xref: /kernel/linux/linux-5.10/fs/ceph/mds_client.h (revision 8c2ecf20)
1/* SPDX-License-Identifier: GPL-2.0 */
2#ifndef _FS_CEPH_MDS_CLIENT_H
3#define _FS_CEPH_MDS_CLIENT_H
4
5#include <linux/completion.h>
6#include <linux/kref.h>
7#include <linux/list.h>
8#include <linux/mutex.h>
9#include <linux/rbtree.h>
10#include <linux/spinlock.h>
11#include <linux/refcount.h>
12#include <linux/utsname.h>
13#include <linux/ktime.h>
14
15#include <linux/ceph/types.h>
16#include <linux/ceph/messenger.h>
17#include <linux/ceph/mdsmap.h>
18#include <linux/ceph/auth.h>
19
20#include "metric.h"
21#include "super.h"
22
23/* The first 8 bits are reserved for old ceph releases */
24enum ceph_feature_type {
25	CEPHFS_FEATURE_MIMIC = 8,
26	CEPHFS_FEATURE_REPLY_ENCODING,
27	CEPHFS_FEATURE_RECLAIM_CLIENT,
28	CEPHFS_FEATURE_LAZY_CAP_WANTED,
29	CEPHFS_FEATURE_MULTI_RECONNECT,
30	CEPHFS_FEATURE_DELEG_INO,
31	CEPHFS_FEATURE_METRIC_COLLECT,
32
33	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_METRIC_COLLECT,
34};
35
36#define CEPHFS_FEATURES_CLIENT_SUPPORTED {	\
37	0, 1, 2, 3, 4, 5, 6, 7,			\
38	CEPHFS_FEATURE_MIMIC,			\
39	CEPHFS_FEATURE_REPLY_ENCODING,		\
40	CEPHFS_FEATURE_LAZY_CAP_WANTED,		\
41	CEPHFS_FEATURE_MULTI_RECONNECT,		\
42	CEPHFS_FEATURE_DELEG_INO,		\
43	CEPHFS_FEATURE_METRIC_COLLECT,		\
44}
45#define CEPHFS_FEATURES_CLIENT_REQUIRED {}
46
47/*
48 * Some lock dependencies:
49 *
50 * session->s_mutex
51 *         mdsc->mutex
52 *
53 *         mdsc->snap_rwsem
54 *
55 *         ci->i_ceph_lock
56 *                 mdsc->snap_flush_lock
57 *                 mdsc->cap_delay_lock
58 *
59 */
60
61struct ceph_fs_client;
62struct ceph_cap;
63
64/*
65 * parsed info about a single inode.  pointers are into the encoded
66 * on-wire structures within the mds reply message payload.
67 */
68struct ceph_mds_reply_info_in {
69	struct ceph_mds_reply_inode *in;
70	struct ceph_dir_layout dir_layout;
71	u32 symlink_len;
72	char *symlink;
73	u32 xattr_len;
74	char *xattr_data;
75	u64 inline_version;
76	u32 inline_len;
77	char *inline_data;
78	u32 pool_ns_len;
79	char *pool_ns_data;
80	u64 max_bytes;
81	u64 max_files;
82	s32 dir_pin;
83	struct ceph_timespec btime;
84	struct ceph_timespec snap_btime;
85	u64 change_attr;
86};
87
88struct ceph_mds_reply_dir_entry {
89	char                          *name;
90	u32                           name_len;
91	struct ceph_mds_reply_lease   *lease;
92	struct ceph_mds_reply_info_in inode;
93	loff_t			      offset;
94};
95
96/*
97 * parsed info about an mds reply, including information about
98 * either: 1) the target inode and/or its parent directory and dentry,
99 * and directory contents (for readdir results), or
100 * 2) the file range lock info (for fcntl F_GETLK results).
101 */
102struct ceph_mds_reply_info_parsed {
103	struct ceph_mds_reply_head    *head;
104
105	/* trace */
106	struct ceph_mds_reply_info_in diri, targeti;
107	struct ceph_mds_reply_dirfrag *dirfrag;
108	char                          *dname;
109	u32                           dname_len;
110	struct ceph_mds_reply_lease   *dlease;
111
112	/* extra */
113	union {
114		/* for fcntl F_GETLK results */
115		struct ceph_filelock *filelock_reply;
116
117		/* for readdir results */
118		struct {
119			struct ceph_mds_reply_dirfrag *dir_dir;
120			size_t			      dir_buf_size;
121			int                           dir_nr;
122			bool			      dir_end;
123			bool			      dir_complete;
124			bool			      hash_order;
125			bool			      offset_hash;
126			struct ceph_mds_reply_dir_entry  *dir_entries;
127		};
128
129		/* for create results */
130		struct {
131			bool has_create_ino;
132			u64 ino;
133		};
134	};
135
136	/* encoded blob describing snapshot contexts for certain
137	   operations (e.g., open) */
138	void *snapblob;
139	int snapblob_len;
140};
141
142
143/*
144 * cap releases are batched and sent to the MDS en masse.
