ceph: decode v5 of osdmap (pool names) [protocol change]

Teach the client to decode an updated format for the osdmap.  The new
format includes pool names, which will be useful shortly.  Get this change
in earlier rather than later.

Signed-off-by: Sage Weil <sage@newdream.net>

3 files changed, 114 insertions, 73 deletions

diff --git a/fs/ceph/osdmap.c b/fs/ceph/osdmap.c
index d82fe87c2a6e..7526d6d33016 100644
--- a/fs/ceph/osdmap.c
+++ b/fs/ceph/osdmap.c
@@ -312,71 +312,6 @@ bad:
 	return ERR_PTR(err);
 }
 
-
-/*
- * osd map
- */
-void ceph_osdmap_destroy(struct ceph_osdmap *map)
-{
-	dout("osdmap_destroy %p\n", map);
-	if (map->crush)
-		crush_destroy(map->crush);
-	while (!RB_EMPTY_ROOT(&map->pg_temp)) {
-		struct ceph_pg_mapping *pg =
-			rb_entry(rb_first(&map->pg_temp),
-				 struct ceph_pg_mapping, node);
-		rb_erase(&pg->node, &map->pg_temp);
-		kfree(pg);
-	}
-	while (!RB_EMPTY_ROOT(&map->pg_pools)) {
-		struct ceph_pg_pool_info *pi =
-			rb_entry(rb_first(&map->pg_pools),
-				 struct ceph_pg_pool_info, node);
-		rb_erase(&pi->node, &map->pg_pools);
-		kfree(pi);
-	}
-	kfree(map->osd_state);
-	kfree(map->osd_weight);
-	kfree(map->osd_addr);
-	kfree(map);
-}
-
-/*
- * adjust max osd value.  reallocate arrays.
- */
-static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
-{
-	u8 *state;
-	struct ceph_entity_addr *addr;
-	u32 *weight;
-
-	state = kcalloc(max, sizeof(*state), GFP_NOFS);
-	addr = kcalloc(max, sizeof(*addr), GFP_NOFS);
-	weight = kcalloc(max, sizeof(*weight), GFP_NOFS);
-	if (state == NULL || addr == NULL || weight == NULL) {
-		kfree(state);
-		kfree(addr);
-		kfree(weight);
-		return -ENOMEM;
-	}
-
-	/* copy old? */
-	if (map->osd_state) {
-		memcpy(state, map->osd_state, map->max_osd*sizeof(*state));
-		memcpy(addr, map->osd_addr, map->max_osd*sizeof(*addr));
-		memcpy(weight, map->osd_weight, map->max_osd*sizeof(*weight));
-		kfree(map->osd_state);
-		kfree(map->osd_addr);
-		kfree(map->osd_weight);
-	}
-
-	map->osd_state = state;
-	map->osd_weight = weight;
-	map->osd_addr = addr;
-	map->max_osd = max;
-	return 0;
-}
-
 /*
  * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid
  * to a set of osds)
@@ -480,6 +415,13 @@ static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, int id)
 	return NULL;
 }
 
+static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi)
+{
+	rb_erase(&pi->node, root);
+	kfree(pi->name);
+	kfree(pi);
+}
+
 void __decode_pool(void **p, struct ceph_pg_pool_info *pi)
 {
 	ceph_decode_copy(p, &pi->v, sizeof(pi->v));
@@ -488,6 +430,98 @@ void __decode_pool(void **p, struct ceph_pg_pool_info *pi)
 	*p += le32_to_cpu(pi->v.num_removed_snap_intervals) * sizeof(u64) * 2;
 }
 
