blob: 0d7398e3804f663e9ca2eba8bca8e90ba28a150f [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,
Marc Eshel5ea0d752006-11-28 16:27:06 -0500176 struct nlm_lock *lock, struct nlm_cookie *cookie)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700177{
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;
Marc Eshel5ea0d752006-11-28 16:27:06 -0500213 block->b_fl = NULL;
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500214 file->f_count++;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700215
216 /* Add to file's list of blocks */
Olaf Kirch68a2d762006-10-04 02:15:57 -0700217 list_add(&block->b_flist, &file->f_blocks);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700218
219 /* Set up RPC arguments for callback */
Trond Myklebust92737232006-03-20 13:44:45 -0500220 block->b_call = call;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700221 call->a_flags = RPC_TASK_ASYNC;
Trond Myklebust92737232006-03-20 13:44:45 -0500222 call->a_block = block;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700223
224 return block;
225
226failed_free:
227 kfree(block);
228failed:
Trond Myklebust92737232006-03-20 13:44:45 -0500229 nlm_release_call(call);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700230 return NULL;
231}
232
233/*
234 * Delete a block. If the lock was cancelled or the grant callback
235 * failed, unlock is set to 1.
236 * It is the caller's responsibility to check whether the file
237 * can be closed hereafter.
238 */
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500239static int nlmsvc_unlink_block(struct nlm_block *block)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700240{
Trond Myklebust09c79382006-03-20 13:44:38 -0500241 int status;
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500242 dprintk("lockd: unlinking block %p...\n", block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700243
244 /* Remove block from list */
Trond Myklebust92737232006-03-20 13:44:45 -0500245 status = posix_unblock_lock(block->b_file->f_file, &block->b_call->a_args.lock.fl);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700246 nlmsvc_remove_block(block);
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500247 return status;
248}
Linus Torvalds1da177e2005-04-16 15:20:36 -0700249
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500250static void nlmsvc_free_block(struct kref *kref)
251{
252 struct nlm_block *block = container_of(kref, struct nlm_block, b_count);
253 struct nlm_file *file = block->b_file;
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500254
255 dprintk("lockd: freeing block %p...\n", block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700256
257 /* Remove block from file's list of blocks */
Neil Brown89e63ef2006-10-04 02:16:06 -0700258 mutex_lock(&file->f_mutex);
Olaf Kirch68a2d762006-10-04 02:15:57 -0700259 list_del_init(&block->b_flist);
Neil Brown89e63ef2006-10-04 02:16:06 -0700260 mutex_unlock(&file->f_mutex);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700261
Trond Myklebust92737232006-03-20 13:44:45 -0500262 nlmsvc_freegrantargs(block->b_call);
263 nlm_release_call(block->b_call);
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500264 nlm_release_file(block->b_file);
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500265 kfree(block->b_fl);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700266 kfree(block);
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500267}
268
269static void nlmsvc_release_block(struct nlm_block *block)
270{
271 if (block != NULL)
272 kref_put(&block->b_count, nlmsvc_free_block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700273}
274
Olaf Kirchf2af7932006-10-04 02:15:59 -0700275/*
276 * Loop over all blocks and delete blocks held by
277 * a matching host.
