blob: 6e748573e0c665db2abeab7a1093f1af72271905 [file] [log] [blame]
Linus Torvalds1da177e2005-04-16 15:20:36 -07001/*
2 * linux/fs/lockd/svclock.c
3 *
4 * Handling of server-side locks, mostly of the blocked variety.
5 * This is the ugliest part of lockd because we tread on very thin ice.
6 * GRANT and CANCEL calls may get stuck, meet in mid-flight, etc.
7 * IMNSHO introducing the grant callback into the NLM protocol was one
8 * of the worst ideas Sun ever had. Except maybe for the idea of doing
9 * NFS file locking at all.
10 *
11 * I'm trying hard to avoid race conditions by protecting most accesses
12 * to a file's list of blocked locks through a semaphore. The global
13 * list of blocked locks is not protected in this fashion however.
14 * Therefore, some functions (such as the RPC callback for the async grant
15 * call) move blocked locks towards the head of the list *while some other
16 * process might be traversing it*. This should not be a problem in
17 * practice, because this will only cause functions traversing the list
18 * to visit some blocks twice.
19 *
20 * Copyright (C) 1996, Olaf Kirch <okir@monad.swb.de>
21 */
22
Linus Torvalds1da177e2005-04-16 15:20:36 -070023#include <linux/types.h>
24#include <linux/errno.h>
25#include <linux/kernel.h>
26#include <linux/sched.h>
27#include <linux/smp_lock.h>
28#include <linux/sunrpc/clnt.h>
29#include <linux/sunrpc/svc.h>
30#include <linux/lockd/nlm.h>
31#include <linux/lockd/lockd.h>
32
33#define NLMDBG_FACILITY NLMDBG_SVCLOCK
34
35#ifdef CONFIG_LOCKD_V4
36#define nlm_deadlock nlm4_deadlock
37#else
38#define nlm_deadlock nlm_lck_denied
39#endif
40
Trond Myklebust6849c0c2006-03-20 13:44:39 -050041static void nlmsvc_release_block(struct nlm_block *block);
Linus Torvalds1da177e2005-04-16 15:20:36 -070042static void nlmsvc_insert_block(struct nlm_block *block, unsigned long);
Olaf Kirch68a2d762006-10-04 02:15:57 -070043static void nlmsvc_remove_block(struct nlm_block *block);
Trond Myklebust963d8fe2006-01-03 09:55:04 +010044
Trond Myklebust5e1abf82006-03-20 13:44:39 -050045static int nlmsvc_setgrantargs(struct nlm_rqst *call, struct nlm_lock *lock);
46static void nlmsvc_freegrantargs(struct nlm_rqst *call);
Trond Myklebust963d8fe2006-01-03 09:55:04 +010047static const struct rpc_call_ops nlmsvc_grant_ops;
Linus Torvalds1da177e2005-04-16 15:20:36 -070048
49/*
50 * The list of blocked locks to retry
51 */
Olaf Kirch68a2d762006-10-04 02:15:57 -070052static LIST_HEAD(nlm_blocked);
Linus Torvalds1da177e2005-04-16 15:20:36 -070053
54/*
55 * Insert a blocked lock into the global list
56 */
57static void
58nlmsvc_insert_block(struct nlm_block *block, unsigned long when)
59{
Olaf Kirch68a2d762006-10-04 02:15:57 -070060 struct nlm_block *b;
61 struct list_head *pos;
Linus Torvalds1da177e2005-04-16 15:20:36 -070062
63 dprintk("lockd: nlmsvc_insert_block(%p, %ld)\n", block, when);
Olaf Kirch68a2d762006-10-04 02:15:57 -070064 if (list_empty(&block->b_list)) {
65 kref_get(&block->b_count);
66 } else {
67 list_del_init(&block->b_list);
68 }
69
70 pos = &nlm_blocked;
Linus Torvalds1da177e2005-04-16 15:20:36 -070071 if (when != NLM_NEVER) {
72 if ((when += jiffies) == NLM_NEVER)
73 when ++;
Olaf Kirch68a2d762006-10-04 02:15:57 -070074 list_for_each(pos, &nlm_blocked) {
75 b = list_entry(pos, struct nlm_block, b_list);
76 if (time_after(b->b_when,when) || b->b_when == NLM_NEVER)
77 break;
78 }
79 /* On normal exit from the loop, pos == &nlm_blocked,
80 * so we will be adding to the end of the list - good
81 */
82 }
Linus Torvalds1da177e2005-04-16 15:20:36 -070083
Olaf Kirch68a2d762006-10-04 02:15:57 -070084 list_add_tail(&block->b_list, pos);
Linus Torvalds1da177e2005-04-16 15:20:36 -070085 block->b_when = when;
Linus Torvalds1da177e2005-04-16 15:20:36 -070086}
87
88/*
89 * Remove a block from the global list
90 */
Olaf Kirch68a2d762006-10-04 02:15:57 -070091static inline void
Linus Torvalds1da177e2005-04-16 15:20:36 -070092nlmsvc_remove_block(struct nlm_block *block)
93{
Olaf Kirch68a2d762006-10-04 02:15:57 -070094 if (!list_empty(&block->b_list)) {
95 list_del_init(&block->b_list);
96 nlmsvc_release_block(block);
Linus Torvalds1da177e2005-04-16 15:20:36 -070097 }
Linus Torvalds1da177e2005-04-16 15:20:36 -070098}
99
100/*
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500101 * Find a block for a given lock
Linus Torvalds1da177e2005-04-16 15:20:36 -0700102 */
103static struct nlm_block *
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500104nlmsvc_lookup_block(struct nlm_file *file, struct nlm_lock *lock)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700105{
Olaf Kirch68a2d762006-10-04 02:15:57 -0700106 struct nlm_block *block;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700107 struct file_lock *fl;
108
109 dprintk("lockd: nlmsvc_lookup_block f=%p pd=%d %Ld-%Ld ty=%d\n",
110 file, lock->fl.fl_pid,
111 (long long)lock->fl.fl_start,
