Merge tag 'ceph-for-4.12-rc1' of git://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "The two main items are support for disabling automatic rbd exclusive
  lock transfers from myself and the long awaited -ENOSPC handling
  series from Jeff.

  The former will allow rbd users to take advantage of exclusive lock's
  built-in blacklist/break-lock functionality while staying in control
  of who owns the lock. With the latter in place, we will abort
  filesystem writes on -ENOSPC instead of having them block
  indefinitely.

  Beyond that we've got the usual pile of filesystem fixes from Zheng,
  some refcount_t conversion patches from Elena and a patch for an
  ancient open() flags handling bug from Alexander"

* tag 'ceph-for-4.12-rc1' of git://github.com/ceph/ceph-client: (31 commits)
  ceph: fix memory leak in __ceph_setxattr()
  ceph: fix file open flags on ppc64
  ceph: choose readdir frag based on previous readdir reply
  rbd: exclusive map option
  rbd: return ResponseMessage result from rbd_handle_request_lock()
  rbd: kill rbd_is_lock_supported()
  rbd: support updating the lock cookie without releasing the lock
  rbd: store lock cookie
  rbd: ignore unlock errors
  rbd: fix error handling around rbd_init_disk()
  rbd: move rbd_unregister_watch() call into rbd_dev_image_release()
  rbd: move rbd_dev_destroy() call out of rbd_dev_image_release()
  ceph: when seeing write errors on an inode, switch to sync writes
  Revert "ceph: SetPageError() for writeback pages if writepages fails"
  ceph: handle epoch barriers in cap messages
  libceph: add an epoch_barrier field to struct ceph_osd_client
  libceph: abort already submitted but abortable requests when map or pool goes full
  libceph: allow requests to return immediately on full conditions if caller wishes
  libceph: remove req->r_replay_version
  ceph: make seeky readdir more efficient
  ...

7 files changed, 38 insertions, 13 deletions

diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index ae2f66833762..fd8b2953c78f 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -105,8 +105,10 @@ static inline u64 ceph_sanitize_features(u64 features)
  */
 #define CEPH_FEATURES_SUPPORTED_DEFAULT		\
 	(CEPH_FEATURE_NOSRCADDR |		\
+	 CEPH_FEATURE_FLOCK |			\
 	 CEPH_FEATURE_SUBSCRIBE2 |		\
 	 CEPH_FEATURE_RECONNECT_SEQ |		\
+	 CEPH_FEATURE_DIRLAYOUTHASH |		\
 	 CEPH_FEATURE_PGID64 |			\
 	 CEPH_FEATURE_PGPOOL3 |			\
 	 CEPH_FEATURE_OSDENC |			\
@@ -114,11 +116,13 @@ static inline u64 ceph_sanitize_features(u64 features)
 	 CEPH_FEATURE_MSG_AUTH |		\
 	 CEPH_FEATURE_CRUSH_TUNABLES2 |		\
 	 CEPH_FEATURE_REPLY_CREATE_INODE |	\
+	 CEPH_FEATURE_MDSENC |			\
 	 CEPH_FEATURE_OSDHASHPSPOOL |		\
 	 CEPH_FEATURE_OSD_CACHEPOOL |		\
 	 CEPH_FEATURE_CRUSH_V2 |		\
 	 CEPH_FEATURE_EXPORT_PEER |		\
 	 CEPH_FEATURE_OSDMAP_ENC |		\
+	 CEPH_FEATURE_MDS_INLINE_DATA |		\
 	 CEPH_FEATURE_CRUSH_TUNABLES3 |		\
 	 CEPH_FEATURE_OSD_PRIMARY_AFFINITY |	\
 	 CEPH_FEATURE_MSGR_KEEPALIVE2 |		\
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index f4b2ee18f38c..ad078ebe25d6 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -365,6 +365,19 @@ extern const char *ceph_mds_op_name(int op);
 #define CEPH_READDIR_FRAG_END		(1<<0)
 #define CEPH_READDIR_FRAG_COMPLETE	(1<<8)
 #define CEPH_READDIR_HASH_ORDER		(1<<9)
+#define CEPH_READDIR_OFFSET_HASH	(1<<10)
+
+/*
+ * open request flags
+ */
+#define CEPH_O_RDONLY		00000000
+#define CEPH_O_WRONLY		00000001
+#define CEPH_O_RDWR		00000002
+#define CEPH_O_CREAT		00000100
+#define CEPH_O_EXCL		00000200
+#define CEPH_O_TRUNC		00001000
+#define CEPH_O_DIRECTORY	00200000
+#define CEPH_O_NOFOLLOW		00400000
 
