[net-next-2.6.git] / fs / ceph / mds_client.h

#ifndef _FS_CEPH_MDS_CLIENT_H
#define _FS_CEPH_MDS_CLIENT_H

#include <linux/completion.h>
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/radix-tree.h>
#include <linux/spinlock.h>

#include "types.h"
#include "messenger.h"
#include "mdsmap.h"

/*
 * Some lock dependencies:
 *
 * session->s_mutex
 *         mdsc->mutex
 *
 *         mdsc->snap_rwsem
 *
 *         inode->i_lock
 *                 mdsc->snap_flush_lock
 *                 mdsc->cap_delay_lock
 *
 */

struct ceph_client;
struct ceph_cap;

/*
 * parsed info about a single inode.  pointers are into the encoded
 * on-wire structures within the mds reply message payload.
 */
struct ceph_mds_reply_info_in {
	struct ceph_mds_reply_inode *in;
	u32 symlink_len;
	char *symlink;
	u32 xattr_len;
	char *xattr_data;
};

/*
 * parsed info about an mds reply, including information about the
 * target inode and/or its parent directory and dentry, and directory
 * contents (for readdir results).
 */
struct ceph_mds_reply_info_parsed {
	struct ceph_mds_reply_head    *head;

	struct ceph_mds_reply_info_in diri, targeti;
	struct ceph_mds_reply_dirfrag *dirfrag;
	char                          *dname;
	u32                           dname_len;
	struct ceph_mds_reply_lease   *dlease;

	struct ceph_mds_reply_dirfrag *dir_dir;
	int                           dir_nr;
	char                          **dir_dname;
	u32                           *dir_dname_len;
	struct ceph_mds_reply_lease   **dir_dlease;
	struct ceph_mds_reply_info_in *dir_in;
	u8                            dir_complete, dir_end;

	/* encoded blob describing snapshot contexts for certain
	   operations (e.g., open) */
	void *snapblob;
	int snapblob_len;
};


/*
 * cap releases are batched and sent to the MDS en masse.
 */
#define CEPH_CAPS_PER_RELEASE ((PAGE_CACHE_SIZE -			\
				sizeof(struct ceph_mds_cap_release)) /	\
			       sizeof(struct ceph_mds_cap_item))


/*
 * state associated with each MDS<->client session
 */
enum {
	CEPH_MDS_SESSION_NEW = 1,
	CEPH_MDS_SESSION_OPENING = 2,
	CEPH_MDS_SESSION_OPEN = 3,
	CEPH_MDS_SESSION_HUNG = 4,
	CEPH_MDS_SESSION_CLOSING = 5,
	CEPH_MDS_SESSION_RESTARTING = 6,
	CEPH_MDS_SESSION_RECONNECTING = 7,
};

struct ceph_mds_session {
	struct ceph_mds_client *s_mdsc;
	int               s_mds;
	int               s_state;
	unsigned long     s_ttl;      /* time until mds kills us */
	u64               s_seq;      /* incoming msg seq # */
	struct mutex      s_mutex;    /* serialize session messages */

	struct ceph_connection s_con;

	/* protected by s_cap_lock */
	spinlock_t        s_cap_lock;
	u32               s_cap_gen;  /* inc each time we get mds stale msg */
	unsigned long     s_cap_ttl;  /* when session caps expire */
	struct list_head  s_caps;     /* all caps issued by this session */
	int               s_nr_caps, s_trim_caps;
	int               s_num_cap_releases;
	struct list_head  s_cap_releases; /* waiting cap_release messages */
	struct list_head  s_cap_releases_done; /* ready to send */

	/* protected by mutex */
	struct list_head  s_cap_flushing;     /* inodes w/ flushing caps */
	struct list_head  s_cap_snaps_flushing;
	unsigned long     s_renew_requested; /* last time we sent a renew req */
	u64               s_renew_seq;

	atomic_t          s_ref;
	struct list_head  s_waiting;  /* waiting requests */
	struct list_head  s_unsafe;   /* unsafe requests */
};

/*
 * modes of choosing which MDS to send a request to
 */
enum {
	USE_ANY_MDS,
	USE_RANDOM_MDS,
	USE_AUTH_MDS,   /* prefer authoritative mds for this metadata item */
};

struct ceph_mds_request;
struct ceph_mds_client;

/*
 * request completion callback
 */
typedef void (*ceph_mds_request_callback_t) (struct ceph_mds_client *mdsc,
					     struct ceph_mds_request *req);

/*
 * an in-flight mds request
 */
struct ceph_mds_request {
	u64 r_tid;                   /* transaction id */

	int r_op;                    /* mds op code */
	int r_mds;