112 (long long)lock->fl.fl_end, lock->fl.fl_type);
Olaf Kirch68a2d762006-10-04 02:15:57 -0700113 list_for_each_entry(block, &nlm_blocked, b_list) {
Trond Myklebust92737232006-03-20 13:44:45 -0500114 fl = &block->b_call->a_args.lock.fl;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700115 dprintk("lockd: check f=%p pd=%d %Ld-%Ld ty=%d cookie=%s\n",
116 block->b_file, fl->fl_pid,
117 (long long)fl->fl_start,
118 (long long)fl->fl_end, fl->fl_type,
Trond Myklebust92737232006-03-20 13:44:45 -0500119 nlmdbg_cookie2a(&block->b_call->a_args.cookie));
Linus Torvalds1da177e2005-04-16 15:20:36 -0700120 if (block->b_file == file && nlm_compare_locks(fl, &lock->fl)) {
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500121 kref_get(&block->b_count);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700122 return block;
123 }
124 }
125
126 return NULL;
127}
128
129static inline int nlm_cookie_match(struct nlm_cookie *a, struct nlm_cookie *b)
130{
131 if(a->len != b->len)
132 return 0;
133 if(memcmp(a->data,b->data,a->len))
134 return 0;
135 return 1;
136}
137
138/*
139 * Find a block with a given NLM cookie.
140 */
141static inline struct nlm_block *
Olaf Kirch39be4502006-10-04 02:16:03 -0700142nlmsvc_find_block(struct nlm_cookie *cookie)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700143{
144 struct nlm_block *block;
145
Olaf Kirch68a2d762006-10-04 02:15:57 -0700146 list_for_each_entry(block, &nlm_blocked, b_list) {
Olaf Kirch39be4502006-10-04 02:16:03 -0700147 if (nlm_cookie_match(&block->b_call->a_args.cookie,cookie))
Olaf Kirch68a2d762006-10-04 02:15:57 -0700148 goto found;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700149 }
150
Olaf Kirch68a2d762006-10-04 02:15:57 -0700151 return NULL;
152
153found:
Olaf Kirch39be4502006-10-04 02:16:03 -0700154 dprintk("nlmsvc_find_block(%s): block=%p\n", nlmdbg_cookie2a(cookie), block);
Olaf Kirch68a2d762006-10-04 02:15:57 -0700155 kref_get(&block->b_count);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700156 return block;
157}
158
159/*
160 * Create a block and initialize it.
161 *
162 * Note: we explicitly set the cookie of the grant reply to that of
163 * the blocked lock request. The spec explicitly mentions that the client
164 * should _not_ rely on the callback containing the same cookie as the
165 * request, but (as I found out later) that's because some implementations
166 * do just this. Never mind the standards comittees, they support our
167 * logging industries.
Olaf Kirch39be4502006-10-04 02:16:03 -0700168 *
169 * 10 years later: I hope we can safely ignore these old and broken
170 * clients by now. Let's fix this so we can uniquely identify an incoming
171 * GRANTED_RES message by cookie, without having to rely on the client's IP
172 * address. --okir
Linus Torvalds1da177e2005-04-16 15:20:36 -0700173 */
174static inline struct nlm_block *
175nlmsvc_create_block(struct svc_rqst *rqstp, struct nlm_file *file,
176 struct nlm_lock *lock, struct nlm_cookie *cookie)
177{
178 struct nlm_block *block;
179 struct nlm_host *host;
Trond Myklebust92737232006-03-20 13:44:45 -0500180 struct nlm_rqst *call = NULL;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700181
182 /* Create host handle for callback */
Olaf Kirchdb4e4c92006-10-04 02:15:52 -0700183 host = nlmsvc_lookup_host(rqstp, lock->caller, lock->len);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700184 if (host == NULL)
185 return NULL;
186
Trond Myklebust92737232006-03-20 13:44:45 -0500187 call = nlm_alloc_call(host);
188 if (call == NULL)
189 return NULL;
190
Linus Torvalds1da177e2005-04-16 15:20:36 -0700191 /* Allocate memory for block, and initialize arguments */
Trond Myklebust92737232006-03-20 13:44:45 -0500192 block = kzalloc(sizeof(*block), GFP_KERNEL);
193 if (block == NULL)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700194 goto failed;
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500195 kref_init(&block->b_count);
Olaf Kirch68a2d762006-10-04 02:15:57 -0700196 INIT_LIST_HEAD(&block->b_list);
197 INIT_LIST_HEAD(&block->b_flist);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700198
Trond Myklebust92737232006-03-20 13:44:45 -0500199 if (!nlmsvc_setgrantargs(call, lock))
Linus Torvalds1da177e2005-04-16 15:20:36 -0700200 goto failed_free;
201
202 /* Set notifier function for VFS, and init args */
Trond Myklebust92737232006-03-20 13:44:45 -0500203 call->a_args.lock.fl.fl_flags |= FL_SLEEP;
204 call->a_args.lock.fl.fl_lmops = &nlmsvc_lock_operations;
Olaf Kirch39be4502006-10-04 02:16:03 -0700205 nlmclnt_next_cookie(&call->a_args.cookie);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700206
207 dprintk("lockd: created block %p...\n", block);
208
209 /* Create and initialize the block */
210 block->b_daemon = rqstp->rq_server;
211 block->b_host = host;
212 block->b_file = file;
