summaryrefslogtreecommitdiff
path: root/include/linux/ceph/libceph.h
blob: a8a574897d3c3ec0b8f685a430f0cbacf8c5872b (plain)
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
#ifndef _FS_CEPH_LIBCEPH_H
#define _FS_CEPH_LIBCEPH_H

#include <linux/ceph/ceph_debug.h>

#include <asm/unaligned.h>
#include <linux/backing-dev.h>
#include <linux/completion.h>
#include <linux/exportfs.h>
#include <linux/bug.h>
#include <linux/fs.h>
#include <linux/mempool.h>
#include <linux/pagemap.h>
#include <linux/wait.h>
#include <linux/writeback.h>
#include <linux/slab.h>

#include <linux/ceph/types.h>
#include <linux/ceph/messenger.h>
#include <linux/ceph/msgpool.h>
#include <linux/ceph/mon_client.h>
#include <linux/ceph/osd_client.h>
#include <linux/ceph/ceph_fs.h>
#include <linux/ceph/string_table.h>

/*
 * mount options
 */
#define CEPH_OPT_FSID             (1<<0)
#define CEPH_OPT_NOSHARE          (1<<1) /* don't share client with other sbs */
#define CEPH_OPT_MYIP             (1<<2) /* specified my ip */
#define CEPH_OPT_NOCRC            (1<<3) /* no data crc on writes */
#define CEPH_OPT_NOMSGAUTH	  (1<<4) /* don't require msg signing feat */
#define CEPH_OPT_TCP_NODELAY	  (1<<5) /* TCP_NODELAY on TCP sockets */
#define CEPH_OPT_NOMSGSIGN	  (1<<6) /* don't sign msgs */

#define CEPH_OPT_DEFAULT   (CEPH_OPT_TCP_NODELAY)

#define ceph_set_opt(client, opt) \
	(client)->options->flags |= CEPH_OPT_##opt;
#define ceph_test_opt(client, opt) \
	(!!((client)->options->flags & CEPH_OPT_##opt))

struct ceph_options {
	int flags;
	struct ceph_fsid fsid;
	struct ceph_entity_addr my_addr;
	unsigned long mount_timeout;		/* jiffies */
	unsigned long osd_idle_ttl;		/* jiffies */
	unsigned long osd_keepalive_timeout;	/* jiffies */

	/*
	 * any type that can't be simply compared or doesn't need need
	 * to be compared should go beyond this point,
	 * ceph_compare_options() should be updated accordingly
	 */

	struct ceph_entity_addr *mon_addr; /* should be the first
					      pointer type of args */
	int num_mon;
	char *name;
	struct ceph_crypto_key *key;
};

/*
 * defaults
 */
#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_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)

/*
 * Handle the largest possible rbd object in one message.
 * There is no limit on the size of cephfs objects, but it has to obey
 * rsize and wsize mount options anyway.
 */
#define CEPH_MSG_MAX_DATA_LEN	(32*1024*1024)

#define CEPH_AUTH_NAME_DEFAULT   "guest"

/*
 * Delay telling the MDS we no longer want caps, in case we reopen
 * the file.  Delay a minimum amount of time, even if we send a cap
 * message for some other reason.  Otherwise, take the oppotunity to
 * update the mds to avoid sending another message later.
 */
#define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT      5  /* cap release delay */
#define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT     60  /* cap release delay */

#define CEPH_CAP_RELEASE_SAFETY_DEFAULT        (CEPH_CAPS_PER_RELEASE * 4)

/* mount state */
enum {
	CEPH_MOUNT_MOUNTING,
	CEPH_MOUNT_MOUNTED,
	CEPH_MOUNT_UNMOUNTING,
	CEPH_MOUNT_UNMOUNTED,
	CEPH_MOUNT_SHUTDOWN,
};

static inline unsigned long ceph_timeout_jiffies(unsigned long timeout)
{
	return timeout ?: MAX_SCHEDULE_TIMEOUT;
}

struct ceph_mds_client;

/*
 * per client state
 *
 * possibly shared by multiple mount points, if they are
 * mounting the same ceph filesystem/cluster.
 */
struct ceph_client {
	struct ceph_fsid fsid;
	bool have_fsid;

	void *private;

	struct ceph_options *options;

	struct mutex mount_mutex;      /* serialize mount attempts */
	wait_queue_head_t auth_wq;
	int auth_err;

	int (*extra_mon_dispatch)(struct ceph_client *, struct ceph_msg *);

	u64 supported_features;
	u64 required_features;

	struct ceph_messenger msgr;   /* messenger instance */
	struct ceph_mon_client monc;
	struct ceph_osd_client osdc;

#ifdef CONFIG_DEBUG_FS
	struct dentry *debugfs_dir;
	struct dentry *debugfs_monmap;
	struct dentry *debugfs_osdmap;
	struct dentry *debugfs_options;
#endif
};