	/* operation on what? */
	struct inode *r_inode;              /* arg1 */
	struct dentry *r_dentry;            /* arg1 */
	struct dentry *r_old_dentry;        /* arg2: rename from or link from */
	char *r_path1, *r_path2;
	struct ceph_vino r_ino1, r_ino2;

	struct inode *r_locked_dir; /* dir (if any) i_mutex locked by vfs */
	struct inode *r_target_inode;       /* resulting inode */

	union ceph_mds_request_args r_args;
	int r_fmode;        /* file mode, if expecting cap */

	/* for choosing which mds to send this request to */
	int r_direct_mode;
	u32 r_direct_hash;      /* choose dir frag based on this dentry hash */
	bool r_direct_is_hash;  /* true if r_direct_hash is valid */

	/* data payload is used for xattr ops */
	struct page **r_pages;
	int r_num_pages;
	int r_data_len;

	/* what caps shall we drop? */
	int r_inode_drop, r_inode_unless;
	int r_dentry_drop, r_dentry_unless;
	int r_old_dentry_drop, r_old_dentry_unless;
	struct inode *r_old_inode;
	int r_old_inode_drop, r_old_inode_unless;

	struct ceph_msg  *r_request;  /* original request */
	struct ceph_msg  *r_reply;
	struct ceph_mds_reply_info_parsed r_reply_info;
	int r_err;

	unsigned long r_timeout;  /* optional.  jiffies */
	unsigned long r_started;  /* start time to measure timeout against */
	unsigned long r_request_started; /* start time for mds request only,
					    used to measure lease durations */

	/* link unsafe requests to parent directory, for fsync */
	struct inode	*r_unsafe_dir;
	struct list_head r_unsafe_dir_item;

	struct ceph_mds_session *r_session;

	int               r_attempts;   /* resend attempts */
	int               r_num_fwd;    /* number of forward attempts */
	int               r_num_stale;
	int               r_resend_mds; /* mds to resend to next, if any*/

	atomic_t          r_ref;
	struct list_head  r_wait;
	struct completion r_completion;
	struct completion r_safe_completion;
	ceph_mds_request_callback_t r_callback;
	struct list_head  r_unsafe_item;  /* per-session unsafe list item */
	bool		  r_got_unsafe, r_got_safe;

	bool              r_did_prepopulate;
	u32               r_readdir_offset;

	struct ceph_cap_reservation r_caps_reservation;
	int r_num_caps;
};

/*
 * mds client state
 */
struct ceph_mds_client {
	struct ceph_client      *client;
	struct mutex            mutex;         /* all nested structures */

	struct ceph_mdsmap      *mdsmap;
	struct completion       safe_umount_waiters, session_close_waiters;
	struct list_head        waiting_for_map;

	struct ceph_mds_session **sessions;    /* NULL for mds if no session */
	int                     max_sessions;  /* len of s_mds_sessions */
	int                     stopping;      /* true if shutting down */

	/*
	 * snap_rwsem will cover cap linkage into snaprealms, and
	 * realm snap contexts.  (later, we can do per-realm snap
	 * contexts locks..)  the empty list contains realms with no
	 * references (implying they contain no inodes with caps) that
	 * should be destroyed.
	 */
	struct rw_semaphore     snap_rwsem;
	struct radix_tree_root  snap_realms;
	struct list_head        snap_empty;
	spinlock_t              snap_empty_lock;  /* protect snap_empty */

	u64                    last_tid;      /* most recent mds request */
	struct radix_tree_root request_tree;  /* pending mds requests */
	struct delayed_work    delayed_work;  /* delayed work */
	unsigned long    last_renew_caps;  /* last time we renewed our caps */
	struct list_head cap_delay_list;   /* caps with delayed release */
	spinlock_t       cap_delay_lock;   /* protects cap_delay_list */
	struct list_head snap_flush_list;  /* cap_snaps ready to flush */
	spinlock_t       snap_flush_lock;

	u64               cap_flush_seq;
	struct list_head  cap_dirty;        /* inodes with dirty caps */
	int               num_cap_flushing; /* # caps we are flushing */
	spinlock_t        cap_dirty_lock;   /* protects above items */
	wait_queue_head_t cap_flushing_wq;

	struct dentry 	  *debugfs_file;

	spinlock_t	  dentry_lru_lock;
	struct list_head  dentry_lru;
	int		  num_dentry;
};

extern const char *ceph_mds_op_name(int op);

extern struct ceph_mds_session *
__ceph_lookup_mds_session(struct ceph_mds_client *, int mds);