145 *
146 * Account for per-message overhead of mds_cap_release header
147 * and __le32 for osd epoch barrier trailing field.
148 */
149#define CEPH_CAPS_PER_RELEASE ((PAGE_SIZE - sizeof(u32) -		\
150				sizeof(struct ceph_mds_cap_release)) /	\
151			        sizeof(struct ceph_mds_cap_item))
152
153
154/*
155 * state associated with each MDS<->client session
156 */
157enum {
158	CEPH_MDS_SESSION_NEW = 1,
159	CEPH_MDS_SESSION_OPENING = 2,
160	CEPH_MDS_SESSION_OPEN = 3,
161	CEPH_MDS_SESSION_HUNG = 4,
162	CEPH_MDS_SESSION_RESTARTING = 5,
163	CEPH_MDS_SESSION_RECONNECTING = 6,
164	CEPH_MDS_SESSION_CLOSING = 7,
165	CEPH_MDS_SESSION_CLOSED = 8,
166	CEPH_MDS_SESSION_REJECTED = 9,
167};
168
169struct ceph_mds_session {
170	struct ceph_mds_client *s_mdsc;
171	int               s_mds;
172	int               s_state;
173	unsigned long     s_ttl;      /* time until mds kills us */
174	unsigned long	  s_features;
175	u64               s_seq;      /* incoming msg seq # */
176	struct mutex      s_mutex;    /* serialize session messages */
177
178	struct ceph_connection s_con;
179
180	struct ceph_auth_handshake s_auth;
181
182	/* protected by s_gen_ttl_lock */
183	spinlock_t        s_gen_ttl_lock;
184	u32               s_cap_gen;  /* inc each time we get mds stale msg */
185	unsigned long     s_cap_ttl;  /* when session caps expire */
186
187	/* protected by s_cap_lock */
188	spinlock_t        s_cap_lock;
189	refcount_t        s_ref;
190	struct list_head  s_caps;     /* all caps issued by this session */
191	struct ceph_cap  *s_cap_iterator;
192	int               s_nr_caps;
193	int               s_num_cap_releases;
194	int		  s_cap_reconnect;
195	int		  s_readonly;
196	struct list_head  s_cap_releases; /* waiting cap_release messages */
197	struct work_struct s_cap_release_work;
198
199	/* See ceph_inode_info->i_dirty_item. */
200	struct list_head  s_cap_dirty;	      /* inodes w/ dirty caps */
201
202	/* See ceph_inode_info->i_flushing_item. */
203	struct list_head  s_cap_flushing;     /* inodes w/ flushing caps */
204
205	unsigned long     s_renew_requested; /* last time we sent a renew req */
206	u64               s_renew_seq;
207
208	struct list_head  s_waiting;  /* waiting requests */
209	struct list_head  s_unsafe;   /* unsafe requests */
210	struct xarray	  s_delegated_inos;
211};
212
213/*
214 * modes of choosing which MDS to send a request to
215 */
216enum {
217	USE_ANY_MDS,
218	USE_RANDOM_MDS,
219	USE_AUTH_MDS,   /* prefer authoritative mds for this metadata item */
220};
221
222struct ceph_mds_request;
223struct ceph_mds_client;
224
225/*
226 * request completion callback
227 */
228typedef void (*ceph_mds_request_callback_t) (struct ceph_mds_client *mdsc,
229					     struct ceph_mds_request *req);
230/*
231 * wait for request completion callback
232 */
233typedef int (*ceph_mds_request_wait_callback_t) (struct ceph_mds_client *mdsc,
234						 struct ceph_mds_request *req);
235
236/*
237 * an in-flight mds request
238 */
239struct ceph_mds_request {
240	u64 r_tid;                   /* transaction id */
241	struct rb_node r_node;
242	struct ceph_mds_client *r_mdsc;
243
244	struct kref       r_kref;
245	int r_op;                    /* mds op code */
246
247	/* operation on what? */
248	struct inode *r_inode;              /* arg1 */
249	struct dentry *r_dentry;            /* arg1 */
250	struct dentry *r_old_dentry;        /* arg2: rename from or link from */
251	struct inode *r_old_dentry_dir;     /* arg2: old dentry's parent dir */
252	char *r_path1, *r_path2;
253	struct ceph_vino r_ino1, r_ino2;
254
