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

Pull Ceph updates from Sage Weil:
 "The biggest chunk is a series of patches from Ilya that add support
  for new Ceph osd and crush map features, including some new tunables,
  primary affinity, and the new encoding that is needed for erasure
  coding support.  This brings things into parity with the server side
  and the looming firefly release.  There is also support for allocation
  hints in RBD that help limit fragmentation on the server side.

  There is also a series of patches from Zheng fixing NFS reexport,
  directory fragmentation support, flock vs fnctl behavior, and some
  issues with clustered MDS.

  Finally, there are some miscellaneous fixes from Yunchuan Wen for
  fscache, Fabian Frederick for ACLs, and from me for fsync(dirfd)
  behavior"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (79 commits)
  ceph: skip invalid dentry during dcache readdir
  libceph: dump pool {read,write}_tier to debugfs
  libceph: output primary affinity values on osdmap updates
  ceph: flush cap release queue when trimming session caps
  ceph: don't grabs open file reference for aborted request
  ceph: drop extra open file reference in ceph_atomic_open()
  ceph: preallocate buffer for readdir reply
  libceph: enable PRIMARY_AFFINITY feature bit
  libceph: redo ceph_calc_pg_primary() in terms of ceph_calc_pg_acting()
  libceph: add support for osd primary affinity
  libceph: add support for primary_temp mappings
  libceph: return primary from ceph_calc_pg_acting()
  libceph: switch ceph_calc_pg_acting() to new helpers
  libceph: introduce apply_temps() helper
  libceph: introduce pg_to_raw_osds() and raw_to_up_osds() helpers
  libceph: ceph_can_shift_osds(pool) and pool type defines
  libceph: ceph_osd_{exists,is_up,is_down}(osd) definitions
  libceph: enable OSDMAP_ENC feature bit
  libceph: primary_affinity decode bits
  libceph: primary_affinity infrastructure
  ...

6 files changed, 91 insertions, 12 deletions

diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index 138448f766b4..d12659ce550d 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -43,6 +43,13 @@
 #define CEPH_FEATURE_CRUSH_V2      (1ULL<<36)  /* new indep; SET_* steps */
 #define CEPH_FEATURE_EXPORT_PEER   (1ULL<<37)
 #define CEPH_FEATURE_OSD_ERASURE_CODES (1ULL<<38)
+#define CEPH_FEATURE_OSD_TMAP2OMAP (1ULL<<38)   /* overlap with EC */
+/* The process supports new-style OSDMap encoding. Monitors also use
+   this bit to determine if peers support NAK messages. */
+#define CEPH_FEATURE_OSDMAP_ENC    (1ULL<<39)
+#define CEPH_FEATURE_MDS_INLINE_DATA     (1ULL<<40)
+#define CEPH_FEATURE_CRUSH_TUNABLES3     (1ULL<<41)
+#define CEPH_FEATURE_OSD_PRIMARY_AFFINITY (1ULL<<41)  /* overlap w/ tunables3 */
 
 /*
  * The introduction of CEPH_FEATURE_OSD_SNAPMAPPER caused the feature
@@ -82,7 +89,10 @@ static inline u64 ceph_sanitize_features(u64 features)
          CEPH_FEATURE_OSDHASHPSPOOL |           \
          CEPH_FEATURE_OSD_CACHEPOOL |           \
          CEPH_FEATURE_CRUSH_V2 |                \
-         CEPH_FEATURE_EXPORT_PEER)
+         CEPH_FEATURE_EXPORT_PEER |             \
+         CEPH_FEATURE_OSDMAP_ENC |              \
+         CEPH_FEATURE_CRUSH_TUNABLES3 |         \
+         CEPH_FEATURE_OSD_PRIMARY_AFFINITY)
 
 #define CEPH_FEATURES_REQUIRED_DEFAULT   \
         (CEPH_FEATURE_NOSRCADDR |        \
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 25bfb0eff772..5f6db18d72e8 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -332,6 +332,7 @@ enum {
         CEPH_MDS_OP_LOOKUPHASH = 0x00102,
         CEPH_MDS_OP_LOOKUPPARENT = 0x00103,
         CEPH_MDS_OP_LOOKUPINO  = 0x00104,
+        CEPH_MDS_OP_LOOKUPNAME = 0x00105,
 