278 */
279void nlmsvc_traverse_blocks(struct nlm_host *host,
280 struct nlm_file *file,
281 nlm_host_match_fn_t match)
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500282{
Olaf Kirch68a2d762006-10-04 02:15:57 -0700283 struct nlm_block *block, *next;
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500284
285restart:
Neil Brown89e63ef2006-10-04 02:16:06 -0700286 mutex_lock(&file->f_mutex);
Olaf Kirch68a2d762006-10-04 02:15:57 -0700287 list_for_each_entry_safe(block, next, &file->f_blocks, b_flist) {
Olaf Kirchf2af7932006-10-04 02:15:59 -0700288 if (!match(block->b_host, host))
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500289 continue;
Olaf Kirch68a2d762006-10-04 02:15:57 -0700290 /* Do not destroy blocks that are not on
291 * the global retry list - why? */
292 if (list_empty(&block->b_list))
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500293 continue;
294 kref_get(&block->b_count);
Neil Brown89e63ef2006-10-04 02:16:06 -0700295 mutex_unlock(&file->f_mutex);
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500296 nlmsvc_unlink_block(block);
297 nlmsvc_release_block(block);
298 goto restart;
299 }
Neil Brown89e63ef2006-10-04 02:16:06 -0700300 mutex_unlock(&file->f_mutex);
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500301}
302
Linus Torvalds1da177e2005-04-16 15:20:36 -0700303/*
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500304 * Initialize arguments for GRANTED call. The nlm_rqst structure
305 * has been cleared already.
306 */
307static int nlmsvc_setgrantargs(struct nlm_rqst *call, struct nlm_lock *lock)
308{
309 locks_copy_lock(&call->a_args.lock.fl, &lock->fl);
310 memcpy(&call->a_args.lock.fh, &lock->fh, sizeof(call->a_args.lock.fh));
Serge E. Hallyne9ff3992006-10-02 02:18:11 -0700311 call->a_args.lock.caller = utsname()->nodename;
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500312 call->a_args.lock.oh.len = lock->oh.len;
313
314 /* set default data area */
315 call->a_args.lock.oh.data = call->a_owner;
316 call->a_args.lock.svid = lock->fl.fl_pid;
317
318 if (lock->oh.len > NLMCLNT_OHSIZE) {
319 void *data = kmalloc(lock->oh.len, GFP_KERNEL);
Trond Myklebust92737232006-03-20 13:44:45 -0500320 if (!data)
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500321 return 0;
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500322 call->a_args.lock.oh.data = (u8 *) data;
323 }
324
325 memcpy(call->a_args.lock.oh.data, lock->oh.data, lock->oh.len);
326 return 1;
327}
328
329static void nlmsvc_freegrantargs(struct nlm_rqst *call)
330{
Trond Myklebust92737232006-03-20 13:44:45 -0500331 if (call->a_args.lock.oh.data != call->a_owner)
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500332 kfree(call->a_args.lock.oh.data);
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500333}
334
335/*
Marc Eshel2b36f412006-11-28 16:26:47 -0500336 * Deferred lock request handling for non-blocking lock
337 */
338static u32
339nlmsvc_defer_lock_rqst(struct svc_rqst *rqstp, struct nlm_block *block)
340{
341 u32 status = nlm_lck_denied_nolocks;
342
343 block->b_flags |= B_QUEUED;
344
345 nlmsvc_insert_block(block, NLM_TIMEOUT);
346
347 block->b_cache_req = &rqstp->rq_chandle;
348 if (rqstp->rq_chandle.defer) {
349 block->b_deferred_req =
350 rqstp->rq_chandle.defer(block->b_cache_req);
351 if (block->b_deferred_req != NULL)
352 status = nlm_drop_reply;
353 }
354 dprintk("lockd: nlmsvc_defer_lock_rqst block %p flags %d status %d\n",
355 block, block->b_flags, status);
356
357 return status;
358}
359
360/*
Linus Torvalds1da177e2005-04-16 15:20:36 -0700361 * Attempt to establish a lock, and if it can't be granted, block it
362 * if required.