255	struct inode *r_parent;		    /* parent dir inode */
256	struct inode *r_target_inode;       /* resulting inode */
257
258#define CEPH_MDS_R_DIRECT_IS_HASH	(1) /* r_direct_hash is valid */
259#define CEPH_MDS_R_ABORTED		(2) /* call was aborted */
260#define CEPH_MDS_R_GOT_UNSAFE		(3) /* got an unsafe reply */
261#define CEPH_MDS_R_GOT_SAFE		(4) /* got a safe reply */
262#define CEPH_MDS_R_GOT_RESULT		(5) /* got a result */
263#define CEPH_MDS_R_DID_PREPOPULATE	(6) /* prepopulated readdir */
264#define CEPH_MDS_R_PARENT_LOCKED	(7) /* is r_parent->i_rwsem wlocked? */
265#define CEPH_MDS_R_ASYNC		(8) /* async request */
266	unsigned long	r_req_flags;
267
268	struct mutex r_fill_mutex;
269
270	union ceph_mds_request_args r_args;
271	int r_fmode;        /* file mode, if expecting cap */
272	kuid_t r_uid;
273	kgid_t r_gid;
274	int r_request_release_offset;
275	struct timespec64 r_stamp;
276
277	/* for choosing which mds to send this request to */
278	int r_direct_mode;
279	u32 r_direct_hash;      /* choose dir frag based on this dentry hash */
280
281	/* data payload is used for xattr ops */
282	struct ceph_pagelist *r_pagelist;
283
284	/* what caps shall we drop? */
285	int r_inode_drop, r_inode_unless;
286	int r_dentry_drop, r_dentry_unless;
287	int r_old_dentry_drop, r_old_dentry_unless;
288	struct inode *r_old_inode;
289	int r_old_inode_drop, r_old_inode_unless;
290
291	struct ceph_msg  *r_request;  /* original request */
292	struct ceph_msg  *r_reply;
293	struct ceph_mds_reply_info_parsed r_reply_info;
294	int r_err;
295
296
297	struct page *r_locked_page;
298	int r_dir_caps;
299	int r_num_caps;
300	u32               r_readdir_offset;
301
302	unsigned long r_timeout;  /* optional.  jiffies, 0 is "wait forever" */
303	unsigned long r_started;  /* start time to measure timeout against */
304	unsigned long r_start_latency;  /* start time to measure latency */
305	unsigned long r_end_latency;    /* finish time to measure latency */
306	unsigned long r_request_started; /* start time for mds request only,
307					    used to measure lease durations */
308
309	/* link unsafe requests to parent directory, for fsync */
310	struct inode	*r_unsafe_dir;
311	struct list_head r_unsafe_dir_item;
312
313	/* unsafe requests that modify the target inode */
314	struct list_head r_unsafe_target_item;
315
316	struct ceph_mds_session *r_session;
317
318	int               r_attempts;   /* resend attempts */
319	int               r_num_fwd;    /* number of forward attempts */
320	int               r_resend_mds; /* mds to resend to next, if any*/
321	u32               r_sent_on_mseq; /* cap mseq request was sent at*/
322	u64		  r_deleg_ino;
323
324	struct list_head  r_wait;
325	struct completion r_completion;
326	struct completion r_safe_completion;
327	ceph_mds_request_callback_t r_callback;
328	ceph_mds_request_wait_callback_t r_wait_for_completion;
329	struct list_head  r_unsafe_item;  /* per-session unsafe list item */
330
331	long long	  r_dir_release_cnt;
332	long long	  r_dir_ordered_cnt;
333	int		  r_readdir_cache_idx;
334
335	struct ceph_cap_reservation r_caps_reservation;
336};
337
338struct ceph_pool_perm {
339	struct rb_node node;
340	int perm;
341	s64 pool;
342	size_t pool_ns_len;
343	char pool_ns[];
344};
345
346struct ceph_snapid_map {
347	struct rb_node node;
348	struct list_head lru;
349	atomic_t ref;
350	u64 snap;
351	dev_t dev;
352	unsigned long last_used;
353};
354
355/*
356 * node for list of quotarealm inodes that are not visible from the filesystem
357 * mountpoint, but required to handle, e.g. quotas.
