static struct attribute *rbd_attrs[] = {
 	&dev_attr_name.attr,
 	&dev_attr_image_id.attr,
 	&dev_attr_current_snap.attr,
+	&dev_attr_parent.attr,
 	&dev_attr_refresh.attr,
 	NULL
 };
@@ -2192,6 +2240,7 @@ struct rbd_device *rbd_dev_create(struct rbd_client *rbdc,
 
 static void rbd_dev_destroy(struct rbd_device *rbd_dev)
 {
+	rbd_spec_put(rbd_dev->parent_spec);
 	kfree(rbd_dev->header_name);
 	rbd_put_client(rbd_dev->rbd_client);
 	rbd_spec_put(rbd_dev->spec);
@@ -2400,6 +2449,71 @@ static int rbd_dev_v2_features(struct rbd_device *rbd_dev)
 						&rbd_dev->header.features);
 }
 
+static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
+{
+	struct rbd_spec *parent_spec;
+	size_t size;
+	void *reply_buf = NULL;
+	__le64 snapid;
+	void *p;
+	void *end;
+	char *image_id;
+	u64 overlap;
+	size_t len = 0;
+	int ret;
+
+	parent_spec = rbd_spec_alloc();
+	if (!parent_spec)
+		return -ENOMEM;
+
+	size = sizeof (__le64) +				/* pool_id */
+		sizeof (__le32) + RBD_IMAGE_ID_LEN_MAX +	/* image_id */
+		sizeof (__le64) +				/* snap_id */
+		sizeof (__le64);				/* overlap */
+	reply_buf = kmalloc(size, GFP_KERNEL);
+	if (!reply_buf) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	snapid = cpu_to_le64(CEPH_NOSNAP);
+	ret = rbd_req_sync_exec(rbd_dev, rbd_dev->header_name,
+				"rbd", "get_parent",
+				(char *) &snapid, sizeof (snapid),
+				(char *) reply_buf, size,
+				CEPH_OSD_FLAG_READ, NULL);
+	dout("%s: rbd_req_sync_exec returned %d\n", __func__, ret);
+	if (ret < 0)
+		goto out_err;
+
+	ret = -ERANGE;
+	p = reply_buf;
+	end = (char *) reply_buf + size;
+	ceph_decode_64_safe(&p, end, parent_spec->pool_id, out_err);
+	if (parent_spec->pool_id == CEPH_NOPOOL)
+		goto out;	/* No parent?  No problem. */
+
+	image_id = ceph_extract_encoded_string(&p, end, &len, GFP_KERNEL);
+	if (IS_ERR(image_id)) {
+		ret = PTR_ERR(image_id);
+		goto out_err;
+	}
+	parent_spec->image_id = image_id;
+	ceph_decode_64_safe(&p, end, parent_spec->snap_id, out_err);
+	ceph_decode_64_safe(&p, end, overlap, out_err);
+
+	rbd_dev->parent_overlap = overlap;
+	rbd_dev->parent_spec = parent_spec;
+	parent_spec = NULL;	/* rbd_dev now owns this */
+out:
+	ret = 0;
+out_err:
+	kfree(reply_buf);
+	rbd_spec_put(parent_spec);
+
+	return ret;
+}
+
 static int rbd_dev_v2_snap_context(struct rbd_device *rbd_dev, u64 *ver)
 {
 	size_t size;
@@ -3154,6 +3268,12 @@ static int rbd_dev_v1_probe(struct rbd_device *rbd_dev)
 	ret = rbd_read_header(rbd_dev, &rbd_dev->header);
 	if (ret < 0)
 		goto out_err;
+
+	/* Version 1 images have no parent (no layering) */
+
+	rbd_dev->parent_spec = NULL;
+	rbd_dev->parent_overlap = 0;
+
 	rbd_dev->image_format = 1;
 
 	dout("discovered version 1 image, header name is %s\n",
@@ -3205,6 +3325,14 @@ static int rbd_dev_v2_probe(struct rbd_device *rbd_dev)
 	if (ret < 0)
 		goto out_err;
 
+	/* If the image supports layering, get the parent info */
+
+	if (rbd_dev->header.features & RBD_FEATURE_LAYERING) {
+		ret = rbd_dev_v2_parent_info(rbd_dev);
+		if (ret < 0)
+			goto out_err;
+	}
+
 	/* crypto and compression type aren't (yet) supported for v2 images */
 
 	rbd_dev->header.crypt_type = 0;
@@ -3224,6 +3352,9 @@ static int rbd_dev_v2_probe(struct rbd_device *rbd_dev)
 
 	return 0;
 out_err:
+	rbd_dev->parent_overlap = 0;
+	rbd_spec_put(rbd_dev->parent_spec);
+	rbd_dev->parent_spec = NULL;
 	kfree(rbd_dev->header_name);
 	rbd_dev->header_name = NULL;
 	kfree(rbd_dev->header.object_prefix);
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 0a99099801a4..15077db662ed 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -87,6 +87,8 @@ struct ceph_pg {
  *
  *  lpgp_num -- as above.
  */
+#define CEPH_NOPOOL  ((__u64) (-1))  /* pool id not defined */
+
 #define CEPH_PG_TYPE_REP     1
 #define CEPH_PG_TYPE_RAID4   2
 #define CEPH_PG_POOL_VERSION 2