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500213 file->f_count++;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700214
215 /* Add to file's list of blocks */
Olaf Kirch68a2d762006-10-04 02:15:57 -0700216 list_add(&block->b_flist, &file->f_blocks);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700217
218 /* Set up RPC arguments for callback */
Trond Myklebust92737232006-03-20 13:44:45 -0500219 block->b_call = call;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700220 call->a_flags = RPC_TASK_ASYNC;
Trond Myklebust92737232006-03-20 13:44:45 -0500221 call->a_block = block;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700222
223 return block;
224
225failed_free:
226 kfree(block);
227failed:
Trond Myklebust92737232006-03-20 13:44:45 -0500228 nlm_release_call(call);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700229 return NULL;
230}
231
232/*
233 * Delete a block. If the lock was cancelled or the grant callback
234 * failed, unlock is set to 1.
235 * It is the caller's responsibility to check whether the file
236 * can be closed hereafter.
237 */
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500238static int nlmsvc_unlink_block(struct nlm_block *block)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700239{
Trond Myklebust09c79382006-03-20 13:44:38 -0500240 int status;
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500241 dprintk("lockd: unlinking block %p...\n", block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700242
243 /* Remove block from list */
Trond Myklebust92737232006-03-20 13:44:45 -0500244 status = posix_unblock_lock(block->b_file->f_file, &block->b_call->a_args.lock.fl);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700245 nlmsvc_remove_block(block);
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500246 return status;
247}
Linus Torvalds1da177e2005-04-16 15:20:36 -0700248
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500249static void nlmsvc_free_block(struct kref *kref)
250{
251 struct nlm_block *block = container_of(kref, struct nlm_block, b_count);
252 struct nlm_file *file = block->b_file;
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500253
254 dprintk("lockd: freeing block %p...\n", block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700255
256 /* Remove block from file's list of blocks */
Neil Brown89e63ef2006-10-04 02:16:06 -0700257 mutex_lock(&file->f_mutex);
Olaf Kirch68a2d762006-10-04 02:15:57 -0700258 list_del_init(&block->b_flist);
Neil Brown89e63ef2006-10-04 02:16:06 -0700259 mutex_unlock(&file->f_mutex);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700260
Trond Myklebust92737232006-03-20 13:44:45 -0500261 nlmsvc_freegrantargs(block->b_call);
262 nlm_release_call(block->b_call);
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500263 nlm_release_file(block->b_file);
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500264 kfree(block->b_fl);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700265 kfree(block);
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500266}
267
268static void nlmsvc_release_block(struct nlm_block *block)
269{
270 if (block != NULL)
271 kref_put(&block->b_count, nlmsvc_free_block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700272}
273
Olaf Kirchf2af7932006-10-04 02:15:59 -0700274/*
275 * Loop over all blocks and delete blocks held by
276 * a matching host.
277 */
278void nlmsvc_traverse_blocks(struct nlm_host *host,
279 struct nlm_file *file,
280 nlm_host_match_fn_t match)
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500281{
Olaf Kirch68a2d762006-10-04 02:15:57 -0700282 struct nlm_block *block, *next;
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500283
284restart:
Neil Brown89e63ef2006-10-04 02:16:06 -0700285 mutex_lock(&file->f_mutex);
Olaf Kirch68a2d762006-10-04 02:15:57 -0700286 list_for_each_entry_safe(block, next, &file->f_blocks, b_flist) {
Olaf Kirchf2af7932006-10-04 02:15:59 -0700287 if (!match(block->b_host, host))
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500288 continue;
Olaf Kirch68a2d762006-10-04 02:15:57 -0700289 /* Do not destroy blocks that are not on
290 * the global retry list - why? */
291 if (list_empty(&block->b_list))
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500292 continue;
293 kref_get(&block->b_count);
Neil Brown89e63ef2006-10-04 02:16:06 -0700294 mutex_unlock(&file->f_mutex);
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500295 nlmsvc_unlink_block(block);
296 nlmsvc_release_block(block);
297 goto restart;
298 }
Neil Brown89e63ef2006-10-04 02:16:06 -0700299 mutex_unlock(&file->f_mutex);
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500300}
301
Linus Torvalds1da177e2005-04-16 15:20:36 -0700302/*
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500303 * Initialize arguments for GRANTED call. The nlm_rqst structure
304 * has been cleared already.