 union ceph_mds_request_args {
 	struct {
@@ -384,6 +397,7 @@ union ceph_mds_request_args {
 		__le32 max_entries;          /* how many dentries to grab */
 		__le32 max_bytes;
 		__le16 flags;
+		__le32 offset_hash;
 	} __attribute__ ((packed)) readdir;
 	struct {
 		__le32 mode;
diff --git a/include/linux/ceph/cls_lock_client.h b/include/linux/ceph/cls_lock_client.h
index 84884d8d4710..0594d3bba774 100644
--- a/include/linux/ceph/cls_lock_client.h
+++ b/include/linux/ceph/cls_lock_client.h
@@ -37,6 +37,11 @@ int ceph_cls_break_lock(struct ceph_osd_client *osdc,
 			struct ceph_object_locator *oloc,
 			char *lock_name, char *cookie,
 			struct ceph_entity_name *locker);
+int ceph_cls_set_cookie(struct ceph_osd_client *osdc,
+			struct ceph_object_id *oid,
+			struct ceph_object_locator *oloc,
+			char *lock_name, u8 type, char *old_cookie,
+			char *tag, char *new_cookie);
 
 void ceph_free_lockers(struct ceph_locker *lockers, u32 num_lockers);
 
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 88cd5dc8e238..3229ae6c7846 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -14,6 +14,7 @@
 #include <linux/wait.h>
 #include <linux/writeback.h>
 #include <linux/slab.h>
+#include <linux/refcount.h>
 
 #include <linux/ceph/types.h>
 #include <linux/ceph/messenger.h>
@@ -161,7 +162,7 @@ struct ceph_client {
  * dirtied.
  */
 struct ceph_snap_context {
-	atomic_t nref;
+	refcount_t nref;
 	u64 seq;
 	u32 num_snaps;
 	u64 snaps[];
@@ -262,10 +263,7 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client);
 extern void ceph_destroy_options(struct ceph_options *opt);
 extern int ceph_compare_options(struct ceph_options *new_opt,
 				struct ceph_client *client);
-extern struct ceph_client *ceph_create_client(struct ceph_options *opt,
-					      void *private,
-					      u64 supported_features,
-					      u64 required_features);
+struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private);
 struct ceph_entity_addr *ceph_client_addr(struct ceph_client *client);
 u64 ceph_client_gid(struct ceph_client *client);
 extern void ceph_destroy_client(struct ceph_client *client);
diff --git a/include/linux/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h
index 8ed5dc505fbb..d5f783f3226a 100644
--- a/include/linux/ceph/mdsmap.h
+++ b/include/linux/ceph/mdsmap.h
@@ -25,6 +25,7 @@ struct ceph_mdsmap {
 	u32 m_session_autoclose;        /* seconds */
 	u64 m_max_file_size;
 	u32 m_max_mds;                  /* size of m_addr, m_state arrays */
+	int m_num_mds;
 	struct ceph_mds_info *m_info;
 