static inline struct ceph_mds_session *
ceph_get_mds_session(struct ceph_mds_session *s)
{
	atomic_inc(&s->s_ref);
	return s;
}

extern void ceph_put_mds_session(struct ceph_mds_session *s);

extern int ceph_send_msg_mds(struct ceph_mds_client *mdsc,
			     struct ceph_msg *msg, int mds);

extern void ceph_mdsc_init(struct ceph_mds_client *mdsc,
			   struct ceph_client *client);
extern void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc);
extern void ceph_mdsc_stop(struct ceph_mds_client *mdsc);

extern void ceph_mdsc_sync(struct ceph_mds_client *mdsc);

extern void ceph_mdsc_lease_release(struct ceph_mds_client *mdsc,
				    struct inode *inode,
				    struct dentry *dn, int mask);

extern struct ceph_mds_request *
ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode);
extern void ceph_mdsc_submit_request(struct ceph_mds_client *mdsc,
				     struct ceph_mds_request *req);
extern int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
				struct inode *dir,
				struct ceph_mds_request *req);
static inline void ceph_mdsc_get_request(struct ceph_mds_request *req)
{
	atomic_inc(&req->r_ref);
}
extern void ceph_mdsc_put_request(struct ceph_mds_request *req);

extern void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc);

extern char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *base,
				  int stop_on_nosnap);

extern void __ceph_mdsc_drop_dentry_lease(struct dentry *dentry);
extern void ceph_mdsc_lease_send_msg(struct ceph_mds_session *session,
				     struct inode *inode,
				     struct dentry *dentry, char action,
				     u32 seq);

extern void ceph_mdsc_handle_map(struct ceph_mds_client *mdsc,
				 struct ceph_msg *msg);