305 */
306static int nlmsvc_setgrantargs(struct nlm_rqst *call, struct nlm_lock *lock)
307{
308 locks_copy_lock(&call->a_args.lock.fl, &lock->fl);
309 memcpy(&call->a_args.lock.fh, &lock->fh, sizeof(call->a_args.lock.fh));
Serge E. Hallyne9ff3992006-10-02 02:18:11 -0700310 call->a_args.lock.caller = utsname()->nodename;
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500311 call->a_args.lock.oh.len = lock->oh.len;
312
313 /* set default data area */
314 call->a_args.lock.oh.data = call->a_owner;
315 call->a_args.lock.svid = lock->fl.fl_pid;
316
317 if (lock->oh.len > NLMCLNT_OHSIZE) {
318 void *data = kmalloc(lock->oh.len, GFP_KERNEL);
Trond Myklebust92737232006-03-20 13:44:45 -0500319 if (!data)
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500320 return 0;
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500321 call->a_args.lock.oh.data = (u8 *) data;
322 }
323
324 memcpy(call->a_args.lock.oh.data, lock->oh.data, lock->oh.len);
325 return 1;
326}
327
328static void nlmsvc_freegrantargs(struct nlm_rqst *call)
329{
Trond Myklebust92737232006-03-20 13:44:45 -0500330 if (call->a_args.lock.oh.data != call->a_owner)
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500331 kfree(call->a_args.lock.oh.data);
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500332}
333
334/*
Marc Eshel2b36f412006-11-28 16:26:47 -0500335 * Deferred lock request handling for non-blocking lock
336 */
337static u32
338nlmsvc_defer_lock_rqst(struct svc_rqst *rqstp, struct nlm_block *block)
339{
340 u32 status = nlm_lck_denied_nolocks;
341
342 block->b_flags |= B_QUEUED;
343
344 nlmsvc_insert_block(block, NLM_TIMEOUT);
345
346 block->b_cache_req = &rqstp->rq_chandle;
347 if (rqstp->rq_chandle.defer) {
348 block->b_deferred_req =
349 rqstp->rq_chandle.defer(block->b_cache_req);
350 if (block->b_deferred_req != NULL)
351 status = nlm_drop_reply;
352 }
353 dprintk("lockd: nlmsvc_defer_lock_rqst block %p flags %d status %d\n",
354 block, block->b_flags, status);
355
356 return status;
357}
358
359/*
Linus Torvalds1da177e2005-04-16 15:20:36 -0700360 * Attempt to establish a lock, and if it can't be granted, block it
361 * if required.
362 */
Al Viro52921e02006-10-19 23:28:46 -0700363__be32
Linus Torvalds1da177e2005-04-16 15:20:36 -0700364nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
365 struct nlm_lock *lock, int wait, struct nlm_cookie *cookie)
366{
Trond Myklebust09c79382006-03-20 13:44:38 -0500367 struct nlm_block *block, *newblock = NULL;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700368 int error;
Al Viro52921e02006-10-19 23:28:46 -0700369 __be32 ret;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700370
371 dprintk("lockd: nlmsvc_lock(%s/%ld, ty=%d, pi=%d, %Ld-%Ld, bl=%d)\n",
Josef Sipek225a7192006-12-08 02:37:18 -0800372 file->f_file->f_path.dentry->d_inode->i_sb->s_id,
373 file->f_file->f_path.dentry->d_inode->i_ino,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700374 lock->fl.fl_type, lock->fl.fl_pid,
375 (long long)lock->fl.fl_start,
376 (long long)lock->fl.fl_end,
377 wait);
378
379
Trond Myklebust09c79382006-03-20 13:44:38 -0500380 lock->fl.fl_flags &= ~FL_SLEEP;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700381again:
382 /* Lock file against concurrent access */
Neil Brown89e63ef2006-10-04 02:16:06 -0700383 mutex_lock(&file->f_mutex);
Trond Myklebust09c79382006-03-20 13:44:38 -0500384 /* Get existing block (in case client is busy-waiting) */
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500385 block = nlmsvc_lookup_block(file, lock);
Trond Myklebust09c79382006-03-20 13:44:38 -0500386 if (block == NULL) {
387 if (newblock != NULL)
Trond Myklebust92737232006-03-20 13:44:45 -0500388 lock = &newblock->b_call->a_args.lock;
Trond Myklebust09c79382006-03-20 13:44:38 -0500389 } else
Trond Myklebust92737232006-03-20 13:44:45 -0500390 lock = &block->b_call->a_args.lock;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700391
Marc Eshel150b3932007-01-18 16:15:35 -0500392 error = posix_lock_file(file->f_file, &lock->fl, NULL);
Trond Myklebust09c79382006-03-20 13:44:38 -0500393 lock->fl.fl_flags &= ~FL_SLEEP;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700394
Andy Adamsona85f1932006-03-20 13:44:25 -0500395 dprintk("lockd: posix_lock_file returned %d\n", error);