363 */
Al Viro52921e02006-10-19 23:28:46 -0700364__be32
Linus Torvalds1da177e2005-04-16 15:20:36 -0700365nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
366 struct nlm_lock *lock, int wait, struct nlm_cookie *cookie)
367{
Marc Eshelf8120482006-12-05 23:48:10 -0500368 struct nlm_block *block = NULL;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700369 int error;
Al Viro52921e02006-10-19 23:28:46 -0700370 __be32 ret;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700371
372 dprintk("lockd: nlmsvc_lock(%s/%ld, ty=%d, pi=%d, %Ld-%Ld, bl=%d)\n",
Josef Sipek225a7192006-12-08 02:37:18 -0800373 file->f_file->f_path.dentry->d_inode->i_sb->s_id,
374 file->f_file->f_path.dentry->d_inode->i_ino,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700375 lock->fl.fl_type, lock->fl.fl_pid,
376 (long long)lock->fl.fl_start,
377 (long long)lock->fl.fl_end,
378 wait);
379
380
Linus Torvalds1da177e2005-04-16 15:20:36 -0700381 /* Lock file against concurrent access */
Neil Brown89e63ef2006-10-04 02:16:06 -0700382 mutex_lock(&file->f_mutex);
Marc Eshelf8120482006-12-05 23:48:10 -0500383 /* Get existing block (in case client is busy-waiting)
384 * or create new block
385 */
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500386 block = nlmsvc_lookup_block(file, lock);
Trond Myklebust09c79382006-03-20 13:44:38 -0500387 if (block == NULL) {
Marc Eshelf8120482006-12-05 23:48:10 -0500388 block = nlmsvc_create_block(rqstp, file, lock, cookie);
389 ret = nlm_lck_denied_nolocks;
390 if (block == NULL)
391 goto out;
Trond Myklebust92737232006-03-20 13:44:45 -0500392 lock = &block->b_call->a_args.lock;
Marc Eshelf8120482006-12-05 23:48:10 -0500393 } else
394 lock->fl.fl_flags &= ~FL_SLEEP;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700395
Marc Eshel150b3932007-01-18 16:15:35 -0500396 error = posix_lock_file(file->f_file, &lock->fl, NULL);
Trond Myklebust09c79382006-03-20 13:44:38 -0500397 lock->fl.fl_flags &= ~FL_SLEEP;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700398
Andy Adamsona85f1932006-03-20 13:44:25 -0500399 dprintk("lockd: posix_lock_file returned %d\n", error);
400
Trond Myklebust09c79382006-03-20 13:44:38 -0500401 switch(error) {
Linus Torvalds1da177e2005-04-16 15:20:36 -0700402 case 0:
Andy Adamson15dadef2006-03-20 13:44:24 -0500403 ret = nlm_granted;
404 goto out;
Trond Myklebust09c79382006-03-20 13:44:38 -0500405 case -EAGAIN:
406 break;
407 case -EDEADLK:
Andy Adamson15dadef2006-03-20 13:44:24 -0500408 ret = nlm_deadlock;
409 goto out;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700410 default: /* includes ENOLCK */
Andy Adamson15dadef2006-03-20 13:44:24 -0500411 ret = nlm_lck_denied_nolocks;
412 goto out;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700413 }
414
Trond Myklebust09c79382006-03-20 13:44:38 -0500415 ret = nlm_lck_denied;
416 if (!wait)
417 goto out;
418
419 ret = nlm_lck_blocked;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700420
421 /* Append to list of blocked */
Marc Eshelf8120482006-12-05 23:48:10 -0500422 nlmsvc_insert_block(block, NLM_NEVER);
Andy Adamson15dadef2006-03-20 13:44:24 -0500423out:
Neil Brown89e63ef2006-10-04 02:16:06 -0700424 mutex_unlock(&file->f_mutex);
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500425 nlmsvc_release_block(block);
Andy Adamson15dadef2006-03-20 13:44:24 -0500426 dprintk("lockd: nlmsvc_lock returned %u\n", ret);
427 return ret;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700428}
429
430/*
431 * Test for presence of a conflicting lock.