#endif
Commit	Line	Data
2f2dc053 SW	1	#ifndef _FS_CEPH_MDS_CLIENT_H
	2	#define _FS_CEPH_MDS_CLIENT_H
	3
	4	#include <linux/completion.h>
	5	#include <linux/list.h>
	6	#include <linux/mutex.h>
	7	#include <linux/radix-tree.h>
	8	#include <linux/spinlock.h>
	9
	10	#include "types.h"
	11	#include "messenger.h"
	12	#include "mdsmap.h"
	13
	14	/*
	15	* Some lock dependencies:
	16	*
	17	* session->s_mutex
	18	* mdsc->mutex
	19	*
	20	* mdsc->snap_rwsem
	21	*
	22	* inode->i_lock
	23	* mdsc->snap_flush_lock
	24	* mdsc->cap_delay_lock
	25	*
	26	*/
	27
	28	struct ceph_client;
	29	struct ceph_cap;
	30
	31	/*
	32	* parsed info about a single inode. pointers are into the encoded
	33	* on-wire structures within the mds reply message payload.
	34	*/
	35	struct ceph_mds_reply_info_in {
	36	struct ceph_mds_reply_inode *in;
	37	u32 symlink_len;
	38	char *symlink;
	39	u32 xattr_len;
	40	char *xattr_data;
	41	};
	42
	43	/*
	44	* parsed info about an mds reply, including information about the
	45	* target inode and/or its parent directory and dentry, and directory
	46	* contents (for readdir results).
	47	*/
	48	struct ceph_mds_reply_info_parsed {
	49	struct ceph_mds_reply_head *head;
	50
	51	struct ceph_mds_reply_info_in diri, targeti;
	52	struct ceph_mds_reply_dirfrag *dirfrag;
	53	char *dname;
	54	u32 dname_len;
	55	struct ceph_mds_reply_lease *dlease;
	56
	57	struct ceph_mds_reply_dirfrag *dir_dir;
	58	int dir_nr;
	59	char **dir_dname;
	60	u32 *dir_dname_len;
	61	struct ceph_mds_reply_lease **dir_dlease;
	62	struct ceph_mds_reply_info_in *dir_in;
	63	u8 dir_complete, dir_end;
	64
65	/* encoded blob describing snapshot contexts for certain
66	operations (e.g., open) */
67	void *snapblob;
68	int snapblob_len;
69	};
70
71
72	/*
73	* cap releases are batched and sent to the MDS en masse.
74	*/
75	#define CEPH_CAPS_PER_RELEASE ((PAGE_CACHE_SIZE - \
76	sizeof(struct ceph_mds_cap_release)) / \
77	sizeof(struct ceph_mds_cap_item))
78
79
80	/*
81	* state associated with each MDS<->client session
82	*/
83	enum {
84	CEPH_MDS_SESSION_NEW = 1,
85	CEPH_MDS_SESSION_OPENING = 2,
86	CEPH_MDS_SESSION_OPEN = 3,
87	CEPH_MDS_SESSION_HUNG = 4,
88	CEPH_MDS_SESSION_CLOSING = 5,
89	CEPH_MDS_SESSION_RESTARTING = 6,
90	CEPH_MDS_SESSION_RECONNECTING = 7,
91	};
92
93	struct ceph_mds_session {
94	struct ceph_mds_client *s_mdsc;
95	int s_mds;
96	int s_state;
97	unsigned long s_ttl; /* time until mds kills us */
98	u64 s_seq; /* incoming msg seq # */
99	struct mutex s_mutex; /* serialize session messages */
100
101	struct ceph_connection s_con;
102
103	/* protected by s_cap_lock */
104	spinlock_t s_cap_lock;
105	u32 s_cap_gen; /* inc each time we get mds stale msg */
106	unsigned long s_cap_ttl; /* when session caps expire */
107	struct list_head s_caps; /* all caps issued by this session */
108	int s_nr_caps, s_trim_caps;
109	int s_num_cap_releases;
110	struct list_head s_cap_releases; /* waiting cap_release messages */
111	struct list_head s_cap_releases_done; /* ready to send */
112
113	/* protected by mutex */
114	struct list_head s_cap_flushing; /* inodes w/ flushing caps */
115	struct list_head s_cap_snaps_flushing;
116	unsigned long s_renew_requested; /* last time we sent a renew req */
117	u64 s_renew_seq;
118
119	atomic_t s_ref;
120	struct list_head s_waiting; /* waiting requests */
121	struct list_head s_unsafe; /* unsafe requests */
122	};
123
124	/*
125	* modes of choosing which MDS to send a request to
126	*/
127	enum {
128	USE_ANY_MDS,
129	USE_RANDOM_MDS,
130	USE_AUTH_MDS, /* prefer authoritative mds for this metadata item */
131	};
132
133	struct ceph_mds_request;
134	struct ceph_mds_client;
135
136	/*
137	* request completion callback
138	*/
139	typedef void (ceph_mds_request_callback_t) (struct ceph_mds_client mdsc,
140	struct ceph_mds_request *req);
141
142	/*
143	* an in-flight mds request
144	*/
145	struct ceph_mds_request {
146	u64 r_tid; /* transaction id */
147
148	int r_op; /* mds op code */
149	int r_mds;
150
151	/* operation on what? */
152	struct inode r_inode; / arg1 */
153	struct dentry r_dentry; / arg1 */
154	struct dentry r_old_dentry; / arg2: rename from or link from */
155	char r_path1, r_path2;
156	struct ceph_vino r_ino1, r_ino2;
157
158	struct inode r_locked_dir; / dir (if any) i_mutex locked by vfs */
159	struct inode r_target_inode; / resulting inode */
160
161	union ceph_mds_request_args r_args;
162	int r_fmode; /* file mode, if expecting cap */
163
164	/* for choosing which mds to send this request to */
165	int r_direct_mode;
166	u32 r_direct_hash; /* choose dir frag based on this dentry hash */
167	bool r_direct_is_hash; /* true if r_direct_hash is valid */
168
169	/* data payload is used for xattr ops */
170	struct page **r_pages;
171	int r_num_pages;
172	int r_data_len;
173
174	/* what caps shall we drop? */
175	int r_inode_drop, r_inode_unless;
176	int r_dentry_drop, r_dentry_unless;
177	int r_old_dentry_drop, r_old_dentry_unless;
178	struct inode *r_old_inode;