358 */
359struct ceph_quotarealm_inode {
360	struct rb_node node;
361	u64 ino;
362	unsigned long timeout; /* last time a lookup failed for this inode */
363	struct mutex mutex;
364	struct inode *inode;
365};
366
367struct cap_wait {
368	struct list_head	list;
369	u64			ino;
370	pid_t			tgid;
371	int			need;
372	int			want;
373};
374
375enum {
376       CEPH_MDSC_STOPPING_BEGIN = 1,
377       CEPH_MDSC_STOPPING_FLUSHED = 2,
378};
379
380/*
381 * mds client state
382 */
383struct ceph_mds_client {
384	struct ceph_fs_client  *fsc;
385	struct mutex            mutex;         /* all nested structures */
386
387	struct ceph_mdsmap      *mdsmap;
388	struct completion       safe_umount_waiters;
389	wait_queue_head_t       session_close_wq;
390	struct list_head        waiting_for_map;
391	int 			mdsmap_err;
392
393	struct ceph_mds_session **sessions;    /* NULL for mds if no session */
394	atomic_t		num_sessions;
395	int                     max_sessions;  /* len of sessions array */
396	int                     stopping;      /* true if shutting down */
397
398	atomic64_t		quotarealms_count; /* # realms with quota */
399	/*
400	 * We keep a list of inodes we don't see in the mountpoint but that we
401	 * need to track quota realms.
402	 */
403	struct rb_root		quotarealms_inodes;
404	struct mutex		quotarealms_inodes_mutex;
405
406	/*
407	 * snap_rwsem will cover cap linkage into snaprealms, and
408	 * realm snap contexts.  (later, we can do per-realm snap
409	 * contexts locks..)  the empty list contains realms with no
410	 * references (implying they contain no inodes with caps) that
411	 * should be destroyed.
412	 */
413	u64			last_snap_seq;
414	struct rw_semaphore     snap_rwsem;
415	struct rb_root          snap_realms;
416	struct list_head        snap_empty;
417	int			num_snap_realms;
418	spinlock_t              snap_empty_lock;  /* protect snap_empty */
419
420	u64                    last_tid;      /* most recent mds request */
421	u64                    oldest_tid;    /* oldest incomplete mds request,
422						 excluding setfilelock requests */
423	struct rb_root         request_tree;  /* pending mds requests */
424	struct delayed_work    delayed_work;  /* delayed work */
425	unsigned long    last_renew_caps;  /* last time we renewed our caps */
426	struct list_head cap_delay_list;   /* caps with delayed release */
427	spinlock_t       cap_delay_lock;   /* protects cap_delay_list */
428	struct list_head snap_flush_list;  /* cap_snaps ready to flush */
429	spinlock_t       snap_flush_lock;
430
431	u64               last_cap_flush_tid;
432	struct list_head  cap_flush_list;
433	struct list_head  cap_dirty_migrating; /* ...that are migration... */
434	int               num_cap_flushing; /* # caps we are flushing */
435	spinlock_t        cap_dirty_lock;   /* protects above items */
436	wait_queue_head_t cap_flushing_wq;
437
438	struct work_struct cap_reclaim_work;
439	atomic_t	   cap_reclaim_pending;
440
441	/*
442	 * Cap reservations
443	 *
444	 * Maintain a global pool of preallocated struct ceph_caps, referenced
445	 * by struct ceph_caps_reservations.  This ensures that we preallocate
446	 * memory needed to successfully process an MDS response.  (If an MDS
447	 * sends us cap information and we fail to process it, we will have
448	 * problems due to the client and MDS being out of sync.)
449	 *
450	 * Reservations are 'owned' by a ceph_cap_reservation context.