432 */
Al Viro52921e02006-10-19 23:28:46 -0700433__be32
Marc Eshel85f3f1b32006-11-28 16:27:06 -0500434nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
435 struct nlm_lock *lock, struct nlm_lock *conflock,
436 struct nlm_cookie *cookie)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700437{
Marc Eshel5ea0d752006-11-28 16:27:06 -0500438 struct nlm_block *block = NULL;
439 int error;
440 __be32 ret;
441
Linus Torvalds1da177e2005-04-16 15:20:36 -0700442 dprintk("lockd: nlmsvc_testlock(%s/%ld, ty=%d, %Ld-%Ld)\n",
Josef Sipek225a7192006-12-08 02:37:18 -0800443 file->f_file->f_path.dentry->d_inode->i_sb->s_id,
444 file->f_file->f_path.dentry->d_inode->i_ino,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700445 lock->fl.fl_type,
446 (long long)lock->fl.fl_start,
447 (long long)lock->fl.fl_end);
448
Marc Eshel5ea0d752006-11-28 16:27:06 -0500449 /* Get existing block (in case client is busy-waiting) */
450 block = nlmsvc_lookup_block(file, lock);
451
452 if (block == NULL) {
453 struct file_lock *conf = kzalloc(sizeof(*conf), GFP_KERNEL);
454
455 if (conf == NULL)
456 return nlm_granted;
457 block = nlmsvc_create_block(rqstp, file, lock, cookie);
458 if (block == NULL) {
459 kfree(conf);
460 return nlm_granted;
461 }
462 block->b_fl = conf;
463 }
464 if (block->b_flags & B_QUEUED) {
465 dprintk("lockd: nlmsvc_testlock deferred block %p flags %d fl %p\n",
466 block, block->b_flags, block->b_fl);
467 if (block->b_flags & B_TIMED_OUT) {
468 nlmsvc_unlink_block(block);
469 return nlm_lck_denied;
470 }
471 if (block->b_flags & B_GOT_CALLBACK) {
472 if (block->b_fl != NULL
473 && block->b_fl->fl_type != F_UNLCK) {
474 lock->fl = *block->b_fl;
475 goto conf_lock;
476 }
477 else {
478 nlmsvc_unlink_block(block);
479 return nlm_granted;
480 }
481 }
482 return nlm_drop_reply;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700483 }
484
Marc Eshel5ea0d752006-11-28 16:27:06 -0500485 error = vfs_test_lock(file->f_file, &lock->fl);
486 if (error == -EINPROGRESS)
487 return nlmsvc_defer_lock_rqst(rqstp, block);
488 if (error) {
489 ret = nlm_lck_denied_nolocks;
490 goto out;
491 }
492 if (lock->fl.fl_type == F_UNLCK) {
493 ret = nlm_granted;
494 goto out;
495 }
496
497conf_lock:
498 dprintk("lockd: conflicting lock(ty=%d, %Ld-%Ld)\n",
499 lock->fl.fl_type, (long long)lock->fl.fl_start,
500 (long long)lock->fl.fl_end);
501 conflock->caller = "somehost"; /* FIXME */
502 conflock->len = strlen(conflock->caller);
503 conflock->oh.len = 0; /* don't return OH info */
504 conflock->svid = lock->fl.fl_pid;
505 conflock->fl.fl_type = lock->fl.fl_type;
506 conflock->fl.fl_start = lock->fl.fl_start;
507 conflock->fl.fl_end = lock->fl.fl_end;
508 ret = nlm_lck_denied;
509out:
510 if (block)
511 nlmsvc_release_block(block);
512 return ret;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700513}
514
515/*
516 * Remove a lock.
517 * This implies a CANCEL call: We send a GRANT_MSG, the client replies
518 * with a GRANT_RES call which gets lost, and calls UNLOCK immediately
519 * afterwards. In this case the block will still be there, and hence
520 * must be removed.