         CEPH_MDS_OP_SETXATTR   = 0x01105,
         CEPH_MDS_OP_RMXATTR    = 0x01106,
@@ -420,8 +421,8 @@ union ceph_mds_request_args {
         struct {
                 __u8 rule; /* currently fcntl or flock */
                 __u8 type; /* shared, exclusive, remove*/
+                __le64 owner; /* owner of the lock */
                 __le64 pid; /* process id requesting the lock */
-                __le64 pid_namespace;
                 __le64 start; /* initial location to lock */
                 __le64 length; /* num bytes to lock from start */
                 __u8 wait; /* will caller wait for lock to become available? */
@@ -532,8 +533,8 @@ struct ceph_filelock {
         __le64 start;/* file offset to start lock at */
         __le64 length; /* num bytes to lock; 0 for all following start */
         __le64 client; /* which client holds the lock */
+        __le64 owner; /* owner the lock */
         __le64 pid; /* process id holding the lock on the client */
-        __le64 pid_namespace;
         __u8 type; /* shared lock, exclusive lock, or unlock */
 } __attribute__ ((packed));
 
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index fd47e872ebcc..94ec69672164 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -43,7 +43,7 @@ struct ceph_osd {
 };
 
 
-#define CEPH_OSD_MAX_OP 2
+#define CEPH_OSD_MAX_OP 3
 
 enum ceph_osd_data_type {
         CEPH_OSD_DATA_TYPE_NONE = 0,
@@ -76,6 +76,7 @@ struct ceph_osd_data {
 
 struct ceph_osd_req_op {
         u16 op;           /* CEPH_OSD_OP_* */
+        u32 flags;        /* CEPH_OSD_OP_FLAG_* */
         u32 payload_len;
         union {
                 struct ceph_osd_data raw_data_in;
@@ -102,6 +103,10 @@ struct ceph_osd_req_op {
                         u32 timeout;
                         __u8 flag;
                 } watch;
+                struct {
+                        u64 expected_object_size;
+                        u64 expected_write_size;
+                } alloc_hint;
         };
 };
 
@@ -293,6 +298,10 @@ extern void osd_req_op_cls_init(struct ceph_osd_request *osd_req,
 extern void osd_req_op_watch_init(struct ceph_osd_request *osd_req,
                                         unsigned int which, u16 opcode,
                                         u64 cookie, u64 version, int flag);
+extern void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req,
+                                       unsigned int which,
+                                       u64 expected_object_size,
+                                       u64 expected_write_size);
 
 extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
                                                struct ceph_snap_context *snapc,
diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 49ff69f0746b..561ea896c657 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -41,6 +41,18 @@ struct ceph_pg_pool_info {
         char *name;
 };
 
+static inline bool ceph_can_shift_osds(struct ceph_pg_pool_info *pool)
+{
+        switch (pool->type) {
+        case CEPH_POOL_TYPE_REP:
+                return true;
+        case CEPH_POOL_TYPE_EC:
+                return false;
+        default:
+                BUG_ON(1);
+        }
+}
+
 struct ceph_object_locator {
         s64 pool;
 };
@@ -60,8 +72,16 @@ struct ceph_object_id {
 struct ceph_pg_mapping {
         struct rb_node node;
         struct ceph_pg pgid;
-        int len;
-        int osds[];
+
+        union {
+                struct {
+                        int len;
+                        int osds[];
+                } pg_temp;
+                struct {
+                        int osd;
+                } primary_temp;
+        };
 };
 
 struct ceph_osdmap {
@@ -78,12 +98,19 @@ struct ceph_osdmap {
         struct ceph_entity_addr *osd_addr;
 
         struct rb_root pg_temp;
+        struct rb_root primary_temp;
+
+        u32 *osd_primary_affinity;
+
         struct rb_root pg_pools;
         u32 pool_max;
 
         /* the CRUSH map specifies the mapping of placement groups to
          * the list of osds that store+replicate them. */
         struct crush_map *crush;
+
+        struct mutex crush_scratch_mutex;
+        int crush_scratch_ary[CEPH_PG_MAX_SIZE * 3];
 };
 
 static inline void ceph_oid_set_name(struct ceph_object_id *oid,
@@ -110,9 +137,21 @@ static inline void ceph_oid_copy(struct ceph_object_id *dest,
         dest->name_len = src->name_len;
 }
 