+static int __decode_pool_names(void **p, void *end, struct ceph_osdmap *map)
+{
+	struct ceph_pg_pool_info *pi;
+	u32 num, len, pool;
+
+	ceph_decode_32_safe(p, end, num, bad);
+	dout(" %d pool names\n", num);
+	while (num--) {
+		ceph_decode_32_safe(p, end, pool, bad);
+		ceph_decode_32_safe(p, end, len, bad);
+		dout("  pool %d len %d\n", pool, len);
+		pi = __lookup_pg_pool(&map->pg_pools, pool);
+		if (pi) {
+			kfree(pi->name);
+			pi->name = kmalloc(len + 1, GFP_NOFS);
+			if (pi->name) {
+				memcpy(pi->name, *p, len);
+				pi->name[len] = '\0';
+				dout("  name is %s\n", pi->name);
+			}
+		}
+		*p += len;
+	}
+	return 0;
+
+bad:
+	return -EINVAL;
+}
+
+/*
+ * osd map
+ */
+void ceph_osdmap_destroy(struct ceph_osdmap *map)
+{
+	dout("osdmap_destroy %p\n", map);
+	if (map->crush)
+		crush_destroy(map->crush);
+	while (!RB_EMPTY_ROOT(&map->pg_temp)) {
+		struct ceph_pg_mapping *pg =
+			rb_entry(rb_first(&map->pg_temp),
+				 struct ceph_pg_mapping, node);
+		rb_erase(&pg->node, &map->pg_temp);
+		kfree(pg);
+	}
+	while (!RB_EMPTY_ROOT(&map->pg_pools)) {
+		struct ceph_pg_pool_info *pi =
+			rb_entry(rb_first(&map->pg_pools),
+				 struct ceph_pg_pool_info, node);
+		__remove_pg_pool(&map->pg_pools, pi);
+	}
+	kfree(map->osd_state);
+	kfree(map->osd_weight);
+	kfree(map->osd_addr);
+	kfree(map);
+}
+
+/*
+ * adjust max osd value.  reallocate arrays.
+ */
+static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
+{
+	u8 *state;
+	struct ceph_entity_addr *addr;
+	u32 *weight;
+
+	state = kcalloc(max, sizeof(*state), GFP_NOFS);
+	addr = kcalloc(max, sizeof(*addr), GFP_NOFS);
+	weight = kcalloc(max, sizeof(*weight), GFP_NOFS);
+	if (state == NULL || addr == NULL || weight == NULL) {
+		kfree(state);
+		kfree(addr);
+		kfree(weight);
+		return -ENOMEM;
+	}
+
+	/* copy old? */
+	if (map->osd_state) {
+		memcpy(state, map->osd_state, map->max_osd*sizeof(*state));
+		memcpy(addr, map->osd_addr, map->max_osd*sizeof(*addr));
+		memcpy(weight, map->osd_weight, map->max_osd*sizeof(*weight));
+		kfree(map->osd_state);
+		kfree(map->osd_addr);
+		kfree(map->osd_weight);
+	}
+
+	map->osd_state = state;
+	map->osd_weight = weight;
+	map->osd_addr = addr;
+	map->max_osd = max;
+	return 0;
+}
+
 /*
  * decode a full map.
  */
@@ -524,7 +558,7 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end)
 	ceph_decode_32_safe(p, end, max, bad);
 	while (max--) {
 		ceph_decode_need(p, end, 4 + 1 + sizeof(pi->v), bad);
-		pi = kmalloc(sizeof(*pi), GFP_NOFS);
+		pi = kzalloc(sizeof(*pi), GFP_NOFS);
 		if (!pi)
 			goto bad;
 		pi->id = ceph_decode_32(p);
@@ -537,6 +571,10 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end)
 		__decode_pool(p, pi);
 		__insert_pg_pool(&map->pg_pools, pi);
 	}
+
+	if (version >= 5 && __decode_pool_names(p, end, map) < 0)
+		goto bad;
+
 	ceph_decode_32_safe(p, end, map->pool_max, bad);
 
 	ceph_decode_32_safe(p, end, map->flags, bad);
@@ -710,7 +748,7 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 		}
 		pi = __lookup_pg_pool(&map->pg_pools, pool);
 		if (!pi) {
-			pi = kmalloc(sizeof(*pi), GFP_NOFS);
+			pi = kzalloc(sizeof(*pi), GFP_NOFS);
 			if (!pi) {
 				err = -ENOMEM;
 				goto bad;
@@ -720,6 +758,8 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 		}
 		__decode_pool(p, pi);
 	}
+	if (version >= 5 && __decode_pool_names(p, end, map) < 0)
+		goto bad;
 
 	/* old_pool */
 	ceph_decode_32_safe(p, end, len, bad);
@@ -728,10 +768,8 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 
 		ceph_decode_32_safe(p, end, pool, bad);
 		pi = __lookup_pg_pool(&map->pg_pools, pool);
-		if (pi) {
-			rb_erase(&pi->node, &map->pg_pools);
-			kfree(pi);
-		}
+		if (pi)
+			__remove_pg_pool(&map->pg_pools, pi);
 	}
 
 	/* new_up */
diff --git a/fs/ceph/osdmap.h b/fs/ceph/osdmap.h
index 1fb55afb2642..8bc9f1e4f562 100644
--- a/fs/ceph/osdmap.h
+++ b/fs/ceph/osdmap.h
@@ -23,6 +23,7 @@ struct ceph_pg_pool_info {
 	int id;
 	struct ceph_pg_pool v;
 	int pg_num_mask, pgp_num_mask, lpg_num_mask, lpgp_num_mask;
+	char *name;
 };
 
 struct ceph_pg_mapping {
diff --git a/fs/ceph/rados.h b/fs/ceph/rados.h
index 26ac8b89a676..a1fc1d017b58 100644
--- a/fs/ceph/rados.h
+++ b/fs/ceph/rados.h
@@ -11,8 +11,10 @@
 /*
  * osdmap encoding versions
  */
-#define CEPH_OSDMAP_INC_VERSION 4
-#define CEPH_OSDMAP_VERSION     4
+#define CEPH_OSDMAP_INC_VERSION     5
+#define CEPH_OSDMAP_INC_VERSION_EXT 5
+#define CEPH_OSDMAP_VERSION         5
+#define CEPH_OSDMAP_VERSION_EXT     5
 
 /*
  * fs id