396
Trond Myklebust09c79382006-03-20 13:44:38 -0500397 switch(error) {
Linus Torvalds1da177e2005-04-16 15:20:36 -0700398 case 0:
Andy Adamson15dadef2006-03-20 13:44:24 -0500399 ret = nlm_granted;
400 goto out;
Trond Myklebust09c79382006-03-20 13:44:38 -0500401 case -EAGAIN:
402 break;
403 case -EDEADLK:
Andy Adamson15dadef2006-03-20 13:44:24 -0500404 ret = nlm_deadlock;
405 goto out;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700406 default: /* includes ENOLCK */
Andy Adamson15dadef2006-03-20 13:44:24 -0500407 ret = nlm_lck_denied_nolocks;
408 goto out;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700409 }
410
Trond Myklebust09c79382006-03-20 13:44:38 -0500411 ret = nlm_lck_denied;
412 if (!wait)
413 goto out;
414
415 ret = nlm_lck_blocked;
416 if (block != NULL)
417 goto out;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700418
Linus Torvalds1da177e2005-04-16 15:20:36 -0700419 /* If we don't have a block, create and initialize it. Then
420 * retry because we may have slept in kmalloc. */
Neil Brown89e63ef2006-10-04 02:16:06 -0700421 /* We have to release f_mutex as nlmsvc_create_block may try to
Linus Torvalds1da177e2005-04-16 15:20:36 -0700422 * to claim it while doing host garbage collection */
Trond Myklebust09c79382006-03-20 13:44:38 -0500423 if (newblock == NULL) {
Neil Brown89e63ef2006-10-04 02:16:06 -0700424 mutex_unlock(&file->f_mutex);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700425 dprintk("lockd: blocking on this lock (allocating).\n");
Trond Myklebust09c79382006-03-20 13:44:38 -0500426 if (!(newblock = nlmsvc_create_block(rqstp, file, lock, cookie)))
Linus Torvalds1da177e2005-04-16 15:20:36 -0700427 return nlm_lck_denied_nolocks;
428 goto again;
429 }
430
431 /* Append to list of blocked */
Trond Myklebust09c79382006-03-20 13:44:38 -0500432 nlmsvc_insert_block(newblock, NLM_NEVER);
Andy Adamson15dadef2006-03-20 13:44:24 -0500433out:
Neil Brown89e63ef2006-10-04 02:16:06 -0700434 mutex_unlock(&file->f_mutex);
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500435 nlmsvc_release_block(newblock);
436 nlmsvc_release_block(block);
Andy Adamson15dadef2006-03-20 13:44:24 -0500437 dprintk("lockd: nlmsvc_lock returned %u\n", ret);
438 return ret;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700439}
440
441/*
442 * Test for presence of a conflicting lock.
443 */
Al Viro52921e02006-10-19 23:28:46 -0700444__be32
Linus Torvalds1da177e2005-04-16 15:20:36 -0700445nlmsvc_testlock(struct nlm_file *file, struct nlm_lock *lock,
446 struct nlm_lock *conflock)
447{
Linus Torvalds1da177e2005-04-16 15:20:36 -0700448 dprintk("lockd: nlmsvc_testlock(%s/%ld, ty=%d, %Ld-%Ld)\n",
Josef Sipek225a7192006-12-08 02:37:18 -0800449 file->f_file->f_path.dentry->d_inode->i_sb->s_id,
450 file->f_file->f_path.dentry->d_inode->i_ino,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700451 lock->fl.fl_type,
452 (long long)lock->fl.fl_start,
453 (long long)lock->fl.fl_end);
454
Marc Eshel9d6a8c52007-02-21 00:55:18 -0500455 if (posix_test_lock(file->f_file, &lock->fl)) {
Linus Torvalds1da177e2005-04-16 15:20:36 -0700456 dprintk("lockd: conflicting lock(ty=%d, %Ld-%Ld)\n",
Marc Eshel9d6a8c52007-02-21 00:55:18 -0500457 lock->fl.fl_type,
458 (long long)lock->fl.fl_start,
459 (long long)lock->fl.fl_end);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700460 conflock->caller = "somehost"; /* FIXME */
Olaf Kirchdb4e4c92006-10-04 02:15:52 -0700461 conflock->len = strlen(conflock->caller);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700462 conflock->oh.len = 0; /* don't return OH info */
Marc Eshel9d6a8c52007-02-21 00:55:18 -0500463 conflock->svid = lock->fl.fl_pid;
464 conflock->fl.fl_type = lock->fl.fl_type;
465 conflock->fl.fl_start = lock->fl.fl_start;
466 conflock->fl.fl_end = lock->fl.fl_end;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700467 return nlm_lck_denied;
468 }
469
470 return nlm_granted;
471}
472
473/*
474 * Remove a lock.
475 * This implies a CANCEL call: We send a GRANT_MSG, the client replies
476 * with a GRANT_RES call which gets lost, and calls UNLOCK immediately
477 * afterwards. In this case the block will still be there, and hence
478 * must be removed.
