Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client

Pull Ceph updates from Sage Weil:
 "This changeset has a few main parts:

   - Ilya has finished a huge refactoring effort to sync up the
     client-side logic in libceph with the user-space client code, which
     has evolved significantly over the last couple years, with lots of
     additional behaviors (e.g., how requests are handled when cluster
     is full and transitions from full to non-full).

     This structure of the code is more closely aligned with userspace
     now such that it will be much easier to maintain going forward when
     behavior changes take place.  There are some locking improvements
     bundled in as well.

   - Zheng adds multi-filesystem support (multiple namespaces within the
     same Ceph cluster)

   - Zheng has changed the readdir offsets and directory enumeration so
     that dentry offsets are hash-based and therefore stable across
     directory fragmentation events on the MDS.

   - Zheng has a smorgasbord of bug fixes across fs/ceph"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (71 commits)
  ceph: fix wake_up_session_cb()
  ceph: don't use truncate_pagecache() to invalidate read cache
  ceph: SetPageError() for writeback pages if writepages fails
  ceph: handle interrupted ceph_writepage()
  ceph: make ceph_update_writeable_page() uninterruptible
  libceph: make ceph_osdc_wait_request() uninterruptible
  ceph: handle -EAGAIN returned by ceph_update_writeable_page()
  ceph: make fault/page_mkwrite return VM_FAULT_OOM for -ENOMEM
  ceph: block non-fatal signals for fault/page_mkwrite
  ceph: make logical calculation functions return bool
  ceph: tolerate bad i_size for symlink inode
  ceph: improve fragtree change detection
  ceph: keep leaf frag when updating fragtree
  ceph: fix dir_auth check in ceph_fill_dirfrag()
  ceph: don't assume frag tree splits in mds reply are sorted
  ceph: fix inode reference leak
  ceph: using hash value to compose dentry offset
  ceph: don't forbid marking directory complete after forward seek
  ceph: record 'offset' for each entry of readdir result
  ceph: define 'end/complete' in readdir reply as bit flags
  ...

1 files changed, 112 insertions, 46 deletions

diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index e55c08bc3a96..ddc426b22d81 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -24,21 +24,29 @@ struct ceph_pg {
 	uint32_t seed;
 };
 
-#define CEPH_POOL_FLAG_HASHPSPOOL  1
+int ceph_pg_compare(const struct ceph_pg *lhs, const struct ceph_pg *rhs);
+
+#define CEPH_POOL_FLAG_HASHPSPOOL	(1ULL << 0) /* hash pg seed and pool id
+						       together */
+#define CEPH_POOL_FLAG_FULL		(1ULL << 1) /* pool is full */
 
 struct ceph_pg_pool_info {
 	struct rb_node node;
 	s64 id;
-	u8 type;
+	u8 type; /* CEPH_POOL_TYPE_* */
 	u8 size;
+	u8 min_size;
 	u8 crush_ruleset;
 	u8 object_hash;
+	u32 last_force_request_resend;
 	u32 pg_num, pgp_num;
 	int pg_num_mask, pgp_num_mask;
 	s64 read_tier;
 	s64 write_tier; /* wins for read+write ops */
-	u64 flags;
+	u64 flags; /* CEPH_POOL_FLAG_* */
 	char *name;
+
+	bool was_full;  /* for handle_one_map() */
 };
 
 static inline bool ceph_can_shift_osds(struct ceph_pg_pool_info *pool)
@@ -57,6 +65,22 @@ struct ceph_object_locator {
 	s64 pool;
 };
 
+static inline void ceph_oloc_init(struct ceph_object_locator *oloc)
+{
+	oloc->pool = -1;
+}
+
+static inline bool ceph_oloc_empty(const struct ceph_object_locator *oloc)
+{
+	return oloc->pool == -1;
+}
+
+static inline void ceph_oloc_copy(struct ceph_object_locator *dest,
+				  const struct ceph_object_locator *src)
+{
+	dest->pool = src->pool;
+}
+
 /*
  * Maximum supported by kernel client object name length
  *
@@ -64,11 +88,47 @@ struct ceph_object_locator {
  */
 #define CEPH_MAX_OID_NAME_LEN 100
 
+/*
+ * 51-char inline_name is long enough for all cephfs and all but one
+ * rbd requests: <imgname> in "<imgname>.rbd"/"rbd_id.<imgname>" can be
+ * arbitrarily long (~PAGE_SIZE).  It's done once during rbd map; all
+ * other rbd requests fit into inline_name.
+ *
+ * Makes ceph_object_id 64 bytes on 64-bit.
+ */
+#define CEPH_OID_INLINE_LEN 52
+
+/*
+ * Both inline and external buffers have space for a NUL-terminator,
+ * which is carried around.  It's not required though - RADOS object
+ * names don't have to be NUL-terminated and may contain NULs.
+ */
 struct ceph_object_id {
-	char name[CEPH_MAX_OID_NAME_LEN];
+	char *name;
+	char inline_name[CEPH_OID_INLINE_LEN];
 	int name_len;
 };
 