521 */
Al Viro52921e02006-10-19 23:28:46 -0700522__be32
Linus Torvalds1da177e2005-04-16 15:20:36 -0700523nlmsvc_unlock(struct nlm_file *file, struct nlm_lock *lock)
524{
525 int error;
526
527 dprintk("lockd: nlmsvc_unlock(%s/%ld, pi=%d, %Ld-%Ld)\n",
Josef Sipek225a7192006-12-08 02:37:18 -0800528 file->f_file->f_path.dentry->d_inode->i_sb->s_id,
529 file->f_file->f_path.dentry->d_inode->i_ino,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700530 lock->fl.fl_pid,
531 (long long)lock->fl.fl_start,
532 (long long)lock->fl.fl_end);
533
534 /* First, cancel any lock that might be there */
535 nlmsvc_cancel_blocked(file, lock);
536
537 lock->fl.fl_type = F_UNLCK;
Marc Eshel150b3932007-01-18 16:15:35 -0500538 error = posix_lock_file(file->f_file, &lock->fl, NULL);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700539
540 return (error < 0)? nlm_lck_denied_nolocks : nlm_granted;
541}
542
543/*
544 * Cancel a previously blocked request.
545 *
546 * A cancel request always overrides any grant that may currently
547 * be in progress.
548 * The calling procedure must check whether the file can be closed.
549 */
Al Viro52921e02006-10-19 23:28:46 -0700550__be32
Linus Torvalds1da177e2005-04-16 15:20:36 -0700551nlmsvc_cancel_blocked(struct nlm_file *file, struct nlm_lock *lock)
552{
553 struct nlm_block *block;
J. Bruce Fields64a318e2006-01-03 09:55:46 +0100554 int status = 0;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700555
556 dprintk("lockd: nlmsvc_cancel(%s/%ld, pi=%d, %Ld-%Ld)\n",
Josef Sipek225a7192006-12-08 02:37:18 -0800557 file->f_file->f_path.dentry->d_inode->i_sb->s_id,
558 file->f_file->f_path.dentry->d_inode->i_ino,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700559 lock->fl.fl_pid,
560 (long long)lock->fl.fl_start,
561 (long long)lock->fl.fl_end);
562
Neil Brown89e63ef2006-10-04 02:16:06 -0700563 mutex_lock(&file->f_mutex);
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500564 block = nlmsvc_lookup_block(file, lock);
Neil Brown89e63ef2006-10-04 02:16:06 -0700565 mutex_unlock(&file->f_mutex);
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500566 if (block != NULL) {
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500567 status = nlmsvc_unlink_block(block);
568 nlmsvc_release_block(block);
569 }
J. Bruce Fields64a318e2006-01-03 09:55:46 +0100570 return status ? nlm_lck_denied : nlm_granted;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700571}
572
573/*
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500574 * This is a callback from the filesystem for VFS file lock requests.
575 * It will be used if fl_grant is defined and the filesystem can not
576 * respond to the request immediately.
577 * For GETLK request it will copy the reply to the nlm_block.
578 * For SETLK or SETLKW request it will get the local posix lock.
579 * In all cases it will move the block to the head of nlm_blocked q where
580 * nlmsvc_retry_blocked() can send back a reply for SETLKW or revisit the
581 * deferred rpc for GETLK and SETLK.
582 */
583static void
584nlmsvc_update_deferred_block(struct nlm_block *block, struct file_lock *conf,
585 int result)
586{
587 block->b_flags |= B_GOT_CALLBACK;
588 if (result == 0)
589 block->b_granted = 1;
590 else
591 block->b_flags |= B_TIMED_OUT;
592 if (conf) {
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500593 if (block->b_fl)
594 locks_copy_lock(block->b_fl, conf);
595 }
596}
597
598static int nlmsvc_grant_deferred(struct file_lock *fl, struct file_lock *conf,
599 int result)
600{
601 struct nlm_block *block;
602 int rc = -ENOENT;
603
604 lock_kernel();
605 list_for_each_entry(block, &nlm_blocked, b_list) {
606 if (nlm_compare_locks(&block->b_call->a_args.lock.fl, fl)) {
607 dprintk("lockd: nlmsvc_notify_blocked block %p flags %d\n",
608 block, block->b_flags);
609 if (block->b_flags & B_QUEUED) {
610 if (block->b_flags & B_TIMED_OUT) {
611 rc = -ENOLCK;
612 break;
613 }
614 nlmsvc_update_deferred_block(block, conf, result);
615 } else if (result == 0)
616 block->b_granted = 1;
617
618 nlmsvc_insert_block(block, 0);
619 svc_wake_up(block->b_daemon);
620 rc = 0;
621 break;
622 }
623 }
624 unlock_kernel();
625 if (rc == -ENOENT)
626 printk(KERN_WARNING "lockd: grant for unknown block\n");
627 return rc;
628}
629
630/*
Linus Torvalds1da177e2005-04-16 15:20:36 -0700631 * Unblock a blocked lock request. This is a callback invoked from the
632 * VFS layer when a lock on which we blocked is removed.