479 */
Al Viro52921e02006-10-19 23:28:46 -0700480__be32
Linus Torvalds1da177e2005-04-16 15:20:36 -0700481nlmsvc_unlock(struct nlm_file *file, struct nlm_lock *lock)
482{
483 int error;
484
485 dprintk("lockd: nlmsvc_unlock(%s/%ld, pi=%d, %Ld-%Ld)\n",
Josef Sipek225a7192006-12-08 02:37:18 -0800486 file->f_file->f_path.dentry->d_inode->i_sb->s_id,
487 file->f_file->f_path.dentry->d_inode->i_ino,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700488 lock->fl.fl_pid,
489 (long long)lock->fl.fl_start,
490 (long long)lock->fl.fl_end);
491
492 /* First, cancel any lock that might be there */
493 nlmsvc_cancel_blocked(file, lock);
494
495 lock->fl.fl_type = F_UNLCK;
Marc Eshel150b3932007-01-18 16:15:35 -0500496 error = posix_lock_file(file->f_file, &lock->fl, NULL);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700497
498 return (error < 0)? nlm_lck_denied_nolocks : nlm_granted;
499}
500
501/*
502 * Cancel a previously blocked request.
503 *
504 * A cancel request always overrides any grant that may currently
505 * be in progress.
506 * The calling procedure must check whether the file can be closed.
507 */
Al Viro52921e02006-10-19 23:28:46 -0700508__be32
Linus Torvalds1da177e2005-04-16 15:20:36 -0700509nlmsvc_cancel_blocked(struct nlm_file *file, struct nlm_lock *lock)
510{
511 struct nlm_block *block;
J. Bruce Fields64a318e2006-01-03 09:55:46 +0100512 int status = 0;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700513
514 dprintk("lockd: nlmsvc_cancel(%s/%ld, pi=%d, %Ld-%Ld)\n",
Josef Sipek225a7192006-12-08 02:37:18 -0800515 file->f_file->f_path.dentry->d_inode->i_sb->s_id,
516 file->f_file->f_path.dentry->d_inode->i_ino,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700517 lock->fl.fl_pid,
518 (long long)lock->fl.fl_start,
519 (long long)lock->fl.fl_end);
520
Neil Brown89e63ef2006-10-04 02:16:06 -0700521 mutex_lock(&file->f_mutex);
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500522 block = nlmsvc_lookup_block(file, lock);
Neil Brown89e63ef2006-10-04 02:16:06 -0700523 mutex_unlock(&file->f_mutex);
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500524 if (block != NULL) {
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500525 status = nlmsvc_unlink_block(block);
526 nlmsvc_release_block(block);
527 }
J. Bruce Fields64a318e2006-01-03 09:55:46 +0100528 return status ? nlm_lck_denied : nlm_granted;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700529}
530
531/*
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500532 * This is a callback from the filesystem for VFS file lock requests.
533 * It will be used if fl_grant is defined and the filesystem can not
534 * respond to the request immediately.
535 * For GETLK request it will copy the reply to the nlm_block.
536 * For SETLK or SETLKW request it will get the local posix lock.
537 * In all cases it will move the block to the head of nlm_blocked q where
538 * nlmsvc_retry_blocked() can send back a reply for SETLKW or revisit the
539 * deferred rpc for GETLK and SETLK.
540 */
541static void
542nlmsvc_update_deferred_block(struct nlm_block *block, struct file_lock *conf,
543 int result)
544{
545 block->b_flags |= B_GOT_CALLBACK;
546 if (result == 0)
547 block->b_granted = 1;
548 else
549 block->b_flags |= B_TIMED_OUT;
550 if (conf) {
551 block->b_fl = kzalloc(sizeof(struct file_lock), GFP_KERNEL);
552 if (block->b_fl)
553 locks_copy_lock(block->b_fl, conf);
554 }
555}
556
557static int nlmsvc_grant_deferred(struct file_lock *fl, struct file_lock *conf,
558 int result)
559{
560 struct nlm_block *block;
561 int rc = -ENOENT;
562
563 lock_kernel();
564 list_for_each_entry(block, &nlm_blocked, b_list) {
565 if (nlm_compare_locks(&block->b_call->a_args.lock.fl, fl)) {
566 dprintk("lockd: nlmsvc_notify_blocked block %p flags %d\n",
567 block, block->b_flags);
568 if (block->b_flags & B_QUEUED) {
569 if (block->b_flags & B_TIMED_OUT) {
570 rc = -ENOLCK;
571 break;
572 }
573 nlmsvc_update_deferred_block(block, conf, result);
574 } else if (result == 0)
575 block->b_granted = 1;
576
577 nlmsvc_insert_block(block, 0);
578 svc_wake_up(block->b_daemon);
579 rc = 0;
580 break;
581 }
582 }
583 unlock_kernel();
584 if (rc == -ENOENT)
585 printk(KERN_WARNING "lockd: grant for unknown block\n");
586 return rc;
587}
588
589/*
Linus Torvalds1da177e2005-04-16 15:20:36 -0700590 * Unblock a blocked lock request. This is a callback invoked from the
591 * VFS layer when a lock on which we blocked is removed.
592 *
593 * This function doesn't grant the blocked lock instantly, but rather moves
594 * the block to the head of nlm_blocked where it can be picked up by lockd.
