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

Pull Ceph updates from Sage Weil:
 "There is quite a bit here, including some overdue refactoring and
  cleanup on the mon_client and osd_client code from Ilya, scattered
  writeback support for CephFS and a pile of bug fixes from Zheng, and a
  few random cleanups and fixes from others"

[ I already decided not to pull this because of it having been rebased
  recently, but ended up changing my mind after all.  Next time I'll
  really hold people to it.  Oh well.   - Linus ]

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (34 commits)
  libceph: use KMEM_CACHE macro
  ceph: use kmem_cache_zalloc
  rbd: use KMEM_CACHE macro
  ceph: use lookup request to revalidate dentry
  ceph: kill ceph_get_dentry_parent_inode()
  ceph: fix security xattr deadlock
  ceph: don't request vxattrs from MDS
  ceph: fix mounting same fs multiple times
  ceph: remove unnecessary NULL check
  ceph: avoid updating directory inode's i_size accidentally
  ceph: fix race during filling readdir cache
  libceph: use sizeof_footer() more
  ceph: kill ceph_empty_snapc
  ceph: fix a wrong comparison
  ceph: replace CURRENT_TIME by current_fs_time()
  ceph: scattered page writeback
  libceph: add helper that duplicates last extent operation
  libceph: enable large, variable-sized OSD requests
  libceph: osdc->req_mempool should be backed by a slab pool
  libceph: make r_request msg_size calculation clearer
  ...

5 files changed, 45 insertions, 18 deletions

diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index 15151f3c4120..ae2f66833762 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -105,6 +105,7 @@ static inline u64 ceph_sanitize_features(u64 features)
  */
 #define CEPH_FEATURES_SUPPORTED_DEFAULT		\
 	(CEPH_FEATURE_NOSRCADDR |		\
+	 CEPH_FEATURE_SUBSCRIBE2 |		\
 	 CEPH_FEATURE_RECONNECT_SEQ |		\
 	 CEPH_FEATURE_PGID64 |			\
 	 CEPH_FEATURE_PGPOOL3 |			\
@@ -127,6 +128,7 @@ static inline u64 ceph_sanitize_features(u64 features)
 
 #define CEPH_FEATURES_REQUIRED_DEFAULT   \
 	(CEPH_FEATURE_NOSRCADDR |	 \
+	 CEPH_FEATURE_SUBSCRIBE2 |	 \
 	 CEPH_FEATURE_RECONNECT_SEQ |	 \
 	 CEPH_FEATURE_PGID64 |		 \
 	 CEPH_FEATURE_PGPOOL3 |		 \
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index d7d072a25c27..37f28bf55ce4 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -198,8 +198,8 @@ struct ceph_client_mount {
 #define CEPH_SUBSCRIBE_ONETIME    1  /* i want only 1 update after have */
 
 struct ceph_mon_subscribe_item {
-	__le64 have_version;    __le64 have;
-	__u8 onetime;
+	__le64 start;
+	__u8 flags;
 } __attribute__ ((packed));
 
 struct ceph_mon_subscribe_ack {
@@ -376,7 +376,8 @@ union ceph_mds_request_args {
 		__le32 stripe_count;         /* ... */
 		__le32 object_size;
 		__le32 file_replication;
-		__le32 unused;               /* used to be preferred osd */
+               __le32 mask;                 /* CEPH_CAP_* */
+               __le32 old_size;
 	} __attribute__ ((packed)) open;
 	struct {
 		__le32 flags;
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 3e3799cdc6e6..e7975e4681e1 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -47,7 +47,6 @@ struct ceph_options {
 	unsigned long mount_timeout;		/* jiffies */
 	unsigned long osd_idle_ttl;		/* jiffies */
 	unsigned long osd_keepalive_timeout;	/* jiffies */
-	unsigned long monc_ping_timeout;	/* jiffies */
 
 	/*
 	 * any type that can't be simply compared or doesn't need need
@@ -68,7 +67,12 @@ struct ceph_options {
 #define CEPH_MOUNT_TIMEOUT_DEFAULT	msecs_to_jiffies(60 * 1000)
 #define CEPH_OSD_KEEPALIVE_DEFAULT	msecs_to_jiffies(5 * 1000)
 #define CEPH_OSD_IDLE_TTL_DEFAULT	msecs_to_jiffies(60 * 1000)
-#define CEPH_MONC_PING_TIMEOUT_DEFAULT	msecs_to_jiffies(30 * 1000)
+
+#define CEPH_MONC_HUNT_INTERVAL		msecs_to_jiffies(3 * 1000)
+#define CEPH_MONC_PING_INTERVAL		msecs_to_jiffies(10 * 1000)
+#define CEPH_MONC_PING_TIMEOUT		msecs_to_jiffies(30 * 1000)
+#define CEPH_MONC_HUNT_BACKOFF		2
+#define CEPH_MONC_HUNT_MAX_MULT		10
 