633 *
634 * This function doesn't grant the blocked lock instantly, but rather moves
635 * the block to the head of nlm_blocked where it can be picked up by lockd.
636 */
637static void
638nlmsvc_notify_blocked(struct file_lock *fl)
639{
Olaf Kirch68a2d762006-10-04 02:15:57 -0700640 struct nlm_block *block;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700641
642 dprintk("lockd: VFS unblock notification for block %p\n", fl);
Olaf Kirch68a2d762006-10-04 02:15:57 -0700643 list_for_each_entry(block, &nlm_blocked, b_list) {
Trond Myklebust92737232006-03-20 13:44:45 -0500644 if (nlm_compare_locks(&block->b_call->a_args.lock.fl, fl)) {
Linus Torvalds1da177e2005-04-16 15:20:36 -0700645 nlmsvc_insert_block(block, 0);
646 svc_wake_up(block->b_daemon);
647 return;
648 }
649 }
650
651 printk(KERN_WARNING "lockd: notification for unknown block!\n");
652}
653
654static int nlmsvc_same_owner(struct file_lock *fl1, struct file_lock *fl2)
655{
656 return fl1->fl_owner == fl2->fl_owner && fl1->fl_pid == fl2->fl_pid;
657}
658
659struct lock_manager_operations nlmsvc_lock_operations = {
660 .fl_compare_owner = nlmsvc_same_owner,
661 .fl_notify = nlmsvc_notify_blocked,
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500662 .fl_grant = nlmsvc_grant_deferred,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700663};
664
665/*
666 * Try to claim a lock that was previously blocked.
667 *
668 * Note that we use both the RPC_GRANTED_MSG call _and_ an async
669 * RPC thread when notifying the client. This seems like overkill...
670 * Here's why:
671 * - we don't want to use a synchronous RPC thread, otherwise
672 * we might find ourselves hanging on a dead portmapper.
673 * - Some lockd implementations (e.g. HP) don't react to
674 * RPC_GRANTED calls; they seem to insist on RPC_GRANTED_MSG calls.
675 */
676static void
677nlmsvc_grant_blocked(struct nlm_block *block)
678{
679 struct nlm_file *file = block->b_file;
Trond Myklebust92737232006-03-20 13:44:45 -0500680 struct nlm_lock *lock = &block->b_call->a_args.lock;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700681 int error;
682
683 dprintk("lockd: grant blocked lock %p\n", block);
684
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500685 kref_get(&block->b_count);
686
Linus Torvalds1da177e2005-04-16 15:20:36 -0700687 /* Unlink block request from list */
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500688 nlmsvc_unlink_block(block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700689
690 /* If b_granted is true this means we've been here before.
