1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
|
#ifndef _FS_CEPH_MDS_CLIENT_H
#define _FS_CEPH_MDS_CLIENT_H
#include <linux/completion.h>
#include <linux/kref.h>
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/rbtree.h>
#include <linux/spinlock.h>
#include <linux/ceph/types.h>
#include <linux/ceph/messenger.h>
#include <linux/ceph/mdsmap.h>
#include <linux/ceph/auth.h>
/*
* Some lock dependencies:
*
* session->s_mutex
* mdsc->mutex
*
* mdsc->snap_rwsem
*
* ci->i_ceph_lock
* mdsc->snap_flush_lock
* mdsc->cap_delay_lock
*
*/
struct ceph_fs_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;
struct ceph_dir_layout dir_layout;
u32 symlink_len;
char *symlink;
u32 xattr_len;
char *xattr_data;
u64 inline_version;
u32 inline_len;
char *inline_data;
u32 pool_ns_len;
char *pool_ns_data;
};
struct ceph_mds_reply_dir_entry {
char *name;
u32 name_len;
struct ceph_mds_reply_lease *lease;
struct ceph_mds_reply_info_in inode;
loff_t offset;
};
/*
* parsed info about an mds reply, including information about
* either: 1) the target inode and/or its parent directory and dentry,
* and directory contents (for readdir results), or
* 2) the file range lock info (for fcntl F_GETLK results).
*/
struct ceph_mds_reply_info_parsed {
struct ceph_mds_reply_head *head;
/* trace */
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;
/* extra */
union {
/* for fcntl F_GETLK results */
struct ceph_filelock *filelock_reply;
/* for readdir results */
struct {
struct ceph_mds_reply_dirfrag *dir_dir;
size_t dir_buf_size;
int dir_nr;
bool dir_complete;
bool dir_end;
bool hash_order;
struct ceph_mds_reply_dir_entry *dir_entries;
};
/* for create results */
struct {
bool has_create_ino;
u64 ino;
};
};
/* 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_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,
CEPH_MDS_SESSION_REJECTED = 8,
};
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;
struct ceph_auth_handshake s_auth;
/* protected by s_gen_ttl_lock */
spinlock_t s_gen_ttl_lock;
u32 s_cap_gen; /* inc each time we get mds stale msg */
unsigned long s_cap_ttl; /* when session caps expire */
/* protected by s_cap_lock */
spinlock_t s_cap_lock;
struct list_head s_caps; /* all caps issued by this session */
int s_nr_caps, s_trim_caps;
int s_num_cap_releases;
int s_cap_reconnect;
int s_readonly;
struct list_head s_cap_releases; /* waiting cap_release messages */
struct ceph_cap *s_cap_iterator;
/* protected by mutex */
struct list_head s_cap_flushing; /* inodes w/ flushing caps */
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);
/*
* wait for request completion callback
*/
typedef int (*ceph_mds_request_wait_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 */
struct rb_node r_node;
struct ceph_mds_client *r_mdsc;
int r_op; /* mds op code */
/* operation on what? */
struct inode *r_inode; /* arg1 */
struct dentry *r_dentry; /* arg1 */
struct dentry *r_old_dentry; /* arg2: rename from or link from */
struct inode *r_old_dentry_dir; /* arg2: old dentry's parent dir */
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 */
struct mutex r_fill_mutex;
union ceph_mds_request_args r_args;
int r_fmode; /* file mode, if expecting cap */
kuid_t r_uid;
kgid_t r_gid;
struct timespec r_stamp;
/* 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 ceph_pagelist *r_pagelist;
/* 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 */
int r_request_release_offset;
struct ceph_msg *r_reply;
struct ceph_mds_reply_info_parsed r_reply_info;
struct page *r_locked_page;
int r_err;
bool r_aborted;
unsigned long r_timeout; /* optional. jiffies, 0 is "wait forever" */
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;
/* unsafe requests that modify the target inode */
struct list_head r_unsafe_target_item;
struct ceph_mds_session *r_session;
int r_attempts; /* resend attempts */
int r_num_fwd; /* number of forward attempts */
int r_resend_mds; /* mds to resend to next, if any*/
u32 r_sent_on_mseq; /* cap mseq request was sent at*/
struct kref r_kref;
struct list_head r_wait;
struct completion r_completion;
struct completion r_safe_completion;
ceph_mds_request_callback_t r_callback;
ceph_mds_request_wait_callback_t r_wait_for_completion;
struct list_head r_unsafe_item; /* per-session unsafe list item */
bool r_got_unsafe, r_got_safe, r_got_result;
bool r_did_prepopulate;
long long r_dir_release_cnt;
long long r_dir_ordered_cnt;
int r_readdir_cache_idx;
u32 r_readdir_offset;
struct ceph_cap_reservation r_caps_reservation;
int r_num_caps;
};
struct ceph_pool_perm {
struct rb_node node;
int perm;
s64 pool;
size_t pool_ns_len;
char pool_ns[];
};
/*
* mds client state
*/
struct ceph_mds_client {
struct ceph_fs_client *fsc;
struct mutex mutex; /* all nested structures */
struct ceph_mdsmap *mdsmap;
struct completion safe_umount_waiters;
wait_queue_head_t session_close_wq;
struct list_head waiting_for_map;
int mdsmap_err;
struct ceph_mds_session **sessions; /* NULL for mds if no session */
atomic_t num_sessions;
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.
*/
u64 last_snap_seq;
struct rw_semaphore snap_rwsem;
struct rb_root snap_realms;
struct list_head snap_empty;
spinlock_t snap_empty_lock; /* protect snap_empty */
u64 last_tid; /* most recent mds request */
u64 oldest_tid; /* oldest incomplete mds request,
excluding setfilelock requests */
struct rb_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 last_cap_flush_tid;
struct list_head cap_flush_list;
struct list_head cap_dirty; /* inodes with dirty caps */
struct list_head cap_dirty_migrating; /* ...that are migration... */
int num_cap_flushing; /* # caps we are flushing */
spinlock_t
|