 #define CEPH_MSG_MAX_FRONT_LEN	(16*1024*1024)
 #define CEPH_MSG_MAX_MIDDLE_LEN	(16*1024*1024)
diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h
index 81810dc21f06..e230e7ed60d3 100644
--- a/include/linux/ceph/mon_client.h
+++ b/include/linux/ceph/mon_client.h
@@ -68,18 +68,24 @@ struct ceph_mon_client {
 
 	bool hunting;
 	int cur_mon;                       /* last monitor i contacted */
-	unsigned long sub_sent, sub_renew_after;
+	unsigned long sub_renew_after;
+	unsigned long sub_renew_sent;
 	struct ceph_connection con;
 
+	bool had_a_connection;
+	int hunt_mult; /* [1..CEPH_MONC_HUNT_MAX_MULT] */
+
 	/* pending generic requests */
 	struct rb_root generic_request_tree;
 	int num_generic_requests;
 	u64 last_tid;
 
-	/* mds/osd map */
-	int want_mdsmap;
-	int want_next_osdmap; /* 1 = want, 2 = want+asked */
-	u32 have_osdmap, have_mdsmap;
+	/* subs, indexed with CEPH_SUB_* */
+	struct {
+		struct ceph_mon_subscribe_item item;
+		bool want;
+		u32 have; /* epoch */
+	} subs[3];
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *debugfs_file;
@@ -93,14 +99,23 @@ extern int ceph_monmap_contains(struct ceph_monmap *m,
 extern int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl);
 extern void ceph_monc_stop(struct ceph_mon_client *monc);
 
+enum {
+	CEPH_SUB_MDSMAP = 0,
+	CEPH_SUB_MONMAP,
+	CEPH_SUB_OSDMAP,
+};
+
+extern const char *ceph_sub_str[];
+
 /*
  * The model here is to indicate that we need a new map of at least
- * epoch @want, and also call in when we receive a map.  We will
+ * epoch @epoch, and also call in when we receive a map.  We will
  * periodically rerequest the map from the monitor cluster until we
  * get what we want.
  */
-extern int ceph_monc_got_mdsmap(struct ceph_mon_client *monc, u32 have);
-extern int ceph_monc_got_osdmap(struct ceph_mon_client *monc, u32 have);
+bool ceph_monc_want_map(struct ceph_mon_client *monc, int sub, u32 epoch,
+			bool continuous);
+void ceph_monc_got_map(struct ceph_mon_client *monc, int sub, u32 epoch);
 
 extern void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc);
 extern int ceph_monc_wait_osdmap(struct ceph_mon_client *monc, u32 epoch,
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 7506b485bb6d..4343df806710 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -43,7 +43,8 @@ struct ceph_osd {
 };
 
 
-#define CEPH_OSD_MAX_OP	3
+#define CEPH_OSD_SLAB_OPS	2
+#define CEPH_OSD_MAX_OPS	16
 
 enum ceph_osd_data_type {
 	CEPH_OSD_DATA_TYPE_NONE = 0,
@@ -77,7 +78,10 @@ struct ceph_osd_data {
 struct ceph_osd_req_op {
 	u16 op;           /* CEPH_OSD_OP_* */
 	u32 flags;        /* CEPH_OSD_OP_FLAG_* */
-	u32 payload_len;
+	u32 indata_len;   /* request */
+	u32 outdata_len;  /* reply */
+	s32 rval;
+
 	union {
 		struct ceph_osd_data raw_data_in;
 		struct {
@@ -136,7 +140,6 @@ struct ceph_osd_request {
 
 	/* request osd ops array  */
 	unsigned int		r_num_ops;
-	struct ceph_osd_req_op	r_ops[CEPH_OSD_MAX_OP];
 
 	/* these are updated on each send */
 	__le32           *r_request_osdmap_epoch;
@@ -148,8 +151,6 @@ struct ceph_osd_request {
 	struct ceph_eversion *r_request_reassert_version;
 
 	int               r_result;
-	int               r_reply_op_len[CEPH_OSD_MAX_OP];
-	s32               r_reply_op_result[CEPH_OSD_MAX_OP];
 	int               r_got_reply;
 	int		  r_linger;
 
@@ -174,6 +175,8 @@ struct ceph_osd_request {
 	unsigned long     r_stamp;            /* send OR check time */
 
 	struct ceph_snap_context *r_snapc;    /* snap context for writes */
+
+	struct ceph_osd_req_op r_ops[];
 };
 
 struct ceph_request_redirect {
@@ -263,6 +266,8 @@ extern void osd_req_op_extent_init(struct ceph_osd_request *osd_req,
 					u64 truncate_size, u32 truncate_seq);
 extern void osd_req_op_extent_update(struct ceph_osd_request *osd_req,
 					unsigned int which, u64 length);
+extern void osd_req_op_extent_dup_last(struct ceph_osd_request *osd_req,
+				       unsigned int which, u64 offset_inc);
 
 extern struct ceph_osd_data *osd_req_op_extent_osd_data(
 					struct ceph_osd_request *osd_req,