691 * Just retry the grant callback, possibly refreshing the RPC
692 * binding */
693 if (block->b_granted) {
694 nlm_rebind_host(block->b_host);
695 goto callback;
696 }
697
698 /* Try the lock operation again */
Trond Myklebust09c79382006-03-20 13:44:38 -0500699 lock->fl.fl_flags |= FL_SLEEP;
Marc Eshel150b3932007-01-18 16:15:35 -0500700 error = posix_lock_file(file->f_file, &lock->fl, NULL);
Trond Myklebust09c79382006-03-20 13:44:38 -0500701 lock->fl.fl_flags &= ~FL_SLEEP;
702
Andy Adamson5de0e502006-03-20 13:44:25 -0500703 switch (error) {
704 case 0:
705 break;
706 case -EAGAIN:
Linus Torvalds1da177e2005-04-16 15:20:36 -0700707 dprintk("lockd: lock still blocked\n");
708 nlmsvc_insert_block(block, NLM_NEVER);
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500709 nlmsvc_release_block(block);
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500710 return;
Andy Adamson5de0e502006-03-20 13:44:25 -0500711 default:
Linus Torvalds1da177e2005-04-16 15:20:36 -0700712 printk(KERN_WARNING "lockd: unexpected error %d in %s!\n",
713 -error, __FUNCTION__);
714 nlmsvc_insert_block(block, 10 * HZ);
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500715 nlmsvc_release_block(block);
Trond Myklebustd9f6eb72006-03-20 13:44:47 -0500716 return;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700717 }
718
719callback:
720 /* Lock was granted by VFS. */
721 dprintk("lockd: GRANTing blocked lock.\n");
722 block->b_granted = 1;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700723
724 /* Schedule next grant callback in 30 seconds */
725 nlmsvc_insert_block(block, 30 * HZ);
726
727 /* Call the client */
Trond Myklebusta995e9e2007-02-02 15:37:43 -0800728 nlm_async_call(block->b_call, NLMPROC_GRANTED_MSG, &nlmsvc_grant_ops);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700729}
730
731/*
732 * This is the callback from the RPC layer when the NLM_GRANTED_MSG
733 * RPC call has succeeded or timed out.
734 * Like all RPC callbacks, it is invoked by the rpciod process, so it
735 * better not sleep. Therefore, we put the blocked lock on the nlm_blocked
736 * chain once more in order to have it removed by lockd itself (which can
737 * then sleep on the file semaphore without disrupting e.g. the nfs client).
738 */
Trond Myklebust963d8fe2006-01-03 09:55:04 +0100739static void nlmsvc_grant_callback(struct rpc_task *task, void *data)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700740{
Trond Myklebust963d8fe2006-01-03 09:55:04 +0100741 struct nlm_rqst *call = data;
Trond Myklebust92737232006-03-20 13:44:45 -0500742 struct nlm_block *block = call->a_block;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700743 unsigned long timeout;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700744
745 dprintk("lockd: GRANT_MSG RPC callback\n");
Linus Torvalds1da177e2005-04-16 15:20:36 -0700746
747 /* Technically, we should down the file semaphore here. Since we
748 * move the block towards the head of the queue only, no harm
749 * can be done, though. */
750 if (task->tk_status < 0) {
751 /* RPC error: Re-insert for retransmission */
752 timeout = 10 * HZ;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700753 } else {
754 /* Call was successful, now wait for client callback */
755 timeout = 60 * HZ;
756 }
757 nlmsvc_insert_block(block, timeout);
758 svc_wake_up(block->b_daemon);
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500759}
760
Adrian Bunkec535ce2006-04-18 13:21:50 -0400761static void nlmsvc_grant_release(void *data)
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500762{
Trond Myklebust6041b792006-03-20 13:44:45 -0500763 struct nlm_rqst *call = data;
764
765 nlmsvc_release_block(call->a_block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700766}
767
Trond Myklebust963d8fe2006-01-03 09:55:04 +0100768static const struct rpc_call_ops nlmsvc_grant_ops = {
769 .rpc_call_done = nlmsvc_grant_callback,
Trond Myklebust5e1abf82006-03-20 13:44:39 -0500770 .rpc_release = nlmsvc_grant_release,
Trond Myklebust963d8fe2006-01-03 09:55:04 +0100771};
772
Linus Torvalds1da177e2005-04-16 15:20:36 -0700773/*
774 * We received a GRANT_RES callback. Try to find the corresponding
775 * block.