179	int r_old_inode_drop, r_old_inode_unless;
180
181	struct ceph_msg r_request; / original request */
182	struct ceph_msg *r_reply;
183	struct ceph_mds_reply_info_parsed r_reply_info;
184	int r_err;
185
186	unsigned long r_timeout; /* optional. jiffies */
187	unsigned long r_started; /* start time to measure timeout against */
188	unsigned long r_request_started; /* start time for mds request only,
189	used to measure lease durations */
190
191	/* link unsafe requests to parent directory, for fsync */
192	struct inode *r_unsafe_dir;
193	struct list_head r_unsafe_dir_item;
194
195	struct ceph_mds_session *r_session;
196
197	int r_attempts; /* resend attempts */
198	int r_num_fwd; /* number of forward attempts */
199	int r_num_stale;
200	int r_resend_mds; /* mds to resend to next, if any*/
201
202	atomic_t r_ref;
203	struct list_head r_wait;
204	struct completion r_completion;
205	struct completion r_safe_completion;
206	ceph_mds_request_callback_t r_callback;
207	struct list_head r_unsafe_item; /* per-session unsafe list item */
208	bool r_got_unsafe, r_got_safe;
209
210	bool r_did_prepopulate;
211	u32 r_readdir_offset;
212
213	struct ceph_cap_reservation r_caps_reservation;
214	int r_num_caps;
215	};
216
217	/*
218	* mds client state
219	*/
220	struct ceph_mds_client {
221	struct ceph_client *client;
222	struct mutex mutex; /* all nested structures */
223
224	struct ceph_mdsmap *mdsmap;
225	struct completion safe_umount_waiters, session_close_waiters;
226	struct list_head waiting_for_map;
227
228	struct ceph_mds_session *sessions; / NULL for mds if no session */
229	int max_sessions; /* len of s_mds_sessions */
230	int stopping; /* true if shutting down */
231
232	/*
233	* snap_rwsem will cover cap linkage into snaprealms, and
234	* realm snap contexts. (later, we can do per-realm snap
235	* contexts locks..) the empty list contains realms with no
236	* references (implying they contain no inodes with caps) that
237	* should be destroyed.
238	*/
239	struct rw_semaphore snap_rwsem;
240	struct radix_tree_root snap_realms;
241	struct list_head snap_empty;
242	spinlock_t snap_empty_lock; /* protect snap_empty */
243
244	u64 last_tid; /* most recent mds request */
245	struct radix_tree_root request_tree; /* pending mds requests */
246	struct delayed_work delayed_work; /* delayed work */
247	unsigned long last_renew_caps; /* last time we renewed our caps */
248	struct list_head cap_delay_list; /* caps with delayed release */
249	spinlock_t cap_delay_lock; /* protects cap_delay_list */
250	struct list_head snap_flush_list; /* cap_snaps ready to flush */
251	spinlock_t snap_flush_lock;
252
253	u64 cap_flush_seq;
254	struct list_head cap_dirty; /* inodes with dirty caps */
255	int num_cap_flushing; /* # caps we are flushing */
256	spinlock_t cap_dirty_lock; /* protects above items */
257	wait_queue_head_t cap_flushing_wq;
258
259	struct dentry *debugfs_file;
260
261	spinlock_t dentry_lru_lock;
262	struct list_head dentry_lru;
263	int num_dentry;
264	};
265
266	extern const char *ceph_mds_op_name(int op);
267
268	extern struct ceph_mds_session *
269	__ceph_lookup_mds_session(struct ceph_mds_client *, int mds);
270
271	static inline struct ceph_mds_session *
272	ceph_get_mds_session(struct ceph_mds_session *s)
273	{
274	atomic_inc(&s->s_ref);
275	return s;
276	}
277
278	extern void ceph_put_mds_session(struct ceph_mds_session *s);
279
280	extern int ceph_send_msg_mds(struct ceph_mds_client *mdsc,
281	struct ceph_msg *msg, int mds);
282
283	extern void ceph_mdsc_init(struct ceph_mds_client *mdsc,
284	struct ceph_client *client);
285	extern void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc);
286	extern void ceph_mdsc_stop(struct ceph_mds_client *mdsc);
287
288	extern void ceph_mdsc_sync(struct ceph_mds_client *mdsc);
289
290	extern void ceph_mdsc_lease_release(struct ceph_mds_client *mdsc,
291	struct inode *inode,
292	struct dentry *dn, int mask);
293
294	extern struct ceph_mds_request *
295	ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode);
296	extern void ceph_mdsc_submit_request(struct ceph_mds_client *mdsc,
297	struct ceph_mds_request *req);
298	extern int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
299	struct inode *dir,
300	struct ceph_mds_request *req);
301	static inline void ceph_mdsc_get_request(struct ceph_mds_request *req)
302	{
303	atomic_inc(&req->r_ref);
304	}
305	extern void ceph_mdsc_put_request(struct ceph_mds_request *req);
306
307	extern void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc);
308
309	extern char ceph_mdsc_build_path(struct dentry dentry, int plen, u64 base,
310	int stop_on_nosnap);
311
312	extern void __ceph_mdsc_drop_dentry_lease(struct dentry *dentry);
313	extern void ceph_mdsc_lease_send_msg(struct ceph_mds_session *session,
314	struct inode *inode,
315	struct dentry *dentry, char action,
316	u32 seq);
317
318	extern void ceph_mdsc_handle_map(struct ceph_mds_client *mdsc,
319	struct ceph_msg *msg);
320
321	#endif