#define from_msgr(ms)	container_of(ms, struct ceph_client, msgr)


/*
 * snapshots
 */

/*
 * A "snap context" is the set of existing snapshots when we
 * write data.  It is used by the OSD to guide its COW behavior.
 *
 * The ceph_snap_context is refcounted, and attached to each dirty
 * page, indicating which context the dirty data belonged when it was
 * dirtied.
 */
struct ceph_snap_context {
	atomic_t nref;
	u64 seq;
	u32 num_snaps;
	u64 snaps[];
};

extern struct ceph_snap_context *ceph_create_snap_context(u32 snap_count,
					gfp_t gfp_flags);
extern struct ceph_snap_context *ceph_get_snap_context(
					struct ceph_snap_context *sc);
extern void ceph_put_snap_context(struct ceph_snap_context *sc);

/*
 * calculate the number of pages a given length and offset map onto,
 * if we align the data.
 */
static inline int calc_pages_for(u64 off, u64 len)
{
	return ((off+len+PAGE_SIZE-1) >> PAGE_SHIFT) -
		(off >> PAGE_SHIFT);
}

/*
 * These are not meant to be generic - an integer key is assumed.
 */
#define DEFINE_RB_INSDEL_FUNCS(name, type, keyfld, nodefld)		\
static void insert_##name(struct rb_root *root, type *t)		\
{									\
	struct rb_node **n = &root->rb_node;				\
	struct rb_node *parent = NULL;					\
									\
	BUG_ON(!RB_EMPTY_NODE(&t->nodefld));				\
									\
	while (*n) {							\
		type *cur = rb_entry(*n, type, nodefld);		\
									\
		parent = *n;						\
		if (t->keyfld < cur->keyfld)				\
			n = &(*n)->rb_left;				\
		else if (t->keyfld > cur->keyfld)			\
			n = &(*n)->rb_right;				\
		else							\
			BUG();						\
	}								\
									\
	rb_link_node(&t->nodefld, parent, n);				\
	rb_insert_color(&t->nodefld, root);				\
}									\
static void erase_##name(struct rb_root *root, type *t)			\
{									\
	BUG_ON(RB_EMPTY_NODE(&t->nodefld));				\
	rb_erase(&t->nodefld, root);					\
	RB_CLEAR_NODE(&t->nodefld);					\
}

#define DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld)		\
extern type __lookup_##name##_key;					\
static type *lookup_##name(struct rb_root *root,			\
			   typeof(__lookup_##name##_key.keyfld) key)	\
{									\
	struct rb_node *n = root->rb_node;				\
									\
	while (n) {							\
		type *cur = rb_entry(n, type, nodefld);			\
									\
		if (key < cur->keyfld)					\
			n = n->rb_left;					\
		else if (key > cur->keyfld)				\
			n = n->rb_right;				\
		else							\
			return cur;					\
	}								\
									\
	return NULL;							\
}

#define DEFINE_RB_FUNCS(name, type, keyfld, nodefld)			\
DEFINE_RB_INSDEL_FUNCS(name, type, keyfld, nodefld)			\
DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld)

extern struct kmem_cache *ceph_inode_cachep;
extern struct kmem_cache *ceph_cap_cachep;
extern struct kmem_cache *ceph_cap_flush_cachep;
extern struct kmem_cache *ceph_dentry_cachep;
extern struct kmem_cache *ceph_file_cachep;

/* ceph_common.c */
extern bool libceph_compatible(void *data);

extern const char *ceph_msg_type_name(int type);
extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid);
extern void *ceph_kvmalloc(size_t size, gfp_t flags);

extern struct ceph_options *ceph_parse_options(char *options,
			      const char *dev_name, const char *dev_name_end,
			      int (*parse_extra_token)(char *c, void *private),
			      void *private);
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_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);
extern int __ceph_open_session(struct ceph_client *client,
			       unsigned long started);
extern int ceph_open_session(struct ceph_client *client);

/* pagevec.c */
extern void ceph_release_page_vector(struct page **pages, int num_pages);

extern struct page **ceph_get_direct_page_vector(const void __user *data,
						 int num_pages,
						 bool write_page);
extern void ceph_put_page_vector(struct page **pages, int num_pages,
				 bool dirty);
extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
extern int ceph_copy_user_to_page_vector(struct page **pages,
					 const void __user *data,
					 loff_t off, size_t len);
extern void ceph_copy_to_page_vector(struct page **pages,
				    const void *data,
				    loff_t off, size_t len);
extern void ceph_copy_from_page_vector(struct page **pages,
				    void *data,
				    loff_t off, size_t len);
extern void ceph_zero_page_vector_range(int off, int len, struct page **pages);


#endif /* _FS_CEPH_SUPER_H */