776 */
777void
Al Viroe8c5c042006-12-13 00:35:03 -0800778nlmsvc_grant_reply(struct nlm_cookie *cookie, __be32 status)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700779{
780 struct nlm_block *block;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700781
Olaf Kirch39be4502006-10-04 02:16:03 -0700782 dprintk("grant_reply: looking for cookie %x, s=%d \n",
783 *(unsigned int *)(cookie->data), status);
784 if (!(block = nlmsvc_find_block(cookie)))
Linus Torvalds1da177e2005-04-16 15:20:36 -0700785 return;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700786
J. Bruce Fieldsf2321422006-01-03 09:55:42 +0100787 if (block) {
Al Viroe8c5c042006-12-13 00:35:03 -0800788 if (status == nlm_lck_denied_grace_period) {
Linus Torvalds1da177e2005-04-16 15:20:36 -0700789 /* Try again in a couple of seconds */
790 nlmsvc_insert_block(block, 10 * HZ);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700791 } else {
792 /* Lock is now held by client, or has been rejected.
793 * In both cases, the block should be removed. */
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500794 nlmsvc_unlink_block(block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700795 }
796 }
Trond Myklebust6849c0c2006-03-20 13:44:39 -0500797 nlmsvc_release_block(block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700798}
799
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500800/* Helper function to handle retry of a deferred block.
801 * If it is a blocking lock, call grant_blocked.
802 * For a non-blocking lock or test lock, revisit the request.
803 */
804static void
805retry_deferred_block(struct nlm_block *block)
806{
807 if (!(block->b_flags & B_GOT_CALLBACK))
808 block->b_flags |= B_TIMED_OUT;
809 nlmsvc_insert_block(block, NLM_TIMEOUT);
810 dprintk("revisit block %p flags %d\n", block, block->b_flags);
811 if (block->b_deferred_req) {
812 block->b_deferred_req->revisit(block->b_deferred_req, 0);
813 block->b_deferred_req = NULL;
814 }
815}
816
Linus Torvalds1da177e2005-04-16 15:20:36 -0700817/*
818 * Retry all blocked locks that have been notified. This is where lockd
819 * picks up locks that can be granted, or grant notifications that must
820 * be retransmitted.
821 */
822unsigned long
823nlmsvc_retry_blocked(void)
824{
Olaf Kirch68a2d762006-10-04 02:15:57 -0700825 unsigned long timeout = MAX_SCHEDULE_TIMEOUT;
826 struct nlm_block *block;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700827
Olaf Kirch68a2d762006-10-04 02:15:57 -0700828 while (!list_empty(&nlm_blocked)) {
829 block = list_entry(nlm_blocked.next, struct nlm_block, b_list);
830
Linus Torvalds1da177e2005-04-16 15:20:36 -0700831 if (block->b_when == NLM_NEVER)
832 break;
Olaf Kirch68a2d762006-10-04 02:15:57 -0700833 if (time_after(block->b_when,jiffies)) {
834 timeout = block->b_when - jiffies;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700835 break;
Olaf Kirch68a2d762006-10-04 02:15:57 -0700836 }
837
J. Bruce Fieldsf3d43c72006-08-03 15:07:47 -0400838 dprintk("nlmsvc_retry_blocked(%p, when=%ld)\n",
839 block, block->b_when);
Marc Eshel0e4ac9d2006-11-28 16:26:51 -0500840 if (block->b_flags & B_QUEUED) {
841 dprintk("nlmsvc_retry_blocked delete block (%p, granted=%d, flags=%d)\n",
842 block, block->b_granted, block->b_flags);
843 retry_deferred_block(block);
844 } else
845 nlmsvc_grant_blocked(block);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700846 }
847
Olaf Kirch68a2d762006-10-04 02:15:57 -0700848 return timeout;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700849}