libceph: primary_temp infrastructure

Add primary_temp mappings infrastructure.  struct ceph_pg_mapping is
overloaded, primary_temp mappings are stored in an rb-tree, rooted at
ceph_osdmap, in a manner similar to pg_temp mappings.

Dump primary_temp mappings to /sys/kernel/debug/ceph/<client>/osdmap,
one 'primary_temp <pgid> <osd>' per line, e.g:

    primary_temp 2.6 4

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>

3 files changed, 21 insertions, 1 deletions

diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 4837e58e3203..db4fb6322aae 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -66,6 +66,9 @@ struct ceph_pg_mapping {
                         int len;
                         int osds[];
                 } pg_temp;
+                struct {
+                        int osd;
+                } primary_temp;
         };
 };
 
@@ -83,6 +86,8 @@ struct ceph_osdmap {
         struct ceph_entity_addr *osd_addr;
 
         struct rb_root pg_temp;
+        struct rb_root primary_temp;
+
         struct rb_root pg_pools;
         u32 pool_max;
 
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index 5865f2c9580a..612bf55e6a8b 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -93,6 +93,13 @@ static int osdmap_show(struct seq_file *s, void *p)
                                    pg->pg_temp.osds[i]);
                 seq_printf(s, "]\n");
         }
+        for (n = rb_first(&map->primary_temp); n; n = rb_next(n)) {
+                struct ceph_pg_mapping *pg =
+                        rb_entry(n, struct ceph_pg_mapping, node);
+
+                seq_printf(s, "primary_temp %llu.%x %d\n", pg->pgid.pool,
+                           pg->pgid.seed, pg->primary_temp.osd);
+        }
 
         return 0;
 }
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index c67a309fdfc2..c0fc517ab321 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -343,7 +343,7 @@ bad:
 
 /*
  * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid
- * to a set of osds)
+ * to a set of osds) and primary_temp (explicit primary setting)
  */
 static int pgid_cmp(struct ceph_pg l, struct ceph_pg r)
 {
@@ -633,6 +633,13 @@ void ceph_osdmap_destroy(struct ceph_osdmap *map)
                 rb_erase(&pg->node, &map->pg_temp);
                 kfree(pg);
         }
+        while (!RB_EMPTY_ROOT(&map->primary_temp)) {
+                struct ceph_pg_mapping *pg =
+                        rb_entry(rb_first(&map->primary_temp),
+                                 struct ceph_pg_mapping, node);
+                rb_erase(&pg->node, &map->primary_temp);
+                kfree(pg);
+        }
         while (!RB_EMPTY_ROOT(&map->pg_pools)) {
                 struct ceph_pg_pool_info *pi =
                         rb_entry(rb_first(&map->pg_pools),
@@ -966,6 +973,7 @@ struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end)
                 return ERR_PTR(-ENOMEM);
 
         map->pg_temp = RB_ROOT;
+        map->primary_temp = RB_ROOT;
         mutex_init(&map->crush_scratch_mutex);
 
         ret = osdmap_decode(p, end, map);