+static inline int 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)
 {
-        return (osd < map->max_osd) && (map->osd_state[osd] & CEPH_OSD_UP);
+        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)
+{
+        return !ceph_osd_is_up(map, osd);
 }
 
 static inline bool ceph_osdmap_flag(struct ceph_osdmap *map, int flag)
@@ -121,6 +160,7 @@ static inline bool ceph_osdmap_flag(struct ceph_osdmap *map, int flag)
 }
 
 extern char *ceph_osdmap_state_str(char *str, int len, int state);
+extern u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd);
 
 static inline struct ceph_entity_addr *ceph_osd_addr(struct ceph_osdmap *map,
                                                      int osd)
@@ -153,7 +193,7 @@ static inline int ceph_decode_pgid(void **p, void *end, struct ceph_pg *pgid)
         return 0;
 }
 
-extern struct ceph_osdmap *osdmap_decode(void **p, void *end);
+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);
@@ -172,7 +212,7 @@ extern int ceph_oloc_oid_to_pg(struct ceph_osdmap *osdmap,
 
 extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap,
                                struct ceph_pg pgid,
-                               int *acting);
+                               int *osds, int *primary);
 extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
                                 struct ceph_pg pgid);
 
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 96292df4041b..f20e0d8a2155 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -81,8 +81,9 @@ struct ceph_pg_v1 {
  */
 #define CEPH_NOPOOL  ((__u64) (-1))  /* pool id not defined */
 
-#define CEPH_PG_TYPE_REP     1
-#define CEPH_PG_TYPE_RAID4   2
+#define CEPH_POOL_TYPE_REP     1
+#define CEPH_POOL_TYPE_RAID4   2 /* never implemented */
+#define CEPH_POOL_TYPE_EC      3
 
 /*
  * stable_mod func is used to control number of placement groups.
@@ -133,6 +134,10 @@ extern const char *ceph_osd_state_name(int s);
 #define CEPH_OSD_IN  0x10000
 #define CEPH_OSD_OUT 0
 
+/* osd primary-affinity.  fixed point value: 0x10000 == baseline */
+#define CEPH_OSD_MAX_PRIMARY_AFFINITY 0x10000
+#define CEPH_OSD_DEFAULT_PRIMARY_AFFINITY 0x10000
+
 
 /*
  * osd map flag bits
@@ -227,6 +232,9 @@ enum {
         CEPH_OSD_OP_OMAPRMKEYS    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 24,
         CEPH_OSD_OP_OMAP_CMP      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 25,
 
+        /* hints */
+        CEPH_OSD_OP_SETALLOCHINT = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 35,
+
         /** multi **/
         CEPH_OSD_OP_CLONERANGE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_MULTI | 1,
         CEPH_OSD_OP_ASSERT_SRC_VERSION = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_MULTI | 2,
@@ -382,7 +390,7 @@ enum {
  */
 struct ceph_osd_op {
         __le16 op;           /* CEPH_OSD_OP_* */
-        __le32 flags;        /* CEPH_OSD_FLAG_* */
+        __le32 flags;        /* CEPH_OSD_OP_FLAG_* */
         union {
                 struct {
                         __le64 offset, length;
@@ -416,6 +424,10 @@ struct ceph_osd_op {
                         __le64 offset, length;
                         __le64 src_offset;
                 } __attribute__ ((packed)) clonerange;
+                struct {
+                        __le64 expected_object_size;
+                        __le64 expected_write_size;
+                } __attribute__ ((packed)) alloc_hint;
         };
         __le32 payload_len;
 } __attribute__ ((packed));
diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h
index acaa5615d634..4fad5f8ee01d 100644
--- a/include/linux/crush/crush.h
+++ b/include/linux/crush/crush.h
@@ -51,6 +51,7 @@ enum {
         CRUSH_RULE_SET_CHOOSELEAF_TRIES = 9, /* override chooseleaf_descend_once */
         CRUSH_RULE_SET_CHOOSE_LOCAL_TRIES = 10,
         CRUSH_RULE_SET_CHOOSE_LOCAL_FALLBACK_TRIES = 11,
+        CRUSH_RULE_SET_CHOOSELEAF_VARY_R = 12
 };
 
 /*
@@ -173,6 +174,12 @@ struct crush_map {
          * apply to a collision: in that case we will retry as we used
          * to. */
         __u32 chooseleaf_descend_once;
+
+        /* if non-zero, feed r into chooseleaf, bit-shifted right by (r-1)
+         * bits.  a value of 1 is best for new clusters.  for legacy clusters
+         * that want to limit reshuffling, a value of 3 or 4 will make the
+         * mappings line up a bit better with previous mappings. */
+        __u8 chooseleaf_vary_r;
 };