+static inline void ceph_oid_init(struct ceph_object_id *oid)
+{
+	oid->name = oid->inline_name;
+	oid->name_len = 0;
+}
+
+static inline bool ceph_oid_empty(const struct ceph_object_id *oid)
+{
+	return oid->name == oid->inline_name && !oid->name_len;
+}
+
+void ceph_oid_copy(struct ceph_object_id *dest,
+		   const struct ceph_object_id *src);
+__printf(2, 3)
+void ceph_oid_printf(struct ceph_object_id *oid, const char *fmt, ...);
+__printf(3, 4)
+int ceph_oid_aprintf(struct ceph_object_id *oid, gfp_t gfp,
+		     const char *fmt, ...);
+void ceph_oid_destroy(struct ceph_object_id *oid);
+
 struct ceph_pg_mapping {
 	struct rb_node node;
 	struct ceph_pg pgid;
@@ -87,7 +147,6 @@ struct ceph_pg_mapping {
 struct ceph_osdmap {
 	struct ceph_fsid fsid;
 	u32 epoch;
-	u32 mkfs_epoch;
 	struct ceph_timespec created, modified;
 
 	u32 flags;         /* CEPH_OSDMAP_* */
@@ -113,43 +172,19 @@ struct ceph_osdmap {
 	int crush_scratch_ary[CEPH_PG_MAX_SIZE * 3];
 };
 
-static inline void ceph_oid_set_name(struct ceph_object_id *oid,
-				     const char *name)
-{
-	int len;
-
-	len = strlen(name);
-	if (len > sizeof(oid->name)) {
-		WARN(1, "ceph_oid_set_name '%s' len %d vs %zu, truncating\n",
-		     name, len, sizeof(oid->name));
-		len = sizeof(oid->name);
-	}
-
-	memcpy(oid->name, name, len);
-	oid->name_len = len;
-}
-
-static inline void ceph_oid_copy(struct ceph_object_id *dest,
-				 struct ceph_object_id *src)
-{
-	BUG_ON(src->name_len > sizeof(dest->name));
-	memcpy(dest->name, src->name, src->name_len);
-	dest->name_len = src->name_len;
-}
-
-static inline int ceph_osd_exists(struct ceph_osdmap *map, int osd)
+static inline bool ceph_osd_exists(struct ceph_osdmap *map, int osd)
 {
 	return osd >= 0 && osd < map->max_osd &&
 	       (map->osd_state[osd] & CEPH_OSD_EXISTS);
 }
 
-static inline int ceph_osd_is_up(struct ceph_osdmap *map, int osd)
+static inline bool ceph_osd_is_up(struct ceph_osdmap *map, int osd)
 {
 	return ceph_osd_exists(map, osd) &&
 	       (map->osd_state[osd] & CEPH_OSD_UP);
 }
 
-static inline int ceph_osd_is_down(struct ceph_osdmap *map, int osd)
+static inline bool ceph_osd_is_down(struct ceph_osdmap *map, int osd)
 {
 	return !ceph_osd_is_up(map, osd);
 }
@@ -192,28 +227,59 @@ static inline int ceph_decode_pgid(void **p, void *end, struct ceph_pg *pgid)
 	return 0;
 }
 
+struct ceph_osdmap *ceph_osdmap_alloc(void);
 extern struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end);
-extern struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
-					    struct ceph_osdmap *map,
-					    struct ceph_messenger *msgr);
+struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
+					     struct ceph_osdmap *map);
 extern void ceph_osdmap_destroy(struct ceph_osdmap *map);
 
+struct ceph_osds {
+	int osds[CEPH_PG_MAX_SIZE];
+	int size;
+	int primary; /* id, NOT index */
+};
+
+static inline void ceph_osds_init(struct ceph_osds *set)
+{
+	set->size = 0;
+	set->primary = -1;
+}
+
+void ceph_osds_copy(struct ceph_osds *dest, const struct ceph_osds *src);
+
+bool ceph_is_new_interval(const struct ceph_osds *old_acting,
+			  const struct ceph_osds *new_acting,
+			  const struct ceph_osds *old_up,
+			  const struct ceph_osds *new_up,
+			  int old_size,
+			  int new_size,
+			  int old_min_size,
+			  int new_min_size,
+			  u32 old_pg_num,
+			  u32 new_pg_num,
+			  bool old_sort_bitwise,
+			  bool new_sort_bitwise,
+			  const struct ceph_pg *pgid);
+bool ceph_osds_changed(const struct ceph_osds *old_acting,
+		       const struct ceph_osds *new_acting,
+		       bool any_change);
+
 /* calculate mapping of a file extent to an object */
 extern int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
 					 u64 off, u64 len,
 					 u64 *bno, u64 *oxoff, u64 *oxlen);
 
-/* calculate mapping of object to a placement group */
-extern int ceph_oloc_oid_to_pg(struct ceph_osdmap *osdmap,
-			       struct ceph_object_locator *oloc,
-			       struct ceph_object_id *oid,
-			       struct ceph_pg *pg_out);
-
-extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap,
-			       struct ceph_pg pgid,
-			       int *osds, int *primary);
-extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
-				struct ceph_pg pgid);
+int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap,
+			      struct ceph_object_id *oid,
+			      struct ceph_object_locator *oloc,
+			      struct ceph_pg *raw_pgid);
+
+void ceph_pg_to_up_acting_osds(struct ceph_osdmap *osdmap,
+			       const struct ceph_pg *raw_pgid,
+			       struct ceph_osds *up,
+			       struct ceph_osds *acting);
+int ceph_pg_to_acting_primary(struct ceph_osdmap *osdmap,
+			      const struct ceph_pg *raw_pgid);
 
 extern struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map,
 						    u64 id);