595 */
596static void
597nlmsvc_notify_blocked(struct file_lock *fl)
598{
Olaf Kirch68a2d762006-10-04 02:15:57 -0700599 struct nlm_block *block;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700600
601 dprintk("lockd: VFS unblock notification for block %p\n", fl);
Olaf Kirch68a2d762006-10-04 02:15:57 -0700602 list_for_each_entry(block, &nlm_blocked, b_list) {
Trond Myklebust92737232006-03-20 13:44:45 -0500603 if (nlm_compare_locks(&block->b_call->a_args.lock.fl, fl)) {
Linus Torvalds1da177e2005-04-16 15:20:36 -0700604 nlmsvc_insert_block(block, 0);
605 svc_wake_up(block->b_daemon);
606 return;
607 }
608 }
609
610 printk(KERN_WARNING "lockd: notification for unknown block!\n");
611}
612
613static int nlmsvc_same_owner(struct file_lock *fl1, struct file_lock *fl2)
614{
615 return fl1->fl_owner == fl2->fl_owner && fl1->fl_pid == fl2->fl_pid;
616}
617
618struct lock_manager_operations nlmsvc_lock_operations = {
619 .fl_compare_owner = nlmsvc_same_owner,
620 .fl_notify = nlmsvc_notify_blocked,
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500621 .fl_grant = nlmsvc_grant_deferred,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700622};
623
624/*
625 * Try to claim a lock that was previously blocked.
626 *
627 * Note that we use both the RPC_GRANTED_MSG call _and_ an async
628 * RPC thread when notifying the client. This seems like overkill...
629 * Here's why:
630 * - we don't want to use a synchronous RPC thread, otherwise
631 * we might find ourselves hanging on a dead portmapper.
632 * - Some lockd implementations (e.g. HP) don't react to
633 * RPC_GRANTED calls; they seem to insist on RPC_GRANTED_MSG calls.
634 */
635static void
636nlmsvc_grant_blocked(struct nlm_block *block)
637{
638 struct nlm_file *file = block->b_file;
Trond Myklebust92737232006-03-20 13:44:45 -0500639 struct nlm_lock *lock = &block->b_call->a_args.lock;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700640 int error;
641
642 dprintk("lockd: grant blocked lock %p\n", block);
643
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500644 kref_get(&block->b_count);
645
Linus Torvalds1da177e2005-04-16 15:20:36 -0700646 /* Unlink block request from list */
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500647 nlmsvc_unlink_block(block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700648
649 /* If b_granted is true this means we've been here before.
650 * Just retry the grant callback, possibly refreshing the RPC
651 * binding */
652 if (block->b_granted) {
653 nlm_rebind_host(block->b_host);
654 goto callback;
655 }
656
657 /* Try the lock operation again */
Trond Myklebust09c79382006-03-20 13:44:38 -0500658 lock->fl.fl_flags |= FL_SLEEP;
Marc Eshel150b3932007-01-18 16:15:35 -0500659 error = posix_lock_file(file->f_file, &lock->fl, NULL);
Trond Myklebust09c79382006-03-20 13:44:38 -0500660 lock->fl.fl_flags &= ~FL_SLEEP;
661
Andy Adamson5de0e502006-03-20 13:44:25 -0500662 switch (error) {
663 case 0:
664 break;
665 case -EAGAIN:
Linus Torvalds1da177e2005-04-16 15:20:36 -0700666 dprintk("lockd: lock still blocked\n");
667 nlmsvc_insert_block(block, NLM_NEVER);
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500668 nlmsvc_release_block(block);
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500669 return;
Andy Adamson5de0e502006-03-20 13:44:25 -0500670 default:
Linus Torvalds1da177e2005-04-16 15:20:36 -0700671 printk(KERN_WARNING "lockd: unexpected error %d in %s!\n",
672 -error, __FUNCTION__);
673 nlmsvc_insert_block(block, 10 * HZ);
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500674 nlmsvc_release_block(block);
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500675 return;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700676 }
677
678callback:
679 /* Lock was granted by VFS. */
680 dprintk("lockd: GRANTing blocked lock.\n");
681 block->b_granted = 1;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700682
683 /* Schedule next grant callback in 30 seconds */
684 nlmsvc_insert_block(block, 30 * HZ);
685
686 /* Call the client */
Trond Myklebusta995e9e2007-02-02 15:37:43 -0800687 nlm_async_call(block->b_call, NLMPROC_GRANTED_MSG, &nlmsvc_grant_ops);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700688}
689
690/*
691 * This is the callback from the RPC layer when the NLM_GRANTED_MSG
692 * RPC call has succeeded or timed out.
693 * Like all RPC callbacks, it is invoked by the rpciod process, so it
694 * better not sleep. Therefore, we put the blocked lock on the nlm_blocked
695 * chain once more in order to have it removed by lockd itself (which can
696 * then sleep on the file semaphore without disrupting e.g. the nfs client).