 	/* which object pools file data can be stored in */
@@ -40,7 +41,7 @@ struct ceph_mdsmap {
 static inline struct ceph_entity_addr *
 ceph_mdsmap_get_addr(struct ceph_mdsmap *m, int w)
 {
-	if (w >= m->m_max_mds)
+	if (w >= m->m_num_mds)
 		return NULL;
 	return &m->m_info[w].addr;
 }
@@ -48,14 +49,14 @@ ceph_mdsmap_get_addr(struct ceph_mdsmap *m, int w)
 static inline int ceph_mdsmap_get_state(struct ceph_mdsmap *m, int w)
 {
 	BUG_ON(w < 0);
-	if (w >= m->m_max_mds)
+	if (w >= m->m_num_mds)
 		return CEPH_MDS_STATE_DNE;
 	return m->m_info[w].state;
 }
 
 static inline bool ceph_mdsmap_is_laggy(struct ceph_mdsmap *m, int w)
 {
-	if (w >= 0 && w < m->m_max_mds)
+	if (w >= 0 && w < m->m_num_mds)
 		return m->m_info[w].laggy;
 	return false;
 }
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index c125b5d9e13c..85650b415e73 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -5,6 +5,7 @@
 #include <linux/kref.h>
 #include <linux/mempool.h>
 #include <linux/rbtree.h>
+#include <linux/refcount.h>
 
 #include <linux/ceph/types.h>
 #include <linux/ceph/osdmap.h>
@@ -27,7 +28,7 @@ typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *);
 
 /* a given osd we're communicating with */
 struct ceph_osd {
-	atomic_t o_ref;
+	refcount_t o_ref;
 	struct ceph_osd_client *o_osdc;
 	int o_osd;
 	int o_incarnation;
@@ -186,12 +187,12 @@ struct ceph_osd_request {
 	struct timespec r_mtime;              /* ditto */
 	u64 r_data_offset;                    /* ditto */
 	bool r_linger;                        /* don't resend on failure */
+	bool r_abort_on_full;		      /* return ENOSPC when full */
 
 	/* internal */
 	unsigned long r_stamp;                /* jiffies, send or check time */
 	unsigned long r_start_stamp;          /* jiffies */
 	int r_attempts;
-	struct ceph_eversion r_replay_version; /* aka reassert_version */
 	u32 r_last_force_resend;
 	u32 r_map_dne_bound;
 
@@ -266,6 +267,7 @@ struct ceph_osd_client {
 	struct rb_root         osds;          /* osds */
 	struct list_head       osd_lru;       /* idle osds */
 	spinlock_t             osd_lru_lock;
+	u32		       epoch_barrier;
 	struct ceph_osd        homeless_osd;
 	atomic64_t             last_tid;      /* tid of last request */
 	u64                    last_linger_id;
@@ -304,6 +306,7 @@ extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc,
 				   struct ceph_msg *msg);
 extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc,
 				 struct ceph_msg *msg);
+void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb);
 
 extern void osd_req_op_init(struct ceph_osd_request *osd_req,
 			    unsigned int which, u16 opcode, u32 flags);
diff --git a/include/linux/ceph/pagelist.h b/include/linux/ceph/pagelist.h
index 13d71fe18b0c..75a7db21457d 100644
--- a/include/linux/ceph/pagelist.h
+++ b/include/linux/ceph/pagelist.h
@@ -2,7 +2,7 @@
 #define __FS_CEPH_PAGELIST_H
 
 #include <asm/byteorder.h>
-#include <linux/atomic.h>
+#include <linux/refcount.h>
 #include <linux/list.h>
 #include <linux/types.h>
 
@@ -13,7 +13,7 @@ struct ceph_pagelist {
 	size_t room;
 	struct list_head free_list;
 	size_t num_pages_free;
-	atomic_t refcnt;
+	refcount_t refcnt;
 };
 
 struct ceph_pagelist_cursor {
@@ -30,7 +30,7 @@ static inline void ceph_pagelist_init(struct ceph_pagelist *pl)
 	pl->room = 0;
 	INIT_LIST_HEAD(&pl->free_list);
 	pl->num_pages_free = 0;
-	atomic_set(&pl->refcnt, 1);
+	refcount_set(&pl->refcnt, 1);
 }
 
 extern void ceph_pagelist_release(struct ceph_pagelist *pl);