451	 */
452	spinlock_t	caps_list_lock;
453	struct		list_head caps_list; /* unused (reserved or
454						unreserved) */
455	struct		list_head cap_wait_list;
456	int		caps_total_count;    /* total caps allocated */
457	int		caps_use_count;      /* in use */
458	int		caps_use_max;	     /* max used caps */
459	int		caps_reserve_count;  /* unused, reserved */
460	int		caps_avail_count;    /* unused, unreserved */
461	int		caps_min_count;      /* keep at least this many
462						(unreserved) */
463	spinlock_t	  dentry_list_lock;
464	struct list_head  dentry_leases;     /* fifo list */
465	struct list_head  dentry_dir_leases; /* lru list */
466
467	struct ceph_client_metric metric;
468
469	spinlock_t		snapid_map_lock;
470	struct rb_root		snapid_map_tree;
471	struct list_head	snapid_map_lru;
472
473	struct rw_semaphore     pool_perm_rwsem;
474	struct rb_root		pool_perm_tree;
475
476	char nodename[__NEW_UTS_LEN + 1];
477};
478
479extern const char *ceph_mds_op_name(int op);
480
481extern bool check_session_state(struct ceph_mds_session *s);
482void inc_session_sequence(struct ceph_mds_session *s);
483
484extern struct ceph_mds_session *
485__ceph_lookup_mds_session(struct ceph_mds_client *, int mds);
486
487extern const char *ceph_session_state_name(int s);
488
489extern struct ceph_mds_session *
490ceph_get_mds_session(struct ceph_mds_session *s);
491extern void ceph_put_mds_session(struct ceph_mds_session *s);
492
493extern int ceph_send_msg_mds(struct ceph_mds_client *mdsc,
494			     struct ceph_msg *msg, int mds);
495
496extern int ceph_mdsc_init(struct ceph_fs_client *fsc);
497extern void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc);
498extern void ceph_mdsc_force_umount(struct ceph_mds_client *mdsc);
499extern void ceph_mdsc_destroy(struct ceph_fs_client *fsc);
500
501extern void ceph_mdsc_sync(struct ceph_mds_client *mdsc);
502
503extern void ceph_invalidate_dir_request(struct ceph_mds_request *req);
504extern int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req,
505					   struct inode *dir);
506extern struct ceph_mds_request *
507ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode);
508extern int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc,
509				    struct inode *dir,
510				    struct ceph_mds_request *req);
511extern int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
512				struct inode *dir,
513				struct ceph_mds_request *req);
514extern void ceph_mdsc_release_dir_caps(struct ceph_mds_request *req);
515extern void ceph_mdsc_release_dir_caps_no_check(struct ceph_mds_request *req);
516static inline void ceph_mdsc_get_request(struct ceph_mds_request *req)
517{
518	kref_get(&req->r_kref);
519}
520extern void ceph_mdsc_release_request(struct kref *kref);
521static inline void ceph_mdsc_put_request(struct ceph_mds_request *req)
522{
523	kref_put(&req->r_kref, ceph_mdsc_release_request);
524}
525
526extern void send_flush_mdlog(struct ceph_mds_session *s);
527extern void ceph_mdsc_iterate_sessions(struct ceph_mds_client *mdsc,
528				       void (*cb)(struct ceph_mds_session *),
529				       bool check_state);
530extern struct ceph_msg *ceph_create_session_msg(u32 op, u64 seq);
531extern void __ceph_queue_cap_release(struct ceph_mds_session *session,
532				    struct ceph_cap *cap);
533extern void ceph_flush_cap_releases(struct ceph_mds_client *mdsc,
534				    struct ceph_mds_session *session);
535extern void ceph_queue_cap_reclaim_work(struct ceph_mds_client *mdsc);
536extern void ceph_reclaim_caps_nr(struct ceph_mds_client *mdsc, int nr);
537extern int ceph_iterate_session_caps(struct ceph_mds_session *session,
538				     int (*cb)(struct inode *,
539					       struct ceph_cap *, void *),
540				     void *arg);
541extern void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc);
542
543static inline void ceph_mdsc_free_path(char *path, int len)
544{
545	if (!IS_ERR_OR_NULL(path))
546		__putname(path - (PATH_MAX - 1 - len));
547}
548
549extern char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *base,
550				  int stop_on_nosnap);
551
552extern void __ceph_mdsc_drop_dentry_lease(struct dentry *dentry);
553extern void ceph_mdsc_lease_send_msg(struct ceph_mds_session *session,
554				     struct dentry *dentry, char action,
555				     u32 seq);
556
557extern void ceph_mdsc_handle_mdsmap(struct ceph_mds_client *mdsc,
558				    struct ceph_msg *msg);
559extern void ceph_mdsc_handle_fsmap(struct ceph_mds_client *mdsc,
560				   struct ceph_msg *msg);
561
562extern struct ceph_mds_session *
563ceph_mdsc_open_export_target_session(struct ceph_mds_client *mdsc, int target);
564extern void ceph_mdsc_open_export_target_sessions(struct ceph_mds_client *mdsc,
565					  struct ceph_mds_session *session);
566
567extern int ceph_trim_caps(struct ceph_mds_client *mdsc,
568			  struct ceph_mds_session *session,
569			  int max_caps);
570
571static inline int ceph_wait_on_async_create(struct inode *inode)
572{
573	struct ceph_inode_info *ci = ceph_inode(inode);
574
575	return wait_on_bit(&ci->i_ceph_flags, CEPH_ASYNC_CREATE_BIT,
576			   TASK_INTERRUPTIBLE);
577}
578
579extern u64 ceph_get_deleg_ino(struct ceph_mds_session *session);
580extern int ceph_restore_deleg_ino(struct ceph_mds_session *session, u64 ino);
581#endif
582