697 */
Trond Myklebust963d8fe2006-01-03 09:55:04 +0100698static void nlmsvc_grant_callback(struct rpc_task *task, void *data)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700699{
Trond Myklebust963d8fe2006-01-03 09:55:04 +0100700 struct nlm_rqst *call = data;
Trond Myklebust92737232006-03-20 13:44:45 -0500701 struct nlm_block *block = call->a_block;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700702 unsigned long timeout;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700703
704 dprintk("lockd: GRANT_MSG RPC callback\n");
Linus Torvalds1da177e2005-04-16 15:20:36 -0700705
706 /* Technically, we should down the file semaphore here. Since we
707 * move the block towards the head of the queue only, no harm
708 * can be done, though. */
709 if (task->tk_status < 0) {
710 /* RPC error: Re-insert for retransmission */
711 timeout = 10 * HZ;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700712 } else {
713 /* Call was successful, now wait for client callback */
714 timeout = 60 * HZ;
715 }
716 nlmsvc_insert_block(block, timeout);
717 svc_wake_up(block->b_daemon);
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500718}
719
Adrian Bunkec535ce2006-04-18 13:21:50 -0400720static void nlmsvc_grant_release(void *data)
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500721{
Trond Myklebust6041b792006-03-20 13:44:45 -0500722 struct nlm_rqst *call = data;
723
724 nlmsvc_release_block(call->a_block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700725}
726
Trond Myklebust963d8fe2006-01-03 09:55:04 +0100727static const struct rpc_call_ops nlmsvc_grant_ops = {
728 .rpc_call_done = nlmsvc_grant_callback,
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500729 .rpc_release = nlmsvc_grant_release,
Trond Myklebust963d8fe2006-01-03 09:55:04 +0100730};
731
Linus Torvalds1da177e2005-04-16 15:20:36 -0700732/*
733 * We received a GRANT_RES callback. Try to find the corresponding
734 * block.
735 */
736void
Al Viroe8c5c042006-12-13 00:35:03 -0800737nlmsvc_grant_reply(struct nlm_cookie *cookie, __be32 status)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700738{
739 struct nlm_block *block;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700740
Olaf Kirch39be4502006-10-04 02:16:03 -0700741 dprintk("grant_reply: looking for cookie %x, s=%d \n",
742 *(unsigned int *)(cookie->data), status);
743 if (!(block = nlmsvc_find_block(cookie)))
Linus Torvalds1da177e2005-04-16 15:20:36 -0700744 return;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700745
J. Bruce Fieldsf2321422006-01-03 09:55:42 +0100746 if (block) {
Al Viroe8c5c042006-12-13 00:35:03 -0800747 if (status == nlm_lck_denied_grace_period) {
Linus Torvalds1da177e2005-04-16 15:20:36 -0700748 /* Try again in a couple of seconds */
749 nlmsvc_insert_block(block, 10 * HZ);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700750 } else {
751 /* Lock is now held by client, or has been rejected.
752 * In both cases, the block should be removed. */
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500753 nlmsvc_unlink_block(block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700754 }
755 }
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500756 nlmsvc_release_block(block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700757}
758
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500759/* Helper function to handle retry of a deferred block.
760 * If it is a blocking lock, call grant_blocked.
761 * For a non-blocking lock or test lock, revisit the request.
762 */
763static void
764retry_deferred_block(struct nlm_block *block)
765{
766 if (!(block->b_flags & B_GOT_CALLBACK))
767 block->b_flags |= B_TIMED_OUT;
768 nlmsvc_insert_block(block, NLM_TIMEOUT);
769 dprintk("revisit block %p flags %d\n", block, block->b_flags);
770 if (block->b_deferred_req) {
771 block->b_deferred_req->revisit(block->b_deferred_req, 0);
772 block->b_deferred_req = NULL;
773 }
774}
775
Linus Torvalds1da177e2005-04-16 15:20:36 -0700776/*
777 * Retry all blocked locks that have been notified. This is where lockd
778 * picks up locks that can be granted, or grant notifications that must
779 * be retransmitted.
780 */
781unsigned long
782nlmsvc_retry_blocked(void)
783{
Olaf Kirch68a2d762006-10-04 02:15:57 -0700784 unsigned long timeout = MAX_SCHEDULE_TIMEOUT;
785 struct nlm_block *block;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700786
Olaf Kirch68a2d762006-10-04 02:15:57 -0700787 while (!list_empty(&nlm_blocked)) {
788 block = list_entry(nlm_blocked.next, struct nlm_block, b_list);
789
Linus Torvalds1da177e2005-04-16 15:20:36 -0700790 if (block->b_when == NLM_NEVER)
791 break;
Olaf Kirch68a2d762006-10-04 02:15:57 -0700792 if (time_after(block->b_when,jiffies)) {
793 timeout = block->b_when - jiffies;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700794 break;
Olaf Kirch68a2d762006-10-04 02:15:57 -0700795 }
796
J. Bruce Fieldsf3d43c72006-08-03 15:07:47 -0400797 dprintk("nlmsvc_retry_blocked(%p, when=%ld)\n",
798 block, block->b_when);
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500799 if (block->b_flags & B_QUEUED) {
800 dprintk("nlmsvc_retry_blocked delete block (%p, granted=%d, flags=%d)\n",
801 block, block->b_granted, block->b_flags);
802 retry_deferred_block(block);
803 } else
804 nlmsvc_grant_blocked(block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700805 }
806
Olaf Kirch68a2d762006-10-04 02:15:57 -0700807 return timeout;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700808}